From b0355dbbf13c0052931dd14c38c789efed64d3de Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Thu, 5 Jan 2023 21:28:12 +0000 Subject: [PATCH 01/57] Fix XFRM-I support for nested ESP tunnels This change adds support for nested IPsec tunnels by ensuring that XFRM-I verifies existing policies before decapsulating a subsequent policies. Addtionally, this clears the secpath entries after policies are verified, ensuring that previous tunnels with no-longer-valid do not pollute subsequent policy checks. This is necessary especially for nested tunnels, as the IP addresses, protocol and ports may all change, thus not matching the previous policies. In order to ensure that packets match the relevant inbound templates, the xfrm_policy_check should be done before handing off to the inner XFRM protocol to decrypt and decapsulate. Notably, raw ESP/AH packets did not perform policy checks inherently, whereas all other encapsulated packets (UDP, TCP encapsulated) do policy checks after calling xfrm_input handling in the respective encapsulation layer. Test: Verified with additional Android Kernel Unit tests Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_interface_core.c | 54 +++++++++++++++++++++++++++++++--- net/xfrm/xfrm_policy.c | 3 ++ 2 files changed, 53 insertions(+), 4 deletions(-) diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 1f99dc4690271..35279c220bd78 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e9eb82c5457d0..ed0976f8e42b7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3742,6 +3742,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } + if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; } From eb6c59b735aa6cca77cdbb59cc69d69a0d63d986 Mon Sep 17 00:00:00 2001 From: Anastasia Belova Date: Tue, 10 Jan 2023 12:14:50 +0300 Subject: [PATCH 02/57] xfrm: compat: change expression for switch in xfrm_xlate64 Compare XFRM_MSG_NEWSPDINFO (value from netlink configuration messages enum) with nlh_src->nlmsg_type instead of nlh_src->nlmsg_type - XFRM_MSG_BASE. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 4e9505064f58 ("net/xfrm/compat: Copy xfrm_spdattr_type_t atributes") Signed-off-by: Anastasia Belova Acked-by: Dmitry Safonov <0x7f454c46@gmail.com> Tested-by: Dmitry Safonov <0x7f454c46@gmail.com> Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06e..12405aa5bce84 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -302,7 +302,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) nla_for_each_attr(nla, attrs, len, remaining) { int err; - switch (type) { + switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; From b6ee896385380aa621102e8ea402ba12db1cabff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 13:02:49 +0000 Subject: [PATCH 03/57] xfrm/compat: prevent potential spectre v1 gadget in xfrm_xlate32_attr() int type = nla_type(nla); if (type > XFRMA_MAX) { return -EOPNOTSUPP; } @type is then used as an array index and can be used as a Spectre v1 gadget. if (nla_len(nla) < compat_policy[type].len) { array_index_nospec() can be used to prevent leaking content of kernel memory to malicious users. Fixes: 5106f4a8acff ("xfrm/compat: Add 32=>64-bit messages translator") Signed-off-by: Eric Dumazet Cc: Dmitry Safonov Cc: Steffen Klassert Reviewed-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 12405aa5bce84..8cbf45a8bcdc2 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -5,6 +5,7 @@ * Based on code and translator idea by: Florian Westphal */ #include +#include #include #include @@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } + type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; From 195e4aac74ce67385f95432301da6db3c2cfc72a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 26 Jan 2023 11:21:29 +0000 Subject: [PATCH 04/57] xfrm: consistently use time64_t in xfrm_timer_handler() For some reason, blamed commit did the right thing in xfrm_policy_timer() but did not in xfrm_timer_handler() Fixes: 386c5680e2e8 ("xfrm: use time64_t for in-kernel timestamps") Signed-off-by: Eric Dumazet Cc: Arnd Bergmann Cc: Steffen Klassert Acked-by: Arnd Bergmann Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 89c731f4f0c72..5f03d1fbb98ed 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -577,7 +577,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { - long tmo = x->lft.hard_add_expires_seconds + + time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { @@ -594,7 +594,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) next = tmo; } if (x->lft.hard_use_expires_seconds) { - long tmo = x->lft.hard_use_expires_seconds + + time64_t tmo = x->lft.hard_use_expires_seconds + (x->curlft.use_time ? : now) - now; if (tmo <= 0) goto expired; @@ -604,7 +604,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { - long tmo = x->lft.soft_add_expires_seconds + + time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; @@ -616,7 +616,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } } if (x->lft.soft_use_expires_seconds) { - long tmo = x->lft.soft_use_expires_seconds + + time64_t tmo = x->lft.soft_use_expires_seconds + (x->curlft.use_time ? : now) - now; if (tmo <= 0) warn = 1; From 0a9e5794b21e2d1303759ff8fe5f9215db7757ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 26 Jan 2023 11:21:30 +0000 Subject: [PATCH 05/57] xfrm: annotate data-race around use_time KCSAN reported multiple cpus can update use_time at the same time. Adds READ_ONCE()/WRITE_ONCE() annotations. Note that 32bit arches are not fully protected, but they will probably no longer be supported/used in 2106. BUG: KCSAN: data-race in __xfrm_policy_check / __xfrm_policy_check write to 0xffff88813e7ec108 of 8 bytes by interrupt on cpu 0: __xfrm_policy_check+0x6ae/0x17f0 net/xfrm/xfrm_policy.c:3664 __xfrm_policy_check2 include/net/xfrm.h:1174 [inline] xfrm_policy_check include/net/xfrm.h:1179 [inline] xfrm6_policy_check+0x2e9/0x320 include/net/xfrm.h:1189 udpv6_queue_rcv_one_skb+0x48/0xa30 net/ipv6/udp.c:703 udpv6_queue_rcv_skb+0x2d6/0x310 net/ipv6/udp.c:792 udp6_unicast_rcv_skb+0x16b/0x190 net/ipv6/udp.c:935 __udp6_lib_rcv+0x84b/0x9b0 net/ipv6/udp.c:1020 udpv6_rcv+0x4b/0x50 net/ipv6/udp.c:1133 ip6_protocol_deliver_rcu+0x99e/0x1020 net/ipv6/ip6_input.c:439 ip6_input_finish net/ipv6/ip6_input.c:484 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] ip6_input+0xca/0x180 net/ipv6/ip6_input.c:493 dst_input include/net/dst.h:454 [inline] ip6_rcv_finish+0x1e9/0x2d0 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:302 [inline] ipv6_rcv+0x85/0x140 net/ipv6/ip6_input.c:309 __netif_receive_skb_one_core net/core/dev.c:5482 [inline] __netif_receive_skb+0x8b/0x1b0 net/core/dev.c:5596 process_backlog+0x23f/0x3b0 net/core/dev.c:5924 __napi_poll+0x65/0x390 net/core/dev.c:6485 napi_poll net/core/dev.c:6552 [inline] net_rx_action+0x37e/0x730 net/core/dev.c:6663 __do_softirq+0xf2/0x2c7 kernel/softirq.c:571 do_softirq+0xb1/0xf0 kernel/softirq.c:472 __local_bh_enable_ip+0x6f/0x80 kernel/softirq.c:396 __raw_read_unlock_bh include/linux/rwlock_api_smp.h:257 [inline] _raw_read_unlock_bh+0x17/0x20 kernel/locking/spinlock.c:284 wg_socket_send_skb_to_peer+0x107/0x120 drivers/net/wireguard/socket.c:184 wg_packet_create_data_done drivers/net/wireguard/send.c:251 [inline] wg_packet_tx_worker+0x142/0x360 drivers/net/wireguard/send.c:276 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 write to 0xffff88813e7ec108 of 8 bytes by interrupt on cpu 1: __xfrm_policy_check+0x6ae/0x17f0 net/xfrm/xfrm_policy.c:3664 __xfrm_policy_check2 include/net/xfrm.h:1174 [inline] xfrm_policy_check include/net/xfrm.h:1179 [inline] xfrm6_policy_check+0x2e9/0x320 include/net/xfrm.h:1189 udpv6_queue_rcv_one_skb+0x48/0xa30 net/ipv6/udp.c:703 udpv6_queue_rcv_skb+0x2d6/0x310 net/ipv6/udp.c:792 udp6_unicast_rcv_skb+0x16b/0x190 net/ipv6/udp.c:935 __udp6_lib_rcv+0x84b/0x9b0 net/ipv6/udp.c:1020 udpv6_rcv+0x4b/0x50 net/ipv6/udp.c:1133 ip6_protocol_deliver_rcu+0x99e/0x1020 net/ipv6/ip6_input.c:439 ip6_input_finish net/ipv6/ip6_input.c:484 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] ip6_input+0xca/0x180 net/ipv6/ip6_input.c:493 dst_input include/net/dst.h:454 [inline] ip6_rcv_finish+0x1e9/0x2d0 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:302 [inline] ipv6_rcv+0x85/0x140 net/ipv6/ip6_input.c:309 __netif_receive_skb_one_core net/core/dev.c:5482 [inline] __netif_receive_skb+0x8b/0x1b0 net/core/dev.c:5596 process_backlog+0x23f/0x3b0 net/core/dev.c:5924 __napi_poll+0x65/0x390 net/core/dev.c:6485 napi_poll net/core/dev.c:6552 [inline] net_rx_action+0x37e/0x730 net/core/dev.c:6663 __do_softirq+0xf2/0x2c7 kernel/softirq.c:571 do_softirq+0xb1/0xf0 kernel/softirq.c:472 __local_bh_enable_ip+0x6f/0x80 kernel/softirq.c:396 __raw_read_unlock_bh include/linux/rwlock_api_smp.h:257 [inline] _raw_read_unlock_bh+0x17/0x20 kernel/locking/spinlock.c:284 wg_socket_send_skb_to_peer+0x107/0x120 drivers/net/wireguard/socket.c:184 wg_packet_create_data_done drivers/net/wireguard/send.c:251 [inline] wg_packet_tx_worker+0x142/0x360 drivers/net/wireguard/send.c:276 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0000000063c62d6f -> 0x0000000063c62d70 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 4185 Comm: kworker/1:2 Tainted: G W 6.2.0-rc4-syzkaller-00009-gd532dd102151-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: wg-crypt-wg0 wg_packet_tx_worker Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Steffen Klassert Cc: Arnd Bergmann Acked-by: Arnd Bergmann Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 11 +++++++---- net/xfrm/xfrm_state.c | 10 +++++----- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ed0976f8e42b7..5c61ec04b839b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -336,7 +336,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -354,7 +354,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; @@ -3661,7 +3661,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 1; } - pol->curlft.use_time = ktime_get_real_seconds(); + /* This lockless write can happen from different cpus. */ + WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; @@ -3676,7 +3677,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, xfrm_pol_put(pols[0]); return 0; } - pols[1]->curlft.use_time = ktime_get_real_seconds(); + /* This write can happen from different cpus. */ + WRITE_ONCE(pols[1]->curlft.use_time, + ktime_get_real_seconds()); npols++; } } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5f03d1fbb98ed..00afe831c71c4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -595,7 +595,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } if (x->lft.hard_use_expires_seconds) { time64_t tmo = x->lft.hard_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -617,7 +617,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } if (x->lft.soft_use_expires_seconds) { time64_t tmo = x->lft.soft_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) @@ -1906,7 +1906,7 @@ int xfrm_state_update(struct xfrm_state *x) hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); - if (x1->curlft.use_time) + if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { @@ -1940,8 +1940,8 @@ int xfrm_state_check_expire(struct xfrm_state *x) { xfrm_dev_state_update_curlft(x); - if (!x->curlft.use_time) - x->curlft.use_time = ktime_get_real_seconds(); + if (!READ_ONCE(x->curlft.use_time)) + WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { From 6028da3f125fec34425dbd5fec18e85d372b2af6 Mon Sep 17 00:00:00 2001 From: Christian Hopps Date: Thu, 26 Jan 2023 11:33:50 -0500 Subject: [PATCH 06/57] xfrm: fix bug with DSCP copy to v6 from v4 tunnel When copying the DSCP bits for decap-dscp into IPv6 don't assume the outer encap is always IPv6. Instead, as with the inner IPv4 case, copy the DSCP bits from the correctly saved "tos" value in the control block. Fixes: 227620e29509 ("[IPSEC]: Separate inner/outer mode processing on input") Signed-off-by: Christian Hopps Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c06e54a105405..436d29640ac2c 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -279,8 +279,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); From ce93fdb5f2ca5c9e2a9668411cc39091507f8dc9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Tue, 31 Jan 2023 11:02:42 +0100 Subject: [PATCH 07/57] net: phylink: move phy_device_free() to correctly release phy device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After calling fwnode_phy_find_device(), the phy device refcount is incremented. Then, when the phy device is attached to a netdev with phy_attach_direct(), the refcount is also incremented but only decremented in the caller if phy_attach_direct() fails. Move phy_device_free() before the "if" to always release it correctly. Indeed, either phy_attach_direct() failed and we don't want to keep a reference to the phydev or it succeeded and a reference has been taken internally. Fixes: 25396f680dd6 ("net: phylink: introduce phylink_fwnode_phy_connect()") Signed-off-by: Clément Léger Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 09cc65c0da930..4d2519cdb8012 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1812,10 +1812,9 @@ int phylink_fwnode_phy_connect(struct phylink *pl, ret = phy_attach_direct(pl->netdev, phy_dev, flags, pl->link_interface); - if (ret) { - phy_device_free(phy_dev); + phy_device_free(phy_dev); + if (ret) return ret; - } ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); if (ret) From cbe83191d40d8925b7a99969d037d2a0caf69294 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 2 Feb 2023 17:32:55 +0800 Subject: [PATCH 08/57] bonding: fix error checking in bond_debug_reregister() Since commit ff9fb72bc077 ("debugfs: return error values, not NULL") changed return value of debugfs_rename() in error cases from %NULL to %ERR_PTR(-ERROR), we should also check error values instead of NULL. Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Signed-off-by: Qi Zheng Acked-by: Jay Vosburgh Link: https://lore.kernel.org/r/20230202093256.32458-1-zhengqi.arch@bytedance.