From e92df790d07a8eea873efcb84776e7b71f81c7d5 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Tue, 11 Mar 2025 00:01:44 +0200 Subject: [PATCH 01/16] net/mlx5e: Prevent bridge link show failure for non-eswitch-allowed devices mlx5_eswitch_get_vepa returns -EPERM if the device lacks eswitch_manager capability, blocking mlx5e_bridge_getlink from retrieving VEPA mode. Since mlx5e_bridge_getlink implements ndo_bridge_getlink, returning -EPERM causes bridge link show to fail instead of skipping devices without this capability. To avoid this, return -EOPNOTSUPP from mlx5e_bridge_getlink when mlx5_eswitch_get_vepa fails, ensuring the command continues processing other devices while ignoring those without the necessary capability. Fixes: 4b89251de024 ("net/mlx5: Support ndo bridge_setlink and getlink") Signed-off-by: Carolina Jubran Reviewed-by: Jianbo Liu Signed-off-by: Tariq Toukan Reviewed-by: Michal Swiatkowski Link: https://patch.msgid.link/1741644104-97767-7-git-send-email-tariqt@nvidia.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a814b63ed97e..8fcaee381b0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5132,11 +5132,9 @@ static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; u8 mode, setting; - int err; - err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting); - if (err) - return err; + if (mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting)) + return -EOPNOTSUPP; mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB; return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, -- 2.51.0 From 3e64bb2ae7d9f2b3a8259d4d6b86ed1984d5460a Mon Sep 17 00:00:00 2001 From: Shradha Gupta Date: Tue, 11 Mar 2025 03:17:40 -0700 Subject: [PATCH 02/16] net: mana: cleanup mana struct after debugfs_remove() When on a MANA VM hibernation is triggered, as part of hibernate_snapshot(), mana_gd_suspend() and mana_gd_resume() are called. If during this mana_gd_resume(), a failure occurs with HWC creation, mana_port_debugfs pointer does not get reinitialized and ends up pointing to older, cleaned-up dentry. Further in the hibernation path, as part of power_down(), mana_gd_shutdown() is triggered. This call, unaware of the failures in resume, tries to cleanup the already cleaned up mana_port_debugfs value and hits the following bug: [ 191.359296] mana 7870:00:00.0: Shutdown was called [ 191.359918] BUG: kernel NULL pointer dereference, address: 0000000000000098 [ 191.360584] #PF: supervisor write access in kernel mode [ 191.361125] #PF: error_code(0x0002) - not-present page [ 191.361727] PGD 1080ea067 P4D 0 [ 191.362172] Oops: Oops: 0002 [#1] SMP NOPTI [ 191.362606] CPU: 11 UID: 0 PID: 1674 Comm: bash Not tainted 6.14.0-rc5+ #2 [ 191.363292] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 11/21/2024 [ 191.364124] RIP: 0010:down_write+0x19/0x50 [ 191.364537] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb e8 de cd ff ff 31 c0 ba 01 00 00 00 48 0f b1 13 75 16 65 48 8b 05 88 24 4c 6a 48 89 43 08 48 8b 5d [ 191.365867] RSP: 0000:ff45fbe0c1c037b8 EFLAGS: 00010246 [ 191.366350] RAX: 0000000000000000 RBX: 0000000000000098 RCX: ffffff8100000000 [ 191.366951] RDX: 0000000000000001 RSI: 0000000000000064 RDI: 0000000000000098 [ 191.367600] RBP: ff45fbe0c1c037c0 R08: 0000000000000000 R09: 0000000000000001 [ 191.368225] R10: ff45fbe0d2b01000 R11: 0000000000000008 R12: 0000000000000000 [ 191.368874] R13: 000000000000000b R14: ff43dc27509d67c0 R15: 0000000000000020 [ 191.369549] FS: 00007dbc5001e740(0000) GS:ff43dc663f380000(0000) knlGS:0000000000000000 [ 191.370213] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 191.370830] CR2: 0000000000000098 CR3: 0000000168e8e002 CR4: 0000000000b73ef0 [ 191.371557] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 191.372192] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 191.372906] Call Trace: [ 191.373262] [ 191.373621] ? show_regs+0x64/0x70 [ 191.374040] ? __die+0x24/0x70 [ 191.374468] ? page_fault_oops+0x290/0x5b0 [ 191.374875] ? do_user_addr_fault+0x448/0x800 [ 191.375357] ? exc_page_fault+0x7a/0x160 [ 191.375971] ? asm_exc_page_fault+0x27/0x30 [ 191.376416] ? down_write+0x19/0x50 [ 191.376832] ? down_write+0x12/0x50 [ 191.377232] simple_recursive_removal+0x4a/0x2a0 [ 191.377679] ? __pfx_remove_one+0x10/0x10 [ 191.378088] debugfs_remove+0x44/0x70 [ 191.378530] mana_detach+0x17c/0x4f0 [ 191.378950] ? __flush_work+0x1e2/0x3b0 [ 191.379362] ? __cond_resched+0x1a/0x50 [ 191.379787] mana_remove+0xf2/0x1a0 [ 191.380193] mana_gd_shutdown+0x3b/0x70 [ 191.380642] pci_device_shutdown+0x3a/0x80 [ 191.381063] device_shutdown+0x13e/0x230 [ 191.381480] kernel_power_off+0x35/0x80 [ 191.381890] hibernate+0x3c6/0x470 [ 191.382312] state_store+0xcb/0xd0 [ 191.382734] kobj_attr_store+0x12/0x30 [ 191.383211] sysfs_kf_write+0x3e/0x50 [ 191.383640] kernfs_fop_write_iter+0x140/0x1d0 [ 191.384106] vfs_write+0x271/0x440 [ 191.384521] ksys_write+0x72/0xf0 [ 191.384924] __x64_sys_write+0x19/0x20 [ 191.385313] x64_sys_call+0x2b0/0x20b0 [ 191.385736] do_syscall_64+0x79/0x150 [ 191.386146] ? __mod_memcg_lruvec_state+0xe7/0x240 [ 191.386676] ? __lruvec_stat_mod_folio+0x79/0xb0 [ 191.387124] ? __pfx_lru_add+0x10/0x10 [ 191.387515] ? queued_spin_unlock+0x9/0x10 [ 191.387937] ? do_anonymous_page+0x33c/0xa00 [ 191.388374] ? __handle_mm_fault+0xcf3/0x1210 [ 191.388805] ? __count_memcg_events+0xbe/0x180 [ 191.389235] ? handle_mm_fault+0xae/0x300 [ 191.389588] ? do_user_addr_fault+0x559/0x800 [ 191.390027] ? irqentry_exit_to_user_mode+0x43/0x230 [ 191.390525] ? irqentry_exit+0x1d/0x30 [ 191.390879] ? exc_page_fault+0x86/0x160 [ 191.391235] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 191.391745] RIP: 0033:0x7dbc4ff1c574 [ 191.392111] Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 [ 191.393412] RSP: 002b:00007ffd95a23ab8 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 [ 191.393990] RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00007dbc4ff1c574 [ 191.394594] RDX: 0000000000000005 RSI: 00005a6eeadb0ce0 RDI: 0000000000000001 [ 191.395215] RBP: 00007ffd95a23ae0 R08: 00007dbc50003b20 R09: 0000000000000000 [ 191.395805] R10: 0000000000000001 R11: 0000000000000202 R12: 0000000000000005 [ 191.396404] R13: 00005a6eeadb0ce0 R14: 00007dbc500045c0 R15: 00007dbc50001ee0 [ 191.396987] To fix this, we explicitly set such mana debugfs variables to NULL after debugfs_remove() is called. Fixes: 6607c17c6c5e ("net: mana: Enable debugfs files for MANA device") Cc: stable@vger.kernel.org Signed-off-by: Shradha Gupta Reviewed-by: Haiyang Zhang Reviewed-by: Michal Kubiak Link: https://patch.msgid.link/1741688260-28922-1-git-send-email-shradhagupta@linux.microsoft.