diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-16 07:51:26 -0500 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-16 07:51:26 -0500 |
| commit | 7475e51b87969e01a6812eac713a1c8310372e8a (patch) | |
| tree | 350f6dcea18fb09fdb70179e8e7ae3e40d470896 | |
| parent | 6eb1acd9766a0dc9d85927843d85787408395e15 (diff) | |
| parent | cff088d924df871296412e6b819823f42d1bb9a5 (diff) | |
| download | linux-rcu-7475e51b87969e01a6812eac713a1c8310372e8a.tar.gz | |
Merge tag 'net-6.7-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from BPF and netfilter.
Current release - regressions:
- core: fix undefined behavior in netdev name allocation
- bpf: do not allocate percpu memory at init stage
- netfilter: nf_tables: split async and sync catchall in two
functions
- mptcp: fix possible NULL pointer dereference on close
Current release - new code bugs:
- eth: ice: dpll: fix initial lock status of dpll
Previous releases - regressions:
- bpf: fix precision backtracking instruction iteration
- af_unix: fix use-after-free in unix_stream_read_actor()
- tipc: fix kernel-infoleak due to uninitialized TLV value
- eth: bonding: stop the device in bond_setup_by_slave()
- eth: mlx5:
- fix double free of encap_header
- avoid referencing skb after free-ing in drop path
- eth: hns3: fix VF reset
- eth: mvneta: fix calls to page_pool_get_stats
Previous releases - always broken:
- core: set SOCK_RCU_FREE before inserting socket into hashtable
- bpf: fix control-flow graph checking in privileged mode
- eth: ppp: limit MRU to 64K
- eth: stmmac: avoid rx queue overrun
- eth: icssg-prueth: fix error cleanup on failing initialization
- eth: hns3: fix out-of-bounds access may occur when coalesce info is
read via debugfs
- eth: cortina: handle large frames
Misc:
- selftests: gso: support CONFIG_MAX_SKB_FRAGS up to 45"
* tag 'net-6.7-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (78 commits)
macvlan: Don't propagate promisc change to lower dev in passthru
net: sched: do not offload flows with a helper in act_ct
net/mlx5e: Check return value of snprintf writing to fw_version buffer for representors
net/mlx5e: Check return value of snprintf writing to fw_version buffer
net/mlx5e: Reduce the size of icosq_str
net/mlx5: Increase size of irq name buffer
net/mlx5e: Update doorbell for port timestamping CQ before the software counter
net/mlx5e: Track xmit submission to PTP WQ after populating metadata map
net/mlx5e: Avoid referencing skb after free-ing in drop path of mlx5e_sq_xmit_wqe
net/mlx5e: Don't modify the peer sent-to-vport rules for IPSec offload
net/mlx5e: Fix pedit endianness
net/mlx5e: fix double free of encap_header in update funcs
net/mlx5e: fix double free of encap_header
net/mlx5: Decouple PHC .adjtime and .adjphase implementations
net/mlx5: DR, Allow old devices to use multi destination FTE
net/mlx5: Free used cpus mask when an IRQ is released
Revert "net/mlx5: DR, Supporting inline WQE when possible"
bpf: Do not allocate percpu memory at init stage
net: Fix undefined behavior in netdev name allocation
dt-bindings: net: ethernet-controller: Fix formatting error
...
80 files changed, 860 insertions, 457 deletions
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 9f6a5ccbcefef4..d14d123ad7a028 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -275,12 +275,12 @@ allOf: properties: rx-internal-delay-ps: description: - RGMII Receive Clock Delay defined in pico seconds.This is used for + RGMII Receive Clock Delay defined in pico seconds. This is used for controllers that have configurable RX internal delays. If this property is present then the MAC applies the RX delay. tx-internal-delay-ps: description: - RGMII Transmit Clock Delay defined in pico seconds.This is used for + RGMII Transmit Clock Delay defined in pico seconds. This is used for controllers that have configurable TX internal delays. If this property is present then the MAC applies the TX delay. diff --git a/MAINTAINERS b/MAINTAINERS index 5c9f868e13b6e9..482d428472e763 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21768,7 +21768,9 @@ F: Documentation/devicetree/bindings/counter/ti-eqep.yaml F: drivers/counter/ti-eqep.c TI ETHERNET SWITCH DRIVER (CPSW) -R: Grygorii Strashko <grygorii.strashko@ti.com> +R: Siddharth Vadapalli <s-vadapalli@ti.com> +R: Ravi Gunasekaran <r-gunasekaran@ti.com> +R: Roger Quadros <rogerq@kernel.org> L: linux-omap@vger.kernel.org L: netdev@vger.kernel.org S: Maintained @@ -21792,6 +21794,15 @@ F: Documentation/devicetree/bindings/media/i2c/ti,ds90* F: drivers/media/i2c/ds90* F: include/media/i2c/ds90* +TI ICSSG ETHERNET DRIVER (ICSSG) +R: MD Danish Anwar <danishanwar@ti.com> +R: Roger Quadros <rogerq@kernel.org> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: netdev@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/net/ti,icss*.yaml +F: drivers/net/ethernet/ti/icssg/* + TI J721E CSI2RX DRIVER M: Jai Luthra <j-luthra@ti.com> L: linux-media@vger.kernel.org diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 51d47eda1c873d..8e6cc0e133b7f1 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1500,6 +1500,10 @@ done: static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { + bool was_up = !!(bond_dev->flags & IFF_UP); + + dev_close(bond_dev); + bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; @@ -1514,6 +1518,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev, bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } + if (was_up) + dev_open(bond_dev, NULL); } /* On bonding slaves other than the currently active slave, suppress diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c index 045fe133f6ee99..5beadabc213618 100644 --- a/drivers/net/ethernet/amd/pds_core/adminq.c +++ b/drivers/net/ethernet/amd/pds_core/adminq.c @@ -146,7 +146,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) } queue_work(pdsc->wq, &qcq->work); - pds_core_intr_mask(&pdsc->intr_ctrl[irq], PDS_CORE_INTR_MASK_CLEAR); + pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR); return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index f3a7deda997245..e35d3e7006bfc1 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -15,7 +15,7 @@ #define PDSC_DRV_DESCRIPTION "AMD/Pensando Core Driver" #define PDSC_WATCHDOG_SECS 5 -#define PDSC_QUEUE_NAME_MAX_SZ 32 +#define PDSC_QUEUE_NAME_MAX_SZ 16 #define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */ #define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */ #define PDSC_TEARDOWN_RECOVERY false diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index 7c1b965d61a926..31940b857e0e50 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -261,10 +261,14 @@ static int pdsc_identify(struct pdsc *pdsc) struct pds_core_drv_identity drv = {}; size_t sz; int err; + int n; drv.drv_type = cpu_to_le32(PDS_DRIVER_LINUX); - snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str), - "%s %s", PDS_CORE_DRV_NAME, utsname()->release); + /* Catching the return quiets a Wformat-truncation complaint */ + n = snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str), + "%s %s", PDS_CORE_DRV_NAME, utsname()->release); + if (n > sizeof(drv.driver_ver_str)) + dev_dbg(pdsc->dev, "release name truncated, don't care\n"); /* Next let's get some info about the device * We use the devcmd_lock at this level in order to diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index 57f88c8b37defe..e9948ea5bbcdba 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -104,7 +104,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, struct pds_core_fw_list_info fw_list; struct pdsc *pdsc = devlink_priv(dl); union pds_core_dev_comp comp; - char buf[16]; + char buf[32]; int listlen; int err; int i; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 1dee27349367e7..48b6191efa56c7 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6889,7 +6889,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) desc_idx, *post_ptr); drop_it_no_recycle: /* Other statistics kept track of by card. */ - tp->rx_dropped++; + tnapi->rx_dropped++; goto next_pkt; } @@ -7918,8 +7918,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi, segs = skb_gso_segment(skb, tp->dev->features & ~(NETIF_F_TSO | NETIF_F_TSO6)); - if (IS_ERR(segs) || !segs) + if (IS_ERR(segs) || !segs) { + tnapi->tx_dropped++; goto tg3_tso_bug_end; + } skb_list_walk_safe(segs, seg, next) { skb_mark_not_on_list(seg); @@ -8190,7 +8192,7 @@ dma_error: drop: dev_kfree_skb_any(skb); drop_nofree: - tp->tx_dropped++; + tnapi->tx_dropped++; return NETDEV_TX_OK; } @@ -9405,7 +9407,7 @@ static void __tg3_set_rx_mode(struct net_device *); /* tp->lock is held. */ static int tg3_halt(struct tg3 *tp, int kind, bool silent) { - int err; + int err, i; tg3_stop_fw(tp); @@ -9426,6 +9428,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent) /* And make sure the next sample is new data */ memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats)); + + for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) { + struct tg3_napi *tnapi = &tp->napi[i]; + + tnapi->rx_dropped = 0; + tnapi->tx_dropped = 0; + } } return err; @@ -11975,6 +11984,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats) { struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev; struct tg3_hw_stats *hw_stats = tp->hw_stats; + unsigned long rx_dropped; + unsigned long tx_dropped; + int i; stats->rx_packets = old_stats->rx_packets + get_stat64(&hw_stats->rx_ucast_packets) + @@ -12021,8 +12033,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats) stats->rx_missed_errors = old_stats->rx_missed_errors + get_stat64(&hw_stats->rx_discards); - stats->rx_dropped = tp->rx_dropped; - stats->tx_dropped = tp->tx_dropped; + /* Aggregate per-queue counters. The per-queue counters are updated + * by a single writer, race-free. The result computed by this loop + * might not be 100% accurate (counters can be updated in the middle of + * the loop) but the next tg3_get_nstats() will recompute the current + * value so it is acceptable. + * + * Note that these counters wrap around at 4G on 32bit machines. + */ + rx_dropped = (unsigned long)(old_stats->rx_dropped); + tx_dropped = (unsigned long)(old_stats->tx_dropped); + + for (i = 0; i < tp->irq_cnt; i++) { + struct tg3_napi *tnapi = &tp->napi[i]; + + rx_dropped += tnapi->rx_dropped; + tx_dropped += tnapi->tx_dropped; + } + + stats->rx_dropped = rx_dropped; + stats->tx_dropped = tx_dropped; } static int tg3_get_regs_len(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index ae5c01bd111043..5016475e50054d 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3018,6 +3018,7 @@ struct tg3_napi { u16 *rx_rcb_prod_idx; struct tg3_rx_prodring_set prodring; struct tg3_rx_buffer_desc *rx_rcb; + unsigned long rx_dropped; u32 tx_prod ____cacheline_aligned; u32 tx_cons; @@ -3026,6 +3027,7 @@ struct tg3_napi { u32 prodmbox; struct tg3_tx_buffer_desc *tx_ring; struct tg3_tx_ring_info *tx_buffers; + unsigned long tx_dropped; dma_addr_t status_mapping; dma_addr_t rx_rcb_mapping; @@ -3220,8 +3222,6 @@ struct tg3 { /* begin "everything else" cacheline(s) section */ - unsigned long rx_dropped; - unsigned long tx_dropped; struct rtnl_link_stats64 net_stats_prev; struct tg3_ethtool_stats estats_prev; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 5423fe26b4ef02..78287cfcbf6388 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -432,8 +432,8 @@ static const struct gmac_max_framelen gmac_maxlens[] = { .val = CONFIG0_MAXLEN_1536, }, { - .max_l3_len = 1542, - .val = CONFIG0_MAXLEN_1542, + .max_l3_len = 1548, + .val = CONFIG0_MAXLEN_1548, }, { .max_l3_len = 9212, @@ -1145,6 +1145,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, dma_addr_t mapping; unsigned short mtu; void *buffer; + int ret; mtu = ETH_HLEN; mtu += netdev->mtu; @@ -1159,9 +1160,30 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, word3 |= mtu; } - if (skb->ip_summed != CHECKSUM_NONE) { + if (skb->len >= ETH_FRAME_LEN) { + /* Hardware offloaded checksumming isn't working on frames + * bigger than 1514 bytes. A hypothesis about this is that the + * checksum buffer is only 1518 bytes, so when the frames get + * bigger they get truncated, or the last few bytes get + * overwritten by the FCS. + * + * Just use software checksumming and bypass on bigger frames. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + ret = skb_checksum_help(skb); + if (ret) + return ret; + } + word1 |= TSS_BYPASS_BIT; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int tcp = 0; + /* We do not switch off the checksumming on non TCP/UDP + * frames: as is shown from tests, the checksumming engine + * is smart enough to see that a frame is not actually TCP + * or UDP and then just pass it through without any changes + * to the frame. + */ if (skb->protocol == htons(ETH_P_IP)) { word1 |= TSS_IP_CHKSUM_BIT; tcp = ip_hdr(skb)->protocol == IPPROTO_TCP; @@ -1978,15 +2000,6 @@ static int gmac_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -static netdev_features_t gmac_fix_features(struct net_device *netdev, - netdev_features_t features) -{ - if (netdev->mtu + ETH_HLEN + VLAN_HLEN > MTU_SIZE_BIT_MASK) - features &= ~GMAC_OFFLOAD_FEATURES; - - return features; -} - static int gmac_set_features(struct net_device *netdev, netdev_features_t features) { @@ -2212,7 +2225,6 @@ static const struct net_device_ops gmac_351x_ops = { .ndo_set_mac_address = gmac_set_mac_address, .ndo_get_stats64 = gmac_get_stats64, .ndo_change_mtu = gmac_change_mtu, - .ndo_fix_features = gmac_fix_features, .ndo_set_features = gmac_set_features, }; @@ -2464,11 +2476,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) netdev->hw_features = GMAC_OFFLOAD_FEATURES; netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO; - /* We can handle jumbo frames up to 10236 bytes so, let's accept - * payloads of 10236 bytes minus VLAN and ethernet header + /* We can receive jumbo frames up to 10236 bytes but only + * transmit 2047 bytes so, let's accept payloads of 2047 + * bytes minus VLAN and ethernet header */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = 10236 - VLAN_ETH_HLEN; + netdev->max_mtu = MTU_SIZE_BIT_MASK - VLAN_ETH_HLEN; port->freeq_refill = 0; netif_napi_add(netdev, &port->napi, gmac_napi_poll); diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h index 9fdf77d5eb3740..24bb989981f233 100644 --- a/drivers/net/ethernet/cortina/gemini.h +++ b/drivers/net/ethernet/cortina/gemini.h @@ -502,7 +502,7 @@ union gmac_txdesc_3 { #define SOF_BIT 0x80000000 #define EOF_BIT 0x40000000 #define EOFIE_BIT BIT(29) -#define MTU_SIZE_BIT_MASK 0x1fff +#define MTU_SIZE_BIT_MASK 0x7ff /* Max MTU 2047 bytes */ /* GMAC Tx Descriptor */ struct gmac_txdesc { @@ -787,7 +787,7 @@ union gmac_config0 { #define CONFIG0_MAXLEN_1536 0 #define CONFIG0_MAXLEN_1518 1 #define CONFIG0_MAXLEN_1522 2 -#define CONFIG0_MAXLEN_1542 3 +#define CONFIG0_MAXLEN_1548 3 #define CONFIG0_MAXLEN_9k 4 /* 9212 */ #define CONFIG0_MAXLEN_10k 5 /* 10236 */ #define CONFIG0_MAXLEN_1518__6 6 diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 276f996f95dcc8..2d42e733837b0d 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -254,10 +254,13 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) if (block->tx) { if (block->tx->q_num < priv->tx_cfg.num_queues) reschedule |= gve_tx_poll(block, budget); - else + else if (budget) reschedule |= gve_xdp_poll(block, budget); } + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll(block, budget); reschedule |= work_done == budget; @@ -298,6 +301,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) if (block->tx) reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll_dqo(block, budget); reschedule |= work_done == budget; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index e84a066aa1a40a..73655347902d2d 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -1007,10 +1007,6 @@ int gve_rx_poll(struct gve_notify_block *block, int budget) feat = block->napi.dev->features; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - if (budget > 0) work_done = gve_clean_rx_done(rx, budget, feat); diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 6957a865cff37c..9f6ffc4a54f0bb 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -925,10 +925,6 @@ bool gve_xdp_poll(struct gve_notify_block *block, int budget) bool repoll; u32 to_do; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - /* Find out how much work there is to be done */ nic_done = gve_tx_load_event_counter(priv, tx); to_do = min_t(u32, (nic_done - tx->done), budget); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 0b138635bafa9d..c083d1d10767bb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -503,11 +503,14 @@ static void hns3_get_coal_info(struct hns3_enet_tqp_vector *tqp_vector, } sprintf(result[j++], "%d", i); - sprintf(result[j++], "%s", dim_state_str[dim->state]); + sprintf(result[j++], "%s", dim->state < ARRAY_SIZE(dim_state_str) ? + dim_state_str[dim->state] : "unknown"); sprintf(result[j++], "%u", dim->profile_ix); - sprintf(result[j++], "%s", dim_cqe_mode_str[dim->mode]); + sprintf(result[j++], "%s", dim->mode < ARRAY_SIZE(dim_cqe_mode_str) ? + dim_cqe_mode_str[dim->mode] : "unknown"); sprintf(result[j++], "%s", - dim_tune_stat_str[dim->tune_state]); + dim->tune_state < ARRAY_SIZE(dim_tune_stat_str) ? + dim_tune_stat_str[dim->tune_state] : "unknown"); sprintf(result[j++], "%u", dim->steps_left); sprintf(result[j++], "%u", dim->steps_right); sprintf(result[j++], "%u", dim->tired); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 06117502001f92..b618797a7e8de2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5139,7 +5139,7 @@ static int hns3_init_mac_addr(struct net_device *netdev) struct hns3_nic_priv *priv = netdev_priv(netdev); char format_mac_addr[HNAE3_FORMAT_MAC_ADDR_LEN]; struct hnae3_handle *h = priv->ae_handle; - u8 mac_addr_temp[ETH_ALEN]; + u8 mac_addr_temp[ETH_ALEN] = {0}; int ret = 0; if (h->ae_algo->ops->get_mac_addr) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 66e5807903a02a..5ea9e59569effb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -61,6 +61,7 @@ static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, int wait_cnt); +static int hclge_update_port_info(struct hclge_dev *hdev); static struct hnae3_ae_algo ae_algo; @@ -3041,6 +3042,9 @@ static void hclge_update_link_status(struct hclge_dev *hdev) if (state != hdev->hw.mac.link) { hdev->hw.mac.link = state; + if (state == HCLGE_LINK_STATUS_UP) + hclge_update_port_info(hdev); + client->ops->link_status_change(handle, state); hclge_config_mac_tnl_int(hdev, state); if (rclient && rclient->ops->link_status_change) @@ -10025,8 +10029,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, struct hclge_vport_vlan_cfg *vlan, *tmp; struct hclge_dev *hdev = vport->back; - mutex_lock(&hdev->vport_lock); - list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { if (vlan->vlan_id == vlan_id) { if (is_write_tbl && vlan->hd_tbl_status) @@ -10041,8 +10043,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, break; } } - - mutex_unlock(&hdev->vport_lock); } void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list) @@ -10451,11 +10451,16 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ + mutex_lock(&hdev->vport_lock); if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, vport->vlan_del_fail_bmap); + mutex_unlock(&hdev->vport_lock); return -EBUSY; + } else if (!is_kill && test_bit(vlan_id, vport->vlan_del_fail_bmap)) { + clear_bit(vlan_id, vport->vlan_del_fail_bmap); } + mutex_unlock(&hdev->vport_lock); /* when port base vlan enabled, we use port base vlan as the vlan * filter entry. In this case, we don't update vlan filter table @@ -10470,17 +10475,22 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, } if (!ret) { - if (!is_kill) + if (!is_kill) { hclge_add_vport_vlan_table(vport, vlan_id, writen_to_tbl); - else if (is_kill && vlan_id != 0) + } else if (is_kill && vlan_id != 0) { + mutex_lock(&hdev->vport_lock); hclge_rm_vport_vlan_table(vport, vlan_id, false); + mutex_unlock(&hdev->vport_lock); + } } else if (is_kill) { /* when remove hw vlan filter failed, record the vlan id, * and try to remove it from hw later, to be consistence * with stack */ + mutex_lock(&hdev->vport_lock); set_bit(vlan_id, vport->vlan_del_fail_bmap); + mutex_unlock(&hdev->vport_lock); } hclge_set_vport_vlan_fltr_change(vport); @@ -10520,6 +10530,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) int i, ret, sync_cnt = 0; u16 vlan_id; + mutex_lock(&hdev->vport_lock); /* start from vport 1 for PF is always alive */ for (i = 0; i < hdev->num_alloc_vport; i++) { struct hclge_vport *vport = &hdev->vport[i]; @@ -10530,21 +10541,26 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, vlan_id, true); - if (ret && ret != -EINVAL) + if (ret && ret != -EINVAL) { + mutex_unlock(&hdev->vport_lock); return; + } clear_bit(vlan_id, vport->vlan_del_fail_bmap); hclge_rm_vport_vlan_table(vport, vlan_id, false); hclge_set_vport_vlan_fltr_change(vport); sync_cnt++; - if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) + if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) { + mutex_unlock(&hdev->vport_lock); return; + } vlan_id = find_first_bit(vport->vlan_del_fail_bmap, VLAN_N_VID); } } + mutex_unlock(&hdev->vport_lock); hclge_sync_vlan_fltr_state(hdev); } @@ -11651,6 +11667,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) goto err_msi_irq_uninit; if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) { + clear_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps); if (hnae3_dev_phy_imp_supported(hdev)) ret = hclge_update_tp_port_info(hdev); else diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a4d68fb216fb92..0aa9beefd1c7ee 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1206,6 +1206,8 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, hdev->vlan_del_fail_bmap); return -EBUSY; + } else if (!is_kill && test_bit(vlan_id, hdev->vlan_del_fail_bmap)) { + clear_bit(vlan_id, hdev->vlan_del_fail_bmap); } hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, @@ -1233,20 +1235,25 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev) int ret, sync_cnt = 0; u16 vlan_id; + if (bitmap_empty(hdev->vlan_del_fail_bmap, VLAN_N_VID)) + return; + + rtnl_lock(); vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID); while (vlan_id != VLAN_N_VID) { ret = hclgevf_set_vlan_filter(handle, htons(ETH_P_8021Q), vlan_id, true); if (ret) - return; + break; clear_bit(vlan_id, hdev->vlan_del_fail_bmap); sync_cnt++; if (sync_cnt >= HCLGEVF_MAX_SYNC_COUNT) - return; + break; vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID); } + rtnl_unlock(); } static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) @@ -1974,8 +1981,18 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, return HCLGEVF_VECTOR0_EVENT_OTHER; } +static void hclgevf_reset_timer(struct timer_list *t) +{ + struct hclgevf_dev *hdev = from_timer(hdev, t, reset_timer); + + hclgevf_clear_event_cause(hdev, HCLGEVF_VECTOR0_EVENT_RST); + hclgevf_reset_task_schedule(hdev); +} + static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) { +#define HCLGEVF_RESET_DELAY 5 + enum hclgevf_evt_cause event_cause; struct hclgevf_dev *hdev = data; u32 clearval; @@ -1987,7 +2004,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) switch (event_cause) { case HCLGEVF_VECTOR0_EVENT_RST: - hclgevf_reset_task_schedule(hdev); + mod_timer(&hdev->reset_timer, + jiffies + msecs_to_jiffies(HCLGEVF_RESET_DELAY)); break; case HCLGEVF_VECTOR0_EVENT_MBX: hclgevf_mbx_handler(hdev); @@ -2930,6 +2948,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) HCLGEVF_DRIVER_NAME); hclgevf_task_schedule(hdev, round_jiffies_relative(HZ)); + timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 81c16b8c8da296..a73f2bf3a56a64 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -219,6 +219,7 @@ struct hclgevf_dev { enum hnae3_reset_type reset_level; unsigned long reset_pending; enum hnae3_reset_type reset_type; + struct timer_list reset_timer; #define HCLGEVF_RESET_REQUESTED 0 #define HCLGEVF_RESET_PENDING 1 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index bbf7b14079de3c..85c2a634c8f96a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -63,6 +63,9 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1, i++; } + /* ensure additional_info will be seen after received_resp */ + smp_rmb(); + if (i >= HCLGEVF_MAX_TRY_TIMES) { dev_err(&hdev->pdev->dev, "VF could not get mbx(%u,%u) resp(=%d) from PF in %d tries\n", @@ -178,6 +181,10 @@ static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev, resp->resp_status = hclgevf_resp_to_errno(resp_status); memcpy(resp->additional_info, req->msg.resp_data, HCLGE_MBX_MAX_RESP_DATA_SIZE * sizeof(u8)); + + /* ensure additional_info will be seen before setting received_resp */ + smp_wmb(); + if (match_id) { /* If match_id is not zero, it means PF support match_id. * if the match_id is right, VF get the right response, or diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index cfb1580f5850b5..8b7504a9df316c 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -1479,14 +1479,14 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw) } /** - * ice_download_pkg + * ice_download_pkg_with_sig_seg * @hw: pointer to the hardware structure * @pkg_hdr: pointer to package header * * Handles the download of a complete package. */ static enum ice_ddp_state -ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) { enum ice_aq_err aq_err = hw->adminq.sq_last_status; enum ice_ddp_state state = ICE_DDP_PKG_ERR; @@ -1519,6 +1519,103 @@ ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) state = ice_post_dwnld_pkg_actions(hw); ice_release_global_cfg_lock(hw); + + return state; +} + +/** + * ice_dwnld_cfg_bufs + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains global config lock and downloads the package configuration buffers + * to the firmware. + */ +static enum ice_ddp_state +ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + enum ice_ddp_state state; + struct ice_buf_hdr *bh; + int status; + + if (!bufs || !count) + return ICE_DDP_PKG_ERR; + + /* If the first buffer's first section has its metadata bit set + * then there are no buffers to be downloaded, and the operation is + * considered a success. + */ + bh = (struct ice_buf_hdr *)bufs; + if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + return ICE_DDP_PKG_SUCCESS; + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + return ICE_DDP_PKG_ALREADY_LOADED; + return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); + } + + state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true); + if (!state) + state = ice_post_dwnld_pkg_actions(hw); + + ice_release_global_cfg_lock(hw); + + return state; +} + +/** + * ice_download_pkg_without_sig_seg + * @hw: pointer to the hardware structure + * @ice_seg: pointer to the segment of the package to be downloaded + * + * Handles the download of a complete package without signature segment. + */ +static enum ice_ddp_state +ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg) +{ + struct ice_buf_table *ice_buf_tbl; + + ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", + ice_seg->hdr.seg_format_ver.major, + ice_seg->hdr.seg_format_ver.minor, + ice_seg->hdr.seg_format_ver.update, + ice_seg->hdr.seg_format_ver.draft); + + ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n", + le32_to_cpu(ice_seg->hdr.seg_type), + le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id); + + ice_buf_tbl = ice_find_buf_table(ice_seg); + + ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", + le32_to_cpu(ice_buf_tbl->buf_count)); + + return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); +} + +/** + * ice_download_pkg + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * @ice_seg: pointer to the segment of the package to be downloaded + * + * Handles the download of a complete package. + */ +static enum ice_ddp_state +ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + struct ice_seg *ice_seg) +{ + enum ice_ddp_state state; + + if (hw->pkg_has_signing_seg) + state = ice_download_pkg_with_sig_seg(hw, pkg_hdr); + else + state = ice_download_pkg_without_sig_seg(hw, ice_seg); + ice_post_pkg_dwnld_vlan_mode_cfg(hw); return state; @@ -2083,7 +2180,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) /* initialize package hints and then download package */ ice_init_pkg_hints(hw, seg); - state = ice_download_pkg(hw, pkg); + state = ice_download_pkg(hw, pkg, seg); if (state == ICE_DDP_PKG_ALREADY_LOADED) { ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 835c419ccc7437..86b180cb32a027 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -815,12 +815,6 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv, struct ice_pf *pf = d->pf; int ret; - if (prio > ICE_DPLL_PRIO_MAX) { - NL_SET_ERR_MSG_FMT(extack, "prio out of supported range 0-%d", - ICE_DPLL_PRIO_MAX); - return -EINVAL; - } - mutex_lock(&pf->dplls.lock); ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack); mutex_unlock(&pf->dplls.lock); @@ -1756,6 +1750,7 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu, } d->pf = pf; if (cgu) { + ice_dpll_update_state(pf, d, true); ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d); if (ret) { dpll_device_put(d->dpll); @@ -1796,8 +1791,6 @@ static int ice_dpll_init_worker(struct ice_pf *pf) struct ice_dplls *d = &pf->dplls; struct kthread_worker *kworker; - ice_dpll_update_state(pf, &d->eec, true); - ice_dpll_update_state(pf, &d->pps, true); kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); kworker = kthread_create_worker(0, "ice-dplls-%s", dev_name(ice_pf_to_dev(pf))); @@ -1830,6 +1823,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, int num_pins, i, ret = -EINVAL; struct ice_hw *hw = &pf->hw; struct ice_dpll_pin *pins; + unsigned long caps; u8 freq_supp_num; bool input; @@ -1849,6 +1843,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, } for (i = 0; i < num_pins; i++) { + caps = 0; pins[i].idx = i; pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input); pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input); @@ -1861,8 +1856,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, &dp->input_prio[i]); if (ret) return ret; - pins[i].prop.capabilities |= - DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE; + caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | + DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE); pins[i].prop.phase_range.min = pf->dplls.input_phase_adj_max; pins[i].prop.phase_range.max = @@ -1872,9 +1867,11 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, pf->dplls.output_phase_adj_max; pins[i].prop.phase_range.max = -pf->dplls.output_phase_adj_max; + ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps); + if (ret) + return ret; } - pins[i].prop.capabilities |= - DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + pins[i].prop.capabilities = caps; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); if (ret) return ret; diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index bb32b6d88373e2..93172e93995b94 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -6,7 +6,6 @@ #include "ice.h" -#define ICE_DPLL_PRIO_MAX 0xF #define ICE_DPLL_RCLK_NUM_MAX 4 /** ice_dpll_pin - store info about pins diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 6d573908de7a0b..a00b55e14aac4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -3961,3 +3961,57 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num) return ret; } + +/** + * ice_cgu_get_output_pin_state_caps - get output pin state capabilities + * @hw: pointer to the hw struct + * @pin_id: id of a pin + * @caps: capabilities to modify + * + * Return: + * * 0 - success, state capabilities were modified + * * negative - failure, capabilities were not modified + */ +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps) +{ + bool can_change = true; + + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3) + can_change = false; + break; + case ICE_DEV_ID_E810C_QSFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4) + can_change = false; + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 && + pin_id == ZL_OUT2) + can_change = false; + else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 && + pin_id == SI_OUT1) + can_change = false; + break; + default: + return -EINVAL; + } + if (can_change) + *caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + else + *caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 36aeeef99ec07e..cf76701566c724 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -282,6 +282,8 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num); void ice_ptp_init_phy_model(struct ice_hw *hw); +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps); #define PFTSYN_SEM_BYTES 4 diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 90817136808d46..29aac327574d64 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4790,14 +4790,17 @@ static void mvneta_ethtool_get_strings(struct net_device *netdev, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) { + struct mvneta_port *pp = netdev_priv(netdev); int i; for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++) memcpy(data + i * ETH_GSTRING_LEN, mvneta_statistics[i].name, ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics); - page_pool_ethtool_stats_get_strings(data); + if (!pp->bm_priv) { + data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics); + page_pool_ethtool_stats_get_strings(data); + } } } @@ -4915,8 +4918,10 @@ static void mvneta_ethtool_pp_stats(struct mvneta_port *pp, u64 *data) struct page_pool_stats stats = {}; int i; - for (i = 0; i < rxq_number; i++) - page_pool_get_stats(pp->rxqs[i].page_pool, &stats); + for (i = 0; i < rxq_number; i++) { + if (pp->rxqs[i].page_pool) + page_pool_get_stats(pp->rxqs[i].page_pool, &stats); + } page_pool_ethtool_stats_get(data, &stats); } @@ -4932,14 +4937,21 @@ static void mvneta_ethtool_get_stats(struct net_device *dev, for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++) *data++ = pp->ethtool_stats[i]; - mvneta_ethtool_pp_stats(pp, data); + if (!pp->bm_priv) + mvneta_ethtool_pp_stats(pp, data); } static int mvneta_ethtool_get_sset_count(struct net_device *dev, int sset) { - if (sset == ETH_SS_STATS) - return ARRAY_SIZE(mvneta_statistics) + - page_pool_ethtool_stats_get_count(); + if (sset == ETH_SS_STATS) { + int count = ARRAY_SIZE(mvneta_statistics); + struct mvneta_port *pp = netdev_priv(dev); + + if (!pp->bm_priv) + count += page_pool_ethtool_stats_get_count(); + + return count; + } return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index bb11e644d24f7b..af3928eddafd11 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -177,6 +177,8 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, struct mlx5_cqe64 *cqe, + u8 *md_buff, + u8 *md_buff_sz, int budget) { struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list; @@ -211,19 +213,24 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp); out: napi_consume_skb(skb, budget); - mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id); + md_buff[*md_buff_sz++] = metadata_id; if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) && !