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 4f9b4a18c74cd..5940945266489 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -76,7 +76,7 @@ void bond_debug_reregister(struct bonding *bond) d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); - if (d) { + if (!IS_ERR(d)) { bond->debug_dir = d; } else { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); From c9011b028e956c3b6baa6f131d9eec43e4e52020 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Thu, 2 Feb 2023 17:56:19 +0530 Subject: [PATCH 09/57] net: macb: Perform zynqmp dynamic configuration only for SGMII interface In zynqmp platforms where firmware supports dynamic SGMII configuration but has other non-SGMII ethernet devices, it fails them with no packets received at the RX interface. To fix this behaviour perform SGMII dynamic configuration only for the SGMII phy interface. Fixes: 32cee7818111 ("net: macb: Add zynqmp SGMII dynamic configuration support") Signed-off-by: Radhey Shyam Pandey Reviewed-by: Jiri Pirko Reported-by: Michal Simek Tested-by: Michal Simek Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/1675340779-27499-1-git-send-email-radhey.shyam.pandey@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 31 ++++++++++++------------ 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 72e42820713df..6cda31520c425 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4627,25 +4627,26 @@ static int init_reset_optional(struct platform_device *pdev) if (ret) return dev_err_probe(&pdev->dev, ret, "failed to init SGMII PHY\n"); - } - ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); - if (!ret) { - u32 pm_info[2]; + ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); + if (!ret) { + u32 pm_info[2]; + + ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", + pm_info, ARRAY_SIZE(pm_info)); + if (ret) { + dev_err(&pdev->dev, "Failed to read power management information\n"); + goto err_out_phy_exit; + } + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); + if (ret) + goto err_out_phy_exit; - ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", - pm_info, ARRAY_SIZE(pm_info)); - if (ret) { - dev_err(&pdev->dev, "Failed to read power management information\n"); - goto err_out_phy_exit; + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); + if (ret) + goto err_out_phy_exit; } - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); - if (ret) - goto err_out_phy_exit; - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); - if (ret) - goto err_out_phy_exit; } /* Fully reset controller at hardware level if mapped in device tree */ From 69ff53e4a4c9498eeed7d1441f68a1481dc69251 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 2 Feb 2023 21:45:36 +0100 Subject: [PATCH 10/57] net: phy: meson-gxl: use MMD access dummy stubs for GXL, internal PHY Jerome provided the information that also the GXL internal PHY doesn't support MMD register access and EEE. MMD reads return 0xffff, what results in e.g. completely wrong ethtool --show-eee output. Therefore use the MMD dummy stubs. Fixes: d853d145ea3e ("net: phy: add an option to disable EEE advertisement") Suggested-by: Jerome Brunet Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/84432fe4-0be4-bc82-4e5c-557206b40f56@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/meson-gxl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index 5e41658b1e2fa..a6015cd03bff8 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -261,6 +261,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { PHY_ID_MATCH_EXACT(0x01803301), .name = "Meson G12A Internal PHY", From e8797a058466b60fc5a3291b92430c93ba90eaff Mon Sep 17 00:00:00 2001 From: Neel Patel Date: Thu, 2 Feb 2023 13:55:35 -0800 Subject: [PATCH 11/57] ionic: clean interrupt before enabling queue to avoid credit race Clear the interrupt credits before enabling the queue rather than after to be sure that the enabled queue starts at 0 and that we don't wipe away possible credits after enabling the queue. Fixes: 0f3154e6bcb3 ("ionic: Add Tx and Rx handling") Signed-off-by: Neel Patel Signed-off-by: Shannon Nelson Reviewed-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 4dd16c487f2b4..5e2dfa79f0e4b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -269,6 +269,7 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) .oper = IONIC_Q_ENABLE, }, }; + int ret; idev = &lif->ionic->idev; dev = lif->ionic->dev; @@ -276,16 +277,24 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", ctx.cmd.q_control.index, ctx.cmd.q_control.type); + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + + ret = ionic_adminq_post_wait(lif, &ctx); + if (ret) + return ret; + + if (qcq->napi.poll) + napi_enable(&qcq->napi); + if (qcq->flags & IONIC_QCQ_F_INTR) { irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); - napi_enable(&qcq->napi); - ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } - return ionic_adminq_post_wait(lif, &ctx); + return 0; } static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int fw_err) From 1fffb0254178de1d4d9e67f467a3460d10680b10 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Thu, 2 Feb 2023 13:55:36 -0800 Subject: [PATCH 12/57] ionic: clear up notifyq alloc commentary Make sure the q+cq alloc for NotifyQ is clearly documented and don't bother with unnecessary local variables. Signed-off-by: Shannon Nelson Reviewed-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5e2dfa79f0e4b..e51d8be7911c3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -573,13 +573,15 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, } if (flags & IONIC_QCQ_F_NOTIFYQ) { - int q_size, cq_size; + int q_size; - /* q & cq need to be contiguous in case of notifyq */ + /* q & cq need to be contiguous in NotifyQ, so alloc it all in q + * and don't alloc qc. We leave new->qc_size and new->qc_base + * as 0 to be sure we don't try to free it later. + */ q_size = ALIGN(num_descs * desc_size, PAGE_SIZE); - cq_size = ALIGN(num_descs * cq_desc_size, PAGE_SIZE); - - new->q_size = PAGE_SIZE + q_size + cq_size; + new->q_size = PAGE_SIZE + q_size + + ALIGN(num_descs * cq_desc_size, PAGE_SIZE); new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa, GFP_KERNEL); if (!new->q_base) { From b69585bfceceeffda940906cabfdaee4b47bde92 Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Thu, 2 Feb 2023 13:55:37 -0800 Subject: [PATCH 13/57] ionic: missed doorbell workaround In one version of the HW there is a remote possibility that it will miss the doorbell ring. This adds a bit of protection to be sure we don't stall a queue from a missed doorbell. Fixes: 0f3154e6bcb3 ("ionic: Add Tx and Rx handling") Signed-off-by: Allen Hubbe Signed-off-by: Shannon Nelson Signed-off-by: Jakub Kicinski --- .../net/ethernet/pensando/ionic/ionic_dev.c | 9 +- .../net/ethernet/pensando/ionic/ionic_dev.h | 12 +++ .../net/ethernet/pensando/ionic/ionic_lif.c | 41 ++++++++- .../net/ethernet/pensando/ionic/ionic_lif.h | 2 + .../net/ethernet/pensando/ionic/ionic_main.c | 29 +++++++ .../net/ethernet/pensando/ionic/ionic_txrx.c | 87 ++++++++++++++++++- 6 files changed, 176 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 626b9113e7c41..d911f4fd9af61 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -708,9 +708,16 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, q->lif->index, q->name, q->hw_type, q->hw_index, q->head_idx, ring_doorbell); - if (ring_doorbell) + if (ring_doorbell) { ionic_dbell_ring(lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_jiffies = jiffies; + + if (q_to_qcq(q)->napi_qcq) + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + } } static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 2a1d7b9c07e7f..bce3ca38669bd 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -25,6 +25,12 @@ #define IONIC_DEV_INFO_REG_COUNT 32 #define IONIC_DEV_CMD_REG_COUNT 32 +#define IONIC_NAPI_DEADLINE (HZ / 200) /* 5ms */ +#define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */ +#define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */ + struct ionic_dev_bar { void __iomem *vaddr; phys_addr_t bus_addr; @@ -216,6 +222,8 @@ struct ionic_queue { struct ionic_lif *lif; struct ionic_desc_info *info; u64 dbval; + unsigned long dbell_deadline; + unsigned long dbell_jiffies; u16 head_idx; u16 tail_idx; unsigned int index; @@ -361,4 +369,8 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, int ionic_heartbeat_check(struct ionic *ionic); bool ionic_is_fw_running(struct ionic_dev *idev); +bool ionic_adminq_poke_doorbell(struct ionic_queue *q); +bool ionic_txq_poke_doorbell(struct ionic_queue *q); +bool ionic_rxq_poke_doorbell(struct ionic_queue *q); + #endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index e51d8be7911c3..63a78a9ac241a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -16,6 +16,7 @@ #include "ionic.h" #include "ionic_bus.h" +#include "ionic_dev.h" #include "ionic_lif.h" #include "ionic_txrx.h" #include "ionic_ethtool.h" @@ -200,6 +201,13 @@ void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep) } } +static void ionic_napi_deadline(struct timer_list *timer) +{ + struct ionic_qcq *qcq = container_of(timer, struct ionic_qcq, napi_deadline); + + napi_schedule(&qcq->napi); +} + static irqreturn_t ionic_isr(int irq, void *data) { struct napi_struct *napi = data; @@ -325,6 +333,7 @@ static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int f synchronize_irq(qcq->intr.vector); irq_set_affinity_hint(qcq->intr.vector, NULL); napi_disable(&qcq->napi); + del_timer_sync(&qcq->napi_deadline); } /* If there was a previous fw communcation error, don't bother with @@ -460,6 +469,7 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; + n_qcq->napi_qcq = src_qcq->napi_qcq; } static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq) @@ -784,8 +794,14 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + q->dbell_deadline = IONIC_TX_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { netif_napi_add(lif->netdev, &qcq->napi, ionic_tx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + } qcq->flags |= IONIC_QCQ_F_INITED; @@ -839,11 +855,17 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi); else netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + qcq->flags |= IONIC_QCQ_F_INITED; return 0; @@ -1161,6 +1183,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) struct ionic_dev *idev = &lif->ionic->idev; unsigned long irqflags; unsigned int flags = 0; + bool resched = false; int rx_work = 0; int tx_work = 0; int n_work = 0; @@ -1198,6 +1221,16 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) ionic_intr_credits(idev->intr_ctrl, intr->index, credits, flags); } + if (!a_work && ionic_adminq_poke_doorbell(&lif->adminqcq->q)) + resched = true; + if (lif->hwstamp_rxq && !rx_work && ionic_rxq_poke_doorbell(&lif->hwstamp_rxq->q)) + resched = true; + if (lif->hwstamp_txq && !tx_work && ionic_txq_poke_doorbell(&lif->hwstamp_txq->q)) + resched = true; + if (resched) + mod_timer(&lif->adminqcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -3256,8 +3289,14 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type); dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_ADMIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + napi_enable(&qcq->napi); if (qcq->flags & IONIC_QCQ_F_INTR) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index a53984bf35448..734519895614f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -74,8 +74,10 @@ struct ionic_qcq { struct ionic_queue q; struct ionic_cq cq; struct ionic_intr_info intr; + struct timer_list napi_deadline; struct napi_struct napi; unsigned int flags; + struct ionic_qcq *napi_qcq; struct dentry *dentry; }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index a13530ec4dd8f..08c42b039d92d 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -289,6 +289,35 @@ static void ionic_adminq_cb(struct ionic_queue *q, complete_all(&ctx->work); } +bool ionic_adminq_poke_doorbell(struct ionic_queue *q) +{ + struct ionic_lif *lif = q->lif; + unsigned long now, then, dif; + unsigned long irqflags; + + spin_lock_irqsave(&lif->adminq_lock, irqflags); + + if (q->tail_idx == q->head_idx) { + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + + return true; +} + int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { struct ionic_desc_info *desc_info; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 0c3977416cd1c..f761780f01624 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -22,6 +22,67 @@ static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, ionic_q_post(q, ring_dbell, cb_func, cb_arg); } +bool ionic_txq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + struct netdev_queue *netdev_txq; + struct net_device *netdev; + + netdev = q->lif->netdev; + netdev_txq = netdev_get_tx_queue(netdev, q->index); + + HARD_TX_LOCK(netdev, netdev_txq, smp_processor_id()); + + if (q->tail_idx == q->head_idx) { + HARD_TX_UNLOCK(netdev, netdev_txq); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + HARD_TX_UNLOCK(netdev, netdev_txq); + + return true; +} + +bool ionic_rxq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + + /* no lock, called from rx napi or txrx napi, nothing else can fill */ + + if (q->tail_idx == q->head_idx) + return false; + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + + dif = 2 * q->dbell_deadline; + if (dif > IONIC_RX_MAX_DOORBELL_DEADLINE) + dif = IONIC_RX_MAX_DOORBELL_DEADLINE; + + q->dbell_deadline = dif; + } + + return true; +} + static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) { return netdev_get_tx_queue(q->lif->netdev, q->index); @@ -424,6 +485,12 @@ void ionic_rx_fill(struct ionic_queue *q) ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); } void ionic_rx_empty(struct ionic_queue *q) @@ -511,6 +578,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_txq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -544,23 +614,29 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_rxq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } int ionic_txrx_napi(struct napi_struct *napi, int budget) { - struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_qcq *rxqcq = napi_to_qcq(napi); struct ionic_cq *rxcq = napi_to_cq(napi); unsigned int qi = rxcq->bound_q->index; + struct ionic_qcq *txqcq; struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; + bool resched = false; u32 rx_work_done = 0; u32 tx_work_done = 0; u32 flags = 0; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; + txqcq = lif->txqcqs[qi]; txcq = &lif->txqcqs[qi]->cq; tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, @@ -572,7 +648,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { - ionic_dim_update(qcq, 0); + ionic_dim_update(rxqcq, 0); flags |= IONIC_INTR_CRED_UNMASK; rxcq->bound_intr->rearm_count++; } @@ -583,6 +659,13 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) tx_work_done + rx_work_done, flags); } + if (!rx_work_done && ionic_rxq_poke_doorbell(&rxqcq->q)) + resched = true; + if (!tx_work_done && ionic_txq_poke_doorbell(&txqcq->q)) + resched = true; + if (resched) + mod_timer(&rxqcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return rx_work_done; } From c1d2ecdf5e38e3489ce8328238b558b3b2866fe1 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 2 Feb 2023 17:25:51 +0200 Subject: [PATCH 14/57] neigh: make sure used and confirmed times are valid Entries can linger in cache without timer for days, thanks to the gc_thresh1 limit. As result, without traffic, the confirmed time can be outdated and to appear to be in the future. Later, on traffic, NUD_STALE entries can switch to NUD_DELAY and start the timer which can see the invalid confirmed time and wrongly switch to NUD_REACHABLE state instead of NUD_PROBE. As result, timer is set many days in the future. This is more visible on 32-bit platforms, with higher HZ value. Why this is a problem? While we expect unused entries to expire, such entries stay in REACHABLE state for too long, locked in cache. They are not expired normally, only when cache is full. Problem and the wrong state change reported by Zhang Changzhong: 172.16.1.18 dev bond0 lladdr 0a:0e:0f:01:12:01 ref 1 used 350521/15994171/350520 probes 4 REACHABLE 350520 seconds have elapsed since this entry was last updated, but it is still in the REACHABLE state (base_reachable_time_ms is 30000), preventing lladdr from being updated through probe. Fix it by ensuring timer is started with valid used/confirmed times. Considering the valid time range is LONG_MAX jiffies, we try not to go too much in the past while we are in DELAY/PROBE state. There are also places that need used/updated times to be validated while timer is not running. Reported-by: Zhang Changzhong Signed-off-by: Julian Anastasov Tested-by: Zhang Changzhong Signed-off-by: David S. Miller --- net/core/neighbour.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f00a79fc301b0..4edd2176e2385 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); @@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl) static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; } - if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock); From 03702d4d29be4e2510ec80b248dbbde4e57030d9 Mon Sep 17 00:00:00 2001 From: "Herton R. Krzesinski" Date: Fri, 3 Feb 2023 13:04:48 -0300 Subject: [PATCH 15/57] uapi: add missing ip/ipv6 header dependencies for linux/stddef.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 58e0be1ef6118 ("net: use struct_group to copy ip/ipv6 header addresses"), ip and ipv6 headers started to use the __struct_group definition, which is defined at include/uapi/linux/stddef.h. However, linux/stddef.h isn't explicitly included in include/uapi/linux/{ip,ipv6}.h, which breaks build of xskxceiver bpf selftest if you install the uapi headers in the system: $ make V=1 xskxceiver -C tools/testing/selftests/bpf ... make: Entering directory '(...)