diff options
| author | Linus Torvalds | 2023-12-07 17:04:13 -0800 |
|---|---|---|
| committer | Linus Torvalds | 2023-12-07 17:04:13 -0800 |
| commit | 5e3f5b81de80c98338bcb47c233aebefee5a4801 (patch) | |
| tree | 21b4ee9f1d4ff54e810f5c9d0d29638348b1b4dd | |
| parent | 9ace34a8e446c1a566f3b0a3e0c4c483987e39a6 (diff) | |
| parent | b0a930e8d90caf66a94fee7a9d0b8472bc3e7561 (diff) | |
Merge tag 'net-6.7-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf and netfilter.
Current release - regressions:
- veth: fix packet segmentation in veth_convert_skb_to_xdp_buff
Current release - new code bugs:
- tcp: assorted fixes to the new Auth Option support
Older releases - regressions:
- tcp: fix mid stream window clamp
- tls: fix incorrect splice handling
- ipv4: ip_gre: handle skb_pull() failure in ipgre_xmit()
- dsa: mv88e6xxx: restore USXGMII support for 6393X
- arcnet: restore support for multiple Sohard Arcnet cards
Older releases - always broken:
- tcp: do not accept ACK of bytes we never sent
- require admin privileges to receive packet traces via netlink
- packet: move reference count in packet_sock to atomic_long_t
- bpf:
- fix incorrect branch offset comparison with cpu=v4
- fix prog_array_map_poke_run map poke update
- netfilter:
- three fixes for crashes on bad admin commands
- xt_owner: fix race accessing sk->sk_socket, TOCTOU null-deref
- nf_tables: fix 'exist' matching on bigendian arches
- leds: netdev: fix RTNL handling to prevent potential deadlock
- eth: tg3: prevent races in error/reset handling
- eth: r8169: fix rtl8125b PAUSE storm when suspended
- eth: r8152: improve reset and surprise removal handling
- eth: hns: fix race between changing features and sending
- eth: nfp: fix sleep in atomic for bonding offload"
* tag 'net-6.7-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (62 commits)
vsock/virtio: fix "comparison of distinct pointer types lacks a cast" warning
net/smc: fix missing byte order conversion in CLC handshake
net: dsa: microchip: provide a list of valid protocols for xmit handler
drop_monitor: Require 'CAP_SYS_ADMIN' when joining "events" group
psample: Require 'CAP_NET_ADMIN' when joining "packets" group
bpf: sockmap, updating the sg structure should also update curr
net: tls, update curr on splice as well
nfp: flower: fix for take a mutex lock in soft irq context and rcu lock
net: dsa: mv88e6xxx: Restore USXGMII support for 6393X
tcp: do not accept ACK of bytes we never sent
selftests/bpf: Add test for early update in prog_array_map_poke_run
bpf: Fix prog_array_map_poke_run map poke update
netfilter: xt_owner: Fix for unsafe access of sk->sk_socket
netfilter: nf_tables: validate family when identifying table via handle
netfilter: nf_tables: bail out on mismatching dynset and set expressions
netfilter: nf_tables: fix 'exist' matching on bigendian arches
netfilter: nft_set_pipapo: skip inactive elements during set walk
netfilter: bpf: fix bad registration on nf_defrag
leds: trigger: netdev: fix RTNL handling to prevent potential deadlock
octeontx2-af: Update Tx link register range
...
88 files changed, 821 insertions, 356 deletions
diff --git a/Documentation/networking/tcp_ao.rst b/Documentation/networking/tcp_ao.rst index cfa5bf1cc542..8a58321acce7 100644 --- a/Documentation/networking/tcp_ao.rst +++ b/Documentation/networking/tcp_ao.rst @@ -99,7 +99,7 @@ also [6.1]:: when it is no longer considered permitted. Linux TCP-AO will try its best to prevent you from removing a key that's -being used, considering it a key management failure. But sine keeping +being used, considering it a key management failure. But since keeping an outdated key may become a security issue and as a peer may unintentionally prevent the removal of an old key by always setting it as RNextKeyID - a forced key removal mechanism is provided, where diff --git a/MAINTAINERS b/MAINTAINERS index 788be9ab5b73..a0fb0df07b43 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15066,6 +15066,7 @@ F: lib/random32.c F: net/ F: tools/net/ F: tools/testing/selftests/net/ +X: net/9p/ X: net/bluetooth/ NETWORKING [IPSEC] diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8c10d9abc239..e89e415aa743 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -3025,3 +3025,49 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp #endif WARN(1, "verification of programs using bpf_throw should have failed\n"); } + +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + u8 *old_addr, *new_addr, *old_bypass_addr; + int ret; + + old_bypass_addr = old ? NULL : poke->bypass_addr; + old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; + new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; + + /* + * On program loading or teardown, the program's kallsym entry + * might not be in place, so we use __bpf_arch_text_poke to skip + * the kallsyms check. + */ + if (new) { + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, new_addr); + BUG_ON(ret < 0); + if (!old) { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + poke->bypass_addr, + NULL); + BUG_ON(ret < 0); + } + } else { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + old_bypass_addr, + poke->bypass_addr); + BUG_ON(ret < 0); + /* let other CPUs finish the execution of program + * so that it will not possible to expose them + * to invalid nop, stack unwind, nop state + */ + if (!ret) + synchronize_rcu(); + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, NULL); + BUG_ON(ret < 0); + } +} diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index e358e77e4b38..d76214fa9ad8 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -226,6 +226,11 @@ static int set_device_name(struct led_netdev_data *trigger_data, cancel_delayed_work_sync(&trigger_data->work); + /* + * Take RTNL lock before trigger_data lock to prevent potential + * deadlock with netdev notifier registration. + */ + rtnl_lock(); mutex_lock(&trigger_data->lock); if (trigger_data->net_dev) { @@ -245,16 +250,14 @@ static int set_device_name(struct led_netdev_data *trigger_data, trigger_data->carrier_link_up = false; trigger_data->link_speed = SPEED_UNKNOWN; trigger_data->duplex = DUPLEX_UNKNOWN; - if (trigger_data->net_dev != NULL) { - rtnl_lock(); + if (trigger_data->net_dev) get_device_state(trigger_data); - rtnl_unlock(); - } trigger_data->last_activity = 0; set_baseline_state(trigger_data); mutex_unlock(&trigger_data->lock); + rtnl_unlock(); return 0; } diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 19e996a829c9..b54275389f8a 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -186,6 +186,8 @@ do { \ #define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ #define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, but default is 2.5MBit. */ +#define ARC_HAS_LED 4 /* card has software controlled LEDs */ +#define ARC_HAS_ROTARY 8 /* card has rotary encoder */ /* information needed to define an encapsulation driver */ struct ArcProto { diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index c580acb8b1d3..7b5c8bb02f11 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -213,12 +213,13 @@ static int com20020pci_probe(struct pci_dev *pdev, if (!strncmp(ci->name, "EAE PLX-PCI FB2", 15)) lp->backplane = 1; - /* Get the dev_id from the PLX rotary coder */ - if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) - dev_id_mask = 0x3; - dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; - - snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); + if (ci->flags & ARC_HAS_ROTARY) { + /* Get the dev_id from the PLX rotary coder */ + if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) + dev_id_mask = 0x3; + dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; + snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); + } if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { pr_err("IO address %Xh is empty!\n", ioaddr); @@ -230,6 +231,10 @@ static int com20020pci_probe(struct pci_dev *pdev, goto err_free_arcdev; } + ret = com20020_found(dev, IRQF_SHARED); + if (ret) + goto err_free_arcdev; + card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev), GFP_KERNEL); if (!card) { @@ -239,41 +244,39 @@ static int com20020pci_probe(struct pci_dev *pdev, card->index = i; card->pci_priv = priv; - card->tx_led.brightness_set = led_tx_set; - card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "arc%d-%d-tx", - dev->dev_id, i); - card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "pci:green:tx:%d-%d", - dev->dev_id, i); - - card->tx_led.dev = &dev->dev; - card->recon_led.brightness_set = led_recon_set; - card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "arc%d-%d-recon", - dev->dev_id, i); - card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "pci:red:recon:%d-%d", - dev->dev_id, i); - card->recon_led.dev = &dev->dev; - card->dev = dev; - - ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); - if (ret) - goto err_free_arcdev; - ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); - if (ret) - goto err_free_arcdev; - - dev_set_drvdata(&dev->dev, card); - - ret = com20020_found(dev, IRQF_SHARED); - if (ret) - goto err_free_arcdev; - - devm_arcnet_led_init(dev, dev->dev_id, i); + if (ci->flags & ARC_HAS_LED) { + card->tx_led.brightness_set = led_tx_set; + card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "arc%d-%d-tx", + dev->dev_id, i); + card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pci:green:tx:%d-%d", + dev->dev_id, i); + + card->tx_led.dev = &dev->dev; + card->recon_led.brightness_set = led_recon_set; + card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "arc%d-%d-recon", + dev->dev_id, i); + card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pci:red:recon:%d-%d", + dev->dev_id, i); + card->recon_led.dev = &dev->dev; + + ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); + if (ret) + goto err_free_arcdev; + + ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); + if (ret) + goto err_free_arcdev; + + dev_set_drvdata(&dev->dev, card); + devm_arcnet_led_init(dev, dev->dev_id, i); + } + card->dev = dev; list_add(&card->list, &priv->list_dev); continue; @@ -329,7 +332,7 @@ static struct com20020_pci_card_info card_info_5mbit = { }; static struct com20020_pci_card_info card_info_sohard = { - .name = "PLX-PCI", + .name = "SOHARD SH ARC-PCI", .devcount = 1, /* SOHARD needs PCI base addr 4 */ .chan_map_tbl = { @@ -364,7 +367,7 @@ static struct com20020_pci_card_info card_info_eae_arc1 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, }; static struct com20020_pci_card_info card_info_eae_ma1 = { @@ -396,7 +399,7 @@ static struct com20020_pci_card_info card_info_eae_ma1 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, }; static struct com20020_pci_card_info card_info_eae_fb2 = { @@ -421,7 +424,7 @@ static struct com20020_pci_card_info card_info_eae_fb2 