diff --git a/MAINTAINERS b/MAINTAINERS index 9a6c4da..61ed6f7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2697,7 +2697,7 @@ S: Maintained F: drivers/net/ethernet/i825xx/eexpress.* ETHERNET BRIDGE -M: Stephen Hemminger <shemminger@xxxxxxxxxx> +M: Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx> L: bridge@xxxxxxxxxxxxxxxxxxxxxxxxxx L: netdev@xxxxxxxxxxxxxxx W: http://www.linuxfoundation.org/en/Net:Bridge @@ -4420,7 +4420,7 @@ S: Maintained MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) M: Mirko Lindner <mlindner@xxxxxxxxxxx> -M: Stephen Hemminger <shemminger@xxxxxxxxxx> +M: Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx> L: netdev@xxxxxxxxxxxxxxx S: Maintained F: drivers/net/ethernet/marvell/sk* @@ -4664,7 +4664,7 @@ S: Supported F: drivers/infiniband/hw/nes/ NETEM NETWORK EMULATOR -M: Stephen Hemminger <shemminger@xxxxxxxxxx> +M: Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx> L: netem@xxxxxxxxxxxxxxxxxxxxxxxxxx S: Maintained F: net/sched/sch_netem.c diff --git a/Makefile b/Makefile index 50dc4d1..fd753ca 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 6 SUBLEVEL = 11 -EXTRAVERSION = +EXTRAVERSION = .1 NAME = Terrified Chipmunk # *DOCUMENTATION* diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 67f1f6f..0133b1b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -56,6 +56,7 @@ config SPARC64 select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_SYSCALL_WRAPPERS + select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 1770610..f368cef 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -58,14 +58,20 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - ptep_set_wrprotect(mm, addr, ptep); + pte_t old_pte = *ptep; + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); } static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { - return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + int changed = !pte_same(*ptep, pte); + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_page(vma, addr); + } + return changed; } static inline pte_t huge_ptep_get(pte_t *ptep) diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index c52add7..7c2d9ac 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -331,7 +331,7 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss) retry_tsb_alloc: gfp_flags = GFP_KERNEL; if (new_size > (PAGE_SIZE * 2)) - gfp_flags = __GFP_NOWARN | __GFP_NORETRY; + gfp_flags |= __GFP_NOWARN | __GFP_NORETRY; new_tsb = kmem_cache_alloc_node(tsb_caches[new_cache_index], gfp_flags, numa_node_id()); diff --git a/drivers/atm/iphase.h b/drivers/atm/iphase.h index 6a0955e..53ecac5 100644 --- a/drivers/atm/iphase.h +++ b/drivers/atm/iphase.h @@ -636,82 +636,82 @@ struct rx_buf_desc { #define SEG_BASE IPHASE5575_FRAG_CONTROL_REG_BASE #define REASS_BASE IPHASE5575_REASS_CONTROL_REG_BASE -typedef volatile u_int freg_t; +typedef volatile u_int ffreg_t; typedef u_int rreg_t; typedef struct _ffredn_t { - freg_t idlehead_high; /* Idle cell header (high) */ - freg_t idlehead_low; /* Idle cell header (low) */ - freg_t maxrate; /* Maximum rate */ - freg_t stparms; /* Traffic Management Parameters */ - freg_t abrubr_abr; /* ABRUBR Priority Byte 1, TCR Byte 0 */ - freg_t rm_type; /* */ - u_int filler5[0x17 - 0x06]; - freg_t cmd_reg; /* Command register */ - u_int filler18[0x20 - 0x18]; - freg_t cbr_base; /* CBR Pointer Base */ - freg_t vbr_base; /* VBR Pointer Base */ - freg_t abr_base; /* ABR Pointer Base */ - freg_t ubr_base; /* UBR Pointer Base */ - u_int filler24; - freg_t vbrwq_base; /* VBR Wait Queue Base */ - freg_t abrwq_base; /* ABR Wait Queue Base */ - freg_t ubrwq_base; /* UBR Wait Queue Base */ - freg_t vct_base; /* Main VC Table Base */ - freg_t vcte_base; /* Extended Main VC Table Base */ - u_int filler2a[0x2C - 0x2A]; - freg_t cbr_tab_beg; /* CBR Table Begin */ - freg_t cbr_tab_end; /* CBR Table End */ - freg_t cbr_pointer; /* CBR Pointer */ - u_int filler2f[0x30 - 0x2F]; - freg_t prq_st_adr; /* Packet Ready Queue Start Address */ - freg_t prq_ed_adr; /* Packet Ready Queue End Address */ - freg_t prq_rd_ptr; /* Packet Ready Queue read pointer */ - freg_t prq_wr_ptr; /* Packet Ready Queue write pointer */ - freg_t tcq_st_adr; /* Transmit Complete Queue Start Address*/ - freg_t tcq_ed_adr; /* Transmit Complete Queue End Address */ - freg_t tcq_rd_ptr; /* Transmit Complete Queue read pointer */ - freg_t tcq_wr_ptr; /* Transmit Complete Queue write pointer*/ - u_int filler38[0x40 - 0x38]; - freg_t queue_base; /* Base address for PRQ and TCQ */ - freg_t desc_base; /* Base address of descriptor table */ - u_int filler42[0x45 - 0x42]; - freg_t mode_reg_0; /* Mode register 0 */ - freg_t mode_reg_1; /* Mode register 1 */ - freg_t intr_status_reg;/* Interrupt Status register */ - freg_t mask_reg; /* Mask Register */ - freg_t cell_ctr_high1; /* Total cell transfer count (high) */ - freg_t cell_ctr_lo1; /* Total cell transfer count (low) */ - freg_t state_reg; /* Status register */ - u_int filler4c[0x58 - 0x4c]; - freg_t curr_desc_num; /* Contains the current descriptor num */ - freg_t next_desc; /* Next descriptor */ - freg_t next_vc; /* Next VC */ - u_int filler5b[0x5d - 0x5b]; - freg_t present_slot_cnt;/* Present slot count */ - u_int filler5e[0x6a - 0x5e]; - freg_t new_desc_num; /* New descriptor number */ - freg_t new_vc; /* New VC */ - freg_t sched_tbl_ptr; /* Schedule table pointer */ - freg_t vbrwq_wptr; /* VBR wait queue write pointer */ - freg_t vbrwq_rptr; /* VBR wait queue read pointer */ - freg_t abrwq_wptr; /* ABR wait queue write pointer */ - freg_t abrwq_rptr; /* ABR wait queue read pointer */ - freg_t ubrwq_wptr; /* UBR wait queue write pointer */ - freg_t ubrwq_rptr; /* UBR wait queue read pointer */ - freg_t cbr_vc; /* CBR VC */ - freg_t vbr_sb_vc; /* VBR SB VC */ - freg_t abr_sb_vc; /* ABR SB VC */ - freg_t ubr_sb_vc; /* UBR SB VC */ - freg_t vbr_next_link; /* VBR next link */ - freg_t abr_next_link; /* ABR next link */ - freg_t ubr_next_link; /* UBR next link */ - u_int filler7a[0x7c-0x7a]; - freg_t out_rate_head; /* Out of rate head */ - u_int filler7d[0xca-0x7d]; /* pad out to full address space */ - freg_t cell_ctr_high1_nc;/* Total cell transfer count (high) */ - freg_t cell_ctr_lo1_nc;/* Total cell transfer count (low) */ - u_int fillercc[0x100-0xcc]; /* pad out to full address space */ + ffreg_t idlehead_high; /* Idle cell header (high) */ + ffreg_t idlehead_low; /* Idle cell header (low) */ + ffreg_t maxrate; /* Maximum rate */ + ffreg_t stparms; /* Traffic Management Parameters */ + ffreg_t abrubr_abr; /* ABRUBR Priority Byte 1, TCR Byte 0 */ + ffreg_t rm_type; /* */ + u_int filler5[0x17 - 0x06]; + ffreg_t cmd_reg; /* Command register */ + u_int filler18[0x20 - 0x18]; + ffreg_t cbr_base; /* CBR Pointer Base */ + ffreg_t vbr_base; /* VBR Pointer Base */ + ffreg_t abr_base; /* ABR Pointer Base */ + ffreg_t ubr_base; /* UBR Pointer Base */ + u_int filler24; + ffreg_t vbrwq_base; /* VBR Wait Queue Base */ + ffreg_t abrwq_base; /* ABR Wait Queue Base */ + ffreg_t ubrwq_base; /* UBR Wait Queue Base */ + ffreg_t vct_base; /* Main VC Table Base */ + ffreg_t vcte_base; /* Extended Main VC Table Base */ + u_int filler2a[0x2C - 0x2A]; + ffreg_t cbr_tab_beg; /* CBR Table Begin */ + ffreg_t cbr_tab_end; /* CBR Table End */ + ffreg_t cbr_pointer; /* CBR Pointer */ + u_int filler2f[0x30 - 0x2F]; + ffreg_t prq_st_adr; /* Packet Ready Queue Start Address */ + ffreg_t prq_ed_adr; /* Packet Ready Queue End Address */ + ffreg_t prq_rd_ptr; /* Packet Ready Queue read pointer */ + ffreg_t prq_wr_ptr; /* Packet Ready Queue write pointer */ + ffreg_t tcq_st_adr; /* Transmit Complete Queue Start Address*/ + ffreg_t tcq_ed_adr; /* Transmit Complete Queue End Address */ + ffreg_t tcq_rd_ptr; /* Transmit Complete Queue read pointer */ + ffreg_t tcq_wr_ptr; /* Transmit Complete Queue write pointer*/ + u_int filler38[0x40 - 0x38]; + ffreg_t queue_base; /* Base address for PRQ and TCQ */ + ffreg_t desc_base; /* Base address of descriptor table */ + u_int filler42[0x45 - 0x42]; + ffreg_t mode_reg_0; /* Mode register 0 */ + ffreg_t mode_reg_1; /* Mode register 1 */ + ffreg_t intr_status_reg;/* Interrupt Status register */ + ffreg_t mask_reg; /* Mask Register */ + ffreg_t cell_ctr_high1; /* Total cell transfer count (high) */ + ffreg_t cell_ctr_lo1; /* Total cell transfer count (low) */ + ffreg_t state_reg; /* Status register */ + u_int filler4c[0x58 - 0x4c]; + ffreg_t curr_desc_num; /* Contains the current descriptor num */ + ffreg_t next_desc; /* Next descriptor */ + ffreg_t next_vc; /* Next VC */ + u_int filler5b[0x5d - 0x5b]; + ffreg_t present_slot_cnt;/* Present slot count */ + u_int filler5e[0x6a - 0x5e]; + ffreg_t new_desc_num; /* New descriptor number */ + ffreg_t new_vc; /* New VC */ + ffreg_t sched_tbl_ptr; /* Schedule table pointer */ + ffreg_t vbrwq_wptr; /* VBR wait queue write pointer */ + ffreg_t vbrwq_rptr; /* VBR wait queue read pointer */ + ffreg_t abrwq_wptr; /* ABR wait queue write pointer */ + ffreg_t abrwq_rptr; /* ABR wait queue read pointer */ + ffreg_t ubrwq_wptr; /* UBR wait queue write pointer */ + ffreg_t ubrwq_rptr; /* UBR wait queue read pointer */ + ffreg_t cbr_vc; /* CBR VC */ + ffreg_t vbr_sb_vc; /* VBR SB VC */ + ffreg_t abr_sb_vc; /* ABR SB VC */ + ffreg_t ubr_sb_vc; /* UBR SB VC */ + ffreg_t vbr_next_link; /* VBR next link */ + ffreg_t abr_next_link; /* ABR next link */ + ffreg_t ubr_next_link; /* UBR next link */ + u_int filler7a[0x7c-0x7a]; + ffreg_t out_rate_head; /* Out of rate head */ + u_int filler7d[0xca-0x7d]; /* pad out to full address space */ + ffreg_t cell_ctr_high1_nc;/* Total cell transfer count (high) */ + ffreg_t cell_ctr_lo1_nc;/* Total cell transfer count (low) */ + u_int fillercc[0x100-0xcc]; /* pad out to full address space */ } ffredn_t; typedef struct _rfredn_t { diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 9dcf76a..31dd451 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -461,7 +461,7 @@ static int generic_request(struct vdc_port *port, u8 op, void *buf, int len) int op_len, err; void *req_buf; - if (!