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work); } -static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) +static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq); - struct mlx5_cqwq *cqwq = &cq->wq; + int budget = min(napi_budget, MLX5E_TX_CQ_POLL_BUDGET); + u8 metadata_buff[MLX5E_TX_CQ_POLL_BUDGET]; + u8 metadata_buff_sz = 0; + struct mlx5_cqwq *cqwq; struct mlx5_cqe64 *cqe; int work_done = 0; + cqwq = &cq->wq; + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state))) return false; @@ -234,7 +241,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) do { mlx5_cqwq_pop(cqwq); - mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget); + mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, + metadata_buff, &metadata_buff_sz, napi_budget); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); mlx5_cqwq_update_db_record(cqwq); @@ -242,6 +250,10 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); + while (metadata_buff_sz > 0) + mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, + metadata_buff[--metadata_buff_sz]); + mlx5e_txqsq_wake(&ptpsq->txqsq); return work_done == budget; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index fea8c0a5fe893b..4358798d6ce14a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -492,11 +492,11 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter, void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) { - char icosq_str[MLX5E_REPORTER_PER_Q_MAX_LEN] = {}; char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; struct mlx5e_icosq *icosq = rq->icosq; struct mlx5e_priv *priv = rq->priv; struct mlx5e_err_ctx err_ctx = {}; + char icosq_str[32] = {}; err_ctx.ctx = rq; err_ctx.recover = mlx5e_rx_reporter_timeout_recover; @@ -505,7 +505,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) if (icosq) snprintf(icosq_str, sizeof(icosq_str), "ICOSQ: 0x%x, ", icosq->sqn); snprintf(err_str, sizeof(err_str), - "RX timeout on channel: %d, %sRQ: 0x%x, CQ: 0x%x", + "RX timeout on channel: %d, %s RQ: 0x%x, CQ: 0x%x", rq->ix, icosq_str, rq->rqn, rq->cq.mcq.cqn); mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 00a04fdd756f57..668da5c70e63de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -300,9 +300,6 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (err) goto destroy_neigh_entry; - e->encap_size = ipv4_encap_size; - e->encap_header = encap_header; - if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event @@ -322,6 +319,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, goto destroy_neigh_entry; } + e->encap_size = ipv4_encap_size; + e->encap_header = encap_header; e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv4_put(&attr); @@ -404,16 +403,12 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, if (err) goto free_encap; - e->encap_size = ipv4_encap_size; - kfree(e->encap_header); - e->encap_header = encap_header; - if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto release_neigh; + goto free_encap; } memset(&reformat_params, 0, sizeof(reformat_params)); @@ -427,6 +422,10 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, goto free_encap; } + e->encap_size = ipv4_encap_size; + kfree(e->encap_header); + e->encap_header = encap_header; + e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv4_put(&attr); @@ -568,9 +567,6 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (err) goto destroy_neigh_entry; - e->encap_size = ipv6_encap_size; - e->encap_header = encap_header; - if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event @@ -590,6 +586,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto destroy_neigh_entry; } + e->encap_size = ipv6_encap_size; + e->encap_header = encap_header; e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv6_put(&attr); @@ -671,16 +669,12 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, if (err) goto free_encap; - e->encap_size = ipv6_encap_size; - kfree(e->encap_header); - e->encap_header = encap_header; - if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto release_neigh; + goto free_encap; } memset(&reformat_params, 0, sizeof(reformat_params)); @@ -694,6 +688,10 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, goto free_encap; } + e->encap_size = ipv6_encap_size; + kfree(e->encap_header); + e->encap_header = encap_header; + e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv6_put(&attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 215261a6925507..792a0ea544cd39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -43,12 +43,17 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, struct ethtool_drvinfo *drvinfo) { struct mlx5_core_dev *mdev = priv->mdev; + int count; strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%04d (%.16s)", - fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), - mdev->board_id); + count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); + if (count == sizeof(drvinfo->fw_version)) + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev)); + strscpy(drvinfo->bus_info, dev_name(mdev->device), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 693e55b010d9e8..3ab682bbcf8678 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -71,13 +71,17 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; + int count; strscpy(drvinfo->driver, mlx5e_rep_driver_name, sizeof(drvinfo->driver)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%04d (%.16s)", - fw_rev_maj(mdev), fw_rev_min(mdev), - fw_rev_sub(mdev), mdev->board_id); + count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); + if (count == sizeof(drvinfo->fw_version)) + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev)); } static const struct counter_desc sw_rep_stats_desc[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9a5a5c2c7da9e1..7ca9e5b86778e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3147,7 +3147,7 @@ static struct mlx5_fields fields[] = { OFFLOAD(DIPV6_31_0, 32, U32_MAX, ip6.daddr.s6_addr32[3], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]), OFFLOAD(IPV6_HOPLIMIT, 8, U8_MAX, ip6.hop_limit, 0, ttl_hoplimit), - OFFLOAD(IP_DSCP, 16, 0xc00f, ip6, 0, ip_dscp), + OFFLOAD(IP_DSCP, 16, 0x0fc0, ip6, 0, ip_dscp), OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source, 0, tcp_sport), OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest, 0, tcp_dport), @@ -3158,21 +3158,31 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; -static unsigned long mask_to_le(unsigned long mask, int size) +static u32 mask_field_get(void *mask, struct mlx5_fields *f) { - __be32 mask_be32; - __be16 mask_be16; - - if (size == 32) { - mask_be32 = (__force __be32)(mask); - mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (size == 16) { - mask_be32 = (__force __be32)(mask); - mask_be16 = *(__be16 *)&mask_be32; - mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); + switch (f->field_bsize) { + case 32: + return be32_to_cpu(*(__be32 *)mask) & f->field_mask; + case 16: + return be16_to_cpu(*(__be16 *)mask) & (u16)f->field_mask; + default: + return *(u8 *)mask & (u8)f->field_mask; } +} - return mask; +static void mask_field_clear(void *mask, struct mlx5_fields *f) +{ + switch (f->field_bsize) { + case 32: + *(__be32 *)mask &= ~cpu_to_be32(f->field_mask); + break; + case 16: + *(__be16 *)mask &= ~cpu_to_be16((u16)f->field_mask); + break; + default: + *(u8 *)mask &= ~(u8)f->field_mask; + break; + } } static int offload_pedit_fields(struct mlx5e_priv *priv, @@ -3184,11 +3194,12 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; struct pedit_headers_action *hdrs = parse_attr->hdrs; void *headers_c, *headers_v, *action, *vals_p; - u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; - unsigned long mask, field_mask; + void *s_masks_p, *a_masks_p; int i, first, last, next_z; struct mlx5_fields *f; + unsigned long mask; + u32 s_mask, a_mask; u8 cmd; mod_acts = &parse_attr->mod_hdr_acts; @@ -3204,15 +3215,11 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, bool skip; f = &fields[i]; - /* avoid seeing bits set from previous iterations */ - s_mask = 0; - a_mask = 0; - s_masks_p = (void *)set_masks + f->offset; a_masks_p = (void *)add_masks + f->offset; - s_mask = *s_masks_p & f->field_mask; - a_mask = *a_masks_p & f->field_mask; + s_mask = mask_field_get(s_masks_p, f); + a_mask = mask_field_get(a_masks_p, f); if (!s_mask && !a_mask) /* nothing to offload here */ continue; @@ -3239,22 +3246,20 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, match_mask, f->field_bsize)) skip = true; /* clear to denote we consumed this field */ - *s_masks_p &= ~f->field_mask; + mask_field_clear(s_masks_p, f); } else { cmd = MLX5_ACTION_TYPE_ADD; mask = a_mask; vals_p = (void *)add_vals + f->offset; /* add 0 is no change */ - if ((*(u32 *)vals_p & f->field_mask) == 0) + if (!mask_field_get(vals_p, f)) skip = true; /* clear to denote we consumed this field */ - *a_masks_p &= ~f->field_mask; + mask_field_clear(a_masks_p, f); } if (skip) continue; - mask = mask_to_le(mask, f->field_bsize); - first = find_first_bit(&mask, f->field_bsize); next_z = find_next_zero_bit(&mask, f->field_bsize, first); last = find_last_bit(&mask, f->field_bsize); @@ -3281,10 +3286,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, MLX5_SET(set_action_in, action, field, f->field); if (cmd == MLX5_ACTION_TYPE_SET) { + unsigned long field_mask = f->field_mask; int start; - field_mask = mask_to_le(f->field_mask, f->field_bsize); - /* if field is bit sized it can start not from first bit */ start = find_first_bit(&field_mask, f->field_bsize); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index d41435c22ce56f..f0b506e562df31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -399,9 +399,9 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata); mlx5e_skb_cb_hwtstamp_init(skb); - mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); + mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); if (!netif_tx_queue_stopped(sq->txq) && mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { netif_tx_stop_queue(sq->txq); @@ -494,10 +494,10 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; - dev_kfree_skb_any(skb); if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist, be32_to_cpu(eseg->flow_table_metadata)); + dev_kfree_skb_any(skb); mlx5e_tx_flush(sq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ea0405e0a43fac..40a6cb052a2da3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -885,11 +885,14 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_irq *irq; + int cpu; irq = xa_load(&table->comp_irqs, vecidx); if (!irq) return; + cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq)); + cpumask_clear_cpu(cpu, &table->used_cpus); xa_erase(&table->comp_irqs, vecidx); mlx5_irq_affinity_irq_release(dev, irq); } @@ -897,16 +900,26 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx) static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; + struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev); + struct irq_affinity_desc af_desc = {}; struct mlx5_irq *irq; - irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx); - if (IS_ERR(irq)) { - /* In case SF irq pool does not exist, fallback to the PF irqs*/ - if (PTR_ERR(irq) == -ENOENT) - return comp_irq_request_pci(dev, vecidx); + /* In case SF irq pool does not exist, fallback to the PF irqs*/ + if (!mlx5_irq_pool_is_sf_pool(pool)) + return comp_irq_request_pci(dev, vecidx); + af_desc.is_managed = 1; + cpumask_copy(&af_desc.mask, cpu_online_mask); + cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus); + irq = mlx5_irq_affinity_request(pool, &af_desc); + if (IS_ERR(irq)) return PTR_ERR(irq); - } + + cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq)); + mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n", + pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)), + cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)), + mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ); return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b296ac52a43974..88236e75fd9013 