diff options
66 files changed, 494 insertions, 350 deletions
diff --git a/Documentation/bpf/bpf_design_QA.rst b/Documentation/bpf/bpf_design_QA.rst index 12a246fcf6cb..2df7b067ab93 100644 --- a/Documentation/bpf/bpf_design_QA.rst +++ b/Documentation/bpf/bpf_design_QA.rst @@ -246,17 +246,6 @@ program is loaded the kernel will print warning message, so this helper is only useful for experiments and prototypes. Tracing BPF programs are root only. -Q: bpf_trace_printk() helper warning ------------------------------------- -Q: When bpf_trace_printk() helper is used the kernel prints nasty -warning message. Why is that? - -A: This is done to nudge program authors into better interfaces when -programs need to pass data to user space. Like bpf_perf_event_output() -can be used to efficiently stream data via perf ring buffer. -BPF maps can be used for asynchronous data sharing between kernel -and user space. bpf_trace_printk() should only be used for debugging. - Q: New functionality via kernel modules? ---------------------------------------- Q: Can BPF functionality such as new program or map types, new diff --git a/MAINTAINERS b/MAINTAINERS index 68b51b70ac8f..2843effadff8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11986,7 +11986,8 @@ F: include/uapi/linux/netrom.h F: net/netrom/ NETRONOME ETHERNET DRIVERS -M: Jakub Kicinski <kuba@kernel.org> +M: Simon Horman <simon.horman@netronome.com> +R: Jakub Kicinski <kuba@kernel.org> L: oss-drivers@netronome.com S: Maintained F: drivers/net/ethernet/netronome/ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 9162856de1b1..e972138a14ad 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1728,7 +1728,7 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) /* hardware completion status should be available by this time */ if (ret) { dev_err(&hdev->pdev->dev, - "could'nt get reset done status from h/w, timeout!\n"); + "couldn't get reset done status from h/w, timeout!\n"); return ret; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c index c6adc776f3c8..16bda7381ba0 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c @@ -334,19 +334,14 @@ void hinic_devlink_unregister(struct hinic_devlink_priv *priv) static int chip_fault_show(struct devlink_fmsg *fmsg, struct hinic_fault_event *event) { - char fault_level[FAULT_TYPE_MAX][FAULT_SHOW_STR_LEN + 1] = { - "fatal", "reset", "flr", "general", "suggestion"}; - char level_str[FAULT_SHOW_STR_LEN + 1] = {0}; - u8 level; + const char * const level_str[FAULT_LEVEL_MAX + 1] = { + "fatal", "reset", "flr", "general", "suggestion", "Unknown"}; + u8 fault_level; int err; - level = event->event.chip.err_level; - if (level < FAULT_LEVEL_MAX) - strncpy(level_str, fault_level[level], strlen(fault_level[level])); - else - strncpy(level_str, "Unknown", strlen("Unknown")); - - if (level == FAULT_LEVEL_SERIOUS_FLR) { + fault_level = (event->event.chip.err_level < FAULT_LEVEL_MAX) ? + event->event.chip.err_level : FAULT_LEVEL_MAX; + if (fault_level == FAULT_LEVEL_SERIOUS_FLR) { err = devlink_fmsg_u32_pair_put(fmsg, "Function level err func_id", (u32)event->event.chip.func_id); if (err) @@ -361,7 +356,7 @@ static int chip_fault_show(struct devlink_fmsg *fmsg, if (err) return err; - err = devlink_fmsg_string_pair_put(fmsg, "err_level", level_str); + err = devlink_fmsg_string_pair_put(fmsg, "err_level", level_str[fault_level]); if (err) return err; @@ -381,18 +376,15 @@ static int chip_fault_show(struct devlink_fmsg *fmsg, static int fault_report_show(struct devlink_fmsg *fmsg, struct hinic_fault_event *event) { - char fault_type[FAULT_TYPE_MAX][FAULT_SHOW_STR_LEN + 1] = { + const char * const type_str[FAULT_TYPE_MAX + 1] = { "chip", "ucode", "mem rd timeout", "mem wr timeout", - "reg rd timeout", "reg wr timeout", "phy fault"}; - char type_str[FAULT_SHOW_STR_LEN + 1] = {0}; + "reg rd timeout", "reg wr timeout", "phy fault", "Unknown"}; + u8 fault_type; int err; - if (event->type < FAULT_TYPE_MAX) - strncpy(type_str, fault_type[event->type], strlen(fault_type[event->type])); - else - strncpy(type_str, "Unknown", strlen("Unknown")); + fault_type = (event->type < FAULT_TYPE_MAX) ? event->type : FAULT_TYPE_MAX; - err = devlink_fmsg_string_pair_put(fmsg, "Fault type", type_str); + err = devlink_fmsg_string_pair_put(fmsg, "Fault type", type_str[fault_type]); if (err) return err; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index dc6e645f2689..701eb81e09a7 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -504,8 +504,6 @@ enum hinic_fault_type { FAULT_TYPE_MAX, }; -#define FAULT_SHOW_STR_LEN 16 - enum hinic_fault_err_level { FAULT_LEVEL_FATAL, FAULT_LEVEL_SERIOUS_RESET, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 1944bf5264db..26988ad7ec97 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -412,7 +412,7 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, new->flags = flags; - new->q.info = devm_kzalloc(dev, sizeof(*new->q.info) * num_descs, + new->q.info = devm_kcalloc(dev, num_descs, sizeof(*new->q.info), GFP_KERNEL); if (!new->q.info) { netdev_err(lif->netdev, "Cannot allocate queue info\n"); @@ -462,7 +462,7 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, new->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; } - new->cq.info = devm_kzalloc(dev, sizeof(*new->cq.info) * num_descs, + new->cq.info = devm_kcalloc(dev, num_descs, sizeof(*new->cq.info), GFP_KERNEL); if (!new->cq.info) { netdev_err(lif->netdev, "Cannot allocate completion queue info\n"); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 20b1b43a0e39..1166b98d8bb2 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -474,13 +474,24 @@ static int emac_clks_phase1_init(struct platform_device *pdev, ret = clk_prepare_enable(adpt->clk[EMAC_CLK_CFG_AHB]); if (ret) - return ret; + goto disable_clk_axi; ret = clk_set_rate(adpt->clk[EMAC_CLK_HIGH_SPEED], 19200000); if (ret) - return ret; + goto disable_clk_cfg_ahb; + + ret = clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]); + if (ret) + goto disable_clk_cfg_ahb; - return clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]); + return 0; + +disable_clk_cfg_ahb: + clk_disable_unprepare(adpt->clk[EMAC_CLK_CFG_AHB]); +disable_clk_axi: + clk_disable_unprepare(adpt->clk[EMAC_CLK_AXI]); + + return ret; } /* Enable clocks; needs emac_clks_phase1_init to be called before */ diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 36598d0542ed..206d70f9d95b 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -979,7 +979,8 @@ static int ef100_process_design_param(struct efx_nic *efx, * EFX_MIN_DMAQ_SIZE is divisible by GRANULARITY. * This is very unlikely to fail. */ - if (EFX_MIN_DMAQ_SIZE % reader->value) { + if (!reader->value || reader->value > EFX_MIN_DMAQ_SIZE || + EFX_MIN_DMAQ_SIZE % (u32)reader->value) { netif_err(efx, probe, efx->net_dev, "%s size granularity is %llu, can't guarantee safety\n", reader->type == ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY ? "RXQ" : "TXQ", diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 02102c781a8c..bf3250e0e59c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -351,6 +351,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) plat_dat->has_gmac = true; plat_dat->bsp_priv = gmac; plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed; + plat_dat->multicast_filter_bins = 0; err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (err) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index efc6ec1b8027..fc8759f146c7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -164,6 +164,9 @@ static void dwmac1000_set_filter(struct mac_device_info *hw, value = GMAC_FRAME_FILTER_PR | GMAC_FRAME_FILTER_PCF; } else if (dev->flags & IFF_ALLMULTI) { value = GMAC_FRAME_FILTER_PM; /* pass all multi */ + } else if (!netdev_mc_empty(dev) && (mcbitslog2 == 0)) { + /* Fall back to all multicast if we've no filter */ + value = GMAC_FRAME_FILTER_PM; } else if (!netdev_mc_empty(dev)) { struct netdev_hw_addr *ha; diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index a7610eb55f30..1901ba277413 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -208,13 +208,6 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable) MV_V2_TEMP_CTRL_MASK, val); } -static void mv3310_hwmon_disable(void *data) -{ - struct phy_device *phydev = data; - - mv3310_hwmon_config(phydev, false); -} - static int mv3310_hwmon_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -238,10 +231,6 @@ static int mv3310_hwmon_probe(struct phy_device *phydev) if (ret) return ret; - ret = devm_add_action_or_reset(dev, mv3310_hwmon_disable, phydev); - if (ret) - return ret; - priv->hwmon_dev = devm_hwmon_device_register_with_info(dev, priv->hwmon_name, phydev, &mv3310_hwmon_chip_info, NULL); @@ -426,6 +415,11 @@ static int mv3310_probe(struct phy_device *phydev) return phy_sfp_probe(phydev, &mv3310_sfp_ops); } +static void mv3310_remove(struct phy_device *phydev) +{ + mv3310_hwmon_config(phydev, false); +} + static int mv3310_suspend(struct phy_device *phydev) { return mv3310_power_down(phydev); @@ -784,6 +778,7 @@ static struct phy_driver mv3310_drivers[] = { .read_status = mv3310_read_status, .get_tunable = mv3310_get_tunable, .set_tunable = mv3310_set_tunable, + .remove = mv3310_remove, }, { .phy_id = MARVELL_PHY_ID_88E2110, @@ -798,6 +793,7 @@ static struct phy_driver mv3310_drivers[] = { .read_status = mv3310_read_status, .get_tunable = mv3310_get_tunable, .set_tunable = mv3310_set_tunable, + .remove = mv3310_remove, }, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1b9523595839..57d44648c8dd 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -615,7 +615,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, if (c45_ids) dev->c45_ids = *c45_ids; dev->irq = bus->irq[addr]; + dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr); + device_initialize(&mdiodev->dev); dev->state = PHY_DOWN; @@ -649,10 +651,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, ret = phy_request_driver_module(dev, phy_id); } - if (!ret) { - device_initialize(&mdiodev->dev); - } else { - kfree(dev); + if (ret) { + put_device(&mdiodev->dev); dev = ERR_PTR(ret); } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7d39f998535d..2b02fefd094d 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1504,7 +1504,7 @@ static int determine_ethernet_addr(struct r8152 *tp, struct sockaddr *sa) sa->sa_family = dev->type; - ret = eth_platform_get_mac_address(&dev->dev, sa->sa_data); + ret = eth_platform_get_mac_address(&tp->udev->dev, sa->sa_data); if (ret < 0) { if (tp->version == RTL_VER_01) { ret = pla_ocp_read(tp, PLA_IDR, 8, sa->sa_data); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index ca395f9679d0..2818015324b8 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -886,7 +886,8 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, switch (protocol) { case IPPROTO_TCP: - ctx->l4_hdr_size = tcp_hdrlen(skb); + ctx->l4_hdr_size = skb->encapsulation ? inner_tcp_hdrlen(skb) : + tcp_hdrlen(skb); break; case IPPROTO_UDP: ctx->l4_hdr_size = sizeof(struct udphdr); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index b2868433718f..1ea15f2123ed 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -157,6 +157,12 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, if (!netif_running(dev)) goto drop; + /* There should be a pseudo header of 1 byte added by upper layers. + * Check to make sure it is there before reading it. + */ + if (skb->len < 1) + goto drop; + switch (skb->data[0]) { case X25_IFACE_DATA: break; @@ -305,6 +311,7 @@ static void lapbeth_setup(struct net_device *dev) dev->netdev_ops = &lapbeth_netdev_ops; dev->needs_free_netdev = true; dev->type = ARPHRD_X25; + dev->hard_header_len = 0; dev->mtu = 1000; dev->addr_len = 0; } @@ -331,7 +338,8 @@ static int lapbeth_new_device(struct net_device *dev) * then this driver prepends a length field of 2 bytes, * then the underlying Ethernet device prepends its own header. */ - ndev->hard_header_len = -1 + 3 + 2 + dev->hard_header_len; + ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + + dev->needed_headroom; lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 84640a0c13f3..de7984463595 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -307,6 +307,14 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } + /* There should be a pseudo header of 1 byte added by upper layers. + * Check to make sure it is there before reading it. + */ + if (skb->len < 1) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + switch (skb->data[0]) { case X25_IFACE_DATA: break; @@ -752,6 +760,12 @@ static void x25_asy_setup(struct net_device *dev) dev->type = ARPHRD_X25; dev->tx_queue_len = 10; + /* When transmitting data: + * first this driver removes a pseudo header of 1 byte, + * then the lapb module prepends an LAPB header of at most 3 bytes. + */ + dev->needed_headroom = 3 - 1; + /* New-style flags. */ dev->flags = IFF_NOARP; } diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 48ea093ff04c..4e035aca6f7e 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -77,7 +77,7 @@ */ #define FIELD_FIT(_mask, _val) \ ({ \ - __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: "); \ + __BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: "); \ !((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \ }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cef4ef0d2b4e..55f694b63164 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1214,15 +1214,17 @@ struct bpf_iter_aux_info { struct bpf_map *map; }; -typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog, - struct bpf_iter_aux_info *aux); +typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux); +typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; - bpf_iter_check_target_t check_target; + bpf_iter_attach_target_t attach_target; + bpf_iter_detach_target_t detach_target; u32 ctx_arg_info_size; - enum bpf_iter_link_info req_linfo; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 96840def9d69..ea193414298b 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -8,26 +8,9 @@ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H -#include <linux/compiler.h> #include <linux/slab.h> #include <linux/uaccess.h> -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE -typedef union { - void *kernel; - void __user *user; -} sockptr_t; - -static inline bool sockptr_is_kernel(sockptr_t sockptr) -{ - return (unsigned long)sockptr.kernel >= TASK_SIZE; -} - -static inline sockptr_t KERNEL_SOCKPTR(void *p) -{ - return (sockptr_t) { .kernel = p }; -} -#else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { void *kernel; @@ -45,15 +28,10 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } -#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p, - size_t size) +static inline sockptr_t USER_SOCKPTR(void __user *p) { - if (!access_ok(p, size)) - return -EFAULT; - *sp = (sockptr_t) { .user = p }; - return 0; + return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 1e209ce7d1bd..aa8893c68c50 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -304,6 +304,10 @@ void inet_csk_listen_stop(struct sock *sk); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); +/* update the fast reuse flag when adding a socket */ +void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, + struct sock *sk); + struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); #define TCP_PINGPONG_THRESH 3 diff --git a/include/net/tcp.h b/include/net/tcp.h index dbf5c791a6eb..eab6c7510b5b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1672,6 +1672,8 @@ void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); +int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, + u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, diff --git a/include/trace/events/random.h b/include/trace/events/random.h index 32c10a515e2d..9570a10cb949 100644 --- a/include/trace/events/random.h +++ b/include/trace/events/random.h @@ -307,6 +307,23 @@ TRACE_EVENT(urandom_read, __entry->pool_left, __entry->input_left) ); +TRACE_EVENT(prandom_u32, + + TP_PROTO(unsigned int ret), + + TP_ARGS(ret), + + TP_STRUCT__entry( + __field( unsigned int, ret) + ), + + TP_fast_assign( + __entry->ret = ret; + ), + + TP_printk("ret=%u" , __entry->ret) +); + #endif /* _TRACE_RANDOM_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b134e679e9db..0480f893facd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -81,6 +81,12 @@ struct bpf_cgroup_storage_key { __u32 attach_type; /* program attach type */ }; +union bpf_iter_link_info { + struct { + __u32 map_fd; + } map; +}; + /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { BPF_MAP_CREATE, @@ -249,13 +255,6 @@ enum bpf_link_type { MAX_BPF_LINK_TYPE, }; -enum bpf_iter_link_info { - BPF_ITER_LINK_UNSPEC = 0, - BPF_ITER_LINK_MAP_FD = 1, - - MAX_BPF_ITER_LINK_INFO, -}; - /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -623,6 +622,8 @@ union bpf_attr { }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ + __aligned_u64 iter_info; /* extra bpf_iter_link_info */ + __u32 iter_info_len; /* iter_info length */ } link_create; struct { /* struct used by BPF_LINK_UPDATE command */ diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 363b9cafc2d8..b6715964b685 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -338,8 +338,8 @@ static void bpf_iter_link_release(struct bpf_link *link) struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); - if (iter_link->aux.map) - bpf_map_put_with_uref(iter_link->aux.map); + if (iter_link->tinfo->reg_info->detach_target) + iter_link->tinfo->reg_info->detach_target(&iter_link->aux); } static void bpf_iter_link_dealloc(struct bpf_link *link) @@ -390,15 +390,35 @@ bool bpf_link_is_iter(struct bpf_link *link) int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + union bpf_iter_link_info __user *ulinfo; struct bpf_link_primer link_primer; struct bpf_iter_target_info *tinfo; - struct bpf_iter_aux_info aux = {}; + union bpf_iter_link_info linfo; struct bpf_iter_link *link; - u32 prog_btf_id, target_fd; + u32 prog_btf_id, linfo_len; bool existed = false; - struct bpf_map *map; int err; + if (attr->link_create.target_fd || attr->link_create.flags) + return -EINVAL; + + memset(&linfo, 0, sizeof(union bpf_iter_link_info)); + + ulinfo = u64_to_user_ptr(attr->link_create.iter_info); + linfo_len = attr->link_create.iter_info_len; + if (!ulinfo ^ !linfo_len) + return -EINVAL; + + if (ulinfo) { + err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo), + linfo_len); + if (err) + return err; + linfo_len = min_t(u32, linfo_len, sizeof(linfo)); + if (copy_from_user(&linfo, ulinfo, linfo_len)) + return -EFAULT; + } + prog_btf_id = prog->aux->attach_btf_id; mutex_lock(&targets_mutex); list_for_each_entry(tinfo, &targets, list) { @@ -411,13 +431,6 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) if (!existed) return -ENOENT; - /* Make sure user supplied flags are target expected. */ - target_fd = attr->link_create.target_fd; - if (attr->link_create.flags != tinfo->reg_info->req_linfo) - return -EINVAL; - if (!attr->link_create.flags && target_fd) - return -EINVAL; - link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); if (!link) return -ENOMEM; @@ -431,28 +444,15 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) return err; } - if (tinfo->reg_info->req_linfo == BPF_ITER_LINK_MAP_FD) { - map = bpf_map_get_with_uref(target_fd); - if (IS_ERR(map)) { - err = PTR_ERR(map); - goto cleanup_link; - } - - aux.map = map; - err = tinfo->reg_info->check_target(prog, &aux); + if (tinfo->reg_info->attach_target) { + err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux); if (err) { - bpf_map_put_with_uref(map); - goto cleanup_link; + bpf_link_cleanup(&link_primer); + return err; } - - link->aux.map = map; } return bpf_link_settle(&link_primer); - -cleanup_link: - bpf_link_cleanup(&link_primer); - return err; } static void init_seq_meta(struct bpf_iter_priv_data *priv_data, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index bde93344164d..ed0b3578867c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1966,7 +1966,7 @@ void bpf_prog_array_delete_safe(struct bpf_prog_array *array, * @index: the index of the program to replace * * Skips over dummy programs, by not counting them, when calculating - * the the position of the program to replace. + * the position of the program to replace. * * Return: * * 0 - Success diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index fbe1f557cb88..af86048e5afd 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -98,12 +98,21 @@ static struct bpf_iter_reg bpf_map_reg_info = { .seq_info = &bpf_map_seq_info, }; -static int bpf_iter_check_map(struct bpf_prog *prog, - struct bpf_iter_aux_info *aux) +static int bpf_iter_attach_map(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) { u32 key_acc_size, value_acc_size, key_size, value_size; - struct bpf_map *map = aux->map; + struct bpf_map *map; bool is_percpu = false; + int err = -EINVAL; + + if (!linfo->map.map_fd) + return -EBADF; + + map = bpf_map_get_with_uref(linfo->map.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || @@ -112,7 +121,7 @@ static int bpf_iter_check_map(struct bpf_prog *prog, else if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) - return -EINVAL; + goto put_map; key_acc_size = prog->aux->max_rdonly_access; value_acc_size = prog->aux->max_rdwr_access; @@ -122,10 +131,22 @@ static int bpf_iter_check_map(struct bpf_prog *prog, else value_size = round_up(map->value_size, 8) * num_possible_cpus(); - if (key_acc_size > key_size || value_acc_size > value_size) - return -EACCES; + if (key_acc_size > key_size || value_acc_size > value_size) { + err = -EACCES; + goto put_map; + } + aux->map = map; return 0; + +put_map: + bpf_map_put_with_uref(map); + return err; +} + +static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) +{ + bpf_map_put_with_uref(aux->map); } DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta, @@ -133,8 +154,8 @@ DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta, static const struct bpf_iter_reg bpf_map_elem_reg_info = { .target = "bpf_map_elem", - .check_target = bpf_iter_check_map, - .req_linfo = BPF_ITER_LINK_MAP_FD, + .attach_target = bpf_iter_attach_map, + .detach_target = bpf_iter_detach_map, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map_elem, key), diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2f343ce15747..86299a292214 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3883,7 +3883,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog * return -EINVAL; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.flags +#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len static int link_create(union bpf_attr *attr) { enum bpf_prog_type ptype; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b6ccfce3bf4c..ef938f17b944 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8294,7 +8294,7 @@ static bool stacksafe(struct bpf_func_state *old, if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in - * this stack slot, but current has has STACK_MISC -> + * this stack slot, but current has STACK_MISC -> * this verifier states are not equivalent, * return false to continue verification of this path */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cb91ef902cc4..a8d4f253ed77 