(((u64)1 << ((u64)op - 1)) & port->operations)) + if (!(((u64)1 << (u64)op) & port->operations)) return -EOPNOTSUPP; switch (op) { diff --git a/drivers/isdn/gigaset/capi.c b/drivers/isdn/gigaset/capi.c index 68452b7..03a0a01 100644 --- a/drivers/isdn/gigaset/capi.c +++ b/drivers/isdn/gigaset/capi.c @@ -248,6 +248,8 @@ static inline void dump_rawmsg(enum debuglevel level, const char *tag, CAPIMSG_APPID(data), CAPIMSG_MSGID(data), l, CAPIMSG_CONTROL(data)); l -= 12; + if (l <= 0) + return; dbgline = kmalloc(3 * l, GFP_ATOMIC); if (!dbgline) return; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 711eb14..3756278 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -1245,14 +1245,26 @@ static int tg3_phy_auxctl_write(struct tg3 *tp, int reg, u32 set) return tg3_writephy(tp, MII_TG3_AUX_CTRL, set | reg); } -#define TG3_PHY_AUXCTL_SMDSP_ENABLE(tp) \ - tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, \ - MII_TG3_AUXCTL_ACTL_SMDSP_ENA | \ - MII_TG3_AUXCTL_ACTL_TX_6DB) +static int tg3_phy_toggle_auxctl_smdsp(struct tg3 *tp, bool enable) +{ + u32 val; + int err; -#define TG3_PHY_AUXCTL_SMDSP_DISABLE(tp) \ - tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, \ - MII_TG3_AUXCTL_ACTL_TX_6DB); + err = tg3_phy_auxctl_read(tp, MII_TG3_AUXCTL_SHDWSEL_AUXCTL, &val); + + if (err) + return err; + if (enable) + + val |= MII_TG3_AUXCTL_ACTL_SMDSP_ENA; + else + val &= ~MII_TG3_AUXCTL_ACTL_SMDSP_ENA; + + err = tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, + val | MII_TG3_AUXCTL_ACTL_TX_6DB); + + return err; +} static int tg3_bmcr_reset(struct tg3 *tp) { @@ -2185,7 +2197,7 @@ static void tg3_phy_apply_otp(struct tg3 *tp) otp = tp->phy_otp; - if (TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) + if (tg3_phy_toggle_auxctl_smdsp(tp, true)) return; phy = ((otp & TG3_OTP_AGCTGT_MASK) >> TG3_OTP_AGCTGT_SHIFT); @@ -2210,7 +2222,7 @@ static void tg3_phy_apply_otp(struct tg3 *tp) ((otp & TG3_OTP_RCOFF_MASK) >> TG3_OTP_RCOFF_SHIFT); tg3_phydsp_write(tp, MII_TG3_DSP_EXP97, phy); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) @@ -2246,9 +2258,9 @@ static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) if (!tp->setlpicnt) { if (current_link_up == 1 && - !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + !tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, 0x0000); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } val = tr32(TG3_CPMU_EEE_MODE); @@ -2264,11 +2276,11 @@ static void tg3_phy_eee_enable(struct tg3 *tp) (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || tg3_flag(tp, 57765_CLASS)) && - !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + !tg3_phy_toggle_auxctl_smdsp(tp, true)) { val = MII_TG3_DSP_TAP26_ALNOKO | MII_TG3_DSP_TAP26_RMRXSTO; tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } val = tr32(TG3_CPMU_EEE_MODE); @@ -2412,7 +2424,7 @@ static int tg3_phy_reset_5703_4_5(struct tg3 *tp) tg3_writephy(tp, MII_CTRL1000, CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER); - err = TG3_PHY_AUXCTL_SMDSP_ENABLE(tp); + err = tg3_phy_toggle_auxctl_smdsp(tp, true); if (err) return err; @@ -2433,7 +2445,7 @@ static int tg3_phy_reset_5703_4_5(struct tg3 *tp) tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x8200); tg3_writephy(tp, MII_TG3_DSP_CONTROL, 0x0000); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); tg3_writephy(tp, MII_CTRL1000, phy9_orig); @@ -2522,10 +2534,10 @@ static int tg3_phy_reset(struct tg3 *tp) out: if ((tp->phy_flags & TG3_PHYFLG_ADC_BUG) && - !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + !tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_phydsp_write(tp, 0x201f, 0x2aaa); tg3_phydsp_write(tp, 0x000a, 0x0323); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } if (tp->phy_flags & TG3_PHYFLG_5704_A0_BUG) { @@ -2534,14 +2546,14 @@ out: } if (tp->phy_flags & TG3_PHYFLG_BER_BUG) { - if (!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + if (!tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_phydsp_write(tp, 0x000a, 0x310b); tg3_phydsp_write(tp, 0x201f, 0x9506); tg3_phydsp_write(tp, 0x401f, 0x14e2); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } } else if (tp->phy_flags & TG3_PHYFLG_JITTER_BUG) { - if (!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + if (!tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x000a); if (tp->phy_flags & TG3_PHYFLG_ADJUST_TRIM) { tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x110b); @@ -2550,7 +2562,7 @@ out: } else tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x010b); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } } @@ -3967,7 +3979,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl) tw32(TG3_CPMU_EEE_MODE, tr32(TG3_CPMU_EEE_MODE) & ~TG3_CPMU_EEEMD_LPI_ENABLE); - err = TG3_PHY_AUXCTL_SMDSP_ENABLE(tp); + err = tg3_phy_toggle_auxctl_smdsp(tp, true); if (!err) { u32 err2; @@ -4000,7 +4012,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl) MII_TG3_DSP_CH34TP2_HIBW01); } - err2 = TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + err2 = tg3_phy_toggle_auxctl_smdsp(tp, false); if (!err) err = err2; } @@ -6703,6 +6715,9 @@ static void tg3_poll_controller(struct net_device *dev) int i; struct tg3 *tp = netdev_priv(dev); + if (tg3_irq_sync(tp)) + return; + for (i = 0; i < tp->irq_cnt; i++) tg3_interrupt(tp->napi[i].irq_vec, &tp->napi[i]); } @@ -15806,6 +15821,7 @@ static int __devinit tg3_init_one(struct pci_dev *pdev, tp->pm_cap = pm_cap; tp->rx_mode = TG3_DEF_RX_MODE; tp->tx_mode = TG3_DEF_TX_MODE; + tp->irq_sync = 1; if (tg3_debug > 0) tp->msg_enable = tg3_debug; diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index 16814b3..e29c1b6 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -546,6 +546,10 @@ static int desc_get_rx_status(struct xgmac_priv *priv, struct xgmac_dma_desc *p) return -1; } + /* All frames should fit into a single buffer */ + if (!(status & RXDESC_FIRST_SEG) || !(status & RXDESC_LAST_SEG)) + return -1; + /* Check if packet has checksum already */ if ((status & RXDESC_FRAME_TYPE) && (status & RXDESC_EXT_STATUS) && !(ext_status & RXDESC_IP_PAYLOAD_MASK)) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index edd9cb8..aa9122f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1435,7 +1435,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) } #ifdef CONFIG_RFS_ACCEL - priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->rx_ring_num); + priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool); if (!priv->dev->rx_cpu_rmap) goto err; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 10bba09..2af24ba 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -630,10 +630,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->tx_csum++; } - /* Copy dst mac address to wqe */ - ethh = (struct ethhdr *)skb->data; - tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest); - tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2)); + if (mlx4_is_mfunc(mdev->dev) || priv->validate_loopback) { + /* Copy dst mac address to wqe. This allows loopback in eSwitch, + * so that VFs and PF can communicate with each other + */ + ethh = (struct ethhdr *)skb->data; + tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest); + tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2)); + } + /* Handle LSO (TSO) packets */ if (lso_header_size) { /* Mark opcode as LSO */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2f816c6..8ca1ed8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1630,15 +1630,8 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) int i; if (msi_x) { - /* In multifunction mode each function gets 2 msi-X vectors - * one for data path completions anf the other for asynch events - * or command completions */ - if (mlx4_is_mfunc(dev)) { - nreq = 2; - } else { - nreq = min_t(int, dev->caps.num_eqs - - dev->caps.reserved_eqs, nreq); - } + nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, + nreq); entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c index bc165f4d..695667d 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c @@ -144,7 +144,7 @@ void netxen_release_tx_buffers(struct netxen_adapter *adapter) buffrag->length, PCI_DMA_TODEVICE); buffrag->dma = 0ULL; } - for (j = 0; j < cmd_buf->frag_count; j++) { + for (j = 1; j < cmd_buf->frag_count; j++) { buffrag++; if (buffrag->dma) { pci_unmap_page(adapter->pdev, buffrag->dma, diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index a77c558..d6a8218 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1963,10 +1963,12 @@ unwind: while (--i >= 0) { nf = &pbuf->frag_array[i+1]; pci_unmap_page(pdev, nf->dma, nf->length, PCI_DMA_TODEVICE); + nf->dma = 0ULL; } nf = &pbuf->frag_array[0]; pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE); + nf->dma = 0ULL; out_err: return -ENOMEM; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index df7bbba..6c1c396 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -6088,13 +6088,6 @@ process_pkt: tp->rx_stats.bytes += pkt_size; u64_stats_update_end(&tp->rx_stats.syncp); } - - /* Work around for AMD plateform. */ - if ((desc->opts2 & cpu_to_le32(0xfffe000)) && - (tp->mac_version == RTL_GIGA_MAC_VER_05)) { - desc->opts2 = 0; - cur_rx++; - } } count = cur_rx - tp->cur_rx; diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 0459c09..046526e0 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1802,7 +1802,7 @@ static void rhine_tx(struct net_device *dev) rp->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); } - dev_kfree_skb_irq(rp->tx_skbuff[entry]); + dev_kfree_skb(rp->tx_skbuff[entry]); rp->tx_skbuff[entry] = NULL; entry = (++rp->dirty_tx) % TX_RING_SIZE; } @@ -2011,11 +2011,7 @@ static void rhine_slow_event_task(struct work_struct *work) if (intr_status & IntrPCIErr) netif_warn(rp, hw, dev, "PCI error\n"); - napi_disable(&rp->napi); - rhine_irq_disable(rp); - /* Slow and safe. Consider __napi_schedule as a replacement ? */ - napi_enable(&rp->napi); - napi_schedule(&rp->napi); + iowrite16(RHINE_EVENT & 0xffff, rp->base + IntrEnable); out_unlock: mutex_unlock(&rp->task_lock); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index e2a06fd..ba61c33 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -77,6 +77,11 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb_orphan(skb); + /* Before queueing this packet to netif_rx(), + * make sure dst is refcounted. + */ + skb_dst_force(skb); + skb->protocol = eth_type_trans(skb, dev); /* it's OK to use per_cpu_ptr() because BHs are off */ diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 66a9bfe..666fc20 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -628,6 +628,7 @@ void macvlan_common_setup(struct net_device *dev) ether_setup(dev); dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); + dev->priv_flags |= IFF_UNICAST_FLT; dev->netdev_ops = &macvlan_netdev_ops; dev->destructor = free_netdev; dev->header_ops = &macvlan_hard_header_ops, @@ -822,7 +823,10 @@ static int macvlan_changelink(struct net_device *dev, static size_t macvlan_get_size(const struct net_device *dev) { - return nla_total_size(4); + return (0 + + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + ); } static int macvlan_fill_info(struct sk_buff *skb, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 5c05572..2603b99 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1021,7 +1021,15 @@ ppp_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return err; } +static struct lock_class_key ppp_tx_busylock; +static int ppp_dev_init(struct net_device *dev) +{ + dev->qdisc_tx_busylock = &ppp_tx_busylock; + return 0; +} + static const struct net_device_ops ppp_netdev_ops = { + .ndo_init = ppp_dev_init, .ndo_start_xmit = ppp_start_xmit, .ndo_do_ioctl = ppp_net_ioctl, }; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index f8cd61f..8a11070 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1008,6 +1008,8 @@ static int team_port_del(struct team *team, struct net_device *port_dev) netdev_set_master(port_dev, NULL); team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); + dev_uc_unsync(port_dev, dev); + dev_mc_unsync(port_dev, dev); dev_close(port_dev); team_port_leave(team, port); team_port_set_orig_mac(port); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3a16d4f..ef7710f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -421,6 +421,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) goto drop; skb_orphan(skb); + nf_reset(skb); + /* Enqueue packet */ skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb); diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 94b79c3..9d7f172 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -151,6 +151,9 @@ void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb); /* Notify xenvif that ring now has space to send an skb to the frontend */ void xenvif_notify_tx_completion(struct xenvif *vif); +/* Prevent the device from generating any further traffic. */ +void xenvif_carrier_off(struct xenvif *vif); + /* Returns number of ring slots required to send an skb to the frontend */ unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index b7d41f8..221f426 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -132,6 +132,7 @@ static void xenvif_up(struct xenvif *vif) static void xenvif_down(struct xenvif *vif) { disable_irq(vif->irq); + del_timer_sync(&vif->credit_timeout); xen_netbk_deschedule_xenvif(vif); xen_netbk_remove_xenvif(vif); } @@ -343,23 +344,26 @@ err: return err; } -void xenvif_disconnect(struct xenvif *vif) +void xenvif_carrier_off(struct xenvif *vif) { struct net_device *dev = vif->dev; - if (netif_carrier_ok(dev)) { - rtnl_lock(); - netif_carrier_off(dev); /* discard queued packets */ - if (netif_running(dev)) - xenvif_down(vif); - rtnl_unlock(); - xenvif_put(vif); - } + + rtnl_lock(); + netif_carrier_off(dev); /* discard queued packets */ + if (netif_running(dev)) + xenvif_down(vif); + rtnl_unlock(); + xenvif_put(vif); +} + +void xenvif_disconnect(struct xenvif *vif) +{ + if (netif_carrier_ok(vif->dev)) + xenvif_carrier_off(vif); atomic_dec(&vif->refcnt); wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0); - del_timer_sync(&vif->credit_timeout); - if (vif->irq) unbind_from_irqhandler(vif->irq, vif); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 682633b..6aa059e 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -146,7 +146,8 @@ void xen_netbk_remove_xenvif(struct xenvif *vif) atomic_dec(&netbk->netfront_count); } -static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx); +static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx, + u8 status); static void make_tx_response(struct xenvif *vif, struct xen_netif_tx_request *txp, s8 st); @@ -850,7 +851,7 @@ static void netbk_tx_err(struct xenvif *vif, do { make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - if (cons >= end) + if (cons == end) break; txp = RING_GET_REQUEST(&vif->tx, cons++); } while (1); @@ -859,6 +860,13 @@ static void netbk_tx_err(struct xenvif *vif, xenvif_put(vif); } +static void netbk_fatal_tx_err(struct xenvif *vif) +{ + netdev_err(vif->dev, "fatal error; disabling device\n"); + xenvif_carrier_off(vif); + xenvif_put(vif); +} + static int netbk_count_requests(struct xenvif *vif, struct xen_netif_tx_request *first, struct xen_netif_tx_request *txp, @@ -872,29 +880,33 @@ static int netbk_count_requests(struct xenvif *vif, do { if (frags >= work_to_do) { - netdev_dbg(vif->dev, "Need more frags\n"); - return -frags; + netdev_err(vif->dev, "Need more frags\n"); + netbk_fatal_tx_err(vif); + return -ENODATA; } if (unlikely(frags >= MAX_SKB_FRAGS)) { - netdev_dbg(vif->dev, "Too many frags\n"); - return -frags; + netdev_err(vif->dev, "Too many frags\n"); + netbk_fatal_tx_err(vif); + return -E2BIG; } memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags), sizeof(*txp)); if (txp->size > first->size) { - netdev_dbg(vif->dev, "Frags galore\n"); - return -frags; + netdev_err(vif->dev, "Frag is bigger than frame.