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -984,7 +984,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) { + if (rep->vport == MLX5_VPORT_UPLINK && + on_esw == from_esw && on_esw->offloads.ft_ipsec_tx_pol) { dest.ft = on_esw->offloads.ft_ipsec_tx_pol; flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c index 047d5fed5f89e6..612e666ec26356 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c @@ -168,45 +168,3 @@ void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *i if (pool->irqs_per_cpu) cpu_put(pool, cpu); } - -/** - * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device. - * @dev: mlx5 device that is requesting the IRQ. - * @used_cpus: cpumask of bounded cpus by the device - * @vecidx: vector index to request an IRQ for. - * - * Each IRQ is bounded to at most 1 CPU. - * This function is requesting an IRQ according to the default assignment. - * The default assignment policy is: - * - request the least loaded IRQ which is not bound to any - * CPU of the previous IRQs requested. - * - * On success, this function updates used_cpus mask and returns an irq pointer. - * In case of an error, an appropriate error pointer is returned. - */ -struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev, - struct cpumask *used_cpus, u16 vecidx) -{ - struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev); - struct irq_affinity_desc af_desc = {}; - struct mlx5_irq *irq; - - if (!mlx5_irq_pool_is_sf_pool(pool)) - return ERR_PTR(-ENOENT); - - af_desc.is_managed = 1; - cpumask_copy(&af_desc.mask, cpu_online_mask); - cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus); - irq = mlx5_irq_affinity_request(pool, &af_desc); - - if (IS_ERR(irq)) - return irq; - - cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq)); - mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n", - pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)), - cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)), - mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ); - - return irq; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index aa29f09e835642..0c83ef174275a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -384,7 +384,12 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) { - return mlx5_ptp_adjtime(ptp, delta); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + return mlx5_ptp_adjtime_real_time(mdev, delta); } static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 653648216730ac..4dcf995cb1a204 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -28,7 +28,7 @@ struct mlx5_irq { struct atomic_notifier_head nh; cpumask_var_t mask; - char name[MLX5_MAX_IRQ_NAME]; + char name[MLX5_MAX_IRQ_FORMATTED_NAME]; struct mlx5_irq_pool *pool; int refcount; struct msi_map map; @@ -292,8 +292,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); - snprintf(irq->name, MLX5_MAX_IRQ_NAME, - "%s@pci:%s", name, pci_name(dev->pdev)); + snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME, + MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev)); err = request_irq(irq->map.virq, irq_int_handler, 0, irq->name, &irq->nh); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h index d3a77a0ab8488b..c4d377f8df3089 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h @@ -7,6 +7,9 @@ #include <linux/mlx5/driver.h> #define MLX5_MAX_IRQ_NAME (32) +#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s") +#define MLX5_MAX_IRQ_FORMATTED_NAME \ + (MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR)) /* max irq_index is 2047, so four chars */ #define MLX5_MAX_IRQ_IDX_CHARS (4) #define MLX5_EQ_REFS_PER_IRQ (2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 6ea88a58180472..e3ec559369fa07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -57,7 +57,8 @@ static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id) static bool mlx5dr_action_supp_fwd_fdb_multi_ft(struct mlx5_core_dev *dev) { - return (MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) || + return (MLX5_CAP_GEN(dev, steering_format_version) < MLX5_STEERING_FORMAT_CONNECTX_6DX || + MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) || MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 4e8527a724f504..6fa06ba2d34653 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -52,7 +52,6 @@ struct dr_qp_init_attr { u32 cqn; u32 pdn; u32 max_send_wr; - u32 max_send_sge; struct mlx5_uars_page *uar; u8 isolate_vl_tc:1; }; @@ -247,37 +246,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne) return err == CQ_POLL_ERR ? err : npolled; } -static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr) -{ - return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_flow_update_ctrl_seg) + - sizeof(struct mlx5_wqe_header_modify_argument_update_seg)); -} - -/* We calculate for specific RC QP with the required functionality */ -static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr) -{ - int update_arg_size; - int inl_size = 0; - int tot_size; - int size; - - update_arg_size = dr_qp_get_args_update_send_wqe_size(attr); - - size = sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg); - inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) + - DR_STE_SIZE, 16); - - size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg); - - size = max(size, update_arg_size); - - tot_size = max(size, inl_size); - - return ALIGN(tot_size, MLX5_SEND_WQE_BB); -} - static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, struct dr_qp_init_attr *attr) { @@ -285,7 +253,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {}; struct mlx5_wq_param wqp; struct mlx5dr_qp *dr_qp; - int wqe_size; int inlen; void *qpc; void *in; @@ -365,15 +332,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, if (err) goto err_in; dr_qp->uar = attr->uar; - wqe_size = dr_qp_calc_rc_send_wqe(attr); - dr_qp->max_inline_data = min(wqe_size - - (sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg)), - (2 * MLX5_SEND_WQE_BB - - (sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg)))); return dr_qp; @@ -437,48 +395,8 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl, MLX5_SEND_WQE_DS; } -static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp, - struct dr_data_seg *data_seg, void *wqe) -{ - int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg); - struct mlx5_wqe_inline_seg *seg; - int left_space; - int inl = 0; - void *addr; - int len; - int idx; - - seg = wqe; - wqe += sizeof(*seg); - addr = (void *)(unsigned long)(data_seg->addr); - len = data_seg->length; - inl += len; - left_space = MLX5_SEND_WQE_BB - inline_header_size; - - if (likely(len > left_space)) { - memcpy(wqe, addr, left_space); - len -= left_space; - addr += left_space; - idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1); - wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx); - } - - memcpy(wqe, addr, len); - - if (likely(inl)) { - seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG); - return DIV_ROUND_UP(inl + sizeof(seg->byte_count), - MLX5_SEND_WQE_DS); - } else { - return 0; - } -} - static void -dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp, - struct mlx5_wqe_ctrl_seg *wq_ctrl, +dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl, u64 remote_addr, u32 rkey, struct dr_data_seg *data_seg, @@ -494,17 +412,15 @@ dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp, wq_raddr->reserved = 0; wq_dseg = (void *)(wq_raddr + 1); - /* WQE ctrl segment + WQE remote addr segment */ - *size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS; - if (data_seg->send_flags & IB_SEND_INLINE) { - *size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg); - } else { - wq_dseg->byte_count = cpu_to_be32(data_seg->length); - wq_dseg->lkey = cpu_to_be32(data_seg->lkey); - wq_dseg->addr = cpu_to_be64(data_seg->addr); - *size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS; /* WQE data segment */ - } + wq_dseg->byte_count = cpu_to_be32(data_seg->length); + wq_dseg->lkey = cpu_to_be32(data_seg->lkey); + wq_dseg->addr = cpu_to_be64(data_seg->addr); + + *size = (sizeof(*wq_ctrl) + /* WQE ctrl segment */ + sizeof(*wq_dseg) + /* WQE data segment */ + sizeof(*wq_raddr)) / /* WQE remote addr segment */ + MLX5_SEND_WQE_DS; } static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl, @@ -535,7 +451,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr, switch (opcode) { case MLX5_OPCODE_RDMA_READ: case MLX5_OPCODE_RDMA_WRITE: - dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr, + dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr, rkey, data_seg, &size); break; case MLX5_OPCODE_FLOW_TBL_ACCESS: @@ -656,7 +572,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring, if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->write.send_flags |= IB_SEND_SIGNALED; else - send_info->write.send_flags &= ~IB_SEND_SIGNALED; + send_info->write.send_flags = 0; } static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, @@ -680,13 +596,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, } send_ring->pending_wqe++; - if (!send_info->write.lkey) - send_info->write.send_flags |= IB_SEND_INLINE; if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->write.send_flags |= IB_SEND_SIGNALED; - else - send_info->write.send_flags &= ~IB_SEND_SIGNALED; send_ring->pending_wqe++; send_info->read.length = send_info->write.length; @@ -696,9 +608,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, send_info->read.lkey = send_ring->sync_mr->mkey; if (send_ring->pending_wqe % send_ring->signal_th == 0) - send_info->read.send_flags |= IB_SEND_SIGNALED; + send_info->read.send_flags = IB_SEND_SIGNALED; else - send_info->read.send_flags &= ~IB_SEND_SIGNALED; + send_info->read.send_flags = 0; } static void dr_fill_data_segs(struct mlx5dr_domain *dmn, @@ -1345,7 +1257,6 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) dmn->send_ring->cq->qp = dmn->send_ring->qp; dmn->info.max_send_wr = QUEUE_SIZE; - init_attr.max_send_sge = 1; dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data, DR_STE_SIZE); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0c76c162b8a9f5..b9bb1d2f0237e9 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -624,6 +624,7 @@ struct rtl8169_private { unsigned supports_gmii:1; unsigned aspm_manageable:1; + unsigned dash_enabled:1; dma_addr_t counters_phys_addr; struct rtl8169_counters *counters; struct rtl8169_tc_offsets tc_offset; @@ -1253,14 +1254,26 @@ static bool r8168ep_check_dash(struct rtl8169_private *tp) return r8168ep_ocp_read(tp, 0x128) & BIT(0); } -static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp) +static bool rtl_dash_is_enabled(struct rtl8169_private *tp) +{ + switch (tp->dash_type) { + case RTL_DASH_DP: + return r8168dp_check_dash(tp); + case RTL_DASH_EP: + return r8168ep_check_dash(tp); + default: + return false; + } +} + +static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp) { switch (tp->mac_version) { case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: - return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE; + return RTL_DASH_DP; case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53: - return r8168ep_check_dash(tp) ? RTL_DASH_EP : RTL_DASH_NONE; + return RTL_DASH_EP; default: return RTL_DASH_NONE; } @@ -1453,7 +1466,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) device_set_wakeup_enable(tp_to_dev(tp), wolopts); - if (tp->dash_type == RTL_DASH_NONE) { + if (!tp->dash_enabled) { rtl_set_d3_pll_down(tp, !wolopts); tp->dev->wol_enabled = wolopts ? 