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 11 ++++++++++- drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ++++++---- 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index be95336ce089..11457b6296cc 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1547,6 +1547,7 @@ unmap_bar: * adapter-MTU file and apc->mana_pci_debugfs folder. */ debugfs_remove_recursive(gc->mana_pci_debugfs); + gc->mana_pci_debugfs = NULL; pci_iounmap(pdev, bar0_va); free_gc: pci_set_drvdata(pdev, NULL); @@ -1569,6 +1570,8 @@ static void mana_gd_remove(struct pci_dev *pdev) debugfs_remove_recursive(gc->mana_pci_debugfs); + gc->mana_pci_debugfs = NULL; + pci_iounmap(pdev, gc->bar0_va); vfree(gc); @@ -1622,6 +1625,8 @@ static void mana_gd_shutdown(struct pci_dev *pdev) debugfs_remove_recursive(gc->mana_pci_debugfs); + gc->mana_pci_debugfs = NULL; + pci_disable_device(pdev); } @@ -1648,8 +1653,10 @@ static int __init mana_driver_init(void) mana_debugfs_root = debugfs_create_dir("mana", NULL); err = pci_register_driver(&mana_driver); - if (err) + if (err) { debugfs_remove(mana_debugfs_root); + mana_debugfs_root = NULL; + } return err; } @@ -1659,6 +1666,8 @@ static void __exit mana_driver_exit(void) pci_unregister_driver(&mana_driver); debugfs_remove(mana_debugfs_root); + + mana_debugfs_root = NULL; } module_init(mana_driver_init); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index aa1e47233fe5..ae76ecc7a5d3 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -738,12 +738,11 @@ static const struct net_device_ops mana_devops = { static void mana_cleanup_port_context(struct mana_port_context *apc) { /* - * at this point all dir/files under the vport directory - * are already cleaned up. - * We are sure the apc->mana_port_debugfs remove will not - * cause any freed memory access issues + * make sure subsequent cleanup attempts don't end up removing already + * cleaned dentry pointer */ debugfs_remove(apc->mana_port_debugfs); + apc->mana_port_debugfs = NULL; kfree(apc->rxqs); apc->rxqs = NULL; } @@ -1254,6 +1253,7 @@ static void mana_destroy_eq(struct mana_context *ac) return; debugfs_remove_recursive(ac->mana_eqs_debugfs); + ac->mana_eqs_debugfs = NULL; for (i = 0; i < gc->max_num_queues; i++) { eq = ac->eqs[i].eq; @@ -1914,6 +1914,7 @@ static void mana_destroy_txq(struct mana_port_context *apc) for (i = 0; i < apc->num_queues; i++) { debugfs_remove_recursive(apc->tx_qp[i].mana_tx_debugfs); + apc->tx_qp[i].mana_tx_debugfs = NULL; napi = &apc->tx_qp[i].tx_cq.napi; if (apc->tx_qp[i].txq.napi_initialized) { @@ -2099,6 +2100,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc, return; debugfs_remove_recursive(rxq->mana_rx_debugfs); + rxq->mana_rx_debugfs = NULL; napi = &rxq->rx_cq.napi; -- 2.51.0 From 1d22a122ffb116c3cf78053e812b8b21f8852ee9 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 18 Feb 2025 23:32:28 +0900 Subject: [PATCH 03/16] can: ucan: fix out of bound read in strscpy() source Commit 7fdaf8966aae ("can: ucan: use strscpy() to instead of strncpy()") unintentionally introduced a one byte out of bound read on strscpy()'s source argument (which is kind of ironic knowing that strscpy() is meant to be a more secure alternative :)). Let's consider below buffers: dest[len + 1]; /* will be NUL terminated */ src[len]; /* may not be NUL terminated */ When doing: strncpy(dest, src, len); dest[len] = '\0'; strncpy() will read up to len bytes from src. On the other hand: strscpy(dest, src, len + 1); will read up to len + 1 bytes from src, that is to say, an out of bound read of one byte will occur on src if it is not NUL terminated. Note that the src[len] byte is never copied, but strscpy() still needs to read it to check whether a truncation occurred or not. This exact pattern happened in ucan. The root cause is that the source is not NUL terminated. Instead of doing a copy in a local buffer, directly NUL terminate it as soon as usb_control_msg() returns. With this, the local firmware_str[] variable can be removed. On top of this do a couple refactors: - ucan_ctl_payload->raw is only used for the firmware string, so rename it to ucan_ctl_payload->fw_str and change its type from u8 to char. - ucan_device_request_in() is only used to retrieve the firmware string, so rename it to ucan_get_fw_str() and refactor it to make it directly handle all the string termination logic. Reported-by: syzbot+d7d8c418e8317899e88c@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-can/67b323a4.050a0220.173698.002b.GAE@google.com/ Fixes: 7fdaf8966aae ("can: ucan: use strscpy() to instead of strncpy()") Signed-off-by: Vincent Mailhol Link: https://patch.msgid.link/20250218143515.627682-2-mailhol.vincent@wanadoo.fr Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/ucan.c | 43 ++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 25 deletions(-) diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index 39a63b7313a4..07406daf7c88 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -186,7 +186,7 @@ union ucan_ctl_payload { */ struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version; - u8 raw[128]; + u8 fw_str[128]; } __packed; enum { @@ -424,18 +424,20 @@ static int ucan_ctrl_command_out(struct ucan_priv *up, UCAN_USB_CTL_PIPE_TIMEOUT); } -static int