diff options
44 files changed, 571 insertions, 208 deletions
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 3cce8ea6b139..db2383cb1df9 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -844,6 +844,11 @@ igmp_max_memberships - INTEGER conf/all/* is special, changes the settings for all interfaces +igmp_qrv - INTEGER + Controls the IGMP query robustness variable (see RFC2236 8.1). + Default: 2 (as specified by RFC2236 8.1) + Minimum: 1 (as specified by RFC6636 4.5) + log_martians - BOOLEAN Log packets with impossible addresses to kernel log. log_martians for the interface will be enabled if at least one of @@ -1152,6 +1157,11 @@ anycast_src_echo_reply - BOOLEAN FALSE: disabled Default: FALSE +mld_qrv - INTEGER + Controls the MLD query robustness variable (see RFC3810 9.1). + Default: 2 (as specified by RFC3810 9.1) + Minimum: 1 (as specified by RFC6636 4.5) + IPv6 Fragmentation: ip6frag_high_thresh - INTEGER diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index a37b989a2f91..a76623bcf722 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -930,5 +930,6 @@ void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) module_free(NULL, fp->bpf_func); - kfree(fp); + + bpf_prog_unlock_free(fp); } diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 05a56619ece2..cfa83cf2447d 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1427,5 +1427,6 @@ void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) module_free(NULL, fp->bpf_func); - kfree(fp); + + bpf_prog_unlock_free(fp); } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 3afa6f4c1957..40c53ff59124 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -697,5 +697,6 @@ void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) module_free(NULL, fp->bpf_func); - kfree(fp); + + bpf_prog_unlock_free(fp); } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 61e45b7c04d7..f2833c5b218a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -887,5 +887,5 @@ void bpf_jit_free(struct bpf_prog *fp) module_free(NULL, header); free_filter: - kfree(fp); + bpf_prog_unlock_free(fp); } diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 1f76c22a6a75..f7a736b645e8 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -812,5 +812,6 @@ void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) module_free(NULL, fp->bpf_func); - kfree(fp); + + bpf_prog_unlock_free(fp); } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index b08a98c59530..39ccfbb4a723 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -972,23 +972,17 @@ out: kfree(addrs); } -static void bpf_jit_free_deferred(struct work_struct *work) +void bpf_jit_free(struct bpf_prog *fp) { - struct bpf_prog *fp = container_of(work, struct bpf_prog, work); unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; struct bpf_binary_header *header = (void *)addr; + if (!fp->jited) + goto free_filter; + set_memory_rw(addr, header->pages); module_free(NULL, header); - kfree(fp); -} -void bpf_jit_free(struct bpf_prog *fp) -{ - if (fp->jited) { - INIT_WORK(&fp->work, bpf_jit_free_deferred); - schedule_work(&fp->work); - } else { - kfree(fp); - } +free_filter: + bpf_prog_unlock_free(fp); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index cc25a3a9e7cf..caade30820d5 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -271,7 +271,6 @@ #define DMA_PBL_X8_DISABLE 0x00 #define DMA_PBL_X8_ENABLE 0x01 - /* MAC register offsets */ #define MAC_TCR 0x0000 #define MAC_RCR 0x0004 @@ -792,7 +791,6 @@ #define MTL_Q_DISABLED 0x00 #define MTL_Q_ENABLED 0x02 - /* MTL traffic class register offsets * Multiple traffic classes can be active. The first class has registers * that begin at 0x1100. Each subsequent queue has registers that @@ -815,7 +813,6 @@ #define MTL_TSA_SP 0x00 #define MTL_TSA_ETS 0x02 - /* PCS MMD select register offset * The MMD select register is used for accessing PCS registers * when the underlying APB3 interface is using indirect addressing. @@ -825,7 +822,6 @@ */ #define PCS_MMD_SELECT 0xff - /* Descriptor/Packet entry bit positions and sizes */ #define RX_PACKET_ERRORS_CRC_INDEX 2 #define RX_PACKET_ERRORS_CRC_WIDTH 1 @@ -929,7 +925,6 @@ #define MDIO_AN_COMP_STAT 0x0030 #endif - /* Bit setting and getting macros * The get macro will extract the current bit field value from within * the variable @@ -957,7 +952,6 @@ do { \ ((0x1 << (_width)) - 1)) << (_index))); \ } while (0) - /* Bit setting and getting macros based on register fields * The get macro uses the bit field definitions formed using the input * names to extract the current bit field value from within the @@ -986,7 +980,6 @@ do { \ _prefix##_##_field##_INDEX, \ _prefix##_##_field##_WIDTH, (_val)) - /* Macros for reading or writing registers * The ioread macros will get bit fields or full values using the * register definitions formed using the input names @@ -1014,7 +1007,6 @@ do { \ XGMAC_IOWRITE((_pdata), _reg, reg_val); \ } while (0) - /* Macros for reading or writing MTL queue or traffic class registers * Similar to the standard read and write macros except that the * base register value is calculated by the queue or traffic class number @@ -1041,7 +1033,6 @@ do { \ XGMAC_MTL_IOWRITE((_pdata), (_n), _reg, reg_val); \ } while (0) - /* Macros for reading or writing DMA channel registers * Similar to the standard read and write macros except that the * base register value is obtained from the ring @@ -1066,7 +1057,6 @@ do { \ XGMAC_DMA_IOWRITE((_channel), _reg, reg_val); \ } while (0) - /* Macros for building, reading or writing register values or bits * within the register values of XPCS registers. */ @@ -1076,7 +1066,6 @@ do { \ #define XPCS_IOREAD(_pdata, _off) \ ioread32((_pdata)->xpcs_regs + (_off)) - /* Macros for building, reading or writing register values or bits * using MDIO. Different from above because of the use of standardized * Linux include values. No shifting is performed with the bit diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c index 7d6a49b24321..8a50b01c2686 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c @@ -120,7 +120,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static int xgbe_dcb_ieee_getets(struct net_device *netdev, struct ieee_ets *ets) { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 346592dca33c..978f9ec961ae 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -121,7 +121,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static ssize_t xgbe_common_read(char __user *buffer, size_t count, loff_t *ppos, unsigned int value) { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c index 1c5d62e8dab6..6fc5da01437d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c @@ -117,7 +117,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static void xgbe_unmap_skb(struct xgbe_prv_data *, struct xgbe_ring_data *); static void xgbe_free_ring(struct xgbe_prv_data *pdata, @@ -524,11 +523,8 @@ static void xgbe_realloc_skb(struct xgbe_channel *channel) /* Allocate skb & assign to each rdesc */ skb = dev_alloc_skb(pdata->rx_buf_size); - if (skb == NULL) { - netdev_alert(pdata->netdev, - "failed to allocate skb\n"); + if (skb == NULL) break; - } skb_dma = dma_map_single(pdata->dev, skb->data, pdata->rx_buf_size, DMA_FROM_DEVICE); if (dma_mapping_error(pdata->dev, skb_dma)) { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index edaca4496264..3be98e505001 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -122,7 +122,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static unsigned int xgbe_usec_to_riwt(struct xgbe_prv_data *pdata, unsigned int usec) { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index dc84f7193c2d..847da66d1548 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -126,7 +126,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static int xgbe_poll(struct napi_struct *, int); static void xgbe_set_rx_mode(struct net_device *); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index a076aca138a1..2289526b6f1c 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -121,7 +121,6 @@ #include "xgbe.h" #include "xgbe-common.h" - struct xgbe_stats { char stat_string[ETH_GSTRING_LEN]; int stat_size; @@ -173,6 +172,7 @@ static const struct xgbe_stats xgbe_gstring_stats[] = { XGMAC_MMC_STAT("rx_watchdog_errors", rxwatchdogerror), XGMAC_MMC_STAT("rx_pause_frames", rxpauseframes), }; + #define XGBE_STATS_COUNT ARRAY_SIZE(xgbe_gstring_stats) static void xgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 8aa6a9353f7b..984161d4ffc9 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -128,7 +128,6 @@ #include "xgbe.h" #include "xgbe-common.h" - MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(XGBE_DRV_VERSION); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 6d2221e023f4..363b210560f3 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -123,7 +123,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static int xgbe_mdio_read(struct mii_bus *mii, int prtad, int mmd_reg) { struct xgbe_prv_data *pdata = mii->priv; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c index 37e64cfa5718..a1bf9d1cdae1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c @@ -122,7 +122,6 @@ #include "xgbe.h" #include "xgbe-common.h" - static cycle_t xgbe_cc_read(const struct cyclecounter *cc) { struct xgbe_prv_data *pdata = container_of(cc, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 07bf70a82908..84fe34ce5571 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -128,7 +128,6 @@ #include <linux/net_tstamp.h> #include <net/dcbnl.h> - #define XGBE_DRV_NAME "amd-xgbe" #define XGBE_DRV_VERSION "1.0.0-a" #define XGBE_DRV_DESC "AMD 10 Gigabit Ethernet Driver" @@ -198,7 +197,6 @@ ((_ring)->rdata + \ ((_idx) & ((_ring)->rdesc_count - 1))) - /* Default coalescing parameters */ #define XGMAC_INIT_DMA_TX_USECS 50 #define XGMAC_INIT_DMA_TX_FRAMES 25 diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 8f91de169663..662cf2222873 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1071,16 +1071,19 @@ static void bcm_sysport_adj_link(struct net_device *dev) if (!phydev->pause) cmd_bits |= CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE; - if (changed) { + if (!changed) + return; + + if (phydev->link) { reg = umac_readl(priv, UMAC_CMD); reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | CMD_HD_EN | CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE); reg |= cmd_bits; umac_writel(priv, reg, UMAC_CMD); - - phy_print_status(priv->phydev); } + + phy_print_status(priv->phydev); } static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 962510f391df..5ba5ad071bb6 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -186,6 +186,7 @@ struct enic { ____cacheline_aligned struct vnic_cq cq[ENIC_CQ_MAX]; unsigned int cq_count; struct enic_rfs_flw_tbl rfs_h; + u32 rx_copybreak; }; static inline struct device *enic_get_dev(struct enic *enic) diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 523c9ceb04c0..85173d620758 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -379,6 +379,43 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return ret; } +static int enic_get_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, void *data) +{ + struct enic *enic = netdev_priv(dev); + int ret = 0; + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = enic->rx_copybreak; + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int enic_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct enic *enic = netdev_priv(dev); + int ret = 0; + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + enic->rx_copybreak = *(u32 *)data; + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + static const struct ethtool_ops enic_ethtool_ops = { .get_settings = enic_get_settings, .get_drvinfo = enic_get_drvinfo, @@ -391,6 +428,8 @@ static const struct ethtool_ops enic_ethtool_ops = { .get_coalesce = enic_get_coalesce, .set_coalesce = enic_set_coalesce, .get_rxnfc = enic_get_rxnfc, + .get_tunable = enic_get_tunable, + .set_tunable = enic_set_tunable, }; void enic_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index c8832bc1c5f7..929bfe70080a 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -66,6 +66,8 @@ #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN 0x0044 /* enet dynamic vnic */ #define PCI_DEVICE_ID_CISCO_VIC_ENET_VF 0x0071 /* enet SRIOV VF */ +#define RX_COPYBREAK_DEFAULT 256 + /* Supported devices */ static const struct pci_device_id enic_id_table[] = { { PCI_VDEVICE(CISCO, PCI_DEVICE_ID_CISCO_VIC_ENET) }, @@ -924,6 +926,7 @@ static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf) pci_unmap_single(enic->pdev, buf->dma_addr, buf->len, PCI_DMA_FROMDEVICE); dev_kfree_skb_any(buf->os_buf); + buf->os_buf = NULL; } static int enic_rq_alloc_buf(struct vnic_rq *rq) @@ -934,7 +937,24 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq) unsigned int len = netdev->mtu + VLAN_ETH_HLEN; unsigned int os_buf_index = 0; dma_addr_t dma_addr; + struct vnic_rq_buf *buf = rq->to_use; + + if (buf->os_buf) { + buf = buf->next; + rq->to_use = buf; + rq->ring.desc_avail--; + if ((buf->index & VNIC_RQ_RETURN_RATE) == 0) { + /* Adding write memory barrier prevents compiler and/or + * CPU reordering, thus avoiding descriptor posting + * before descriptor is initialized. Otherwise, hardware + * can read stale descriptor fields. + */ + wmb(); + iowrite32(buf->index, &rq->ctrl->posted_index); + } + return 0; + } skb = netdev_alloc_skb_ip_align(netdev, len); if (!skb) return -ENOMEM; @@ -957,6 +977,25 @@ static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size, pkt_size->small_pkt_bytes_cnt += pkt_len; } +static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb, + struct vnic_rq_buf *buf, u16 len) +{ + struct enic *enic = netdev_priv(netdev); + struct sk_buff *new_skb; + + if (len > enic->rx_copybreak) + return false; + new_skb = netdev_alloc_skb_ip_align(netdev, len); + if (!new_skb) + return false; + pci_dma_sync_single_for_cpu(enic->pdev, buf->dma_addr, len, + DMA_FROM_DEVICE); + memcpy(new_skb->data, (*skb)->data, len); + *skb = new_skb; + + return true; +} + static void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc, struct vnic_rq_buf *buf, int skipped, void *opaque) @@ -978,9 +1017,6 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, return; skb = buf->os_buf; - prefetch(skb->data - NET_IP_ALIGN); - pci_unmap_single(enic->pdev, buf->dma_addr, - buf->len, PCI_DMA_FROMDEVICE); cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &type, &color, &q_number, &completed_index, @@ -1011,6 +1047,13 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, /* Good receive */ + if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) { + buf->os_buf = NULL; + pci_unmap_single(enic->pdev, buf->dma_addr, buf->len, + PCI_DMA_FROMDEVICE); + } + prefetch(skb->data - NET_IP_ALIGN); + skb_put(skb, bytes_written); skb->protocol = eth_type_trans(skb, netdev); skb_record_rx_queue(skb, q_number); @@ -2531,6 +2574,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(dev, "Cannot register net device, aborting\n"); goto err_out_dev_deinit; } + enic->rx_copybreak = RX_COPYBREAK_DEFAULT; return 0; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 999fb72688d2..03b409988566 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2232,18 +2232,24 @@ static int cpsw_probe(struct platform_device *pdev) } while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) { - for (i = res->start; i <= res->end; i++) { - if (devm_request_irq(&pdev->dev, i, cpsw_interrupt, 0, - dev_name(&pdev->dev), priv)) { - dev_err(priv->dev, "error attaching irq\n"); - goto clean_ale_ret; - } - priv->irqs_table[k] = i; - priv->num_irqs = k + 1; + if (k >= ARRAY_SIZE(priv->irqs_table)) { + ret = -EINVAL; + goto clean_ale_ret; } + + ret = devm_request_irq(&pdev->dev, res->start, cpsw_interrupt, + 0, dev_name(&pdev->dev), priv); + if (ret < 0) { + dev_err(priv->dev, "error attaching irq (%d)\n", ret); + goto clean_ale_ret; + } + + priv->irqs_table[k] = res->start; k++; } + priv->num_irqs = k; + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; ndev->netdev_ops = &cpsw_netdev_ops; diff --git a/drivers/net/phy/amd-xgbe-phy.c b/drivers/net/phy/amd-xgbe-phy.c index f3230eef41fd..4e1f7f734d27 100644 --- a/drivers/net/phy/amd-xgbe-phy.c +++ b/drivers/net/phy/amd-xgbe-phy.c @@ -75,7 +75,6 @@ #include <linux/of_device.h> #include <linux/uaccess.h> - MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION("1.0.0-a"); @@ -100,9 +99,11 @@ MODULE_DESCRIPTION("AMD 10GbE (amd-xgbe) PHY driver"); #ifndef MDIO_PMA_10GBR_PMD_CTRL #define MDIO_PMA_10GBR_PMD_CTRL 0x0096 #endif + #ifndef MDIO_PMA_10GBR_FEC_CTRL #define MDIO_PMA_10GBR_FEC_CTRL 0x00ab #endif + #ifndef MDIO_AN_XNP #define MDIO_AN_XNP 0x0016 #endif @@ -110,14 +111,23 @@ MODULE_DESCRIPTION("AMD 10GbE (amd-xgbe) PHY driver"); #ifndef MDIO_AN_INTMASK #define MDIO_AN_INTMASK 0x8001 #endif + #ifndef MDIO_AN_INT #define MDIO_AN_INT 0x8002 #endif +#ifndef MDIO_AN_KR_CTRL +#define MDIO_AN_KR_CTRL 0x8003 +#endif + #ifndef MDIO_CTRL1_SPEED1G #define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100) #endif +#ifndef MDIO_KR_CTRL_PDETECT +#define MDIO_KR_CTRL_PDETECT 0x01 +#endif + /* SerDes integration register offsets */ #define SIR0_KR_RT_1 0x002c #define SIR0_STATUS 0x0040 @@ -161,7 +171,6 @@ MODULE_DESCRIPTION("AMD 10GbE (amd-xgbe) PHY driver"); #define SPEED_1000_TXAMP 0xf #define SPEED_1000_WORD 0x1 - /* SerDes RxTx register offsets */ #define RXTX_REG20 0x0050 #define RXTX_REG114 0x01c8 @@ -255,7 +264,6 @@ do { \ XSIR1_IOWRITE((_priv), _reg, reg_val); \ } while (0) - /* Macros for reading or writing SerDes RxTx registers * The ioread macros will get bit fields or full values using the * register definitions formed using the input names @@ -283,7 +291,6 @@ do { \ XRXTX_IOWRITE((_priv), _reg, reg_val); \ } while (0) - enum amd_xgbe_phy_an { AMD_XGBE_AN_READY = 0, AMD_XGBE_AN_START, @@ -331,7 +338,6 @@ struct amd_xgbe_phy_priv { /* Maintain link status for re-starting auto-negotiation */ unsigned int link; - enum amd_xgbe_phy_mode mode; unsigned int speed_set; /* Auto-negotiation state machine support */ @@ -342,6 +348,7 @@ struct amd_xgbe_phy_priv { enum amd_xgbe_phy_rx kx_state; struct work_struct an_work; struct workqueue_struct *an_workqueue; + unsigned int