1 : 0; } @@ -2512,7 +2525,7 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp) static void rtl_prepare_power_down(struct rtl8169_private *tp) { - if (tp->dash_type != RTL_DASH_NONE) + if (tp->dash_enabled) return; if (tp->mac_version == RTL_GIGA_MAC_VER_32 || @@ -4648,10 +4661,16 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl8169_cleanup(tp); rtl_disable_exit_l1(tp); rtl_prepare_power_down(tp); + + if (tp->dash_type != RTL_DASH_NONE) + rtl8168_driver_stop(tp); } static void rtl8169_up(struct rtl8169_private *tp) { + if (tp->dash_type != RTL_DASH_NONE) + rtl8168_driver_start(tp); + pci_set_master(tp->pci_dev); phy_init_hw(tp->phydev); phy_resume(tp->phydev); @@ -4869,7 +4888,7 @@ static int rtl8169_runtime_idle(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); - if (tp->dash_type != RTL_DASH_NONE) + if (tp->dash_enabled) return -EBUSY; if (!netif_running(tp->dev) || !netif_carrier_ok(tp->dev)) @@ -4895,8 +4914,7 @@ static void rtl_shutdown(struct pci_dev *pdev) /* Restore original MAC address */ rtl_rar_set(tp, tp->dev->perm_addr); - if (system_state == SYSTEM_POWER_OFF && - tp->dash_type == RTL_DASH_NONE) { + if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) { pci_wake_from_d3(pdev, tp->saved_wolopts); pci_set_power_state(pdev, PCI_D3hot); } @@ -5254,7 +5272,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); tp->aspm_manageable = !rc; - tp->dash_type = rtl_check_dash(tp); + tp->dash_type = rtl_get_dash_type(tp); + tp->dash_enabled = rtl_dash_is_enabled(tp); tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK; @@ -5325,7 +5344,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* configure chip for default features */ rtl8169_set_features(dev, dev->features); - if (tp->dash_type == RTL_DASH_NONE) { + if (!tp->dash_enabled) { rtl_set_d3_pll_down(tp, true); } else { rtl_set_d3_pll_down(tp, false); @@ -5365,7 +5384,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) "ok" : "ko"); if (tp->dash_type != RTL_DASH_NONE) { - netdev_info(dev, "DASH enabled\n"); + netdev_info(dev, "DASH %s\n", + tp->dash_enabled ? "enabled" : "disabled"); rtl8168_driver_start(tp); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3e50fd53a61744..2afb2bd25977a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5293,6 +5293,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) dma_dir = page_pool_get_dma_dir(rx_q->page_pool); buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE; + limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit); if (netif_msg_rx_status(priv)) { void *rx_head; @@ -5328,10 +5329,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) len = 0; } +read_again: if (count >= limit) break; -read_again: buf1_len = 0; buf2_len = 0; entry = next_entry; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 6c4b64227ac886..411898a4f38caa 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -2063,7 +2063,7 @@ static int prueth_probe(struct platform_device *pdev) &prueth->shram); if (ret) { dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret); - pruss_put(prueth->pruss); + goto put_pruss; } prueth->sram_pool = of_gen_pool_get(np, "sram", 0); @@ -2105,10 +2105,7 @@ static int prueth_probe(struct platform_device *pdev) prueth->iep1 = icss_iep_get_idx(np, 1); if (IS_ERR(prueth->iep1)) { ret = dev_err_probe(dev, PTR_ERR(prueth->iep1), "iep1 get failed\n"); - icss_iep_put(prueth->iep0); - prueth->iep0 = NULL; - prueth->iep1 = NULL; - goto free_pool; + goto put_iep0; } if (prueth->pdata.quirk_10m_link_issue) { @@ -2205,6 +2202,12 @@ netdev_exit: exit_iep: if (prueth->pdata.quirk_10m_link_issue) icss_iep_exit_fw(prueth->iep1); + icss_iep_put(prueth->iep1); + +put_iep0: + icss_iep_put(prueth->iep0); + prueth->iep0 = NULL; + prueth->iep1 = NULL; free_pool: gen_pool_free(prueth->sram_pool, @@ -2212,6 +2215,8 @@ free_pool: put_mem: pruss_release_mem_region(prueth->pruss, &prueth->shram); + +put_pruss: pruss_put(prueth->pruss); put_cores: diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 21e9cac7312186..2d5b021b4ea605 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -411,7 +411,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, return addr; } -static int ipvlan_process_v4_outbound(struct sk_buff *skb) +static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) { const struct iphdr *ip4h = ip_hdr(skb); struct net_device *dev = skb->dev; @@ -453,13 +453,11 @@ out: } #if IS_ENABLED(CONFIG_IPV6) -static int ipvlan_process_v6_outbound(struct sk_buff *skb) + +static noinline_for_stack int +ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct net_device *dev = skb->dev; - struct net *net = dev_net(dev); - struct dst_entry *dst; - int err, ret = NET_XMIT_DROP; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .daddr = ip6h->daddr, @@ -469,27 +467,38 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; + struct dst_entry *dst; + int err; - dst = ip6_route_output(net, NULL, &fl6); - if (dst->error) { - ret = dst->error; + dst = ip6_route_output(dev_net(dev), NULL, &fl6); + err = dst->error; + if (err) { dst_release(dst); - goto err; + return err; } skb_dst_set(skb, dst); + return 0; +} + +static int ipvlan_process_v6_outbound(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + int err, ret = NET_XMIT_DROP; + + err = ipvlan_route_v6_outbound(dev, skb); + if (unlikely(err)) { + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return err; + } memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - err = ip6_local_out(net, skb->sk, skb); + err = ip6_local_out(dev_net(dev), skb->sk, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; - goto out; -err: - DEV_STATS_INC(dev, tx_errors); - kfree_skb(skb); -out: return ret; } #else diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 02bd201bc7e58e..c8da94af4161a5 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -780,7 +780,7 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change) if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) + if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index ebcdffdf4f0e01..52d05ce4a28198 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -453,6 +453,10 @@ ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, (int __user *) argp)) break; + if (val > U16_MAX) { + err = -EINVAL; + break; + } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; @@ -687,7 +691,7 @@ ppp_sync_input(struct syncppp *ap, const u8 *buf, const u8 *flags, int count) /* strip address/control field if present */ p = skb->data; - if (p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { + if (skb->len >= 2 && p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto err; diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 3f7a7478880240..7513018c9f9ac7 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -572,7 +572,8 @@ ssize_t ptp_read(struct posix_clock_context *pccontext, uint rdflags, for (i = 0; i < cnt; i++) { event[i] = queue->buf[queue->head]; - queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS; + /* Paired with READ_ONCE() in queue_cnt() */ + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); } spin_unlock_irqrestore(&queue->lock, flags); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 3134568af622d3..15b804ba48685e 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -57,10 +57,11 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, dst->t.sec = seconds; dst->t.nsec = remainder; + /* Both WRITE_ONCE() are paired with READ_ONCE() in queue_cnt() */ if (!queue_free(queue)) - queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS; + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); - queue->tail = (queue->tail + 1) % PTP_MAX_TIMESTAMPS; + WRITE_ONCE(queue->tail, (queue->tail + 1) % PTP_MAX_TIMESTAMPS); spin_unlock_irqrestore(&queue->lock, flags); } diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 35fde0a0574606..45f9002a5dcaea 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -85,9 +85,13 @@ struct ptp_vclock { * that a writer might concurrently increment the tail does not * matter, since the queue remains nonempty nonetheless. */ -static inline int queue_cnt(struct timestamp_event_queue *q) +static inline int queue_cnt(const struct timestamp_event_queue *q) { - int cnt = q->tail - q->head; + /* + * Paired with WRITE_ONCE() in enqueue_external_timestamp(), + * ptp_read(), extts_fifo_show(). + */ + int cnt = READ_ONCE(q->tail) - READ_ONCE(q->head); return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt; } diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 7d023d9d0acbfb..f7a499a1bd39ec 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -94,7 +94,8 @@ static ssize_t extts_fifo_show(struct device *dev, qcnt = queue_cnt(queue); if (qcnt) { event = queue->buf[queue->head]; - queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS; + /* Paired with READ_ONCE() in queue_cnt() */ + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); } spin_unlock_irqrestore(&queue->lock, flags); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4825d3cdb2923..6762dac3ef7615 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,7 +56,7 @@ extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; -extern bool bpf_global_ma_set, bpf_global_percpu_ma_set; +extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, @@ -909,10 +909,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static bool bpf_is_ldimm64(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; + return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 8fa23bdcedbf98..007fd9c3e4b62c 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -420,7 +420,7 @@ static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising) * A function that translates value of following registers to the linkmode: * IEEE 802.3-2018 45.2.3.10 "EEE control and capability 1" register (3.20) * IEEE 802.3-2018 45.2.7.13 "EEE advertisement 1" register (7.60) - * IEEE 802.3-2018 45.2.7.14 "EEE "link partner ability 1 register (7.61) + * IEEE 802.3-2018 45.2.7.14 "EEE link partner ability 1" register (7.61) */ static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val) { diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3bbd13ab1ecf59..b157c5cafd14cf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -178,9 +178,9 @@ static inline __be32 nft_reg_load_be32(const u32 *sreg) return *(__force __be32 *)sreg; } -static inline void nft_reg_store64(u32 *dreg, u64 val) +static inline void nft_reg_store64(u64 *dreg, u64 val) { - put_unaligned(val, (u64 *)dreg); + put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index 8a6dbfb233362b..77f87c622a2ef4 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -58,6 +58,11 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a) return to_ct_params(a)->nf_ft; } +static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a) +{ + return to_ct_params(a)->helper; +} + #else static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; } static inline int tcf_ct_action(const struct tc_action *a) { return 0; } @@ -65,6 +70,10 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a) { return NULL; } +static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a) +{ + return NULL; +} #endif /* CONFIG_NF_CONNTRACK */ #if IS_ENABLED(CONFIG_NET_ACT_CT) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 08626b519ce23f..cd3afe57ece3cc 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -64,8 +64,8 @@ #define OFF insn->off #define IMM insn->imm -struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; -bool bpf_global_ma_set, bpf_global_percpu_ma_set; +struct bpf_mem_alloc bpf_global_ma; +bool bpf_global_ma_set; /* No hurry in this branch * @@ -2934,9 +2934,7 @@ static int __init bpf_global_ma_init(void) ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); bpf_global_ma_set = !ret; - ret = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true); - bpf_global_percpu_ma_set = !ret; - return !bpf_global_ma_set || !bpf_global_percpu_ma_set; + return