diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-07-02 11:18:28 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-07-02 11:18:28 -0700 |
| commit | 4e33d7d47943aaa84a5904472cf2f9c6d6b0a6ca (patch) | |
| tree | 6eb46696758bee8da0e8b830db4bc6915128bf60 | |
| parent | 021c91791a5e7e85c567452f1be3e4c2c6cb6063 (diff) | |
| parent | e48e097996439cd73f36c89b98ba4175d84c9be6 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Verify netlink attributes properly in nf_queue, from Eric Dumazet.
2) Need to bump memory lock rlimit for test_sockmap bpf test, from
Yonghong Song.
3) Fix VLAN handling in lan78xx driver, from Dave Stevenson.
4) Fix uninitialized read in nf_log, from Jann Horn.
5) Fix raw command length parsing in mlx5, from Alex Vesker.
6) Cleanup loopback RDS connections upon netns deletion, from Sowmini
Varadhan.
7) Fix regressions in FIB rule matching during create, from Jason A.
Donenfeld and Roopa Prabhu.
8) Fix mpls ether type detection in nfp, from Pieter Jansen van Vuuren.
9) More bpfilter build fixes/adjustments from Masahiro Yamada.
10) Fix XDP_{TX,REDIRECT} flushing in various drivers, from Jesper
Dangaard Brouer.
11) fib_tests.sh file permissions were broken, from Shuah Khan.
12) Make sure BH/preemption is disabled in data path of mac80211, from
Denis Kenzior.
13) Don't ignore nla_parse_nested() return values in nl80211, from
Johannes berg.
14) Properly account sock objects ot kmemcg, from Shakeel Butt.
15) Adjustments to setting bpf program permissions to read-only, from
Daniel Borkmann.
16) TCP Fast Open key endianness was broken, it always took on the host
endiannness. Whoops. Explicitly make it little endian. From Yuching
Cheng.
17) Fix prefix route setting for link local addresses in ipv6, from
David Ahern.
18) Potential Spectre v1 in zatm driver, from Gustavo A. R. Silva.
19) Various bpf sockmap fixes, from John Fastabend.
20) Use after free for GRO with ESP, from Sabrina Dubroca.
21) Passing bogus flags to crypto_alloc_shash() in ipv6 SR code, from
Eric Biggers.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
qede: Adverstise software timestamp caps when PHC is not available.
qed: Fix use of incorrect size in memcpy call.
qed: Fix setting of incorrect eswitch mode.
qed: Limit msix vectors in kdump kernel to the minimum required count.
ipvlan: call dev_change_flags when ipvlan mode is reset
ipv6: sr: fix passing wrong flags to crypto_alloc_shash()
net: fix use-after-free in GRO with ESP
tcp: prevent bogus FRTO undos with non-SACK flows
bpf: sockhash, add release routine
bpf: sockhash fix omitted bucket lock in sock_close
bpf: sockmap, fix smap_list_map_remove when psock is in many maps
bpf: sockmap, fix crash when ipv6 sock is added
net: fib_rules: bring back rule_exists to match rule during add
hv_netvsc: split sub-channel setup into async and sync
net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN
atm: zatm: Fix potential Spectre v1
s390/qeth: consistently re-enable device features
s390/qeth: don't clobber buffer on async TX completion
s390/qeth: avoid using is_multicast_ether_addr_64bits on (u8 *)[6]
s390/qeth: fix race when setting MAC address
...
114 files changed, 1249 insertions, 624 deletions
@@ -507,11 +507,6 @@ ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLA KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO endif -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y) - CC_CAN_LINK := y - export CC_CAN_LINK -endif - # The expansion should be delayed until arch/$(SRCARCH)/Makefile is included. # Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile. # CC_VERSION_TEXT is referenced from Kconfig (so it needs export), diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 6e8b71613039..f6a62ae44a65 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1844,7 +1844,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - set_memory_ro((unsigned long)header, header->pages); + bpf_jit_binary_lock_ro(header); prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index d2db8acb1a55..5f0234ec8038 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1286,6 +1286,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) goto free_addrs; } if (bpf_jit_prog(&jit, fp)) { + bpf_jit_binary_free(header); fp = orig_fp; goto free_addrs; } diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index ff81a576347e..82532c299bb5 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -1618,7 +1618,7 @@ static int rx_init(struct atm_dev *dev) skb_queue_head_init(&iadev->rx_dma_q); iadev->rx_free_desc_qhead = NULL; - iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL); + iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL); if (!iadev->rx_open) { printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n", dev->number); diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index a8d2eb0ceb8d..2c288d1f42bb 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) return -EFAULT; if (pool < 0 || pool > ZATM_LAST_POOL) return -EINVAL; + pool = array_index_nospec(pool, + ZATM_LAST_POOL + 1); if (copy_from_user(&info, &((struct zatm_pool_req __user *) arg)->info, sizeof(info))) return -EFAULT; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index e3e330f59c2c..b3ba9a222550 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -6113,7 +6113,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), MLX5_CAP_GEN(mdev, num_vhca_ports)); - if (MLX5_VPORT_MANAGER(mdev) && + if (MLX5_ESWITCH_MANAGER(mdev) && mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0); diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 40826bba06b6..fcfab6635f9c 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -207,29 +207,19 @@ void lirc_bpf_free(struct rc_dev *rcdev) bpf_prog_array_free(rcdev->raw->progs); } -int lirc_prog_attach(const union bpf_attr *attr) +int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { - struct bpf_prog *prog; struct rc_dev *rcdev; int ret; if (attr->attach_flags) return -EINVAL; - prog = bpf_prog_get_type(attr->attach_bpf_fd, - BPF_PROG_TYPE_LIRC_MODE2); - if (IS_ERR(prog)) - return PTR_ERR(prog); - rcdev = rc_dev_get_from_fd(attr->target_fd); - if (IS_ERR(rcdev)) { - bpf_prog_put(prog); + if (IS_ERR(rcdev)) return PTR_ERR(rcdev); - } ret = lirc_bpf_attach(rcdev, prog); - if (ret) - bpf_prog_put(prog); put_device(&rcdev->dev); diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 567ee54504bc..5e5022fa1d04 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct alx_priv *alx = pci_get_drvdata(pdev); struct alx_hw *hw = &alx->hw; + int err; alx_reset_phy(hw); if (!netif_running(alx->dev)) return 0; netif_device_attach(alx->dev); - return __alx_open(alx, true); + + rtnl_lock(); + err = __alx_open(alx, true); + rtnl_unlock(); + + return err; } static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index d847e1b9c37b..be1506169076 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1533,6 +1533,7 @@ struct bnx2x { struct link_vars link_vars; u32 link_cnt; struct bnx2x_link_report_data last_reported_link; + bool force_link_down; struct mdio_if_info mdio; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 8cd73ff5debc..af7b5a4d8ba0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1261,6 +1261,11 @@ void __bnx2x_link_report(struct bnx2x *bp) { struct bnx2x_link_report_data cur_data; + if (bp->force_link_down) { + bp->link_vars.link_up = 0; + return; + } + /* reread mf_cfg */ if (IS_PF(bp) && !CHIP_IS_E1(bp)) bnx2x_read_mf_cfg(bp); @@ -2817,6 +2822,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) bp->pending_max = 0; } + bp->force_link_down = false; if (bp->port.pmf) { rc = bnx2x_initial_phy_init(bp, load_mode); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 5b1ed240bf18..57348f2b49a3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -10279,6 +10279,12 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work) bp->sp_rtnl_state = 0; smp_mb(); + /* Immediately indicate link as down */ + bp->link_vars.link_up = 0; + bp->force_link_down = true; + netif_carrier_off(bp->dev); + BNX2X_ERR("Indicating link is down due to Tx-timeout\n"); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, true); /* When ret value shows failure of allocation failure, * the nic is rebooted again. If open still fails, a error diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 30273a7717e2..4fd829b5e65d 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -660,7 +660,7 @@ static int cnic_init_id_tbl(struct cnic_id_tbl *id_tbl, u32 size, u32 start_id, id_tbl->max = size; id_tbl->next = next; spin_lock_init(&id_tbl->lock); - id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL); + id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL); if (!id_tbl->table) return -ENOMEM; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 3e93df5d4e3b..96cc03a6d942 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3726,6 +3726,8 @@ static int at91ether_init(struct platform_device *pdev) int err; u32 reg; + bp->queues[0].bp = bp; + dev->netdev_ops = &at91ether_netdev_ops; dev->ethtool_ops = &macb_ethtool_ops; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 5f4e1ffa7b95..ab02057ac730 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -125,6 +125,9 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); /* Default alignment for start of data in an Rx FD */ #define DPAA_FD_DATA_ALIGNMENT 16 +/* The DPAA requires 256 bytes reserved and mapped for the SGT */ +#define DPAA_SGT_SIZE 256 + /* Values for the L3R field of the FM Parse Results */ /* L3 Type field: First IP Present IPv4 */ @@ -1617,8 +1620,8 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) { nr_frags = skb_shinfo(skb)->nr_frags; - dma_unmap_single(dev, addr, qm_fd_get_offset(fd) + - sizeof(struct qm_sg_entry) * (1 + nr_frags), + dma_unmap_single(dev, addr, + qm_fd_get_offset(fd) + DPAA_SGT_SIZE, dma_dir); /* The sgt buffer has been allocated with netdev_alloc_frag(), @@ -1903,8 +1906,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, void *sgt_buf; /* get a page frag to store the SGTable */ - sz = SKB_DATA_ALIGN(priv->tx_headroom + - sizeof(struct qm_sg_entry) * (1 + nr_frags)); + sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE); sgt_buf = netdev_alloc_frag(sz); if (unlikely(!sgt_buf)) { netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n", @@ -1972,9 +1974,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, skbh = (struct sk_buff **)buffer_start; *skbh = skb; - addr = dma_map_single(dev, buffer_start, priv->tx_headroom + - sizeof(struct qm_sg_entry) * (1 + nr_frags), - dma_dir); + addr = dma_map_single(dev, buffer_start, + priv->tx_headroom + DPAA_SGT_SIZE, dma_dir); if (unlikely(dma_mapping_error(dev, addr))) { dev_err(dev, "DMA mapping failed"); err = -EINVAL; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index ce6e24c74978..ecbf6187e13a 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -324,6 +324,10 @@ struct fman_port_qmi_regs { #define HWP_HXS_PHE_REPORT 0x00000800 #define HWP_HXS_PCAC_PSTAT 0x00000100 #define HWP_HXS_PCAC_PSTOP 0x00000001 +#define HWP_HXS_TCP_OFFSET 0xA +#define HWP_HXS_UDP_OFFSET 0xB +#define HWP_HXS_SH_PAD_REM 0x80000000 + struct fman_port_hwp_regs { struct { u32 ssa; /* Soft Sequence Attachment */ @@ -728,6 +732,10 @@ static void init_hwp(struct fman_port *port) iowrite32be(0xffffffff, ®s->pmda[i].lcv); } + /* Short packet padding removal from checksum calculation */ + iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_TCP_OFFSET].ssa); + iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_UDP_OFFSET].ssa); + start_port_hwp(port); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index e2e5cdc7119c..4c0f7eda1166 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -439,6 +439,7 @@ static void rx_free_irq(struct hinic_rxq *rxq) { struct hinic_rq *rq = rxq->rq; + irq_set_affinity_hint(rq->irq, NULL); free_irq(rq->irq, rxq); rx_del_napi(rxq); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index ed6dbcfd4e96..b151ae316546 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2199,9 +2199,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, return true; } -#define I40E_XDP_PASS 0 -#define I40E_XDP_CONSUMED 1 -#define I40E_XDP_TX 2 +#define I40E_XDP_PASS 0 +#define I40E_XDP_CONSUMED BIT(0) +#define I40E_XDP_TX BIT(1) +#define I40E_XDP_REDIR BIT(2) static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring); @@ -2248,7 +2249,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED; + result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; break; default: bpf_warn_invalid_xdp_action(act); @@ -2311,7 +2312,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); - bool failure = false, xdp_xmit = false; + unsigned int xdp_xmit = 0; + bool failure = false; struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; @@ -2372,8 +2374,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -I40E_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + xdp_xmit |= xdp_res; i40e_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2427,12 +2431,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & I40E_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & I40E_XDP_TX) { struct i40e_ring *xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; i40e_xdp_ring_update_tail(xdp_ring); - xdp_do_flush_map(); } rx_ring->skb = skb; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3e87dbbc9024..62e57b05a0ae 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2186,9 +2186,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -#define IXGBE_XDP_PASS 0 -#define IXGBE_XDP_CONSUMED 1 -#define IXGBE_XDP_TX 2 +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, struct xdp_frame *xdpf); @@ -2225,7 +2226,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); if (!err) - result = IXGBE_XDP_TX; + result = IXGBE_XDP_REDIR; else result = IXGBE_XDP_CONSUMED; break; @@ -2285,7 +2286,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; @@ -2328,8 +2329,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBE_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2401,7 +2404,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; /* Force memory writes to complete before letting h/w @@ -2409,8 +2415,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ wmb(); writel(ring->next_to_use, ring->tail); - - xdp_do_flush_map(); } u64_stats_update_begin(&rx_ring->syncp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 487388aed98f..384c1fa49081 