ucan_device_request_in(struct ucan_priv *up, - u8 cmd, u16 subcmd, u16 datalen) +static void ucan_get_fw_str(struct ucan_priv *up, char *fw_str, size_t size) { - return usb_control_msg(up->udev, - usb_rcvctrlpipe(up->udev, 0), - cmd, - USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - subcmd, - 0, - up->ctl_msg_buffer, - datalen, - UCAN_USB_CTL_PIPE_TIMEOUT); + int ret; + + ret = usb_control_msg(up->udev, usb_rcvctrlpipe(up->udev, 0), + UCAN_DEVICE_GET_FW_STRING, + USB_DIR_IN | USB_TYPE_VENDOR | + USB_RECIP_DEVICE, + 0, 0, fw_str, size - 1, + UCAN_USB_CTL_PIPE_TIMEOUT); + if (ret > 0) + fw_str[ret] = '\0'; + else + strscpy(fw_str, "unknown", size); } /* Parse the device information structure reported by the device and @@ -1314,7 +1316,6 @@ static int ucan_probe(struct usb_interface *intf, u8 in_ep_addr; u8 out_ep_addr; union ucan_ctl_payload *ctl_msg_buffer; - char firmware_str[sizeof(union ucan_ctl_payload) + 1]; udev = interface_to_usbdev(intf); @@ -1527,17 +1528,6 @@ static int ucan_probe(struct usb_interface *intf, */ ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info); - /* just print some device information - if available */ - ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0, - sizeof(union ucan_ctl_payload)); - if (ret > 0) { - /* copy string while ensuring zero termination */ - strscpy(firmware_str, up->ctl_msg_buffer->raw, - sizeof(union ucan_ctl_payload) + 1); - } else { - strcpy(firmware_str, "unknown"); - } - /* device is compatible, reset it */ ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0); if (ret < 0) @@ -1555,7 +1545,10 @@ static int ucan_probe(struct usb_interface *intf, /* initialisation complete, log device info */ netdev_info(up->netdev, "registered device\n"); - netdev_info(up->netdev, "firmware string: %s\n", firmware_str); + ucan_get_fw_str(up, up->ctl_msg_buffer->fw_str, + sizeof(up->ctl_msg_buffer->fw_str)); + netdev_info(up->netdev, "firmware string: %s\n", + up->ctl_msg_buffer->fw_str); /* success */ return 0; -- 2.51.0 From 80b5f90158d1364cbd80ad82852a757fc0692bf2 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 10 Mar 2025 15:33:53 +0100 Subject: [PATCH 04/16] can: statistics: use atomic access in hot path In can_send() and can_receive() CAN messages and CAN filter matches are counted to be visible in the CAN procfs files. KCSAN detected a data race within can_send() when two CAN frames have been generated by a timer event writing to the same CAN netdevice at the same time. Use atomic operations to access the statistics in the hot path to fix the KCSAN complaint. Reported-by: syzbot+78ce4489b812515d5e4d@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/67cd717d.050a0220.e1a89.0006.GAE@google.com Signed-off-by: Oliver Hartkopp Reviewed-by: Vincent Mailhol Link: https://patch.msgid.link/20250310143353.3242-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- net/can/af_can.c | 12 ++++++------ net/can/af_can.h | 12 ++++++------ net/can/proc.c | 46 +++++++++++++++++++++++++++------------------- 3 files changed, 39 insertions(+), 31 deletions(-) diff --git a/net/can/af_can.c b/net/can/af_can.c index 01f3fbb3b67d..65230e81fa08 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -287,8 +287,8 @@ int can_send(struct sk_buff *skb, int loop) netif_rx(newskb); /* update statistics */ - pkg_stats->tx_frames++; - pkg_stats->tx_frames_delta++; + atomic_long_inc(&pkg_stats->tx_frames); + atomic_long_inc(&pkg_stats->tx_frames_delta); return 0; @@ -647,8 +647,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) int matches; /* update statistics */ - pkg_stats->rx_frames++; - pkg_stats->rx_frames_delta++; + atomic_long_inc(&pkg_stats->rx_frames); + atomic_long_inc(&pkg_stats->rx_frames_delta); /* create non-zero unique skb identifier together with *skb */ while (!(can_skb_prv(skb)->skbcnt)) @@ -669,8 +669,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); if (matches > 0) { - pkg_stats->matches++; - pkg_stats->matches_delta++; + atomic_long_inc(&pkg_stats->matches); + atomic_long_inc(&pkg_stats->matches_delta); } } diff --git a/net/can/af_can.h b/net/can/af_can.h index 7c2d9161e224..22f3352c77fe 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -66,9 +66,9 @@ struct receiver { struct can_pkg_stats { unsigned long jiffies_init; - unsigned long rx_frames; - unsigned long tx_frames; - unsigned long matches; + atomic_long_t rx_frames; + atomic_long_t tx_frames; + atomic_long_t matches; unsigned long total_rx_rate; unsigned long total_tx_rate; @@ -82,9 +82,9 @@ struct can_pkg_stats { unsigned long max_tx_rate; unsigned long max_rx_match_ratio; - unsigned long rx_frames_delta; - unsigned long tx_frames_delta; - unsigned long matches_delta; + atomic_long_t rx_frames_delta; + atomic_long_t tx_frames_delta; + atomic_long_t matches_delta; }; /* persistent statistics */ diff --git a/net/can/proc.c b/net/can/proc.c index bbce97825f13..25fdf060e30d 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -118,6 +118,13 @@ void can_stat_update(struct timer_list *t) struct can_pkg_stats *pkg_stats = net->can.pkg_stats; unsigned long j = jiffies; /* snapshot */ + long rx_frames = atomic_long_read(&pkg_stats->rx_frames); + long tx_frames = atomic_long_read(&pkg_stats->tx_frames); + long matches = atomic_long_read(&pkg_stats->matches); + long rx_frames_delta = atomic_long_read(&pkg_stats->rx_frames_delta); + long tx_frames_delta = atomic_long_read(&pkg_stats->tx_frames_delta); + long matches_delta = atomic_long_read(&pkg_stats->matches_delta); + /* restart counting in timer context on user request */ if (user_reset) can_init_stats(net); @@ -127,35 +134,33 @@ void can_stat_update(struct timer_list *t) can_init_stats(net); /* prevent overflow in calc_rate() */ - if (pkg_stats->rx_frames > (ULONG_MAX / HZ)) + if (rx_frames > (LONG_MAX / HZ)) can_init_stats(net); /* prevent overflow in calc_rate() */ - if (pkg_stats->tx_frames > (ULONG_MAX / HZ)) + if (tx_frames > (LONG_MAX / HZ)) can_init_stats(net); /* matches