parallel_detect; }; static int amd_xgbe_an_enable_kr_training(struct phy_device *phydev) @@ -468,8 +475,6 @@ static int amd_xgbe_phy_xgmii_mode(struct phy_device *phydev) amd_xgbe_phy_serdes_complete_ratechange(phydev); - priv->mode = AMD_XGBE_MODE_KR; - return 0; } @@ -518,8 +523,6 @@ static int amd_xgbe_phy_gmii_2500_mode(struct phy_device *phydev) amd_xgbe_phy_serdes_complete_ratechange(phydev); - priv->mode = AMD_XGBE_MODE_KX; - return 0; } @@ -568,18 +571,43 @@ static int amd_xgbe_phy_gmii_mode(struct phy_device *phydev) amd_xgbe_phy_serdes_complete_ratechange(phydev); - priv->mode = AMD_XGBE_MODE_KX; + return 0; +} + +static int amd_xgbe_phy_cur_mode(struct phy_device *phydev, + enum amd_xgbe_phy_mode *mode) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2); + if (ret < 0) + return ret; + + if ((ret & MDIO_PCS_CTRL2_TYPE) == MDIO_PCS_CTRL2_10GBR) + *mode = AMD_XGBE_MODE_KR; + else + *mode = AMD_XGBE_MODE_KX; return 0; } +static bool amd_xgbe_phy_in_kr_mode(struct phy_device *phydev) +{ + enum amd_xgbe_phy_mode mode; + + if (amd_xgbe_phy_cur_mode(phydev, &mode)) + return false; + + return (mode == AMD_XGBE_MODE_KR); +} + static int amd_xgbe_phy_switch_mode(struct phy_device *phydev) { struct amd_xgbe_phy_priv *priv = phydev->priv; int ret; /* If we are in KR switch to KX, and vice-versa */ - if (priv->mode == AMD_XGBE_MODE_KR) { + if (amd_xgbe_phy_in_kr_mode(phydev)) { if (priv->speed_set == AMD_XGBE_PHY_SPEEDSET_1000_10000) ret = amd_xgbe_phy_gmii_mode(phydev); else @@ -591,27 +619,31 @@ static int amd_xgbe_phy_switch_mode(struct phy_device *phydev) return ret; } -static enum amd_xgbe_phy_an amd_xgbe_an_switch_mode(struct phy_device *phydev) +static int amd_xgbe_phy_set_mode(struct phy_device *phydev, + enum amd_xgbe_phy_mode mode) { + enum amd_xgbe_phy_mode cur_mode; int ret; - ret = amd_xgbe_phy_switch_mode(phydev); - if (ret < 0) - return AMD_XGBE_AN_ERROR; + ret = amd_xgbe_phy_cur_mode(phydev, &cur_mode); + if (ret) + return ret; - return AMD_XGBE_AN_START; + if (mode != cur_mode) + ret = amd_xgbe_phy_switch_mode(phydev); + + return ret; } static enum amd_xgbe_phy_an amd_xgbe_an_tx_training(struct phy_device *phydev, enum amd_xgbe_phy_rx *state) { - struct amd_xgbe_phy_priv *priv = phydev->priv; int ad_reg, lp_reg, ret; *state = AMD_XGBE_RX_COMPLETE; - /* If we're in KX mode then we're done */ - if (priv->mode == AMD_XGBE_MODE_KX) + /* If we're not in KR mode then we're done */ + if (!amd_xgbe_phy_in_kr_mode(phydev)) return AMD_XGBE_AN_EVENT; /* Enable/Disable FEC */ @@ -669,7 +701,6 @@ static enum amd_xgbe_phy_an amd_xgbe_an_tx_xnp(struct phy_device *phydev, static enum amd_xgbe_phy_an amd_xgbe_an_rx_bpa(struct phy_device *phydev, enum amd_xgbe_phy_rx *state) { - struct amd_xgbe_phy_priv *priv = phydev->priv; unsigned int link_support; int ret, ad_reg, lp_reg; @@ -679,9 +710,9 @@ static enum amd_xgbe_phy_an amd_xgbe_an_rx_bpa(struct phy_device *phydev, return AMD_XGBE_AN_ERROR; /* Check for a supported mode, otherwise restart in a different one */ - link_support = (priv->mode == AMD_XGBE_MODE_KR) ? 0x80 : 0x20; + link_support = amd_xgbe_phy_in_kr_mode(phydev) ? 0x80 : 0x20; if (!(ret & link_support)) - return amd_xgbe_an_switch_mode(phydev); + return AMD_XGBE_AN_INCOMPAT_LINK; /* Check Extended Next Page support */ ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE); @@ -722,7 +753,7 @@ static enum amd_xgbe_phy_an amd_xgbe_an_start(struct phy_device *phydev) int ret; /* Be sure we aren't looping trying to negotiate */ - if (priv->mode == AMD_XGBE_MODE_KR) { + if (amd_xgbe_phy_in_kr_mode(phydev)) { if (priv->kr_state != AMD_XGBE_RX_READY) return AMD_XGBE_AN_NO_LINK; priv->kr_state = AMD_XGBE_RX_BPA; @@ -785,6 +816,13 @@ static enum amd_xgbe_phy_an amd_xgbe_an_start(struct phy_device *phydev) /* Enable and start auto-negotiation */ phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0); + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_KR_CTRL); + if (ret < 0) + return AMD_XGBE_AN_ERROR; + + ret |= MDIO_KR_CTRL_PDETECT; + phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_KR_CTRL, ret); + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1); if (ret < 0) return AMD_XGBE_AN_ERROR; @@ -825,8 +863,8 @@ static enum amd_xgbe_phy_an amd_xgbe_an_page_received(struct phy_device *phydev) enum amd_xgbe_phy_rx *state; int ret; - state = (priv->mode == AMD_XGBE_MODE_KR) ? &priv->kr_state - : &priv->kx_state; + state = amd_xgbe_phy_in_kr_mode(phydev) ? &priv->kr_state + : &priv->kx_state; switch (*state) { case AMD_XGBE_RX_BPA: @@ -846,7 +884,13 @@ static enum amd_xgbe_phy_an amd_xgbe_an_page_received(struct phy_device *phydev) static enum amd_xgbe_phy_an amd_xgbe_an_incompat_link(struct phy_device *phydev) { - return amd_xgbe_an_switch_mode(phydev); + int ret; + + ret = amd_xgbe_phy_switch_mode(phydev); + if (ret) + return AMD_XGBE_AN_ERROR; + + return AMD_XGBE_AN_START; } static void amd_xgbe_an_state_machine(struct work_struct *work) @@ -859,6 +903,10 @@ static void amd_xgbe_an_state_machine(struct work_struct *work) int sleep; unsigned int an_supported = 0; + /* Start in KX mode */ + if (amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KX)) + priv->an_state = AMD_XGBE_AN_ERROR; + while (1) { mutex_lock(&priv->an_mutex); @@ -866,8 +914,9 @@ static void amd_xgbe_an_state_machine(struct work_struct *work) switch (priv->an_state) { case AMD_XGBE_AN_START: - priv->an_state = amd_xgbe_an_start(phydev); an_supported = 0; + priv->parallel_detect = 0; + priv->an_state = amd_xgbe_an_start(phydev); break; case AMD_XGBE_AN_EVENT: @@ -884,6 +933,7 @@ static void amd_xgbe_an_state_machine(struct work_struct *work) break; case AMD_XGBE_AN_COMPLETE: + priv->parallel_detect = an_supported ? 0 : 1; netdev_info(phydev->attached_dev, "%s successful\n", an_supported ? "Auto negotiation" : "Parallel detection"); @@ -1018,7 +1068,6 @@ static int amd_xgbe_phy_config_aneg(struct phy_device *phydev) { struct amd_xgbe_phy_priv *priv = phydev->priv; u32 mmd_mask = phydev->c45_ids.devices_in_package; - int ret; if (phydev->autoneg != AUTONEG_ENABLE) return amd_xgbe_phy_setup_forced(phydev); @@ -1027,11 +1076,6 @@ static int amd_xgbe_phy_config_aneg(struct phy_device *phydev) if (!