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, }; static const struct pci_device_id com20020pci_id_table[] = { diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 3fed406fb46a..ff4b39601c93 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2713,10 +2713,18 @@ static int ksz_connect_tag_protocol(struct dsa_switch *ds, { struct ksz_tagger_data *tagger_data; - tagger_data = ksz_tagger_data(ds); - tagger_data->xmit_work_fn = ksz_port_deferred_xmit; - - return 0; + switch (proto) { + case DSA_TAG_PROTO_KSZ8795: + return 0; + case DSA_TAG_PROTO_KSZ9893: + case DSA_TAG_PROTO_KSZ9477: + case DSA_TAG_PROTO_LAN937X: + tagger_data = ksz_tagger_data(ds); + tagger_data->xmit_work_fn = ksz_port_deferred_xmit; + return 0; + default: + return -EPROTONOSUPPORT; + } } static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c index 9a8429f5d09c..d758a6c1b226 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c @@ -465,6 +465,7 @@ mv88e639x_pcs_select(struct mv88e6xxx_chip *chip, int port, case PHY_INTERFACE_MODE_10GBASER: case PHY_INTERFACE_MODE_XAUI: case PHY_INTERFACE_MODE_RXAUI: + case PHY_INTERFACE_MODE_USXGMII: return &mpcs->xg_pcs; default: @@ -873,7 +874,8 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs, struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); int err; - if (interface == PHY_INTERFACE_MODE_10GBASER) { + if (interface == PHY_INTERFACE_MODE_10GBASER || + interface == PHY_INTERFACE_MODE_USXGMII) { err = mv88e6393x_erratum_5_2(mpcs); if (err) return err; @@ -886,12 +888,37 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs, return mv88e639x_xg_pcs_enable(mpcs); } +static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); + u16 status, lp_status; + int err; + + if (state->interface != PHY_INTERFACE_MODE_USXGMII) + return mv88e639x_xg_pcs_get_state(pcs, state); + + state->link = false; + + err = mv88e639x_read(mpcs, MV88E6390_USXGMII_PHY_STATUS, &status); + err = err ? : mv88e639x_read(mpcs, MV88E6390_USXGMII_LP_STATUS, &lp_status); + if (err) { + dev_err(mpcs->mdio.dev.parent, + "can't read USXGMII status: %pe\n", ERR_PTR(err)); + return; + } + + state->link = !!(status & MDIO_USXGMII_LINK); + state->an_complete = state->link; + phylink_decode_usxgmii_word(state, lp_status); +} + static const struct phylink_pcs_ops mv88e6393x_xg_pcs_ops = { .pcs_enable = mv88e6393x_xg_pcs_enable, .pcs_disable = mv88e6393x_xg_pcs_disable, .pcs_pre_config = mv88e6393x_xg_pcs_pre_config, .pcs_post_config = mv88e6393x_xg_pcs_post_config, - .pcs_get_state = mv88e639x_xg_pcs_get_state, + .pcs_get_state = mv88e6393x_xg_pcs_get_state, .pcs_config = mv88e639x_xg_pcs_config, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c index 80b44043e6c5..28c9b6f1a54f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c @@ -553,17 +553,17 @@ void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp) /* aq_ptp_rx_hwtstamp - utility function which checks for RX time stamp * @adapter: pointer to adapter struct - * @skb: particular skb to send timestamp with + * @shhwtstamps: particular skb_shared_hwtstamps to save timestamp * * if the timestamp is valid, we convert it into the timecounter ns * value, then store that result into the hwtstamps structure which * is passed up the network stack */ -static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct sk_buff *skb, +static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct skb_shared_hwtstamps *shhwtstamps, u64 timestamp) { timestamp -= atomic_read(&aq_ptp->offset_ingress); - aq_ptp_convert_to_hwtstamp(aq_ptp, skb_hwtstamps(skb), timestamp); + aq_ptp_convert_to_hwtstamp(aq_ptp, shhwtstamps, timestamp); } void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp, @@ -639,7 +639,7 @@ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring) &aq_ptp->ptp_rx == ring || &aq_ptp->hwts_rx == ring; } -u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p, +u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p, unsigned int len) { struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp; @@ -648,7 +648,7 @@ u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p, p, len, ×tamp); if (ret > 0) - aq_ptp_rx_hwtstamp(aq_ptp, skb, timestamp); + aq_ptp_rx_hwtstamp(aq_ptp, shhwtstamps, timestamp); return ret; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h index 28ccb7ca2df9..210b723f2207 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h @@ -67,7 +67,7 @@ int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp, /* Return either ring is belong to PTP or not*/ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring); -u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p, +u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p, unsigned int len); struct ptp_clock *aq_ptp_get_ptp_clock(struct aq_ptp_s *aq_ptp); @@ -143,7 +143,7 @@ static inline bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring) } static inline u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, - struct sk_buff *skb, u8 *p, + struct skb_shared_hwtstamps *shhwtstamps, u8 *p, unsigned int len) { return 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4de22eed099a..694daeaf3e61 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -647,7 +647,7 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, } if (is_ptp_ring) buff->len -= - aq_ptp_extract_ts(self->aq_nic, skb, + aq_ptp_extract_ts(self->aq_nic, skb_hwtstamps(skb), aq_buf_vaddr(&buff->rxdata), buff->len); @@ -742,6 +742,8 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring, struct aq_ring_buff_s *buff = &rx_ring->buff_ring[rx_ring->sw_head]; bool is_ptp_ring = aq_ptp_ring(rx_ring->aq_nic, rx_ring); struct aq_ring_buff_s *buff_ = NULL; + u16 ptp_hwtstamp_len = 0; + struct skb_shared_hwtstamps shhwtstamps; struct sk_buff *skb = NULL; unsigned int next_ = 0U; struct xdp_buff xdp; @@ -810,11 +812,12 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring, hard_start = page_address(buff->rxdata.page) + buff->rxdata.pg_off - rx_ring->page_offset; - if (is_ptp_ring) - buff->len -= - aq_ptp_extract_ts(rx_ring->aq_nic, skb, - aq_buf_vaddr(&buff->rxdata), - buff->len); + if (is_ptp_ring) { + ptp_hwtstamp_len = aq_ptp_extract_ts(rx_ring->aq_nic, &shhwtstamps, + aq_buf_vaddr(&buff->rxdata), + buff->len); + buff->len -= ptp_hwtstamp_len; + } xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); xdp_prepare_buff(&xdp, hard_start, rx_ring->page_offset, @@ -834,6 +837,9 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring, if (IS_ERR(skb) || !skb) continue; + if (ptp_hwtstamp_len > 0) + *skb_hwtstamps(skb) = shhwtstamps; + if (buff->is_vlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), buff->vlan_rx_tag); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 38d89d80b4a9..273c9ba48f09 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -2075,6 +2075,7 @@ destroy_flow_table: rhashtable_destroy(&tc_info->flow_table); free_tc_info: kfree(tc_info); + bp->tc_info = NULL; return rc; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 48b6191efa56..f52830dfb26a 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6474,6 +6474,14 @@ static void tg3_dump_state(struct tg3 *tp) int i; u32 *regs; + /* If it is a PCI error, all registers will be 0xffff, + * we don't dump them out, just report the error and return + */ + if (tp->pdev->error_state != pci_channel_io_normal) { + netdev_err(tp->dev, "PCI channel ERROR!\n"); + return; + } + regs = kzalloc(TG3_REG_BLK_SIZE, GFP_ATOMIC); if (!regs) return; @@ -11259,7 +11267,8 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0); - if (tp->pcierr_recovery || !netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev) || + tp->pdev->error_state != pci_channel_io_normal) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 928d934cb21a..f75668c47935 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -66,6 +66,27 @@ static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb) } } +static u32 hns_mac_link_anti_shake(struct mac_driver *mac_ctrl_drv) +{ +#define HNS_MAC_LINK_WAIT_TIME 5 +#define HNS_MAC_LINK_WAIT_CNT 40 + + u32 link_status = 0; + int i; + + if (!mac_ctrl_drv->get_link_status) + return link_status; + + for (i = 0; i < HNS_MAC_LINK_WAIT_CNT; i++) { + msleep(HNS_MAC_LINK_WAIT_TIME); + mac_ctrl_drv->get_link_status(mac_ctrl_drv, &link_status); + if (!link_status) + break; + } + + return link_status; +} + void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) { struct mac_driver *mac_ctrl_drv; @@ -83,6 +104,14 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) &sfp_prsnt); if (!ret) *link_status = *link_status && sfp_prsnt; + + /* for FIBER port, it may have a fake link up. + * when the link status changes from down to up, we need to do + * anti-shake. the anti-shake time is base on tests. + * only FIBER port need to do this. + */ + if (*link_status && !mac_cb->link) + *link_status = hns_mac_link_anti_shake(mac_ctrl_drv); } mac_cb->link = *link_status; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 0900abf5c508..8a713eed4465 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -142,7 +142,8 @@ MODULE_DEVICE_TABLE(acpi, hns_enet_acpi_match); static void fill_desc(struct hnae_ring *ring, void *priv, int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu) + int buf_num, enum hns_desc_type type, int mtu, + bool is_gso) { struct hnae_desc *desc = &ring->desc[ring->next_to_use]; struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; @@ -275,6 +276,15 @@ static int hns_nic_maybe_stop_tso( return 0; } +static int hns_nic_maybe_stop_tx_v2(struct sk_buff **out_skb, int *bnum, + struct hnae_ring *ring) +{ + if (skb_is_gso(*out_skb)) + return hns_nic_maybe_stop_tso(out_skb, bnum, ring); + else + return hns_nic_maybe_stop_tx(out_skb, bnum, ring); +} + static void fill_tso_desc(struct hnae_ring *ring, void *priv, int size, dma_addr_t dma, int frag_end, int buf_num, enum hns_desc_type type, int mtu) @@ -300,6 +310,19 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv, mtu); } +static void fill_desc_v2(struct hnae_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu, + bool is_gso) +{ + if (is_gso) + fill_tso_desc(ring, priv, size, dma, frag_end, buf_num, type, + mtu); + else + fill_v2_desc(ring, priv, size, dma, frag_end, buf_num, type, + mtu); +} + netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, struct sk_buff *skb, struct hns_nic_ring_data *ring_data) @@ -313,6 +336,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, int seg_num; dma_addr_t dma; int size, next_to_use; + bool is_gso; int i; switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) { @@ -339,8 +363,9 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, ring->stats.sw_err_cnt++; goto out_err_tx_ok; } + is_gso = skb_is_gso(skb); priv->ops.fill_desc(ring, skb, size, dma, seg_num == 1 ? 