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -383,7 +383,7 @@ static DEFINE_RAW_SPINLOCK(trace_printk_lock); #define BPF_TRACE_PRINTK_SIZE 1024 -static inline __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...) +static __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...) { static char buf[BPF_TRACE_PRINTK_SIZE]; unsigned long flags; diff --git a/lib/random32.c b/lib/random32.c index 3d749abb9e80..932345323af0 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -39,6 +39,7 @@ #include <linux/random.h> #include <linux/sched.h> #include <asm/unaligned.h> +#include <trace/events/random.h> #ifdef CONFIG_RANDOM32_SELFTEST static void __init prandom_state_selftest(void); @@ -82,6 +83,7 @@ u32 prandom_u32(void) u32 res; res = prandom_u32_state(state); + trace_prandom_u32(res); put_cpu_var(net_rand_state); return res; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index d3377c90a291..b988f48153a4 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -1384,18 +1384,39 @@ static int bpf_iter_init_sk_storage_map(void *priv_data, return 0; } -static int bpf_iter_check_map(struct bpf_prog *prog, - struct bpf_iter_aux_info *aux) +static int bpf_iter_attach_map(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) { - struct bpf_map *map = aux->map; + struct bpf_map *map; + int err = -EINVAL; + + if (!linfo->map.map_fd) + return -EBADF; + + map = bpf_map_get_with_uref(linfo->map.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) - return -EINVAL; + goto put_map; - if (prog->aux->max_rdonly_access > map->value_size) - return -EACCES; + if (prog->aux->max_rdonly_access > map->value_size) { + err = -EACCES; + goto put_map; + } + aux->map = map; return 0; + +put_map: + bpf_map_put_with_uref(map); + return err; +} + +static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) +{ + bpf_map_put_with_uref(aux->map); } static const struct seq_operations bpf_sk_storage_map_seq_ops = { @@ -1414,8 +1435,8 @@ static const struct bpf_iter_seq_info iter_seq_info = { static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", - .check_target = bpf_iter_check_map, - .req_linfo = BPF_ITER_LINK_MAP_FD, + .attach_target = bpf_iter_attach_map, + .detach_target = bpf_iter_detach_map, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 9de33b594ff2..efec66fa78b7 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -757,11 +757,13 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, return err; } - hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; - cpumask_and(mask, mask, housekeeping_cpumask(hk_flags)); - if (cpumask_empty(mask)) { - free_cpumask_var(mask); - return -EINVAL; + if (!cpumask_empty(mask)) { + hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; + cpumask_and(mask, mask, housekeeping_cpumask(hk_flags)); + if (cpumask_empty(mask)) { + free_cpumask_var(mask); + return -EINVAL; + } } map = kzalloc(max_t(unsigned int, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2828f6d5ba89..7e2e502ef519 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4853,7 +4853,7 @@ static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) if (err < 0) goto out; - if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + if (ip_is_fragment(ip_hdr(skb))) fragment = true; off = ip_hdrlen(skb); diff --git a/net/core/sock.c b/net/core/sock.c index a2044b4b606b..e4f40b175acb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3414,6 +3414,16 @@ static void sock_inuse_add(struct net *net, int val) } #endif +static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) +{ + if (!twsk_prot) + return; + kfree(twsk_prot->twsk_slab_name); + twsk_prot->twsk_slab_name = NULL; + kmem_cache_destroy(twsk_prot->twsk_slab); + twsk_prot->twsk_slab = NULL; +} + static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) @@ -3484,7 +3494,7 @@ int proto_register(struct proto *prot, int alloc_slab) prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) - goto out_free_timewait_sock_slab_name; + goto out_free_timewait_sock_slab; } } @@ -3492,15 +3502,15 @@ int proto_register(struct proto *prot, int alloc_slab) ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); - goto out_free_timewait_sock_slab_name; + goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; -out_free_timewait_sock_slab_name: +out_free_timewait_sock_slab: if (alloc_slab && prot->twsk_prot) - kfree(prot->twsk_prot->twsk_slab_name); + tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); @@ -3524,12 +3534,7 @@ void proto_unregister(struct proto *prot) prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); - - if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) { - kmem_cache_destroy(prot->twsk_prot->twsk_slab); - kfree(prot->twsk_prot->twsk_slab_name); - prot->twsk_prot->twsk_slab = NULL; - } + tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c index 545b2640f019..1b34cb9a7708 100644 --- a/net/ipv4/bpfilter/sockopt.c +++ b/net/ipv4/bpfilter/sockopt.c @@ -57,18 +57,16 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval, return bpfilter_mbox_request(sk, optname, optval, optlen, true); } -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, - char __user *user_optval, int __user *optlen) +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen) { - sockptr_t optval; - int err, len; + int len; if (get_user(len, optlen)) return -EFAULT; - err = init_user_sockptr(&optval, user_optval, len); - if (err) - return err; - return bpfilter_mbox_request(sk, optname, optval, len, false); + + return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len, + false); } static int __init bpfilter_sockopt_init(void) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d1a3913eebe0..b457dd2d6c75 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -296,6 +296,57 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, ipv6_only_sock(sk), true, false); } +void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, + struct sock *sk) +{ + kuid_t uid = sock_i_uid(sk); + bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; + + if (hlist_empty(&tb->owners)) { + tb->fastreuse = reuse; + if (sk->sk_reuseport) { + tb->fastreuseport = FASTREUSEPORT_ANY; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } else { + tb->fastreuseport = 0; + } + } else { + if (!reuse) + tb->fastreuse = 0; + if (sk->sk_reuseport) { + /* We didn't match or we don't have fastreuseport set on + * the tb, but we have sk_reuseport set on this socket + * and we know that there are no bind conflicts with + * this socket in this tb, so reset our tb's reuseport + * settings so that any subsequent sockets that match + * our current socket will be put on the fast path. + * + * If we reset we need to set FASTREUSEPORT_STRICT so we + * do extra checking for all subsequent sk_reuseport + * socks. + */ + if (!sk_reuseport_match(tb, sk)) { + tb->fastreuseport = FASTREUSEPORT_STRICT; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } + } else { + tb->fastreuseport = 0; + } + } +} + /* Obtain a reference to a local port for the given sock, * if snum is zero it means select any available local port. * We try to allocate an odd port (and leave even ports for connect()) @@ -308,7 +359,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); struct inet_bind_bucket *tb = NULL; - kuid_t uid = sock_i_uid(sk); int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); @@ -345,49 +395,8 @@ tb_found: goto fail_unlock; } success: - if (hlist_empty(&tb->owners)) { - tb->fastreuse = reuse; - if (sk->sk_reuseport) { - tb->fastreuseport = FASTREUSEPORT_ANY; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } else { - tb->fastreuseport = 0; - } - } else { - if (!reuse) - tb->fastreuse = 0; - if (sk->sk_reuseport) { - /* We didn't match or we don't have