(mmd_mask & MDIO_DEVS_AN)) return -EINVAL; - /* Get the current speed mode */ - ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2); - if (ret < 0) - return ret; - /* Start/Restart the auto-negotiation state machine */ mutex_lock(&priv->an_mutex); priv->an_result = AMD_XGBE_AN_READY; @@ -1121,18 +1165,14 @@ static int amd_xgbe_phy_read_status(struct phy_device *phydev) { struct amd_xgbe_phy_priv *priv = phydev->priv; u32 mmd_mask = phydev->c45_ids.devices_in_package; - int ret, mode, ad_ret, lp_ret; + int ret, ad_ret, lp_ret; ret = amd_xgbe_phy_update_link(phydev); if (ret) return ret; - mode = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2); - if (mode < 0) - return mode; - mode &= MDIO_PCS_CTRL2_TYPE; - - if (phydev->autoneg == AUTONEG_ENABLE) { + if ((phydev->autoneg == AUTONEG_ENABLE) && + !priv->parallel_detect) { if (!(mmd_mask & MDIO_DEVS_AN)) return -EINVAL; @@ -1163,40 +1203,39 @@ static int amd_xgbe_phy_read_status(struct phy_device *phydev) ad_ret &= lp_ret; if (ad_ret & 0x80) { phydev->speed = SPEED_10000; - if (mode != MDIO_PCS_CTRL2_10GBR) { - ret = amd_xgbe_phy_xgmii_mode(phydev); - if (ret < 0) - return ret; - } + ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KR); + if (ret) + return ret; } else { - int (*mode_fcn)(struct phy_device *); - - if (priv->speed_set == - AMD_XGBE_PHY_SPEEDSET_1000_10000) { + switch (priv->speed_set) { + case AMD_XGBE_PHY_SPEEDSET_1000_10000: phydev->speed = SPEED_1000; - mode_fcn = amd_xgbe_phy_gmii_mode; - } else { + break; + + case AMD_XGBE_PHY_SPEEDSET_2500_10000: phydev->speed = SPEED_2500; - mode_fcn = amd_xgbe_phy_gmii_2500_mode; + break; } - if (mode == MDIO_PCS_CTRL2_10GBR) { - ret = mode_fcn(phydev); - if (ret < 0) - return ret; - } + ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KX); + if (ret) + return ret; } phydev->duplex = DUPLEX_FULL; } else { - if (mode == MDIO_PCS_CTRL2_10GBR) { + if (amd_xgbe_phy_in_kr_mode(phydev)) { phydev->speed = SPEED_10000; } else { - if (priv->speed_set == - AMD_XGBE_PHY_SPEEDSET_1000_10000) + switch (priv->speed_set) { + case AMD_XGBE_PHY_SPEEDSET_1000_10000: phydev->speed = SPEED_1000; - else + break; + + case AMD_XGBE_PHY_SPEEDSET_2500_10000: phydev->speed = SPEED_2500; + break; + } } phydev->duplex = DUPLEX_FULL; phydev->pause = 0; @@ -1329,14 +1368,6 @@ static int amd_xgbe_phy_probe(struct phy_device *phydev) priv->link = 1; - ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2); - if (ret < 0) - goto err_sir1; - if ((ret & MDIO_PCS_CTRL2_TYPE) == MDIO_PCS_CTRL2_10GBR) - priv->mode = AMD_XGBE_MODE_KR; - else - priv->mode = AMD_XGBE_MODE_KX; - mutex_init(&priv->an_mutex); INIT_WORK(&priv->an_work, amd_xgbe_an_state_machine); priv->an_workqueue = create_singlethread_workqueue(wq_name); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 80b0179bff1f..f95e678cb69d 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -975,34 +975,6 @@ void write_mii_word(struct net_device *netdev, int phy_id, int reg, int val) static int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags); -static inline void set_ethernet_addr(struct r8152 *tp) -{ - struct net_device *dev = tp->netdev; - int ret; - u8 node_id[8] = {0}; - - if (tp->version == RTL_VER_01) - ret = pla_ocp_read(tp, PLA_IDR, sizeof(node_id), node_id); - else - ret = pla_ocp_read(tp, PLA_BACKUP, sizeof(node_id), node_id); - - if (ret < 0) { - netif_notice(tp, probe, dev, "inet addr fail\n"); - } else { - if (tp->version != RTL_VER_01) { - ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, - CRWECR_CONFIG); - pla_ocp_write(tp, PLA_IDR, BYTE_EN_SIX_BYTES, - sizeof(node_id), node_id); - ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, - CRWECR_NORAML); - } - - memcpy(dev->dev_addr, node_id, dev->addr_len); - memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); - } -} - static int rtl8152_set_mac_address(struct net_device *netdev, void *p) { struct r8152 *tp = netdev_priv(netdev); @@ -1020,6 +992,37 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p) return 0; } +static int set_ethernet_addr(struct r8152 *tp) +{ + struct net_device *dev = tp->netdev; + struct sockaddr sa; + int ret; + + if (tp->version == RTL_VER_01) + ret = pla_ocp_read(tp, PLA_IDR, 8, sa.sa_data); + else + ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa.sa_data); + + if (ret < 0) { + netif_err(tp, probe, dev, "Get ether addr fail\n"); + } else if (!is_valid_ether_addr(sa.sa_data)) { + netif_err(tp, probe, dev, "Invalid ether addr %pM\n", + sa.sa_data); + eth_hw_addr_random(dev); + ether_addr_copy(sa.sa_data, dev->dev_addr); + ret = rtl8152_set_mac_address(dev, &sa); + netif_info(tp, probe, dev, "Random ether addr %pM\n", + sa.sa_data); + } else { + if (tp->version == RTL_VER_01) + ether_addr_copy(dev->dev_addr, sa.sa_data); + else + ret = rtl8152_set_mac_address(dev, &sa); + } + + return ret; +} + static void read_bulk_callback(struct urb *urb) { struct net_device *netdev; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e658229fee39..c1a2d60dfb82 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -257,6 +257,10 @@ struct ethtool_ops { struct ethtool_eeprom *, u8 *); int (*get_eee)(struct net_device *, struct ethtool_eee *); int (*set_eee)(struct net_device *, struct ethtool_eee *); + int (*get_tunable)(struct net_device *, + const struct ethtool_tunable *, void *); + int (*set_tunable)(struct net_device *, + const struct ethtool_tunable *, const void *); }; diff --git a/include/linux/filter.h b/include/linux/filter.h index a5227ab8ccb1..c78994593355 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -9,6 +9,11 @@ #include <linux/skbuff.h> #include <linux/workqueue.h> #include <uapi/linux/filter.h> +#include <asm/cacheflush.h> + +struct sk_buff; +struct sock; +struct seccomp_data; /* Internally used and optimized filter representation with extended * instruction set based on top of classic BPF. @@ -320,20 +325,23 @@ struct