overflow - very improbable */ - if (pkg_stats->matches > (ULONG_MAX / 100)) + if (matches > (LONG_MAX / 100)) can_init_stats(net); /* calc total values */ - if (pkg_stats->rx_frames) - pkg_stats->total_rx_match_ratio = (pkg_stats->matches * 100) / - pkg_stats->rx_frames; + if (rx_frames) + pkg_stats->total_rx_match_ratio = (matches * 100) / rx_frames; pkg_stats->total_tx_rate = calc_rate(pkg_stats->jiffies_init, j, - pkg_stats->tx_frames); + tx_frames); pkg_stats->total_rx_rate = calc_rate(pkg_stats->jiffies_init, j, - pkg_stats->rx_frames); + rx_frames); /* calc current values */ - if (pkg_stats->rx_frames_delta) + if (rx_frames_delta) pkg_stats->current_rx_match_ratio = - (pkg_stats->matches_delta * 100) / - pkg_stats->rx_frames_delta; + (matches_delta * 100) / rx_frames_delta; - pkg_stats->current_tx_rate = calc_rate(0, HZ, pkg_stats->tx_frames_delta); - pkg_stats->current_rx_rate = calc_rate(0, HZ, pkg_stats->rx_frames_delta); + pkg_stats->current_tx_rate = calc_rate(0, HZ, tx_frames_delta); + pkg_stats->current_rx_rate = calc_rate(0, HZ, rx_frames_delta); /* check / update maximum values */ if (pkg_stats->max_tx_rate < pkg_stats->current_tx_rate) @@ -168,9 +173,9 @@ void can_stat_update(struct timer_list *t) pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio; /* clear values for 'current rate' calculation */ - pkg_stats->tx_frames_delta = 0; - pkg_stats->rx_frames_delta = 0; - pkg_stats->matches_delta = 0; + atomic_long_set(&pkg_stats->tx_frames_delta, 0); + atomic_long_set(&pkg_stats->rx_frames_delta, 0); + atomic_long_set(&pkg_stats->matches_delta, 0); /* restart timer (one second) */ mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ)); @@ -214,9 +219,12 @@ static int can_stats_proc_show(struct seq_file *m, void *v) struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; seq_putc(m, '\n'); - seq_printf(m, " %8ld transmitted frames (TXF)\n", pkg_stats->tx_frames); - seq_printf(m, " %8ld received frames (RXF)\n", pkg_stats->rx_frames); - seq_printf(m, " %8ld matched frames (RXMF)\n", pkg_stats->matches); + seq_printf(m, " %8ld transmitted frames (TXF)\n", + atomic_long_read(&pkg_stats->tx_frames)); + seq_printf(m, " %8ld received frames (RXF)\n", + atomic_long_read(&pkg_stats->rx_frames)); + seq_printf(m, " %8ld matched frames (RXMF)\n", + atomic_long_read(&pkg_stats->matches)); seq_putc(m, '\n'); -- 2.51.0 From 51f6fc9eb1d77ae5cacc796fc043dedc1f0f0073 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Fri, 7 Mar 2025 17:03:26 +0000 Subject: [PATCH 05/16] dt-bindings: can: renesas,rcar-canfd: Fix typo in pattern properties for R-Car V4M The Renesas R-Car V4M(R8A779H0) SoC, supports up to four channels. Fix the typo 5->4 in pattern properties. Fixes: ced52c6ed257 ("dt-bindings: can: renesas,rcar-canfd: Document R-Car V4M support") Cc: stable@vger.kernel.org Reviewed-by: Geert Uytterhoeven Acked-by: "Rob Herring (Arm)" Signed-off-by: Biju Das Link: https://patch.msgid.link/20250307170330.173425-2-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde --- .../devicetree/bindings/net/can/renesas,rcar-canfd.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml index 7c5ac5d2e880..f6884f6e59e7 100644 --- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml +++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml @@ -170,7 +170,7 @@ allOf: const: renesas,r8a779h0-canfd then: patternProperties: - "^channel[5-7]$": false + "^channel[4-7]$": false else: if: not: -- 2.51.0 From 1dba0a37644ed3022558165bbb5cb9bda540eaf7 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Fri, 7 Mar 2025 17:03:27 +0000 Subject: [PATCH 06/16] can: rcar_canfd: Fix page entries in the AFL list There are a total of 96 AFL pages and each page has 16 entries with registers CFDGAFLIDr, CFDGAFLMr, CFDGAFLP0r, CFDGAFLP1r holding the rule entries (r = 0..15). Currently, RCANFD_GAFL* macros use a start variable to find AFL entries, which is incorrect as the testing on RZ/G3E shows ch1 and ch4 gets a start value of 0 and the register contents are overwritten. Fix this issue by using rule_entry corresponding to the channel to find the page entries in the AFL list. Fixes: dd3bd23eb438 ("can: rcar_canfd: Add Renesas R-Car CAN FD driver") Cc: stable@vger.kernel.org Signed-off-by: Biju Das Tested-by: Geert Uytterhoeven Link: https://patch.msgid.link/20250307170330.173425-3-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/rcar/rcar_canfd.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index df1a5d0b37b2..aa3df0d05b85 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -787,22 +787,14 @@ static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv) } static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv, - u32 ch) + u32 ch, u32 rule_entry) { - u32 cfg; - int offset, start, page, num_rules = RCANFD_CHANNEL_NUMRULES; + int offset, page, num_rules = RCANFD_CHANNEL_NUMRULES; + u32 rule_entry_index = rule_entry % 16; u32 ridx = ch + RCANFD_RFFIFO_IDX; - if (ch == 0) { - start = 0; /* Channel 0 always starts from 0th rule */ - } else { - /* Get number of Channel 0 rules and adjust */ - cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG(ch)); - start = RCANFD_GAFLCFG_GETRNC(gpriv, 0, cfg); - } - /* Enable write access to entry */ - page = RCANFD_GAFL_PAGENUM(start); + page = RCANFD_GAFL_PAGENUM(rule_entry); rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR, (RCANFD_GAFLECTR_AFLPN(gpriv, page) | RCANFD_GAFLECTR_AFLDAE)); @@ -818,13 +810,13 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv, offset = RCANFD_C_GAFL_OFFSET; /* Accept all IDs */ - rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, start), 0); + rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, rule_entry_index), 0); /* IDE or RTR is not considered for matching */ - rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, start), 0); + rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, rule_entry_index), 0); /* Any data length