fastreuseport set on - * the tb, but we have sk_reuseport set on this socket - * and we know that there are no bind conflicts with - * this socket in this tb, so reset our tb's reuseport - * settings so that any subsequent sockets that match - * our current socket will be put on the fast path. - * - * If we reset we need to set FASTREUSEPORT_STRICT so we - * do extra checking for all subsequent sk_reuseport - * socks. - */ - if (!sk_reuseport_match(tb, sk)) { - tb->fastreuseport = FASTREUSEPORT_STRICT; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } - } else { - tb->fastreuseport = 0; - } - } + inet_csk_update_fastreuse(tb, sk); + if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 4eb4cd8d20dd..239e54474b65 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) return -ENOMEM; } } + inet_csk_update_fastreuse(tb, child); } inet_bind_hash(child, tb, port); spin_unlock(&head->lock); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5653e3b011bf..54023a46db04 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -301,24 +301,16 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2 * TCP_FASTOPEN_KEY_MAX) + (TCP_FASTOPEN_KEY_MAX * 5)) }; - struct tcp_fastopen_context *ctx; - u32 user_key[TCP_FASTOPEN_KEY_MAX * 4]; - __le32 key[TCP_FASTOPEN_KEY_MAX * 4]; + u32 user_key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u32)]; + __le32 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(__le32)]; char *backup_data; - int ret, i = 0, off = 0, n_keys = 0; + int ret, i = 0, off = 0, n_keys; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) return -ENOMEM; - rcu_read_lock(); - ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); - if (ctx) { - n_keys = tcp_fastopen_context_len(ctx); - memcpy(&key[0], &ctx->key[0], TCP_FASTOPEN_KEY_LENGTH * n_keys); - } - rcu_read_unlock(); - + n_keys = tcp_fastopen_get_cipher(net, NULL, (u64 *)key); if (!n_keys) { memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH); n_keys = 1; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c06d2bfd2ec4..31f3b858db81 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3685,22 +3685,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return 0; case TCP_FASTOPEN_KEY: { - __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; - struct tcp_fastopen_context *ctx; - unsigned int key_len = 0; + u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; + unsigned int key_len; if (get_user(len, optlen)) return -EFAULT; - rcu_read_lock(); - ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); - if (ctx) { - key_len = tcp_fastopen_context_len(ctx) * - TCP_FASTOPEN_KEY_LENGTH; - memcpy(&key[0], &ctx->key[0], key_len); - } - rcu_read_unlock(); - + key_len = tcp_fastopen_get_cipher(net, icsk, key) * + TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (put_user(len, optlen)) return -EFAULT; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index c1a54f3d58f5..09b62de04eea 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -108,6 +108,29 @@ out: return err; } +int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, + u64 *key) +{ + struct tcp_fastopen_context *ctx; + int n_keys = 0, i; + + rcu_read_lock(); + if (icsk) + ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); + else + ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + if (ctx) { + n_keys = tcp_fastopen_context_len(ctx); + for (i = 0; i < n_keys; i++) { + put_unaligned_le64(ctx->key[i].key[0], key + (i * 2)); + put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1); + } + } + rcu_read_unlock(); + + return n_keys; +} + static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req, struct sk_buff *syn, const siphash_key_t *key, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 96f4f2fe50ad..e8cac2655c82 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -423,12 +423,12 @@ static void mptcp_sock_destruct(struct sock *sk) * also remove the mptcp socket, via * sock_put(ctx->conn). * - * Problem is that the mptcp socket will not be in - * SYN_RECV state and doesn't have SOCK_DEAD flag. + * Problem is that the mptcp socket will be in + * ESTABLISHED state and will not have the SOCK_DEAD flag. * Both result in warnings from inet_sock_destruct. */ - if (sk->sk_state == TCP_SYN_RECV) { + if (sk->sk_state == TCP_ESTABLISHED) { sk->sk_state = TCP_CLOSE; WARN_ON_ONCE(sk->sk_socket); sock_orphan(sk); diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index b2061b6746ea..955c195ae14b 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -328,10 +328,13 @@ static int rawsock_create(struct net *net, struct socket *sock, if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW)) return -ESOCKTNOSUPPORT; - if (sock->type == SOCK_RAW) + if (sock->type == SOCK_RAW) { + if (!capable(CAP_NET_RAW)) + return -EPERM; sock->ops = &rawsock_raw_ops; - else + } else { sock->ops = &rawsock_ops; + } sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern); if (!sk) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 42f8cc70bb2c..6e47ef7ef036 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1756,6 +1756,7 @@ err: /* Called with ovs_mutex. */ static void __dp_destroy(struct datapath *dp) { + struct flow_table *table = &dp->table; int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { @@ -1774,7 +1775,14 @@ static void __dp_destroy(struct datapath *dp) */ ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); - /* RCU destroy the flow table */ + /* Flush sw_flow in the tables. RCU cb only releases resource + * such as dp, ports and tables. That may avoid some issues + * such as RCU usage warning. + */ + table_instance_flow_flush(table, ovsl_dereference(table->ti), + ovsl_dereference(table->ufid_ti)); + + /* RCU destroy the ports, meters and flow tables. */ call_rcu(&dp->rcu, destroy_dp_rcu); } diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 8c12675cbb67..e2235849a57e 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -473,19 +473,15 @@ static void table_instance_flow_free(struct flow_table *table, flow_mask_remove(table, flow->mask); } -static void table_instance_destroy(struct flow_table *table, - struct table_instance *ti, - struct table_instance *ufid_ti, - bool deferred) +/* Must be called with OVS mutex held. */ +void table_instance_flow_flush(struct flow_table *table, + struct table_instance *ti, + struct table_instance *ufid_ti) { int i; - if (!ti) - return; - - BUG_ON(!ufid_ti); if (ti->keep_flows) - goto skip_flows; + return; for (i = 0; i < ti->n_buckets; i++) { struct sw_flow *flow; @@ -497,18 +493,16 @@ static void table_instance_destroy(struct flow_table *table, table_instance_flow_free(table, ti, ufid_ti, flow, false); - ovs_flow_free(flow, deferred); + ovs_flow_free(flow, true); } } +} -skip_flows: - if (deferred) { - call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); - call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb); - } else { - __table_instance_destroy(ti); - __table_instance_destroy(ufid_ti); - } +static void table_instance_destroy(struct table_instance *ti, + struct table_instance *ufid_ti) +{ + call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); + call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb); } /* No need for locking this function is called from RCU callback or @@ -523,7 +517,7 @@ void ovs_flow_tbl_destroy(struct flow_table *table) call_rcu(&mc->rcu, mask_cache_rcu_cb); call_rcu(&ma->rcu, mask_array_rcu_cb); - table_instance_destroy(table, ti, ufid_ti, false); + table_instance_destroy(ti, ufid_ti); } struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti, @@ -641,7 +635,8 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table) flow_table->count = 0; flow_table->ufid_count = 0; - table_instance_destroy(flow_table, old_ti, old_ufid_ti, true); + table_instance_flow_flush(flow_table, old_ti, old_ufid_ti); + table_instance_destroy(old_ti, old_ufid_ti); return 0; err_free_ti: diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 74ce48fecba9..6e7d4ac59353 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -105,5 +105,8 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, bool full, const struct sw_flow_mask *mask); void ovs_flow_masks_rebalance(struct flow_table *table); +void table_instance_flow_flush(struct flow_table *table, + struct table_instance *ti, + struct table_instance *ufid_ti); #endif /* flow_table.h */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0b8160d1a6e0..479c257ded73 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -941,6 +941,7 @@ static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) + __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); @@ -989,6 +990,7 @@ static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) + __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; @@ -2286,8 +2288,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (do_vnet && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) + vio_le(), true, 0)) { + if (po->tp_version == TPACKET_V3) + prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; + } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); @@ -2393,7 +2398,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); - } else { + } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } diff --git a/net/socket.c b/net/socket.c index aff52e81653c..dbbe8ea7d395 100644 --- a/net/socket.c +++ b/net/socket.c @@ -500,7 +500,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) if (f.file) { sock = sock_from_file(f.file, err); if (likely(sock)) { - *fput_needed = f.flags; + *fput_needed = f.flags & FDPUT_FPUT; return sock; } fdput(f); @@ -1325,7 +1325,7 @@ int sock_wake_async(struct socket_wq *wq, int how, int band) case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; - /* fall through */ + fallthrough; case SOCK_WAKE_IO: call_kill: kill_fasync(&wq->fasync_list, SIGIO, band); @@ -1804,8 +1804,7 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, upeer_addrlen, flags, rlimit(RLIMIT_NOFILE)); - if (f.flags) - fput(f.file); + fdput(f); } return ret; @@ -1868,8 +1867,7 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (!ret) ret = __sys_connect_file(f.file, &address, addrlen, 0); - if (f.flags) - fput(f.file); + fdput(f); } return ret; @@ -2097,7 +2095,7 @@ static bool sock_use_custom_sol_socket(const struct socket *sock) int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, int optlen) { - sockptr_t optval; + sockptr_t optval = USER_SOCKPTR(user_optval); char *kernel_optval = NULL; int err, fput_needed; struct socket *sock; @@ -2105,10 +2103,6 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, if (optlen < 0) return -EINVAL; - err = init_user_sockptr(&optval, user_optval, optlen); - if (err) - return err; - sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; @@ -3065,7 +3059,7 @@ static int __init sock_init(void) err = register_filesystem(&sock_fs_type); if (err) - goto out_fs; + goto out; sock_mnt = kern_mount(&sock_fs_type); if (IS_ERR(sock_mnt)) { err = PTR_ERR(sock_mnt); @@ -3088,7 +3082,6 @@ out: out_mount: unregister_filesystem(&sock_fs_type); -out_fs: goto out; } @@ -3161,13 +3154,13 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) return -ENOMEM; buf_size += rule_cnt * sizeof(u32); - /* fall through */ + fallthrough; case ETHTOOL_GRXRINGS: case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_SRXCLSRLINS: convert_out = true; - /* fall through */ + fallthrough; case ETHTOOL_SRXCLSRLDEL: buf_size += sizeof(struct ethtool_rxnfc); convert_in = true; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 18fa6067bb7f..b74e2741f74f 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -561,7 +561,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; - char *kaddr = kmap(page); + char *kaddr; struct kvec iov; int rc; @@ -576,6 +576,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, goto out; } + kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 710bd44eaa49..9a3d9fedd7aa 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -935,7 +935,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int ret = 0; int pending; - if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) + if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_CMSG_COMPAT)) return -EOPNOTSUPP; mutex_lock(&tls_ctx->tx_lock); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 27bbcfad9c17..9e93bc201cc0 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1032,7 +1032,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, } /* Connected sockets that can produce data can be written. */ - if (sk->sk_state == TCP_ESTABLISHED) { + if (transport && sk->sk_state == TCP_ESTABLISHED) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { bool space_avail_now = false; int ret = transport->notify_poll_out( diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index c9dba7543dba..3b1aad7535dd 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -11,6 +11,7 @@ static int do_pin(int argc, char **argv) { DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, iter_opts); + union bpf_iter_link_info linfo; const char *objfile, *path; struct bpf_program *prog; struct bpf_object *obj; @@ -36,6 +37,11 @@ static int do_pin(int argc, char **argv) map_fd = map_parse_fd(&argc, &argv); if (map_fd < 0) return -1; + + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + iter_opts.link_info = &linfo; + iter_opts.link_info_len = sizeof(linfo); } } @@ -57,9 +63,6 @@ static int do_pin(int argc, char **argv) goto close_obj; } - if (map_fd >= 0) - iter_opts.map_fd = map_fd; - link = bpf_program__attach_iter(prog, &iter_opts); if (IS_ERR(link)) { err = PTR_ERR(link); diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 52d883325a23..4d9ecb975862 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -566,6 +566,7 @@ static int sets_patch(struct object *obj) next = rb_next(next); } + return 0; } static int symbols_patch(struct object *obj) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b134e679e9db..0480f893facd 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -81,6 +81,12 @@ struct bpf_cgroup_storage_key { __u32 attach_type; /* program attach type */ }; +union bpf_iter_link_info { + struct { + __u32 map_fd; + } map; +}; + /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { BPF_MAP_CREATE, @@ -249,13 +255,6 @@ enum bpf_link_type { MAX_BPF_LINK_TYPE, }; -enum bpf_iter_link_info { - BPF_ITER_LINK_UNSPEC = 0, - BPF_ITER_LINK_MAP_FD = 1, - - MAX_BPF_ITER_LINK_INFO, -}; - /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -623,6 +622,8 @@ union bpf_attr { }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ + __aligned_u64 iter_info; /* extra bpf_iter_link_info */ + __u32 iter_info_len; /* iter_info length */ } link_create; struct { /* struct used by BPF_LINK_UPDATE command */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index eab14c97c15d..0750681057c2 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -599,6 +599,9 @@ int bpf_link_create(int prog_fd, int target_fd, attr.link_create.target_fd = target_fd; attr.link_create.attach_type = attach_type; attr.link_create.flags = OPTS_GET(opts, flags, 0); + attr.link_create.iter_info = + ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0)); + attr.link_create.iter_info_len = OPTS_GET(opts, iter_info_len, 0); return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 28855fd5b5f4..015d13f25fcc 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -168,11 +168,14 @@ LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); +union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */ struct bpf_link_create_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 flags; + union bpf_iter_link_info *iter_info; + __u32 iter_info_len; }; -#define bpf_link_create_opts__last_field flags +#define bpf_link_create_opts__last_field iter_info_len LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 856b09a04563..4843e44916f7 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -564,8 +564,8 @@ done: struct btf *btf__parse_raw(const char *path) { + struct btf *btf = NULL; void *data = NULL; - struct btf *btf; FILE *f = NULL; __u16 magic; int err = 0; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7be04e45d29c..0a06124f7999 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -8306,10 +8306,8 @@ bpf_program__attach_iter(struct bpf_program *prog, if (!OPTS_VALID(opts, bpf_iter_attach_opts)) return ERR_PTR(-EINVAL); - if (OPTS_HAS(opts, map_fd)) { - target_fd = opts->map_fd; - link_create_opts.flags = BPF_ITER_LINK_MAP_FD; - } + link_create_opts.iter_info = OPTS_GET(opts, link_info, (void *)0); + link_create_opts.iter_info_len = OPTS_GET(opts, link_info_len, 0); prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 3ed1399bfbbc..5ecb4069a9f0 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -267,9 +267,10 @@ LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ - __u32 map_fd; + union bpf_iter_link_info *link_info; + __u32 link_info_len; }; -#define bpf_iter_attach_opts__last_field map_fd +#define bpf_iter_attach_opts__last_field link_info_len LIBBPF_API struct bpf_link * bpf_program__attach_iter(struct bpf_program *prog, diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e7a8cf83ba48..a83b5827532f 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -102,7 +102,7 @@ endif OVERRIDE_TARGETS := 1 override define CLEAN $(call msg,CLEAN) - $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) + $(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) endef include ../lib.mk @@ -123,17 +123,21 @@ $(notdir $(TEST_GEN_PROGS) \ $(TEST_GEN_PROGS_EXTENDED) \ $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ; +$(OUTPUT)/%.o: %.c + $(call msg,CC,,$@) + $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ + $(OUTPUT)/%:%.c $(call msg,BINARY,,$@) - $(LINK.c) $^ $(LDLIBS) -o $@ + $(Q)$(LINK.c) $^ $(LDLIBS) -o $@ $(OUTPUT)/urandom_read: urandom_read.c $(call msg,BINARY,,$@) - $(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id + $(Q)$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) $(call msg,CC,,$@) - $(CC) -c $(CFLAGS) -o $@ $< + $(Q)$(CC) -c $(CFLAGS) -o $@ $< VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ @@ -142,7 +146,9 @@ VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ /boot/vmlinux-$(shell uname -r) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) -$(OUTPUT)/runqslower: $(BPFOBJ) +DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool + +$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ @@ -164,7 +170,6 @@ $(OUTPUT)/test_netcnt: cgroup_helpers.c $(OUTPUT)/test_sock_fields: cgroup_helpers.c $(OUTPUT)/test_sysctl: cgroup_helpers.c -DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(BPFOBJ) | $(BUILD_DIR)/bpftool @@ -180,15 +185,15 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(BUILD_DIR)/resolve_btfids $(INCLUDE_DIR): $(call msg,MKDIR,,$@) - mkdir -p $@ + $(Q)mkdir -p $@ $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR) ifeq ($(VMLINUX_H),) $(call msg,GEN,,$@) - $(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ + $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ else $(call msg,CP,,$@) - cp "$(VMLINUX_H)" $@ + $(Q)cp "$(VMLINUX_H)" $@ endif $(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids \ @@ -237,28 +242,28 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h # $4 - LDFLAGS define CLANG_BPF_BUILD_RULE $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) - ($(CLANG) $3 -O2 -target bpf -emit-llvm \ + $(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -mattr=dwarfris -march=bpf -mcpu=v3 $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) - ($(CLANG) $3 -O2 -target bpf -emit-llvm \ + $(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC define CLANG_NATIVE_BPF_BUILD_RULE $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) - ($(CLANG) $3 -O2 -emit-llvm \ + $(Q)($(CLANG) $3 -O2 -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=v3 $4 -filetype=obj -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) - $(BPF_GCC) $3 $4 -O2 -c $1 -o $2 + $(Q)$(BPF_GCC) $3 $4 -O2 -c $1 -o $2 endef SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c @@ -300,7 +305,7 @@ ifeq ($($(TRUNNER_OUTPUT)-dir),) $(TRUNNER_OUTPUT)-dir := y $(TRUNNER_OUTPUT): $$(call msg,MKDIR,,$$@) - mkdir -p $$@ + $(Q)mkdir -p $$@ endif # ensure we set up BPF objects generation rule just once for a given @@ -320,7 +325,7 @@ $(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \ $(TRUNNER_OUTPUT)/%.o \ | $(BPFTOOL) $(TRUNNER_OUTPUT) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) - $$(BPFTOOL) gen skeleton $$< > $$@ + $(Q)$$(BPFTOOL) gen skeleton $$< > $$@ endif # ensure we set up tests.h header generation rule just once @@ -344,7 +349,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_BPF_SKELS) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) - cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) + $(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ %.c \ @@ -352,13 +357,13 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_TESTS_HDR) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@) - $$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ + $(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ # only copy extra resources if in flavored build $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT) ifneq ($2,) $$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES)) - cp -a $$^ $(TRUNNER_OUTPUT)/ + $(Q)cp -a $$^ $(TRUNNER_OUTPUT)/ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ @@ -366,8 +371,8 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(RESOLVE_BTFIDS) \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) - $$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ - $(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@ + $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ + $(Q)$(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@ endef @@ -420,17 +425,17 @@ verifier/tests.h: verifier/*.c ) > verifier/tests.h) $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) $(call msg,BINARY,,$@) - $(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) - $(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ + $(Q)$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ # Benchmark runner $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(call msg,CC,,$@) - $(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ + $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ @@ -443,7 +448,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ $(OUTPUT)/bench_trigger.o \ $(OUTPUT)/bench_ringbufs.o $(call msg,BINARY,,$@) - $(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS) + $(Q)$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS) EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 4ffefdc1130f..7375d9a6d242 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -468,6 +468,7 @@ static void test_bpf_hash_map(void) DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_hash_map *skel; int err, i, len, map_fd, iter_fd; + union bpf_iter_link_info linfo; __u64 val, expected_val = 0; struct bpf_link *link; struct key_t { @@ -490,13 +491,16 @@ static void test_bpf_hash_map(void) goto out; /* iterator with hashmap2 and hashmap3 should fail */ - opts.map_fd = bpf_map__fd(skel->maps.hashmap2); + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap2); + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); if (CHECK(!IS_ERR(link), "attach_iter", "attach_iter for hashmap2 unexpected succeeded\n")) goto out; - opts.map_fd = bpf_map__fd(skel->maps.hashmap3); + linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap3); link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); if (CHECK(!IS_ERR(link), "attach_iter", "attach_iter for hashmap3 unexpected succeeded\n")) @@ -519,7 +523,7 @@ static void test_bpf_hash_map(void) goto out; } - opts.map_fd = map_fd; + linfo.map.map_fd = map_fd; link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) goto out; @@ -562,6 +566,7 @@ static void test_bpf_percpu_hash_map(void) DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_percpu_hash_map *skel; int err, i, j, len, map_fd, iter_fd; + union bpf_iter_link_info linfo; __u32 expected_val = 0; struct bpf_link *link; struct key_t { @@ -606,7 +611,10 @@ static void test_bpf_percpu_hash_map(void) goto out; } - opts.map_fd = map_fd; + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts); if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) goto out; @@ -649,6 +657,7 @@ static void test_bpf_array_map(void) DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); __u32 expected_key = 0, res_first_key; struct bpf_iter_bpf_array_map *skel; + union bpf_iter_link_info linfo; int err, i, map_fd, iter_fd; struct bpf_link *link; char buf[64] = {}; @@ -673,7 +682,10 @@ static void test_bpf_array_map(void) goto out; } - opts.map_fd = map_fd; + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts); if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) goto out; @@ -730,6 +742,7 @@ static void test_bpf_percpu_array_map(void) DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_percpu_array_map *skel; __u32 expected_key = 0, expected_val = 0; + union bpf_iter_link_info linfo; int err, i, j, map_fd, iter_fd; struct bpf_link *link; char buf[64]; @@ -765,7 +778,10 @@ static void test_bpf_percpu_array_map(void) goto out; } - opts.map_fd = map_fd; + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts); if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) goto out; @@ -803,6 +819,7 @@ static void test_bpf_sk_storage_map(void) DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); int err, i, len, map_fd, iter_fd, num_sockets; struct bpf_iter_bpf_sk_storage_map *skel; + union bpf_iter_link_info linfo; int sock_fd[3] = {-1, -1, -1}; __u32 val, expected_val = 0; struct bpf_link *link; @@ -829,7 +846,10 @@ static void test_bpf_sk_storage_map(void) goto out; } - opts.map_fd = map_fd; + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts); if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) goto out; @@ -871,6 +891,7 @@ static void test_rdonly_buf_out_of_bound(void) { DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_test_kern5 *skel; + union bpf_iter_link_info linfo; struct bpf_link *link; skel = bpf_iter_test_kern5__open_and_load(); @@ -878,7 +899,10 @@ static void test_rdonly_buf_out_of_bound(void) "skeleton open_and_load failed\n")) return; - opts.map_fd = bpf_map__fd(skel->maps.hashmap1); + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap1); + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n")) bpf_link__destroy(link); diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 504abb7bfb95..7043e6ded0e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -48,21 +48,19 @@ static void test_send_signal_common(struct perf_event_attr *attr, close(pipe_p2c[1]); /* close write */ /* notify parent signal handler is installed */ - write(pipe_c2p[1], buf, 1); + CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno); /* make sure parent enabled bpf program to send_signal */ - read(pipe_p2c[0], buf, 1); + CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno); /* wait a little for signal handler */ sleep(1); - if (sigusr1_received) - write(pipe_c2p[1], "2", 1); - else - write(pipe_c2p[1], "0", 1); + buf[0] = sigusr1_received ? '2' : '0'; + CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno); /* wait for parent notification and exit */ - read(pipe_p2c[0], buf, 1); + CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno); close(pipe_c2p[1]); close(pipe_p2c[0]); @@ -99,7 +97,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, } /* wait until child signal handler installed */ - read(pipe_c2p[0], buf, 1); + CHECK(read(pipe_c2p[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno); /* trigger the bpf send_signal */ skel->bss->pid = pid; @@ -107,7 +105,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, skel->bss->signal_thread = signal_thread; /* notify child that bpf program can send_signal now */ - write(pipe_p2c[1], buf, 1); + CHECK(write(pipe_p2c[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno); /* wait for result */ err = read(pipe_c2p[0], buf, 1); @@ -121,7 +119,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, CHECK(buf[0] != '2', test_name, "incorrect result\n"); /* notify child safe to exit */ - write(pipe_p2c[1], buf, 1); + CHECK(write(pipe_p2c[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno); disable_pmu: close(pmu_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index f002e3090d92..11a769e18f5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -6,11 +6,13 @@ static __u64 read_perf_max_sample_freq(void) { __u64 sample_freq = 5000; /* fallback to 5000 on error */ FILE *f; + __u32 duration = 0; f = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r"); if (f == NULL) return sample_freq; - fscanf(f, "%llu", &sample_freq); + CHECK(fscanf(f, "%llu", &sample_freq) != 1, "Get max sample rate", + "return default value: 5000,err %d\n", -errno); fclose(f); return sample_freq; } diff --git a/tools/testing/selftests/bpf/settings b/tools/testing/selftests/bpf/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/bpf/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 8549b31716ab..73da7fe8c152 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -124,17 +124,24 @@ int main(int argc, char **argv) sprintf(test_script, "iptables -A INPUT -p tcp --dport %d -j DROP", TESTPORT); - system(test_script); + if (system(test_script)) { + printf("FAILED: execute command: %s, err %d\n", test_script, -errno); + goto err; + } sprintf(test_script, "nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ", TESTPORT); - system(test_script); + if (system(test_script)) + printf("execute command: %s, err %d\n", test_script, -errno); sprintf(test_script, "iptables -D INPUT -p tcp --dport %d -j DROP", TESTPORT); - system(test_script); + if (system(test_script)) { + printf("FAILED: execute command: %s, err %d\n", test_script, -errno); + goto err; + } rv = bpf_map_lookup_elem(bpf_map__fd(global_map), &key, &g); if (rv != 0) { diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 2499824d9e1c..8df5cb8f71ff 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,4 +1,6 @@ CONFIG_MPTCP=y CONFIG_MPTCP_IPV6=y +CONFIG_INET_DIAG=m +CONFIG_INET_MPTCP_DIAG=m CONFIG_VETH=y CONFIG_NET_SCH_NETEM=m diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index cad6f73a5fd0..090620c3e10c 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -406,10 +406,11 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd) /* ... but we still receive. * Close our write side, ev. give some time - * for address notification + * for address notification and/or checking + * the current status */ - if (cfg_join) - usleep(400000); + if (cfg_wait) + usleep(cfg_wait); shutdown(peerfd, SHUT_WR); } else { if (errno == EINTR) @@ -427,7 +428,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd) } /* leave some time for late join/announce */ - if (cfg_wait) + if (cfg_join) usleep(cfg_wait); close(peerfd); |