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -807,6 +807,7 @@ static void cmd_work_handler(struct work_struct *work) unsigned long flags; bool poll_cmd = ent->polling; int alloc_ret; + int cmd_mode; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -853,6 +854,7 @@ static void cmd_work_handler(struct work_struct *work) set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); ent->ts1 = ktime_get_ns(); + cmd_mode = cmd->mode; if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); @@ -877,7 +879,7 @@ static void cmd_work_handler(struct work_struct *work) iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell); mmiowb(); /* if not in polling don't use ent after this point */ - if (cmd->mode == CMD_MODE_POLLING || poll_cmd) { + if (cmd_mode == CMD_MODE_POLLING || poll_cmd) { poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); @@ -1276,7 +1278,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, { struct mlx5_core_dev *dev = filp->private_data; struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - char outlen_str[8]; + char outlen_str[8] = {0}; int outlen; void *ptr; int err; @@ -1291,8 +1293,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, if (copy_from_user(outlen_str, buf, count)) return -EFAULT; - outlen_str[7] = 0; - err = sscanf(outlen_str, "%d", &outlen); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 56c1b6f5593e..dae4156a710d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2846,7 +2846,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); @@ -2857,7 +2857,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { mlx5e_redirect_rqts_to_drop(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_remove_sqs_fwd_rules(priv); /* FIXME: This is a W/A only for tx timeout watch dog false alarm when @@ -4597,7 +4597,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_set_netdev_dev_addr(netdev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) - if (MLX5_VPORT_MANAGER(mdev)) + if (MLX5_ESWITCH_MANAGER(mdev)) netdev->switchdev_ops = &mlx5e_switchdev_ops; #endif @@ -4753,7 +4753,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_enable_async_events(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_register_vport_reps(priv); if (netdev->reg_state != NETREG_REGISTERED) @@ -4788,7 +4788,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_unregister_vport_reps(priv); mlx5e_disable_async_events(priv); @@ -4972,7 +4972,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return NULL; #ifdef CONFIG_MLX5_ESWITCH - if (MLX5_VPORT_MANAGER(mdev)) { + if (MLX5_ESWITCH_MANAGER(mdev)) { rpriv = mlx5e_alloc_nic_rep_priv(mdev); if (!rpriv) { mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 57987f6546e8..2b8040a3cdbd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -823,7 +823,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) return false; rep = rpriv->rep; @@ -837,8 +837,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_eswitch_rep *rep; + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) + return false; + + rep = rpriv->rep; if (rep && rep->vport != FDB_UPLINK_VPORT) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index f63dfbcd29fe..b79d74860a30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1594,17 +1594,15 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) } /* Public E-Switch API */ -#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev)) +#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) + int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { int err; int i, enabled_events; - if (!ESW_ALLOWED(esw)) - return 0; - - if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) || + if (!ESW_ALLOWED(esw) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n"); return -EOPNOTSUPP; @@ -1806,7 +1804,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, u64 node_guid; int err = 0; - if (!ESW_ALLOWED(esw)) + if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) return -EPERM; if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac)) return -EINVAL; @@ -1883,7 +1881,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, { struct mlx5_vport *evport; - if (!ESW_ALLOWED(esw)) + if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) return -EPERM; if (!LEGAL_VPORT(esw, vport)) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index cecd201f0b73..91f1209886ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1079,8 +1079,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return -EOPNOTSUPP; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; + if(!MLX5_ESWITCH_MANAGER(dev)) + return -EPERM; if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 49a75d31185e..f1a86cea86a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -32,6 +32,7 @@ #include <linux/mutex.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "fs_core.h" @@ -2652,7 +2653,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) { err = init_fdb_root_ns(steering); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index afd9f4fa22f4..41ad24f0de2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -32,6 +32,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/cmd.h> +#include <linux/mlx5/eswitch.h> #include <linux/module.h> #include "mlx5_core.h" #include "../../mlxfw/mlxfw.h" @@ -159,13 +160,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) } if (MLX5_CAP_GEN(dev, vport_group_manager) && - MLX5_CAP_GEN(dev, eswitch_flow_table)) { + MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); if (err) return err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 7cb67122e8b5..98359559c77e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include <linux/etherdevice.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "lib/mpfs.h" @@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); struct mlx5_mpfs *mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); @@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) { struct mlx5_mpfs *mpfs = dev->priv.mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return; WARN_ON(!hlist_empty(mpfs->hash)); @@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) u32 index; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); @@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index fa9d0760dd36..31a9cbd85689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc); static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, int inlen) { - u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; @@ -713,7 +713,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, int outlen) { - u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 2a8b529ce6dd..a0674962f02c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return -EBUSY; } + if (!MLX5_ESWITCH_MANAGER(dev)) + goto enable_vfs_hca; + err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); if (err) { mlx5_core_warn(dev, @@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return err; } +enable_vfs_hca: for (vf = 0; vf < num_vfs; vf++) { err = mlx5_core_enable_hca(dev, vf + 1); if (err) { @@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) } out: - mlx5_eswitch_disable_sriov(dev->priv.eswitch); + if (MLX5_ESWITCH_MANAGER(dev)) + mlx5_eswitch_disable_sriov(dev->priv.eswitch); if (mlx5_wait_for_vf_pages(dev)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 719cecb182c6..7eecd5b07bb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -549,8 +549,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, return -EINVAL; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES; - if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify)) - return -EOPNOTSUPP; in = kvzalloc(inlen, GFP_KERNEL); if (!in) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index fcdfb8e7fdea..40216d56dddc 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -81,10 +81,10 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn, ret = nfp_net_bpf_offload(nn, prog, running, extack); /* Stop offload if replace not possible */ - if (ret && prog) - nfp_bpf_xdp_offload(app, nn, NULL, extack); + if (ret) + return ret; - nn->dp.bpf_offload_xdp = prog && !ret; + nn->dp.bpf_offload_xdp = !!prog; return ret; } @@ -202,6 +202,9 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + if (tcf_block_shared(f->block)) + return -EOPNOTSUPP; + switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 91935405f586..84f7a5dbea9d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -123,6 +123,20 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, NFP_FLOWER_MASK_MPLS_Q; frame->mpls_lse = cpu_to_be32(t_mpls); + } else if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC)) { + /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q + * bit, which indicates an mpls ether type but without any + * mpls fields. + */ + struct flow_dissector_key_basic *key_basic; + + key_basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + flow->key); + if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || + key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) + frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index c42e64f32333..525057bee0ed 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -264,6 +264,14 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, case cpu_to_be16(ETH_P_ARP): return -EOPNOTSUPP; + case cpu_to_be16(ETH_P_MPLS_UC): + case cpu_to_be16(ETH_P_MPLS_MC): + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + key_layer |= NFP_FLOWER_LAYER_MAC; + key_size += sizeof(struct nfp_flower_mac_mpls); + } + break; + /* Will be included in layer 2. */ case cpu_to_be16(ETH_P_8021Q): break; @@ -623,6 +631,9 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + if (tcf_block_shared(f->block)) + return -EOPNOTSUPP; + switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c index cd34097b79f1..37a6d7822a38 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c @@ -232,7 +232,7 @@ struct nfp_nffw_info *nfp_nffw_info_open(struct nfp_cpp *cpp) err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res), nfp_resource_address(state->res), fwinf, sizeof(*fwinf)); - if (err < sizeof(*fwinf)) + if (err < (int)sizeof(*fwinf)) goto err_release; if (!nffw_res_flg_init_get(fwinf)) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index f0b01385d5cb..e0680ce91328 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -709,9 +709,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn, p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id, - ARRAY_SIZE(p_local->local_chassis_id)); + sizeof(p_local->local_chassis_id)); memcpy(params->lldp_local.local_port_id, p_local->local_port_id, - ARRAY_SIZE(p_local->local_port_id)); + sizeof(p_local->local_port_id)); } static void @@ -723,9 +723,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn, p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id, - ARRAY_SIZE(p_remote->peer_chassis_id)); + sizeof(p_remote->peer_chassis_id)); memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id, - ARRAY_SIZE(p_remote->peer_port_id)); + sizeof(p_remote->peer_port_id)); } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 329781cda77f..e5249b4741d0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1804,7 +1804,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) DP_INFO(p_hwfn, "Failed to update driver state\n"); rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt, - QED_OV_ESWITCH_VEB); + QED_OV_ESWITCH_NONE); if (rc) DP_INFO(p_hwfn, "Failed to update eswitch mode\n"); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 5c10fd7210c3..0cbc74d6ca8b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -789,6 +789,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev, /* We want a minimum of one slowpath and one fastpath vector per hwfn */ cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2; + if (is_kdump_kernel()) { + DP_INFO(cdev, + "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n", + cdev->int_params.in.min_msix_cnt); + cdev->int_params.in.num_vectors = + cdev->int_params.in.min_msix_cnt; + } + rc = qed_set_int_mode(cdev, false); if (rc) { DP_ERR(cdev, "qed_slowpath_setup_int ERR\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index f01bf52bc381..fd59cf45f4be 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -4513,6 +4513,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn, static int qed_sriov_enable(struct qed_dev *cdev, int num) { struct qed_iov_vf_init_params params; + struct qed_hwfn *hwfn; + struct qed_ptt *ptt; int i, j, rc; if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) { @@ -4525,8 +4527,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) /* Initialize HW for VF access */ for_each_hwfn(cdev, j) { - struct qed_hwfn *hwfn = &cdev->hwfns[j]; - struct qed_ptt *ptt = qed_ptt_acquire(hwfn); + hwfn = &cdev->hwfns[j]; + ptt = qed_ptt_acquire(hwfn); /* Make sure not to use more than 16 queues per VF */ params.num_queues = min_t(int, @@ -4562,6 +4564,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) goto err; } + hwfn = QED_LEADING_HWFN(cdev); + ptt = qed_ptt_acquire(hwfn); + if (!ptt) { + DP_ERR(hwfn, "Failed to acquire ptt\n"); + rc = -EBUSY; + goto err; + } + + rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB); + if (rc) + DP_INFO(cdev, "Failed to update eswitch mode\n"); + qed_ptt_release(hwfn, ptt); + return num; err: diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 02adb513f475..013ff567283c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info) { struct qede_ptp *ptp = edev->ptp; - if (!ptp) - return -EIO; + if (!ptp) { + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + + return 0; + } info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 8edf20967c82..e045a5d6b938 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -2794,6 +2794,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx) if (!state) return -ENOMEM; efx->filter_state = state; + init_rwsem(&state->lock); table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP]; table->id = EFX_FARCH_FILTER_TABLE_RX_IP; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index d37f17ca62fe..65bc3556bd8f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -407,6 +407,16 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan) } } +static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) +{ + u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); + + value &= ~DMA_RBSZ_MASK; + value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK; + + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); +} + const struct stmmac_dma_ops