\n"); + netbk_fatal_tx_err(vif); + return -EIO; } first->size -= txp->size; frags++; if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) { - netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n", + netdev_err(vif->dev, "txp->offset: %x, size: %u\n", txp->offset, txp->size); - return -frags; + netbk_fatal_tx_err(vif); + return -EINVAL; } } while ((txp++)->flags & XEN_NETTXF_more_data); return frags; @@ -937,7 +949,7 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk, pending_idx = netbk->pending_ring[index]; page = xen_netbk_alloc_page(netbk, skb, pending_idx); if (!page) - return NULL; + goto err; gop->source.u.ref = txp->gref; gop->source.domid = vif->domid; @@ -959,6 +971,17 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk, } return gop; +err: + /* Unwind, freeing all pages and sending error responses. */ + while (i-- > start) { + xen_netbk_idx_release(netbk, frag_get_pending_idx(&frags[i]), + XEN_NETIF_RSP_ERROR); + } + /* The head too, if necessary. */ + if (start) + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR); + + return NULL; } static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, @@ -967,30 +990,20 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, { struct gnttab_copy *gop = *gopp; u16 pending_idx = *((u16 *)skb->data); - struct pending_tx_info *pending_tx_info = netbk->pending_tx_info; - struct xenvif *vif = pending_tx_info[pending_idx].vif; - struct xen_netif_tx_request *txp; struct skb_shared_info *shinfo = skb_shinfo(skb); int nr_frags = shinfo->nr_frags; int i, err, start; /* Check status of header. */ err = gop->status; - if (unlikely(err)) { - pending_ring_idx_t index; - index = pending_index(netbk->pending_prod++); - txp = &pending_tx_info[pending_idx].req; - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - netbk->pending_ring[index] = pending_idx; - xenvif_put(vif); - } + if (unlikely(err)) + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR); /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); for (i = start; i < nr_frags; i++) { int j, newerr; - pending_ring_idx_t index; pending_idx = frag_get_pending_idx(&shinfo->frags[i]); @@ -999,16 +1012,12 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, if (likely(!newerr)) { /* Had a previous error? Invalidate this fragment. */ if (unlikely(err)) - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); continue; } /* Error on this fragment: respond to client with an error. */ - txp = &netbk->pending_tx_info[pending_idx].req; - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - index = pending_index(netbk->pending_prod++); - netbk->pending_ring[index] = pending_idx; - xenvif_put(vif); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR); /* Not the first error? Preceding frags already invalidated. */ if (err) @@ -1016,10 +1025,10 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, /* First error: invalidate header and preceding fragments. */ pending_idx = *((u16 *)skb->data); - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); for (j = start; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); } /* Remember the error: invalidate all subsequent fragments. */ @@ -1053,7 +1062,7 @@ static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb) /* Take an extra reference to offset xen_netbk_idx_release */ get_page(netbk->mmap_pages[pending_idx]); - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); } } @@ -1066,7 +1075,8 @@ static int xen_netbk_get_extras(struct xenvif *vif, do { if (unlikely(work_to_do-- <= 0)) { - netdev_dbg(vif->dev, "Missing extra info\n"); + netdev_err(vif->dev, "Missing extra info\n"); + netbk_fatal_tx_err(vif); return -EBADR; } @@ -1075,8 +1085,9 @@ static int xen_netbk_get_extras(struct xenvif *vif, if (unlikely(!extra.type || extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { vif->tx.req_cons = ++cons; - netdev_dbg(vif->dev, + netdev_err(vif->dev, "Invalid extra type: %d\n", extra.type); + netbk_fatal_tx_err(vif); return -EINVAL; } @@ -1092,13 +1103,15 @@ static int netbk_set_skb_gso(struct xenvif *vif, struct xen_netif_extra_info *gso) { if (!gso->u.gso.size) { - netdev_dbg(vif->dev, "GSO size must not be zero.\n"); + netdev_err(vif->dev, "GSO size must not be zero.\n"); + netbk_fatal_tx_err(vif); return -EINVAL; } /* Currently only TCPv4 S.O. is supported. */ if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) { - netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + netbk_fatal_tx_err(vif); return -EINVAL; } @@ -1235,9 +1248,25 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) /* Get a netif from the list with work to do. */ vif = poll_net_schedule_list(netbk); + /* This can sometimes happen because the test of + * list_empty(net_schedule_list) at the top of the + * loop is unlocked. Just go back and have another + * look. + */ if (!vif) continue; + if (vif->tx.sring->req_prod - vif->tx.req_cons > + XEN_NETIF_TX_RING_SIZE) { + netdev_err(vif->dev, + "Impossible number of requests. " + "req_prod %d, req_cons %d, size %ld\n", + vif->tx.sring->req_prod, vif->tx.req_cons, + XEN_NETIF_TX_RING_SIZE); + netbk_fatal_tx_err(vif); + continue; + } + RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do); if (!work_to_do) { xenvif_put(vif); @@ -1265,17 +1294,14 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) work_to_do = xen_netbk_get_extras(vif, extras, work_to_do); idx = vif->tx.req_cons; - if (unlikely(work_to_do < 0)) { - netbk_tx_err(vif, &txreq, idx); + if (unlikely(work_to_do < 0)) continue; - } } ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do); - if (unlikely(ret < 0)) { - netbk_tx_err(vif, &txreq, idx - ret); + if (unlikely(ret < 0)) continue; - } + idx += ret; if (unlikely(txreq.size < ETH_HLEN)) { @@ -1287,11 +1313,11 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) /* No crossing a page as the payload mustn't fragment. */ if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) { - netdev_dbg(vif->dev, + netdev_err(vif->dev, "txreq.offset: %x, size: %u, end: %lu\n", txreq.offset, txreq.size, (txreq.offset&~PAGE_MASK) + txreq.size); - netbk_tx_err(vif, &txreq, idx); + netbk_fatal_tx_err(vif); continue; } @@ -1319,8 +1345,8 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; if (netbk_set_skb_gso(vif, skb, gso)) { + /* Failure in netbk_set_skb_gso is fatal. */ kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); continue; } } @@ -1419,7 +1445,7 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk) txp->size -= data_len; } else { /* Schedule a response immediately. */ - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); } if (txp->flags & XEN_NETTXF_csum_blank) @@ -1474,7 +1500,8 @@ static void xen_netbk_tx_action(struct xen_netbk *netbk) } -static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx) +static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx, + u8 status) { struct xenvif *vif; struct pending_tx_info *pending_tx_info; @@ -1488,7 +1515,7 @@ static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx) vif = pending_tx_info->vif; - make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY); + make_tx_response(vif, &pending_tx_info->req, status); index = pending_index(netbk->pending_prod++); netbk->pending_ring[index] = pending_idx; diff --git a/fs/splice.c b/fs/splice.c index 41514dd..c69fbb7 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -696,8 +696,10 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, return -EINVAL; more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0; - if (sd->len < sd->total_len) + + if (sd->len < sd->total_len && pipe->nrbufs > 1) more |= MSG_SENDPAGE_NOTLAST; + return file->f_op->sendpage(file, buf->page, buf->offset, sd->len, &pos, more); } diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 561e130..9b0c614 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -327,7 +327,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; - unsigned char *rawp; + unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer @@ -340,8 +340,8 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, return; } - rawp = skb->data; - if (*(unsigned short *) rawp == 0xFFFF) + rawp = (unsigned short *)(vhdr + 1); + if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without diff --git a/include/net/dst.h b/include/net/dst.h index 621e351..3e3fffe 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -36,13 +36,9 @@ struct dst_entry { struct net_device *dev; struct dst_ops *ops; unsigned long _metrics; - union { - unsigned long expires; - /* point to where the dst_entry copied from */ - struct dst_entry *from; - }; + unsigned long expires; struct dst_entry *path; - void *__pad0; + struct dst_entry *from; #ifdef CONFIG_XFRM struct xfrm_state *xfrm; #else diff --git a/include/net/icmp.h b/include/net/icmp.h index 9ac2524..081439f 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -41,6 +41,7 @@ struct net; extern void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info); extern int icmp_rcv(struct sk_buff *skb); +extern void icmp_err(struct sk_buff *, u32 info); extern int icmp_init(void); extern void icmp_out_count(struct net *net, unsigned char type); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 9e34c87..f071f50 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -28,16 +28,16 @@ struct inet_hashinfo; -/* I have no idea if this is a good hash for v6 or not. -DaveM */ static inline unsigned int inet6_ehashfn(struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { - u32 ports = (lport ^ (__force u16)fport); + u32 ports = (((u32)lport) << 16) | (__force u32)fport; return jhash_3words((__force u32)laddr->s6_addr32[3], - (__force u32)faddr->s6_addr32[3], - ports, inet_ehash_secret + net_hash_mix(net)); + ipv6_addr_jhash(faddr), + ports, + inet_ehash_secret + net_hash_mix(net)); } static inline int inet6_sk_ehashfn(const struct sock *sk) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ba1d361..1832927 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -318,6 +318,7 @@ extern void inet_csk_reqsk_queue_prune(struct sock *parent, const unsigned long max_rto); extern void inet_csk_destroy_sock(struct sock *sk); +extern void inet_csk_prepare_forced_close(struct sock *sk); /* * LISTEN is a special case for poll.. diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 