1 : 0, - buf_num, DESC_TYPE_SKB, ndev->mtu); + buf_num, DESC_TYPE_SKB, ndev->mtu, is_gso); /* fill the fragments */ for (i = 1; i < seg_num; i++) { @@ -354,7 +379,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, } priv->ops.fill_desc(ring, skb_frag_page(frag), size, dma, seg_num - 1 == i ? 1 : 0, buf_num, - DESC_TYPE_PAGE, ndev->mtu); + DESC_TYPE_PAGE, ndev->mtu, is_gso); } /*complete translate all packets*/ @@ -1776,15 +1801,6 @@ static int hns_nic_set_features(struct net_device *netdev, netdev_info(netdev, "enet v1 do not support tso!\n"); break; default: - if (features & (NETIF_F_TSO | NETIF_F_TSO6)) { - priv->ops.fill_desc = fill_tso_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso; - /* The chip only support 7*4096 */ - netif_set_tso_max_size(netdev, 7 * 4096); - } else { - priv->ops.fill_desc = fill_v2_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx; - } break; } netdev->features = features; @@ -2159,16 +2175,9 @@ static void hns_nic_set_priv_ops(struct net_device *netdev) priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx; } else { priv->ops.get_rxd_bnum = get_v2rx_desc_bnum; - if ((netdev->features & NETIF_F_TSO) || - (netdev->features & NETIF_F_TSO6)) { - priv->ops.fill_desc = fill_tso_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso; - /* This chip only support 7*4096 */ - netif_set_tso_max_size(netdev, 7 * 4096); - } else { - priv->ops.fill_desc = fill_v2_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx; - } + priv->ops.fill_desc = fill_desc_v2; + priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx_v2; + netif_set_tso_max_size(netdev, 7 * 4096); /* enable tso when init * control tso on/off through TSE bit in bd */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h index ffa9d6573f54..3f3ee032f631 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -44,7 +44,8 @@ struct hns_nic_ring_data { struct hns_nic_ops { void (*fill_desc)(struct hnae_ring *ring, void *priv, int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu); + int buf_num, enum hns_desc_type type, int mtu, + bool is_gso); int (*maybe_stop_tx)(struct sk_buff **out_skb, int *bnum, struct hnae_ring *ring); void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f7a332e51524..1ab8dbe2d880 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16224,7 +16224,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; if (val < MAX_FRAME_SIZE_DEFAULT) dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", - i, val); + pf->hw.port, val); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 6f236d1a6444..19cbfe554689 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -827,18 +827,10 @@ static int __iavf_set_coalesce(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); int i; - if (ec->rx_coalesce_usecs == 0) { - if (ec->use_adaptive_rx_coalesce) - netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) || - (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) { + if (ec->rx_coalesce_usecs > IAVF_MAX_ITR) { netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; - } else if (ec->tx_coalesce_usecs == 0) { - if (ec->use_adaptive_tx_coalesce) - netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) || - (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) { + } else if (ec->tx_coalesce_usecs > IAVF_MAX_ITR) { netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 7e6ee32d19b6..10ba36602c0c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -15,7 +15,6 @@ */ #define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */ -#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */ #define IAVF_ITR_100K 10 /* all values below must be even */ #define IAVF_ITR_50K 20 #define IAVF_ITR_20K 50 diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 2a5e6616cc0a..e1494f24f661 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -374,16 +374,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) */ int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) { - struct ice_pf *pf; - if (!vf || !q_vector) return -EINVAL; - pf = vf->pf; - /* always add one to account for the OICR being the first MSIX */ - return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id + - q_vector->v_idx + 1; + return vf->first_vector_idx + q_vector->v_idx + 1; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index d7b10dc67f03..80dc4bcdd3a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -32,7 +32,6 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) /* setup outer VLAN ops */ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; /* setup inner VLAN ops */ vlan_ops = &vsi->inner_vlan_ops; @@ -47,8 +46,13 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; } + + /* all Rx traffic should be in the domain of the assigned port VLAN, + * so prevent disabling Rx VLAN filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; } @@ -77,6 +81,8 @@ static void ice_port_vlan_off(struct ice_vsi *vsi) vlan_ops->del_vlan = ice_vsi_del_vlan; } + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -141,7 +147,6 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index de11b3186bd7..1c7b4ded948b 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1523,7 +1523,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) u16 num_q_vectors_mapped, vsi_id, vector_id; struct virtchnl_irq_map_info *irqmap_info; struct virtchnl_vector_map *map; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; int i; @@ -1535,7 +1534,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) * there is actually at least a single VF queue vector mapped */ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - pf->vfs.num_msix_per < num_q_vectors_mapped || + vf->num_msix < num_q_vectors_mapped || !num_q_vectors_mapped) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -1557,7 +1556,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) /* vector_id is always 0-based for each VF, and can never be * larger than or equal to the max allowed interrupts per VF */ - if (!(vector_id < pf->vfs.num_msix_per) || + if (!(vector_id < vf->num_msix) || !ice_vc_isvalid_vsi_id(vf, vsi_id) || (!vector_id && (map->rxq_map || map->txq_map))) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6845556581c3..5df42634ceb8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1945,7 +1945,7 @@ struct mcs_hw_info { u8 tcam_entries; /* RX/TX Tcam entries per mcs block */ u8 secy_entries; /* RX/TX SECY entries per mcs block */ u8 sc_entries; /* RX/TX SC CAM entries per mcs block */ - u8 sa_entries; /* PN table entries = SA entries */ + u16 sa_entries; /* PN table entries = SA entries */ u64 rsvd[16]; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index c43f19dfbd74..c1775bd01c2b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -117,7 +117,7 @@ void mcs_get_rx_secy_stats(struct mcs *mcs, struct mcs_secy_stats *stats, int id reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYTAGGEDCTLX(id); stats->pkt_tagged_ctl_cnt = mcs_reg_read(mcs, reg); - reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(id); + reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(id); stats->pkt_untaged_cnt = mcs_reg_read(mcs, reg); reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(id); @@ -215,7 +215,7 @@ void mcs_get_sc_stats(struct mcs *mcs, struct mcs_sc_stats *stats, reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCNOTVALIDX(id); stats->pkt_notvalid_cnt = mcs_reg_read(mcs, reg); - reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(id); + reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(id); stats->pkt_unchecked_cnt = mcs_reg_read(mcs, reg); if (mcs->hw->mcs_blks > 1) { @@ -1219,6 +1219,17 @@ struct mcs *mcs_get_pdata(int mcs_id) return NULL; } +bool is_mcs_bypass(int mcs_id) +{ + struct mcs *mcs_dev; + + list_for_each_entry(mcs_dev, &mcs_list, mcs_list) { + if (mcs_dev->mcs_id == mcs_id) + return mcs_dev->bypass; + } + return true; +} + void mcs_set_port_cfg(struct mcs *mcs, struct mcs_port_cfg_set_req *req) { u64 val = 0; @@ -1436,7 +1447,7 @@ static int mcs_x2p_calibration(struct mcs *mcs) return err; } -static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass) +static void mcs_set_external_bypass(struct mcs *mcs, bool bypass) { u64 val; @@ -1447,6 +1458,7 @@ static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass) else val &= ~BIT_ULL(6); mcs_reg_write(mcs, MCSX_MIL_GLOBAL, val); + mcs->bypass = bypass; } static void mcs_global_cfg(struct mcs *mcs) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h index 0f89dcb76465..f927cc61dfd2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h @@ -149,6 +149,7 @@ struct mcs { u16 num_vec; void *rvu; u16 *tx_sa_active; + bool bypass; }; struct mcs_ops { @@ -206,6 +207,7 @@ void mcs_get_custom_tag_cfg(struct mcs *mcs, struct mcs_custom_tag_cfg_get_req * int mcs_alloc_ctrlpktrule(struct rsrc_bmap *rsrc, u16 *pf_map, u16 offset, u16 pcifunc); int mcs_free_ctrlpktrule(struct mcs *mcs, struct mcs_free_ctrl_pkt_rule_req *req); int mcs_ctrlpktrule_write(struct mcs *mcs, struct mcs_ctrl_pkt_rule_write_req *req); +bool is_mcs_bypass(int mcs_id); /* CN10K-B APIs */ void cn10kb_mcs_set_hw_capabilities(struct mcs *mcs); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h index f3ab01fc363c..f4c6de89002c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h @@ -810,14 +810,37 @@ offset = 0x9d8ull; \ offset; }) +#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(a) ({ \ + u64 offset; \ + \ + offset = 0xee80ull; \ + if (mcs->hw->mcs_blks > 1) \ + offset = 0xe818ull; \ + offset += (a) * 0x8ull; \ + offset; }) + +#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a) ({ \ + u64 offset; \ + \ + offset = 0xa680ull; \ + if (mcs->hw->mcs_blks > 1) \ + offset = 0xd018ull; \ + offset += (a) * 0x8ull; \ + offset; }) + +#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a) ({ \ + u64 offset; \ + \ + offset = 0xf680ull; \ + if (mcs->hw->mcs_blks > 1) \ + offset = 0xe018ull; \ + offset += (a) * 0x8ull; \ + offset; }) + #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCDECRYPTEDX(a) (0xe680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCVALIDATEX(a) (0xde80ull + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(a) (0xa680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYNOTAGX(a) (0xd218 + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a) (0xd018ull + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(a) (0xee80ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(a) (0xb680ull + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a) (0xf680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSAINVALIDX(a) (0x12680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTUSINGSAERRORX(a) (0x15680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTVALIDX(a) (0x13680ull + (a) * 0x8ull) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 22c395c7d040..731bb82b577c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2631,6 +2631,9 