accepted */ - rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, start), 0); + rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, rule_entry_index), 0); /* Place the msg in corresponding Rx FIFO entry */ - rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, start), + rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, rule_entry_index), RCANFD_GAFLP1_GAFLFDP(ridx)); /* Disable write access to page */ @@ -1851,6 +1843,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) unsigned long channels_mask = 0; int err, ch_irq, g_irq; int g_err_irq, g_recc_irq; + u32 rule_entry = 0; bool fdmode = true; /* CAN FD only mode - default */ char name[9] = "channelX"; int i; @@ -2023,7 +2016,8 @@ static int rcar_canfd_probe(struct platform_device *pdev) rcar_canfd_configure_tx(gpriv, ch); /* Configure receive rules */ - rcar_canfd_configure_afl_rules(gpriv, ch); + rcar_canfd_configure_afl_rules(gpriv, ch, rule_entry); + rule_entry += RCANFD_CHANNEL_NUMRULES; } /* Configure common interrupts */ -- 2.51.0 From fd99d6ed20234b83d65b9c5417794343577cf3e5 Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Fri, 14 Mar 2025 19:01:44 +0800 Subject: [PATCH 07/16] can: flexcan: only change CAN state when link up in system PM After a suspend/resume cycle on a down interface, it will come up as ERROR-ACTIVE. $ ip -details -s -s a s dev flexcan0 3: flexcan0: mtu 16 qdisc pfifo_fast state DOWN group default qlen 10 link/can promiscuity 0 allmulti 0 minmtu 0 maxmtu 0 can state STOPPED (berr-counter tx 0 rx 0) restart-ms 1000 $ sudo systemctl suspend $ ip -details -s -s a s dev flexcan0 3: flexcan0: mtu 16 qdisc pfifo_fast state DOWN group default qlen 10 link/can promiscuity 0 allmulti 0 minmtu 0 maxmtu 0 can state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 1000 And only set CAN state to CAN_STATE_ERROR_ACTIVE when resume process has no issue, otherwise keep in CAN_STATE_SLEEPING as suspend did. Fixes: 4de349e786a3 ("can: flexcan: fix resume function") Cc: stable@vger.kernel.org Signed-off-by: Haibo Chen Link: https://patch.msgid.link/20250314110145.899179-1-haibo.chen@nxp.com Reported-by: Marc Kleine-Budde Closes: https://lore.kernel.org/all/20250314-married-polar-elephant-b15594-mkl@pengutronix.de [mkl: add newlines] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan/flexcan-core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index ac1a860986df..3a71fd235722 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -2266,8 +2266,9 @@ static int __maybe_unused flexcan_suspend(struct device *device) } netif_stop_queue(dev); netif_device_detach(dev); + + priv->can.state = CAN_STATE_SLEEPING; } - priv->can.state = CAN_STATE_SLEEPING; return 0; } @@ -2278,7 +2279,6 @@ static int __maybe_unused flexcan_resume(struct device *device) struct flexcan_priv *priv = netdev_priv(dev); int err; - priv->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(dev)) { netif_device_attach(dev); netif_start_queue(dev); @@ -2298,6 +2298,8 @@ static int __maybe_unused flexcan_resume(struct device *device) flexcan_chip_interrupts_enable(dev); } + + priv->can.state = CAN_STATE_ERROR_ACTIVE; } return 0; -- 2.51.0 From 5a19143124be42900b3fbc9ada3c919632eb45eb Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Fri, 14 Mar 2025 19:01:45 +0800 Subject: [PATCH 08/16] can: flexcan: disable transceiver during system PM During system PM, if no wakeup requirement, disable transceiver to save power. Fixes: 4de349e786a3 ("can: flexcan: fix resume function") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Signed-off-by: Haibo Chen Link: https://patch.msgid.link/20250314110145.899179-2-haibo.chen@nxp.com [mkl: add newlines] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan/flexcan-core.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 3a71fd235722..b080740bcb10 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -2260,6 +2260,10 @@ static int __maybe_unused flexcan_suspend(struct device *device) flexcan_chip_interrupts_disable(dev); + err = flexcan_transceiver_disable(priv); + if (err) + return err; + err = pinctrl_pm_select_sleep_state(device); if (err) return err; @@ -2292,10 +2296,16 @@ static int __maybe_unused flexcan_resume(struct device *device) if (err) return err; - err = flexcan_chip_start(dev); + err = flexcan_transceiver_enable(priv); if (err) return err; + err = flexcan_chip_start(dev); + if (err) { + flexcan_transceiver_disable(priv); + return err; + } + flexcan_chip_interrupts_enable(dev); } -- 2.51.0 From 5f079290e5913a0060e059500b7d440990ac1066 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Tue, 11 Mar 2025 21:12:59 +0530 Subject: [PATCH 09/16] net: ethernet: ti: am65-cpsw: Fix NAPI registration sequence Registering the interrupts for TX or RX DMA Channels prior to registering their respective NAPI callbacks can result in a NULL pointer dereference. This is seen in practice as a random occurrence since it depends on the randomness associated with the generation of traffic by Linux and the reception of traffic from the wire. Fixes: 681eb2beb3ef ("net: ethernet: ti: am65-cpsw: ensure proper channel cleanup in error path") Signed-off-by: Vignesh Raghavendra Co-developed-by: Siddharth Vadapalli Signed-off-by: Siddharth Vadapalli Reviewed-by: Alexander Sverdlin Reviewed-by: Roger Quadros Link: https://patch.msgid.link/20250311154259.102865-1-s-vadapalli@ti.