613cfa4..8eac4a9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -203,6 +203,7 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, extern int inet_sk_rebuild_header(struct sock *sk); extern u32 inet_ehash_secret; +extern u32 ipv6_hash_secret; extern void build_ehash_secret(void); static inline unsigned int inet_ehashfn(struct net *net, diff --git a/include/net/ip.h b/include/net/ip.h index 5a5d84d..2d03843 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -141,6 +141,8 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) extern int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +extern void ip4_datagram_release_cb(struct sock *sk); + struct ip_reply_arg { struct kvec iov[1]; int flags; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 9fc7114..0235de8 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -156,50 +156,35 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) static inline void rt6_clean_expires(struct rt6_info *rt) { - if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) - dst_release(rt->dst.from); - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.from = NULL; } static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires) { - if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) - dst_release(rt->dst.from); - - rt->rt6i_flags |= RTF_EXPIRES; rt->dst.expires = expires; + rt->rt6i_flags |= RTF_EXPIRES; } -static inline void rt6_update_expires(struct rt6_info *rt, int timeout) +static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) { - if (!(rt->rt6i_flags & RTF_EXPIRES)) { - if (rt->dst.from) - dst_release(rt->dst.from); - /* dst_set_expires relies on expires == 0 - * if it has not been set previously. - */ - rt->dst.expires = 0; - } - - dst_set_expires(&rt->dst, timeout); - rt->rt6i_flags |= RTF_EXPIRES; + struct rt6_info *rt; + + for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); + rt = (struct rt6_info *)rt->dst.from); + if (rt && rt != rt0) + rt0->dst.expires = rt->dst.expires; + + dst_set_expires(&rt0->dst, timeout); + rt0->rt6i_flags |= RTF_EXPIRES; } static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) { struct dst_entry *new = (struct dst_entry *) from; - if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) { - if (new == rt->dst.from) - return; - dst_release(rt->dst.from); - } - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.from = new; dst_hold(new); + rt->dst.from = new; } struct fib6_walker_t { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 01c34b3..640591f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -15,6 +15,7 @@ #include <linux/ipv6.h> #include <linux/hardirq.h> +#include <linux/jhash.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/flow.h> @@ -432,6 +433,17 @@ static inline u32 ipv6_addr_hash(const struct in6_addr *a) #endif } +/* more secured version of ipv6_addr_hash() */ +static inline u32 ipv6_addr_jhash(const struct in6_addr *a) +{ + u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1]; + + return jhash_3words(v, + (__force u32)a->s6_addr32[2], + (__force u32)a->s6_addr32[3], + ipv6_hash_secret); +} + static inline bool ipv6_addr_loopback(const struct in6_addr *a) { return (a->s6_addr32[0] | a->s6_addr32[1] | diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 96a3b5c..826a541 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -77,6 +77,13 @@ struct ra_msg { __be32 retrans_timer; }; +struct rd_msg { + struct icmp6hdr icmph; + struct in6_addr target; + struct in6_addr dest; + __u8 opt[0]; +}; + struct nd_opt_hdr { __u8 nd_opt_type; __u8 nd_opt_len; diff --git a/include/net/sock.h b/include/net/sock.h index adb7da2..450a2af 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1012,7 +1012,7 @@ static inline void sk_refcnt_debug_dec(struct sock *sk) sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks)); } -inline void sk_refcnt_debug_release(const struct sock *sk) +static inline void sk_refcnt_debug_release(const struct sock *sk) { if (atomic_read(&sk->sk_refcnt) != 1) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 469daab..1476f26 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -119,7 +119,7 @@ batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) unsigned int msecs; msecs = atomic_read(&bat_priv->orig_interval) - BATADV_JITTER; - msecs += (random32() % 2 * BATADV_JITTER); + msecs += random32() % (2 * BATADV_JITTER); return jiffies + msecs_to_jiffies(msecs); } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 68e8f36..fe43bc7 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -265,6 +265,9 @@ static int br_parse_ip_options(struct sk_buff *skb) struct net_device *dev = skb->dev; u32 len; + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto inhdr_error; + iph = ip_hdr(skb); opt = &(IPCB(skb)->opt); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index fd30a60..a8aa2d5 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -16,6 +16,7 @@ #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> @@ -40,6 +41,7 @@ static void br_send_bpdu(struct net_bridge_port *p, skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); memcpy(__skb_put(skb, length), data, length); diff --git a/net/core/datagram.c b/net/core/datagram.c index 0337e2b..368f9c3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -187,7 +187,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, skb_queue_walk(queue, skb) { *peeked = skb->peeked; if (flags & MSG_PEEK) { - if (*off >= skb->len) { + if (*off >= skb->len && skb->len) { *off -= skb->len; continue; } diff --git a/net/core/dev.c b/net/core/dev.c index 1dce5b5..c41efb7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3296,6 +3296,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: + ret = NET_RX_SUCCESS; goto unlock; case RX_HANDLER_ANOTHER: goto another_round; diff --git a/net/core/dst.c b/net/core/dst.c index 56d6361..c63220e 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -179,6 +179,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst_init_metrics(dst, dst_default_metrics, true); dst->expires = 0UL; dst->path = dst; + dst->from = NULL; #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif diff --git a/net/core/pktgen.c b/net/core/pktgen.c index e356b8d..d7881b2 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1797,10 +1797,13 @@ static ssize_t pktgen_thread_write(struct file *file, return -EFAULT; i += len; mutex_lock(&pktgen_thread_lock); - pktgen_add_device(t, f); + ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2c5a0a0..4908588 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -976,6 +976,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, * report anything. */ ivi.spoofchk = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) break; vf_mac.vf = diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9708777..043139d01 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1606,7 +1606,7 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct page *p = sk->sk_sndmsg_page; unsigned int off; @@ -1658,14 +1658,14 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd, static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, bool linear, + bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { - page = linear_to_page(page, len, &offset, skb, sk); + page = linear_to_page(page, len, &offset, sk); if (!page) return true; } @@ -1682,23 +1682,9 @@ static bool spd_fill_page(struct splice_pipe_desc *spd, return false; } -static inline void __segment_seek(struct page **page, unsigned int *poff, - unsigned int *plen, unsigned int off) -{ - unsigned long n; - - *poff += off; - n = *poff / PAGE_SIZE; - if (n) - *page = nth_page(*page, n); - - *poff = *poff % PAGE_SIZE; - *plen -= off; -} - static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, + unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) @@ -1713,23 +1699,19 @@ static bool __splice_segment(struct page *page, unsigned int poff, } /* ignore any bits we already processed */ - if (*off) { - __segment_seek(&page, &poff, &plen, *off); - *off = 0; - } + poff += *off; + plen -= *off; + *off = 0; do { unsigned int flen = min(*len, plen); - /* the linear region may spread across several pages */ - flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) return true; - - __segment_seek(&page, &poff, &plen, flen); + poff += flen; + plen -= flen; *len -= flen; - } while (*len && plen); return false; @@ -1753,7 +1735,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, + offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; @@ -1766,7 +1748,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, false, sk, pipe)) + offset, len, spd, false, sk, pipe)) return true; } diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 9d8755e..a2ad320 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -121,6 +121,9 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; + if (req->sdiag_family >= AF_MAX) + return -EINVAL; + hndl = sock_diag_lock_handler(req->sdiag_family); if (hndl == NULL) err = -ENOENT; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 81f2bb6..eb1b2eb 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -284,6 +284,7 @@ static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh, if (!netdev->dcbnl_ops->getpermhwaddr) return -EOPNOTSUPP; + memset(perm_addr, 0, sizeof(perm_addr)); netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr); @@ -1042,6 +1043,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getets) { struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); err = ops->ieee_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) @@ -1050,6 +1052,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getmaxrate) { struct ieee_maxrate maxrate; + memset(&maxrate, 0, sizeof(maxrate)); err = ops->ieee_getmaxrate(netdev, &maxrate); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, @@ -1061,6 +1064,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getpfc) { struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) @@ -1094,6 +1098,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); err = ops->ieee_peer_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) @@ -1102,6 +1107,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_peer_getpfc) { struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) @@ -1280,6 +1286,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) /* peer info if available */ if (ops->cee_peer_getpg) { struct cee_pg pg; + memset(&pg, 0, sizeof(pg)); err = ops->cee_peer_getpg(netdev, &pg); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg)) @@ -1288,6 +1295,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->cee_peer_getpfc) { struct cee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->cee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc)) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 176ecdb..4f9f5eb 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -439,8 +439,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: - bh_unlock_sock(newsk); - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); goto exit; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 56840b2..6e05981 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -585,7 +585,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newinet->inet_rcv_saddr = LOOPBACK4_IPV6; if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); goto out; } __inet6_hash(newsk, NULL); diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index 8c2251f..bba5f83 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -84,7 +84,7 @@ (memcmp(addr1, addr2, length >> 3) == 0) /* local link, i.e. FE80::/10 */ -#define is_addr_link_local(a) (((a)->s6_addr16[0]) == 0x80FE) +#define is_addr_link_local(a) (((a)->s6_addr16[0]) == htons(0xFE80)) /* * check whether we can compress the IID to 16 bits, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fe4582c..dfeb658 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -228,8 +228,12 @@ EXPORT_SYMBOL(inet_listen); u32 inet_ehash_secret __read_mostly; EXPORT_SYMBOL(inet_ehash_secret); +u32 ipv6_hash_secret __read_mostly; +EXPORT_SYMBOL(ipv6_hash_secret); + /* - * inet_ehash_secret must be set exactly once + * inet_ehash_secret must be set exactly once, and to a non nul value + * ipv6_hash_secret must be set exactly once. */ void build_ehash_secret(void) { @@ -239,7 +243,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - cmpxchg(&inet_ehash_secret, 0, rnd); + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) + get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); } EXPORT_SYMBOL(build_ehash_secret); @@ -1556,7 +1561,7 @@ static const struct net_protocol udp_protocol = { static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, - .err_handler = ping_err, + .err_handler = icmp_err, .no_policy = 1, .netns_ok = 1, }; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 424fafb..b28e863 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -85,3 +85,28 @@ out: return err; } EXPORT_SYMBOL(ip4_datagram_connect); + +void ip4_datagram_release_cb(struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; + struct flowi4 fl4; + struct rtable *rt; + + if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) + return; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_protocol, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + if (!IS_ERR(rt)) + __sk_dst_set(sk, &rt->dst); + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 17ff9fd..3ac5dff 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -934,6 +934,29 @@ error: goto drop; } +void icmp_err(struct sk_buff *skb, u32 info) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; + struct net *net = dev_net(skb->dev); + + /* + * Use ping_err to handle all icmp errors except those + * triggered by ICMP_ECHOREPLY which sent from kernel. + */ + if (icmph->type != ICMP_ECHOREPLY) { + ping_err(skb, info); + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0); +} + /* * This table is the definition of how we handle ICMP. */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0405cc8..567c31f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -679,6 +679,22 @@ void inet_csk_destroy_sock(struct sock *sk) } EXPORT_SYMBOL(inet_csk_destroy_sock); +/* This function allows to force a closure of a socket after the call to + * tcp/dccp_create_openreq_child(). + */ +void inet_csk_prepare_forced_close(struct sock *sk) +{ + /* sk_clone_lock locked the socket and set refcnt to 2 */ + bh_unlock_sock(sk); + sock_put(sk); + + /* The below has to be done to allow calling inet_csk_destroy_sock */ + sock_set_flag(sk, SOCK_DEAD); + percpu_counter_inc(sk->sk_prot->orphan_count); + inet_sk(sk)->inet_num = 0; +} +EXPORT_SYMBOL(inet_csk_prepare_forced_close); + int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) { struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b062a98..3ee08ce 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -946,8 +946,12 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev ptr--; } if (tunnel->parms.o_flags&GRE_CSUM) { + int offset = skb_transport_offset(skb); + *ptr = 0; - *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, + skb->len - offset, + 0)); } } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 14bbfcf..e95d72b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -590,7 +590,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_TTL: if (optlen < 1) goto e_inval; - if (val != -1 && (val < 0 || val > 255)) + if (val != -1 && (val < 1 || val > 255)) goto e_inval; inet->uc_ttl = val; break; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 6232d47..af8739a 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -328,8 +328,8 @@ void ping_err(struct sk_buff *skb, u32 info) struct iphdr *iph = (struct iphdr *)skb->data; struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); struct inet_sock *inet_sock; - int type = icmph->type; - int code = icmph->code; + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; @@ -744,6 +744,7 @@ struct proto ping_prot = { .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = ping_v4_hash, .unhash = ping_v4_unhash, .get_port = ping_v4_get_port, diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index d23c657..f9c0d05 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -894,6 +894,7 @@ struct proto raw_prot = { .recvmsg = raw_recvmsg, .bind = raw_bind, .backlog_rcv = raw_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw_sock), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 285a18f..39de0ca 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -912,6 +912,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct dst_entry *dst = &rt->dst; struct fib_result res; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + if (dst->dev->mtu < mtu) return; @@ -962,7 +965,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; @@ -975,6 +978,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) ip_rt_put(rt); } } + +void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; + struct dst_entry *dst; + bool new = false; + + bh_lock_sock(sk); + rt = (struct rtable *) __sk_dst_get(sk); + + if (sock_owned_by_user(sk) || !rt) { + __ipv4_sk_update_pmtu(skb, sk, mtu); + goto out; + } + + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + + if (!