sock_fprog_kern { struct sock_filter *filter; }; -struct sk_buff; -struct sock; -struct seccomp_data; +struct bpf_work_struct { + struct bpf_prog *prog; + struct work_struct work; +}; struct bpf_prog { + u32 pages; /* Number of allocated pages */ u32 jited:1, /* Is our filter JIT'ed? */ len:31; /* Number of filter blocks */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ + struct bpf_work_struct *work; /* Deferred free work struct */ unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); + /* Instructions for interpreter */ union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; - struct work_struct work; }; }; @@ -353,6 +361,26 @@ static inline unsigned int bpf_prog_size(unsigned int proglen) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +{ + set_memory_ro((unsigned long)fp, fp->pages); +} + +static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) +{ + set_memory_rw((unsigned long)fp, fp->pages); +} +#else +static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +{ +} + +static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) +{ +} +#endif /* CONFIG_DEBUG_SET_MODULE_RONX */ + int sk_filter(struct sock *sk, struct sk_buff *skb); void bpf_prog_select_runtime(struct bpf_prog *fp); @@ -361,6 +389,17 @@ void bpf_prog_free(struct bpf_prog *fp); int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_insn *new_prog, int *new_len); +struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); +struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, + gfp_t gfp_extra_flags); +void __bpf_prog_free(struct bpf_prog *fp); + +static inline void bpf_prog_unlock_free(struct bpf_prog *fp) +{ + bpf_prog_unlock_ro(fp); + __bpf_prog_free(fp); +} + int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); void bpf_prog_destroy(struct bpf_prog *fp); @@ -450,7 +489,7 @@ static inline void bpf_jit_compile(struct bpf_prog *fp) static inline void bpf_jit_free(struct bpf_prog *fp) { - kfree(fp); + bpf_prog_unlock_free(fp); } #endif /* CONFIG_BPF_JIT */ diff --git a/include/linux/igmp.h b/include/linux/igmp.h index f47550d75f85..2c677afeea47 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -39,6 +39,7 @@ static inline struct igmpv3_query * extern int sysctl_igmp_max_memberships; extern int sysctl_igmp_max_msf; +extern int sysctl_igmp_qrv; struct ip_sf_socklist { unsigned int sl_max; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9922093f575e..f30fd554127e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -87,7 +87,7 @@ struct fib_nh { int nh_saddr_genid; struct rtable __rcu * __percpu *nh_pcpu_rth_output; struct rtable __rcu *nh_rth_input; - struct fnhe_hash_bucket *nh_exceptions; + struct fnhe_hash_bucket __rcu *nh_exceptions; }; /* diff --git a/include/net/ipv6.h b/include/net/ipv6.h index a2db816e8461..7e247e9b8765 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -121,6 +121,7 @@ struct frag_hdr { /* sysctls */ extern int sysctl_mld_max_msf; +extern int sysctl_mld_qrv; #define _DEVINC(net, statname, modifier, idev, field) \ ({ \ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index e3c7a719c76b..7a364f2f3d3f 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -209,6 +209,32 @@ struct ethtool_value { __u32 data; }; +enum tunable_id { + ETHTOOL_ID_UNSPEC, + ETHTOOL_RX_COPYBREAK, +}; + +enum tunable_type_id { + ETHTOOL_TUNABLE_UNSPEC, + ETHTOOL_TUNABLE_U8, + ETHTOOL_TUNABLE_U16, + ETHTOOL_TUNABLE_U32, + ETHTOOL_TUNABLE_U64, + ETHTOOL_TUNABLE_STRING, + ETHTOOL_TUNABLE_S8, + ETHTOOL_TUNABLE_S16, + ETHTOOL_TUNABLE_S32, + ETHTOOL_TUNABLE_S64, +}; + +struct ethtool_tunable { + __u32 cmd; + __u32 id; + __u32 type_id; + __u32 len; + void *data[0]; +}; + /** * struct ethtool_regs - hardware register dump * @cmd: Command number = %ETHTOOL_GREGS @@ -1152,6 +1178,8 @@ enum ethtool_sfeatures_retval_bits { #define ETHTOOL_GRSSH 0x00000046 /* Get RX flow hash configuration */ #define ETHTOOL_SRSSH 0x00000047 /* Set RX flow hash configuration */ +#define ETHTOOL_GTUNABLE 0x00000048 /* Get tunable configuration */ +#define ETHTOOL_STUNABLE 0x00000049 /* Set tunable configuration */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7f0dbcbb34af..b54bb2c2e494 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -22,6 +22,7 @@ */ #include <linux/filter.h> #include <linux/skbuff.h> +#include <linux/vmalloc.h> #include <asm/unaligned.h> /* Registers */ @@ -63,6 +64,67 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns return NULL; } +struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | + gfp_extra_flags; + struct bpf_work_struct *ws; + struct bpf_prog *fp; + + size = round_up(size, PAGE_SIZE); + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + if (fp == NULL) + return NULL; + + ws = kmalloc(sizeof(*ws), GFP_KERNEL | gfp_extra_flags); + if (ws == NULL) { + vfree(fp); + return NULL; + } + + fp->pages = size / PAGE_SIZE; + fp->work = ws; + + return fp; +} +EXPORT_SYMBOL_GPL(bpf_prog_alloc); + +struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, + gfp_t gfp_extra_flags) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | + gfp_extra_flags; + struct bpf_prog *fp; + + BUG_ON(fp_old == NULL); + + size = round_up(size, PAGE_SIZE); + if (size <= fp_old->pages * PAGE_SIZE) + return fp_old; + + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + if (fp != NULL) { + memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); + fp->pages = size / PAGE_SIZE; + + /* We keep fp->work from fp_old around in the new + * reallocated structure. + */ + fp_old->work = NULL; + __bpf_prog_free(fp_old); + } + + return fp; +} +EXPORT_SYMBOL_GPL(bpf_prog_realloc); + +void __bpf_prog_free(struct bpf_prog *fp) +{ + kfree(fp->work); + vfree(fp); +} +EXPORT_SYMBOL_GPL(__bpf_prog_free); + /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. @@ -523,12 +585,26 @@ void bpf_prog_select_runtime(struct bpf_prog *fp) /* Probe if internal BPF can be JITed */ bpf_int_jit_compile(fp); + /* Lock whole bpf_prog as read-only */ + bpf_prog_lock_ro(fp); } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); -/* free internal BPF program */ +static void