ret; } late_initcall(bpf_global_ma_init); #endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bd1c42eb540f1f..6da370a047feb9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -26,6 +26,7 @@ #include <linux/poison.h> #include <linux/module.h> #include <linux/cpumask.h> +#include <linux/bpf_mem_alloc.h> #include <net/xdp.h> #include "disasm.h" @@ -41,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #undef BPF_LINK_TYPE }; +struct bpf_mem_alloc bpf_global_percpu_ma; +static bool bpf_global_percpu_ma_set; + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -336,6 +340,7 @@ struct bpf_kfunc_call_arg_meta { struct btf *btf_vmlinux; static DEFINE_MUTEX(bpf_verifier_lock); +static DEFINE_MUTEX(bpf_percpu_ma_lock); static const struct bpf_line_info * find_linfo(const struct bpf_verifier_env *env, u32 insn_off) @@ -3516,12 +3521,29 @@ static int push_jmp_history(struct bpf_verifier_env *env, /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. + * Return -ENOENT if we exhausted all instructions within given state. + * + * It's legal to have a bit of a looping with the same starting and ending + * insn index within the same state, e.g.: 3->4->5->3, so just because current + * instruction index is the same as state's first_idx doesn't mean we are + * done. If there is still some jump history left, we should keep going. We + * need to take into account that we might have a jump history between given + * state's parent and itself, due to checkpointing. In this case, we'll have + * history entry recording a jump from last instruction of parent state and + * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; + if (i == st->first_insn_idx) { + if (cnt == 0) + return -ENOENT; + if (cnt == 1 && st->jmp_history[0].idx == i) + return -ENOENT; + } + if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; @@ -4401,10 +4423,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) * Nothing to be tracked further in the parent state. */ return 0; - if (i == first_idx) - break; subseq_idx = i; i = get_prev_insn_idx(st, i, &history); + if (i == -ENOENT) + break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask @@ -12074,8 +12096,19 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set) return -ENOMEM; - if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && !bpf_global_percpu_ma_set) - return -ENOMEM; + if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { + if (!bpf_global_percpu_ma_set) { + mutex_lock(&bpf_percpu_ma_lock); + if (!bpf_global_percpu_ma_set) { + err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true); + if (!err) + bpf_global_percpu_ma_set = true; + } + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + } if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); @@ -15386,8 +15419,7 @@ enum { * w - next instruction * e - edge */ -static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, - bool loop_ok) +static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; @@ -15419,7 +15451,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, insn_stack[env->cfg.cur_stack++] = w; return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - if (loop_ok && env->bpf_capable) + if (env->bpf_capable) return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); @@ -15439,24 +15471,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { - int ret; + int ret, insn_sz; - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; + ret = push_insn(t, t + insn_sz, FALLTHROUGH, env); if (ret) return ret; - mark_prune_point(env, t + 1); + mark_prune_point(env, t + insn_sz); /* when we exit from subprog, we need to record non-linear history */ - mark_jmp_point(env, t + 1); + mark_jmp_point(env, t + insn_sz); if (visit_callee) { mark_prune_point(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, - /* It's ok to allow recursion from CFG point of - * view. __check_func_call() will do the actual - * check. - */ - bpf_pseudo_func(insns + t)); + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); } return ret; } @@ -15469,15 +15497,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, static int visit_insn(int t, struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; - int ret, off; + int ret, off, insn_sz; if (bpf_pseudo_func(insn)) return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ if (BPF_CLASS(insn->code) != BPF_JMP && - BPF_CLASS(insn->code) != BPF_JMP32) - return push_insn(t, t + 1, FALLTHROUGH, env, false); + BPF_CLASS(insn->code) != BPF_JMP32) { + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + return push_insn(t, t + insn_sz, FALLTHROUGH, env); + } switch (BPF_OP(insn->code)) { case BPF_EXIT: @@ -15523,8 +15553,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) off = insn->imm; /* unconditional jump with single edge */ - ret = push_insn(t, t + off + 1, FALLTHROUGH, env, - true); + ret = push_insn(t, t + off + 1, FALLTHROUGH, env); if (ret) return ret; @@ -15537,11 +15566,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env) /* conditional jump with two edges */ mark_prune_point(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env, true); + ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) return ret; - return push_insn(t, t + insn->off + 1, BRANCH, env, true); + return push_insn(t, t + insn->off + 1, BRANCH, env); } } @@ -15607,11 +15636,21 @@ walk_cfg: } for (i = 0; i < insn_cnt; i++) { + struct bpf_insn *insn = &env->prog->insnsi[i]; + if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } + if (bpf_is_ldimm64(insn)) { + if (insn_state[i + 1] != 0) { + verbose(env, "jump into the middle of ldimm64 insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + i++; /* skip second half of ldimm64 */ + } } ret = 0; /* cfg looks good */ diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index b5c406a6e7654f..abb090f94ed260 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -37,7 +37,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, ktime_t tstamp = skb->tstamp; struct ip_frag_state state; struct iphdr *iph; - int err; + int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && diff --git a/net/core/dev.c b/net/core/dev.c index 0d548431f3fadf..af53f6d838ce9e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1119,7 +1119,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *res) if (i == max_netdevices) return -ENFILE; - snprintf(res, IFNAMSIZ, name, i); + /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */ + strscpy(buf, name, IFNAMSIZ); + snprintf(res, IFNAMSIZ, buf, i); return i; } diff --git a/net/core/gso_test.c b/net/core/gso_test.c index ceb684be4cbf86..4c2e77bd12f4b1 100644 --- a/net/core/gso_test.c +++ b/net/core/gso_test.c @@ -180,18 +180,17 @@ static void gso_test_func(struct kunit *test) } if (tcase->frag_skbs) { - unsigned int total_size = 0, total_true_size = 0, alloc_size = 0; + unsigned int total_size = 0, total_true_size = 0; struct sk_buff *frag_skb, *prev = NULL; - page = alloc_page(GFP_KERNEL); - KUNIT_ASSERT_NOT_NULL(test, page); - page_ref_add(page, tcase->nr_frag_skbs - 1); - for (i = 0; i < tcase->nr_frag_skbs; i++) { unsigned int frag_size; + page = alloc_page(GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, page); + frag_size = tcase->frag_skbs[i]; - frag_skb = build_skb(page_address(page) + alloc_size, + frag_skb = build_skb(page_address(page), frag_size + shinfo_size); KUNIT_ASSERT_NOT_NULL(test, frag_skb); __skb_put(frag_skb, frag_size); @@ -204,11 +203,8 @@ static void gso_test_func(struct kunit *test) total_size += frag_size; total_true_size += frag_skb->truesize; - alloc_size += frag_size + shinfo_size; } - KUNIT_ASSERT_LE(test, alloc_size, PAGE_SIZE); - skb->len += total_size; skb->data_len += total_size; skb->truesize += total_true_size; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 598c1b114d2c22..a532f749e47781 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -751,12 +751,12 @@ int __inet_hash(struct sock *sk, struct sock *osk) if (err) goto unlock; } + sock_set_flag(sk, SOCK_RCU_FREE); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) __sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head); else __sk_nulls_add_node_rcu(sk, &ilb2->nulls_head); - sock_set_flag(sk, SOCK_RCU_FREE); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); unlock: spin_unlock(&ilb2->lock); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 1529ec35881552..bf4d96f6f99a6e 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1515,8 +1515,9 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - remove_anno_list_by_saddr(msk, &entry->addr); - if (alist.nr < MPTCP_RM_IDS_MAX) + if ((remove_anno_list_by_saddr(msk, &entry->addr) || + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && + alist.nr < MPTCP_RM_IDS_MAX) alist.ids[alist.nr++] = entry->addr.id; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a0b8356cd8c58f..bc81ea53a04992 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1230,6 +1230,8 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk, mptcp_do_fallback(ssk); } +#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1)) + static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) @@ -1256,6 +1258,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, return -EAGAIN; /* compute send limit */ + if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE)) + ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE; info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); copy = info->size_goal; @@ -3398,10 +3402,11 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); if (unlikely(msk->cb_flags)) { - /* be sure to set the current sk state before tacking actions - * depending on sk_state, that is processing MPTCP_ERROR_REPORT + /* be sure to set the current sk state before taking actions + * depending on sk_state (MPTCP_ERROR_REPORT) + * On sk release avoid actions depending on the first subflow */ - if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags)) + if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags) && msk->first) __mptcp_set_connected(sk); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 77f5e8932abf64..35368073370048 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -738,8 +738,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname, val = READ_ONCE(inet_sk(sk)->tos); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + slow = lock_sock_fast(ssk); __ip_sock_set_tos(ssk, val); + unlock_sock_fast(ssk, slow); } release_sock(sk); diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index f8854bff286cbd..62fb1031763d14 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, if ((had_link == has_link) || chained) return 0; - if (had_link) - netif_carrier_off(ndp->ndev.dev); - else - netif_carrier_on(ndp->ndev.dev); - if (!ndp->multi_package && !nc->package->multi_channel) { if (had_link) { ndp->flags |= NCSI_DEV_RESHUFFLE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 35d2f9c9ada025..4c133e06be1de2 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); ip_set_dereference((inst)->ip_set_list)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] +#define ip_set_dereference_nfnl(p) \ + rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -708,15 +710,10 @@ __ip_set_put_netlink(struct ip_set *set) static struct ip_set * ip_set_rcu_get(struct net *net, ip_set_id_t index) { - struct ip_set *set; struct ip_set_net *inst = ip_set_pernet(net); - rcu_read_lock(); - /* ip_set_list itself needs to be protected */ - set = rcu_dereference(inst->ip_set_list)[index]; - rcu_read_unlock(); - - return set; + /* ip_set_list and the set pointer need to be protected */ + return ip_set_dereference_nfnl(inst->ip_set_list)[index]; } static inline void @@ -1397,6 +1394,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); + /* Make sure all readers of the old set pointers are completed. */ + synchronize_rcu(); + return 0; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a761ee6796f6fa..c0a42989b98226 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7263,10 +7263,11 @@ static int nf_tables_delsetelem(struct sk_buff *skb, if (err < 0) { NL_SET_BAD_ATTR(extack, attr); - break; + return err; } } - return err; + + return 0; } /* @@ -9679,16 +9680,14 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) call_rcu(&trans->rcu, nft_trans_gc_trans_free); } -static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq, - bool sync) +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq) { - struct nft_set_elem_catchall *catchall, *next; + struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; - struct nft_elem_priv *elem_priv; struct nft_set_ext *ext; - list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_expired(ext)) @@ -9698,35 +9697,42 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, nft_set_elem_dead(ext); dead_elem: - if (sync) - gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); - else - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); - + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); if (!gc) return NULL; - elem_priv = catchall->elem; - if (sync) { - nft_setelem_data_deactivate(gc->net, gc->set, elem_priv); - nft_setelem_catchall_destroy(catchall); - } - - nft_trans_gc_elem_add(gc, elem_priv); + nft_trans_gc_elem_add(gc, catchall->elem); } return gc; } -struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, - unsigned int gc_seq) -{ - return nft_trans_gc_catchall(gc, gc_seq, false); -} - struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) { - return nft_trans_gc_catchall(gc, 0, true); + struct nft_set_elem_catchall *catchall, *next; + const struct nft_set *set = gc->set; + struct nft_elem_priv *elem_priv; + struct nft_set_ext *ext; + + WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net)); + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); + if (!gc) + return NULL; + + elem_priv = catchall->elem; + nft_setelem_data_deactivate(gc->net, gc->set, elem_priv); + nft_setelem_catchall_destroy(catchall); + nft_trans_gc_elem_add(gc, elem_priv); + } + + return gc; } static void nf_tables_module_autoload_cleanup(struct net *net) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index e596d1a842f702..f6e791a6810151 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -38,13 +38,14 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->size) { case 8: { + u64 *dst64 = (void *)dst; u64 src64; switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { src64 = nft_reg_load64(&src[i]); - nft_reg_store64(&dst[i], + nft_reg_store64(&dst64[i], be64_to_cpu((__force __be64)src64)); } break; @@ -52,7 +53,7 @@ void nft_byteorder_eval(const struct nft_expr *expr, for (i = 0; i < priv->len / 8; i++) { src64 = (__force __u64) cpu_to_be64(nft_reg_load64(&src[i])); - nft_reg_store64(&dst[i], src64); + nft_reg_store64(&dst64[i], src64); } break; } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index f7da7c43333b5a..ba0d3683a45d32 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key, { switch (key) { case NFT_META_TIME_NS: - nft_reg_store64(dest, ktime_get_real_ns()); + nft_reg_store64((u64 *)dest, ktime_get_real_ns()); break; case NFT_META_TIME_DAY: nft_reg_store8(dest, nft_meta_weekday()); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 6f1186abd47b43..baa3fea4fe65c8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -624,14 +624,12 @@ static void nft_rbtree_gc(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; - struct nftables_pernet *nft_net; struct rb_node *node, *next; struct nft_trans_gc *gc; struct net *net; set = nft_set_container_of(priv); net = read_pnet(&set->net); - nft_net = nft_pernet(net); gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 0db0ecf1d11038..b3f4a503ee2ba4 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1549,6 +1549,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data, if (bind) { struct flow_action_entry *entry = entry_data; + if (tcf_ct_helper(act)) + return -EOPNOTSUPP; + entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 5bc076f2fa74a2..c763008a8adbaa 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -102,6 +102,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) return -EMSGSIZE; skb_put(skb, TLV_SPACE(len)); + memset(tlv, 0, TLV_SPACE(len)); tlv->tlv_type = htons(type); tlv->tlv_len = htons(TLV_LENGTH(len)); if (len && data) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 45506a95b25f8a..a357dc5f24046d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2581,15 +2581,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) WRITE_ONCE(u->oob_skb, NULL); - + else + skb_get(oob_skb); unix_state_unlock(sk); chunk = state->recv_actor(oob_skb, 0, chunk, state); - if (!(state->flags & MSG_PEEK)) { + if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - kfree_skb(oob_skb); - } + + consume_skb(oob_skb); mutex_unlock(&u->iolock); diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c index df7697b94007b1..c1f55e1d80a426 100644 --- a/tools/testing/selftests/bpf/progs/verifier_cfg.c +++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c @@ -97,4 +97,66 @@ l0_%=: r2 = r0; \ " ::: __clobber_all); } +SEC("socket") +__description("conditional loop (2)") +__success +__failure_unpriv __msg_unpriv("back-edge from insn 10 to 11") +__naked void conditional_loop2(void) +{ + asm volatile (" \ + r9 = 2 ll; \ + r3 = 0x20 ll; \ + r4 = 0x35 ll; \ + r8 = r4; \ + goto l1_%=; \ +l0_%=: r9 -= r3; \ + r9 -= r4; \ + r9 -= r8; \ +l1_%=: r8 += r4; \ + if r8 < 0x64 goto l0_%=; \ + r0 = r9; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unconditional loop after conditional jump") +__failure __msg("infinite loop detected") +__failure_unpriv __msg_unpriv("back-edge from insn 3 to 2") +__naked void uncond_loop_after_cond_jmp(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 > 0 goto l1_%=; \ +l0_%=: r0 = 1; \ + goto l0_%=; \ +l1_%=: exit; \ +" ::: __clobber_all); +} + + +__naked __noinline __used +static unsigned long never_ending_subprog() +{ + asm volatile (" \ + r0 = r1; \ + goto -1; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unconditional loop after conditional jump") +/* infinite loop is detected *after* check_cfg() */ +__failure __msg("infinite loop detected") +__naked void uncond_loop_in_subprog_after_cond_jmp(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 > 0 goto l1_%=; \ +l0_%=: r0 += 1; \ + call never_ending_subprog; \ +l1_%=: exit; \ +" ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c index 5bc86af80a9ad4..71735dbf33d4f8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_loops1.c +++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c @@ -75,9 +75,10 @@ l0_%=: r0 += 1; \ " ::: __clobber_all); } -SEC("tracepoint") +SEC("socket") __description("bounded loop, start in the middle") -__failure __msg("back-edge") +__success +__failure_unpriv __msg_unpriv("back-edge") __naked void loop_start_in_the_middle(void) { asm volatile (" \ @@ -136,7 +137,9 @@ l0_%=: exit; \ SEC("tracepoint") __description("bounded recursion") -__failure __msg("back-edge") +__failure +/* verifier limitation in detecting max stack depth */ +__msg("the call stack of 8 frames is too deep !") __naked void bounded_recursion(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 193c0f8272d056..6b564d4c09866a 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -91,3 +91,43 @@ __naked int bpf_end_bswap(void) } #endif /* v4 instruction */ + +SEC("?raw_tp") +__success __log_level(2) +/* + * Without the bug fix there will be no history between "last_idx 3 first_idx 3" + * and "parent state regs=" lines. "R0_w=6" parts are here to help anchor + * expected log messages to the one specific mark_chain_precision operation. + * + * This is quite fragile: if verifier checkpointing heuristic changes, this + * might need adjusting. + */ +__msg("2: (07) r0 += 1 ; R0_w=6") +__msg("3: (35) if r0 >= 0xa goto pc+1") +__msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1") +__msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1") +__msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4") +__msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1") +__msg("mark_precise: frame0: parent state regs= stack=: R0_rw=P4") +__msg("3: R0_w=6") +__naked int state_loop_first_last_equal(void) +{ + asm volatile ( + "r0 = 0;" + "l0_%=:" + "r0 += 1;" + "r0 += 1;" + /* every few iterations we'll have a checkpoint here with + * first_idx == last_idx, potentially confusing precision + * backtracking logic + */ + "if r0 >= 10 goto l1_%=;" /* checkpoint + mark_precise */ + "goto l0_%=;" + "l1_%=:" + "exit;" + ::: __clobber_common + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 1bdf2b43e49eaf..3d5cd51071f047 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -442,7 +442,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn 0 to 0", + .errstr = "the call stack of 9 frames is too deep", .result = REJECT, }, { @@ -799,7 +799,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge", + .errstr = "the call stack of 9 frames is too deep", .result = REJECT, }, { @@ -811,7 +811,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge", + .errstr = "the call stack of 9 frames is too deep", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c index f9297900cea6d4..78f19c255f20b4 100644 --- a/tools/testing/selftests/bpf/verifier/ld_imm64.c +++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c @@ -9,8 +9,8 @@ BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { @@ -23,8 +23,8 @@ BPF_LD_IMM64(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 591ca9637b23e8..b604c570309a7f 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -908,8 +908,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) struct xdp_info *meta = data - sizeof(struct xdp_info); if (meta->count != pkt->pkt_nb) { - ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n", - __func__, pkt->pkt_nb, meta->count); + ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n", + __func__, pkt->pkt_nb, + (unsigned long long)meta->count); return false; } @@ -926,11 +927,13 @@ static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 exp if (addr >= umem->num_frames * umem->frame_size || addr + len > umem->num_frames * umem->frame_size) { - ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len); + ksft_print_msg("Frag invalid addr: %llx len: %u\n", + (unsigned long long)addr, len); return false; } if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) { - ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len); + ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", + (unsigned long long)addr, len); return false; } @@ -1029,7 +1032,8 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size) u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); ksft_print_msg("[%s] Too many packets completed\n", __func__); - ksft_print_msg("Last completion address: %llx\n", addr); + ksft_print_msg("Last completion address: %llx\n", + (unsigned long long)addr); return TEST_FAILURE; } @@ -1513,8 +1517,9 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject) } if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) { - ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n", - __func__, stats.tx_invalid_descs, + ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n", + __func__, + (unsigned long long)stats.tx_invalid_descs, ifobject->xsk->pkt_stream->nb_pkts); return TEST_FAILURE; } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 75a2438efdf373..3c94f2f194d681 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3240,7 +3240,7 @@ fastclose_tests() if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr 0 0 0 + chk_join_nr 0 0 0 0 0 0 1 chk_fclose_nr 1 1 invert chk_rst_nr 1 1 fi |