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc) rvu_npc_free_mcam_entries(rvu, pcifunc, -1); rvu_mac_reset(rvu, pcifunc); + if (rvu->mcs_blk_cnt) + rvu_mcs_flr_handler(rvu, pcifunc); + mutex_unlock(&rvu->flr_lock); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index c4d999ef5ab4..cce2806aaa50 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -345,6 +345,7 @@ struct nix_hw { struct nix_txvlan txvlan; struct nix_ipolicer *ipolicer; u64 *tx_credits; + u8 cc_mcs_cnt; }; /* RVU block's capabilities or functionality, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index c70932625d0d..62780d8b4f9a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1087,7 +1087,7 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl) rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq"); if (!rvu_dl->devlink_wq) - goto err; + return -ENOMEM; INIT_WORK(&rvu_reporters->intr_work, rvu_npa_intr_work); INIT_WORK(&rvu_reporters->err_work, rvu_npa_err_work); @@ -1095,9 +1095,6 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl) INIT_WORK(&rvu_reporters->ras_work, rvu_npa_ras_work); return 0; -err: - rvu_npa_health_reporters_destroy(rvu_dl); - return -ENOMEM; } static int rvu_npa_health_reporters_create(struct rvu_devlink *rvu_dl) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index c112c71ff576..4227ebb4a758 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -12,6 +12,7 @@ #include "rvu_reg.h" #include "rvu.h" #include "npc.h" +#include "mcs.h" #include "cgx.h" #include "lmac_common.h" #include "rvu_npc_hash.h" @@ -4389,6 +4390,12 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS); } + /* Get MCS external bypass status for CN10K-B */ + if (mcs_get_blkcnt() == 1) { + /* Adjust for 2 credits when external bypass is disabled */ + nix_hw->cc_mcs_cnt = is_mcs_bypass(0) ? 0 : 2; + } + /* Set credits for Tx links assuming max packet length allowed. * This will be reconfigured based on MTU set for PF/VF. */ @@ -4412,6 +4419,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, tx_credits = (lmac_fifo_len - lmac_max_frs) / 16; /* Enable credits and set credit pkt count to max allowed */ cfg = (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1); + cfg |= FIELD_PREP(NIX_AF_LINKX_MCS_CNT_MASK, nix_hw->cc_mcs_cnt); link = iter + slink; nix_hw->tx_credits[link] = tx_credits; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 16cfc802e348..f65805860c8d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -389,7 +389,13 @@ static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, int bank, nixlf, index; /* get ucast entry rule entry index */ - nix_get_nixlf(rvu, pf_func, &nixlf, NULL); + if (nix_get_nixlf(rvu, pf_func, &nixlf, NULL)) { + dev_err(rvu->dev, "%s: nixlf not attached to pcifunc:0x%x\n", + __func__, pf_func); + /* Action 0 is drop */ + return 0; + } + index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf, NIXLF_UCAST_ENTRY); bank = npc_get_bank(mcam, index); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c index b3150f053291..d46ac29adb96 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c @@ -31,8 +31,8 @@ static struct hw_reg_map txsch_reg_map[NIX_TXSCH_LVL_CNT] = { {NIX_TXSCH_LVL_TL4, 3, 0xFFFF, {{0x0B00, 0x0B08}, {0x0B10, 0x0B18}, {0x1200, 0x12E0} } }, {NIX_TXSCH_LVL_TL3, 4, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608}, - {0x1610, 0x1618}, {0x1700, 0x17B0} } }, - {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } }, + {0x1610, 0x1618}, {0x1700, 0x17C8} } }, + {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17C8} } }, {NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } }, }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index b42e631e52d0..18c1c9f361cc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -437,6 +437,7 @@ #define NIX_AF_LINKX_BASE_MASK GENMASK_ULL(11, 0) #define NIX_AF_LINKX_RANGE_MASK GENMASK_ULL(19, 16) +#define NIX_AF_LINKX_MCS_CNT_MASK GENMASK_ULL(33, 32) /* SSO */ #define SSO_AF_CONST (0x1000) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 9efcec549834..53f6258a973c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -334,9 +334,12 @@ static void otx2_get_pauseparam(struct net_device *netdev, if (is_otx2_lbkvf(pfvf->pdev)) return; + mutex_lock(&pfvf->mbox.lock); req = otx2_mbox_alloc_msg_cgx_cfg_pause_frm(&pfvf->mbox); - if (!req) + if (!req) { + mutex_unlock(&pfvf->mbox.lock); return; + } if (!otx2_sync_mbox_msg(&pfvf->mbox)) { rsp = (struct cgx_pause_frm_cfg *) @@ -344,6 +347,7 @@ static void otx2_get_pauseparam(struct net_device *netdev, pause->rx_pause = rsp->rx_pause; pause->tx_pause = rsp->tx_pause; } + mutex_unlock(&pfvf->mbox.lock); } static int otx2_set_pauseparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 532e324bdcc8..0c17ebdda148 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1688,6 +1688,14 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf) mutex_unlock(&pf->mbox.lock); } +static void otx2_set_irq_coalesce(struct otx2_nic *pfvf) +{ + int cint; + + for (cint = 0; cint < pfvf->hw.cint_cnt; cint++) + otx2_config_irq_coalescing(pfvf, cint); +} + static void otx2_dim_work(struct work_struct *w) { struct dim_cq_moder cur_moder; @@ -1703,6 +1711,7 @@ static void otx2_dim_work(struct work_struct *w) CQ_TIMER_THRESH_MAX : cur_moder.usec; pfvf->hw.cq_ecount_wait = (cur_moder.pkts > NAPI_POLL_WEIGHT) ? NAPI_POLL_WEIGHT : cur_moder.pkts; + otx2_set_irq_coalesce(pfvf); dim->state = DIM_START_MEASURE; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 6ee15f3c25ed..4d519ea833b2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -512,11 +512,18 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p { struct dim_sample dim_sample; u64 rx_frames, rx_bytes; + u64 tx_frames, tx_bytes; rx_frames = OTX2_GET_RX_STATS(RX_BCAST) + OTX2_GET_RX_STATS(RX_MCAST) + OTX2_GET_RX_STATS(RX_UCAST); rx_bytes = OTX2_GET_RX_STATS(RX_OCTS); - dim_update_sample(pfvf->napi_events, rx_frames, rx_bytes, &dim_sample); + tx_bytes = OTX2_GET_TX_STATS(TX_OCTS); + tx_frames = OTX2_GET_TX_STATS(TX_UCAST); + + dim_update_sample(pfvf->napi_events, + rx_frames + tx_frames, + rx_bytes + tx_bytes, + &dim_sample); net_dim(&cq_poll->dim, dim_sample); } @@ -558,16 +565,9 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) if (pfvf->flags & OTX2_FLAG_INTF_DOWN) return workdone; - /* Check for adaptive interrupt coalesce */ - if (workdone != 0 && - ((pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) == - OTX2_FLAG_ADPTV_INT_COAL_ENABLED)) { - /* Adjust irq coalese using net_dim */ + /* Adjust irq coalese using net_dim */ + if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) otx2_adjust_adaptive_coalese(pfvf, cq_poll); - /* Update irq coalescing */ - for (i = 0; i < pfvf->hw.cint_cnt; i++) - otx2_config_irq_coalescing(pfvf, i); - } if (unlikely(!filled_cnt)) { struct refill_work *work; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 060a77f2265d..e522845c7c21 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -160,6 +160,18 @@ struct nfp_tun_mac_addr_offload { u8 addr[ETH_ALEN]; }; +/** + * struct nfp_neigh_update_work - update neighbour information to nfp + * @work: Work queue for writing neigh to the nfp + * @n: neighbour entry + * @app: Back pointer to app + */ +struct nfp_neigh_update_work { + struct work_struct work; + struct neighbour *n; + struct nfp_app *app; +}; + enum nfp_flower_mac_offload_cmd { NFP_TUNNEL_MAC_OFFLOAD_ADD = 0, NFP_TUNNEL_MAC_OFFLOAD_DEL = 1, @@ -607,38 +619,30 @@ err: nfp_flower_cmsg_warn(app, "Neighbour configuration failed.\n"); } -static int -nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, - void *ptr) +static void +nfp_tun_release_neigh_update_work(struct nfp_neigh_update_work *update_work) { - struct nfp_flower_priv *app_priv; - struct netevent_redirect *redir; - struct neighbour *n; + neigh_release(update_work->n); + kfree(update_work); +} + +static void nfp_tun_neigh_update(struct work_struct *work) +{ + struct nfp_neigh_update_work *update_work; struct nfp_app *app; + struct neighbour *n; bool neigh_invalid; int err; - switch (event) { - case NETEVENT_REDIRECT: - redir = (struct netevent_redirect *)ptr; - n = redir->neigh; - break; - case NETEVENT_NEIGH_UPDATE: - n = (struct neighbour *)ptr; - break; - default: - return NOTIFY_DONE; - } - - neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead; - - app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb); - app = app_priv->app; + update_work = container_of(work, struct nfp_neigh_update_work, work); + app = update_work->app; + n = update_work->n; if (!nfp_flower_get_port_id_from_netdev(app, n->dev)) - return NOTIFY_DONE; + goto out; #if IS_ENABLED(CONFIG_INET) + neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead; if (n->tbl->family == AF_INET6) { #if IS_ENABLED(CONFIG_IPV6) struct flowi6 flow6 = {}; @@ -655,13 +659,11 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, dst = ip6_dst_lookup_flow(dev_net(n->dev), NULL, &flow6, NULL); if (IS_ERR(dst)) - return NOTIFY_DONE; + goto out; dst_release(dst); } nfp_tun_write_neigh(n->dev, app, &flow6, n, true, false); -#else - return NOTIFY_DONE; #endif /* CONFIG_IPV6 */ } else { struct flowi4 flow4 = {}; @@ -678,17 +680,71 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, rt = ip_route_output_key(dev_net(n->dev), &flow4); err = PTR_ERR_OR_ZERO(rt); if (err) - return NOTIFY_DONE; + goto out; ip_rt_put(rt); } nfp_tun_write_neigh(n->dev, app, &flow4, n, false, false); } -#else - return NOTIFY_DONE; #endif /* CONFIG_INET */ +out: + nfp_tun_release_neigh_update_work(update_work); +} - return NOTIFY_OK; +static struct nfp_neigh_update_work * +nfp_tun_alloc_neigh_update_work(struct nfp_app *app, struct neighbour *n) +{ + struct nfp_neigh_update_work *update_work; + + update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC); + if (!update_work) + return NULL; + + INIT_WORK(&update_work->work, nfp_tun_neigh_update); + neigh_hold(n); + update_work->n = n; + update_work->app = app; + + return update_work; +} + +static int +nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct nfp_neigh_update_work *update_work; + struct nfp_flower_priv *app_priv; + struct netevent_redirect *redir; + struct neighbour *n; + struct nfp_app *app; + + switch (event) { + case NETEVENT_REDIRECT: + redir = (struct netevent_redirect *)ptr; + n = redir->neigh; + break; + case NETEVENT_NEIGH_UPDATE: + n = (struct neighbour *)ptr; + break; + default: + return NOTIFY_DONE; + } +#if IS_ENABLED(CONFIG_IPV6) + if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl) +#else + if (n->tbl != &arp_tbl) +#endif + return NOTIFY_DONE; + + app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb); + app = app_priv->app; + update_work = nfp_tun_alloc_neigh_update_work(app, n); + if (!update_work) + return NOTIFY_DONE; + + queue_work(system_highpri_wq, &update_work->work); + + return NOTIFY_DONE; } void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) @@ -706,6 +762,7 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL); if (!netdev) goto fail_rcu_unlock; + dev_hold(netdev); flow.daddr = payload->ipv4_addr; flow.flowi4_proto = IPPROTO_UDP; @@ -725,13 +782,16 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) ip_rt_put(rt); if (!n) goto fail_rcu_unlock; + rcu_read_unlock(); + nfp_tun_write_neigh(n->dev, app, &flow, n, false, true); neigh_release(n); - rcu_read_unlock(); + dev_put(netdev); return; fail_rcu_unlock: rcu_read_unlock(); + dev_put(netdev); nfp_flower_cmsg_warn(app, "Requested route not found.