bpf_prog_free_deferred(struct work_struct *work) +{ + struct bpf_work_struct *ws; + + ws = container_of(work, struct bpf_work_struct, work); + bpf_jit_free(ws->prog); +} + +/* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { - bpf_jit_free(fp); + struct bpf_work_struct *ws = fp->work; + + INIT_WORK(&ws->work, bpf_prog_free_deferred); + ws->prog = fp; + schedule_work(&ws->work); } EXPORT_SYMBOL_GPL(bpf_prog_free); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 44eb005c6695..84922befea84 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -395,16 +395,15 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) if (!filter) goto free_prog; - filter->prog = kzalloc(bpf_prog_size(new_len), - GFP_KERNEL|__GFP_NOWARN); + filter->prog = bpf_prog_alloc(bpf_prog_size(new_len), __GFP_NOWARN); if (!filter->prog) goto free_filter; ret = bpf_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len); if (ret) goto free_filter_prog; - kfree(fp); + kfree(fp); atomic_set(&filter->usage, 1); filter->prog->len = new_len; @@ -413,7 +412,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) return filter; free_filter_prog: - kfree(filter->prog); + __bpf_prog_free(filter->prog); free_filter: kfree(filter); free_prog: diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 8c66c6aace04..9a67456ba29a 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1836,7 +1836,7 @@ static struct bpf_prog *generate_filter(int which, int *err) break; case INTERNAL: - fp = kzalloc(bpf_prog_size(flen), GFP_KERNEL); + fp = bpf_prog_alloc(bpf_prog_size(flen), 0); if (fp == NULL) { pr_cont("UNEXPECTED_FAIL no memory left\n"); *err = -ENOMEM; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index cf999e09bcd2..72e899a3efda 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -365,11 +365,8 @@ void dev_load(struct net *net, const char *name) no_module = !dev; if (no_module && capable(CAP_NET_ADMIN)) no_module = request_module("netdev-%s", name); - if (no_module && capable(CAP_SYS_MODULE)) { - if (!request_module("%s", name)) - pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", - name); - } + if (no_module && capable(CAP_SYS_MODULE)) + request_module("%s", name); } EXPORT_SYMBOL(dev_load); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 17cb912793fa..27e61b886520 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1621,6 +1621,80 @@ static int ethtool_get_module_eeprom(struct net_device *dev, modinfo.eeprom_len); } +static int ethtool_tunable_valid(const struct ethtool_tunable *tuna) +{ + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + if (tuna->len != sizeof(u32) || + tuna->type_id != ETHTOOL_TUNABLE_U32) + return -EINVAL; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) +{ + int ret; + struct ethtool_tunable tuna; + const struct ethtool_ops *ops = dev->ethtool_ops; + void *data; + + if (!ops->get_tunable) + return -EOPNOTSUPP; + if (copy_from_user(&tuna, useraddr, sizeof(tuna))) + return -EFAULT; + ret = ethtool_tunable_valid(&tuna); + if (ret) + return ret; + data = kmalloc(tuna.len, GFP_USER); + if (!data) + return -ENOMEM; + ret = ops->get_tunable(dev, &tuna, data); + if (ret) + goto out; + useraddr += sizeof(tuna); + ret = -EFAULT; + if (copy_to_user(useraddr, data, tuna.len)) + goto out; + ret = 0; + +out: + kfree(data); + return ret; +} + +static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr) +{ + int ret; + struct ethtool_tunable tuna; + const struct ethtool_ops *ops = dev->ethtool_ops; + void *data; + + if (!ops->set_tunable) + return -EOPNOTSUPP; + if (copy_from_user(&tuna, useraddr, sizeof(tuna))) + return -EFAULT; + ret = ethtool_tunable_valid(&tuna); + if (ret) + return ret; + data = kmalloc(tuna.len, GFP_USER); + if (!data) + return -ENOMEM; + useraddr += sizeof(tuna); + ret = -EFAULT; + if (copy_from_user(data, useraddr, tuna.len)) + goto out; + ret = ops->set_tunable(dev, &tuna, data); + +out: + kfree(data); + return ret; +} + /* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) @@ -1670,6 +1744,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GCHANNELS: case ETHTOOL_GET_TS_INFO: case ETHTOOL_GEEE: + case ETHTOOL_GTUNABLE: break; default: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -1857,6 +1932,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GMODULEEEPROM: rc = ethtool_get_module_eeprom(dev, useraddr); break; + case ETHTOOL_GTUNABLE: + rc = ethtool_get_tunable(dev, useraddr); + break; + case ETHTOOL_STUNABLE: + rc = ethtool_set_tunable(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/filter.c b/net/core/filter.c index d814b8a89d0f..37f8eb06fdee 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -933,7 +933,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) /* Expand fp for appending the new filter representation. */ old_fp = fp; - fp = krealloc(old_fp, bpf_prog_size(new_len), GFP_KERNEL); + fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. @@ -1013,7 +1013,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) if (fprog->filter == NULL) return -EINVAL; - fp = kmalloc(bpf_prog_size(fprog->len), GFP_KERNEL); + fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; @@ -1069,7 +1069,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (fprog->filter == NULL) return -EINVAL; - prog = kmalloc(bpf_fsize, GFP_KERNEL); + prog = bpf_prog_alloc(bpf_fsize, 0); if (!prog) return -ENOMEM; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b10cd43a4722..5b6efb3d2308 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -157,9 +157,12 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp) static void free_nh_exceptions(struct fib_nh *nh) { - struct fnhe_hash_bucket *hash = nh->nh_exceptions; + struct fnhe_hash_bucket *hash; int i; + hash = rcu_dereference_protected(nh->nh_exceptions, 1); + if (!hash) + return; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; @@ -205,8 +208,7 @@ static void free_fib_info_rcu(struct rcu_head *head) change_nexthops(fi) { if (nexthop_nh->nh_dev) dev_put(nexthop_nh->nh_dev); - if (nexthop_nh->nh_exceptions) - free_nh_exceptions(nexthop_nh); + free_nh_exceptions(nexthop_nh); rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 