From 1696ec8654016dad3b1baf6c024303e584400453 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Aug 2023 10:40:29 -0700 Subject: mISDN: Update parameter type of dsp_cmx_send() When booting a kernel with CONFIG_MISDN_DSP=y and CONFIG_CFI_CLANG=y, there is a failure when dsp_cmx_send() is called indirectly from call_timer_fn(): [ 0.371412] CFI failure at call_timer_fn+0x2f/0x150 (target: dsp_cmx_send+0x0/0x530; expected type: 0x92ada1e9) The function pointer prototype that call_timer_fn() expects is void (*fn)(struct timer_list *) whereas dsp_cmx_send() has a parameter type of 'void *', which causes the control flow integrity checks to fail because the parameter types do not match. Change dsp_cmx_send()'s parameter type to be 'struct timer_list' to match the expected prototype. The argument is unused anyways, so this has no functional change, aside from avoiding the CFI failure. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202308020936.58787e6c-oliver.sang@intel.com Signed-off-by: Nathan Chancellor Reviewed-by: Sami Tolvanen Reviewed-by: Kees Cook Fixes: e313ac12eb13 ("mISDN: Convert timers to use timer_setup()") Link: https://lore.kernel.org/r/20230802-fix-dsp_cmx_send-cfi-failure-v1-1-2f2e79b0178d@kernel.org Signed-off-by: Jakub Kicinski --- drivers/isdn/mISDN/dsp.h | 2 +- drivers/isdn/mISDN/dsp_cmx.c | 2 +- drivers/isdn/mISDN/dsp_core.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fa09d511a8ed..baf31258f5c9 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -247,7 +247,7 @@ extern void dsp_cmx_hardware(struct dsp_conf *conf, struct dsp *dsp); extern int dsp_cmx_conf(struct dsp *dsp, u32 conf_id); extern void dsp_cmx_receive(struct dsp *dsp, struct sk_buff *skb); extern void dsp_cmx_hdlc(struct dsp *dsp, struct sk_buff *skb); -extern void dsp_cmx_send(void *arg); +extern void dsp_cmx_send(struct timer_list *arg); extern void dsp_cmx_transmit(struct dsp *dsp, struct sk_buff *skb); extern int dsp_cmx_del_conf_member(struct dsp *dsp); extern int dsp_cmx_del_conf(struct dsp_conf *conf); diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 357b87592eb4..61cb45c5d0d8 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -1614,7 +1614,7 @@ static u16 dsp_count; /* last sample count */ static int dsp_count_valid; /* if we have last sample count */ void -dsp_cmx_send(void *arg) +dsp_cmx_send(struct timer_list *arg) { struct dsp_conf *conf; struct dsp_conf_member *member; diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 386084530c2f..fae95f166688 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1195,7 +1195,7 @@ static int __init dsp_init(void) } /* set sample timer */ - timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); + timer_setup(&dsp_spl_tl, dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); -- cgit v1.2.3 From e58f30246c35c126c7571065b33bee4b3b1d2ef8 Mon Sep 17 00:00:00 2001 From: Li Yang Date: Wed, 2 Aug 2023 14:13:46 -0500 Subject: net: phy: at803x: fix the wol setting functions In commit 7beecaf7d507 ("net: phy: at803x: improve the WOL feature"), it seems not correct to use a wol_en bit in a 1588 Control Register which is only available on AR8031/AR8033(share the same phy_id) to determine if WoL is enabled. Change it back to use AT803X_INTR_ENABLE_WOL for determining the WoL status which is applicable on all chips supporting wol. Also update the at803x_set_wol() function to only update the 1588 register on chips having it. After this change, disabling wol at probe from commit d7cd5e06c9dd ("net: phy: at803x: disable WOL at probe") is no longer needed. Change it to just disable the WoL bit in 1588 register for AR8031/AR8033 to be aligned with AT803X_INTR_ENABLE_WOL in probe. Fixes: 7beecaf7d507 ("net: phy: at803x: improve the WOL feature") Signed-off-by: Li Yang Reviewed-by: Viorel Suman Reviewed-by: Wei Fang Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/at803x.c | 45 +++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index c1f307d90518..9c2c2e2ee94b 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -459,21 +459,27 @@ static int at803x_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i], mac[(i * 2) + 1] | (mac[(i * 2)] << 8)); - /* Enable WOL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - if (ret) - return ret; + /* Enable WOL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + if (ret) + return ret; + } /* Enable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL); if (ret) return ret; } else { - /* Disable WoL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - if (ret) - return ret; + /* Disable WoL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; + } /* Disable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0); if (ret) @@ -508,11 +514,11 @@ static void at803x_get_wol(struct phy_device *phydev, wol->supported = WAKE_MAGIC; wol->wolopts = 0; - value = phy_read_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL); + value = phy_read(phydev, AT803X_INTR_ENABLE); if (value < 0) return; - if (value & AT803X_WOL_EN) + if (value & AT803X_INTR_ENABLE_WOL) wol->wolopts |= WAKE_MAGIC; } @@ -858,9 +864,6 @@ static int at803x_probe(struct phy_device *phydev) if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; - struct ethtool_wolinfo wol = { - .wolopts = 