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 32 +++++++++++++----------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2806238629f8..bef734c6e5c2 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2306,14 +2306,18 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common) static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) { struct device *dev = common->dev; + struct am65_cpsw_tx_chn *tx_chn; int i, ret = 0; for (i = 0; i < common->tx_ch_num; i++) { - struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; + tx_chn = &common->tx_chns[i]; hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback; + netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, + am65_cpsw_nuss_tx_poll); + ret = devm_request_irq(dev, tx_chn->irq, am65_cpsw_nuss_tx_irq, IRQF_TRIGGER_HIGH, @@ -2323,19 +2327,16 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) tx_chn->id, tx_chn->irq, ret); goto err; } - - netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, - am65_cpsw_nuss_tx_poll); } return 0; err: - for (--i ; i >= 0 ; i--) { - struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - - netif_napi_del(&tx_chn->napi_tx); + netif_napi_del(&tx_chn->napi_tx); + for (--i; i >= 0; i--) { + tx_chn = &common->tx_chns[i]; devm_free_irq(dev, tx_chn->irq, tx_chn); + netif_napi_del(&tx_chn->napi_tx); } return ret; @@ -2569,6 +2570,9 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) HRTIMER_MODE_REL_PINNED); flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback; + netif_napi_add(common->dma_ndev, &flow->napi_rx, + am65_cpsw_nuss_rx_poll); + ret = devm_request_irq(dev, flow->irq, am65_cpsw_nuss_rx_irq, IRQF_TRIGGER_HIGH, @@ -2577,11 +2581,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) dev_err(dev, "failure requesting rx %d irq %u, %d\n", i, flow->irq, ret); flow->irq = -EINVAL; - goto err_flow; + goto err_request_irq; } - - netif_napi_add(common->dma_ndev, &flow->napi_rx, - am65_cpsw_nuss_rx_poll); } /* setup classifier to route priorities to flows */ @@ -2589,11 +2590,14 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) return 0; +err_request_irq: + netif_napi_del(&flow->napi_rx); + err_flow: - for (--i; i >= 0 ; i--) { + for (--i; i >= 0; i--) { flow = &rx_chn->flows[i]; - netif_napi_del(&flow->napi_rx); devm_free_irq(dev, flow->irq, flow); + netif_napi_del(&flow->napi_rx); } err: -- 2.51.0 From 2fc8a346625eb1abfe202062c7e6a13d76cde5ea Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Tue, 11 Mar 2025 13:12:54 -0700 Subject: [PATCH 10/16] net: mana: Support holes in device list reply msg According to GDMA protocol, holes (zeros) are allowed at the beginning or middle of the gdma_list_devices_resp message. The existing code cannot properly handle this, and may miss some devices in the list. To fix, scan the entire list until the num_of_devs are found, or until the end of the list. Cc: stable@vger.kernel.org Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)") Signed-off-by: Haiyang Zhang Reviewed-by: Long Li Reviewed-by: Shradha Gupta Reviewed-by: Michal Swiatkowski Link: https://patch.msgid.link/1741723974-1534-1-git-send-email-haiyangz@microsoft.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 14 ++++++++++---- include/net/mana/gdma.h | 11 +++++++---- 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 11457b6296cc..638ef64d639f 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -134,9 +134,10 @@ static int mana_gd_detect_devices(struct pci_dev *pdev) struct gdma_list_devices_resp resp = {}; struct gdma_general_req req = {}; struct gdma_dev_id dev; - u32 i, max_num_devs; + int found_dev = 0; u16 dev_type; int err; + u32 i; mana_gd_init_req_hdr(&req.hdr, GDMA_LIST_DEVICES, sizeof(req), sizeof(resp)); @@ -148,12 +149,17 @@ static int mana_gd_detect_devices(struct pci_dev *pdev) return err ? err : -EPROTO; } - max_num_devs = min_t(u32, MAX_NUM_GDMA_DEVICES, resp.num_of_devs); - - for (i = 0; i < max_num_devs; i++) { + for (i = 0; i < GDMA_DEV_LIST_SIZE && + found_dev < resp.num_of_devs; i++) { dev = resp.devs[i]; dev_type = dev.type; + /* Skip empty devices */ + if (dev.as_uint32 == 0) + continue; + + found_dev++; + /* HWC is already detected in mana_hwc_create_channel(). */ if (dev_type == GDMA_DEVICE_HWC) continue; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 90f56656b572..62e9d7673862 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -408,8 +408,6 @@ struct gdma_context { struct gdma_dev mana_ib; }; -#define MAX_NUM_GDMA_DEVICES 4 - static inline bool mana_gd_is_mana(struct gdma_dev *gd) { return gd->dev_id.type == GDMA_DEVICE_MANA; @@ -556,11 +554,15 @@ enum { #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) #define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5) +/* Driver can handle holes (zeros) in the device list */ +#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11) + #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \ - GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT) + GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \ + GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP) #define GDMA_DRV_CAP_FLAGS2 0 @@ -621,11 +623,12 @@ struct gdma_query_max_resources_resp { }; /* HW DATA */ /* GDMA_LIST_DEVICES */ +#define GDMA_DEV_LIST_SIZE 64 struct gdma_list_devices_resp { struct gdma_resp_hdr hdr; u32 num_of_devs; u32 reserved; - struct gdma_dev_id devs[64]; + struct gdma_dev_id devs[GDMA_DEV_LIST_SIZE]; }; /* HW DATA */ /* GDMA_REGISTER_DEVICE */ -- 2.51.0 From daa624d3c2ddffdcbad140a9625a4064371db44f Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 11 Mar 2025 22:25:30 +0100 Subject: [PATCH 11/16] net: ipv6: fix TCP GSO segmentation with NAT When updating the source/destination address, the TCP/UDP checksum needs to be updated as well. Fixes: bee88cd5bd83 ("net: add support for segmenting TCP fraglist GSO packets") Signed-off-by: Felix Fietkau Link: https://patch.msgid.link/20250311212530.91519-1-nbd@nbd.name Signed-off-by: Paolo Abeni --- net/ipv6/tcpv6_offload.