890c4258804c..4146153d875d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -117,7 +117,7 @@ #define IGMP_V2_Unsolicited_Report_Interval (10*HZ) #define IGMP_V3_Unsolicited_Report_Interval (1*HZ) #define IGMP_Query_Response_Interval (10*HZ) -#define IGMP_Unsolicited_Report_Count 2 +#define IGMP_Query_Robustness_Variable 2 #define IGMP_Initial_Report_Delay (1) @@ -756,8 +756,7 @@ static void igmp_ifc_event(struct in_device *in_dev) { if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + in_dev->mr_ifc_count = in_dev->mr_qrv ?: sysctl_igmp_qrv; igmp_ifc_start_timer(in_dev, 1); } @@ -1086,8 +1085,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1226,8 +1224,7 @@ static void igmp_group_added(struct ip_mc_list *im) } /* else, v3 */ - im->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + im->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; igmp_ifc_event(in_dev); #endif } @@ -1322,7 +1319,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); - im->unsolicit_count = IGMP_Unsolicited_Report_Count; + im->unsolicit_count = sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; @@ -1460,7 +1457,7 @@ void ip_mc_init_dev(struct in_device *in_dev) (unsigned long)in_dev); setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, (unsigned long)in_dev); - in_dev->mr_qrv = IGMP_Unsolicited_Report_Count; + in_dev->mr_qrv = sysctl_igmp_qrv; #endif spin_lock_init(&in_dev->mc_tomb_lock); @@ -1474,6 +1471,9 @@ void ip_mc_up(struct in_device *in_dev) ASSERT_RTNL(); +#ifdef CONFIG_IP_MULTICAST + in_dev->mr_qrv = sysctl_igmp_qrv; +#endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) @@ -1540,7 +1540,9 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) */ int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS; int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; - +#ifdef CONFIG_IP_MULTICAST +int sysctl_igmp_qrv __read_mostly = IGMP_Query_Robustness_Variable; +#endif static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) @@ -1575,8 +1577,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + psf->sf_crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1639,8 +1640,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -1818,8 +1818,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index eaa4b000c7b4..44b0cbdd76f1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -628,12 +628,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, spin_lock_bh(&fnhe_lock); - hash = nh->nh_exceptions; + hash = rcu_dereference(nh->nh_exceptions); if (!hash) { hash = kzalloc(FNHE_HASH_SIZE * sizeof(*hash), GFP_ATOMIC); if (!hash) goto out_unlock; - nh->nh_exceptions = hash; + rcu_assign_pointer(nh->nh_exceptions, hash); } hash += hval; @@ -1242,7 +1242,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { - struct fnhe_hash_bucket *hash = nh->nh_exceptions; + struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions); struct fib_nh_exception *fnhe; u32 hval; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 79a007c52558..45d156dacd61 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -450,6 +450,16 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_IP_MULTICAST + { + .procname = "igmp_qrv", + .data = &sysctl_igmp_qrv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, +#endif { .procname = "inet_peer_threshold", .data = &inet_peer_threshold, diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 70881795da96..64919425f1ab 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -121,6 +121,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; +int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; /* * socket join on multicast group @@ -1191,15 +1192,16 @@ static void mld_update_qrv(struct inet6_dev *idev, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ + const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; - if (unlikely(idev->mc_qrv < 2)) { + if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", - idev->mc_qrv, MLD_QRV_DEFAULT); - idev->mc_qrv = MLD_QRV_DEFAULT; + idev->mc_qrv, min_qrv); + idev->mc_qrv = min_qrv; } } @@ -2478,6 +2480,14 @@ void ipv6_mc_down(struct inet6_dev *idev) mld_clear_delrec(idev); } +static void ipv6_mc_reset(struct inet6_dev *idev) +{ + idev->mc_qrv = sysctl_mld_qrv; + idev->mc_qi = MLD_QI_DEFAULT; + idev->mc_qri = MLD_QRI_DEFAULT; + idev->mc_v1_seen = 0; + idev->mc_maxdelay = unsolicited_report_interval(idev); +} /* Device going up */ @@ -2488,6 +2498,7 @@ void ipv6_mc_up(struct inet6_dev *idev) /* Install multicast list, except for all-nodes (already installed) */ read_lock_bh(&idev->lock); + ipv6_mc_reset(idev); for (i = idev->mc_list; i; i = i->next) igmp6_group_added(i); read_unlock_bh(&idev->lock); @@ -2508,13 +2519,7 @@ void ipv6_mc_init_dev(struct inet6_dev *idev) (unsigned long)idev); setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire, (unsigned long)idev); - - idev->mc_qrv = MLD_QRV_DEFAULT; - idev->mc_qi = MLD_QI_DEFAULT; - idev->mc_qri = MLD_QRI_DEFAULT; - - idev->mc_maxdelay = unsolicited_report_interval(idev); - idev->mc_v1_seen = 0; + ipv6_mc_reset(idev); write_unlock_bh(&idev->lock); } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 0c56c93619e0..c5c10fafcfe2 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,6 +16,8 @@ #include <net/addrconf.h> #include <net/inet_frag.h> +static int one = 1; + static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", @@ -63,6 +65,14 @@ static struct ctl_table ipv6_rotable[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "mld_qrv", + .data = &sysctl_mld_qrv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, { } }; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 797c0af71c06..2aa2b6c15f20 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -148,7 +148,7 @@ do { \ atomic_read(&_t->ref_count)); \ l2tp_tunnel_inc_refcount_1(_t); \ } while (0) -#define l2tp_tunnel_dec_refcount(_t) +#define l2tp_tunnel_dec_refcount(_t) \ do { \ pr_debug("l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", \ __func__, __LINE__, (_t)->name, \ |