0, - }; if (ccr < 0) return ccr; @@ -877,12 +880,14 @@ static int at803x_probe(struct phy_device *phydev) break; } - /* Disable WOL by default */ - ret = at803x_set_wol(phydev, &wol); - if (ret < 0) { - phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); + /* Disable WoL in 1588 register which is enabled + * by default + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) return ret; - } } return 0; -- cgit v1.2.3 From d7791cec2304aea22eb2ada944e4d467302f5bfe Mon Sep 17 00:00:00 2001 From: Li Yang Date: Wed, 2 Aug 2023 14:13:47 -0500 Subject: net: phy: at803x: remove set/get wol callbacks for AR8032 Since the AR8032 part does not support wol, remove related callbacks from it. Fixes: 5800091a2061 ("net: phy: at803x: add support for AR8032 PHY") Signed-off-by: Li Yang Cc: David Bauer Signed-off-by: David S. Miller --- drivers/net/phy/at803x.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 9c2c2e2ee94b..8a77ec33b417 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -2064,8 +2064,6 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, - .set_wol = at803x_set_wol, - .get_wol = at803x_get_wol, .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ -- cgit v1.2.3 From 17ebf8a4c38b5481c29623f5e003fdf7583947f9 Mon Sep 17 00:00:00 2001 From: Xiang Yang Date: Thu, 3 Aug 2023 07:24:38 +0000 Subject: mptcp: fix the incorrect judgment for msk->cb_flags Coccicheck reports the error below: net/mptcp/protocol.c:3330:15-28: ERROR: test of a variable/field address Since the address of msk->cb_flags is used in __test_and_clear_bit, the address should not be NULL. The judgment for if (unlikely(msk->cb_flags)) will always be true, we should check the real value of msk->cb_flags here. Fixes: 65a569b03ca8 ("mptcp: optimize release_cb for the common case") Signed-off-by: Xiang Yang Reviewed-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803072438.1847500-1-xiangyang3@huawei.com Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3317d1cca156..be5f6f4b94c7 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3328,7 +3328,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ -- cgit v1.2.3 From a94c16a2fda010866b8858a386a8bfbeba4f72c5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 3 Aug 2023 16:42:53 +0300 Subject: net: dsa: ocelot: call dsa_tag_8021q_unregister() under rtnl_lock() on driver remove When the tagging protocol in current use is "ocelot-8021q" and we unbind the driver, we see this splat: $ echo '0000:00:00.2' > /sys/bus/pci/drivers/fsl_enetc/unbind mscc_felix 0000:00:00.5 swp0: left promiscuous mode sja1105 spi2.0: Link is Down DSA: tree 1 torn down mscc_felix 0000:00:00.5 swp2: left promiscuous mode sja1105 spi2.2: Link is Down DSA: tree 3 torn down fsl_enetc 0000:00:00.2 eno2: left promiscuous mode mscc_felix 0000:00:00.5: Link is Down ------------[ cut here ]------------ RTNL: assertion failed at net/dsa/tag_8021q.c (409) WARNING: CPU: 1 PID: 329 at net/dsa/tag_8021q.c:409 dsa_tag_8021q_unregister+0x12c/0x1a0 Modules linked in: CPU: 1 PID: 329 Comm: bash Not tainted 6.5.0-rc3+ #771 pc : dsa_tag_8021q_unregister+0x12c/0x1a0 lr : dsa_tag_8021q_unregister+0x12c/0x1a0 Call trace: dsa_tag_8021q_unregister+0x12c/0x1a0 felix_tag_8021q_teardown+0x130/0x150 felix_teardown+0x3c/0xd8 dsa_tree_teardown_switches+0xbc/0xe0 dsa_unregister_switch+0x168/0x260 felix_pci_remove+0x30/0x60 pci_device_remove+0x4c/0x100 device_release_driver_internal+0x188/0x288 device_links_unbind_consumers+0xfc/0x138 device_release_driver_internal+0xe0/0x288 device_driver_detach+0x24/0x38 unbind_store+0xd8/0x108 drv_attr_store+0x30/0x50 ---[ end trace 0000000000000000 ]--- ------------[ cut here ]------------ RTNL: assertion failed at net/8021q/vlan_core.c (376) WARNING: CPU: 1 PID: 329 at net/8021q/vlan_core.c:376 vlan_vid_del+0x1b8/0x1f0 CPU: 1 PID: 329 Comm: bash Tainted: G W 6.5.0-rc3+ #771 pc : vlan_vid_del+0x1b8/0x1f0 lr : vlan_vid_del+0x1b8/0x1f0 dsa_tag_8021q_unregister+0x8c/0x1a0 felix_tag_8021q_teardown+0x130/0x150 felix_teardown+0x3c/0xd8 dsa_tree_teardown_switches+0xbc/0xe0 dsa_unregister_switch+0x168/0x260 felix_pci_remove+0x30/0x60 pci_device_remove+0x4c/0x100 device_release_driver_internal+0x188/0x288 device_links_unbind_consumers+0xfc/0x138 device_release_driver_internal+0xe0/0x288 device_driver_detach+0x24/0x38 unbind_store+0xd8/0x108 drv_attr_store+0x30/0x50 DSA: tree 0 torn down This was somewhat not so easy to spot, because "ocelot-8021q" is not the default tagging protocol, and thus, not everyone who tests the unbinding path may have switched to it beforehand. The default felix_tag_npi_teardown() does not require rtnl_lock() to be held. Fixes: 7c83a7c539ab ("net: dsa: add a second tagger for Ocelot switches based on tag_8021q") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230803134253.2711124-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8da46d284e35..bef879c6d500 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1625,8 +1625,10 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); struct dsa_port *dp; + rtnl_lock(); if (felix->tag_proto_ops) felix->tag_proto_ops->teardown(ds); + rtnl_unlock(); dsa_switch_for_each_available_port(dp, ds) ocelot_deinit_port(ocelot, dp->index); -- cgit v1.2.3 From 