\n"); } @@ -749,6 +809,7 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb) netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL); if (!netdev) goto fail_rcu_unlock; + dev_hold(netdev); flow.daddr = payload->ipv6_addr; flow.flowi6_proto = IPPROTO_UDP; @@ -766,14 +827,16 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb) dst_release(dst); if (!n) goto fail_rcu_unlock; + rcu_read_unlock(); nfp_tun_write_neigh(n->dev, app, &flow, n, true, true); neigh_release(n); - rcu_read_unlock(); + dev_put(netdev); return; fail_rcu_unlock: rcu_read_unlock(); + dev_put(netdev); nfp_flower_cmsg_warn(app, "Requested IPv6 route not found.\n"); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 1dbc3cb50b1d..9b5463040075 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -223,7 +223,7 @@ struct ionic_desc_info { void *cb_arg; }; -#define IONIC_QUEUE_NAME_MAX_SZ 32 +#define IONIC_QUEUE_NAME_MAX_SZ 16 struct ionic_queue { struct device *dev; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index edc14730ce88..bad919343180 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -49,24 +49,24 @@ static void ionic_lif_queue_identify(struct ionic_lif *lif); static void ionic_dim_work(struct work_struct *work) { struct dim *dim = container_of(work, struct dim, work); + struct ionic_intr_info *intr; struct dim_cq_moder cur_moder; struct ionic_qcq *qcq; + struct ionic_lif *lif; u32 new_coal; cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); qcq = container_of(dim, struct ionic_qcq, dim); - new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec); + lif = qcq->q.lif; + new_coal = ionic_coal_usec_to_hw(lif->ionic, cur_moder.usec); new_coal = new_coal ? new_coal : 1; - if (qcq->intr.dim_coal_hw != new_coal) { - unsigned int qi = qcq->cq.bound_q->index; - struct ionic_lif *lif = qcq->q.lif; - - qcq->intr.dim_coal_hw = new_coal; + intr = &qcq->intr; + if (intr->dim_coal_hw != new_coal) { + intr->dim_coal_hw = new_coal; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->rxqcqs[qi]->intr.index, - qcq->intr.dim_coal_hw); + intr->index, intr->dim_coal_hw); } dim->state = DIM_START_MEASURE; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 62cabeeb842a..bb787a52bc75 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -196,6 +196,7 @@ enum rtl_registers { /* No threshold before first PCI xfer */ #define RX_FIFO_THRESH (7 << RXCFG_FIFO_SHIFT) #define RX_EARLY_OFF (1 << 11) +#define RX_PAUSE_SLOT_ON (1 << 11) /* 8125b and later */ #define RXCFG_DMA_SHIFT 8 /* Unlimited maximum PCI burst. */ #define RX_DMA_BURST (7 << RXCFG_DMA_SHIFT) @@ -2306,9 +2307,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_63: + case RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; + case RTL_GIGA_MAC_VER_63: + RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST | + RX_PAUSE_SLOT_ON); + break; default: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); break; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index e95d35f1e5a0..8fd167501fa0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -710,28 +710,22 @@ void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev, } } -void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq, +void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable) { u32 value; - if (!enable) { - value = readl(ioaddr + MAC_FPE_CTRL_STS); - - value &= ~EFPE; - - writel(value, ioaddr + MAC_FPE_CTRL_STS); - return; + if (enable) { + cfg->fpe_csr = EFPE; + value = readl(ioaddr + GMAC_RXQ_CTRL1); + value &= ~GMAC_RXQCTRL_FPRQ; + value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT; + writel(value, ioaddr + GMAC_RXQ_CTRL1); + } else { + cfg->fpe_csr = 0; } - - value = readl(ioaddr + GMAC_RXQ_CTRL1); - value &= ~GMAC_RXQCTRL_FPRQ; - value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT; - writel(value, ioaddr + GMAC_RXQ_CTRL1); - - value = readl(ioaddr + MAC_FPE_CTRL_STS); - value |= EFPE; - writel(value, ioaddr + MAC_FPE_CTRL_STS); + writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS); } int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) @@ -741,6 +735,9 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) status = FPE_EVENT_UNKNOWN; + /* Reads from the MAC_FPE_CTRL_STS register should only be performed + * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read" + */ value = readl(ioaddr + MAC_FPE_CTRL_STS); if (value & TRSP) { @@ -766,19 +763,15 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) return status; } -void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, enum stmmac_mpacket_type type) +void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + enum stmmac_mpacket_type type) { - u32 value; + u32 value = cfg->fpe_csr; - value = readl(ioaddr + MAC_FPE_CTRL_STS); - - if (type == MPACKET_VERIFY) { - value &= ~SRSP; + if (type == MPACKET_VERIFY) value |= SVER; - } else { - value &= ~SVER; + else if (type == MPACKET_RESPONSE) value |= SRSP; - } writel(value, ioaddr + MAC_FPE_CTRL_STS); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 53c138d0ff48..34e620790eb3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -153,9 +153,11 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, unsigned int ptp_rate); void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev, struct stmmac_extra_stats *x, u32 txqcnt); -void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq, +void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable); void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, + struct stmmac_fpe_cfg *cfg, enum stmmac_mpacket_type type); int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 453e88b75be0..a74e71db79f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -1484,7 +1484,8 @@ static int dwxgmac3_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, return 0; } -static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq, +static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable) { u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index b95d3e137813..68aa2d5ca6e5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -412,9 +412,11 @@ struct stmmac_ops { unsigned int ptp_rate); void (*est_irq_status)(void __iomem *ioaddr, struct net_device *dev, struct stmmac_extra_stats *x, u32 txqcnt); - void (*fpe_configure)(void __iomem *ioaddr, u32 num_txq, u32 num_rxq, + void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable); void (*fpe_send_mpacket)(void __iomem *ioaddr, + struct stmmac_fpe_cfg *cfg, enum stmmac_mpacket_type type); int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev); }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2afb2bd25977..37e64283f910 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -964,7 +964,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) bool *hs_enable = &fpe_cfg->hs_enable; if (is_up && *hs_enable) { - stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY); + stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg, + MPACKET_VERIFY); } else { *lo_state = FPE_STATE_OFF; *lp_state = FPE_STATE_OFF; @@ -5839,6 +5840,7 @@ static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status) /* If user has requested FPE enable, quickly response */ if (*hs_enable) stmmac_fpe_send_mpacket(priv, priv->ioaddr, + fpe_cfg, MPACKET_RESPONSE); } @@ -7263,6 +7265,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work) if (*lo_state == FPE_STATE_ENTERING_ON && *lp_state == FPE_STATE_ENTERING_ON) { stmmac_fpe_configure(priv, priv->ioaddr, + fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, *enable); @@ -7281,6 +7284,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work) netdev_info(priv->dev, SEND_VERIFY_MPAKCET_FMT, *lo_state, *lp_state); stmmac_fpe_send_mpacket(priv, priv->ioaddr, + fpe_cfg, MPACKET_VERIFY); } /* Sleep then retry */ @@ -7295,6 +7299,7 @@ void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable) if (priv->plat->fpe_cfg->hs_enable != enable) { if (enable) { stmmac_fpe_send_mpacket(priv, priv->ioaddr, + priv->plat->fpe_cfg, MPACKET_VERIFY); } else { priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF; @@ -7755,6 +7760,7 @@ int stmmac_suspend(struct device *dev) if (priv->dma_cap.fpesel) { /* Disable FPE */ stmmac_fpe_configure(priv, priv->ioaddr, + priv->plat->fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, false); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index ac41ef4cbd2f..6ad3e0a11936 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -1079,6 +1079,7 @@ disable: priv->plat->fpe_cfg->enable = false; stmmac_fpe_configure(priv, priv->ioaddr, + priv->plat->fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, false); diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig index ca7bf7f897d3..c8cbd85adcf9 100644 --- a/drivers/net/hyperv/Kconfig +++ b/drivers/net/hyperv/Kconfig @@ -3,5 +3,6 @@ config HYPERV_NET tristate "Microsoft Hyper-V virtual network driver" depends on HYPERV select UCS2_STRING + select NLS help Select this option to enable the Hyper-V virtual network driver. diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2c5c1e91ded6..9bf2140fd0a1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3000,6 +3000,8 @@ static void rtl8152_nic_reset(struct r8152 *tp) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, CR_RST); for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; if (!(ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CR) & CR_RST)) break; usleep_range(100, 400); @@ -3329,6 +3331,8 @@ static void rtl_disable(struct r8152 *tp) rxdy_gated_en(tp, true); for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); if ((ocp_data & FIFO_EMPTY) == FIFO_EMPTY) break; @@ -3336,6 +3340,8 @@ static void rtl_disable(struct r8152 *tp) } for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR0) & TCR0_TX_EMPTY) break; usleep_range(1000, 2000); @@ -5499,6 +5505,8 @@ static void wait_oob_link_list_ready(struct r8152 *tp) int i; for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); if (ocp_data & LINK_LIST_READY) break; @@ -5513,6 +5521,8 @@ static void r8156b_wait_loading_flash(struct r8152 *tp) int i; for (i = 0; i < 100; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; if (ocp_read_word(tp, MCU_TYPE_USB, USB_GPHY_CTRL) & GPHY_PATCH_DONE) break; usleep_range(1000, 2000); @@ -5635,6 +5645,8 @@ static int r8153_pre_firmware_1(struct r8152 *tp) for (i = 0; i < 104; i++) { u32 ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_WDT1_CTRL); + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return -ENODEV; if (!