/tools/testing/selftests/bpf' gcc -g -O0 -rdynamic -Wall -Werror (...) In file included from xskxceiver.c:79: /usr/include/linux/ip.h:103:9: error: expected specifier-qualifier-list before ‘__struct_group’ 103 | __struct_group(/* no tag */, addrs, /* no attrs */, | ^~~~~~~~~~~~~~ ... Include the missing dependency in ip.h and do the same for the ipv6.h header. Fixes: 58e0be1ef611 ("net: use struct_group to copy ip/ipv6 header addresses") Signed-off-by: Herton R. Krzesinski Reviewed-by: Carlos O'Donell Tested-by: Carlos O'Donell Signed-off-by: David S. Miller --- include/uapi/linux/ip.h | 1 + include/uapi/linux/ipv6.h | 1 + 2 files changed, 2 insertions(+) diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 874a92349bf5b..283dec7e36451 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -18,6 +18,7 @@ #ifndef _UAPI_LINUX_IP_H #define _UAPI_LINUX_IP_H #include +#include #include #define IPTOS_TOS_MASK 0x1E diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 81f4243bebb1c..53326dfc59ecb 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -4,6 +4,7 @@ #include #include +#include #include #include From d7d94b2612f5dc25d61dc7bf58aafe7b31f40191 Mon Sep 17 00:00:00 2001 From: Casper Andersson Date: Fri, 3 Feb 2023 09:55:57 +0100 Subject: [PATCH 16/57] net: microchip: sparx5: fix PTP init/deinit not checking all ports Check all ports instead of just port_count ports. PTP init was only checking ports 0 to port_count. If the hardware ports are not mapped starting from 0 then they would be missed, e.g. if only ports 20-30 were mapped it would attempt to init ports 0-10, resulting in NULL pointers when attempting to timestamp. Now it will init all mapped ports. Fixes: 70dfe25cd866 ("net: sparx5: Update extraction/injection for timestamping") Signed-off-by: Casper Andersson Reviewed-by: Horatiu Vultur Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 0ed1ea7727c54..69e76634f9aa8 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -633,7 +633,7 @@ int sparx5_ptp_init(struct sparx5 *sparx5) /* Enable master counters */ spx5_wr(PTP_PTP_DOM_CFG_PTP_ENA_SET(0x7), sparx5, PTP_PTP_DOM_CFG); - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; @@ -649,7 +649,7 @@ void sparx5_ptp_deinit(struct sparx5 *sparx5) struct sparx5_port *port; int i; - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; From 811d581194f7412eda97acc03d17fc77824b561f Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 3 Feb 2023 14:32:09 -0500 Subject: [PATCH 17/57] net: USB: Fix wrong-direction WARNING in plusb.c The syzbot fuzzer detected a bug in the plusb network driver: A zero-length control-OUT transfer was treated as a read instead of a write. In modern kernels this error provokes a WARNING: usb 1-1: BOGUS control dir, pipe 80000280 doesn't match bRequestType c0 WARNING: CPU: 0 PID: 4645 at drivers/usb/core/urb.c:411 usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Modules linked in: CPU: 1 PID: 4645 Comm: dhcpcd Not tainted 6.2.0-rc6-syzkaller-00050-g9f266ccaa2f5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 RIP: 0010:usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 ... Call Trace: usb_start_wait_urb+0x101/0x4b0 drivers/usb/core/message.c:58 usb_internal_control_msg drivers/usb/core/message.c:102 [inline] usb_control_msg+0x320/0x4a0 drivers/usb/core/message.c:153 __usbnet_read_cmd+0xb9/0x390 drivers/net/usb/usbnet.c:2010 usbnet_read_cmd+0x96/0xf0 drivers/net/usb/usbnet.c:2068 pl_vendor_req drivers/net/usb/plusb.c:60 [inline] pl_set_QuickLink_features drivers/net/usb/plusb.c:75 [inline] pl_reset+0x2f/0xf0 drivers/net/usb/plusb.c:85 usbnet_open+0xcc/0x5d0 drivers/net/usb/usbnet.c:889 __dev_open+0x297/0x4d0 net/core/dev.c:1417 __dev_change_flags+0x587/0x750 net/core/dev.c:8530 dev_change_flags+0x97/0x170 net/core/dev.c:8602 devinet_ioctl+0x15a2/0x1d70 net/ipv4/devinet.c:1147 inet_ioctl+0x33f/0x380 net/ipv4/af_inet.c:979 sock_do_ioctl+0xcc/0x230 net/socket.c:1169 sock_ioctl+0x1f8/0x680 net/socket.c:1286 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x197/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The fix is to call usbnet_write_cmd() instead of usbnet_read_cmd() and remove the USB_DIR_IN flag. Reported-and-tested-by: syzbot+2a0e7abd24f1eb90ce25@syzkaller.appspotmail.com Signed-off-by: Alan Stern Fixes: 090ffa9d0e90 ("[PATCH] USB: usbnet (9/9) module for pl2301/2302 cables") CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/00000000000052099f05f3b3e298@google.com/ Signed-off-by: David S. Miller --- drivers/net/usb/plusb.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 2c82fbcaab223..7a2b0094de51f 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -57,9 +57,7 @@ static inline int pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index) { - return usbnet_read_cmd(dev, req, - USB_DIR_IN | USB_TYPE_VENDOR | - USB_RECIP_DEVICE, + return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE, val, index, NULL, 0); } From 4d159f7884f78b1aacb99b4fc37d1e3cb1194e39 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Mon, 30 Jan 2023 14:06:40 -0800 Subject: [PATCH 18/57] ice: Do not use WQ_MEM_RECLAIM flag for workqueue When both ice and the irdma driver are loaded, a warning in check_flush_dependency is being triggered. This is due to ice driver workqueue being allocated with the WQ_MEM_RECLAIM flag and the irdma one is not. According to kernel documentation, this flag should be set if the workqueue will be involved in the kernel's memory reclamation flow. Since it is not, there is no need for the ice driver's WQ to have this flag set so remove it. Example trace: [ +0.000004] workqueue: WQ_MEM_RECLAIM ice:ice_service_task [ice] is flushing !WQ_MEM_RECLAIM infiniband:0x0 [ +0.000139] WARNING: CPU: 0 PID: 728 at kernel/workqueue.c:2632 check_flush_dependency+0x178/0x1a0 [ +0.000011] Modules linked in: bonding tls xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_cha in_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink bridge stp llc rfkill vfat fat intel_rapl_msr intel _rapl_common isst_if_common skx_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct1 0dif_pclmul crc32_pclmul ghash_clmulni_intel rapl intel_cstate rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_ core_mod ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_cm iw_cm iTCO_wdt iTCO_vendor_support ipmi_ssif irdma mei_me ib_uverbs ib_core intel_uncore joydev pcspkr i2c_i801 acpi_ipmi mei lpc_ich i2c_smbus intel_pch_thermal ioatdma ipmi_si acpi_power_meter acpi_pad xfs libcrc32c sd_mod t10_pi crc64_rocksoft crc64 sg ahci ixgbe libahci ice i40e igb crc32c_intel mdio i2c_algo_bit liba ta dca wmi dm_mirror dm_region_hash dm_log dm_mod ipmi_devintf ipmi_msghandler fuse [ +0.000161] [last unloaded: bonding] [ +0.000006] CPU: 0 PID: 728 Comm: kworker/0:2 Tainted: G S 6.2.0-rc2_next-queue-13jan-00458-gc20aabd57164 #1 [ +0.000006] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0010.010620200716 01/06/2020 [ +0.000003] Workqueue: ice ice_service_task [ice] [ +0.000127] RIP: 0010:check_flush_dependency+0x178/0x1a0 [ +0.000005] Code: 89 8e 02 01 e8 49 3d 40 00 49 8b 55 18 48 8d 8d d0 00 00 00 48 8d b3 d0 00 00 00 4d 89 e0 48 c7 c7 e0 3b 08 9f e8 bb d3 07 01 <0f> 0b e9 be fe ff ff 80 3d 24 89 8e 02 00 0f 85 6b ff ff ff e9 06 [ +0.000004] RSP: 0018:ffff88810a39f990 EFLAGS: 00010282 [ +0.000005] RAX: 0000000000000000 RBX: ffff888141bc2400 RCX: 0000000000000000 [ +0.000004] RDX: 0000000000000001 RSI: dffffc0000000000 RDI: ffffffffa1213a80 [ +0.000003] RBP: ffff888194bf3400 R08: ffffed117b306112 R09: ffffed117b306112 [ +0.000003] R10: ffff888bd983088b R11: ffffed117b306111 R12: 0000000000000000 [ +0.000003] R13: ffff888111f84d00 R14: ffff88810a3943ac R15: ffff888194bf3400 [ +0.000004] FS: 0000000000000000(0000) GS:ffff888bd9800000(0000) knlGS:0000000000000000 [ +0.000003] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ +0.000003] CR2: 000056035b208b60 CR3: 000000017795e005 CR4: 00000000007706f0 [ +0.000003] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ +0.000003] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ +0.000002] PKRU: 55555554 [ +0.000003] Call Trace: [ +0.000002] [ +0.000003] __flush_workqueue+0x203/0x840 [ +0.000006] ? mutex_unlock+0x84/0xd0 [ +0.000008] ? __pfx_mutex_unlock+0x10/0x10 [ +0.000004] ? __pfx___flush_workqueue+0x10/0x10 [ +0.000006] ? mutex_lock+0xa3/0xf0 [ +0.000005] ib_cache_cleanup_one+0x39/0x190 [ib_core] [ +0.000174] __ib_unregister_device+0x84/0xf0 [ib_core] [ +0.000094] ib_unregister_device+0x25/0x30 [ib_core] [ +0.000093] irdma_ib_unregister_device+0x97/0xc0 [irdma] [ +0.000064] ? __pfx_irdma_ib_unregister_device+0x10/0x10 [irdma] [ +0.000059] ? up_write+0x5c/0x90 [ +0.000005] irdma_remove+0x36/0x90 [irdma] [ +0.000062] auxiliary_bus_remove+0x32/0x50 [ +0.000007] device_release_driver_internal+0xfa/0x1c0 [ +0.000005] bus_remove_device+0x18a/0x260 [ +0.000007] device_del+0x2e5/0x650 [ +0.000005] ? __pfx_device_del+0x10/0x10 [ +0.000003] ? mutex_unlock+0x84/0xd0 [ +0.000004] ? __pfx_mutex_unlock+0x10/0x10 [ +0.000004] ? _raw_spin_unlock+0x18/0x40 [ +0.000005] ice_unplug_aux_dev+0x52/0x70 [ice] [ +0.000160] ice_service_task+0x1309/0x14f0 [ice] [ +0.000134] ? __pfx___schedule+0x10/0x10 [ +0.000006] process_one_work+0x3b1/0x6c0 [ +0.000008] worker_thread+0x69/0x670 [ +0.000005] ? __kthread_parkme+0xec/0x110 [ +0.000007] ? __pfx_worker_thread+0x10/0x10 [ +0.000005] kthread+0x17f/0x1b0 [ +0.000005] ? __pfx_kthread+0x10/0x10 [ +0.000004] ret_from_fork+0x29/0x50 [ +0.000009] Fixes: 940b61af02f4 ("ice: Initialize PF and setup miscellaneous interrupt") Signed-off-by: Anirudh Venkataramanan Signed-off-by: Marcin Szycik Tested-by: Jakub Andrysiak Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5f86e4111fa9b..b288a01a321a0 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5541,7 +5541,7 @@ static int __init ice_module_init(void) pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); - ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; From b2dbde3ad44f290ded319f00b71dccec90083a50 Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Wed, 4 Jan 2023 09:25:17 +0100 Subject: [PATCH 19/57] ice: fix out-of-bounds KASAN warning in virtchnl KASAN reported: [ 9793.708867] BUG: KASAN: global-out-of-bounds in ice_get_link_speed+0x16/0x30 [ice] [ 9793.709205] Read of size 4 at addr ffffffffc1271b1c by task kworker/6:1/402 [ 9793.709222] CPU: 6 PID: 402 Comm: kworker/6:1 Kdump: loaded Tainted: G B OE 6.1.0+ #3 [ 9793.709235] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.00.01.0014.070920180847 07/09/2018 [ 9793.709245] Workqueue: ice ice_service_task [ice] [ 9793.709575] Call Trace: [ 9793.709582] [ 9793.709588] dump_stack_lvl+0x44/0x5c [ 9793.709613] print_report+0x17f/0x47b [ 9793.709632] ? __cpuidle_text_end+0x5/0x5 [ 9793.709653] ? ice_get_link_speed+0x16/0x30 [ice] [ 9793.709986] ? ice_get_link_speed+0x16/0x30 [ice] [ 9793.710317] kasan_report+0xb7/0x140 [ 9793.710335] ? ice_get_link_speed+0x16/0x30 [ice] [ 9793.710673] ice_get_link_speed+0x16/0x30 [ice] [ 9793.711006] ice_vc_notify_vf_link_state+0x14c/0x160 [ice] [ 9793.711351] ? ice_vc_repr_cfg_promiscuous_mode+0x120/0x120 [ice] [ 9793.711698] ice_vc_process_vf_msg+0x7a7/0xc00 [ice] [ 9793.712074] __ice_clean_ctrlq+0x98f/0xd20 [ice] [ 9793.712534] ? ice_bridge_setlink+0x410/0x410 [ice] [ 9793.712979] ? __request_module+0x320/0x520 [ 9793.713014] ? ice_process_vflr_event+0x27/0x130 [ice] [ 9793.713489] ice_service_task+0x11cf/0x1950 [ice] [ 9793.713948] ? io_schedule_timeout+0xb0/0xb0 [ 9793.713972] process_one_work+0x3d0/0x6a0 [ 9793.714003] worker_thread+0x8a/0x610 [ 9793.714031] ? process_one_work+0x6a0/0x6a0 [ 9793.714049] kthread+0x164/0x1a0 [ 9793.714071] ? kthread_complete_and_exit+0x20/0x20 [ 9793.714100] ret_from_fork+0x1f/0x30 [ 9793.714137] [ 9793.714151] The buggy address belongs to the variable: [ 9793.714158] ice_aq_to_link_speed+0x3c/0xffffffffffff3520 [ice] [ 9793.714632] Memory state around the buggy address: [ 9793.714642] ffffffffc1271a00: f9 f9 f9 f9 00 00 05 f9 f9 f9 f9 f9 00 00 02 f9 [ 9793.714656] ffffffffc1271a80: f9 f9 f9 f9 00 00 04 f9 f9 f9 f9 f9 00 00 00 00 [ 9793.714670] >ffffffffc1271b00: 00 00 00 04 f9 f9 f9 f9 04 f9 f9 f9 f9 f9 f9 f9 [ 9793.714680] ^ [ 9793.714690] ffffffffc1271b80: 00 00 00 00 00 04 f9 f9 f9 f9 f9 f9 00 00 00 00 [ 9793.714704] ffffffffc1271c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 The ICE_AQ_LINK_SPEED_UNKNOWN define is BIT(15). The value is bigger than both legacy and normal link speed tables. Add one element (0 - unknown) to both tables. There is no need to explicitly set table size, leave it empty. Fixes: 1d0e28a9be1f ("ice: Remove and replace ice speed defines with ethtool.h versions") Signed-off-by: Michal Swiatkowski Reviewed-by: Alexander Lobakin Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky --- drivers/net/ethernet/intel/ice/ice_common.c | 9 ++++----- drivers/net/ethernet/intel/ice/ice_vf_mbx.c | 21 ++++++++------------- 2 files changed, 12 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index d02b55b6aa9cf..3e08847505ce1 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5524,7 +5524,7 @@ bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) * returned by the firmware is a 16 bit * value, but is indexed * by [fls(speed) - 1] */ -static const u32 ice_aq_to_link_speed[15] = { +static const u32 ice_aq_to_link_speed[] = { SPEED_10, /* BIT(0) */ SPEED_100, SPEED_1000, @@ -5536,10 +5536,6 @@ static const u32 ice_aq_to_link_speed[15] = { SPEED_40000, SPEED_50000, SPEED_100000, /* BIT(10) */ - 0, - 0, - 0, - 0 /* BIT(14) */ }; /** @@ -5550,5 +5546,8 @@ static const u32 ice_aq_to_link_speed[15] = { */ u32 ice_get_link_speed(u16 index) { + if (index >= ARRAY_SIZE(ice_aq_to_link_speed)) + return 0; + return ice_aq_to_link_speed[index]; } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index d4a4001b6e5dd..f56fa94ff3d0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -39,7 +39,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); } -static const u32 ice_legacy_aq_to_vc_speed[15] = { +static const u32 ice_legacy_aq_to_vc_speed[] = { VIRTCHNL_LINK_SPEED_100MB, /* BIT(0) */ VIRTCHNL_LINK_SPEED_100MB, VIRTCHNL_LINK_SPEED_1GB, @@ -51,10 +51,6 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN /* BIT(14) */ }; /** @@ -71,21 +67,20 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { */ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) { - u32 speed; + /* convert a BIT() value into an array index */ + u32 index = fls(link_speed) - 1; - if (adv_link_support) { - /* convert a BIT() value into an array index */ - speed = ice_get_link_speed(fls(link_speed) - 1); - } else { + if (adv_link_support) + return ice_get_link_speed(index); + else if (index < ARRAY_SIZE(ice_legacy_aq_to_vc_speed)) /* Virtchnl speeds are not defined for every speed supported in * the hardware. To maintain compatibility with older AVF * drivers, while reporting the speed the new speed values are * resolved to the closest known virtchnl speeds */ - speed = ice_legacy_aq_to_vc_speed[fls(link_speed) - 1]; - } + return ice_legacy_aq_to_vc_speed[index]; - return speed; + return VIRTCHNL_LINK_SPEED_UNKNOWN; } /* The mailbox overflow detection algorithm helps to check if there From c793f8ea15e312789b5b6b4a5e7b0b92315be5cb Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 16 Jan 2023 13:34:58 +0100 Subject: [PATCH 20/57] ice: Fix disabling Rx VLAN filtering with port VLAN enabled If the user turns on the vf-true-promiscuous-support flag, then Rx VLAN filtering will be disabled if the VF requests to enable promiscuous mode. When the VF is in a port VLAN, this is the incorrect behavior because it will allow the VF to receive traffic outside of its port VLAN domain. Fortunately this only resulted in the VF(s) receiving broadcast traffic outside of the VLAN domain because all of the VLAN promiscuous rules are based on the port VLAN ID. Fix this by setting the .disable_rx_filtering VLAN op to a no-op when a port VLAN is enabled on the VF. Also, make sure to make this fix for both Single VLAN Mode and Double VLAN Mode enabled devices. Fixes: c31af68a1b94 ("ice: Add outer_vlan_ops and VSI specific VLAN ops implementations") Signed-off-by: Brett Creeley Signed-off-by: Karen Ostrowska Tested-by: Marek Szlosek Signed-off-by: Tony Nguyen --- .../net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index 5ecc0ee9a78e0..b1ffb81893d48 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -44,13 +44,17 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) /* outer VLAN ops regardless of port VLAN config */ vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; if (ice_vf_is_port_vlan_ena(vf)) { /* setup outer VLAN ops */ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; @@ -63,6 +67,9 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -96,7 +103,14 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else From 3f4870df1b15d62665cb86ca116c8c9cf0e830b0 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 28 Oct 2022 18:02:24 +0300 Subject: [PATCH 21/57] ice: Fix off by one in ice_tc_forward_to_queue() The > comparison should be >= to prevent reading one element beyond the end of the array. The "vsi->num_rxq" is not strictly speaking the number of elements in the vsi->rxq_map[] array. The array has "vsi->alloc_rxq" elements and "vsi->num_rxq" is less than or equal to the number of elements in the array. The array