__sk_dst_check(sk, 0)) { + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); + + dst = dst_check(&rt->dst, 0); + if (!dst) { + if (new) + dst_release(&rt->dst); + + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + if (new) + __sk_dst_set(sk, &rt->dst); + +out: + bh_unlock_sock(sk); +} EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, @@ -1123,7 +1173,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) if (!mtu) mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu && rt_is_output_route(rt)) + if (mtu) return mtu; mtu = dst->dev->mtu; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b0b39f6..a07e91c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1454,12 +1454,12 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) } #endif -static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) +static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; - skb_queue_walk(&sk->sk_receive_queue, skb) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1467,6 +1467,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) *off = offset; return skb; } + /* This looks weird, but this can happen if TCP collapsing + * splitted a fat GRO packet, while we released socket lock + * in skb_splice_bits() + */ + sk_eat_skb(sk, skb, false); } return NULL; } @@ -1508,7 +1513,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } used = recv_actor(desc, skb, offset, len); - if (used < 0) { + if (used <= 0) { if (!copied) copied = used; break; @@ -1517,15 +1522,19 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, copied += used; offset += used; } - /* - * If recv_actor drops the lock (e.g. TCP splice + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ - skb = tcp_recv_skb(sk, seq-1, &offset); - if (!skb || (offset+1 != skb->len)) + skb = tcp_recv_skb(sk, seq - 1, &offset); + if (!skb) break; + /* TCP coalescing might have appended data to the skb. + * Try to splice more frags + */ + if (offset + 1 != skb->len) + continue; } if (tcp_hdr(skb)->fin) { sk_eat_skb(sk, skb, false); @@ -1542,8 +1551,10 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) + if (copied > 0) { + tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); + } return copied; } EXPORT_SYMBOL(tcp_read_sock); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1432cdb..fc582a7 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -309,6 +309,12 @@ void tcp_slow_start(struct tcp_sock *tp) { int cnt; /* increase in packets */ unsigned int delta = 0; + u32 snd_cwnd = tp->snd_cwnd; + + if (unlikely(!snd_cwnd)) { + pr_err_once("snd_cwnd is nul, please report this bug.\n"); + snd_cwnd = 1U; + } /* RFC3465: ABC Slow start * Increase only after a full MSS of bytes is acked @@ -323,7 +329,7 @@ void tcp_slow_start(struct tcp_sock *tp) if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh) cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */ else - cnt = tp->snd_cwnd; /* exponential increase */ + cnt = snd_cwnd; /* exponential increase */ /* RFC3465: ABC * We MAY increase by 2 if discovered delayed ack @@ -333,11 +339,11 @@ void tcp_slow_start(struct tcp_sock *tp) tp->bytes_acked = 0; tp->snd_cwnd_cnt += cnt; - while (tp->snd_cwnd_cnt >= tp->snd_cwnd) { - tp->snd_cwnd_cnt -= tp->snd_cwnd; + while (tp->snd_cwnd_cnt >= snd_cwnd) { + tp->snd_cwnd_cnt -= snd_cwnd; delta++; } - tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp); + tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_slow_start); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c92c4da..396c6ae 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3531,6 +3531,11 @@ static bool tcp_process_frto(struct sock *sk, int flag) } } else { if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { + if (!tcp_packets_in_flight(tp)) { + tcp_enter_frto_loss(sk, 2, flag); + return true; + } + /* Prevent sending of new data. */ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)); @@ -3579,6 +3584,24 @@ static bool tcp_process_frto(struct sock *sk, int flag) return false; } +/* RFC 5961 7 [ACK Throttling] */ +static void tcp_send_challenge_ack(struct sock *sk) +{ + /* unprotected vars, we dont care of overwrites */ + static u32 challenge_timestamp; + static unsigned int challenge_count; + u32 now = jiffies / HZ; + + if (now != challenge_timestamp) { + challenge_timestamp = now; + challenge_count = 0; + } + if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + tcp_send_ack(sk); + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3598,8 +3621,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* If the ack is older than previous acks * then we can probably ignore it. */ - if (before(ack, prior_snd_una)) + if (before(ack, prior_snd_una)) { + /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ + if (before(ack, prior_snd_una - tp->max_window)) { + tcp_send_challenge_ack(sk); + return -1; + } goto old_ack; + } /* If the ack includes data we haven't sent yet, discard * this segment (RFC793 Section 3.9). @@ -5271,23 +5300,6 @@ out: } #endif /* CONFIG_NET_DMA */ -static void tcp_send_challenge_ack(struct sock *sk) -{ - /* unprotected vars, we dont care of overwrites */ - static u32 challenge_timestamp; - static unsigned int challenge_count; - u32 now = jiffies / HZ; - - if (now != challenge_timestamp) { - challenge_timestamp = now; - challenge_count = 0; - } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); - tcp_send_ack(sk); - } -} - /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ @@ -5340,11 +5352,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, goto discard; } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 3: check security and precedence [ignored] */ /* step 4: Check for a SYN @@ -5518,6 +5525,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tcp_checksum_complete_user(sk, skb)) goto csum_error; + if ((int)skb->truesize > sk->sk_forward_alloc) + goto step5; + /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: @@ -5529,9 +5539,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); - if ((int)skb->truesize > sk->sk_forward_alloc) - goto step5; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ @@ -5579,6 +5586,11 @@ step5: if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5666,8 +5678,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, * the remote receives only the retransmitted (regular) SYNs: either * the original SYN-data or the corresponding SYN-ACK is lost. */ - syn_drop = (cookie->len <= 0 && data && - inet_csk(sk)->icsk_retransmits); + syn_drop = (cookie->len <= 0 && data && tp->total_retrans); tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); @@ -6106,6 +6117,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db7bfad..c883f4f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -379,11 +379,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk) && - type != ICMP_DEST_UNREACH && - code != ICMP_FRAG_NEEDED) - NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out; @@ -1537,10 +1536,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: - tcp_clear_xmit_timers(newsk); - tcp_cleanup_congestion_control(newsk); - bh_unlock_sock(newsk); - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6735bea..6a1cdc8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1342,8 +1342,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) return 0; } -/* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(struct sock *sk, int pmtu) +/* Calculate MSS not accounting any TCP options. */ +static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1372,13 +1372,17 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) /* Then reserve room for full set of TCP options and 8 bytes of data */ if (mss_now < 48) mss_now = 48; - - /* Now subtract TCP options size, not including SACKs */ - mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); - return mss_now; } +/* Calculate MSS. Not accounting for SACKs here. */ +int tcp_mtu_to_mss(struct sock *sk, int pmtu) +{ + /* Subtract TCP options size, not including SACKs */ + return __tcp_mtu_to_mss(sk, pmtu) - + (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); +} + /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { @@ -2914,7 +2918,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) */ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; - space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; syn_data = skb_copy_expand(syn, skb_headroom(syn), space, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2814f66..ee4b36a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1952,6 +1952,7 @@ struct proto udp_prot = { .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b10374d..fd82a30 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1736,7 +1736,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->rt6i_flags & flags) != flags) continue; - if ((noflags != 0) && ((rt->rt6i_flags & flags) != 0)) + if ((rt->rt6i_flags & noflags) != 0) continue; dst_hold(&rt->dst); break; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 24d69db..4d844d7 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -81,10 +81,22 @@ static inline struct sock *icmpv6_sk(struct net *net) return net->ipv6.icmp_sk[smp_processor_id()]; } +static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct net *net = dev_net(skb->dev); + + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, 0, 0); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); +} + static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, + .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index a52d864..b196852 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -270,7 +270,8 @@ int ip6_mc_input(struct sk_buff *skb) * IPv6 multicast router mode is now supported ;) */ if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && - !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&hdr->daddr) & + (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5b2d63e..3d485ec 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1287,10 +1287,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, cork->length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; - dst_exthdrlen = rt->dst.header_len; + dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2edce30..89dab79 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1333,6 +1333,12 @@ out: static void ndisc_redirect_rcv(struct sk_buff *skb) { + u8 *hdr; + struct ndisc_options ndopts; + struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); + u32 ndoptlen = skb->tail - (skb->transport_header + + offsetof(struct rd_msg, opt)); + #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: @@ -1349,6 +1355,17 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } + if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) + return; + + if (!ndopts.nd_opts_rh) + return; + + hdr = (u8 *)ndopts.nd_opts_rh; + hdr += 8; + if (!pskb_pull(skb, hdr - skb_transport_header(skb))) + return; + icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 070a3ce..103880b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -297,6 +297,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; + struct dst_entry *from = dst->from; if (rt->n) neigh_release(rt->n); @@ -309,8 +310,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } - if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) - dst_release(dst->from); + dst->from = NULL; + dst_release(from); if (rt6_has_peer(rt)) { struct inet_peer *peer = rt6_peer_ptr(rt); @@ -881,7 +882,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!rt->n && !(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_LOCAL))) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -1007,7 +1008,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags; - rt6_clean_expires(rt); rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -1810,8 +1810,6 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) rt6_set_from(rt, ort); - else - rt6_clean_expires(rt); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES @@ -1943,7 +1941,8 @@ void rt6_purge_dflt_routers(struct net *net) restart: read_lock_bh(&table->tb6_lock); for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); ip6_del_rt(rt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7e32d42..8b45fb4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1371,7 +1371,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #endif if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); goto out; } __inet6_hash(newsk, NULL); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f8c4c08..bf6912e 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -236,6 +236,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + if (likely(xdst->u.rt6.n)) + neigh_release(xdst->u.rt6.n); if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 286366e..e966602 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -355,6 +355,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh l2tp_xmit_skb(session, skb, session->hdr_len); sock_put(ps->tunnel_sock); + sock_put(sk); return error; diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index f30f6d4..c5e24c8 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -387,7 +387,7 @@ void mac802154_wpan_setup(struct net_device *dev) static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) { - return netif_rx(skb); + return netif_rx_ni(skb); } static int diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index e7ff694..7fe20d0 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1189,8 +1189,6 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; - u32 skip_addr4 = cb->args[2]; - u32 skip_addr6 = cb->args[3]; u32 iter_bkt; u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; @@ -1215,7 +1213,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < skip_addr4) + if (iter_addr4++ < cb->args[2]) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1231,7 +1229,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < skip_addr6) + if (iter_addr6++ < cb->args[3]) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1250,10 +1248,10 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, unlabel_staticlist_return: rcu_read_unlock(); - cb->args[0] = skip_bkt; - cb->args[1] = skip_chain; - cb->args[2] = skip_addr4; - cb->args[3] = skip_addr6; + cb->args[0] = iter_bkt; + cb->args[1] = iter_chain; + cb->args[2] = iter_addr4; + cb->args[3] = iter_addr6; return skb->len; } @@ -1273,12 +1271,9 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, { struct netlbl_unlhsh_walk_arg cb_arg; struct netlbl_unlhsh_iface *iface; - u32 skip_addr4 = cb->args[0]; - u32 skip_addr6 = cb->args[1]; - u32 iter_addr4 = 0; + u32 iter_addr4 = 0, iter_addr6 = 0; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) - u32 iter_addr6 = 0; struct netlbl_af6list *addr6; #endif @@ -1292,7 +1287,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, goto unlabel_staticlistdef_return; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < skip_addr4) + if (iter_addr4++ < cb->args[0]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, @@ -1305,7 +1300,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < skip_addr6) + if (iter_addr6++ < cb->args[1]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, @@ -1320,8 +1315,8 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, unlabel_staticlistdef_return: rcu_read_unlock(); - cb->args[0] = skip_addr4; - cb->args[1] = skip_addr6; + cb->args[0] = iter_addr4; + cb->args[1] = iter_addr6; return skb->len; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c5c9e2a..70f7e18 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2443,13 +2443,15 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); - memset(&req_u, 0, sizeof(req_u)); - - if (po->rx_ring.pg_vec) + if (po->rx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); + } - if (po->tx_ring.pg_vec) + if (po->tx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); + } fanout_release(sk); diff --git a/net/rds/message.c b/net/rds/message.c index f0a4658..aff589c 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -197,6 +197,9 @@ struct rds_message *rds_message_alloc(unsigned int extra_len, gfp_t gfp) { struct rds_message *rm; + if (extra_len > KMALLOC_MAX_SIZE - sizeof(struct rds_message)) + return NULL; + rm = kzalloc(sizeof(struct rds_message) + extra_len, gfp); if (!rm) goto out; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 9d75b77..e9ea2f3 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -874,7 +874,7 @@ ok: q->now = psched_get_time(); start_at = jiffies; - next_event = q->now + 5 * PSCHED_TICKS_PER_SEC; + next_event = q->now + 5LLU * PSCHED_TICKS_PER_SEC; for (level = 0; level < TC_HTB_MAXDEPTH; level++) { /* common case optimization - skip event handler quickly */ diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 68a385d..58cd035 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -248,6 +248,8 @@ void sctp_endpoint_free(struct sctp_endpoint *ep) /* Final destructor for endpoint. */ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) { + int i; + SCTP_ASSERT(ep->base.dead, "Endpoint is not dead", return); /* Free up the HMAC transform. */ @@ -270,6 +272,9 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) sctp_inq_free(&ep->base.inqueue); sctp_bind_addr_free(&ep->base.bind_addr); + for (i = 0; i < SCTP_HOW_MANY_SECRETS; ++i) + memset(&ep->secret_key[i], 0, SCTP_SECRET_SIZE); + /* Remove and free the port */ if (sctp_sk(ep->base.sk)->bind_hash) sctp_put_port(ep->base.sk); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index e7aa177c..e0902c9 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -223,7 +223,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) /* Free the outqueue structure and any related pending chunks. */ -void sctp_outq_teardown(struct sctp_outq *q) +static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; @@ -276,8 +276,6 @@ void sctp_outq_teardown(struct sctp_outq *q) sctp_chunk_free(chunk); } - q->error = 0; - /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); @@ -285,11 +283,17 @@ void sctp_outq_teardown(struct sctp_outq *q) } } +void sctp_outq_teardown(struct sctp_outq *q) +{ + __sctp_outq_teardown(q); + sctp_outq_init(q->asoc, q); +} + /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ - sctp_outq_teardown(q); + __sctp_outq_teardown(q); /* If we were kmalloc()'d, free the memory. */ if (q->malloced) diff --git a/net/sctp/probe.c b/net/sctp/probe.c index bc6cd75..5f7518d 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -122,7 +122,8 @@ static const struct file_operations sctpprobe_fops = { .llseek = noop_llseek, }; -sctp_disposition_t jsctp_sf_eat_sack(const struct sctp_endpoint *ep, +sctp_disposition_t jsctp_sf_eat_sack(struct net *net, + const struct sctp_endpoint *ep, const struct sctp_association *asoc, const sctp_subtype_t type, void *arg, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index cb54123..d32d86d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3375,7 +3375,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey); out: - kfree(authkey); + kzfree(authkey); return ret; } -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html