(ocp_data & WTD1_EN)) break; usleep_range(1000, 2000); @@ -5791,6 +5803,8 @@ static void r8153_aldps_en(struct r8152 *tp, bool enable) data &= ~EN_ALDPS; ocp_reg_write(tp, OCP_POWER_CFG, data); for (i = 0; i < 20; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return; usleep_range(1000, 2000); if (ocp_read_word(tp, MCU_TYPE_PLA, 0xe000) & 0x0100) break; @@ -8397,6 +8411,8 @@ static int rtl8152_pre_reset(struct usb_interface *intf) struct r8152 *tp = usb_get_intfdata(intf); struct net_device *netdev; + rtnl_lock(); + if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) return 0; @@ -8428,20 +8444,17 @@ static int rtl8152_post_reset(struct usb_interface *intf) struct sockaddr sa; if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) - return 0; + goto exit; rtl_set_accessible(tp); /* reset the MAC address in case of policy change */ - if (determine_ethernet_addr(tp, &sa) >= 0) { - rtnl_lock(); + if (determine_ethernet_addr(tp, &sa) >= 0) dev_set_mac_address (tp->netdev, &sa, NULL); - rtnl_unlock(); - } netdev = tp->netdev; if (!netif_running(netdev)) - return 0; + goto exit; set_bit(WORK_ENABLE, &tp->flags); if (netif_carrier_ok(netdev)) { @@ -8460,6 +8473,8 @@ static int rtl8152_post_reset(struct usb_interface *intf) if (!list_empty(&tp->rx_done)) napi_schedule(&tp->napi); +exit: + rtnl_unlock(); return 0; } @@ -10034,6 +10049,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff) }, { USB_DEVICE(VENDOR_ID_TPLINK, 0x0601) }, { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, + { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, {} }; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 57efb3454c57..977861c46b1f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -790,7 +790,8 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, skb_add_rx_frag(nskb, i, page, page_offset, size, truesize); - if (skb_copy_bits(skb, off, page_address(page), + if (skb_copy_bits(skb, off, + page_address(page) + page_offset, size)) { consume_skb(nskb); goto drop; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6762dac3ef76..cff5bb08820e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3175,6 +3175,9 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old); + void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0b4658a7eceb..dee5ad6e48c5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -175,6 +175,7 @@ struct stmmac_fpe_cfg { bool hs_enable; /* FPE handshake enable */ enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */ enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ + u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ }; struct stmmac_safety_feature_cfg { diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 68f3d315d2e1..b646b574b060 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -169,7 +169,7 @@ struct tcp_request_sock { #ifdef CONFIG_TCP_AO u8 ao_keyid; u8 ao_rcv_next; - u8 maclen; + bool used_tcp_ao; #endif }; @@ -180,14 +180,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) static inline bool tcp_rsk_used_ao(const struct request_sock *req) { - /* The real length of MAC is saved in the request socket, - * signing anything with zero-length makes no sense, so here is - * a little hack.. - */ #ifndef CONFIG_TCP_AO return false; #else - return tcp_rsk(req)->maclen != 0; + return tcp_rsk(req)->used_tcp_ao; #endif } diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 287e9d83fb8b..33a4c146dc19 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -30,6 +30,7 @@ #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 #define VENDOR_ID_DLINK 0x2001 +#define VENDOR_ID_ASUS 0x0b05 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index e18a4c0d69ee..c53244f20437 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -12,10 +12,12 @@ * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) + * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; + u8 cap_sys_admin:1; }; struct genl_split_ops; diff --git a/include/net/tcp.h b/include/net/tcp.h index d2f0736b76b8..144ba48bb07b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1514,17 +1514,22 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { int unused_mem = sk_unused_reserved_mem(sk); struct tcp_sock *tp = tcp_sk(sk); - tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); if (unused_mem) tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, tcp_win_from_space(sk, unused_mem)); } +static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +{ + __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); +} + void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index b56be10838f0..647781080613 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key) return key->maclen; } +/* Use tcp_ao_len_aligned() for TCP header calculations */ static inline int tcp_ao_len(const struct tcp_ao_key *key) { return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr); } +static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key) +{ + return round_up(tcp_ao_len(key), 4); +} + static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key) { return key->digest_size; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 2058e89b5ddd..c85ff9162a5c 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map, mutex_unlock(&aux->poke_mutex); } +void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + WARN_ON_ONCE(1); +} + static void prog_array_map_poke_run(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new) { - u8 *old_addr, *new_addr, *old_bypass_addr; struct prog_poke_elem *elem; struct bpf_array_aux *aux; @@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, list_for_each_entry(elem, &aux->poke_progs, list) { struct bpf_jit_poke_descriptor *poke; - int i, ret; + int i; for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; @@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, * activated, so tail call updates can arrive from here * while JIT is still finishing its final fixup for * non-activated poke entries. - * 3) On program teardown, the program's kallsym entry gets - * removed out of RCU callback, but we can only untrack - * from sleepable context, therefore bpf_arch_text_poke() - * might not see that this is in BPF text section and - * bails out with -EINVAL. As these are unreachable since - * RCU grace period already passed, we simply skip them. - * 4) Also programs reaching refcount of zero while patching + * 3) Also programs reaching refcount of zero while patching * is in progress is okay since we're protected under * poke_mutex and untrack the programs before the JIT - * buffer is freed. When we're still in the middle of - * patching and suddenly kallsyms entry of the program - * gets evicted, we just skip the rest which is fine due - * to point 3). - * 5) Any other error happening below from bpf_arch_text_poke() - * is a unexpected bug. + * buffer is freed. */ if (!READ_ONCE(poke->tailcall_target_stable)) continue; @@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, poke->tail_call.key != key) continue; - old_bypass_addr = old ? NULL : poke->bypass_addr; - old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; - new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; - - if (new) { - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, new_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - if (!old) { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - poke->bypass_addr, - NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } - } else { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - old_bypass_addr, - poke->bypass_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - /* let other CPUs finish the execution of program - * so that it will not possible to expose them - * to invalid nop, stack unwind, nop state - */ - if (!ret) - synchronize_rcu(); - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } + bpf_arch_poke_desc_update(poke, new, old); } } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index cd3afe57ece3..fe254ae035fe 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -371,14 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { - const s32 off_min = S16_MIN, off_max = S16_MAX; + s64 off_min, off_max, off; s32 delta = end_new - end_old; - s32 off; - if (insn->code == (BPF_JMP32 | BPF_JA)) + if (insn->code == (BPF_JMP32 | BPF_JA)) { off = insn->imm; - else + off_min = S32_MIN; + off_max = S32_MAX; + } else { off = insn->off; + off_min = S16_MIN; + off_max = S16_MAX; + } if (curr < pos && curr + off + 1 >= end_old) off += delta; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index aff31cd944c2..b240d9aae4a6 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -183,7 +183,7 @@ out: } static const struct genl_multicast_group dropmon_mcgrps[] = { - { .name = "events", }, + { .name = "events", .cap_sys_admin = 1 }, }; static void send_dm_alert(struct work_struct *work) @@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, diff --git a/net/core/filter.c b/net/core/filter.c index 7e4d7c3bcc84..1737884be52f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2602,6 +2602,22 @@ BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) return 0; } +static void sk_msg_reset_curr(struct sk_msg *msg) +{ + u32 i = msg->sg.start; + u32 len = 0; + + do { + len += sk_msg_elem(msg, i)->length; + sk_msg_iter_var_next(i); + if (len >= msg->sg.size) + break; + } while (i != msg->sg.end); + + msg->sg.curr = i; + msg->sg.copybreak = 0; +} + static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, @@ -2721,6 +2737,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: + sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; @@ -2857,6 +2874,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, msg->sg.data[new] = rsge; } + sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } @@ -3025,6 +3043,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); + sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 22a26d1d29a0..5169c3c72cff 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing - * to gre header. - */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + if (!pskb_network_may_pull(skb, pull_len)) + goto free_skb; + + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ + skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 53bcc17c91e4..ff6838ca2e58 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3368,9 +3368,25 @@ int tcp_set_window_clamp(struct sock *sk, int val) return -EINVAL; tp->window_clamp = 0; } else { - tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? - SOCK_MIN_RCVBUF / 2 : val; - tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; + u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? + SOCK_MIN_RCVBUF / 2 : val; + + if (new_window_clamp == old_window_clamp) + return 0; + + tp->window_clamp = new_window_clamp; + if (new_window_clamp < old_window_clamp) { + /* need to apply the reserved mem provisioning only + * when shrinking the window clamp + */ + __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); + + } else { + new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + tp->rcv_ssthresh = max(new_rcv_ssthresh, + tp->rcv_ssthresh); + } } return 0; } @@ -3594,6 +3610,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_AO_REPAIR: + if (!tcp_can_repair_sock(sk)) { + err = -EPERM; + break; + } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO @@ -4293,6 +4313,8 @@ zerocopy_rcv_out: } #endif case TCP_AO_REPAIR: + if (!tcp_can_repair_sock(sk)) + return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 7696417d0640..f8308d3f565e 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -851,7 +851,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, const struct tcp_ao_hdr *aoh; struct tcp_ao_key *key; - treq->maclen = 0; + treq->used_tcp_ao = false; if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh) return; @@ -863,7 +863,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, treq->ao_rcv_next = aoh->keyid; treq->ao_keyid = aoh->rnext_keyid; - treq->maclen = tcp_ao_maclen(key); + treq->used_tcp_ao = true; } static enum skb_drop_reason @@ -1100,7 +1100,7 @@ void tcp_ao_connect_init(struct sock *sk) ao_info->current_key = key; if (!ao_info->rnext_key) ao_info->rnext_key = key; - tp->tcp_header_len += tcp_ao_len(key); + tp->tcp_header_len += tcp_ao_len_aligned(key); ao_info->lisn = htonl(tp->write_seq); ao_info->snd_sne = 0; @@ -1346,7 +1346,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key) syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED; syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED; syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED; - if (tcp_ao_len(key) > syn_tcp_option_space) { + if (tcp_ao_len_aligned(key) > syn_tcp_option_space) { err = -EMSGSIZE; goto err_kfree; } @@ -1608,6 +1608,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, if (!dev || !l3index) return -EINVAL; + if (!bound_dev_if || bound_dev_if != cmd.ifindex) { + /* tcp_ao_established_key() doesn't expect having + * non peer-matching key on an established TCP-AO + * connection. + */ + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) + return -EINVAL; + } + /* It's still possible to bind after adding keys or even * re-bind to a different dev (with CAP_NET_RAW). * So, no reason to return error here, rather try to be diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bcb55d98004c..90de838a2745 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3871,8 +3871,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk); return -SKB_DROP_REASON_TCP_TOO_OLD_ACK; @@ -7182,11 +7186,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto drop_and_release; /* Invalid TCP options */ if (aoh) { - tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr); + tcp_rsk(req)->used_tcp_ao = true; tcp_rsk(req)->ao_rcv_next = aoh->keyid; tcp_rsk(req)->ao_keyid = aoh->rnext_keyid; + } else { - tcp_rsk(req)->maclen = 0; + tcp_rsk(req)->used_tcp_ao = false; } #endif tcp_rsk(req)->snt_isn = isn; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5f693bbd578d..0c50c5a32b84 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb, reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) | (aoh->rnext_keyid << 8) | keyid); - arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4); + arg->iov[0].iov_len += tcp_ao_len_aligned(key); reply->doff = arg->iov[0].iov_len / 4; if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1], @@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk, (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | key->rcv_next); - arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4); + arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key); rep.th.doff = arg.iov[0].iov_len / 4; tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a9807eeb311c..9e85f2a0bddd 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1); if (ao_key) - newtp->tcp_header_len += tcp_ao_len(ao_key); + newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index eb13a55d660c..f5ef15e1d9ac 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps); if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - remaining -= tcp_ao_len(key->ao_key); + remaining -= tcp_ao_len_aligned(key->ao_key); } } @@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, ireq->tstamp_ok &= !ireq->sack_ok; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - remaining -= tcp_ao_len(key->ao_key); + remaining -= tcp_ao_len_aligned(key->ao_key); ireq->tstamp_ok &= !ireq->sack_ok; } @@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb size += TCPOLEN_MD5SIG_ALIGNED; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - size += tcp_ao_len(key->ao_key); + size += tcp_ao_len_aligned(key->ao_key); } if (likely(tp->rx_opt.tstamp_ok)) { @@ -3720,7 +3720,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, if (tcp_rsk_used_ao(req)) { #ifdef CONFIG_TCP_AO struct tcp_ao_key *ao_key = NULL; - u8 maclen = tcp_rsk(req)->maclen; u8 keyid = tcp_rsk(req)->ao_keyid; ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), @@ -3730,13 +3729,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, * for another peer-matching key, but the peer has requested * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. */ - if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) { - u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0; - + if (unlikely(!ao_key)) { rcu_read_unlock(); kfree_skb(skb); - net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n", - keyid, maclen, key_maclen); + net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", + keyid); return NULL; } key.ao_key = ao_key; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 28b01a068412..7772f42ff2b9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1511,13 +1511,9 @@ out: if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); + if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; - } -#endif fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 937a02c2e534..8c6623496dd7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -881,7 +881,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (tcp_key_is_md5(key)) tot_len += TCPOLEN_MD5SIG_ALIGNED; if (tcp_key_is_ao(key)) - tot_len += tcp_ao_len(key->ao_key); + tot_len += tcp_ao_len_aligned(key->ao_key); #ifdef CONFIG_MPTCP if (rst && !tcp_key_is_md5(key)) { diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index e502ec00b2fe..0e4beae421f8 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -31,7 +31,7 @@ struct bpf_nf_link { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static const struct nf_defrag_hook * get_proto_defrag_hook(struct bpf_nf_link *link, - const struct nf_defrag_hook __rcu *global_hook, + const struct nf_defrag_hook __rcu **ptr_global_hook, const char *mod) { const struct nf_defrag_hook *hook; @@ -39,7 +39,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, /* RCU protects us from races against module unloading */ rcu_read_lock(); - hook = rcu_dereference(global_hook); + hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); err = request_module(mod); @@ -47,7 +47,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, return ERR_PTR(err < 0 ? err : -EINVAL); rcu_read_lock(); - hook = rcu_dereference(global_hook); + hook = rcu_dereference(*ptr_global_hook); } if (hook && try_module_get(hook->owner)) { @@ -78,7 +78,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link) switch (link->hook_ops.pf) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) case NFPROTO_IPV4: - hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4"); + hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4"); if (IS_ERR(hook)) return PTR_ERR(hook); @@ -87,7 +87,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link) #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) case NFPROTO_IPV6: - hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6"); + hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6"); if (IS_ERR(hook)) return PTR_ERR(hook); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c0a42989b982..c5c17c6e80ed 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -803,7 +803,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask, u32 nlpid) + int family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; @@ -811,6 +811,7 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && + table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) @@ -1544,7 +1545,7 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask, + table = nft_table_lookup_byhandle(net, attr, family, genmask, NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index b18a79039125..c09dba57354c 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -280,10 +280,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx, priv->expr_array[i] = dynset_expr; priv->num_exprs++; - if (set->num_exprs && - dynset_expr->ops != set->exprs[i]->ops) { - err = -EOPNOTSUPP; - goto err_expr_free; + if (set->num_exprs) { + if (i >= set->num_exprs) { + err = -EINVAL; + goto err_expr_free; + } + if (dynset_expr->ops != set->exprs[i]->ops) { + err = -EOPNOTSUPP; + goto err_expr_free; + } } i++; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 3fbaa7bf41f9..6eb571d0c3fd 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -214,7 +214,7 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, offset = i + priv->offset; if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = 1; + nft_reg_store8(dest, 1); } else { if (priv->len % NFT_REG32_SIZE) dest[priv->len / NFT_REG32_SIZE] = 0; @@ -461,7 +461,7 @@ static void nft_exthdr_dccp_eval(const struct nft_expr *expr, type = bufp[0]; if (type == priv->type) { - *dest = 1; + nft_reg_store8(dest, 1); return; } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 1bfe258018da..37cfe6dd712d 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -145,11 +145,15 @@ void nft_fib_store_result(void *reg, const struct nft_fib *priv, switch (priv->result) { case NFT_FIB_RESULT_OIF: index = dev ? dev->ifindex : 0; - *dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index; + if (priv->flags & NFTA_FIB_F_PRESENT) + nft_reg_store8(dreg, !!index); + else + *dreg = index; + break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) - *dreg = !!dev; + nft_reg_store8(dreg, !!dev); else strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ); break; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 701977af3ee8..7252fcdae349 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2043,6 +2043,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index e85ce69924ae..50332888c8d2 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -76,18 +76,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) */ return false; - filp = sk->sk_socket->file; - if (filp == NULL) + read_lock_bh(&sk->sk_callback_lock); + filp = sk->sk_socket ? sk->sk_socket->file : NULL; + if (filp == NULL) { + read_unlock_bh(&sk->sk_callback_lock); return ((info->match ^ info->invert) & (XT_OWNER_UID | XT_OWNER_GID)) == 0; + } if (info->match & XT_OWNER_UID) { kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); if ((uid_gte(filp->f_cred->fsuid, uid_min) && uid_lte(filp->f_cred->fsuid, uid_max)) ^ - !(info->invert & XT_OWNER_UID)) + !(info->invert & XT_OWNER_UID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } if (info->match & XT_OWNER_GID) { @@ -112,10 +117,13 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } } - if (match ^ !(info->invert & XT_OWNER_GID)) + if (match ^ !(info->invert & XT_OWNER_GID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } + read_unlock_bh(&sk->sk_callback_lock); return true; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 92ef5ed2e7b0..9c7ffd10df2a 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1691,6 +1691,9 @@ static int genl_bind(struct net *net, int group) if ((grp->flags & GENL_UNS_ADMIN_PERM) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; + if (grp->cap_sys_admin && + !ns_capable(net->user_ns, CAP_SYS_ADMIN)) + ret = -EPERM; break; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a84e00b5904b..7adf48549a3b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4300,7 +4300,7 @@ static void packet_mm_open(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_inc(&pkt_sk(sk)->mapped); + atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) @@ -4310,7 +4310,7 @@ static void packet_mm_close(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_dec(&pkt_sk(sk)->mapped); + atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { @@ -4405,7 +4405,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; if (!closing) { - if (atomic_read(&po->mapped)) + if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; @@ -4508,7 +4508,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; mutex_lock(&po->pg_vec_lock); - if (closing || atomic_read(&po->mapped) == 0) { + if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); @@ -4526,9 +4526,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); - if (atomic_read(&po->mapped)) - pr_err("packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + if (atomic_long_read(&po->mapped)) + pr_err("packet_mmap: vma is busy: %ld\n", + atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -4606,7 +4606,7 @@ static int packet_mmap(struct file *file, struct socket *sock, } } - atomic_inc(&po->mapped); + atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; diff --git a/net/packet/internal.h b/net/packet/internal.h index d29c94c45159..d5d70712007a 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -122,7 +122,7 @@ struct packet_sock { __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; - atomic_t mapped; + atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; diff --git a/net/psample/psample.c b/net/psample/psample.c index 81a794e36f53..c34e902855db 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -31,7 +31,8 @@ enum psample_nl_multicast_groups { static const struct genl_multicast_group psample_nl_mcgrps[] = { [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME }, - [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME }, + [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME, + .flags = GENL_UNS_ADMIN_PERM }, }; static struct genl_family psample_nl_family __ro_after_init; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 2a1388841951..73eebddbbf41 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -723,7 +723,7 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc, int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size); smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx; - smc->conn.peer_token = clc->d0.token; + smc->conn.peer_token = ntohll(clc->d0.token); /* msg header takes up space in the buffer */ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); @@ -1415,7 +1415,7 @@ static int smc_connect_ism(struct smc_sock *smc, if (rc) return rc; } - ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid; + ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid); /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 8deb46c28f1d..72f4d81a3f41 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1004,6 +1004,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, { struct smc_connection *conn = &smc->conn; struct smc_clc_first_contact_ext_v2x fce; + struct smcd_dev *smcd = conn->lgr->smcd; struct smc_clc_msg_accept_confirm *clc; struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; @@ -1021,17 +1022,15 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); clc->hdr.typev1 = SMC_TYPE_D; - clc->d0.gid = - conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd); - clc->d0.token = conn->rmb_desc->token; + clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd)); + clc->d0.token = htonll(conn->rmb_desc->token); clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - clc_v2->d1.chid = - htons(smc_ism_get_chid(conn->lgr->smcd)); + clc_v2->d1.chid = htons(smc_ism_get_chid(smcd)); if (eid && eid[0]) memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index c5c8e7db775a..08155a96a02a 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -204,8 +204,8 @@ struct smcr_clc_msg_accept_confirm { /* SMCR accept/confirm */ } __packed; struct smcd_clc_msg_accept_confirm_common { /* SMCD accept/confirm */ - u64 gid; /* Sender GID */ - u64 token; /* DMB token */ + __be64 gid; /* Sender GID */ + __be64 token; /* DMB token */ u8 dmbe_idx; /* DMBE index */ #if defined(__BIG_ENDIAN_BITFIELD) u8 dmbe_size : 4, /* buf size (compressed) */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 316f76187962..e37b4d2e2acd 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -952,6 +952,8 @@ static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg, } sk_msg_page_add(msg_pl, page, part, off); + msg_pl->sg.copybreak = 0; + msg_pl->sg.curr = msg_pl->sg.end; sk_mem_charge(sk, part); *copied += part; try_to_copy -= part; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index f6dc896bf44c..c8e162c9d1df 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -59,8 +59,7 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, t_ops = virtio_transport_get_ops(info->vsk); if (t_ops->can_msgzerocopy) { - int pages_in_iov = iov_iter_npages(iov_iter, MAX_SKB_FRAGS); - int pages_to_send = min(pages_in_iov, MAX_SKB_FRAGS); + int pages_to_send = iov_iter_npages(iov_iter, MAX_SKB_FRAGS); /* +1 is for packet header. */ return t_ops->can_msgzerocopy(pages_to_send + 1); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index ae9f8cb611f6..3da0b52f308d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -947,7 +947,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, rcu_read_lock(); if (xsk_check_common(xs)) - goto skip_tx; + goto out; pool = xs->pool; @@ -959,12 +959,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, xsk_generic_xmit(sk); } -skip_tx: if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; - +out: rcu_read_unlock(); return mask; } diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index fc6b2954e8f5..59993fc9c0d7 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> #include <test_progs.h> #include <network_helpers.h> +#include "tailcall_poke.skel.h" + /* test_tailcall_1 checks basic functionality by patching multiple locations * in a single program for a single tail call slot with nop->jmp, jmp->nop @@ -1105,6 +1108,85 @@ out: bpf_object__close(tgt_obj); } +#define JMP_TABLE "/sys/fs/bpf/jmp_table" + +static int poke_thread_exit; + +static void *poke_update(void *arg) +{ + __u32 zero = 0, prog1_fd, prog2_fd, map_fd; + struct tailcall_poke *call = arg; + + map_fd = bpf_map__fd(call->maps.jmp_table); + prog1_fd = bpf_program__fd(call->progs.call1); + prog2_fd = bpf_program__fd(call->progs.call2); + + while (!poke_thread_exit) { + bpf_map_update_elem(map_fd, &zero, &prog1_fd, BPF_ANY); + bpf_map_update_elem(map_fd, &zero, &prog2_fd, BPF_ANY); + } + + return NULL; +} + +/* + * We are trying to hit prog array update during another program load + * that shares the same prog array map. + * + * For that we share the jmp_table map between two skeleton instances + * by pinning the jmp_table to same path. Then first skeleton instance + * periodically updates jmp_table in 'poke update' thread while we load + * the second skeleton instance in the main thread. + */ +static void test_tailcall_poke(void) +{ + struct tailcall_poke *call, *test; + int err, cnt = 10; + pthread_t thread; + + unlink(JMP_TABLE); + + call = tailcall_poke__open_and_load(); + if (!ASSERT_OK_PTR(call, "tailcall_poke__open")) + return; + + err = bpf_map__pin(call->maps.jmp_table, JMP_TABLE); + if (!ASSERT_OK(err, "bpf_map__pin")) + goto out; + + err = pthread_create(&thread, NULL, poke_update, call); + if (!ASSERT_OK(err, "new toggler")) + goto out; + + while (cnt--) { + test = tailcall_poke__open(); + if (!ASSERT_OK_PTR(test, "tailcall_poke__open")) + break; + + err = bpf_map__set_pin_path(test->maps.jmp_table, JMP_TABLE); + if (!ASSERT_OK(err, "bpf_map__pin")) { + tailcall_poke__destroy(test); + break; + } + + bpf_program__set_autoload(test->progs.test, true); + bpf_program__set_autoload(test->progs.call1, false); + bpf_program__set_autoload(test->progs.call2, false); + + err = tailcall_poke__load(test); + tailcall_poke__destroy(test); + if (!ASSERT_OK(err, "tailcall_poke__load")) + break; + } + + poke_thread_exit = 1; + ASSERT_OK(pthread_join(thread, NULL), "pthread_join"); + +out: + bpf_map__unpin(call->maps.jmp_table, JMP_TABLE); + tailcall_poke__destroy(call); +} + void test_tailcalls(void) { if (test__start_subtest("tailcall_1")) @@ -1139,4 +1221,6 @@ void test_tailcalls(void) test_tailcall_bpf2bpf_fentry_fexit(); if (test__start_subtest("tailcall_bpf2bpf_fentry_entry")) test_tailcall_bpf2bpf_fentry_entry(); + if (test__start_subtest("tailcall_poke")) + test_tailcall_poke(); } diff --git a/tools/testing/selftests/bpf/progs/tailcall_poke.c b/tools/testing/selftests/bpf/progs/tailcall_poke.c new file mode 100644 index 000000000000..c78b94b75e83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall_poke.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +SEC("?fentry/bpf_fentry_test1") +int BPF_PROG(test, int a) +{ + bpf_tail_call_static(ctx, &jmp_table, 0); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(call1, int a) +{ + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(call2, int a) +{ + return 0; +} |