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index a45bf17cb2a1..ae2da28f9dfb 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -94,14 +94,23 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) } static void __tcpv6_gso_segment_csum(struct sk_buff *seg, + struct in6_addr *oldip, + const struct in6_addr *newip, __be16 *oldport, __be16 newport) { - struct tcphdr *th; + struct tcphdr *th = tcp_hdr(seg); + + if (!ipv6_addr_equal(oldip, newip)) { + inet_proto_csum_replace16(&th->check, seg, + oldip->s6_addr32, + newip->s6_addr32, + true); + *oldip = *newip; + } if (*oldport == newport) return; - th = tcp_hdr(seg); inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false); *oldport = newport; } @@ -129,10 +138,10 @@ static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs) th2 = tcp_hdr(seg); iph2 = ipv6_hdr(seg); - iph2->saddr = iph->saddr; - iph2->daddr = iph->daddr; - __tcpv6_gso_segment_csum(seg, &th2->source, th->source); - __tcpv6_gso_segment_csum(seg, &th2->dest, th->dest); + __tcpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, + &th2->source, th->source); + __tcpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, + &th2->dest, th->dest); } return segs; -- 2.51.0 From 9740890ee20e01f99ff1dde84c63dcf089fabb98 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 11 Mar 2025 18:03:25 -0700 Subject: [PATCH 12/16] ipv6: Fix memleak of nhc_pcpu_rth_output in fib_check_nh_v6_gw(). fib_check_nh_v6_gw() expects that fib6_nh_init() cleans up everything when it fails. Commit 7dd73168e273 ("ipv6: Always allocate pcpu memory in a fib6_nh") moved fib_nh_common_init() before alloc_percpu_gfp() within fib6_nh_init() but forgot to add cleanup for fib6_nh->nh_common.nhc_pcpu_rth_output in case it fails to allocate fib6_nh->rt6i_pcpu, resulting in memleak. Let's call fib_nh_common_release() and clear nhc_pcpu_rth_output in the error path. Note that we can remove the fib6_nh_release() call in nh_create_ipv6() later in net-next.git. Fixes: 7dd73168e273 ("ipv6: Always allocate pcpu memory in a fib6_nh") Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250312010333.56001-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- net/ipv6/route.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ef2d23a1e3d5..bc6bcf5d7133 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3644,7 +3644,8 @@ out: in6_dev_put(idev); if (err) { - lwtstate_put(fib6_nh->fib_nh_lws); + fib_nh_common_release(&fib6_nh->nh_common); + fib6_nh->nh_common.nhc_pcpu_rth_output = NULL; fib6_nh->fib_nh_lws = NULL; netdev_put(dev, dev_tracker); } -- 2.51.0 From 9a81fc3480bf5dbe2bf80e278c440770f6ba2692 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 11 Mar 2025 18:38:48 -0700 Subject: [PATCH 13/16] ipv6: Set errno after ip_fib_metrics_init() in ip6_route_info_create(). While creating a new IPv6, we could get a weird -ENOMEM when RTA_NH_ID is set and either of the conditions below is true: 1) CONFIG_IPV6_SUBTREES is enabled and rtm_src_len is specified 2) nexthop_get() fails e.g.) # strace ip -6 route add fe80::dead:beef:dead:beef nhid 1 from :: recvmsg(3, {msg_iov=[{iov_base=[...[ {error=-ENOMEM, msg=[... [...]]}, [{nla_len=49, nla_type=NLMSGERR_ATTR_MSG}, "Nexthops can not be used with so"...] ]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 148 Let's set err explicitly after ip_fib_metrics_init() in ip6_route_info_create(). Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info") Signed-off-by: Kuniyuki Iwashima Reviewed-by: David Ahern Link: https://patch.msgid.link/20250312013854.61125-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- net/ipv6/route.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index bc6bcf5d7133..15ce21afc8c6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3803,10 +3803,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); + err = -EINVAL; goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + err = -ENOENT; goto out_free; } rt->nh = nh; -- 2.51.0 From fa8eda19015ca9ae625f46d4ecb13df651bb54cc Mon Sep 17 00:00:00 2001 From: Przemek Kitszel Date: Thu, 6 Feb 2025 23:30:23 +0100 Subject: [PATCH 14/16] ice: health.c: fix compilation on gcc 7.5 GCC 7 is not as good as GCC 8+ in telling what is a compile-time const, and thus could be used for static storage. Fortunately keeping strings as const arrays is enough to make old gcc happy. Excerpt from the report: My GCC is: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0. CC [M] drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.o drivers/net/ethernet/intel/ice/devlink/health.c:35:3: error: initializer element is not constant ice_common_port_solutions, {ice_port_number_label}}, ^~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/intel/ice/devlink/health.c:35:3: note: (near initialization for 'ice_health_status_lookup[0].solution') drivers/net/ethernet/intel/ice/devlink/health.c:35:31: error: initializer element is not constant ice_common_port_solutions, {ice_port_number_label}}, ^~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/intel/ice/devlink/health.c:35:31: note: (near initialization for 'ice_health_status_lookup[0].data_label[0]') drivers/net/ethernet/intel/ice/devlink/health.c:37:46: error: initializer element is not constant "Change or replace the module or cable.", {ice_port_number_label}}, ^~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/intel/ice/devlink/health.c:37:46: note: (near initialization for 'ice_health_status_lookup[1].data_label[0]') drivers/net/ethernet/intel/ice/devlink/health.c:39:3: error: initializer element is not constant ice_common_port_solutions, {ice_port_number_label}}, ^~~~~~~~~~~~~~~~~~~~~~~~~ Fixes: 85d6164ec56d ("ice: add fw and port health reporters") Reported-by: Qiuxu Zhuo Closes: https://lore.kernel.org/netdev/CY8PR11MB7134BF7A46D71E50D25FA7A989F72@CY8PR11MB7134.namprd11.prod.outlook.com Reviewed-by: Michal Swiatkowski Suggested-by: Simon Horman Signed-off-by: Przemek Kitszel Reviewed-by: Simon Horman Tested-by: Sunitha Mekala (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/devlink/health.