is allocated in ice_vsi_alloc_arrays(). It's still an off by one but it might not access outside the end of the array. Fixes: 143b86f346c7 ("ice: Enable RX queue selection using skbedit action") Signed-off-by: Dan Carpenter Acked-by: Amritha Nambiar Tested-by: Bharathi Sreenivas Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky --- drivers/net/ethernet/intel/ice/ice_tc_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index faba0f857cd9f..95f392ab96708 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -1681,7 +1681,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, struct ice_vsi *ch_vsi = NULL; u16 queue = act->rx_queue; - if (queue > vsi->num_rxq) { + if (queue >= vsi->num_rxq) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified queue is invalid"); return -EINVAL; From 4a606ce68426c88ff2563382b33cc34f3485fe57 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Mon, 12 Dec 2022 15:11:26 -0800 Subject: [PATCH 22/57] ice: switch: fix potential memleak in ice_add_adv_recipe() When ice_add_special_words() fails, the 'rm' is not released, which will lead to a memory leak. Fix this up by going to 'err_unroll' label. Compile tested only. Fixes: 8b032a55c1bd ("ice: low level support for tunnels") Signed-off-by: Zhang Changzhong Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky --- drivers/net/ethernet/intel/ice/ice_switch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 9b762f7972ce5..61f844d225123 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -5420,7 +5420,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, */ status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw)); if (status) - goto err_free_lkup_exts; + goto err_unroll; /* Group match words into recipes using preferred recipe grouping * criteria. From 0b6d6425103a676e2b6a81f3fd35d7ea4f9b90ec Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 Feb 2023 16:07:13 +0200 Subject: [PATCH 23/57] net: dsa: mt7530: don't change PVC_EG_TAG when CPU port becomes VLAN-aware MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Frank reports that in a mt7530 setup where some ports are standalone and some are in a VLAN-aware bridge, 8021q uppers of the standalone ports lose their VLAN tag on xmit, as seen by the link partner. This seems to occur because once the other ports join the VLAN-aware bridge, mt7530_port_vlan_filtering() also calls mt7530_port_set_vlan_aware(ds, cpu_dp->index), and this affects the way that the switch processes the traffic of the standalone port. Relevant is the PVC_EG_TAG bit. The MT7530 documentation says about it: EG_TAG: Incoming Port Egress Tag VLAN Attribution 0: disabled (system default) 1: consistent (keep the original ingress tag attribute) My interpretation is that this setting applies on the ingress port, and "disabled" is basically the normal behavior, where the egress tag format of the packet (tagged or untagged) is decided by the VLAN table (MT7530_VLAN_EGRESS_UNTAG or MT7530_VLAN_EGRESS_TAG). But there is also an option of overriding the system default behavior, and for the egress tagging format of packets to be decided not by the VLAN table, but simply by copying the ingress tag format (if ingress was tagged, egress is tagged; if ingress was untagged, egress is untagged; aka "consistent). This is useful in 2 scenarios: - VLAN-unaware bridge ports will always encounter a miss in the VLAN table. They should forward a packet as-is, though. So we use "consistent" there. See commit e045124e9399 ("net: dsa: mt7530: fix tagged frames pass-through in VLAN-unaware mode"). - Traffic injected from the CPU port. The operating system is in god mode; if it wants a packet to exit as VLAN-tagged, it sends it as VLAN-tagged. Otherwise it sends it as VLAN-untagged*. *This is true only if we don't consider the bridge TX forwarding offload feature, which mt7530 doesn't support. So for now, make the CPU port always stay in "consistent" mode to allow software VLANs to be forwarded to their egress ports with the VLAN tag intact, and not stripped. Link: https://lore.kernel.org/netdev/trinity-e6294d28-636c-4c40-bb8b-b523521b00be-1674233135062@3c-app-gmx-bs36/ Fixes: e045124e9399 ("net: dsa: mt7530: fix tagged frames pass-through in VLAN-unaware mode") Reported-by: Frank Wunderlich Tested-by: Frank Wunderlich Signed-off-by: Vladimir Oltean Tested-by: Arınç ÜNAL Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230205140713.1609281-1-vladimir.oltean@nxp.com Signed-off-by: Paolo Abeni --- drivers/net/dsa/mt7530.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 908fa89444c90..338f238f2043c 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1309,14 +1309,26 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) if (!priv->ports[port].pvid) mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK, MT7530_VLAN_ACC_TAGGED); - } - /* Set the port as a user port which is to be able to recognize VID - * from incoming packets before fetching entry within the VLAN table. - */ - mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK, - VLAN_ATTR(MT7530_VLAN_USER) | - PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + /* Set the port as a user port which is to be able to recognize + * VID from incoming packets before fetching entry within the + * VLAN table. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), + VLAN_ATTR_MASK | PVC_EG_TAG_MASK, + VLAN_ATTR(MT7530_VLAN_USER) | + PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + } else { + /* Also set CPU ports to the "user" VLAN port attribute, to + * allow VLAN classification, but keep the EG_TAG attribute as + * "consistent" (i.o.w. don't change its value) for packets + * received by the switch from the CPU, so that tagged packets + * are forwarded to user ports as tagged, and untagged as + * untagged. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK, + VLAN_ATTR(MT7530_VLAN_USER)); + } } static void From f964f8399df29d3e3ced77177cf35131cd2491bf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 Feb 2023 21:24:08 +0200 Subject: [PATCH 24/57] net: mscc: ocelot: fix VCAP filters not matching on MAC with "protocol 802.1Q" Alternative short title: don't instruct the hardware to match on EtherType with "protocol 802.1Q" flower filters. It doesn't work for the reasons detailed below. With a command such as the following: tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \ protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \ action vlan modify id 300 \ action goto chain $(IS2 0 0) the created filter is set by ocelot_flower_parse_key() to be of type OCELOT_VCAP_KEY_ETYPE, and etype is set to {value=0x8100, mask=0xffff}. This gets propagated all the way to is1_entry_set() which commits it to hardware (the VCAP_IS1_HK_ETYPE field of the key). Compare this to the case where src_mac isn't specified - the key type is OCELOT_VCAP_KEY_ANY, and is1_entry_set() doesn't populate VCAP_IS1_HK_ETYPE. The problem is that for VLAN-tagged frames, the hardware interprets the ETYPE field as holding the encapsulated VLAN protocol. So the above filter will only match those packets which have an encapsulated protocol of 0x8100, rather than all packets with VLAN ID 200 and the given src_mac. The reason why this is allowed to occur is because, although we have a block of code in ocelot_flower_parse_key() which sets "match_protocol" to false when VLAN keys are present, that code executes too late. There is another block of code, which executes for Ethernet addresses, and has a "goto finished_key_parsing" and skips the VLAN header parsing. By skipping it, "match_protocol" remains with the value it was initialized with, i.e. "true", and "proto" is set to f->common.protocol, or 0x8100. The concept of ignoring some keys rather than erroring out when they are present but can't be offloaded is dubious in itself, but is present since the initial commit fe3490e6107e ("net: mscc: ocelot: Hardware ofload for tc flower filter"), and it's outside of the scope of this patch to change that. The problem was introduced when the driver started to interpret the flower filter's protocol, and populate the VCAP filter's ETYPE field based on it. To fix this, it is sufficient to move the code that parses the VLAN keys earlier than the "goto finished_key_parsing" instruction. This will ensure that if we have a flower filter with both VLAN and Ethernet address keys, it won't match on ETYPE 0x8100, because the VLAN key parsing sets "match_protocol = false". Fixes: 86b956de119c ("net: mscc: ocelot: support matching on EtherType") Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230205192409.1796428-1-vladimir.oltean@nxp.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mscc/ocelot_flower.c | 24 +++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 7c0897e779dc6..ee052404eb55a 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -605,6 +605,18 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, flow_rule_match_control(rule, &match); } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->vlan.vid.value = match.key->vlan_id; + filter->vlan.vid.mask = match.mask->vlan_id; + filter->vlan.pcp.value[0] = match.key->vlan_priority; + filter->vlan.pcp.mask[0] = match.mask->vlan_priority; + match_protocol = false; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -737,18 +749,6 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, match_protocol = false; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_match_vlan match; - - flow_rule_match_vlan(rule, &match); - filter->key_type = OCELOT_VCAP_KEY_ANY; - filter->vlan.vid.value = match.key->vlan_id; - filter->vlan.vid.mask = match.mask->vlan_id; - filter->vlan.pcp.value[0] = match.key->vlan_priority; - filter->vlan.pcp.mask[0] = match.mask->vlan_priority; - match_protocol = false; - } - finished_key_parsing: if (match_protocol && proto != ETH_P_ALL) { if (filter->block_id == VCAP_ES0) { From bbb253b206b9c417928a6c827d038e457f3012e9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 Feb 2023 21:24:09 +0200 Subject: [PATCH 25/57] selftests: ocelot: tc_flower_chains: make test_vlan_ingress_modify() more comprehensive We have two IS1 filters of the OCELOT_VCAP_KEY_ANY key type (the one with "action vlan pop" and the one with "action vlan modify") and one of the OCELOT_VCAP_KEY_IPV4 key type (the one with "action skbedit priority"). But we have no IS1 filter with the OCELOT_VCAP_KEY_ETYPE key type, and there was an uncaught breakage there. To increase test coverage, convert one of the OCELOT_VCAP_KEY_ANY filters to OCELOT_VCAP_KEY_ETYPE, by making the filter also match on the MAC SA of the traffic sent by mausezahn, $h1_mac. Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230205192409.1796428-2-vladimir.oltean@nxp.com Signed-off-by: Paolo Abeni --- tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index 9c79bbcce5a87..aff0a59f92d9a 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -246,7 +246,7 @@ test_vlan_ingress_modify() bridge vlan add dev $swp2 vid 300 tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \ - protocol 802.1Q flower skip_sw vlan_id 200 \ + protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \ action vlan modify id 300 \ action goto chain $(IS2 0 0) From 565b4824c39fa335cba2028a09d7beb7112f3c9a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Feb 2023 10:41:51 +0100 Subject: [PATCH 26/57] devlink: change port event netdev notifier from per-net to global Currently only the network namespace of devlink instance is monitored for port events. If netdev is moved to a different namespace and then unregistered, NETDEV_PRE_UNINIT is missed which leads to trigger following WARN_ON in devl_port_unregister(). WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET); Fix this by changing the netdev notifier from per-net to global so no event is missed. Fixes: 02a68a47eade ("net: devlink: track netdev with devlink_port assigned") Signed-off-by: Jiri Pirko Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20230206094151.2557264-1-jiri@resnulli.us Signed-off-by: Paolo Abeni --- net/core/devlink.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/core/devlink.c b/net/core/devlink.c index 032d6d0a5ce64..909a10e4b0ddf 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -9979,7 +9979,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, goto err_xa_alloc; devlink->netdevice_nb.notifier_call = devlink_netdevice_event; - ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + ret = register_netdevice_notifier(&devlink->netdevice_nb); if (ret) goto err_register_netdevice_notifier; @@ -10171,8 +10171,7 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->snapshot_ids); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), - &devlink->netdevice_nb)); + WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); xa_erase(&devlinks, devlink->index); @@ -10503,6 +10502,8 @@ static int devlink_netdevice_event(struct notifier_block *nb, break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this @@ -10512,6 +10513,8 @@ static int devlink_netdevice_event(struct notifier_block *nb, netdev); break; case NETDEV_UNREGISTER: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. From 4ae5e1e97c44f4654516c1d41591a462ed62fa7b Mon Sep 17 00:00:00 2001 From: Devid Antonio Filoni Date: Fri, 25 Nov 2022 18:04:18 +0100 Subject: [PATCH 27/57] can: j1939: do not wait 250 ms if the same addr was already claimed The ISO 11783-5 standard, in "4.5.2 - Address claim requirements", states: d) No CF shall begin, or resume, transmission on the network until 250 ms after it has successfully claimed an address except when responding to a request for address-claimed. But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim prioritization" show that the CF begins the transmission after 250 ms from the first AC (address-claimed) message even if it sends another AC message during that time window to resolve the address contention with another CF. As stated in "4.4.2.3 - Address-claimed message": In order to successfully claim an address, the CF sending an address claimed message shall not receive a contending claim from another CF for at least 250 ms. As stated in "4.4.3.2 - NAME management (NM) message": 1) A commanding CF can d) request that a CF with a specified NAME transmit the address- claimed message with its current NAME. 2) A target CF shall d) send an address-claimed message in response to a request for a matching NAME Taking the above arguments into account, the 250 ms wait is requested only during network initialization. Do not restart the timer on AC message if both the NAME and the address match and so if the address has already been claimed (timer has expired) or the AC message has been sent to resolve the contention with another CF (timer is still running). Signed-off-by: Devid Antonio Filoni Acked-by: Oleksij Rempel Link: https://lore.kernel.org/all/20221125170418.34575-1-devid.filoni@egluetechnologies.com Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/j1939/address-claim.c | 40 +++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c473279278..ca4ad6cdd5cbf 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); From 1e66220948df815d7b37e0ff8b4627ce10433738 Mon Sep 17 00:00:00 2001 From: Adham Faris Date: Sun, 8 Jan 2023 18:09:32 +0200 Subject: [PATCH 28/57] net/mlx5e: Update rx ring hw mtu upon each rx-fcs flag change rq->hw_mtu is used in function en_rx.c/mlx5e_skb_from_cqe_mpwrq_linear() to catch oversized packets. If FCS is concatenated to the end of the packet then the check should be updated accordingly. Rx rings initialization (mlx5e_init_rxq_rq()) invoked for every new set of channels, as part of mlx5e_safe_switch_params(), unknowingly if it runs with default configuration or not. Current rq->hw_mtu initialization assumes default configuration and ignores params->scatter_fcs_en flag state. Fix this, by accounting for params->scatter_fcs_en flag state during rq->hw_mtu initialization. In addition, updating rq->hw_mtu value during ingress traffic might lead to packets drop and oversize_pkts_sw_drop counter increase with no good reason. Hence we remove this optimization and switch the set of channels with a new one, to make sure we don't get false positives on the oversize_pkts_sw_drop counter. Fixes: 102722fc6832 ("net/mlx5e: Add support for RXFCS feature flag") Signed-off-by: Adham Faris Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 86 ++++--------------- 