8a9896177784063d01068293caea3f74f6830ff6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Aug 2023 14:56:00 +0000 Subject: net/packet: annotate data-races around tp->status Another syzbot report [1] is about tp->status lockless reads from __packet_get_status() [1] BUG: KCSAN: data-race in __packet_rcv_has_room / __packet_set_status write to 0xffff888117d7c080 of 8 bytes by interrupt on cpu 0: __packet_set_status+0x78/0xa0 net/packet/af_packet.c:407 tpacket_rcv+0x18bb/0x1a60 net/packet/af_packet.c:2483 deliver_skb net/core/dev.c:2173 [inline] __netif_receive_skb_core+0x408/0x1e80 net/core/dev.c:5337 __netif_receive_skb_one_core net/core/dev.c:5491 [inline] __netif_receive_skb+0x57/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x57/0xa0 kernel/softirq.c:650 sysvec_apic_timer_interrupt+0x6d/0x80 arch/x86/kernel/apic/apic.c:1106 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:645 smpboot_thread_fn+0x33c/0x4a0 kernel/smpboot.c:112 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 read to 0xffff888117d7c080 of 8 bytes by interrupt on cpu 1: __packet_get_status net/packet/af_packet.c:436 [inline] packet_lookup_frame net/packet/af_packet.c:524 [inline] __tpacket_has_room net/packet/af_packet.c:1255 [inline] __packet_rcv_has_room+0x3f9/0x450 net/packet/af_packet.c:1298 tpacket_rcv+0x275/0x1a60 net/packet/af_packet.c:2285 deliver_skb net/core/dev.c:2173 [inline] dev_queue_xmit_nit+0x38a/0x5e0 net/core/dev.c:2243 xmit_one net/core/dev.c:3574 [inline] dev_hard_start_xmit+0xcf/0x3f0 net/core/dev.c:3594 __dev_queue_xmit+0xefb/0x1d10 net/core/dev.c:4244 dev_queue_xmit include/linux/netdevice.h:3088 [inline] can_send+0x4eb/0x5d0 net/can/af_can.c:276 bcm_can_tx+0x314/0x410 net/can/bcm.c:302 bcm_tx_timeout_handler+0xdb/0x260 __run_hrtimer kernel/time/hrtimer.c:1685 [inline] __hrtimer_run_queues+0x217/0x700 kernel/time/hrtimer.c:1749 hrtimer_run_softirq+0xd6/0x120 kernel/time/hrtimer.c:1766 __do_softirq+0xc1/0x265 kernel/softirq.c:571 run_ksoftirqd+0x17/0x20 kernel/softirq.c:939 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0000000000000000 -> 0x0000000020000081 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 19 Comm: ksoftirqd/1 Not tainted 6.4.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230803145600.2937518-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a4631cb457a9..a2935bd18ed9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -401,18 +401,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -429,17 +431,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); -- cgit v1.2.3 From 6a7ac3d20593865209dceb554d8b3f094c6bd940 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 3 Aug 2023 17:26:49 +0200 Subject: tunnels: fix kasan splat when generating ipv4 pmtu error If we try to emit an icmp error in response to a nonliner skb, we get BUG: KASAN: slab-out-of-bounds in ip_compute_csum+0x134/0x220 Read of size 4 at addr ffff88811c50db00 by task iperf3/1691 CPU: 2 PID: 1691 Comm: iperf3 Not tainted 6.5.0-rc3+ #309 [..] kasan_report+0x105/0x140 ip_compute_csum+0x134/0x220 iptunnel_pmtud_build_icmp+0x554/0x1020 skb_tunnel_check_pmtu+0x513/0xb80 vxlan_xmit_one+0x139e/0x2ef0 vxlan_xmit+0x1867/0x2760 dev_hard_start_xmit+0x1ee/0x4f0 br_dev_queue_push_xmit+0x4d1/0x660 [..] ip_compute_csum() cannot deal with nonlinear skbs, so avoid it. After this change, splat is gone and iperf3 is no longer stuck. Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets") Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230803152653.29535-2-fw@strlen.de Signed-off-by: Jakub Kicinski --- net/ipv4/ip_tunnel_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); -- cgit v1.2.3 From 136a1b434bbb90c5e50831646ad0680c744c79bb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 3 Aug 2023 17:26:50 +0200 Subject: selftests: net: test vxlan pmtu exceptions with tcp TCP might get stuck if a nonlinear skb exceeds the path MTU, icmp error contains an incorrect icmp checksum in that case. Extend the existing test for vxlan to also send at least 1MB worth of data via TCP in addition to the existing 'large icmp packet adds route exception'. On my test VM this fails due to 0-size output file without "tunnels: fix kasan splat when generating ipv4 pmtu error". Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230803152653.29535-3-fw@strlen.de Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/pmtu.sh | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index dfe3d287f01d..f838dd370f6a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -361,6 +361,7 @@ err_buf= tcpdump_pids= nettest_pids= socat_pids= +tmpoutfile= err() { err_buf="${err_buf}${1} @@ -951,6 +952,7 @@ cleanup() { ip link del veth_A-R1 2>/dev/null ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null + rm -f "$tmpoutfile" } mtu() { @@ -1328,6 +1330,39 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" + + tmpoutfile=$(mktemp) + + # Flush Exceptions, retry with TCP + run_cmd ${ns_a} ip route flush cached ${dst} + run_cmd ${ns_b} ip route flush cached ${dst} + run_cmd ${ns_c} ip route flush cached ${dst} + + for target in "${ns_a}" "${ns_c}" ; do + if [ ${family} -eq 4 ]; then + TCPDST=TCP:${dst}:50000 + else + TCPDST="TCP:[${dst}]:50000" + fi + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + + sleep 