dwmac4_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, @@ -431,6 +441,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { .set_rx_tail_ptr = dwmac4_set_rx_tail_ptr, .set_tx_tail_ptr = dwmac4_set_tx_tail_ptr, .enable_tso = dwmac4_enable_tso, + .set_bfsize = dwmac4_set_bfsize, }; const struct stmmac_dma_ops dwmac410_dma_ops = { @@ -457,4 +468,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = { .set_rx_tail_ptr = dwmac4_set_rx_tail_ptr, .set_tx_tail_ptr = dwmac4_set_tx_tail_ptr, .enable_tso = dwmac4_enable_tso, + .set_bfsize = dwmac4_set_bfsize, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index c63c1fe3f26b..22a4a6dbb1a4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -120,6 +120,8 @@ /* DMA Rx Channel X Control register defines */ #define DMA_CONTROL_SR BIT(0) +#define DMA_RBSZ_MASK GENMASK(14, 1) +#define DMA_RBSZ_SHIFT 1 /* Interrupt status per channel */ #define DMA_CHAN_STATUS_REB GENMASK(21, 19) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e44e7b26ce82..fe8b536b13f8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -183,6 +183,7 @@ struct stmmac_dma_ops { void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); + void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan); }; #define stmmac_reset(__priv, __args...) \ @@ -235,6 +236,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args) #define stmmac_enable_tso(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, enable_tso, __args) +#define stmmac_set_dma_bfsize(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, set_bfsize, __args) struct mac_device_info; struct net_device; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cba46b62a1cd..60f59abab009 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1804,6 +1804,8 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz, qmode); + stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz, + chan); } for (chan = 0; chan < tx_channels_count; chan++) { diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 750eaa53bf0c..ada33c2d9ac2 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -476,7 +476,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 1a924b867b07..4b6e308199d2 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -210,7 +210,7 @@ int netvsc_recv_callback(struct net_device *net, void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); -void rndis_set_subchannel(struct work_struct *w); +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 5d5bd513847f..8e9d0ee1572b 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -65,6 +65,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf) VM_PKT_DATA_INBAND, 0); } +/* Worker to setup sub channels on initial setup + * Initial hotplug event occurs in softirq context + * and can't wait for channels. + */ +static void netvsc_subchan_work(struct work_struct *w) +{ + struct netvsc_device *nvdev = + container_of(w, struct netvsc_device, subchan_work); + struct rndis_device *rdev; + int i, ret; + + /* Avoid deadlock with device removal already under RTNL */ + if (!rtnl_trylock()) { + schedule_work(w); + return; + } + + rdev = nvdev->extension; + if (rdev) { + ret = rndis_set_subchannel(rdev->ndev, nvdev); + if (ret == 0) { + netif_device_attach(rdev->ndev); + } else { + /* fallback to only primary channel */ + for (i = 1; i < nvdev->num_chn; i++) + netif_napi_del(&nvdev->chan_table[i].napi); + + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + rtnl_unlock(); +} + static struct netvsc_device *alloc_net_device(void) { struct netvsc_device *net_device; @@ -81,7 +116,7 @@ static struct netvsc_device *alloc_net_device(void) init_completion(&net_device->channel_init_wait); init_waitqueue_head(&net_device->subchan_open); - INIT_WORK(&net_device->subchan_work, rndis_set_subchannel); + INIT_WORK(&net_device->subchan_work, netvsc_subchan_work); return net_device; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index fe2256bf1d13..dd1d6e115145 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -905,8 +905,20 @@ static int netvsc_attach(struct net_device *ndev, if (IS_ERR(nvdev)) return PTR_ERR(nvdev); - /* Note: enable and attach happen when sub-channels setup */ + if (nvdev->num_chn > 1) { + ret = rndis_set_subchannel(ndev, nvdev); + + /* if unavailable, just proceed with one queue */ + if (ret) { + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + /* In any case device is now ready */ + netif_device_attach(ndev); + /* Note: enable and attach happen when sub-channels setup */ netif_carrier_off(ndev); if (netif_running(ndev)) { @@ -2089,6 +2101,9 @@ static int netvsc_probe(struct hv_device *dev, memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); + if (nvdev->num_chn > 1) + schedule_work(&nvdev->subchan_work); + /* hw_features computed in rndis_netdev_set_hwcaps() */ net->features = net->hw_features | NETIF_F_HIGHDMA | NETIF_F_SG | diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 5428bb261102..9b4e3c3787e5 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1062,29 +1062,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) * This breaks overlap of processing the host message for the * new primary channel with the initialization of sub-channels. */ -void rndis_set_subchannel(struct work_struct *w) +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev) { - struct netvsc_device *nvdev - = container_of(w, struct netvsc_device, subchan_work); struct nvsp_message *init_packet = &nvdev->channel_init_pkt; - struct net_device_context *ndev_ctx; - struct rndis_device *rdev; - struct net_device *ndev; - struct hv_device *hv_dev; + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hv_dev = ndev_ctx->device_ctx; + struct rndis_device *rdev = nvdev->extension; int i, ret; - if (!rtnl_trylock()) { - schedule_work(w); - return; - } - - rdev = nvdev->extension; - if (!rdev) - goto unlock; /* device was removed */ - - ndev = rdev->ndev; - ndev_ctx = netdev_priv(ndev); - hv_dev = ndev_ctx->device_ctx; + ASSERT_RTNL(); memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL; @@ -1100,13 +1086,13 @@ void rndis_set_subchannel(struct work_struct *w) VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret) { netdev_err(ndev, "sub channel allocate send failed: %d\n", ret); - goto failed; + return ret; } wait_for_completion(&nvdev->channel_init_wait); if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) { netdev_err(ndev, "sub channel request failed\n"); - goto failed; + return -EIO; } nvdev->num_chn = 1 + @@ -1125,21 +1111,7 @@ void rndis_set_subchannel(struct work_struct *w) for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; - netif_device_attach(ndev); - rtnl_unlock(); - return; - -failed: - /* fallback to only primary channel */ - for (i = 1; i < nvdev->num_chn; i++) - netif_napi_del(&nvdev->chan_table[i].napi); - - nvdev->max_chn = 1; - nvdev->num_chn = 1; - - netif_device_attach(ndev); -unlock: - rtnl_unlock(); + return 0; } static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, @@ -1360,21 +1332,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, netif_napi_add(net, &net_device->chan_table[i].napi, netvsc_poll, NAPI_POLL_WEIGHT); - if (net_device->num_chn > 1) - schedule_work(&net_device->subchan_work); + return net_device; out: - /* if unavailable, just proceed with one queue */ - if (ret) { - net_device->max_chn = 1; - net_device->num_chn = 1; - } - - /* No sub channels, device is ready */ - if (net_device->num_chn == 1) - netif_device_attach(net); - - return net_device; + /* setting up multiple channels failed */ + net_device->max_chn = 1; + net_device->num_chn = 1; err_dev_remv: rndis_filter_device_remove(dev, net_device); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 23c1d6600241..4a949569ec4c 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -75,10 +75,23 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval) { struct ipvl_dev *ipvlan; struct net_device *mdev = port->dev; - int err = 0; + unsigned int flags; + int err; ASSERT_RTNL(); if (port->mode != nval) { + list_for_each_entry(ipvlan, &port->ipvlans, pnode) { + flags = ipvlan->dev->flags; + if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) { + err = dev_change_flags(ipvlan->dev, + flags | IFF_NOARP); + } else { + err = dev_change_flags(ipvlan->dev, + flags & ~IFF_NOARP); + } + if (unlikely(err)) + goto fail; + } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); @@ -86,21 +99,28 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval) mdev->l3mdev_ops = &ipvl_l3mdev_ops; mdev->priv_flags |= IFF_L3MDEV_MASTER; } else - return err; + goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ mdev->priv_flags &= ~IFF_L3MDEV_MASTER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); mdev->l3mdev_ops = NULL; } - list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) - ipvlan->dev->flags |= IFF_NOARP; - else - ipvlan->dev->flags &= ~IFF_NOARP; - } port->mode = nval; } + return 0; + +fail: + /* Undo the flags changes that have been done so far. */ + list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) { + flags = ipvlan->dev->flags; + if (port->mode == IPVLAN_MODE_L3 || + port->mode == IPVLAN_MODE_L3S) + dev_change_flags(ipvlan->dev, flags | IFF_NOARP); + else + dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP); + } + return err; } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 081d99aa3985..49ac678eb2dc 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -222,7 +222,7 @@ static int dp83811_config_intr(struct phy_device *phydev) if (err < 0) return err; - err = phy_write(phydev, MII_DP83811_INT_STAT1, 0); + err = phy_write(phydev, MII_DP83811_INT_STAT2, 0); } return err; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 8dff87ec6d99..2e4130746c40 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -64,6 +64,7 @@ #define DEFAULT_RX_CSUM_ENABLE (true) #define DEFAULT_TSO_CSUM_ENABLE (true) #define DEFAULT_VLAN_FILTER_ENABLE (true) +#define DEFAULT_VLAN_RX_OFFLOAD (true) #define TX_OVERHEAD (8) #define RXW_PADDING 2 @@ -2298,7 +2299,7 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; - ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN); + ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); netdev->mtu = new_mtu; @@ -2364,6 +2365,11 @@ static int lan78xx_set_features(struct net_device *netdev, } if (features & NETIF_F_HW_VLAN_CTAG_RX) + pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_; + else + pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_; + + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; else pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; @@ -2587,7 +2593,8 @@ static int lan78xx_reset(struct lan78xx_net *dev) buf |= FCT_TX_CTL_EN_; ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf); - ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN); + ret = lan78xx_set_rx_max_frame_length(dev, + dev->net->mtu + VLAN_ETH_HLEN); ret = lan78xx_read_reg(dev, MAC_RX, &buf); buf |= MAC_RX_RXEN_; @@ -2975,6 +2982,12 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) if (DEFAULT_TSO_CSUM_ENABLE) dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG; + if (DEFAULT_VLAN_RX_OFFLOAD) + dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX; + + if (DEFAULT_VLAN_FILTER_ENABLE) + dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + dev->net->hw_features = dev->net->features; ret = lan78xx_setup_irq_domain(dev); @@ -3039,8 +3052,13 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, struct sk_buff *skb, u32 rx_cmd_a, u32 rx_cmd_b) { + /* HW Checksum offload appears to be flawed if used when not stripping + * VLAN headers. Drop back to S/W checksums under these conditions. + */ if (!(dev->net->features & NETIF_F_RXCSUM) || - unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) { + unlikely(rx_cmd_a & RX_CMD_A_ICSM_) || + ((rx_cmd_a & RX_CMD_A_FVTG_) && + !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) { skb->ip_summed = CHECKSUM_NONE; } else { skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_)); @@ -3048,6 +3066,16 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, } } +static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev, + struct sk_buff *skb, + u32 rx_cmd_a, u32 rx_cmd_b) +{ + if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) && + (rx_cmd_a & RX_CMD_A_FVTG_)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + (rx_cmd_b & 0xffff)); +} + static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) { int status; @@ -3112,6 +3140,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb) if (skb->len == size) { lan78xx_rx_csum_offload(dev, skb, rx_cmd_a, rx_cmd_b); + lan78xx_rx_vlan_offload(dev, skb, + rx_cmd_a, rx_cmd_b); skb_trim(skb, skb->len - 4); /* remove fcs */ skb->truesize = size + sizeof(struct sk_buff); @@ -3130,6 +3160,7 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb) skb_set_tail_pointer(skb2, size); lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b); + lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b); skb_trim(skb2, skb2->len - 4); /* remove fcs */ skb2->truesize = size + sizeof(struct sk_buff); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 86f7196f9d91..2a58607a6aea 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3962,7 +3962,8 @@ static int rtl8152_close(struct net_device *netdev) #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&tp->pm_notifier); #endif - napi_disable(&tp->napi); + if (!test_bit(RTL8152_UNPLUG, &tp->flags)) + napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b6c9a2af3732..53085c63277b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -53,6 +53,10 @@ module_param(napi_tx, bool, 0644); /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */ #define VIRTIO_XDP_HEADROOM 256 +/* Separating two types of XDP xmit */ +#define VIRTIO_XDP_TX BIT(0) +#define VIRTIO_XDP_REDIR BIT(1) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -582,7 +586,7 @@ static struct sk_buff *receive_small(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, - bool *xdp_xmit) + unsigned int *xdp_xmit) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -654,14 +658,14 @@ static struct sk_buff *receive_small(struct net_device *dev, trace_xdp_exception(vi->dev, xdp_prog, act); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_TX; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: err = xdp_do_redirect(dev, &xdp, xdp_prog); if (err) goto err_xdp; - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_REDIR; rcu_read_unlock(); goto xdp_xmit; default: @@ -723,7 +727,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *buf, void *ctx, unsigned int len, - bool *xdp_xmit) + unsigned int *xdp_xmit) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -818,7 +822,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(xdp_page); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_TX; if (unlikely(xdp_page != page)) put_page(page); rcu_read_unlock(); @@ -830,7 +834,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(xdp_page); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_REDIR; if (unlikely(xdp_page != page)) put_page(page); rcu_read_unlock(); @@ -939,7 +943,8 @@ xdp_xmit: } static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx, bool *xdp_xmit) + void *buf, unsigned int len, void **ctx, + unsigned int *xdp_xmit) { struct net_device *dev = vi->dev; struct sk_buff *skb; @@ -1232,7 +1237,8 @@ static void refill_work(struct work_struct *work) } } -static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit) +static int virtnet_receive(struct receive_queue *rq, int budget, + unsigned int *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int len, received = 0, bytes = 0; @@ -1321,7 +1327,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget) struct virtnet_info *vi = rq->vq->vdev->priv; struct send_queue *sq; unsigned int received, qp; - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; virtnet_poll_cleantx(rq); @@ -1331,12 +1337,14 @@ static int virtnet_poll(struct napi_struct *napi, int budget) if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); - if (xdp_xmit) { + if (xdp_xmit & VIRTIO_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & VIRTIO_XDP_TX) { qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); sq = &vi->sq[qp]; virtqueue_kick(sq->vq); - xdp_do_flush_map(); } return received; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index aee0e60471f1..f6bb1d54d4bd 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, flush = 0; out: - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 2a5fec55bf60..a246a618f9a4 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -829,6 +829,17 @@ struct qeth_trap_id { /*some helper functions*/ #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "") +static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, + unsigned int elements) +{ + unsigned int i; + + for (i = 0; i < elements; i++) + memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element)); + buf->element[14].sflags = 0; + buf->element[15].sflags = 0; +} + /** * qeth_get_elements_for_range() - find number of SBALEs to cover range. * @start: Start of the address range. @@ -1029,7 +1040,7 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, __u16, __u16, enum qeth_prot_versions); int qeth_set_features(struct net_device *, netdev_features_t); -void qeth_recover_features(struct net_device *dev); +void qeth_enable_hw_features(struct net_device *dev); netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); netdev_features_t qeth_features_check(struct sk_buff *skb, struct net_device *dev, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8e1474f1ffac..d01ac29fd986 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -73,9 +73,6 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, struct qeth_qdio_out_buffer *buf, enum iucv_tx_notify notification); static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf); -static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, - struct qeth_qdio_out_buffer *buf, - enum qeth_qdio_buffer_states newbufstate); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); struct workqueue_struct *qeth_wq; @@ -489,6 +486,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, struct qaob *aob; struct qeth_qdio_out_buffer *buffer; enum iucv_tx_notify notification; + unsigned int i; aob = (struct qaob *) phys_to_virt(phys_aob_addr); QETH_CARD_TEXT(card, 5, "haob"); @@ -513,10 +511,18 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, qeth_notify_skbs(buffer->q, buffer, notification); buffer->aob = NULL; - qeth_clear_output_buffer(buffer->q, buffer, - QETH_QDIO_BUF_HANDLED_DELAYED); + /* Free dangling allocations. The attached skbs are handled by + * qeth_cleanup_handled_pending(). + */ + for (i = 0; + i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card); + i++) { + if (aob->sba[i] && buffer->is_header[i]) + kmem_cache_free(qeth_core_header_cache, + (void *) aob->sba[i]); + } + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); - /* from here on: do not touch buffer anymore */ qdio_release_aob(aob); } @@ -3759,6 +3765,10 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, QETH_CARD_TEXT(queue->card, 5, "aob"); QETH_CARD_TEXT_(queue->card, 5, "%lx", virt_to_phys(buffer->aob)); + + /* prepare the queue slot for re-use: */ + qeth_scrub_qdio_buffer(buffer->buffer, + QETH_MAX_BUFFER_ELEMENTS(card)); if (qeth_init_qdio_out_buf(queue, bidx)) { QETH_CARD_TEXT(card, 2, "outofbuf"); qeth_schedule_recovery(card); @@ -4834,7 +4844,7 @@ int qeth_vm_request_mac(struct qeth_card *card) goto out; } - ccw_device_get_id(CARD_RDEV(card), &id); + ccw_device_get_id(CARD_DDEV(card), &id); request->resp_buf_len = sizeof(*response); request->resp_version = DIAG26C_VERSION2; request->op_code = DIAG26C_GET_MAC; @@ -6459,28 +6469,27 @@ static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on) #define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \ NETIF_F_IPV6_CSUM) /** - * qeth_recover_features() - Restore device features after recovery - * @dev: the recovering net_device - * - * Caller must hold rtnl lock. + * qeth_enable_hw_features() - (Re-)Enable HW functions for device features + * @dev: a net_device */ -void qeth_recover_features(struct net_device *dev) +void qeth_enable_hw_features(struct net_device *dev) { - netdev_features_t features = dev->features; struct qeth_card *card = dev->ml_priv; + netdev_features_t features; + rtnl_lock(); + features = dev->features; /* force-off any feature that needs an IPA sequence. * netdev_update_features() will restart them. */ dev->features &= ~QETH_HW_FEATURES; netdev_update_features(dev); - - if (features == dev->features) - return; - dev_warn(&card->gdev->dev, - "Device recovery failed to restore all offload features\n"); + if (features != dev->features) + dev_warn(&card->gdev->dev, + "Device recovery failed to restore all offload features\n"); + rtnl_unlock(); } -EXPORT_SYMBOL_GPL(qeth_recover_features); +EXPORT_SYMBOL_GPL(qeth_enable_hw_features); int qeth_set_features(struct net_device *dev, netdev_features_t features) { diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index a7cb37da6a21..2487f0aeb165 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -140,7 +140,7 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) { - enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? + enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ? IPA_CMD_SETGMAC : IPA_CMD_SETVMAC; int rc; @@ -157,7 +157,7 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) { - enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? + enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ? IPA_CMD_DELGMAC : IPA_CMD_DELVMAC; int rc; @@ -501,27 +501,34 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) return -ERESTARTSYS; } + /* avoid racing against concurrent state change: */ + if (!mutex_trylock(&card->conf_mutex)) + return -EAGAIN; + if (!qeth_card_hw_is_reachable(card)) { ether_addr_copy(dev->dev_addr, addr->sa_data); - return 0; + goto out_unlock; } /* don't register the same address twice */ if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) && (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)) - return 0; + goto out_unlock; /* add the new address, switch over, drop the old */ rc = qeth_l2_send_setmac(card, addr->sa_data); if (rc) - return rc; + goto out_unlock; ether_addr_copy(old_addr, dev->dev_addr); ether_addr_copy(dev->dev_addr, addr->sa_data); if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED) qeth_l2_remove_mac(card, old_addr); card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED; - return 0; + +out_unlock: + mutex_unlock(&card->conf_mutex); + return rc; } static void qeth_promisc_to_bridge(struct qeth_card *card) @@ -1112,6 +1119,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) netif_carrier_off(card->dev); qeth_set_allowed_threads(card, 0xffffffff, 0); + + qeth_enable_hw_features(card->dev); if (recover_flag == CARD_STATE_RECOVER) { if (recovery_mode && card->info.type != QETH_CARD_TYPE_OSN) { @@ -1123,9 +1132,6 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) } /* this also sets saved unicast addresses */ qeth_l2_set_rx_mode(card->dev); - rtnl_lock(); - qeth_recover_features(card->dev); - rtnl_unlock(); } /* let user_space know that device is online */ kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index e7fa479adf47..5905dc63e256 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2662,6 +2662,8 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) netif_carrier_on(card->dev); else netif_carrier_off(card->dev); + + qeth_enable_hw_features(card->dev); if (recover_flag == CARD_STATE_RECOVER) { rtnl_lock(); if (recovery_mode) @@ -2669,7 +2671,6 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) else dev_open(card->dev); qeth_l3_set_rx_mode(card->dev); - qeth_recover_features(card->dev); rtnl_unlock(); } qeth_trace_features(card); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 975fb4cf1bb7..79795c5fa7c3 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -188,12 +188,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, \ __ret; \ }) +int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, struct bpf_prog *prog); +int cgroup_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype); +int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); #else +struct bpf_prog; struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} + #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7df32a3200f7..8827e797ff97 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -696,6 +696,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); +int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -714,6 +716,12 @@ static inline int sock_map_prog(struct bpf_map *map, { return -EOPNOTSUPP; } + +static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog) +{ + return -EINVAL; +} #endif #if defined(CONFIG_XDP_SOCKETS) diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h index 5f8a4283092d..9d9ff755ec29 100644 --- a/include/linux/bpf_lirc.h +++ b/include/linux/bpf_lirc.h @@ -5,11 +5,12 @@ #include <uapi/linux/bpf.h> #ifdef CONFIG_BPF_LIRC_MODE2 -int lirc_prog_attach(const union bpf_attr *attr); +int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int lirc_prog_detach(const union bpf_attr *attr); int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else -static inline int lirc_prog_attach(const union bpf_attr *attr) +static inline int lirc_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) { return -EINVAL; } diff --git a/include/linux/filter.h b/include/linux/filter.h index 20f2659dd829..300baad62c88 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -470,9 +470,7 @@ struct sock_fprog_kern { }; struct bpf_binary_header { - u16 pages; - u16 locked:1; - + u32 pages; /* Some arches need word alignment for their instructions */ u8 image[] __aligned(4); }; @@ -481,7 +479,7 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - locked:1, /* Program image locked? */ + undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -677,46 +675,24 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - fp->locked = 1; - if (set_memory_ro((unsigned long)fp, fp->pages)) - fp->locked = 0; -#endif + fp->undo_set_mem = 1; + set_memory_ro((unsigned long)fp, fp->pages); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - if (fp->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - fp->locked = 0; - } -#endif + if (fp->undo_set_mem) + set_memory_rw((unsigned long)fp, fp->pages); } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - hdr->locked = 1; - if (set_memory_ro((unsigned long)hdr, hdr->pages)) - hdr->locked = 0; -#endif + set_memory_ro((unsigned long)hdr, hdr->pages); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - if (hdr->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - hdr->locked = 0; - } -#endif + set_memory_rw((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * @@ -728,22 +704,6 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp) return (void *)addr; } -#ifdef CONFIG_ARCH_HAS_SET_MEMORY -static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp) -{ - if (!fp->locked) - return -ENOLCK; - if (fp->jited) { - const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); - - if (!hdr->locked) - return -ENOLCK; - } - - return 0; -} -#endif - int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index d3c9db492b30..fab5121ffb8f 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -8,6 +8,8 @@ #include <linux/mlx5/driver.h> +#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) + enum { SRIOV_NONE, SRIOV_LEGACY, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 27134c4fcb76..ac281f5ec9b8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -922,7 +922,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vnic_env_queue_counters[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 eswitch_flow_table[0x1]; + u8 eswitch_manager[0x1]; u8 device_memory[0x1]; u8 mcam_reg[0x1]; u8 pcam_reg[0x1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec9850c7936..3d0cc0b5cec2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2789,11 +2789,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 47e35cce3b64..a71264d75d7f 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -128,6 +128,7 @@ struct net { #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag nf_frag; + struct ctl_table_header *nf_frag_frags_hdr; #endif struct sock *nfnl; struct sock *nfnl_stash; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index c978a31b0f84..762ac9931b62 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -109,7 +109,6 @@ struct netns_ipv6 { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag { - struct netns_sysctl_ipv6 sysctl; struct netns_frags frags; }; #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3c1a2c47cd4..20b059574e60 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { } +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return false; +} + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 