1 file changed, 15 insertions(+), 71 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index abcc614b6191b..f8b5e5993f351 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -591,7 +591,8 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param rq->ix = c->ix; rq->channel = c; rq->mdev = mdev; - rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + rq->hw_mtu = + MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN * !params->scatter_fcs_en; rq->xdpsq = &c->rq_xdpsq; rq->stats = &c->priv->channel_stats[c->ix]->rq; rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev); @@ -1014,35 +1015,6 @@ int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) return mlx5e_rq_to_ready(rq, curr_state); } -static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) -{ - struct mlx5_core_dev *mdev = rq->mdev; - - void *in; - void *rqc; - int inlen; - int err; - - inlen = MLX5_ST_SZ_BYTES(modify_rq_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); - - MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY); - MLX5_SET64(modify_rq_in, in, modify_bitmask, - MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS); - MLX5_SET(rqc, rqc, scatter_fcs, enable); - MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY); - - err = mlx5_core_modify_rq(mdev, rq->rqn, in); - - kvfree(in); - - return err; -} - static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5_core_dev *mdev = rq->mdev; @@ -3314,20 +3286,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) mlx5e_destroy_tises(priv); } -static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) -{ - int err = 0; - int i; - - for (i = 0; i < chs->num; i++) { - err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); - if (err) - return err; - } - - return 0; -} - static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { int err; @@ -3903,41 +3861,27 @@ static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) return mlx5_set_ports_check(mdev, in, sizeof(in)); } +static int mlx5e_set_rx_port_ts_wrap(struct mlx5e_priv *priv, void *ctx) +{ + struct mlx5_core_dev *mdev = priv->mdev; + bool enable = *(bool *)ctx; + + return mlx5e_set_rx_port_ts(mdev, enable); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels *chs = &priv->channels; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_params new_params; int err; mutex_lock(&priv->state_lock); - if (enable) { - err = mlx5e_set_rx_port_ts(mdev, false); - if (err) - goto out; - - chs->params.scatter_fcs_en = true; - err = mlx5e_modify_channels_scatter_fcs(chs, true); - if (err) { - chs->params.scatter_fcs_en = false; - mlx5e_set_rx_port_ts(mdev, true); - } - } else { - chs->params.scatter_fcs_en = false; - err = mlx5e_modify_channels_scatter_fcs(chs, false); - if (err) { - chs->params.scatter_fcs_en = true; - goto out; - } - err = mlx5e_set_rx_port_ts(mdev, true); - if (err) { - mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); - err = 0; - } - } - -out: + new_params = chs->params; + new_params.scatter_fcs_en = enable; + err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_set_rx_port_ts_wrap, + &new_params.scatter_fcs_en, true); mutex_unlock(&priv->state_lock); return err; } From 288d85e07fbca5ee35882a4884dd701e43637be1 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 17 Jan 2023 17:34:20 +0200 Subject: [PATCH 29/57] net/mlx5: DR, Fix potential race in dr_rule_create_rule_nic Selecting builder should be protected by the lock to prevent the case where a new rule sets a builder in the nic_matcher while the previous rule is still using the nic_matcher. Fixing this issue and cleaning the error flow. Fixes: b9b81e1e9382 ("net/mlx5: DR, For short chains of STEs, avoid allocating ste_arr dynamically") Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_rule.c | 25 +++++++++++-------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index b851141e03de3..042ca03491243 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -1138,12 +1138,14 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, rule->flow_source)) return 0; + mlx5dr_domain_nic_lock(nic_dmn); + ret = mlx5dr_matcher_select_builders(matcher, nic_matcher, dr_rule_get_ipv(¶m->outer), dr_rule_get_ipv(¶m->inner)); if (ret) - return ret; + goto err_unlock; hw_ste_arr_is_opt = nic_matcher->num_of_builders <= DR_RULE_MAX_STES_OPTIMIZED; if (likely(hw_ste_arr_is_opt)) { @@ -1152,12 +1154,12 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, hw_ste_arr = kzalloc((nic_matcher->num_of_builders + DR_ACTION_MAX_STES) * DR_STE_SIZE, GFP_KERNEL); - if (!hw_ste_arr) - return -ENOMEM; + if (!hw_ste_arr) { + ret = -ENOMEM; + goto err_unlock; + } } - mlx5dr_domain_nic_lock(nic_dmn); - ret = mlx5dr_matcher_add_to_tbl_nic(dmn, nic_matcher); if (ret) goto free_hw_ste; @@ -1223,7 +1225,10 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - goto out; + if (unlikely(!hw_ste_arr_is_opt)) + kfree(hw_ste_arr); + + return 0; free_rule: dr_rule_clean_rule_members(rule, nic_rule); @@ -1238,12 +1243,12 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher); free_hw_ste: - mlx5dr_domain_nic_unlock(nic_dmn); - -out: - if (unlikely(!hw_ste_arr_is_opt)) + if (!hw_ste_arr_is_opt) kfree(hw_ste_arr); +err_unlock: + mlx5dr_domain_nic_unlock(nic_dmn); + return ret; } From da0c52426cd23f8728eff72c2b2d2a3eb6b451f5 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 26 Jan 2023 14:47:12 +0100 Subject: [PATCH 30/57] net/mlx5: Bridge, fix ageing of peer FDB entries SWITCHDEV_FDB_ADD_TO_BRIDGE event handler that updates FDB entry 'lastuse' field is only executed for eswitch that owns the entry. However, if peer entry processed packets at least once it will have hardware counter 'used' value greater than entry 'lastuse' from that point on, which will cause FDB entry not being aged out. Process the event on all eswitch instances. Fixes: ff9b7521468b ("net/mlx5: Bridge, support LAG") Signed-off-by: Vlad Buslov Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c | 4 ---- drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c | 2 +- 2 files changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 8099a21e674c9..ce85b48d327da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -438,10 +438,6 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: - /* only handle the event on native eswtich of representor */ - if (!mlx5_esw_bridge_is_local(dev, rep, esw)) - break; - fdb_info = container_of(info, struct switchdev_notifier_fdb_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index b176648d1343a..3cdcb0e0b20f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1715,7 +1715,7 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 struct mlx5_esw_bridge *bridge; port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); - if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER) + if (!port) return; bridge = port->bridge; From 8974aa9638df557f4642acef707af15648a03555 Mon Sep 17 00:00:00 2001 From: Amir Tzin Date: Sun, 8 Jan 2023 15:54:46 +0200 Subject: [PATCH 31/57] net/mlx5e: Fix crash unsetting rx-vlan-filter in switchdev mode Moving to switchdev mode with rx-vlan-filter on and then setting it off causes the kernel to crash since fs->vlan is freed during nic profile cleanup flow. RX VLAN filtering is not supported in switchdev mode so unset it when changing to switchdev and restore its value when switching back to legacy. trace: [] RIP: 0010:mlx5e_disable_cvlan_filter+0x43/0x70 [] set_feature_cvlan_filter+0x37/0x40 [mlx5_core] [] mlx5e_handle_feature+0x3a/0x60 [mlx5_core] [] mlx5e_set_features+0x6d/0x160 [mlx5_core] [] __netdev_update_features+0x288/0xa70 [] ethnl_set_features+0x309/0x380 [] ? __nla_parse+0x21/0x30 [] genl_family_rcv_msg_doit.isra.17+0x110/0x150 [] genl_rcv_msg+0x112/0x260 [] ? features_reply_size+0xe0/0xe0 [] ? genl_family_rcv_msg_doit.isra.17+0x150/0x150 [] netlink_rcv_skb+0x4e/0x100 [] genl_rcv+0x24/0x40 [] netlink_unicast+0x1ab/0x290 [] netlink_sendmsg+0x257/0x4f0 [] sock_sendmsg+0x5c/0x70 Fixes: cb67b832921c ("net/mlx5e: Introduce SRIOV VF representors") Signed-off-by: Amir Tzin Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 1892ccb889b3f..7cd36f4ac3efc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -443,7 +443,7 @@ void mlx5e_enable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) void mlx5e_disable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) { - if (fs->vlan->cvlan_filter_disabled) + if (!fs->vlan || fs->vlan->cvlan_filter_disabled) return; fs->vlan->cvlan_filter_disabled = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f8b5e5993f351..6c24f33a5ea5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4018,6 +4018,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_GRO_HW) netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n"); + return features; } From 8aa5f171d51c1cb69e5e3106df4dd1a446102823 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Mon, 23 Jan 2023 16:06:32 +0200 Subject: [PATCH 32/57] net/mlx5e: IPoIB, Show unknown speed instead of error ethtool is returning an error for unknown speeds for the IPoIB interface: $ ethtool ib0 netlink error: failed to retrieve link settings netlink error: Invalid argument netlink error: failed to retrieve link settings netlink error: Invalid argument Settings for ib0: Link detected: no After this change, ethtool will return success and show "unknown speed": $ ethtool ib0 Settings for ib0: Supported ports: [ ] Supported link modes: Not reported Supported pause frame use: No Supports auto-negotiation: No Supported FEC modes: Not reported Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: Not reported Speed: Unknown! Duplex: Full Auto-negotiation: off Port: Other PHYAD: 0 Transceiver: internal Link detected: no Fixes: eb234ee9d541 ("net/mlx5e: IPoIB, Add support for get_link_ksettings in ethtool") Signed-off-by: Dragos Tatulea Reviewed-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index eff92dc0927c1..e09518f887a04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -189,16 +189,16 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) } } -static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) +static u32 mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) { int rate, width; rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper); if (rate < 0) - return -EINVAL; + return SPEED_UNKNOWN; width = mlx5_ptys_width_enum_to_int(ib_link_width_oper); if (width < 0) - return -EINVAL; + return SPEED_UNKNOWN; return rate * width; } @@ -221,16 +221,13 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper); - if (speed < 0) - return -EINVAL; + link_ksettings->base.speed = speed; + link_ksettings->base.duplex = speed == SPEED_UNKNOWN ? DUPLEX_UNKNOWN : DUPLEX_FULL; - link_ksettings->base.duplex = DUPLEX_FULL; link_ksettings->base.port = PORT_OTHER; link_ksettings->base.autoneg = AUTONEG_DISABLE; - link_ksettings->base.speed = speed; - return 0; } From c3bdbaea654d8df39112de33037106134a520dc7 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Sun, 22 Jan 2023 21:09:40 +0200 Subject: [PATCH 33/57] net/mlx5: Store page counters in a single array Currently, an independent page counter is used for tracking memory usage for each function type such as VF, PF and host PF (DPU). For better code-readibilty, use a single array that stores the number of allocated memory pages for each function type. Signed-off-by: Maher Sanalla Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/debugfs.c | 4 +- .../net/ethernet/mellanox/mlx5/core/ecpf.c | 2 +- .../ethernet/mellanox/mlx5/core/pagealloc.c | 37 +++++++++++-------- .../net/ethernet/mellanox/mlx5/core/sriov.c | 2 +- include/linux/mlx5/driver.h | 12 ++++-- 5 files changed, 34 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 3e232a65a0c3e..c3e7c24a0971e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -245,8 +245,8 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) pages = dev->priv.dbg.pages_debugfs; debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); - debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages); - debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages); + debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]); + debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]); debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped); debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 464eb3a184506..cdc87ecae5d39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -87,7 +87,7 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) mlx5_host_pf_cleanup(dev); - err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages); + err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); if (err) mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 60596357bfc7a..9f99292ab5ced 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -74,6 +74,14 @@ static u32 get_function(u16 func_id, bool ec_function) return (u32)func_id | (ec_function << 16); } +static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function) +{ + if (!func_id) + return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF; + + return MLX5_VF; +} + static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function) { struct rb_root *root; @@ -332,6 +340,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); int notify_fail = event; + u16 func_type; u64 addr; int err; u32 *in; @@ -383,11 +392,9 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, goto out_dropped; } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] += npages; dev->priv.fw_pages += npages; - if (func_id) - dev->priv.vfs_pages += npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages += npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", npages, ec_function, func_id, err); @@ -414,6 +421,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, struct rb_root *root; struct rb_node *p; int npages = 0; + u16 func_type; root = xa_load(&dev->priv.page_root_xa, function); if (WARN_ON_ONCE(!root)) @@ -428,11 +436,9 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, free_fwp(dev, fwp, fwp->free_count); } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= npages; dev->priv.fw_pages -= npages; - if (func_id) - dev->priv.vfs_pages -= npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n", npages, ec_function, func_id); @@ -498,6 +504,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {}; int num_claimed; + u16 func_type; u32 *out; int err; int i; @@ -549,11 +556,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, if (nclaimed) *nclaimed = num_claimed; + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= num_claimed; dev->priv.fw_pages -= num_claimed; - if (func_id) - dev->priv.vfs_pages -= num_claimed; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= num_claimed; out_free: kvfree(out); @@ -706,12 +711,12 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.fw_pages, "FW pages counter is %d after reclaiming all pages\n", dev->priv.fw_pages); - WARN(dev->priv.vfs_pages, + WARN(dev->priv.page_counters[MLX5_VF], "VFs FW pages counter is %d after reclaiming all pages\n", - dev->priv.vfs_pages); - WARN(dev->priv.host_pf_pages, + dev->priv.page_counters[MLX5_VF]); + WARN(dev->priv.page_counters[MLX5_HOST_PF], "External host PF FW pages counter is %d after reclaiming all pages\n", - dev->priv.host_pf_pages); + dev->priv.page_counters[MLX5_HOST_PF]); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index c0e6c487c63c1..3008e9ce2bbff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); - if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) + if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 76ef2e4fde38d..82a9bd4274b87 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -573,6 +573,13 @@ struct mlx5_debugfs_entries { struct dentry *lag_debugfs; }; +enum mlx5_func_type { + MLX5_PF, + MLX5_VF, + MLX5_HOST_PF, + MLX5_FUNC_TYPE_NUM, +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -583,11 +590,10 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - u32 vfs_pages; - u32 host_pf_pages; + u32 fw_pages; + u32 page_counters[MLX5_FUNC_TYPE_NUM]; u32 fw_pages_alloc_failed; u32 give_pages_dropped; u32 reclaim_pages_discard; From 9965bbebae59b3563a4d95e4aed121e8965dfdc2 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Sun, 22 Jan 2023 23:24:56 +0200 Subject: [PATCH 34/57] net/mlx5: Expose SF firmware pages counter Currently, each core device has VF pages counter which stores number of fw pages used by its VFs and SFs. The current design led to a hang when performing firmware reset on DPU, where the DPU PFs stalled in sriov unload flow due to waiting on release of SFs pages instead of waiting on only VFs pages. Thus, Add a separate counter for SF firmware pages, which will prevent the stall scenario described above. Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Signed-off-by: Maher Sanalla Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 2 +- include/linux/mlx5/driver.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index c3e7c24a0971e..bb95b40d25eb5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -246,6 +246,7 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]); + debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]); debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]); debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 9f99292ab5ced..0eb50be175cc4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -79,7 +79,7 @@ static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_funct if (!func_id) return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF; - return MLX5_VF; + return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF; } static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 82a9bd4274b87..333c1fec72f87 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -576,6 +576,7 @@ struct mlx5_debugfs_entries { enum mlx5_func_type { MLX5_PF, MLX5_VF, + MLX5_SF, MLX5_HOST_PF, MLX5_FUNC_TYPE_NUM, }; From db561fed6b8fa3878e74d5df6512a4a38152b63e Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 9 Jan 2023 15:27:40 +0200 Subject: [PATCH 35/57] net/mlx5: fw_tracer, Clear load bit when freeing string DBs buffers Whenever the driver is reading the string DBs into buffers, the driver is setting the load bit, but the driver never clears this bit. As a result, in case load bit is on and the driver query the device for new string DBs, the driver won't read again the string DBs. Fix it by clearing the load bit when query the device for new string DBs. Fixes: 2d69356752ff ("net/mlx5: Add support for fw live patch event") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 21831386b26e8..d82e98a0cdfa7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -64,6 +64,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) MLX5_GET(mtrc_cap, out, num_string_trace); tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db); tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + tracer->str_db.loaded = false; for (i = 0; i < tracer->str_db.num_string_db; i++) { mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]); From 184e1e4474dbcfebc4dbd1fa823a329978f25506 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 25 Jan 2023 17:39:36 +0200 Subject: [PATCH 36/57] net/mlx5: fw_tracer, Zero consumer index when reloading the tracer When tracer is reloaded, the device will log the traces at the beginning of the log buffer. Also, driver is reading the log buffer in chunks in accordance to the consumer index. Hence, zero consumer index when reloading the tracer. Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload") Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index d82e98a0cdfa7..5b05b884b5fb3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -757,6 +757,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) if (err) mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err); + tracer->buff.consumer_index = 0; return err; } @@ -821,7 +822,6 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work) mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner); if (tracer->owner) { tracer->owner = false; - tracer->buff.consumer_index = 0; return; } From 8f0d1451ecf7b3bd5a06ffc866c753d0f3ab4683 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 14 Dec 2022 22:16:23 +0200 Subject: [PATCH 37/57] net/mlx5: Serialize module cleanup with reload and remove Currently, remove and reload flows can run in parallel to module cleanup. This design is error prone. For example: aux_drivers callbacks are called from both cleanup and remove flows with different lockings, which can cause a deadlock[1]. Hence, serialize module cleanup with reload and remove. [1] cleanup remove ------- ------ auxiliary_driver_unregister(); devl_lock() auxiliary_device_delete(mlx5e_aux) device_lock(mlx5e_aux) devl_lock() device_lock(mlx5e_aux) Fixes: 912cebf420c2 ("net/mlx5e: Connect ethernet part to auxiliary bus") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3d5f2a4b1fed4..4e1b5757528a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2110,7 +2110,7 @@ static int __init mlx5_init(void) mlx5_core_verify_params(); mlx5_register_debugfs(); - err = pci_register_driver(&mlx5_core_driver); + err = mlx5e_init(); if (err) goto err_debug; @@ -2118,16 +2118,16 @@ static int __init mlx5_init(void) if (err) goto err_sf; - err = mlx5e_init(); + err = pci_register_driver(&mlx5_core_driver); if (err) - goto err_en; + goto err_pci; return 0; -err_en: +err_pci: mlx5_sf_driver_unregister(); err_sf: - pci_unregister_driver(&mlx5_core_driver); + mlx5e_cleanup(); err_debug: mlx5_unregister_debugfs(); return err; @@ -2135,9 +2135,9 @@ static int __init mlx5_init(void) static void __exit mlx5_cleanup(void) { - mlx5e_cleanup(); - mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); + mlx5_sf_driver_unregister(); + mlx5e_cleanup(); mlx5_unregister_debugfs(); } From c6aa9d3b43cd11ac13a8220368a3b0483c6751d4 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 6 Feb 2023 12:11:57 -0800 Subject: [PATCH 38/57] hv_netvsc: Allocate memory in netvsc_dma_map() with GFP_ATOMIC Memory allocations in the network transmit path must use GFP_ATOMIC so they won't sleep. Reported-by: Paolo Abeni Link: https://lore.kernel.org/lkml/8a4d08f94d3e6fe8b6da68440eaa89a088ad84f9.camel@redhat.com/ Fixes: 846da38de0e8 ("net: netvsc: Add Isolation VM support for netvsc driver") Cc: stable@vger.kernel.org Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1675714317-48577-1-git-send-email-mikelley@microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/hyperv/netvsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index e02d1e3ef672a..79f4e13620a46 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1034,7 +1034,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, packet->dma_range = kcalloc(page_count, sizeof(*packet->dma_range), - GFP_KERNEL); + GFP_ATOMIC); if (!packet->dma_range) return -ENOMEM; From 18a048370b06a3a521219e9e5b10bdc2178ef19c Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Mon, 6 Feb 2023 13:28:49 -0800 Subject: [PATCH 39/57] net: mana: Fix accessing freed irq affinity_hint After calling irq_set_affinity_and_hint(), the cpumask pointer is saved in desc->affinity_hint, and will be used later when reading /proc/irq//affinity_hint. So the cpumask variable needs to be persistent. Otherwise, we are accessing freed memory when reading the affinity_hint file. Also, need to clear affinity_hint before free_irq(), otherwise there is a one-time warning and stack trace during module unloading: [ 243.948687] WARNING: CPU: 10 PID: 1589 at kernel/irq/manage.c:1913 free_irq+0x318/0x360 ... [ 243.948753] Call Trace: [ 243.948754] [ 243.948760] mana_gd_remove_irqs+0x78/0xc0 [mana] [ 243.948767] mana_gd_remove+0x3e/0x80 [mana] [ 243.948773] pci_device_remove+0x3d/0xb0 [ 243.948778] device_remove+0x46/0x70 [ 243.948782] device_release_driver_internal+0x1fe/0x280 [ 243.948785] driver_detach+0x4e/0xa0 [ 243.948787] bus_remove_driver+0x70/0xf0 [ 243.948789] driver_unregister+0x35/0x60 [ 243.948792] pci_unregister_driver+0x44/0x90 [ 243.948794] mana_driver_exit+0x14/0x3fe [mana] [ 243.948800] __do_sys_delete_module.constprop.0+0x185/0x2f0 To fix the bug, use the persistent mask, cpumask_of(cpu#), and set affinity_hint to NULL before freeing the IRQ, as required by free_irq(). Cc: stable@vger.kernel.org Fixes: 71fa6887eeca ("net: mana: Assign interrupts to CPUs based on NUMA nodes") Signed-off-by: Haiyang Zhang Reviewed-by: Michael Kelley Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/1675718929-19565-1-git-send-email-haiyangz@microsoft.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/microsoft/mana/gdma_main.c | 37 ++++++------------- 1 file changed, 11 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index b144f2237748e..f9b8f372ec8a7 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1217,9 +1217,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) unsigned int max_queues_per_port = num_online_cpus(); struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_irq_context *gic; - unsigned int max_irqs; - u16 *cpus; - cpumask_var_t req_mask; + unsigned int max_irqs, cpu; int nvec, irq; int err, i = 0, j; @@ -1240,21 +1238,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) goto free_irq_vector; } - if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { - err = -ENOMEM; - goto free_irq; - } - - cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); - if (!cpus) { - err = -ENOMEM; - goto free_mask; - } - for (i = 0; i < nvec; i++) - cpus[i] = cpumask_local_spread(i, gc->numa_node); - for (i = 0; i < nvec; i++) { - cpumask_set_cpu(cpus[i], req_mask); gic = &gc->irq_contexts[i]; gic->handler = NULL; gic->arg = NULL; @@ -1269,17 +1253,16 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) irq = pci_irq_vector(pdev, i); if (irq < 0) { err = irq; - goto free_mask; + goto free_irq; } err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); if (err) - goto free_mask; - irq_set_affinity_and_hint(irq, req_mask); - cpumask_clear(req_mask); + goto free_irq; + + cpu = cpumask_local_spread(i, gc->numa_node); + irq_set_affinity_and_hint(irq, cpumask_of(cpu)); } - free_cpumask_var(req_mask); - kfree(cpus); err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); if (err) @@ -1290,13 +1273,12 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) return 0; -free_mask: - free_cpumask_var(req_mask); - kfree(cpus); free_irq: for (j = i - 1; j >= 0; j--) { irq = pci_irq_vector(pdev, j); gic = &gc->irq_contexts[j]; + + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } @@ -1324,6 +1306,9 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) continue; gic = &gc->irq_contexts[i]; + + /* Need to clear the hint before free_irq */ + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } From 9b275176270efd18f2f4e328b32be1bad34c4c0d Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Mon, 6 Feb 2023 15:58:18 -0800 Subject: [PATCH 40/57] igc: Add ndo_tx_timeout support On some platforms, 100/1000/2500 speeds seem to have sometimes problems reporting false positive tx unit hang during stressful UDP traffic. Likely other Intel drivers introduce responses to a tx hang. Update the 'tx hang' comparator with the comparison of the head and tail of ring pointers and restore the tx_timeout_factor to the previous value (one). This can be test by using netperf or iperf3 applications. Example: iperf3 -s -p 5001 iperf3 -c 192.168.0.2 --udp -p 5001 --time 600 -b 0 netserver -p 16604 netperf -H 192.168.0.2 -l 600 -p 16604 -t UDP_STREAM -- -m 64000 Fixes: b27b8dc77b5e ("igc: Increase timeout value for Speed 100/1000/2500") Signed-off-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230206235818.662384-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_main.c | 25 +++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 44b1740dc0983..1dd2a7fee8d46 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2942,7 +2942,9 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + (adapter->tx_timeout_factor * HZ)) && - !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) { + !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) && + (rd32(IGC_TDH(tx_ring->reg_idx)) != + readl(tx_ring->tail))) { /* detected Tx unit hang */ netdev_err(tx_ring->netdev, "Detected Tx Unit Hang\n" @@ -5068,6 +5070,24 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) return 0; } +/** + * igc_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: queue number that timed out + **/ +static void igc_tx_timeout(struct net_device *netdev, + unsigned int __always_unused txqueue) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + wr32(IGC_EICS, + (adapter->eims_enable_mask & ~adapter->eims_other)); +} + /** * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure @@ -5495,7 +5515,7 @@ static void igc_watchdog_task(struct work_struct *work) case SPEED_100: case SPEED_1000: case SPEED_2500: - adapter->tx_timeout_factor = 7; + adapter->tx_timeout_factor = 1; break; } @@ -6320,6 +6340,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, + .ndo_tx_timeout = igc_tx_timeout, .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, From 9cec2aaffe969f2a3e18b5ec105fc20bb908e475 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Feb 2023 16:18:32 +0300 Subject: [PATCH 41/57] net: sched: sch: Fix off by one in htb_activate_prios() The > needs be >= to prevent an out of bounds access. Fixes: de5ca4c3852f ("net: sched: sch: Bounds check priority") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/Y+D+KN18FQI2DKLq@kili Signed-off-by: Jakub Kicinski --- net/sched/sch_htb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cc28e41fb745c..92f2975b6a827 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -433,7 +433,7 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (m) { unsigned int prio = ffz(~m); - if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) break; m &= ~(1 << prio); From 21386e692613702502f7c982d81e0dfa86d25cfd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sun, 5 Feb 2023 20:53:31 +0300 Subject: [PATCH 42/57] net: ethernet: mtk_eth_soc: enable special tag when any MAC uses DSA MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The special tag is only enabled when the first MAC uses DSA. However, it must be enabled when any MAC uses DSA. Change the check accordingly. This fixes hardware DSA untagging not working on the second MAC of the MT7621 and MT7623 SoCs, and likely other SoCs too. Therefore, remove the check that disables hardware DSA untagging for the second MAC of the MT7621 and MT7623 SoCs. Fixes: a1f47752fd62 ("net: ethernet: mtk_eth_soc: disable hardware DSA untagging for second MAC") Co-developed-by: Richard van Schagen Signed-off-by: Richard van Schagen Signed-off-by: Arınç ÜNAL Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index d56eda6397a41..d73e69ed3e950 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3111,7 +3111,7 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config) val |= config; - if (!i && eth->netdev[0] && netdev_uses_dsa(eth->netdev[0])) + if (eth->netdev[i] && netdev_uses_dsa(eth->netdev[i])) val |= MTK_GDMA_SPECIAL_TAG; mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i)); @@ -3177,8 +3177,7 @@ static int mtk_open(struct net_device *dev) struct mtk_eth *eth = mac->hw; int i, err; - if ((mtk_uses_dsa(dev) && !eth->prog) && - !(mac->id == 1 && MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_TRGMII))) { + if (mtk_uses_dsa(dev) && !eth->prog) { for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { struct metadata_dst *md_dst = eth->dsa_meta[i]; @@ -3195,8 +3194,7 @@ static int mtk_open(struct net_device *dev) } } else { /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA, or the second MAC of the MT7621 and - * MT7623 SoCs is being used. + * one MAC does not use DSA. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; From c966153d120222cd4e85e1e1601584d7d4d91dcb Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 6 Feb 2023 22:47:03 +0200 Subject: [PATCH 43/57] net: ethernet: mtk_eth_soc: fix wrong parameters order in __xdp_rxq_info_reg() Parameters 'queue_index' and 'napi_id' are passed in a swapped order. Fix it here. Fixes: 23233e577ef9 ("net: ethernet: mtk_eth_soc: rely on page_pool for single page buffers") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index d73e69ed3e950..8f61e3b052c63 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1570,8 +1570,8 @@ static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth, if (IS_ERR(pp)) return pp; - err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, eth->rx_napi.napi_id, - id, PAGE_SIZE); + err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, id, + eth->rx_napi.napi_id, PAGE_SIZE); if (err < 0) goto err_free_pp; From c11204c78d6966c5bda6dd05c3ac5cbb193f93e3 Mon Sep 17 00:00:00 2001 From: Kevin Yang Date: Tue, 7 Feb 2023 02:08:20 +0000 Subject: [PATCH 44/57] txhash: fix sk->sk_txrehash default This code fix a bug that sk->sk_txrehash gets its default enable value from sysctl_txrehash only when the socket is a TCP listener. We should have sysctl_txrehash to set the default sk->sk_txrehash, no matter TCP, nor listerner/connector. Tested by following packetdrill: 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 socket(..., SOCK_DGRAM, IPPROTO_UDP) = 4 // SO_TXREHASH == 74, default to sysctl_txrehash == 1 +0 getsockopt(3, SOL_SOCKET, 74, [1], [4]) = 0 +0 getsockopt(4, SOL_SOCKET, 74, [1], [4]) = 0 Fixes: 26859240e4ee ("txhash: Add socket option to control TX hash rethink behavior") Signed-off-by: Kevin Yang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 3 ++- net/ipv4/af_inet.c | 1 + net/ipv4/inet_connection_sock.c | 3 --- net/ipv6/af_inet6.c | 1 + 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index f954d5893e799..6f27c24016fee 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1531,6 +1531,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname, ret = -EINVAL; break; } + if ((u8)val == SOCK_TXREHASH_DEFAULT) + val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -3451,7 +3453,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; - sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6c0ec27899431..cf11f10927e1a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -347,6 +347,7 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet->mc_loop = 1; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d1f8375793983..f2c43f67187db 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1225,9 +1225,6 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); - if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) - sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fee9163382c25..847934763868b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -222,6 +222,7 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. From 821de68c1f9c0236b0b9c10834cda900ae9b443c Mon Sep 17 00:00:00 2001 From: Yu Xiao Date: Tue, 7 Feb 2023 11:16:50 +0100 Subject: [PATCH 45/57] nfp: ethtool: fix the bug of setting unsupported port speed Unsupported port speed can be set and cause error. Now fixing it and return an error if setting unsupported speed. This fix depends on the following, which was included in v6.2-rc1: commit a61474c41e8c ("nfp: ethtool: support reporting link modes"). Fixes: 7c698737270f ("nfp: add support for .set_link_ksettings()") Signed-off-by: Yu Xiao Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 194 ++++++++++++++---- drivers/net/ethernet/netronome/nfp/nfp_port.h | 12 ++ 2 files changed, 170 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index a4a89ef3f18b4..cc97b3d00414e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -293,35 +293,131 @@ nfp_net_set_fec_link_mode(struct nfp_eth_table_port *eth_port, } } -static const u16 nfp_eth_media_table[] = { - [NFP_MEDIA_1000BASE_CX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_1000BASE_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_10GBASE_KX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - [NFP_MEDIA_10GBASE_CX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, - [NFP_MEDIA_10GBASE_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, - [NFP_MEDIA_10GBASE_ER] = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, - [NFP_MEDIA_25GBASE_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_KR_S] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_CR_S] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - [NFP_MEDIA_40GBASE_CR4] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, - [NFP_MEDIA_40GBASE_KR4] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, - [NFP_MEDIA_40GBASE_SR4] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, - [NFP_MEDIA_40GBASE_LR4] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, - [NFP_MEDIA_50GBASE_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, - [NFP_MEDIA_50GBASE_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, - [NFP_MEDIA_50GBASE_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, - [NFP_MEDIA_50GBASE_LR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_ER] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_100GBASE_KR4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_SR4] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR4] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, - [NFP_MEDIA_100GBASE_KP4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR10] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, +static const struct nfp_eth_media_link_mode { + u16 ethtool_link_mode; + u16 speed; +} nfp_eth_media_table[NFP_MEDIA_LINK_MODES_NUMBER] = { + [NFP_MEDIA_1000BASE_CX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_1000BASE_KX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_10GBASE_KX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_25GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_KR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_40GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_LR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_50GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_LR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_FR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_100GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_KP4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR10] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, +}; + +static const unsigned int nfp_eth_speed_map[NFP_SUP_SPEED_NUMBER] = { + [NFP_SPEED_1G] = SPEED_1000, + [NFP_SPEED_10G] = SPEED_10000, + [NFP_SPEED_25G] = SPEED_25000, + [NFP_SPEED_40G] = SPEED_40000, + [NFP_SPEED_50G] = SPEED_50000, + [NFP_SPEED_100G] = SPEED_100000, }; static void nfp_add_media_link_mode(struct nfp_port *port, @@ -334,8 +430,12 @@ static void nfp_add_media_link_mode(struct nfp_port *port, }; struct nfp_cpp *cpp = port->app->cpp; - if (nfp_eth_read_media(cpp, ðm)) + if (nfp_eth_read_media(cpp, ðm)) { + bitmap_fill(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); return; + } + + bitmap_zero(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); for (u32 i = 0; i < 2; i++) { supported_modes[i] = le64_to_cpu(ethm.supported_modes[i]); @@ -344,20 +444,26 @@ static void nfp_add_media_link_mode(struct nfp_port *port, for (u32 i = 0; i < NFP_MEDIA_LINK_MODES_NUMBER; i++) { if (i < 64) { - if (supported_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[0] & BIT_ULL(i)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } else { - if (supported_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[1] & BIT_ULL(i - 64)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } } @@ -468,6 +574,22 @@ nfp_net_set_link_ksettings(struct net_device *netdev, if (cmd->base.speed != SPEED_UNKNOWN) { u32 speed = cmd->base.speed / eth_port->lanes; + bool is_supported = false; + + for (u32 i = 0; i < NFP_SUP_SPEED_NUMBER; i++) { + if (cmd->base.speed == nfp_eth_speed_map[i] && + test_bit(i, port->speed_bitmap)) { + is_supported = true; + break; + } + } + + if (!is_supported) { + netdev_err(netdev, "Speed %u is not supported.\n", + cmd->base.speed); + err = -EINVAL; + goto err_bad_set; + } if (req_aneg) { netdev_err(netdev, "Speed changing is not allowed when working on autoneg mode.\n"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index f8cd157ca1d79..9c04f9f0e2c90 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -38,6 +38,16 @@ enum nfp_port_flags { NFP_PORT_CHANGED = 0, }; +enum { + NFP_SPEED_1G, + NFP_SPEED_10G, + NFP_SPEED_25G, + NFP_SPEED_40G, + NFP_SPEED_50G, + NFP_SPEED_100G, + NFP_SUP_SPEED_NUMBER +}; + /** * struct nfp_port - structure representing NFP port * @netdev: backpointer to associated netdev @@ -52,6 +62,7 @@ enum nfp_port_flags { * @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change * @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry * @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available + * @speed_bitmap: for %NFP_PORT_PHYS_PORT supported speed bitmap * @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3) * @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id * @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC @@ -78,6 +89,7 @@ struct nfp_port { bool eth_forced; struct nfp_eth_table_port *eth_port; u8 __iomem *eth_stats; + DECLARE_BITMAP(speed_bitmap, NFP_SUP_SPEED_NUMBER); }; /* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */ struct { From 1a3245fe0cf84e630598da4ab110a5f8a2d6730d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 7 Feb 2023 12:30:27 +0200 Subject: [PATCH 46/57] net: ethernet: mtk_eth_soc: fix DSA TX tag hwaccel for switch port 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Arınç reports that on his MT7621AT Unielec U7621-06 board and MT7623NI Bananapi BPI-R2, packets received by the CPU over mt7530 switch port 0 (of which this driver acts as the DSA master) are not processed correctly by software. More precisely, they arrive without a DSA tag (in packet or in the hwaccel area - skb_metadata_dst()), so DSA cannot demux them towards the switch's interface for port 0. Traffic from other ports receives a skb_metadata_dst() with the correct port and is demuxed properly. Looking at mtk_poll_rx(), it becomes apparent that this driver uses the skb vlan hwaccel area: union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; as a temporary storage for the VLAN hwaccel tag, or the DSA hwaccel tag. If this is a DSA master it's a DSA hwaccel tag, and finally clears up the skb VLAN hwaccel header. I'm guessing that the problem is the (mis)use of API. skb_vlan_tag_present() looks like this: #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) So if both vlan_proto and vlan_tci are zeroes, skb_vlan_tag_present() returns precisely false. I don't know for sure what is the format of the DSA hwaccel tag, but I surely know that lowermost 3 bits of vlan_proto are 0 when receiving from port 0: unsigned int port = vlan_proto & GENMASK(2, 0); If the RX descriptor has no other bits set to non-zero values in RX_DMA_VTAG, then the call to __vlan_hwaccel_put_tag() will not, in fact, make the subsequent skb_vlan_tag_present() return true, because it's implemented like this: static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; } What we need to do to fix this problem (assuming this is the problem) is to stop using skb->vlan_all as temporary storage for driver affairs, and just create some local variables that serve the same purpose, but hopefully better. Instead of calling skb_vlan_tag_present(), let's look at a boolean has_hwaccel_tag which we set to true when the RX DMA descriptors have something. Disambiguate based on netdev_uses_dsa() whether this is a VLAN or DSA hwaccel tag, and only call __vlan_hwaccel_put_tag() if we're certain it's a VLAN tag. Arınç confirms that the treatment works, so this validates the assumption. Link: https://lore.kernel.org/netdev/704f3a72-fc9e-714a-db54-272e17612637@arinc9.com/ Fixes: 2d7605a72906 ("net: ethernet: mtk_eth_soc: enable hardware DSA untagging") Reported-by: Arınç ÜNAL Tested-by: Arınç ÜNAL Signed-off-by: Vladimir Oltean Reviewed-by: Felix Fietkau Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 24 ++++++++++++--------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8f61e3b052c63..e3123723522e3 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1870,7 +1870,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, while (done < budget) { unsigned int pktlen, *rxdcsum; + bool has_hwaccel_tag = false; struct net_device *netdev; + u16 vlan_proto, vlan_tci; dma_addr_t dma_addr; u32 hash, reason; int mac = 0; @@ -2010,27 +2012,29 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - if (trxd.rxd3 & RX_DMA_VTAG_V2) - __vlan_hwaccel_put_tag(skb, - htons(RX_DMA_VPID(trxd.rxd4)), - RX_DMA_VID(trxd.rxd4)); + if (trxd.rxd3 & RX_DMA_VTAG_V2) { + vlan_proto = RX_DMA_VPID(trxd.rxd4); + vlan_tci = RX_DMA_VID(trxd.rxd4); + has_hwaccel_tag = true; + } } else if (trxd.rxd2 & RX_DMA_VTAG) { - __vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)), - RX_DMA_VID(trxd.rxd3)); + vlan_proto = RX_DMA_VPID(trxd.rxd3); + vlan_tci = RX_DMA_VID(trxd.rxd3); + has_hwaccel_tag = true; } } /* When using VLAN untagging in combination with DSA, the * hardware treats the MTK special tag as a VLAN and untags it. */ - if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) { - unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0); + if (has_hwaccel_tag && netdev_uses_dsa(netdev)) { + unsigned int port = vlan_proto & GENMASK(2, 0); if (port < ARRAY_SIZE(eth->dsa_meta) && eth->dsa_meta[port]) skb_dst_set_noref(skb, ð->dsa_meta[port]->dst); - - __vlan_hwaccel_clear_tag(skb); + } else if (has_hwaccel_tag) { + __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci); } skb_record_rx_queue(skb, 0); From d4e85922e3e7ef2071f91f65e61629b60f3a9cf4 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 7 Feb 2023 14:04:13 +0100 Subject: [PATCH 47/57] mptcp: do not wait for bare sockets' timeout If the peer closes all the existing subflows for a given mptcp socket and later the application closes it, the current implementation let it survive until the timewait timeout expires. While the above is allowed by the protocol specification it consumes resources for almost no reason and additionally causes sporadic self-tests failures. Let's move the mptcp socket to the TCP_CLOSE state when there are no alive subflows at close time, so that the allocated resources will be freed immediately. Fixes: e16163b6e2b7 ("mptcp: refactor shutdown and close") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8cd6cc67c2c5c..bc6c1f62a6905 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2897,6 +2897,7 @@ bool __mptcp_close(struct sock *sk, long timeout) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; + int subflows_alive = 0; sk->sk_shutdown = SHUTDOWN_MASK; @@ -2922,6 +2923,8 @@ bool __mptcp_close(struct sock *sk, long timeout) struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + subflows_alive += ssk->sk_state != TCP_CLOSE; + /* since the close timeout takes precedence on the fail one, * cancel the latter */ @@ -2937,6 +2940,12 @@ bool __mptcp_close(struct sock *sk, long timeout) } sock_orphan(sk); + /* all the subflows are closed, only timeout can change the msk + * state, let's not keep resources busy for no reasons + */ + if (subflows_alive == 0) + inet_sk_state_store(sk, TCP_CLOSE); + sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) From 21e43569685de4ad773fb060c11a15f3fd5e7ac4 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 7 Feb 2023 14:04:14 +0100 Subject: [PATCH 48/57] mptcp: fix locking for setsockopt corner-case We need to call the __mptcp_nmpc_socket(), and later subflow socket access under the msk socket lock, or e.g. a racing connect() could change the socket status under the hood, with unexpected results. Fixes: 54635bd04701 ("mptcp: add TCP_FASTOPEN_CONNECT socket option") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/sockopt.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index d4b1e6ec1b361..7f2c3727ab230 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct sock *sk = (struct sock *)msk; struct socket *sock; + int ret = -EINVAL; /* Limit to first subflow, before the connection establishment */ + lock_sock(sk); sock = __mptcp_nmpc_socket(msk); if (!sock) - return -EINVAL; + goto unlock; - return tcp_setsockopt(sock->sk, level, optname, optval, optlen); + ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); + +unlock: + release_sock(sk); + return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, From ad2171009d968104ccda9dc517f5a3ba891515db Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 7 Feb 2023 14:04:15 +0100 Subject: [PATCH 49/57] mptcp: fix locking for in-kernel listener creation For consistency, in mptcp_pm_nl_create_listen_socket(), we need to call the __mptcp_nmpc_socket() under the msk socket lock. Note that as a side effect, mptcp_subflow_create_socket() needs a 'nested' lockdep annotation, as it will acquire the subflow (kernel) socket lock under the in-kernel listener msk socket lock. The current lack of locking is almost harmless, because the relevant socket is not exposed to the user space, but in future we will add more complexity to the mentioned helper, let's play safe. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/pm_netlink.c | 10 ++++++---- net/mptcp/subflow.c | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2ea7eae43bdb1..10fe9771a852a 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -998,8 +998,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, { int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct mptcp_sock *msk; struct socket *ssock; + struct sock *newsk; int backlog = 1024; int err; @@ -1008,11 +1008,13 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; - msk = mptcp_sk(entry->lsk->sk); - if (!msk) + newsk = entry->lsk->sk; + if (!newsk) return -EINVAL; - ssock = __mptcp_nmpc_socket(msk); + lock_sock(newsk); + ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + release_sock(newsk); if (!ssock) return -EINVAL; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ec54413fb31f7..a3e5026bee5bf 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1679,7 +1679,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, if (err) return err; - lock_sock(sf->sk); + lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); From 1249db44a102d9d3541ed7798d4b01ffdcf03524 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 7 Feb 2023 14:04:16 +0100 Subject: [PATCH 50/57] mptcp: be careful on subflow status propagation on errors Currently the subflow error report callback unconditionally propagates the fallback subflow status to the owning msk. If the msk is already orphaned, the above prevents the code from correctly tracking the msk moving to the TCP_CLOSE state and doing the appropriate cleanup. All the above causes increasing memory usage over time and sporadic self-tests failures. There is a great deal of infrastructure trying to propagate correctly the fallback subflow status to the owning mptcp socket, e.g. via mptcp_subflow_eof() and subflow_sched_work_if_closed(): in the error propagation path we need only to cope with unorphaned sockets. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/339 Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a3e5026bee5bf..32904c76c6a17 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1399,6 +1399,7 @@ void __mptcp_error_report(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err = sock_error(ssk); + int ssk_state; if (!err) continue; @@ -1409,7 +1410,14 @@ void __mptcp_error_report(struct sock *sk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) continue; - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); sk->sk_err = -err; /* This barrier is coupled with smp_rmb() in mptcp_poll() */ From a635a8c3df66ab68dc088c08a4e9e955e22c0e64 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 7 Feb 2023 14:04:17 +0100 Subject: [PATCH 51/57] selftests: mptcp: allow more slack for slow test-case A test-case is frequently failing on some extremely slow VMs. The mptcp transfer completes before the script is able to do all the required PM manipulation. Address the issue in the simplest possible way, making the transfer even more slow. Additionally dump more info in case of failures, to help debugging similar problems in the future and init dump_stats var. Fixes: e274f7154008 ("selftests: mptcp: add subflow limits test-cases") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/323 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index d11d3d5666086..f8a969300ef4c 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1694,6 +1694,7 @@ chk_subflow_nr() local subflow_nr=$3 local cnt1 local cnt2 + local dump_stats if [ -n "${need_title}" ]; then printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" @@ -1711,7 +1712,12 @@ chk_subflow_nr() echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) + if [ "${dump_stats}" = 1 ]; then + ss -N $ns1 -tOni + ss -N $ns1 -tOni | grep token + ip -n $ns1 mptcp endpoint + dump_stats + fi } chk_link_usage() @@ -3069,7 +3075,7 @@ endpoint_tests() pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 & wait_mpj $ns2 pm_nl_del_endpoint $ns2 2 10.0.2.2 From 070d6dafacbaa9d1f2e4e3edc263853d194af15e Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Tue, 7 Feb 2023 14:04:18 +0100 Subject: [PATCH 52/57] selftests: mptcp: stop tests earlier These 'endpoint' tests from 'mptcp_join.sh' selftest start a transfer in the background and check the status during this transfer. Once the expected events have been recorded, there is no reason to wait for the data transfer to finish. It can be stopped earlier to reduce the execution time by more than half. For these tests, the exchanged data were not verified. Errors, if any, were ignored but that's fine, plenty of other tests are looking at that. It is then OK to mute stderr now that we are sure errors will be printed (and still ignored) because the transfer is stopped before the end. Fixes: e274f7154008 ("selftests: mptcp: add subflow limits test-cases") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f8a969300ef4c..079f8f46849de 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -498,6 +498,12 @@ kill_events_pids() kill_wait $evts_ns2_pid } +kill_tests_wait() +{ + kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) + wait +} + pm_nl_set_limits() { local ns=$1 @@ -3055,7 +3061,7 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & wait_mpj $ns1 pm_nl_check_endpoint 1 "creation" \ @@ -3068,14 +3074,14 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint 0 "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - wait + kill_tests_wait fi if reset "delete and re-add"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 & + run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & wait_mpj $ns2 pm_nl_del_endpoint $ns2 2 10.0.2.2 @@ -3085,7 +3091,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "" "after re-add" 2 - wait + kill_tests_wait fi } From b963d9d5b9437a6b99504987310f98537c9e77d4 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 7 Feb 2023 16:18:19 +0200 Subject: [PATCH 53/57] selftests: Fix failing VXLAN VNI filtering test iproute2 does not recognize the "group6" and "remote6" keywords. Fix by using "group" and "remote" instead. Before: # ./test_vxlan_vnifiltering.sh [...] Tests passed: 25 Tests failed: 2 After: # ./test_vxlan_vnifiltering.sh [...] Tests passed: 27 Tests failed: 0 Fixes: 3edf5f66c12a ("selftests: add new tests for vxlan vnifiltering") Signed-off-by: Ido Schimmel Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230207141819.256689-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- .../selftests/net/test_vxlan_vnifiltering.sh | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 704997ffc2449..8c3ac0a725451 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -293,19 +293,11 @@ setup-vm() { elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then # Add per vni group config with 'bridge vni' api if [ -n "$group" ]; then - if [ "$family" == "v4" ]; then - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group - fi - else - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group - fi - fi + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group + fi fi fi done From 363d7c2298e730083df942446534825654d65c5e Mon Sep 17 00:00:00 2001 From: Jiawen Wu Date: Wed, 8 Feb 2023 10:30:35 +0800 Subject: [PATCH 54/57] net: txgbe: Update support email address Update new email address for Wangxun 10Gb NIC support team. Signed-off-by: Jiawen Wu Link: https://lore.kernel.org/r/20230208023035.3371250-1-jiawenwu@trustnetic.com Signed-off-by: Jakub Kicinski --- .../networking/device_drivers/ethernet/wangxun/txgbe.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst index eaa87dbe8848d..d052ef40fe367 100644 --- a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst +++ b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst @@ -16,5 +16,5 @@ Contents Support ======= -If you got any problem, contact Wangxun support team via support@trustnetic.com +If you got any problem, contact Wangxun support team via nic-support@net-swift.com and Cc: netdev. From f753a68980cf4b59a80fe677619da2b1804f526d Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Tue, 7 Feb 2023 18:26:34 +0000 Subject: [PATCH 55/57] rds: rds_rm_zerocopy_callback() use list_first_entry() rds_rm_zerocopy_callback() uses list_entry() on the head of a list causing a type confusion. Use list_first_entry() to actually access the first element of the rs_zcookie_queue list. Fixes: 9426bbc6de99 ("rds: use list structure to track information for zerocopy completion notification") Reviewed-by: Willem de Bruijn Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230202-rds-zerocopy-v3-1-83b0df974f9a@diag.uniroma1.it Signed-off-by: Paolo Abeni --- net/rds/message.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/rds/message.c b/net/rds/message.c index b47e4f0a16393..c19c935612278 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ From 2fcde9fe258ec8b88d41def38e43ca4da32c0a9a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 7 Feb 2023 20:31:17 +0200 Subject: [PATCH 56/57] net: mscc: ocelot: fix all IPv6 getting trapped to CPU when PTP timestamping is used While running this selftest which usually passes: ~/selftests/drivers/net/dsa# ./local_termination.sh eno0 swp0 TEST: swp0: Unicast IPv4 to primary MAC address [ OK ] TEST: swp0: Unicast IPv4 to macvlan MAC address [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address, promisc [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address, allmulti [ OK ] TEST: swp0: Multicast IPv4 to joined group [ OK ] TEST: swp0: Multicast IPv4 to unknown group [ OK ] TEST: swp0: Multicast IPv4 to unknown group, promisc [ OK ] TEST: swp0: Multicast IPv4 to unknown group, allmulti [ OK ] TEST: swp0: Multicast IPv6 to joined group [ OK ] TEST: swp0: Multicast IPv6 to unknown group [ OK ] TEST: swp0: Multicast IPv6 to unknown group, promisc [ OK ] TEST: swp0: Multicast IPv6 to unknown group, allmulti [ OK ] if I start PTP timestamping then run it again (debug prints added by me), the unknown IPv6 MC traffic is seen by the CPU port even when it should have been dropped: ~/selftests/drivers/net/dsa# ptp4l -i swp0 -2 -P -m ptp4l[225.410]: selected /dev/ptp1 as PTP clock [ 225.445746] mscc_felix 0000:00:00.5: ocelot_l2_ptp_trap_add: port 0 adding L2 PTP trap [ 225.453815] mscc_felix 0000:00:00.5: ocelot_ipv4_ptp_trap_add: port 0 adding IPv4 PTP event trap [ 225.462703] mscc_felix 0000:00:00.5: ocelot_ipv4_ptp_trap_add: port 0 adding IPv4 PTP general trap [ 225.471768] mscc_felix 0000:00:00.5: ocelot_ipv6_ptp_trap_add: port 0 adding IPv6 PTP event trap [ 225.480651] mscc_felix 0000:00:00.5: ocelot_ipv6_ptp_trap_add: port 0 adding IPv6 PTP general trap ptp4l[225.488]: port 1: INITIALIZING to LISTENING on INIT_COMPLETE ptp4l[225.488]: port 0: INITIALIZING to LISTENING on INIT_COMPLETE ^C ~/selftests/drivers/net/dsa# ./local_termination.sh eno0 swp0 TEST: swp0: Unicast IPv4 to primary MAC address [ OK ] TEST: swp0: Unicast IPv4 to macvlan MAC address [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address, promisc [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address, allmulti [ OK ] TEST: swp0: Multicast IPv4 to joined group [ OK ] TEST: swp0: Multicast IPv4 to unknown group [ OK ] TEST: swp0: Multicast IPv4 to unknown group, promisc [ OK ] TEST: swp0: Multicast IPv4 to unknown group, allmulti [ OK ] TEST: swp0: Multicast IPv6 to joined group [ OK ] TEST: swp0: Multicast IPv6 to unknown group [FAIL] reception succeeded, but should have failed TEST: swp0: Multicast IPv6 to unknown group, promisc [ OK ] TEST: swp0: Multicast IPv6 to unknown group, allmulti [ OK ] The PGID_MCIPV6 is configured correctly to not flood to the CPU, I checked that. Furthermore, when I disable back PTP RX timestamping (ptp4l doesn't do that when it exists), packets are RX filtered again as they should be: ~/selftests/drivers/net/dsa# hwstamp_ctl -i swp0 -r 0 [ 218.202854] mscc_felix 0000:00:00.5: ocelot_l2_ptp_trap_del: port 0 removing L2 PTP trap [ 218.212656] mscc_felix 0000:00:00.5: ocelot_ipv4_ptp_trap_del: port 0 removing IPv4 PTP event trap [ 218.222975] mscc_felix 0000:00:00.5: ocelot_ipv4_ptp_trap_del: port 0 removing IPv4 PTP general trap [ 218.233133] mscc_felix 0000:00:00.5: ocelot_ipv6_ptp_trap_del: port 0 removing IPv6 PTP event trap [ 218.242251] mscc_felix 0000:00:00.5: ocelot_ipv6_ptp_trap_del: port 0 removing IPv6 PTP general trap current settings: tx_type 1 rx_filter 12 new settings: tx_type 1 rx_filter 0 ~/selftests/drivers/net/dsa# ./local_termination.sh eno0 swp0 TEST: swp0: Unicast IPv4 to primary MAC address [ OK ] TEST: swp0: Unicast IPv4 to macvlan MAC address [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address, promisc [ OK ] TEST: swp0: Unicast IPv4 to unknown MAC address, allmulti [ OK ] TEST: swp0: Multicast IPv4 to joined group [ OK ] TEST: swp0: Multicast IPv4 to unknown group [ OK ] TEST: swp0: Multicast IPv4 to unknown group, promisc [ OK ] TEST: swp0: Multicast IPv4 to unknown group, allmulti [ OK ] TEST: swp0: Multicast IPv6 to joined group [ OK ] TEST: swp0: Multicast IPv6 to unknown group [ OK ] TEST: swp0: Multicast IPv6 to unknown group, promisc [ OK ] TEST: swp0: Multicast IPv6 to unknown group, allmulti [ OK ] So it's clear that something in the PTP RX trapping logic went wrong. Looking a bit at the code, I can see that there are 4 typos, which populate "ipv4" VCAP IS2 key filter fields for IPv6 keys. VCAP IS2 keys of type OCELOT_VCAP_KEY_IPV4 and OCELOT_VCAP_KEY_IPV6 are handled by is2_entry_set(). OCELOT_VCAP_KEY_IPV4 looks at &filter->key.ipv4, and OCELOT_VCAP_KEY_IPV6 at &filter->key.ipv6. Simply put, when we populate the wrong key field, &filter->key.ipv6 fields "proto.mask" and "proto.value" remain all zeroes (or "don't care"). So is2_entry_set() will enter the "else" of this "if" condition: if (msk == 0xff && (val == IPPROTO_TCP || val == IPPROTO_UDP)) and proceed to ignore the "proto" field. The resulting rule will match on all IPv6 traffic, trapping it to the CPU. This is the reason why the local_termination.sh selftest sees it, because control traps are stronger than the PGID_MCIPV6 used for flooding (from the forwarding data path). But the problem is in fact much deeper. We trap all IPv6 traffic to the CPU, but if we're bridged, we set skb->offload_fwd_mark = 1, so software forwarding will not take place and IPv6 traffic will never reach its destination. The fix is simple - correct the typos. I was intentionally inaccurate in the commit message about the breakage occurring when any PTP timestamping is enabled. In fact it only happens when L4 timestamping is requested (HWTSTAMP_FILTER_PTP_V2_EVENT or HWTSTAMP_FILTER_PTP_V2_L4_EVENT). But ptp4l requests a larger RX timestamping filter than it needs for "-2": HWTSTAMP_FILTER_PTP_V2_EVENT. I wanted people skimming through git logs to not think that the bug doesn't affect them because they only use ptp4l in L2 mode. Fixes: 96ca08c05838 ("net: mscc: ocelot: set up traps for PTP packets") Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230207183117.1745754-1-vladimir.oltean@nxp.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mscc/ocelot_ptp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index 1a82f10c88539..2180ae94c7447 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -335,8 +335,8 @@ static void ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_EV_PORT; trap->key.ipv6.dport.mask = 0xffff; } @@ -355,8 +355,8 @@ static void ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_GEN_PORT; trap->key.ipv6.dport.mask = 0xffff; } From 3a082086aa200852545cf15159213582c0c80eba Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 8 Feb 2023 11:21:10 +0800 Subject: [PATCH 57/57] selftests: forwarding: lib: quote the sysctl values When set/restore sysctl value, we should quote the value as some keys may have multi values, e.g. net.ipv4.ping_group_range Fixes: f5ae57784ba8 ("selftests: forwarding: lib: Add sysctl_set(), sysctl_restore()") Signed-off-by: Hangbin Liu Reviewed-by: Petr Machata Link: https://lore.kernel.org/r/20230208032110.879205-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/forwarding/lib.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1c4f866de7d7d..3d8e4ebda1b64 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -914,14 +914,14 @@ sysctl_set() local value=$1; shift SYSCTL_ORIG[$key]=$(sysctl -n $key) - sysctl -qw $key=$value + sysctl -qw $key="$value" } sysctl_restore() { local key=$1; shift - sysctl -qw $key=${SYSCTL_ORIG["$key"]} + sysctl -qw $key="${SYSCTL_ORIG[$key]}" } forwarding_enable()