1 + + dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + + size=$(du -sb $tmpoutfile) + size=${size%%/tmp/*} + + [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + done + + rm -f "$tmpoutfile" + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp: exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp exceeding link layer MTU on locally bridged ${type} interface" } test_pmtu_ipv4_br_vxlan4_exception() { -- cgit v1.2.3 From aaf2123a5cf46dbd97f84b6eee80269758064d93 Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Thu, 3 Aug 2023 18:27:27 +0200 Subject: selftests: mptcp: join: fix 'delete and re-add' test mptcp_join 'delete and re-add' test fails when using ip mptcp: $ ./mptcp_join.sh -iI 002 delete and re-add before delete[ ok ] mptcp_info subflows=1 [ ok ] Error: argument "ADDRESS" is wrong: invalid for non-zero id address after delete[fail] got 2:2 subflows expected 1 This happens because endpoint delete includes an ip address while id is not 0, contrary to what is indicated in the ip mptcp man page: "When used with the delete id operation, an IFADDR is only included when the ID is 0." This fixes the issue using the $addr variable in pm_nl_del_endpoint() only when id is 0. Fixes: 34aa6e3bccd8 ("selftests: mptcp: add ip mptcp wrappers") Cc: stable@vger.kernel.org Signed-off-by: Andrea Claudi Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-1-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c2096ac97ef..067fabc401f1 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -705,6 +705,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr -- cgit v1.2.3 From c8c101ae390a3e817369e94a6f12a1ddea420702 Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Thu, 3 Aug 2023 18:27:28 +0200 Subject: selftests: mptcp: join: fix 'implicit EP' test mptcp_join 'implicit EP' test currently fails when using ip mptcp: $ ./mptcp_join.sh -iI 001 implicit EP creation[fail] expected '10.0.2.2 10.0.2.2 id 1 implicit' found '10.0.2.2 id 1 rawflags 10 ' Error: too many addresses or duplicate one: -22. ID change is prevented[fail] expected '10.0.2.2 10.0.2.2 id 1 implicit' found '10.0.2.2 id 1 rawflags 10 ' modif is allowed[fail] expected '10.0.2.2 10.0.2.2 id 1 signal' found '10.0.2.2 id 1 signal ' This happens because of two reasons: - iproute v6.3.0 does not support the implicit flag, fixed with iproute2-next commit 3a2535a41854 ("mptcp: add support for implicit flag") - pm_nl_check_endpoint wrongly expects the ip address to be repeated two times in iproute output, and does not account for a final whitespace in it. This fixes the issue trimming the whitespace in the output string and removing the double address in the expected string. Fixes: 69c6ce7b6eca ("selftests: mptcp: add implicit endpoint test case") Cc: stable@vger.kernel.org Signed-off-by: Andrea Claudi Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-2-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 067fabc401f1..d01b73a8ed0f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -796,10 +796,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" -- cgit v1.2.3 From ff18f9ef30ee87740f741b964375d0cfb84e1ec2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 3 Aug 2023 18:27:29 +0200 Subject: mptcp: avoid bogus reset on fallback close Since the blamed commit, the MPTCP protocol unconditionally sends TCP resets on all the subflows on disconnect(). That fits full-blown MPTCP sockets - to implement the fastclose mechanism - but causes unexpected corruption of the data stream, caught as sporadic self-tests failures. Fixes: d21f83485518 ("mptcp: use fastclose on more edge scenarios") Cc: stable@vger.kernel.org Tested-by: Matthieu Baerts Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/419 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-3-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index be5f6f4b94c7..d80658547836 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2335,7 +2335,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ -- cgit v1.2.3 From 511b90e39250135a7f900f1c3afbce25543018a2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 3 Aug 2023 18:27:30 +0200 Subject: mptcp: fix disconnect vs accept race Despite commit 0ad529d9fd2b ("mptcp: fix possible divide by zero in recvmsg()"), the mptcp protocol is still prone to a race between disconnect() (or shutdown) and accept. The root cause is that the mentioned commit checks the msk-level flag, but mptcp_stream_accept() does acquire the msk-level lock, as it can rely directly on the first subflow lock. As reported by Christoph than can lead to a race where an msk socket is accepted after that mptcp_subflow_queue_clean() releases the listener socket lock and just before it takes destructive actions leading to the following splat: BUG: kernel NULL pointer dereference, address: 0000000000000012 PGD 5a4ca067 P4D 5a4ca067 PUD 37d4c067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 2 PID: 10955 Comm: syz-executor.5 Not tainted 6.5.0-rc1-gdc7b257ee5dd #37 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 RIP: 0010:mptcp_stream_accept+0x1ee/0x2f0 include/net/inet_sock.h:330 Code: 0a 09 00 48 8b 1b 4c 39 e3 74 07 e8 bc 7c 7f fe eb a1 e8 b5 7c 7f fe 4c 8b 6c 24 08 eb 05 e8 a9 7c 7f fe 49 8b 85 d8 09 00 00 <0f> b6 40 12 88 44 24 07 0f b6 6c 24 07 bf 07 00 00 00 89 ee e8 89 RSP: 0018:ffffc90000d07dc0 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff888037e8d020 RCX: ffff88803b093300 RDX: 0000000000000000 RSI: ffffffff833822c5 RDI: ffffffff8333896a RBP: 0000607f82031520 R08: ffff88803b093300 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000003e83 R12: ffff888037e8d020 R13: ffff888037e8c680 R14: ffff888009af7900 R15: ffff888009af6880 FS: 00007fc26d708640(0000) GS:ffff88807dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000012 CR3: 0000000066bc5001 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: do_accept+0x1ae/0x260 net/socket.c:1872 __sys_accept4+0x9b/0x110 net/socket.c:1913 __do_sys_accept4 net/socket.c:1954 [inline] __se_sys_accept4 net/socket.c:1951 [inline] __x64_sys_accept4+0x20/0x30 net/socket.c:1951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x47/0xa0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Address the issue by temporary removing the pending request socket from the accept queue, so that racing accept() can't touch them. After depleting the msk - the ssk still exists, as plain TCP sockets, re-insert them into the accept queue, so that later inet_csk_listen_stop() will complete the tcp socket disposal. Fixes: 2a6a870e44dd ("mptcp: stops worker on unaccepted sockets at listener close") Cc: stable@vger.kernel.org Reported-by: Christoph Paasch Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/423 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-4-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.h | 1 - net/mptcp/subflow.c | 58 ++++++++++++++++++++++++++-------------------------- 2 files changed, 29 insertions(+), 30 deletions(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37fbe22e2433..ba2a873a4d2e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -325,7 +325,6 @@ struct mptcp_sock { u32 subflow_id; u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ee3b7abbaf6..94ae7dd01c65 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1793,16 +1793,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1810,32 +1825,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1859,6 +1852,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) -- cgit v1.2.3 From a47e598fbd8617967e49d85c49c22f9fc642704c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Aug 2023 16:30:21 +0000 Subject: dccp: fix data-race around dp->dccps_mss_cache dccp_sendmsg() reads dp->dccps_mss_cache before locking the socket. Same thing in do_dccp_getsockopt(). Add READ_ONCE()/WRITE_ONCE() annotations, and change dccp_sendmsg() to check again dccps_mss_cache after socket is locked. Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230803163021.2958262-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/dccp/output.c | 2 +- net/dccp/proto.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index f331e5977a84..4e3266e4d7c3 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -630,7 +630,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -739,7 +739,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -772,6 +772,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) -- cgit v1.2.3 From 6b47808f223c70ff564f9b363446d2a5fa1e05b2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Aug 2023 15:59:51 -0700 Subject: net: tls: avoid discarding data on record close TLS records end with a 16B tag. For TLS device offload we only need to make space for this tag in the stream, the device will generate and replace it with the actual calculated tag. Long time ago the code would just re-reference the head frag which mostly worked but was suboptimal because it prevented TCP from combining the record into a single skb frag. I'm not sure if it was correct as the first frag may be shorter than the tag. The commit under fixes tried to replace that with using the page frag and if the allocation failed rolling back the data, if record was long enough. It achieves better fragment coalescing but is also buggy. We don't roll back the iterator, so unless we're at the end of send we'll skip the data we designated as tag and start the next record as if the rollback never happened. There's also the possibility that the record was constructed with MSG_MORE and the data came from a different syscall and we already told the user space that we "got it". Allocate a single dummy page and use it as fallback. Found by code inspection, and proven by forcing allocation failures. Fixes: e7b159a48ba6 ("net/tls: remove the record tail optimization") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/tls/tls_device.c | 64 +++++++++++++++++++++++++++------------------------- 1 file changed, 33 insertions(+), 31 deletions(-) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 2021fe557e50..529101eb20bd 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -312,36 +314,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -541,18 +540,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1450,14 +1439,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1466,4 +1467,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } -- cgit v1.2.3 From 32d0a49d36a2a306c2e47fe5659361e424f0ed3f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Aug 2023 17:26:52 +0000 Subject: macsec: use DEV_STATS_INC() syzbot/KCSAN reported data-races in macsec whenever dev->stats fields are updated. It appears all of these updates can happen from multiple cpus. Adopt SMP safe DEV_STATS_INC() to update dev->stats fields. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Sabrina Dubroca Signed-off-by: David S. Miller --- drivers/net/macsec.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 984dfa5d6c11..144ec756c796 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -743,7 +743,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_dropped++; + DEV_STATS_INC(secy->netdev, rx_dropped); return false; } @@ -767,7 +767,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); return false; } @@ -1069,7 +1069,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } @@ -1179,7 +1179,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } @@ -1196,7 +1196,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; @@ -1230,7 +1230,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } @@ -1271,7 +1271,7 @@ deliver: if (ret == NET_RX_SUCCESS) count_rx(dev, len); else - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); @@ -1308,7 +1308,7 @@ nosci: u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_errors++; + DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } @@ -1327,7 +1327,7 @@ nosci: secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } @@ -3422,7 +3422,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, if (!secy->operational) { kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3430,7 +3430,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3667,9 +3667,9 @@ static void macsec_get_stats64(struct net_device *dev, dev_fetch_sw_netstats(s, dev->tstats); - s->rx_dropped = dev->stats.rx_dropped; - s->tx_dropped = dev->stats.tx_dropped; - s->rx_errors = dev->stats.rx_errors; + s->rx_dropped = atomic_long_read(&dev->stats.__rx_dropped); + s->tx_dropped = atomic_long_read(&dev->stats.__tx_dropped); + s->rx_errors = atomic_long_read(&dev->stats.__rx_errors); } static int macsec_get_iflink(const struct net_device *dev) -- cgit v1.2.3 From b1c936e9af5dd08636d568736fc6075ed9d1d529 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 4 Aug 2023 18:53:36 +0300 Subject: drivers: vxlan: vnifilter: free percpu vni stats on error path In case rhashtable_lookup_insert_fast() fails inside vxlan_vni_add(), the allocated percpu vni stats are not freed on the error path. Introduce vxlan_vni_free() which would work as a nice wrapper to free vxlan_vni_node resources properly. Found by Linux Verification Center (linuxtesting.org). Fixes: 4095e0e1328a ("drivers: vxlan: vnifilter: per vni stats") Suggested-by: Ido Schimmel Signed-off-by: Fedor Pchelkin Signed-off-by: David S. Miller --- drivers/net/vxlan/vxlan_vnifilter.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index a3de081cda5e..c3ff30ab782e 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -713,6 +713,12 @@ static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, return vninode; } +static void vxlan_vni_free(struct vxlan_vni_node *vninode) +{ + free_percpu(vninode->stats); + kfree(vninode); +} + static int vxlan_vni_add(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, union vxlan_addr *group, @@ -740,7 +746,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan, &vninode->vnode, vxlan_vni_rht_params); if (err) { - kfree(vninode); + vxlan_vni_free(vninode); return err; } @@ -763,8 +769,7 @@ static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) struct vxlan_vni_node *v; v = container_of(rcu, struct vxlan_vni_node, rcu); - free_percpu(v->stats); - kfree(v); + vxlan_vni_free(v); } static int vxlan_vni_del(struct vxlan_dev *vxlan, -- cgit v1.2.3 From 52417a95ff2d810dc31a68ae71102e741efea772 Mon Sep 17 00:00:00 2001 From: Nitya Sunkad Date: Fri, 4 Aug 2023 13:56:22 -0700 Subject: ionic: Add missing err handling for queue reconfig ionic_start_queues_reconfig returns an error code if txrx_init fails. Handle this error code in the relevant places. This fixes a corner case where the device could get left in a detached state if the CMB reconfig fails and the attempt to clean up the mess also fails. Note that calling netif_device_attach when the netdev is already attached does not lead to unexpected behavior. Change goto name "errout" to "err_out" to maintain consistency across goto statements. Fixes: 40bc471dc714 ("ionic: add tx/rx-push support with device Component Memory Buffers") Fixes: 6f7d6f0fd7a3 ("ionic: pull reset_queues into tx_timeout handler") Signed-off-by: Nitya Sunkad Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 612b0015dc43..432fb93aa801 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1817,6 +1817,7 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) static void ionic_tx_timeout_work(struct work_struct *ws) { struct ionic_lif *lif = container_of(ws, struct ionic_lif, tx_timeout_work); + int err; if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) return; @@ -1829,8 +1830,11 @@ static void ionic_tx_timeout_work(struct work_struct *ws) mutex_lock(&lif->queue_lock); ionic_stop_queues_reconfig(lif); - ionic_start_queues_reconfig(lif); + err = ionic_start_queues_reconfig(lif); mutex_unlock(&lif->queue_lock); + + if (err) + dev_err(lif->ionic->dev, "%s: Restarting queues failed\n", __func__); } static void ionic_tx_timeout(struct net_device *netdev, unsigned int txqueue) @@ -2800,17 +2804,22 @@ static int ionic_cmb_reconfig(struct ionic_lif *lif, if (err) { dev_err(lif->ionic->dev, "CMB restore failed: %d\n", err); - goto errout; + goto err_out; } } - ionic_start_queues_reconfig(lif); - } else { - /* This was detached in ionic_stop_queues_reconfig() */ - netif_device_attach(lif->netdev); + err = ionic_start_queues_reconfig(lif); + if (err) { + dev_err(lif->ionic->dev, + "CMB reconfig failed: %d\n", err); + goto err_out; + } } -errout: +err_out: + /* This was detached in ionic_stop_queues_reconfig() */ + netif_device_attach(lif->netdev); + return err; } -- cgit v1.2.3 From 72cc654970658e88a1cdea08f06b11c218efa4da Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 16 Jul 2023 14:28:10 +0300 Subject: net/mlx5e: Take RTNL lock when needed before calling xdp_set_features() Hold RTNL lock when calling xdp_set_features() with a registered netdev, as the call triggers the netdev notifiers. This could happen when switching from uplink rep to nic profile for example. This resolves the following call trace: RTNL: assertion failed at net/core/dev.c (1953) WARNING: CPU: 6 PID: 112670 at net/core/dev.c:1953 call_netdevice_notifiers_info+0x7c/0x80 Modules linked in: sch_mqprio sch_mqprio_lib act_tunnel_key act_mirred act_skbedit cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress bonding ib_umad ip_gre rdma_ucm mlx5_vfio_pci ipip tunnel4 ip6_gre gre mlx5_ib vfio_pci vfio_pci_core vfio_iommu_type1 ib_uverbs vfio mlx5_core ib_ipoib geneve nf_tables ip6_tunnel tunnel6 iptable_raw openvswitch nsh rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay zram zsmalloc fuse [last unloaded: ib_uverbs] CPU: 6 PID: 112670 Comm: devlink Not tainted 6.4.0-rc7_for_upstream_min_debug_2023_06_28_17_02 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:call_netdevice_notifiers_info+0x7c/0x80 Code: 90 ff 80 3d 2d 6b f7 00 00 75 c5 ba a1 07 00 00 48 c7 c6 e4 ce 0b 82 48 c7 c7 c8 f4 04 82 c6 05 11 6b f7 00 01 e8 a4 7c 8e ff <0f> 0b eb a2 0f 1f 44 00 00 55 48 89 e5 41 54 48 83 e4 f0 48 83 ec RSP: 0018:ffff8882a21c3948 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffffffff82e6f880 RCX: 0000000000000027 RDX: ffff88885f99b5c8 RSI: 0000000000000001 RDI: ffff88885f99b5c0 RBP: 0000000000000028 R08: ffff88887ffabaa8 R09: 0000000000000003 R10: ffff88887fecbac0 R11: ffff88887ff7bac0 R12: ffff8882a21c3968 R13: ffff88811c018940 R14: 0000000000000000 R15: ffff8881274401a0 FS: 00007fe141c81800(0000) GS:ffff88885f980000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f787c28b948 CR3: 000000014bcf3005 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __warn+0x79/0x120 ? call_netdevice_notifiers_info+0x7c/0x80 ? report_bug+0x17c/0x190 ? handle_bug+0x3c/0x60 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? call_netdevice_notifiers_info+0x7c/0x80 ? call_netdevice_notifiers_info+0x7c/0x80 call_netdevice_notifiers+0x2e/0x50 mlx5e_set_xdp_feature+0x21/0x50 [mlx5_core] mlx5e_nic_init+0xf1/0x1a0 [mlx5_core] mlx5e_netdev_init_profile+0x76/0x110 [mlx5_core] mlx5e_netdev_attach_profile+0x1f/0x90 [mlx5_core] mlx5e_netdev_change_profile+0x92/0x160 [mlx5_core] mlx5e_netdev_attach_nic_profile+0x1b/0x30 [mlx5_core] mlx5e_vport_rep_unload+0xaa/0xc0 [mlx5_core] __esw_offloads_unload_rep+0x52/0x60 [mlx5_core] mlx5_esw_offloads_rep_unload+0x52/0x70 [mlx5_core] esw_offloads_unload_rep+0x34/0x70 [mlx5_core] esw_offloads_disable+0x2b/0x90 [mlx5_core] mlx5_eswitch_disable_locked+0x1b9/0x210 [mlx5_core] mlx5_devlink_eswitch_mode_set+0xf5/0x630 [mlx5_core] ? devlink_get_from_attrs_lock+0x9e/0x110 devlink_nl_cmd_eswitch_set_doit+0x60/0xe0 genl_family_rcv_msg_doit.isra.0+0xc2/0x110 genl_rcv_msg+0x17d/0x2b0 ? devlink_get_from_attrs_lock+0x110/0x110 ? devlink_nl_cmd_eswitch_get_doit+0x290/0x290 ? devlink_pernet_pre_exit+0xf0/0xf0 ? genl_family_rcv_msg_doit.isra.0+0x110/0x110 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1f6/0x2c0 netlink_sendmsg+0x232/0x4a0 sock_sendmsg+0x38/0x60 ? _copy_from_user+0x2a/0x60 __sys_sendto+0x110/0x160 ? __count_memcg_events+0x48/0x90 ? handle_mm_fault+0x161/0x260 ? do_user_addr_fault+0x278/0x6e0 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fe141b1340a Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007fff61d03de8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000afab00 RCX: 00007fe141b1340a RDX: 0000000000000038 RSI: 0000000000afab00 RDI: 0000000000000003 RBP: 0000000000afa910 R08: 00007fe141d80200 R09: 000000000000000c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000001 Fixes: 4d5ab0ad964d ("net/mlx5e: take into account device reconfiguration for xdp_features flag") Signed-off-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1c820119e438..c27df14df145 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5266,6 +5266,7 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) static int mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { + const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_flow_steering *fs; int err; @@ -5294,9 +5295,19 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_health_create_reporters(priv); + + /* If netdev is already registered (e.g. move from uplink to nic profile), + * RTNL lock must be held before triggering netdev notifiers. + */ + if (take_rtnl) + rtnl_lock(); + /* update XDP supported features */ mlx5e_set_xdp_feature(netdev); + if (take_rtnl) + rtnl_unlock(); + return 0; } -- cgit v1.2.3 From ac5da544a3c2047cbfd715acd9cec8380d7fe5c6 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Fri, 14 Apr 2023 08:48:20 +0000 Subject: net/mlx5e: TC, Fix internal port memory leak The flow rule can be splited, and the extra post_act rules are added to post_act table. It's possible to trigger memleak when the rule forwards packets from internal port and over tunnel, in the case that, for example, CT 'new' state offload is allowed. As int_port object is assigned to the flow attribute of post_act rule, and its refcnt is incremented by mlx5e_tc_int_port_get(), but mlx5e_tc_int_port_put() is not called, the refcnt is never decremented, then int_port is never freed. The kmemleak reports the following error: unreferenced object 0xffff888128204b80 (size 64): comm "handler20", pid 50121, jiffies 4296973009 (age 642.932s) hex dump (first 32 bytes): 01 00 00 00 19 00 00 00 03 f0 00 00 04 00 00 00 ................ 98 77 67 41 81 88 ff ff 98 77 67 41 81 88 ff ff .wgA.....wgA.... backtrace: [<00000000e992680d>] kmalloc_trace+0x27/0x120 [<000000009e945a98>] mlx5e_tc_int_port_get+0x3f3/0xe20 [mlx5_core] [<0000000035a537f0>] mlx5e_tc_add_fdb_flow+0x473/0xcf0 [mlx5_core] [<0000000070c2cec6>] __mlx5e_add_fdb_flow+0x7cf/0xe90 [mlx5_core] [<000000005cc84048>] mlx5e_configure_flower+0xd40/0x4c40 [mlx5_core] [<000000004f8a2031>] mlx5e_rep_indr_offload.isra.0+0x10e/0x1c0 [mlx5_core] [<000000007df797dc>] mlx5e_rep_indr_setup_tc_cb+0x90/0x130 [mlx5_core] [<0000000016c15cc3>] tc_setup_cb_add+0x1cf/0x410 [<00000000a63305b4>] fl_hw_replace_filter+0x38f/0x670 [cls_flower] [<000000008bc9e77c>] fl_change+0x1fd5/0x4430 [cls_flower] [<00000000e7f766e4>] tc_new_tfilter+0x867/0x2010 [<00000000e101c0ef>] rtnetlink_rcv_msg+0x6fc/0x9f0 [<00000000e1111d44>] netlink_rcv_skb+0x12c/0x360 [<0000000082dd6c8b>] netlink_unicast+0x438/0x710 [<00000000fc568f70>] netlink_sendmsg+0x794/0xc50 [<0000000016e92590>] sock_sendmsg+0xc5/0x190 So fix this by moving int_port cleanup code to the flow attribute free helper, which is used by all the attribute free cases. Fixes: 8300f225268b ("net/mlx5e: Create new flow attr for multi table actions") Signed-off-by: Jianbo Liu Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 92377632f9e0..31708d5aa608 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1943,9 +1943,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; - struct mlx5_esw_flow_attr *esw_attr; - esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); remove_unready_flow(flow); @@ -1966,12 +1964,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); - if (esw_attr->int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port); - - if (esw_attr->dest_int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port); - if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -4268,6 +4260,7 @@ static void mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + struct mlx5_esw_flow_attr *esw_attr; if (!attr) return; @@ -4285,6 +4278,18 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr); } + if (mlx5e_is_eswitch_flow(flow)) { + esw_attr = attr->esw_attr; + + if (esw_attr->int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->int_port); + + if (esw_attr->dest_int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->dest_int_port); + } + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); free_branch_attr(flow, attr->branch_true); -- cgit v1.2.3 From 8bfe1e19fb96d89fce14302e35cba0cd9f39d0a1 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Wed, 26 Jul 2023 14:38:03 +0300 Subject: net/mlx5: DR, Fix wrong allocation of modify hdr pattern Fixing wrong calculation of the modify hdr pattern size, where the previously calculated number would not be enough to accommodate the required number of actions. Fixes: da5d0027d666 ("net/mlx5: DR, Add cache for modify header pattern") Signed-off-by: Yevgeny Kliteynik Reviewed-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index d6947fe13d56..8ca534ef5d03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -82,7 +82,7 @@ dr_ptrn_alloc_pattern(struct mlx5dr_ptrn_mgr *mgr, u32 chunk_size; u32 index; - chunk_size = ilog2(num_of_actions); + chunk_size = ilog2(roundup_pow_of_two(num_of_actions)); /* HW modify action index granularity is at least 64B */ chunk_size = max_t(u32, chunk_size, DR_CHUNK_SIZE_8); -- cgit v1.2.3 From 06c868fde61fd0bbf9a7c7405f6eb9925bf0c2ed Mon Sep 17 00:00:00 2001 From: Daniel Jurgens Date: Mon, 26 Jun 2023 22:55:03 +0300 Subject: net/mlx5: Return correct EC_VF function ID The ECVF function ID range is 1..max_ec_vfs. Currently mlx5_vport_to_func_id returns 0..max_ec_vfs - 1. Which results in a syndrome when querying the caps with more recent firmware, or reading incorrect caps with older firmware that supports EC VFs. Fixes: 9ac0b128248e ("net/mlx5: Update vport caps query/set for EC VFs") Signed-off-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c4be257c043d..682d3dc00dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5