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c index ea40f7941259..19c3d37aa768 100644 --- a/drivers/net/ethernet/intel/ice/devlink/health.c +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -25,10 +25,10 @@ struct ice_health_status { * The below lookup requires to be sorted by code. */ -static const char *const ice_common_port_solutions = +static const char ice_common_port_solutions[] = "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex."; -static const char *const ice_port_number_label = "Port Number"; -static const char *const ice_update_nvm_solution = "Update to the latest NVM image."; +static const char ice_port_number_label[] = "Port Number"; +static const char ice_update_nvm_solution[] = "Update to the latest NVM image."; static const struct ice_health_status ice_health_status_lookup[] = { {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.", -- 2.51.0 From 53ce7166cbffd2b8f3bd821fd3918be665afd4c6 Mon Sep 17 00:00:00 2001 From: Karol Kolacinski Date: Wed, 19 Feb 2025 14:13:27 -0800 Subject: [PATCH 15/16] ice: ensure periodic output start time is in the future On E800 series hardware, if the start time for a periodic output signal is programmed into GLTSYN_TGT_H and GLTSYN_TGT_L registers, the hardware logic locks up and the periodic output signal never starts. Any future attempt to reprogram the clock function is futile as the hardware will not reset until a power on. The ice_ptp_cfg_perout function has logic to prevent this, as it checks if the requested start time is in the past. If so, a new start time is calculated by rounding up. Since commit d755a7e129a5 ("ice: Cache perout/extts requests and check flags"), the rounding is done to the nearest multiple of the clock period, rather than to a full second. This is more accurate, since it ensures the signal matches the user request precisely. Unfortunately, there is a race condition with this rounding logic. If the current time is close to the multiple of the period, we could calculate a target time that is extremely soon. It takes time for the software to program the registers, during which time this requested start time could become a start time in the past. If that happens, the periodic output signal will lock up. For large enough periods, or for the logic prior to the mentioned commit, this is unlikely. However, with the new logic rounding to the period and with a small enough period, this becomes inevitable. For example, attempting to enable a 10MHz signal requires a period of 100 nanoseconds. This means in the *best* case, we have 99 nanoseconds to program the clock output. This is essentially impossible, and thus such a small period practically guarantees that the clock output function will lock up. To fix this, add some slop to the clock time used to check if the start time is in the past. Because it is not critical that output signals start immediately, but it *is* critical that we do not brick the function, 0.5 seconds is selected. This does mean that any requested output will be delayed by at least 0.5 seconds. This slop is applied before rounding, so that we always round up to the nearest multiple of the period that is at least 0.5 seconds in the future, ensuring a minimum of 0.5 seconds to program the clock output registers. Finally, to ensure that the hardware registers programming the clock output complete in a timely manner, add a write flush to the end of ice_ptp_write_perout. This ensures we don't risk any issue with PCIe transaction batching. Strictly speaking, this fixes a race condition all the way back at the initial implementation of periodic output programming, as it is theoretically possible to trigger this bug even on the old logic when always rounding to a full second. However, the window is narrow, and the code has been refactored heavily since then, making a direct backport not apply cleanly. Fixes: d755a7e129a5 ("ice: Cache perout/extts requests and check flags") Signed-off-by: Karol Kolacinski Signed-off-by: Jacob Keller Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ptp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e26320ce52ca..a99e0fbd0b8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1783,6 +1783,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, 8 + chan + (tmr_idx * 4)); wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + ice_flush(hw); return 0; } @@ -1843,9 +1844,10 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, div64_u64_rem(start, period, &phase); /* If we have only phase or start time is in the past, start the timer - * at the next multiple of period, maintaining phase. + * at the next multiple of period, maintaining phase at least 0.5 second + * from now, so we have time to write it to HW. */ - clk = ice_ptp_read_src_clk_reg(pf, NULL); + clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500; if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns) start = div64_u64(clk + period - 1, period) * period + phase; -- 2.51.0 From 7fd71f317288d5150d353ce9d65b1e2abf99a8e2 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 6 Mar 2025 09:56:34 -0800 Subject: [PATCH 16/16] ice: fix reservation of resources for RDMA when disabled If the CONFIG_INFINIBAND_IRDMA symbol is not enabled as a module or a built-in, then don't let the driver reserve resources for RDMA. The result of this change is a large savings in resources for older kernels, and a cleaner driver configuration for the IRDMA=n case for old and new kernels. Implement this by avoiding enabling the RDMA capability when scanning hardware capabilities. Note: Loading the out-of-tree irdma driver in connection to the in-kernel ice driver, is not supported, and should not be attempted, especially when disabling IRDMA in the kernel config. Fixes: d25a0fc41c1f ("ice: Initialize RDMA support") Signed-off-by: Jesse Brandeburg Acked-by: Dave Ertman Reviewed-by: Aleksandr Loktionov Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 7a2a2e8da8fa..1e801300310e 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2271,7 +2271,8 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, caps->nvm_unified_update); break; case ICE_AQC_CAPS_RDMA: - caps->rdma = (number == 1); + if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA)) + caps->rdma = (number == 1); ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma); break; case ICE_AQC_CAPS_MAX_MTU: -- 2.51.0