59b19b6a40d7..b7db3261c62d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1857,7 +1857,8 @@ union bpf_attr { * is resolved), the nexthop address is returned in ipv4_dst * or ipv6_dst based on family, smac is set to mac address of * egress device, dmac is set to nexthop mac address, rt_metric - * is set to metric from route (IPv4/IPv6 only). + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. * * *plen* argument is the size of the passed in struct. * *flags* argument can be a combination of one or more of the @@ -1873,9 +1874,10 @@ union bpf_attr { * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. * Return - * Egress device index on success, 0 if packet needs to continue - * up the stack for further processing or a negative error in case - * of failure. + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * * packet is not forwarded or needs assist from full stack * * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) * Description @@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args { #define BPF_FIB_LOOKUP_DIRECT BIT(0) #define BPF_FIB_LOOKUP_OUTPUT BIT(1) +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + struct bpf_fib_lookup { /* input: network family for lookup (AF_INET, AF_INET6) * output: network family of egress nexthop @@ -2625,7 +2639,11 @@ struct bpf_fib_lookup { /* total length of packet from network header - used for MTU check */ __u16 tot_len; - __u32 ifindex; /* L3 device index for lookup */ + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; union { /* inputs to lookup */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index f7c00bd6f8e4..3d83ee7df381 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, return ret; } +int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, struct bpf_prog *prog) +{ + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); + cgroup_put(cgrp); + return ret; +} + +int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + struct bpf_prog *prog; + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + + cgroup_put(cgrp); + return ret; +} + +int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + ret = cgroup_bpf_query(cgrp, attr, uattr); + + cgroup_put(cgrp); + return ret; +} + /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a9e6c04d0f4a..1e5625d46414 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -598,8 +598,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, bpf_fill_ill_insns(hdr, size); hdr->pages = size / PAGE_SIZE; - hdr->locked = 0; - hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -1450,22 +1448,6 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) return 0; } -static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp) -{ -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - int i, err; - - for (i = 0; i < fp->aux->func_cnt; i++) { - err = bpf_prog_check_pages_ro_single(fp->aux->func[i]); - if (err) - return err; - } - - return bpf_prog_check_pages_ro_single(fp); -#endif - return 0; -} - static void bpf_prog_select_func(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON @@ -1524,17 +1506,7 @@ finalize: * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); - if (*err) - return fp; - - /* Checkpoint: at this point onwards any cBPF -> eBPF or - * native eBPF program is read-only. If we failed to change - * the page attributes (e.g. allocation failure from - * splitting large pages), then reject the whole program - * in order to guarantee not ending up with any W+X pages - * from BPF side in kernel. - */ - *err = bpf_prog_check_pages_ro_locked(fp); + return fp; } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 52a91d816c0e..cf7b6a6dbd1f 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -72,6 +72,7 @@ struct bpf_htab { u32 n_buckets; u32 elem_size; struct bpf_sock_progs progs; + struct rcu_head rcu; }; struct htab_elem { @@ -89,8 +90,8 @@ enum smap_psock_state { struct smap_psock_map_entry { struct list_head list; struct sock **entry; - struct htab_elem *hash_link; - struct bpf_htab *htab; + struct htab_elem __rcu *hash_link; + struct bpf_htab __rcu *htab; }; struct smap_psock { @@ -120,6 +121,7 @@ struct smap_psock { struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; struct list_head maps; + spinlock_t maps_lock; /* Back reference used when sock callback trigger sockmap operations */ struct sock *sock; @@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); static int bpf_tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +static void bpf_tcp_close(struct sock *sk, long timeout); static inline struct smap_psock *smap_psock_sk(const struct sock *sk) { @@ -161,7 +164,42 @@ out: return !empty; } -static struct proto tcp_bpf_proto; +enum { + SOCKMAP_IPV4, + SOCKMAP_IPV6, + SOCKMAP_NUM_PROTS, +}; + +enum { + SOCKMAP_BASE, + SOCKMAP_TX, + SOCKMAP_NUM_CONFIGS, +}; + +static struct proto *saved_tcpv6_prot __read_mostly; +static DEFINE_SPINLOCK(tcpv6_prot_lock); +static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; +static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], + struct proto *base) +{ + prot[SOCKMAP_BASE] = *base; + prot[SOCKMAP_BASE].close = bpf_tcp_close; + prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; + prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; + + prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; + prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; + prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; +} + +static void update_sk_prot(struct sock *sk, struct smap_psock *psock) +{ + int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; + int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; + + sk->sk_prot = &bpf_tcp_prots[family][conf]; +} + static int bpf_tcp_init(struct sock *sk) { struct smap_psock *psock; @@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk) psock->save_close = sk->sk_prot->close; psock->sk_proto = sk->sk_prot; - if (psock->bpf_tx_msg) { - tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg; - tcp_bpf_proto.sendpage = bpf_tcp_sendpage; - tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg; - tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read; + /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ + if (sk->sk_family == AF_INET6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + spin_lock_bh(&tcpv6_prot_lock); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + spin_unlock_bh(&tcpv6_prot_lock); } - - sk->sk_prot = &tcp_bpf_proto; + update_sk_prot(sk, psock); rcu_read_unlock(); return 0; } @@ -219,16 +260,54 @@ out: rcu_read_unlock(); } +static struct htab_elem *lookup_elem_raw(struct hlist_head *head, + u32 hash, void *key, u32 key_size) +{ + struct htab_elem *l; + + hlist_for_each_entry_rcu(l, head, hash_node) { + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + } + + return NULL; +} + +static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &htab->buckets[hash & (htab->n_buckets - 1)]; +} + +static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &__select_bucket(htab, hash)->head; +} + static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { atomic_dec(&htab->count); kfree_rcu(l, rcu); } +static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, + struct smap_psock *psock) +{ + struct smap_psock_map_entry *e; + + spin_lock_bh(&psock->maps_lock); + e = list_first_entry_or_null(&psock->maps, + struct smap_psock_map_entry, + list); + if (e) + list_del(&e->list); + spin_unlock_bh(&psock->maps_lock); + return e; +} + static void bpf_tcp_close(struct sock *sk, long timeout) { void (*close_fun)(struct sock *sk, long timeout); - struct smap_psock_map_entry *e, *tmp; + struct smap_psock_map_entry *e; struct sk_msg_buff *md, *mtmp; struct smap_psock *psock; struct sock *osk; @@ -247,7 +326,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout) */ close_fun = psock->save_close; - write_lock_bh(&sk->sk_callback_lock); if (psock->cork) { free_start_sg(psock->sock, psock->cork); kfree(psock->cork); @@ -260,20 +338,38 @@ static void bpf_tcp_close(struct sock *sk, long timeout) kfree(md); } - list_for_each_entry_safe(e, tmp, &psock->maps, list) { + e = psock_map_pop(sk, psock); + while (e) { if (e->entry) { osk = cmpxchg(e->entry, sk, NULL); if (osk == sk) { - list_del(&e->list); smap_release_sock(psock, sk); } } else { - hlist_del_rcu(&e->hash_link->hash_node); - smap_release_sock(psock, e->hash_link->sk); - free_htab_elem(e->htab, e->hash_link); + struct htab_elem *link = rcu_dereference(e->hash_link); + struct bpf_htab *htab = rcu_dereference(e->htab); + struct hlist_head *head; + struct htab_elem *l; + struct bucket *b; + + b = __select_bucket(htab, link->hash); + head = &b->head; + raw_spin_lock_bh(&b->lock); + l = lookup_elem_raw(head, + link->hash, link->key, + htab->map.key_size); + /* If another thread deleted this object skip deletion. + * The refcnt on psock may or may not be zero. + */ + if (l) { + hlist_del_rcu(&link->hash_node); + smap_release_sock(psock, link->sk); + free_htab_elem(htab, link); + } + raw_spin_unlock_bh(&b->lock); } + e = psock_map_pop(sk, psock); } - write_unlock_bh(&sk->sk_callback_lock); rcu_read_unlock(); close_fun(sk, timeout); } @@ -1111,8 +1207,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock, static int bpf_tcp_ulp_register(void) { - tcp_bpf_proto = tcp_prot; - tcp_bpf_proto.close = bpf_tcp_close; + build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); /* Once BPF TX ULP is registered it is never unregistered. It * will be in the ULP list for the lifetime of the system. Doing * duplicate registers is not a problem. @@ -1357,7 +1452,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { if (refcount_dec_and_test(&psock->refcnt)) { tcp_cleanup_ulp(sock); + write_lock_bh(&sock->sk_callback_lock); smap_stop_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); clear_bit(SMAP_TX_RUNNING, &psock->state); rcu_assign_sk_user_data(sock, NULL); call_rcu_sched(&psock->rcu, smap_destroy_psock); @@ -1508,6 +1605,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node) INIT_LIST_HEAD(&psock->maps); INIT_LIST_HEAD(&psock->ingress); refcount_set(&psock->refcnt, 1); + spin_lock_init(&psock->maps_lock); rcu_assign_sk_user_data(sock, psock); sock_hold(sock); @@ -1564,18 +1662,32 @@ free_stab: return ERR_PTR(err); } -static void smap_list_remove(struct smap_psock *psock, - struct sock **entry, - struct htab_elem *hash_link) +static void smap_list_map_remove(struct smap_psock *psock, + struct sock **entry) { struct smap_psock_map_entry *e, *tmp; + spin_lock_bh(&psock->maps_lock); list_for_each_entry_safe(e, tmp, &psock->maps, list) { - if (e->entry == entry || e->hash_link == hash_link) { + if (e->entry == entry) list_del(&e->list); - break; - } } + spin_unlock_bh(&psock->maps_lock); +} + +static void smap_list_hash_remove(struct smap_psock *psock, + struct htab_elem *hash_link) +{ + struct smap_psock_map_entry *e, *tmp; + + spin_lock_bh(&psock->maps_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + struct htab_elem *c = rcu_dereference(e->hash_link); + + if (c == hash_link) + list_del(&e->list); + } + spin_unlock_bh(&psock->maps_lock); } static void sock_map_free(struct bpf_map *map) @@ -1601,7 +1713,6 @@ static void sock_map_free(struct bpf_map *map) if (!sock) continue; - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get the * sk_callback_lock before this case but after xchg happens @@ -1609,10 +1720,9 @@ static void sock_map_free(struct bpf_map *map) * to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, &stab->sock_map[i], NULL); + smap_list_map_remove(psock, &stab->sock_map[i]); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock(); @@ -1661,17 +1771,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key) if (!sock) return -EINVAL; - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); if (!psock) goto out; if (psock->bpf_parse) smap_stop_sock(psock, sock); - smap_list_remove(psock, &stab->sock_map[k], NULL); + smap_list_map_remove(psock, &stab->sock_map[k]); smap_release_sock(psock, sock); out: - write_unlock_bh(&sock->sk_callback_lock); return 0; } @@ -1752,7 +1860,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, } } - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* 2. Do not allow inheriting programs if psock exists and has @@ -1809,7 +1916,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, if (err) goto out_free; smap_init_progs(psock, verdict, parse); + write_lock_bh(&sock->sk_callback_lock); smap_start_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); } /* 4. Place psock in sockmap for use and stop any programs on @@ -1819,9 +1928,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, */ if (map_link) { e->entry = map_link; + spin_lock_bh(&psock->maps_lock); list_add_tail(&e->list, &psock->maps); + spin_unlock_bh(&psock->maps_lock); } - write_unlock_bh(&sock->sk_callback_lock); return err; out_free: smap_release_sock(psock, sock); @@ -1832,7 +1942,6 @@ out_progs: } if (tx_msg) bpf_prog_put(tx_msg); - write_unlock_bh(&sock->sk_callback_lock); kfree(e); return err; } @@ -1869,10 +1978,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (osock) { struct smap_psock *opsock = smap_psock_sk(osock); - write_lock_bh(&osock->sk_callback_lock); - smap_list_remove(opsock, &stab->sock_map[i], NULL); + smap_list_map_remove(opsock, &stab->sock_map[i]); smap_release_sock(opsock, osock); - write_unlock_bh(&osock->sk_callback_lock); } out: return err; @@ -1915,6 +2022,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) return 0; } +int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog) +{ + int ufd = attr->target_fd; + struct bpf_map *map; + struct fd f; + int err; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = sock_map_prog(map, prog, attr->attach_type); + fdput(f); + return err; +} + static void *sock_map_lookup(struct bpf_map *map, void *key) { return NULL; @@ -2043,14 +2168,13 @@ free_htab: return ERR_PTR(err); } -static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) +static void __bpf_htab_free(struct rcu_head *rcu) { - return &htab->buckets[hash & (htab->n_buckets - 1)]; -} + struct bpf_htab *htab; -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &__select_bucket(htab, hash)->head; + htab = container_of(rcu, struct bpf_htab, rcu); + bpf_map_area_free(htab->buckets); + kfree(htab); } static void sock_hash_free(struct bpf_map *map) @@ -2069,16 +2193,18 @@ static void sock_hash_free(struct bpf_map *map) */ rcu_read_lock(); for (i = 0; i < htab->n_buckets; i++) { - struct hlist_head *head = select_bucket(htab, i); + struct bucket *b = __select_bucket(htab, i); + struct hlist_head *head; struct hlist_node *n; struct htab_elem *l; + raw_spin_lock_bh(&b->lock); + head = &b->head; hlist_for_each_entry_safe(l, n, head, hash_node) { struct sock *sock = l->sk; struct smap_psock *psock; hlist_del_rcu(&l->hash_node); - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get * the sk_callback_lock before this case but after xchg @@ -2086,16 +2212,15 @@ static void sock_hash_free(struct bpf_map *map) * (psock) to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, NULL, l); + smap_list_hash_remove(psock, l); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); - kfree(l); + free_htab_elem(htab, l); } + raw_spin_unlock_bh(&b->lock); } rcu_read_unlock(); - bpf_map_area_free(htab->buckets); - kfree(htab); + call_rcu(&htab->rcu, __bpf_htab_free); } static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, @@ -2122,19 +2247,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, return l_new; } -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, - u32 hash, void *key, u32 key_size) -{ - struct htab_elem *l; - - hlist_for_each_entry_rcu(l, head, hash_node) { - if (l->hash == hash && !memcmp(&l->key, key, key_size)) - return l; - } - - return NULL; -} - static inline u32 htab_map_hash(const void *key, u32 key_len) { return jhash(key, key_len, 0); @@ -2254,9 +2366,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto bucket_err; } - e->hash_link = l_new; - e->htab = container_of(map, struct bpf_htab, map); + rcu_assign_pointer(e->hash_link, l_new); + rcu_assign_pointer(e->htab, + container_of(map, struct bpf_htab, map)); + spin_lock_bh(&psock->maps_lock); list_add_tail(&e->list, &psock->maps); + spin_unlock_bh(&psock->maps_lock); /* add new element to the head of the list, so that * concurrent search will find it before old elem @@ -2266,7 +2381,7 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, psock = smap_psock_sk(l_old->sk); hlist_del_rcu(&l_old->hash_node); - smap_list_remove(psock, NULL, l_old); + smap_list_hash_remove(psock, l_old); smap_release_sock(psock, l_old->sk); free_htab_elem(htab, l_old); } @@ -2326,7 +2441,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct smap_psock *psock; hlist_del_rcu(&l->hash_node); - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get the * sk_callback_lock before this case but after xchg happens @@ -2334,10 +2448,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) * to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, NULL, l); + smap_list_hash_remove(psock, l); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); free_htab_elem(htab, l); ret = 0; } @@ -2383,6 +2496,7 @@ const struct bpf_map_ops sock_hash_ops = { .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_hash_update_elem, .map_delete_elem = sock_hash_delete_elem, + .map_release_uref = sock_map_release, }; BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 35dc466641f2..d10ecd78105f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1483,8 +1483,6 @@ out_free_tp: return err; } -#ifdef CONFIG_CGROUP_BPF - static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { @@ -1499,40 +1497,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, #define BPF_PROG_ATTACH_LAST_FIELD attach_flags -static int sockmap_get_from_fd(const union bpf_attr *attr, - int type, bool attach) -{ - struct bpf_prog *prog = NULL; - int ufd = attr->target_fd; - struct bpf_map *map; - struct fd f; - int err; - - f = fdget(ufd); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return PTR_ERR(map); - - if (attach) { - prog = bpf_prog_get_type(attr->attach_bpf_fd, type); - if (IS_ERR(prog)) { - fdput(f); - return PTR_ERR(prog); - } - } - - err = sock_map_prog(map, prog, attr->attach_type); - if (err) { - fdput(f); - if (prog) - bpf_prog_put(prog); - return err; - } - - fdput(f); - return 0; -} - #define BPF_F_ATTACH_MASK \ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) @@ -1540,7 +1504,6 @@ static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; - struct cgroup *cgrp; int ret; if (!capable(CAP_NET_ADMIN)) @@ -1577,12 +1540,15 @@ static int bpf_prog_attach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true); + ptype = BPF_PROG_TYPE_SK_MSG; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true); + ptype = BPF_PROG_TYPE_SK_SKB; + break; case BPF_LIRC_MODE2: - return lirc_prog_attach(attr); + ptype = BPF_PROG_TYPE_LIRC_MODE2; + break; default: return -EINVAL; } @@ -1596,18 +1562,20 @@ static int bpf_prog_attach(const union bpf_attr *attr) return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) { - bpf_prog_put(prog); - return PTR_ERR(cgrp); + switch (ptype) { + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_SK_MSG: + ret = sockmap_get_from_fd(attr, ptype, prog); + break; + case BPF_PROG_TYPE_LIRC_MODE2: + ret = lirc_prog_attach(attr, prog); + break; + default: + ret = cgroup_bpf_prog_attach(attr, ptype, prog); } - ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, - attr->attach_flags); if (ret) bpf_prog_put(prog); - cgroup_put(cgrp); - return ret; } @@ -1616,9 +1584,6 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { enum bpf_prog_type ptype; - struct bpf_prog *prog; - struct cgroup *cgrp; - int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1651,29 +1616,17 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); default: return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); - if (IS_ERR(prog)) - prog = NULL; - - ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); - if (prog) - bpf_prog_put(prog); - cgroup_put(cgrp); - return ret; + return cgroup_bpf_prog_detach(attr, ptype); } #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt @@ -1681,9 +1634,6 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - struct cgroup *cgrp; - int ret; - if (!capable(CAP_NET_ADMIN)) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) @@ -1711,14 +1661,9 @@ static int bpf_prog_query(const union bpf_attr *attr, default: return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->query.target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - ret = cgroup_bpf_query(cgrp, attr, uattr); - cgroup_put(cgrp); - return ret; + + return cgroup_bpf_prog_query(attr, uattr); } -#endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -2365,7 +2310,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; -#ifdef CONFIG_CGROUP_BPF case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; @@ -2375,7 +2319,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr); break; -#endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); break; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 60aedc879361..08d3d59dca17 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -5282,21 +5282,31 @@ static struct bpf_test tests[] = { { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Ctx heavy transformations", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { }, { { 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }, { 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) } }, .fill_helper = bpf_fill_maxinsns6, + .expected_errcode = -ENOTSUPP, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Call heavy transformations", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, +#else CLASSIC | FLAG_NO_DATA, +#endif { }, { { 1, 0 }, { 10, 0 } }, .fill_helper = bpf_fill_maxinsns7, + .expected_errcode = -ENOTSUPP, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Jump heavy test", @@ -5347,18 +5357,28 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: exec all MSH", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { 0xfa, 0xfb, 0xfc, 0xfd, }, { { 4, 0xababab83 } }, .fill_helper = bpf_fill_maxinsns13, + .expected_errcode = -ENOTSUPP, }, { "BPF_MAXINSNS: ld_abs+get_processor_id", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { }, { { 1, 0xbee } }, .fill_helper = bpf_fill_ld_abs_get_processor_id, + .expected_errcode = -ENOTSUPP, }, /* * LD_IND / LD_ABS on fragmented SKBs diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 73a65789271b..8ccee3d01822 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -693,7 +693,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/Makefile b/net/Makefile index 13ec0d5415c7..bdaf53925acd 100644 --- a/net/Makefile +++ b/net/Makefile @@ -20,11 +20,7 @@ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ obj-$(CONFIG_NET) += ipv6/ -ifneq ($(CC_CAN_LINK),y) -$(warning CC cannot link executables. Skipping bpfilter.) -else obj-$(CONFIG_BPFILTER) += bpfilter/ -endif obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig index a948b072c28f..76deb6615883 100644 --- a/net/bpfilter/Kconfig +++ b/net/bpfilter/Kconfig @@ -1,6 +1,5 @@ menuconfig BPFILTER bool "BPF based packet filtering framework (BPFILTER)" - default n depends on NET && BPF && INET help This builds experimental bpfilter framework that is aiming to @@ -9,6 +8,7 @@ menuconfig BPFILTER if BPFILTER config BPFILTER_UMH tristate "bpfilter kernel module with user mode helper" + depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC)) default m help This builds bpfilter kernel module with embedded user mode helper diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index 051dc18b8ccb..39c6980b5d99 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -15,20 +15,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y) HOSTLDFLAGS += -static endif -# a bit of elf magic to convert bpfilter_umh binary into a binary blob -# inside bpfilter_umh.o elf file referenced by -# _binary_net_bpfilter_bpfilter_umh_start symbol -# which bpfilter_kern.c passes further into umh blob loader at run-time -quiet_cmd_copy_umh = GEN $@ - cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \ - $(OBJCOPY) -I binary \ - `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \ - |awk -F' |,' '/file format/{print "-O",$$NF} \ - /^architecture:/{print "-B",$$2}'` \ - --rename-section .data=.init.rodata $< $@ - -$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh - $(call cmd,copy_umh) +$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o -bpfilter-objs += bpfilter_kern.o bpfilter_umh.o +bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index 09522573f611..f0fc182d3db7 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -10,11 +10,8 @@ #include <linux/file.h> #include "msgfmt.h" -#define UMH_start _binary_net_bpfilter_bpfilter_umh_start -#define UMH_end _binary_net_bpfilter_bpfilter_umh_end - -extern char UMH_start; -extern char UMH_end; +extern char bpfilter_umh_start; +extern char bpfilter_umh_end; static struct umh_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ @@ -93,7 +90,9 @@ static int __init load_umh(void) int err; /* fork usermode process */ - err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info); + err = fork_usermode_blob(&bpfilter_umh_start, + &bpfilter_umh_end - &bpfilter_umh_start, + &info); if (err) return err; pr_info("Loaded bpfilter_umh pid %d\n", info.pid); diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S new file mode 100644 index 000000000000..40311d10d2f2 --- /dev/null +++ b/net/bpfilter/bpfilter_umh_blob.S @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + .section .init.rodata, "a" + .global bpfilter_umh_start +bpfilter_umh_start: + .incbin "net/bpfilter/bpfilter_umh" + .global bpfilter_umh_end +bpfilter_umh_end: diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index a04e1e88bf3a..50537ff961a7 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) if (ifr->ifr_qlen < 0) return -EINVAL; if (dev->tx_queue_len ^ ifr->ifr_qlen) { - unsigned int orig_len = dev->tx_queue_len; - - dev->tx_queue_len = ifr->ifr_qlen; - err = call_netdevice_notifiers( - NETDEV_CHANGE_TX_QUEUE_LEN, dev); - err = notifier_to_errno(err); - if (err) { - dev->tx_queue_len = orig_len; + err = dev_change_tx_queue_len(dev, ifr->ifr_qlen); + if (err) return err; - } } return 0; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 126ffc5bc630..f64aa13811ea 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->mark && r->mark != rule->mark) continue; + if (rule->suppress_ifgroup != -1 && + r->suppress_ifgroup != rule->suppress_ifgroup) + continue; + + if (rule->suppress_prefixlen != -1 && + r->suppress_prefixlen != rule->suppress_prefixlen) + continue; + if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; @@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; + if (rule->proto && r->proto != rule->proto) + continue; + if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) @@ -645,6 +656,73 @@ errout: return err; } +static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, + struct nlattr **tb, struct fib_rule *rule) +{ + struct fib_rule *r; + + list_for_each_entry(r, &ops->rules_list, list) { + if (r->action != rule->action) + continue; + + if (r->table != rule->table) + continue; + + if (r->pref != rule->pref) + continue; + + if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) + continue; + + if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) + continue; + + if (r->mark != rule->mark) + continue; + + if (r->suppress_ifgroup != rule->suppress_ifgroup) + continue; + + if (r->suppress_prefixlen != rule->suppress_prefixlen) + continue; + + if (r->mark_mask != rule->mark_mask) + continue; + + if (r->tun_id != rule->tun_id) + continue; + + if (r->fr_net != rule->fr_net) + continue; + + if (r->l3mdev != rule->l3mdev) + continue; + + if (!uid_eq(r->uid_range.start, rule->uid_range.start) || + !uid_eq(r->uid_range.end, rule->uid_range.end)) + continue; + + if (r->ip_proto != rule->ip_proto) + continue; + + if (r->proto != rule->proto) + continue; + + if (!fib_rule_port_range_compare(&r->sport_range, + &rule->sport_range)) + continue; + + if (!fib_rule_port_range_compare(&r->dport_range, + &rule->dport_range)) + continue; + + if (!ops->compare(r, frh, tb)) + continue; + return 1; + } + return 0; +} + int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && - rule_find(ops, frh, tb, rule, user_priority)) { + rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } diff --git a/net/core/filter.c b/net/core/filter.c index e7f12e9f598c..0ca6907d7efe 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4073,8 +4073,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + params->ifindex = dev->ifindex; - return dev->ifindex; + return 0; } #endif @@ -4098,7 +4099,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) - return 0; + return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; @@ -4123,7 +4124,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, tb = fib_get_table(net, tbid); if (unlikely(!tb)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { @@ -4135,8 +4136,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } - if (err || res.type != RTN_UNICAST) - return 0; + if (err) { + /* map fib lookup errors to RTN_ type */ + if (err == -EINVAL) + return BPF_FIB_LKUP_RET_BLACKHOLE; + if (err == -EHOSTUNREACH) + return BPF_FIB_LKUP_RET_UNREACHABLE; + if (err == -EACCES) + return BPF_FIB_LKUP_RET_PROHIBIT; + + return BPF_FIB_LKUP_RET_NOT_FWDED; + } + + if (res.type != RTN_UNICAST) + return BPF_FIB_LKUP_RET_NOT_FWDED; if (res.fi->fib_nhs > 1) fib_select_path(net, &res, &fl4, NULL); @@ -4144,19 +4157,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) - return 0; + return BPF_FIB_LKUP_RET_FRAG_NEEDED; } nh = &res.fi->fib_nh[res.nh_sel]; /* do not handle lwt encaps right now */ if (nh->nh_lwtstate) - return 0; + return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nh->nh_dev; - if (unlikely(!dev)) - return 0; - if (nh->nh_gw) params->ipv4_dst = nh->nh_gw; @@ -4166,10 +4176,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, * rcu_read_lock_bh is not needed here */ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); - if (neigh) - return bpf_fib_set_fwd_params(params, neigh, dev); + if (!neigh) + return BPF_FIB_LKUP_RET_NO_NEIGH; - return 0; + return bpf_fib_set_fwd_params(params, neigh, dev); } #endif @@ -4190,7 +4200,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -4198,7 +4208,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !net->ipv6.devconf_all->forwarding)) - return 0; + return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; @@ -4225,7 +4235,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict); } else { @@ -4238,11 +4248,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, } if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; + + if (unlikely(f6i->fib6_flags & RTF_REJECT)) { + switch (f6i->fib6_type) { + case RTN_BLACKHOLE: + return BPF_FIB_LKUP_RET_BLACKHOLE; + case RTN_UNREACHABLE: + return BPF_FIB_LKUP_RET_UNREACHABLE; + case RTN_PROHIBIT: + return BPF_FIB_LKUP_RET_PROHIBIT; + default: + return BPF_FIB_LKUP_RET_NOT_FWDED; + } + } - if (unlikely(f6i->fib6_flags & RTF_REJECT || - f6i->fib6_type != RTN_UNICAST)) - return 0; + if (f6i->fib6_type != RTN_UNICAST) + return BPF_FIB_LKUP_RET_NOT_FWDED; if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0) f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6, @@ -4252,11 +4274,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src); if (params->tot_len > mtu) - return 0; + return BPF_FIB_LKUP_RET_FRAG_NEEDED; } if (f6i->fib6_nh.nh_lwtstate) - return 0; + return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (f6i->fib6_flags & RTF_GATEWAY) *dst = f6i->fib6_nh.nh_gw; @@ -4270,10 +4292,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, */ neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, ndisc_hashfn, dst, dev); - if (neigh) - return bpf_fib_set_fwd_params(params, neigh, dev); + if (!neigh) + return BPF_FIB_LKUP_RET_NO_NEIGH; - return 0; + return bpf_fib_set_fwd_params(params, neigh, dev); } #endif @@ -4315,7 +4337,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); - int index = -EAFNOSUPPORT; + int rc = -EAFNOSUPPORT; if (plen < sizeof(*params)) return -EINVAL; @@ -4326,25 +4348,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: - index = bpf_ipv4_fib_lookup(net, params, flags, false); + rc = bpf_ipv4_fib_lookup(net, params, flags, false); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - index = bpf_ipv6_fib_lookup(net, params, flags, false); + rc = bpf_ipv6_fib_lookup(net, params, flags, false); break; #endif } - if (index > 0) { + if (!rc) { struct net_device *dev; - dev = dev_get_by_index_rcu(net, index); + dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) - index = 0; + rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; } - return index; + return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c642304f178c..eba8dae22c25 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5276,8 +5276,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, if (npages >= 1 << order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NOWARN, order); if (page) goto fill_page; diff --git a/net/core/sock.c b/net/core/sock.c index bcc41829a16d..9e8f65585b81 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot) rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, - prot->slab_flags, NULL); + SLAB_ACCOUNT | prot->slab_flags, + NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", @@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab) if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, - SLAB_HWCACHE_ALIGN | prot->slab_flags, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | + prot->slab_flags, prot->useroffset, prot->usersize, NULL); @@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab) kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, 0, + SLAB_ACCOUNT | prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..c9ec1603666b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -448,9 +448,7 @@ next_proto: out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1859c473b21a..6a7d980105f6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d06247ba08b2..af0a857d8352 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -265,8 +265,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; - int ret; u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + __le32 key[4]; + int ret, i; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) @@ -275,11 +276,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) - memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else - memset(user_key, 0, sizeof(user_key)); + memset(key, 0, sizeof(key)); rcu_read_unlock(); + for (i = 0; i < ARRAY_SIZE(key); i++) + user_key[i] = le32_to_cpu(key[i]); + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", user_key[0], user_key[1], user_key[2], user_key[3]); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); @@ -290,13 +294,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(net, NULL, user_key, + + for (i = 0; i < ARRAY_SIZE(user_key); i++) + key[i] = cpu_to_le32(user_key[i]); + + tcp_fastopen_reset_cipher(net, NULL, key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", - user_key[0], user_key[1], user_key[2], user_key[3], + user_key[0], user_key[1], user_key[2], user_key[3], (char *)tbl.data, ret); kfree(tbl.data); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 355d3dffd021..8e5522c6833a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -265,7 +265,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) * it is probably a retransmit. */ if (tp->ecn_flags & TCP_ECN_SEEN) - tcp_enter_quickack_mode(sk, 1); + tcp_enter_quickack_mode(sk, 2); break; case INET_ECN_CE: if (tcp_ca_needs_ecn(sk)) @@ -273,7 +273,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { /* Better not delay acks, sender can have a very low cwnd */ - tcp_enter_quickack_mode(sk, 1); + tcp_enter_quickack_mode(sk, 2); tp->ecn_flags |= TCP_ECN_DEMAND_CWR; } tp->ecn_flags |= TCP_ECN_SEEN; @@ -3181,6 +3181,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); + + /* If any of the cumulatively ACKed segments was + * retransmitted, non-SACK case cannot confirm that + * progress was due to original transmission due to + * lack of TCPCB_SACKED_ACKED bits even if some of + * the packets may have been never retransmitted. + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + flag &= ~FLAG_ORIG_SACK_ACKED; } else { int delta; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 92dc9e5a7ff3..69c54540d5b4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -394,7 +394,7 @@ unflush: out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c134286d6a41..91580c62bb86 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4528,6 +4528,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, u32 flags) { struct fib6_info *f6i; + u32 prio; f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, @@ -4536,13 +4537,15 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, if (!f6i) return -ENOENT; - if (f6i->fib6_metric != ifp->rt_priority) { + prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF; + if (f6i->fib6_metric != prio) { + /* delete old one */ + ip6_del_rt(dev_net(ifp->idev->dev), f6i); + /* add new one */ addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); - /* delete old one */ - ip6_del_rt(dev_net(ifp->idev->dev), f6i); } else { if (!expires) fib6_clean_expires(f6i); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e0332014c17..a452d99c9f52 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net) if (hdr == NULL) goto err_reg; - net->nf_frag.sysctl.frags_hdr = hdr; + net->nf_frag_frags_hdr = hdr; return 0; err_reg: @@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct ctl_table *table; - table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg; - unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr); + table = net->nf_frag_frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->nf_frag_frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 33fb35cbfac1..558fe8cc6d43 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void) return -ENOMEM; for_each_possible_cpu(cpu) { - tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL); + tfm = crypto_alloc_shash(algo->name, 0, 0); if (IS_ERR(tfm)) return PTR_ERR(tfm); p_tfm = per_cpu_ptr(algo->tfms, cpu); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 44b5dfe8727d..fa1f1e63a264 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4845,7 +4845,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, skb_reset_network_header(skb); skb_reset_mac_header(skb); + local_bh_disable(); __ieee80211_subif_start_xmit(skb, skb->dev, flags); + local_bh_enable(); return 0; } diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index d8383609fe28..510039862aa9 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -47,6 +47,8 @@ struct nf_conncount_tuple { struct hlist_node node; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; + int cpu; + u32 jiffies32; }; struct nf_conncount_rb { @@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head, return false; conn->tuple = *tuple; conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; hlist_add_head(&conn->node, head); return true; } EXPORT_SYMBOL_GPL(nf_conncount_add); +static const struct nf_conntrack_tuple_hash * +find_or_evict(struct net *net, struct nf_conncount_tuple *conn) +{ + const struct nf_conntrack_tuple_hash *found; + unsigned long a, b; + int cpu = raw_smp_processor_id(); + __s32 age; + + found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); + if (found) + return found; + b = conn->jiffies32; + a = (u32)jiffies; + + /* conn might have been added just before by another cpu and + * might still be unconfirmed. In this case, nf_conntrack_find() + * returns no result. Thus only evict if this cpu added the + * stale entry or if the entry is older than two jiffies. + */ + age = a - b; + if (conn->cpu == cpu || age >= 2) { + hlist_del(&conn->node); + kmem_cache_free(conncount_conn_cachep, conn); + return ERR_PTR(-ENOENT); + } + + return ERR_PTR(-EAGAIN); +} + unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone, @@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn; - struct hlist_node *n; struct nf_conn *found_ct; + struct hlist_node *n; unsigned int length = 0; *addit = tuple ? true : false; /* check the saved connections */ hlist_for_each_entry_safe(conn, n, head, node) { - found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); - if (found == NULL) { - hlist_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + found = find_or_evict(net, conn); + if (IS_ERR(found)) { + /* Not found, but might be about to be confirmed */ + if (PTR_ERR(found) == -EAGAIN) { + length++; + if (!tuple) + continue; + + if (nf_ct_tuple_equal(&conn->tuple, tuple) && + nf_ct_zone_id(&conn->zone, conn->zone.dir) == + nf_ct_zone_id(zone, zone->dir)) + *addit = false; + } continue; } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 551a1eddf0fa..a75b11c39312 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) nf_ct_expect_iterate_destroy(expect_iter_me, NULL); nf_ct_iterate_destroy(unhelp, me); + + /* Maybe someone has gotten the helper already when unhelp above. + * So need to wait it. + */ + synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 426457047578..a61d6df6e5f6 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, if (write) { struct ctl_table tmp = *table; + /* proc_dostring() can append to existing strings, so we need to + * initialize it as an empty string. + */ + buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) @@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { + struct ctl_table tmp = *table; + + tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) - table->data = "NONE"; + strlcpy(buf, "NONE", sizeof(buf)); else - table->data = logger->name; - r = proc_dostring(table, write, buffer, lenp, ppos); + strlcpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); + r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4ccd2988f9db..ea4ba551abb2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl, static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { [NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) }, [NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) }, + [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 }, + [NFQA_CFG_MASK] = { .type = NLA_U32 }, + [NFQA_CFG_FLAGS] = { .type = NLA_U32 }, }; static const struct nf_queue_handler nfqh = { diff --git a/net/rds/connection.c b/net/rds/connection.c index abef75da89a7..cfb05953b0e5 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -659,11 +659,19 @@ static void rds_conn_info(struct socket *sock, unsigned int len, int rds_conn_init(void) { + int ret; + + ret = rds_loop_net_init(); /* register pernet callback */ + if (ret) + return ret; + rds_conn_slab = kmem_cache_create("rds_connection", sizeof(struct rds_connection), 0, 0, NULL); - if (!rds_conn_slab) + if (!rds_conn_slab) { + rds_loop_net_exit(); return -ENOMEM; + } rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info); rds_info_register_func(RDS_INFO_SEND_MESSAGES, @@ -676,6 +684,7 @@ int rds_conn_init(void) void rds_conn_exit(void) { + rds_loop_net_exit(); /* unregister pernet callback */ rds_loop_exit(); WARN_ON(!hlist_empty(rds_conn_hash)); diff --git a/net/rds/loop.c b/net/rds/loop.c index dac6218a460e..feea1f96ee2a 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -33,6 +33,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/in.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include "rds_single_path.h" #include "rds.h" @@ -40,6 +42,17 @@ static DEFINE_SPINLOCK(loop_conns_lock); static LIST_HEAD(loop_conns); +static atomic_t rds_loop_unloading = ATOMIC_INIT(0); + +static void rds_loop_set_unloading(void) +{ + atomic_set(&rds_loop_unloading, 1); +} + +static bool rds_loop_is_unloading(struct rds_connection *conn) +{ + return atomic_read(&rds_loop_unloading) != 0; +} /* * This 'loopback' transport is a special case for flows that originate @@ -165,6 +178,8 @@ void rds_loop_exit(void) struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); + rds_loop_set_unloading(); + synchronize_rcu(); /* avoid calling conn_destroy with irqs off */ spin_lock_irq(&loop_conns_lock); list_splice(&loop_conns, &tmp_list); @@ -177,6 +192,46 @@ void rds_loop_exit(void) } } +static void rds_loop_kill_conns(struct net *net) +{ + struct rds_loop_connection *lc, *_lc; + LIST_HEAD(tmp_list); + + spin_lock_irq(&loop_conns_lock); + list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) { + struct net *c_net = read_pnet(&lc->conn->c_net); + + if (net != c_net) + continue; + list_move_tail(&lc->loop_node, &tmp_list); + } + spin_unlock_irq(&loop_conns_lock); + + list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { + WARN_ON(lc->conn->c_passive); + rds_conn_destroy(lc->conn); + } +} + +static void __net_exit rds_loop_exit_net(struct net *net) +{ + rds_loop_kill_conns(net); +} + +static struct pernet_operations rds_loop_net_ops = { + .exit = rds_loop_exit_net, +}; + +int rds_loop_net_init(void) +{ + return register_pernet_device(&rds_loop_net_ops); +} + +void rds_loop_net_exit(void) +{ + unregister_pernet_device(&rds_loop_net_ops); +} + /* * This is missing .xmit_* because loop doesn't go through generic * rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and @@ -194,4 +249,5 @@ struct rds_transport rds_loop_transport = { .inc_free = rds_loop_inc_free, .t_name = "loopback", .t_type = RDS_TRANS_LOOP, + .t_unloading = rds_loop_is_unloading, }; diff --git a/net/rds/loop.h b/net/rds/loop.h index 469fa4b2da4f..bbc8cdd030df 100644 --- a/net/rds/loop.h +++ b/net/rds/loop.h @@ -5,6 +5,8 @@ /* loop.c */ extern struct rds_transport rds_loop_transport; +int rds_loop_net_init(void); +void rds_loop_net_exit(void); void rds_loop_exit(void); #endif diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 973b4471b532..e017b6a4452b 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group */ static void smc_tcp_listen_work(struct work_struct *); +static void smc_connect_work(struct work_struct *); static void smc_set_keepalive(struct sock *sk, int val) { @@ -122,6 +123,12 @@ static int smc_release(struct socket *sock) goto out; smc = smc_sk(sk); + + /* cleanup for a dangling non-blocking connect */ + flush_work(&smc->connect_work); + kfree(smc->connect_info); + smc->connect_info = NULL; + if (sk->sk_state == SMC_LISTEN) /* smc_close_non_accepted() is called and acquires * sock lock for child sockets again @@ -186,6 +193,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_protocol = protocol; smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); + INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); INIT_LIST_HEAD(&smc->accept_q); spin_lock_init(&smc->accept_q_lock); @@ -576,6 +584,35 @@ static int __smc_connect(struct smc_sock *smc) return 0; } +static void smc_connect_work(struct work_struct *work) +{ + struct smc_sock *smc = container_of(work, struct smc_sock, + connect_work); + int rc; + + lock_sock(&smc->sk); + rc = kernel_connect(smc->clcsock, &smc->connect_info->addr, + smc->connect_info->alen, smc->connect_info->flags); + if (smc->clcsock->sk->sk_err) { + smc->sk.sk_err = smc->clcsock->sk->sk_err; + goto out; + } + if (rc < 0) { + smc->sk.sk_err = -rc; + goto out; + } + + rc = __smc_connect(smc); + if (rc < 0) + smc->sk.sk_err = -rc; + +out: + smc->sk.sk_state_change(&smc->sk); + kfree(smc->connect_info); + smc->connect_info = NULL; + release_sock(&smc->sk); +} + static int smc_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { @@ -605,15 +642,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, smc_copy_sock_settings_to_clc(smc); tcp_sk(smc->clcsock->sk)->syn_smc = 1; - rc = kernel_connect(smc->clcsock, addr, alen, flags); - if (rc) - goto out; + if (flags & O_NONBLOCK) { + if (smc->connect_info) { + rc = -EALREADY; + goto out; + } + smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL); + if (!smc->connect_info) { + rc = -ENOMEM; + goto out; + } + smc->connect_info->alen = alen; + smc->connect_info->flags = flags ^ O_NONBLOCK; + memcpy(&smc->connect_info->addr, addr, alen); + schedule_work(&smc->connect_work); + rc = -EINPROGRESS; + } else { + rc = kernel_connect(smc->clcsock, addr, alen, flags); + if (rc) + goto out; - rc = __smc_connect(smc); - if (rc < 0) - goto out; - else - rc = 0; /* success cases including fallback */ + rc = __smc_connect(smc); + if (rc < 0) + goto out; + else + rc = 0; /* success cases including fallback */ + } out: release_sock(sk); @@ -1279,40 +1333,18 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask = 0; struct smc_sock *smc; - int rc; if (!sk) return EPOLLNVAL; smc = smc_sk(sock->sk); - sock_hold(sk); - lock_sock(sk); if ((sk->sk_state == SMC_INIT) || smc->use_fallback) { /* delegate to CLC child sock */ - release_sock(sk); mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); - lock_sock(sk); sk->sk_err = smc->clcsock->sk->sk_err; - if (sk->sk_err) { + if (sk->sk_err) mask |= EPOLLERR; - } else { - /* if non-blocking connect finished ... */ - if (sk->sk_state == SMC_INIT && - mask & EPOLLOUT && - smc->clcsock->sk->sk_state != TCP_CLOSE) { - rc = __smc_connect(smc); - if (rc < 0) - mask |= EPOLLERR; - /* success cases including fallback */ - mask |= EPOLLOUT | EPOLLWRNORM; - } - } } else { - if (sk->sk_state != SMC_CLOSED) { - release_sock(sk); - sock_poll_wait(file, sk_sleep(sk), wait); - lock_sock(sk); - } if (sk->sk_err) mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || @@ -1340,8 +1372,6 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, mask |= EPOLLPRI; } - release_sock(sk); - sock_put(sk); return mask; } diff --git a/net/smc/smc.h b/net/smc/smc.h index 51ae1f10d81a..d7ca26570482 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -187,11 +187,19 @@ struct smc_connection { struct work_struct close_work; /* peer sent some closing */ }; +struct smc_connect_info { + int flags; + int alen; + struct sockaddr addr; +}; + struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ + struct smc_connect_info *connect_info; /* connect address & flags */ + struct work_struct connect_work; /* handle non-blocking connect*/ struct work_struct tcp_listen_work;/* handle tcp socket accepts */ struct work_struct smc_listen_work;/* prepare new accept socket */ struct list_head accept_q; /* sockets to be accepted */ diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 373836615c57..625acb27efcc 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -35,7 +35,6 @@ struct _strp_msg { */ struct strp_msg strp; int accum_len; - int early_eaten; }; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) @@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, head = strp->skb_head; if (head) { /* Message already in progress */ - - stm = _strp_msg(head); - if (unlikely(stm->early_eaten)) { - /* Already some number of bytes on the receive sock - * data saved in skb_head, just indicate they - * are consumed. - */ - eaten = orig_len <= stm->early_eaten ? - orig_len : stm->early_eaten; - stm->early_eaten -= eaten; - - return eaten; - } - if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we @@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, } stm->accum_len += cand_len; + eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c7bbe5f0aae8..4eece06be1e7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6231,7 +6231,7 @@ do { \ nl80211_check_s32); /* * Check HT operation mode based on - * IEEE 802.11 2012 8.4.2.59 HT Operation element. + * IEEE 802.11-2016 9.4.2.57 HT Operation element. */ if (tb[NL80211_MESHCONF_HT_OPMODE]) { ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]); @@ -6241,22 +6241,9 @@ do { \ IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) return -EINVAL; - if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) && - (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) - return -EINVAL; + /* NON_HT_STA bit is reserved, but some programs set it */ + ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; - switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) { - case IEEE80211_HT_OP_MODE_PROTECTION_NONE: - case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: - if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT) - return -EINVAL; - break; - case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: - case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: - if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) - return -EINVAL; - break; - } cfg->ht_opmode = ht_opmode; mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1)); } @@ -10962,9 +10949,12 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - nl80211_packet_pattern_policy, - info->extack); + err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, + info->extack); + if (err) + goto error; + err = -EINVAL; if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) @@ -11213,8 +11203,11 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - nl80211_packet_pattern_policy, NULL); + err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, NULL); + if (err) + return err; + if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) return -EINVAL; diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c index 6673cdb9f55c..a7e94e7ff87d 100644 --- a/samples/bpf/xdp_fwd_kern.c +++ b/samples/bpf/xdp_fwd_kern.c @@ -48,9 +48,9 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) struct ethhdr *eth = data; struct ipv6hdr *ip6h; struct iphdr *iph; - int out_index; u16 h_proto; u64 nh_off; + int rc; nh_off = sizeof(*eth); if (data + nh_off > data_end) @@ -101,7 +101,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) fib_params.ifindex = ctx->ingress_ifindex; - out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); + rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); /* verify egress index has xdp support * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with @@ -109,7 +109,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) * NOTE: without verification that egress index supports XDP * forwarding packets are dropped. */ - if (out_index > 0) { + if (rc == 0) { if (h_proto == htons(ETH_P_IP)) ip_decrease_ttl(iph); else if (h_proto == htons(ETH_P_IPV6)) @@ -117,7 +117,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); memcpy(eth->h_source, fib_params.smac, ETH_ALEN); - return bpf_redirect_map(&tx_port, out_index, 0); + return bpf_redirect_map(&tx_port, fib_params.ifindex, 0); } return XDP_PASS; diff --git a/scripts/cc-can-link.sh b/scripts/cc-can-link.sh index 208eb2825dab..6efcead31989 100755 --- a/scripts/cc-can-link.sh +++ b/scripts/cc-can-link.sh @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y" +cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 #include <stdio.h> int main(void) { diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 05f42a46d6ed..959aa53ab678 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -694,15 +694,19 @@ static int do_load(int argc, char **argv) return -1; } - if (do_pin_fd(prog_fd, argv[1])) { - p_err("failed to pin program"); - return -1; - } + if (do_pin_fd(prog_fd, argv[1])) + goto err_close_obj; if (json_output) jsonw_null(json_wtr); + bpf_object__close(obj); + return 0; + +err_close_obj: + bpf_object__close(obj); + return -1; } static int do_help(int argc, char **argv) diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 7eb613ffef55..b4994a94968b 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -6,6 +6,7 @@ CONFIG_TEST_BPF=m CONFIG_CGROUP_BPF=y CONFIG_NETDEVSIM=m CONFIG_NET_CLS_ACT=y +CONFIG_NET_SCHED=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_IPIP=y CONFIG_IPV6=y diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index 35669ccd4d23..9df0d2ac45f8 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -1,6 +1,15 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +msg="skip all tests:" +if [ "$(id -u)" != "0" ]; then + echo $msg please run this as root >&2 + exit $ksft_skip +fi + SRC_TREE=../../../../ test_run() diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh index ce2e15e4f976..677686198df3 100755 --- a/tools/testing/selftests/bpf/test_lirc_mode2.sh +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -1,6 +1,15 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +msg="skip all tests:" +if [ $UID != 0 ]; then + echo $msg please run this as root >&2 + exit $ksft_skip +fi + GREEN='\033[0;92m' RED='\033[0;31m' NC='\033[0m' # No Color diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 1c77994b5e71..270fa8f49573 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -21,6 +21,15 @@ # An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this # datagram can be read on NS6 when binding to fb00::6. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +msg="skip all tests:" +if [ $UID != 0 ]; then + echo $msg please run this as root >&2 + exit $ksft_skip +fi + TMP_FILE="/tmp/selftest_lwt_seg6local.txt" cleanup() diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 05c8cb71724a..9e78df207919 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1413,18 +1413,12 @@ out: int main(int argc, char **argv) { - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; int iov_count = 1, length = 1024, rate = 1; struct sockmap_options options = {0}; int opt, longindex, err, cg_fd = 0; char *bpf_file = BPF_SOCKMAP_FILENAME; int test = PING_PONG; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (argc < 2) return test_suite(); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 78245d60d8bc..78245d60d8bc 100644..100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh |