diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 10742902146f..b522883a5a84 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -478,6 +478,15 @@ tcp_syn_retries - INTEGER tcp_timestamps - BOOLEAN Enable timestamps as defined in RFC1323. +tcp_min_tso_segs - INTEGER + Minimal number of segments per TSO frame. + Since linux-3.12, TCP does an automatic sizing of TSO frames, + depending on flow rate, instead of filling 64Kbytes packets. + For specific usages, it's possible to force TCP to build big + TSO frames. Note that TCP stack might split too big TSO packets + if available window is too small. + Default: 2 + tcp_tso_win_divisor - INTEGER This allows control over what percentage of the congestion window can be consumed by a single TSO frame. diff --git a/Makefile b/Makefile index e87ba831bd2d..686adf7f2035 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 11 -SUBLEVEL = 6 +SUBLEVEL = 7 EXTRAVERSION = NAME = Linux for Workgroups diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts index ff1aea0ee043..72693a69f830 100644 --- a/arch/arm/boot/dts/integratorcp.dts +++ b/arch/arm/boot/dts/integratorcp.dts @@ -9,11 +9,6 @@ model = "ARM Integrator/CP"; compatible = "arm,integrator-cp"; - aliases { - arm,timer-primary = &timer2; - arm,timer-secondary = &timer1; - }; - chosen { bootargs = "root=/dev/ram0 console=ttyAMA0,38400n8 earlyprintk"; }; @@ -24,14 +19,18 @@ }; timer0: timer@13000000 { + /* TIMER0 runs @ 25MHz */ compatible = "arm,integrator-cp-timer"; + status = "disabled"; }; timer1: timer@13000100 { + /* TIMER1 runs @ 1MHz */ compatible = "arm,integrator-cp-timer"; }; timer2: timer@13000200 { + /* TIMER2 runs @ 1MHz */ compatible = "arm,integrator-cp-timer"; }; diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index f1d96d4e8092..73ddd7239b33 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned int i, unsigned int n, unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; @@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task, unsigned int i, unsigned int n, const unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { pr_warning("%s called with max args %d, handling only %d\n", __func__, i + n, SYSCALL_MAX_ARGS); diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 08ae128cce9b..c73fc2b74de2 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -65,6 +65,7 @@ void proc_fork_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -80,6 +81,7 @@ void proc_fork_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ /* If cn_netlink_send() failed, the data is not sent */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -96,6 +98,7 @@ void proc_exec_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -106,6 +109,7 @@ void proc_exec_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -122,6 +126,7 @@ void proc_id_connector(struct task_struct *task, int which_id) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->what = which_id; ev->event_data.id.process_pid = task->pid; ev->event_data.id.process_tgid = task->tgid; @@ -145,6 +150,7 @@ void proc_id_connector(struct task_struct *task, int which_id) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -160,6 +166,7 @@ void proc_sid_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -170,6 +177,7 @@ void proc_sid_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -185,6 +193,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -203,6 +212,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -218,6 +228,7 @@ void proc_comm_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -229,6 +240,7 @@ void proc_comm_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -244,6 +256,7 @@ void proc_coredump_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -254,6 +267,7 @@ void proc_coredump_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -269,6 +283,7 @@ void proc_exit_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -281,6 +296,7 @@ void proc_exit_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -304,6 +320,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -313,6 +330,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 6ecfa758942c..0daa11e418b1 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -157,17 +157,18 @@ static int cn_call_callback(struct sk_buff *skb) static void cn_rx_skb(struct sk_buff *__skb) { struct nlmsghdr *nlh; - int err; struct sk_buff *skb; + int len, err; skb = skb_get(__skb); if (skb->len >= NLMSG_HDRLEN) { nlh = nlmsg_hdr(skb); + len = nlmsg_len(nlh); - if (nlh->nlmsg_len < sizeof(struct cn_msg) || + if (len < (int)sizeof(struct cn_msg) || skb->len < nlh->nlmsg_len || - nlh->nlmsg_len > CONNECTOR_MAX_MSG_SIZE) { + len > CONNECTOR_MAX_MSG_SIZE) { kfree_skb(skb); return; } diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c index 761c4705dfbb..baf301f36b42 100644 --- a/drivers/gpio/gpio-lynxpoint.c +++ b/drivers/gpio/gpio-lynxpoint.c @@ -248,14 +248,15 @@ static void lp_gpio_irq_handler(unsigned irq, struct irq_desc *desc) struct lp_gpio *lg = irq_data_get_irq_handler_data(data); struct irq_chip *chip = irq_data_get_irq_chip(data); u32 base, pin, mask; - unsigned long reg, pending; + unsigned long reg, ena, pending; unsigned virq; /* check from GPIO controller which pin triggered the interrupt */ for (base = 0; base < lg->chip.ngpio; base += 32) { reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT); + ena = lp_gpio_reg(&lg->chip, base, LP_INT_ENABLE); - while ((pending = inl(reg))) { + while ((pending = (inl(reg) & inl(ena)))) { pin = __ffs(pending); mask = BIT(pin); /* Clear before handling so we don't lose an edge */ diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index cd82eb44e4c4..7c9f053556f2 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -393,6 +393,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc = &priv->hw[priv->head]; + /* Initialize the DMA buffer */ + memset(priv->dma_buffer, 0, sizeof(priv->dma_buffer)); + /* Initialize the descriptor */ memset(desc, 0, sizeof(struct ismt_desc)); desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 4caa8e6d59d7..2d2b1b7588d7 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -269,6 +269,14 @@ static chunk_t area_location(struct pstore *ps, chunk_t area) return NUM_SNAPSHOT_HDR_CHUNKS + ((ps->exceptions_per_area + 1) * area); } +static void skip_metadata(struct pstore *ps) +{ + uint32_t stride = ps->exceptions_per_area + 1; + chunk_t next_free = ps->next_free; + if (sector_div(next_free, stride) == NUM_SNAPSHOT_HDR_CHUNKS) + ps->next_free++; +} + /* * Read or write a metadata area. Remembering to skip the first * chunk which holds the header. @@ -502,6 +510,8 @@ static int read_exceptions(struct pstore *ps, ps->current_area--; + skip_metadata(ps); + return 0; } @@ -616,8 +626,6 @@ static int persistent_prepare_exception(struct dm_exception_store *store, struct dm_exception *e) { struct pstore *ps = get_info(store); - uint32_t stride; - chunk_t next_free; sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev); /* Is there enough room ? */ @@ -630,10 +638,8 @@ static int persistent_prepare_exception(struct dm_exception_store *store, * Move onto the next free pending, making sure to take * into account the location of the metadata chunks. */ - stride = (ps->exceptions_per_area + 1); - next_free = ++ps->next_free; - if (sector_div(next_free, stride) == 1) - ps->next_free++; + ps->next_free++; + skip_metadata(ps); atomic_inc(&ps->pending_count); return 0; diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index f9cba4123c66..1870c4731a57 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -705,14 +705,14 @@ static size_t can_get_size(const struct net_device *dev) size_t size; size = nla_total_size(sizeof(u32)); /* IFLA_CAN_STATE */ - size += sizeof(struct can_ctrlmode); /* IFLA_CAN_CTRLMODE */ + size += nla_total_size(sizeof(struct can_ctrlmode)); /* IFLA_CAN_CTRLMODE */ size += nla_total_size(sizeof(u32)); /* IFLA_CAN_RESTART_MS */ - size += sizeof(struct can_bittiming); /* IFLA_CAN_BITTIMING */ - size += sizeof(struct can_clock); /* IFLA_CAN_CLOCK */ + size += nla_total_size(sizeof(struct can_bittiming)); /* IFLA_CAN_BITTIMING */ + size += nla_total_size(sizeof(struct can_clock)); /* IFLA_CAN_CLOCK */ if (priv->do_get_berr_counter) /* IFLA_CAN_BERR_COUNTER */ - size += sizeof(struct can_berr_counter); + size += nla_total_size(sizeof(struct can_berr_counter)); if (priv->bittiming_const) /* IFLA_CAN_BITTIMING_CONST */ - size += sizeof(struct can_bittiming_const); + size += nla_total_size(sizeof(struct can_bittiming_const)); return size; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 0cc26110868d..4b0877e68653 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -676,6 +676,7 @@ static void bnx2x_gro_receive(struct bnx2x *bp, struct bnx2x_fastpath *fp, } } #endif + skb_record_rx_queue(skb, fp->rx_queue); napi_gro_receive(&fp->napi, skb); } diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 8ec5d74ad44d..13ac104bbf4b 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1150,7 +1150,6 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo) if (lancer_chip(adapter)) { req->hdr.version = 1; - req->if_id = cpu_to_le16(adapter->if_handle); } else if (BEx_chip(adapter)) { if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) req->hdr.version = 2; @@ -1158,6 +1157,8 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo) req->hdr.version = 2; } + if (req->hdr.version > 0) + req->if_id = cpu_to_le16(adapter->if_handle); req->num_pages = PAGES_4K_SPANNED(q_mem->va, q_mem->size); req->ulp_num = BE_ULP1_NUM; req->type = BE_ETH_TX_RING_TYPE_STANDARD; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index c35db735958f..39334d428891 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1131,15 +1131,13 @@ static void mib_counters_update(struct mv643xx_eth_private *mp) p->rx_discard += rdlp(mp, RX_DISCARD_FRAME_CNT); p->rx_overrun += rdlp(mp, RX_OVERRUN_FRAME_CNT); spin_unlock_bh(&mp->mib_counters_lock); - - mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ); } static void mib_counters_timer_wrapper(unsigned long _mp) { struct mv643xx_eth_private *mp = (void *)_mp; - mib_counters_update(mp); + mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ); } @@ -2237,6 +2235,7 @@ static int mv643xx_eth_open(struct net_device *dev) mp->int_mask |= INT_TX_END_0 << i; } + add_timer(&mp->mib_counters_timer); port_start(mp); wrlp(mp, INT_MASK_EXT, INT_EXT_LINK_PHY | INT_EXT_TX); @@ -2916,7 +2915,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mp->mib_counters_timer.data = (unsigned long)mp; mp->mib_counters_timer.function = mib_counters_timer_wrapper; mp->mib_counters_timer.expires = jiffies + 30 * HZ; - add_timer(&mp->mib_counters_timer); spin_lock_init(&mp->mib_counters_lock); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index dec455c8f627..afe2efa69c86 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -70,14 +70,15 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, put_page(page); return -ENOMEM; } - page_alloc->size = PAGE_SIZE << order; + page_alloc->page_size = PAGE_SIZE << order; page_alloc->page = page; page_alloc->dma = dma; - page_alloc->offset = frag_info->frag_align; + page_alloc->page_offset = frag_info->frag_align; /* Not doing get_page() for each frag is a big win * on asymetric workloads. */ - atomic_set(&page->_count, page_alloc->size / frag_info->frag_stride); + atomic_set(&page->_count, + page_alloc->page_size / frag_info->frag_stride); return 0; } @@ -96,16 +97,19 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, for (i = 0; i < priv->num_frags; i++) { frag_info = &priv->frag_info[i]; page_alloc[i] = ring_alloc[i]; - page_alloc[i].offset += frag_info->frag_stride; - if (page_alloc[i].offset + frag_info->frag_stride <= ring_alloc[i].size) + page_alloc[i].page_offset += frag_info->frag_stride; + + if (page_alloc[i].page_offset + frag_info->frag_stride <= + ring_alloc[i].page_size) continue; + if (mlx4_alloc_pages(priv, &page_alloc[i], frag_info, gfp)) goto out; } for (i = 0; i < priv->num_frags; i++) { frags[i] = ring_alloc[i]; - dma = ring_alloc[i].dma + ring_alloc[i].offset; + dma = ring_alloc[i].dma + ring_alloc[i].page_offset; ring_alloc[i] = page_alloc[i]; rx_desc->data[i].addr = cpu_to_be64(dma); } @@ -117,7 +121,7 @@ out: frag_info = &priv->frag_info[i]; if (page_alloc[i].page != ring_alloc[i].page) { dma_unmap_page(priv->ddev, page_alloc[i].dma, - page_alloc[i].size, PCI_DMA_FROMDEVICE); + page_alloc[i].page_size, PCI_DMA_FROMDEVICE); page = page_alloc[i].page; atomic_set(&page->_count, 1); put_page(page); @@ -131,10 +135,12 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv, int i) { const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; + u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride; + - if (frags[i].offset + frag_info->frag_stride > frags[i].size) - dma_unmap_page(priv->ddev, frags[i].dma, frags[i].size, - PCI_DMA_FROMDEVICE); + if (next_frag_end > frags[i].page_size) + dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, + PCI_DMA_FROMDEVICE); if (frags[i].page) put_page(frags[i].page); @@ -161,7 +167,7 @@ out: page_alloc = &ring->page_alloc[i]; dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->size, PCI_DMA_FROMDEVICE); + page_alloc->page_size, PCI_DMA_FROMDEVICE); page = page_alloc->page; atomic_set(&page->_count, 1); put_page(page); @@ -184,10 +190,11 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, i, page_count(page_alloc->page)); dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->size, PCI_DMA_FROMDEVICE); - while (page_alloc->offset + frag_info->frag_stride < page_alloc->size) { + page_alloc->page_size, PCI_DMA_FROMDEVICE); + while (page_alloc->page_offset + frag_info->frag_stride < + page_alloc->page_size) { put_page(page_alloc->page); - page_alloc->offset += frag_info->frag_stride; + page_alloc->page_offset += frag_info->frag_stride; } page_alloc->page = NULL; } @@ -478,7 +485,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, /* Save page reference in skb */ __skb_frag_set_page(&skb_frags_rx[nr], frags[nr].page); skb_frag_size_set(&skb_frags_rx[nr], frag_info->frag_size); - skb_frags_rx[nr].page_offset = frags[nr].offset; + skb_frags_rx[nr].page_offset = frags[nr].page_offset; skb->truesize += frag_info->frag_stride; frags[nr].page = NULL; } @@ -517,7 +524,7 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, /* Get pointer to first fragment so we could copy the headers into the * (linear part of the) skb */ - va = page_address(frags[0].page) + frags[0].offset; + va = page_address(frags[0].page) + frags[0].page_offset; if (length <= SMALL_PACKET_SIZE) { /* We are copying all relevant data to the skb - temporarily @@ -645,7 +652,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh), DMA_FROM_DEVICE); ethh = (struct ethhdr *)(page_address(frags[0].page) + - frags[0].offset); + frags[0].page_offset); if (is_multicast_ether_addr(ethh->h_dest)) { struct mlx4_mac_entry *entry; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 5e0aa569306a..bf06e3610d27 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -237,8 +237,8 @@ struct mlx4_en_tx_desc { struct mlx4_en_rx_alloc { struct page *page; dma_addr_t dma; - u32 offset; - u32 size; + u32 page_offset; + u32 page_size; }; struct mlx4_en_tx_ring { diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 1a222bce4bd7..45c167fc96c5 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -876,8 +876,7 @@ static void emac_dev_mcast_set(struct net_device *ndev) netdev_mc_count(ndev) > EMAC_DEF_MAX_MULTICAST_ADDRESSES) { mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST); emac_add_mcast(priv, EMAC_ALL_MULTI_SET, NULL); - } - if (!netdev_mc_empty(ndev)) { + } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3d2a90a62649..1d01534c2020 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -916,7 +916,9 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) return -EINVAL; } else { vi->curr_queue_pairs = queue_pairs; - schedule_delayed_work(&vi->refill, 0); + /* virtnet_open() will refill when device is going to up. */ + if (dev->flags & IFF_UP) + schedule_delayed_work(&vi->refill, 0); } return 0; @@ -1094,6 +1096,11 @@ static int virtnet_cpu_callback(struct notifier_block *nfb, { struct virtnet_info *vi = container_of(nfb, struct virtnet_info, nb); + mutex_lock(&vi->config_lock); + + if (!vi->config_enable) + goto done; + switch(action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: case CPU_DOWN_FAILED: @@ -1106,6 +1113,9 @@ static int virtnet_cpu_callback(struct notifier_block *nfb, default: break; } + +done: + mutex_unlock(&vi->config_lock); return NOTIFY_OK; } @@ -1706,7 +1716,9 @@ static int virtnet_restore(struct virtio_device *vdev) vi->config_enable = true; mutex_unlock(&vi->config_lock); + rtnl_lock(); virtnet_set_queues(vi, vi->curr_queue_pairs); + rtnl_unlock(); return 0; } diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 3f0c4f268751..bcfff0d62de4 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -1972,6 +1972,7 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, } i = port->index; + memset(&sync, 0, sizeof(sync)); sync.clock_rate = FST_RDL(card, portConfig[i].lineSpeed); /* Lucky card and linux use same encoding here */ sync.clock_type = FST_RDB(card, portConfig[i].internalClock) == diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index 6a24a5a70cc7..4c0a69779b89 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -355,6 +355,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ifr->ifr_settings.size = size; /* data size wanted */ return -ENOBUFS; } + memset(&line, 0, sizeof(line)); line.clock_type = get_status(port)->clocking; line.clock_rate = 0; line.loopback = 0; diff --git a/drivers/net/wireless/cw1200/cw1200_spi.c b/drivers/net/wireless/cw1200/cw1200_spi.c index 899cad34ccd3..755a0c8edfe1 100644 --- a/drivers/net/wireless/cw1200/cw1200_spi.c +++ b/drivers/net/wireless/cw1200/cw1200_spi.c @@ -237,7 +237,9 @@ static irqreturn_t cw1200_spi_irq_handler(int irq, void *dev_id) struct hwbus_priv *self = dev_id; if (self->core) { + cw1200_spi_lock(self); cw1200_irq_handler(self->core); + cw1200_spi_unlock(self); return IRQ_HANDLED; } else { return IRQ_NONE; diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 8a4d77ee9c5b..4d9a5e70c992 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -120,6 +120,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, unsigned long rx_ring_ref, unsigned int tx_evtchn, unsigned int rx_evtchn); void xenvif_disconnect(struct xenvif *vif); +void xenvif_free(struct xenvif *vif); void xenvif_get(struct xenvif *vif); void xenvif_put(struct xenvif *vif); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 087d2db0389d..73336c144d92 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -326,6 +326,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, } netdev_dbg(dev, "Successfully created xenvif\n"); + + __module_get(THIS_MODULE); + return vif; } @@ -413,12 +416,6 @@ void xenvif_carrier_off(struct xenvif *vif) void xenvif_disconnect(struct xenvif *vif) { - /* Disconnect funtion might get called by generic framework - * even before vif connects, so we need to check if we really - * need to do a module_put. - */ - int need_module_put = 0; - if (netif_carrier_ok(vif->dev)) xenvif_carrier_off(vif); @@ -432,18 +429,16 @@ void xenvif_disconnect(struct xenvif *vif) unbind_from_irqhandler(vif->tx_irq, vif); unbind_from_irqhandler(vif->rx_irq, vif); } - /* vif->irq is valid, we had a module_get in - * xenvif_connect. - */ - need_module_put = 1; } - unregister_netdev(vif->dev); - xen_netbk_unmap_frontend_rings(vif); +} + +void xenvif_free(struct xenvif *vif) +{ + unregister_netdev(vif->dev); free_netdev(vif->dev); - if (need_module_put) - module_put(THIS_MODULE); + module_put(THIS_MODULE); } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 1fe48fe364ed..a53782ef1540 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -42,7 +42,7 @@ static int netback_remove(struct xenbus_device *dev) if (be->vif) { kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); - xenvif_disconnect(be->vif); + xenvif_free(be->vif); be->vif = NULL; } kfree(be); @@ -213,9 +213,18 @@ static void disconnect_backend(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); + if (be->vif) + xenvif_disconnect(be->vif); +} + +static void destroy_backend(struct xenbus_device *dev) +{ + struct backend_info *be = dev_get_drvdata(&dev->dev); + if (be->vif) { + kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); - xenvif_disconnect(be->vif); + xenvif_free(be->vif); be->vif = NULL; } } @@ -246,14 +255,11 @@ static void frontend_changed(struct xenbus_device *dev, case XenbusStateConnected: if (dev->state == XenbusStateConnected) break; - backend_create_xenvif(be); if (be->vif) connect(be); break; case XenbusStateClosing: - if (be->vif) - kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); disconnect_backend(dev); xenbus_switch_state(dev, XenbusStateClosing); break; @@ -262,6 +268,7 @@ static void frontend_changed(struct xenbus_device *dev, xenbus_switch_state(dev, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; + destroy_backend(dev); /* fall through if not online */ case XenbusStateUnknown: device_unregister(&dev->dev); diff --git a/drivers/tty/serial/vt8500_serial.c b/drivers/tty/serial/vt8500_serial.c index 48af43de3467..007c2c1ee8c0 100644 --- a/drivers/tty/serial/vt8500_serial.c +++ b/drivers/tty/serial/vt8500_serial.c @@ -559,12 +559,13 @@ static int vt8500_serial_probe(struct platform_device *pdev) if (!mmres || !irqres) return -ENODEV; - if (np) + if (np) { port = of_alias_get_id(np, "serial"); if (port >= VT8500_MAX_PORTS) port = -1; - else + } else { port = -1; + } if (port < 0) { /* calculate the port id */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 80a7104d5ddb..f1507c052a2e 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -451,6 +451,10 @@ static void option_instat_callback(struct urb *urb); #define CHANGHONG_VENDOR_ID 0x2077 #define CHANGHONG_PRODUCT_CH690 0x7001 +/* Inovia */ +#define INOVIA_VENDOR_ID 0x20a6 +#define INOVIA_SEW858 0x1105 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -1257,7 +1261,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) }, - { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200) }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200), + .driver_info = (kernel_ulong_t)&net_intf6_blacklist + }, { USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */ { USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/ { USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) }, @@ -1345,6 +1351,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 5c9f9b1d7736..4ced88ebcecb 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -203,6 +203,7 @@ static struct usb_device_id ti_id_table_combined[19+2*TI_EXTRA_VID_PID_COUNT+1] { USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) }, { USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) }, { USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_PRODUCT_ID) }, + { USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) }, { USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) }, { } }; diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 0459df843c58..15a6ddf7f3ca 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -680,7 +680,10 @@ static int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) atomic_set(&sl->refcnt, 0); init_completion(&sl->released); + /* slave modules need to be loaded in a context with unlocked mutex */ + mutex_unlock(&dev->mutex); request_module("w1-family-0x%0x", rn->family); + mutex_lock(&dev->mutex); spin_lock(&w1_flock); f = w1_family_registered(rn->family); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 1194b1f0f839..f8cde46de9cd 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1783,7 +1783,7 @@ retry: d_tmpfile(dentry, inode); err = ext3_orphan_add(handle, inode); if (err) - goto err_drop_inode; + goto err_unlock_inode; mark_inode_dirty(inode); unlock_new_inode(inode); } @@ -1791,10 +1791,9 @@ retry: if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; -err_drop_inode: +err_unlock_inode: ext3_journal_stop(handle); unlock_new_inode(inode); - iput(inode); return err; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 35f55a0dbc4b..b53cbc6966a2 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2319,7 +2319,7 @@ retry: d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); if (err) - goto err_drop_inode; + goto err_unlock_inode; mark_inode_dirty(inode); unlock_new_inode(inode); } @@ -2328,10 +2328,9 @@ retry: if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; -err_drop_inode: +err_unlock_inode: ext4_journal_stop(handle); unlock_new_inode(inode); - iput(inode); return err; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3b71a4e83642..6bd165be52e3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1316,6 +1316,11 @@ static inline int skb_pagelen(const struct sk_buff *skb) return len + skb_headlen(skb); } +static inline bool skb_has_frags(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->nr_frags; +} + /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index a7a683e30b64..a8c2ef6d3b93 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -290,6 +290,7 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, unsigned char err_offset = 0; u8 opt_len = opt[1]; u8 opt_iter; + u8 tag_len; if (opt_len < 8) { err_offset = 1; @@ -302,11 +303,12 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, } for (opt_iter = 6; opt_iter < opt_len;) { - if (opt[opt_iter + 1] > (opt_len - opt_iter)) { + tag_len = opt[opt_iter + 1]; + if ((tag_len == 0) || (opt[opt_iter + 1] > (opt_len - opt_iter))) { err_offset = opt_iter + 1; goto out; } - opt_iter += opt[opt_iter + 1]; + opt_iter += tag_len; } out: diff --git a/include/net/dst.h b/include/net/dst.h index 1f8fd109e225..e0c97f5a57cf 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -477,10 +477,22 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, { return dst_orig; } + +static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) +{ + return NULL; +} + #else extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, struct sock *sk, int flags); + +/* skb attached with this dst needs transformation if dst->xfrm is valid */ +static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) +{ + return dst->xfrm; +} #endif #endif /* _NET_DST_H */ diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f667248202b6..c7b8860f29fd 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -196,11 +196,9 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } -static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, struct in6_addr *dest) +static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt) { - if (rt->rt6i_flags & RTF_GATEWAY) - return &rt->rt6i_gateway; - return dest; + return &rt->rt6i_gateway; } #endif diff --git a/include/net/sock.h b/include/net/sock.h index 31d5cfbb51ec..04e148f45277 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -232,6 +232,7 @@ struct cg_proto; * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode + * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_sndbuf: size of send buffer in bytes * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings @@ -361,6 +362,7 @@ struct sock { kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; + u32 sk_pacing_rate; /* bytes per second */ netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; int sk_gso_type; diff --git a/include/net/tcp.h b/include/net/tcp.h index d1980054ec75..46cb8a406b8f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -284,6 +284,7 @@ extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; +extern int sysctl_tcp_min_tso_segs; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f2820fbf67c9..70861a1fdd64 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2709,6 +2709,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; +again: mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); spin_lock(&mm->page_table_lock); if (unlikely(!pmd_trans_huge(*pmd))) { @@ -2731,7 +2732,14 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, split_huge_page(page); put_page(page); - BUG_ON(pmd_trans_huge(*pmd)); + + /* + * We don't always have down_write of mmap_sem here: a racing + * do_huge_pmd_wp_page() might have copied-on-write to another + * huge page before our split_huge_page() got the anon_vma lock. + */ + if (unlikely(pmd_trans_huge(*pmd))) + goto again; } void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, diff --git a/mm/memory.c b/mm/memory.c index af84bc0ec17c..440986e57218 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -861,6 +861,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); set_pte_at(src_mm, addr, src_pte, pte); } } diff --git a/mm/migrate.c b/mm/migrate.c index 25ca7caf9092..81af4e678101 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -157,6 +157,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, get_page(new); pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/mprotect.c b/mm/mprotect.c index 94722a4d6b43..a3af058f68e4 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -94,13 +94,16 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { + pte_t newpte; /* * A protection check is difficult so * just be safe and disable write */ make_migration_entry_read(&entry); - set_pte_at(mm, addr, pte, - swp_entry_to_pte(entry)); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + set_pte_at(mm, addr, pte, newpte); } pages++; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3f0c895c71fe..241a746f864c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1104,11 +1104,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty, return 1; } -static long bdi_max_pause(struct backing_dev_info *bdi, - unsigned long bdi_dirty) +static unsigned long bdi_max_pause(struct backing_dev_info *bdi, + unsigned long bdi_dirty) { - long bw = bdi->avg_write_bandwidth; - long t; + unsigned long bw = bdi->avg_write_bandwidth; + unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long @@ -1120,7 +1120,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi, t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; - return min_t(long, t, MAX_PAUSE); + return min_t(unsigned long, t, MAX_PAUSE); } static long bdi_min_pause(struct backing_dev_info *bdi, diff --git a/mm/zswap.c b/mm/zswap.c index deda2b671e12..cbd9578c1e88 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -816,6 +816,10 @@ static void zswap_frontswap_invalidate_area(unsigned type) } tree->rbroot = RB_ROOT; spin_unlock(&tree->lock); + + zbud_destroy_pool(tree->pool); + kfree(tree); + zswap_trees[type] = NULL; } static struct zbud_ops zswap_zbud_ops = { diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 309129732285..c7e634af8516 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev) return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */ nla_total_size(2) + /* IFLA_VLAN_ID */ - sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */ + nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */ vlan_qos_map_size(vlan->nr_ingress_mappings) + vlan_qos_map_size(vlan->nr_egress_mappings); } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 08125f3f6064..c8e0671422a3 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -61,6 +61,7 @@ static int __init batadv_init(void) batadv_recv_handler_init(); batadv_iv_init(); + batadv_nc_init(); batadv_event_workqueue = create_singlethread_workqueue("bat_events"); @@ -138,7 +139,7 @@ int batadv_mesh_init(struct net_device *soft_iface) if (ret < 0) goto err; - ret = batadv_nc_init(bat_priv); + ret = batadv_nc_mesh_init(bat_priv); if (ret < 0) goto err; @@ -163,7 +164,7 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_vis_quit(bat_priv); batadv_gw_node_purge(bat_priv); - batadv_nc_free(bat_priv); + batadv_nc_mesh_free(bat_priv); batadv_dat_free(bat_priv); batadv_bla_free(bat_priv); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index a487d46e0aec..4ecc0b6bf8ab 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -35,6 +35,20 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); /** + * batadv_nc_init - one-time initialization for network coding + */ +int __init batadv_nc_init(void) +{ + int ret; + + /* Register our packet type */ + ret = batadv_recv_handler_register(BATADV_CODED, + batadv_nc_recv_coded_packet); + + return ret; +} + +/** * batadv_nc_start_timer - initialise the nc periodic worker * @bat_priv: the bat priv with all the soft interface information */ @@ -45,10 +59,10 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv) } /** - * batadv_nc_init - initialise coding hash table and start house keeping + * batadv_nc_mesh_init - initialise coding hash table and start house keeping * @bat_priv: the bat priv with all the soft interface information */ -int batadv_nc_init(struct batadv_priv *bat_priv) +int batadv_nc_mesh_init(struct batadv_priv *bat_priv) { bat_priv->nc.timestamp_fwd_flush = jiffies; bat_priv->nc.timestamp_sniffed_purge = jiffies; @@ -70,11 +84,6 @@ int batadv_nc_init(struct batadv_priv *bat_priv) batadv_hash_set_lock_class(bat_priv->nc.coding_hash, &batadv_nc_decoding_hash_lock_class_key); - /* Register our packet type */ - if (batadv_recv_handler_register(BATADV_CODED, - batadv_nc_recv_coded_packet) < 0) - goto err; - INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); batadv_nc_start_timer(bat_priv); @@ -1721,12 +1730,11 @@ free_nc_packet: } /** - * batadv_nc_free - clean up network coding memory + * batadv_nc_mesh_free - clean up network coding memory * @bat_priv: the bat priv with all the soft interface information */ -void batadv_nc_free(struct batadv_priv *bat_priv) +void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { - batadv_recv_handler_unregister(BATADV_CODED); cancel_delayed_work_sync(&bat_priv->nc.work); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 85a4ec81ad50..ddfa618e80bf 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -22,8 +22,9 @@ #ifdef CONFIG_BATMAN_ADV_NC -int batadv_nc_init(struct batadv_priv *bat_priv); -void batadv_nc_free(struct batadv_priv *bat_priv); +int batadv_nc_init(void); +int batadv_nc_mesh_init(struct batadv_priv *bat_priv); +void batadv_nc_mesh_free(struct batadv_priv *bat_priv); void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, @@ -46,12 +47,17 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_NC */ -static inline int batadv_nc_init(struct batadv_priv *bat_priv) +static inline int batadv_nc_init(void) { return 0; } -static inline void batadv_nc_free(struct batadv_priv *bat_priv) +static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv) +{ + return 0; +} + +static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { return; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 6319c4333c39..de3a0e76ab75 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -451,7 +451,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) call_rcu_bh(&p->rcu, br_multicast_free_pg); err = 0; - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); break; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index bbcb43582496..fbad619c70b7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -271,7 +271,7 @@ static void br_multicast_del_pg(struct net_bridge *br, del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -619,7 +619,6 @@ rehash: mp->br = br; mp->addr = *group; - setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); @@ -659,6 +658,7 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + unsigned long now = jiffies; int err; spin_lock(&br->multicast_lock); @@ -673,6 +673,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (!port) { mp->mglist = true; + mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -680,7 +681,7 @@ static int br_multicast_add_group(struct net_bridge *br, (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->port == port) - goto out; + goto found; if ((unsigned long)p->port < (unsigned long)port) break; } @@ -691,6 +692,8 @@ static int br_multicast_add_group(struct net_bridge *br, rcu_assign_pointer(*pp, p); br_mdb_notify(br->dev, port, group, RTM_NEWMDB); +found: + mod_timer(&p->timer, now + br->multicast_membership_interval); out: err = 0; @@ -1190,9 +1193,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && @@ -1269,9 +1269,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? @@ -1357,7 +1354,7 @@ static void br_multicast_leave_group(struct net_bridge *br, call_rcu_bh(&p->rcu, br_multicast_free_pg); br_mdb_notify(br->dev, port, group, RTM_DELMDB); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } @@ -1369,12 +1366,30 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (mp->mglist && mp->timer_armed && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } + + goto out; + } + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; } out: spin_unlock(&br->multicast_lock); @@ -1791,7 +1806,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - mp->timer_armed = false; call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index cde1eb14d9a2..aa05bd80e9bb 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,7 +126,6 @@ struct net_bridge_mdb_entry struct timer_list timer; struct br_ip addr; bool mglist; - bool timer_armed; }; struct net_bridge_mdb_htable diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 108084a04671..656a6f3e40de 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -134,7 +134,7 @@ static void br_stp_start(struct net_bridge *br) if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); - else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY) + else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); if (r == 0) { diff --git a/net/compat.c b/net/compat.c index f0a1ba6c8086..89032580bd1d 100644 --- a/net/compat.c +++ b/net/compat.c @@ -71,6 +71,8 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + return -EINVAL; kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 3f1ec1586ae1..8d9d05edd2eb 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -10,6 +10,7 @@ #include +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) #define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; @@ -29,6 +30,7 @@ static void net_secret_init(void) cmpxchg(&net_secret[--i], 0, tmp); } } +#endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) diff --git a/net/core/sock.c b/net/core/sock.c index 2c097c5a35dd..8729d9135790 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2297,6 +2297,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_ll_usec = sysctl_net_busy_read; #endif + sk->sk_pacing_rate = ~0U; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7bd8983dbfcf..96da9c77deca 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -287,7 +287,7 @@ begintw: if (unlikely(!INET_TW_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a04d872c54f9..7f4ab5d31c16 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -836,7 +836,7 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; cork->length += length; - if (((length > mtu) || (skb && skb_is_gso(skb))) && + if (((length > mtu) || (skb && skb_has_frags(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 17cc0ffa8c0d..065604127418 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -285,8 +285,17 @@ static int vti_rcv(struct sk_buff *skb) tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); if (tunnel != NULL) { struct pcpu_tstats *tstats; + u32 oldmark = skb->mark; + int ret; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + + /* temporarily mark the skb with the tunnel o_key, to + * only match policies with this mark. + */ + skb->mark = be32_to_cpu(tunnel->parms.o_key); + ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); + skb->mark = oldmark; + if (!ret) return -1; tstats = this_cpu_ptr(tunnel->dev->tstats); @@ -295,7 +304,6 @@ static int vti_rcv(struct sk_buff *skb) tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - skb->mark = 0; secpath_reset(skb); skb->dev = tunnel->dev; return 1; @@ -327,7 +335,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl4, 0, sizeof(fl4)); flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos), + be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPIP, 0, dst, tiph->saddr, 0, 0); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a9a54a236832..2de16d940528 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2074,7 +2074,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) RT_SCOPE_LINK); goto make_route; } - if (fl4->saddr) { + if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 610e324348d1..6900b8b97d93 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -29,6 +29,7 @@ static int zero; static int one = 1; static int four = 4; +static int gso_max_segs = GSO_MAX_SEGS; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; @@ -754,6 +755,15 @@ static struct ctl_table ipv4_table[] = { .extra2 = &four, }, { + .procname = "tcp_min_tso_segs", + .data = &sysctl_tcp_min_tso_segs, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &gso_max_segs, + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 95544e4028c0..ec586e553361 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -283,6 +283,8 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; +int sysctl_tcp_min_tso_segs __read_mostly = 2; + struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); @@ -789,12 +791,28 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, xmit_size_goal = mss_now; if (large_allowed && sk_can_gso(sk)) { - xmit_size_goal = ((sk->sk_gso_max_size - 1) - - inet_csk(sk)->icsk_af_ops->net_header_len - - inet_csk(sk)->icsk_ext_hdr_len - - tp->tcp_header_len); + u32 gso_size, hlen; + + /* Maybe we should/could use sk->sk_prot->max_header here ? */ + hlen = inet_csk(sk)->icsk_af_ops->net_header_len + + inet_csk(sk)->icsk_ext_hdr_len + + tp->tcp_header_len; + + /* Goal is to send at least one packet per ms, + * not one big TSO packet every 100 ms. + * This preserves ACK clocking and is consistent + * with tcp_tso_should_defer() heuristic. + */ + gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC); + gso_size = max_t(u32, gso_size, + sysctl_tcp_min_tso_segs * mss_now); + + xmit_size_goal = min_t(u32, gso_size, + sk->sk_gso_max_size - 1 - hlen); - /* TSQ : try to have two TSO segments in flight */ + /* TSQ : try to have at least two segments in flight + * (one in NIC TX ring, another in Qdisc) + */ xmit_size_goal = min_t(u32, xmit_size_goal, sysctl_tcp_limit_output_bytes >> 1); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3ca2139a130b..723951aec07e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -688,6 +688,34 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) } } +/* Set the sk_pacing_rate to allow proper sizing of TSO packets. + * Note: TCP stack does not yet implement pacing. + * FQ packet scheduler can be used to implement cheap but effective + * TCP pacing, to smooth the burst on large writes when packets + * in flight is significantly lower than cwnd (or rwin) + */ +static void tcp_update_pacing_rate(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u64 rate; + + /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ + rate = (u64)tp->mss_cache * 2 * (HZ << 3); + + rate *= max(tp->snd_cwnd, tp->packets_out); + + /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3), + * be conservative and assume srtt = 1 (125 us instead of 1.25 ms) + * We probably need usec resolution in the future. + * Note: This also takes care of possible srtt=0 case, + * when tcp_rtt_estimator() was not yet called. + */ + if (tp->srtt > 8 + 2) + do_div(rate, tp->srtt); + + sk->sk_pacing_rate = min_t(u64, rate, ~0U); +} + /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ @@ -1251,7 +1279,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tp->lost_cnt_hint -= tcp_skb_pcount(prev); } - TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags; + TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + TCP_SKB_CB(prev)->end_seq++; + if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); @@ -3253,7 +3284,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tcp_init_cwnd_reduction(sk, true); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); - tcp_set_ca_state(sk, TCP_CA_Open); + tcp_try_keep_open(sk); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } @@ -3269,7 +3300,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight; + u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt; u32 prior_fackets; int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; @@ -3375,6 +3406,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); + if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd) + tcp_update_pacing_rate(sk); return 1; no_queue: @@ -5671,6 +5704,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else tcp_init_metrics(sk); + tcp_update_pacing_rate(sk); + /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 170737a9d56d..28c0d6a00d96 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -892,8 +892,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; - skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? - tcp_wfree : sock_wfree; + skb->destructor = tcp_wfree; atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ @@ -982,6 +981,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { + /* Make sure we own this skb before messing gso_size/gso_segs */ + WARN_ON_ONCE(skb_cloned(skb)); + if (skb->len <= mss_now || !sk_can_gso(sk) || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal @@ -1063,9 +1065,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; - if (skb_cloned(skb) && - skb_is_nonlinear(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -1628,7 +1628,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) /* If a full-sized TSO skb can be sent, do it. */ if (limit >= min_t(unsigned int, sk->sk_gso_max_size, - sk->sk_gso_max_segs * tp->mss_cache)) + tp->xmit_size_goal_segs * tp->mss_cache)) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ @@ -1837,7 +1837,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1866,13 +1865,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } - /* TSQ : sk_wmem_alloc accounts skb truesize, - * including skb overhead. But thats OK. + /* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates */ - if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + limit = max(skb->truesize, sk->sk_pacing_rate >> 10); + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); break; } + limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, @@ -2334,6 +2340,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { + if (skb_unclone(skb, GFP_ATOMIC)) + return -ENOMEM; tcp_init_tso_segs(sk, skb, cur_mss); tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 32b4a1675d82..066640e0ba8e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -116,7 +116,7 @@ begintw: } if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 44df1c92a0d6..5b25f850faf9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -130,7 +130,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -899,7 +899,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1252,7 +1252,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, skb = skb_peek_tail(&sk->sk_write_queue); cork->length += length; if (((length > mtu) || - (skb && skb_is_gso(skb))) && + (skb && skb_has_frags(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { err = ip6_ufo_append_data(sk, getfrag, from, length, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8d9a93ed9c59..1e32d5c0b615 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -477,6 +477,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -500,17 +518,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; - if (neigh) { + work = kmalloc(sizeof(*work), GFP_ATOMIC); + + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); @@ -852,7 +876,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; @@ -1270,6 +1293,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1824,7 +1848,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) @@ -2111,6 +2138,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 86f639ba5407..a51ad079ee58 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1708,7 +1708,6 @@ static void __net_exit sit_exit_net(struct net *net) rtnl_lock(); sit_destroy_tunnels(sitn, &list); - unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index feae495a0a30..b076e8309bc2 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -115,6 +115,11 @@ struct l2tp_net { static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); +static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) +{ + return sk->sk_user_data; +} + static inline struct l2tp_net *l2tp_pernet(struct net *net) { BUG_ON(!net); @@ -504,7 +509,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk, return 0; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { + if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) { if (!uh->check) { LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n"); return 1; @@ -1128,7 +1133,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6) + if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1255,7 +1260,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) l2tp_xmit_ipv6_csum(sk, skb, udp_len); else #endif @@ -1304,10 +1309,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel; + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); struct l2tp_net *pn; - tunnel = sk->sk_user_data; if (tunnel == NULL) goto end; @@ -1675,7 +1679,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } /* Check if this socket has already been prepped */ - tunnel = (struct l2tp_tunnel *)sk->sk_user_data; + tunnel = l2tp_tunnel(sk); if (tunnel != NULL) { /* This socket has already been prepped */ err = -EBUSY; @@ -1704,6 +1708,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + if (ipv6_addr_v4mapped(&np->saddr) && + ipv6_addr_v4mapped(&np->daddr)) { + struct inet_sock *inet = inet_sk(sk); + + tunnel->v4mapped = true; + inet->inet_saddr = np->saddr.s6_addr32[3]; + inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3]; + inet->inet_daddr = np->daddr.s6_addr32[3]; + } else { + tunnel->v4mapped = false; + } + } +#endif + /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@ -1712,7 +1734,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) udpv6_encap_enable(); else #endif diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 66a559b104b6..6f251cbc2ed7 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -194,6 +194,9 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ +#if IS_ENABLED(CONFIG_IPV6) + bool v4mapped; +#endif struct work_struct del_work; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5ebee2ded9e9..8c46b271064a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -353,7 +353,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh goto error_put_sess_tun; } + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(ps->tunnel_sock); sock_put(sk); @@ -422,7 +424,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[0] = ppph[0]; skb->data[1] = ppph[1]; + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(sk_tun); sock_put(sk); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bdebd03bc8cd..70866d192efc 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, - sizeof(rt1->rt6i_gateway)) && + if (ipv6_addr_equal(rt6_nexthop(rt1), + rt6_nexthop(rt2)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 82f6016d89ab..3626010e8f0b 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -358,6 +358,21 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } +static void tfifo_reset(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct rb_node *p; + + while ((p = rb_first(&q->t_root))) { + struct sk_buff *skb = netem_rb_to_skb(p); + + rb_erase(p, &q->t_root); + skb->next = NULL; + skb->prev = NULL; + kfree_skb(skb); + } +} + static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -523,6 +538,7 @@ static unsigned int netem_drop(struct Qdisc *sch) skb->next = NULL; skb->prev = NULL; len = qdisc_pkt_len(skb); + sch->qstats.backlog -= len; kfree_skb(skb); } } @@ -612,6 +628,7 @@ static void netem_reset(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); + tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); diff --git a/net/sctp/output.c b/net/sctp/output.c index a46d1eb41762..013a07d9c454 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -542,7 +542,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in . */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + (dst_xfrm(dst) != NULL) || packet->ipfragok) { __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); /* 3) Put the resultant value into the checksum field in the diff --git a/net/socket.c b/net/socket.c index b2d7c629eeb9..4b946438d560 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1973,6 +1973,16 @@ struct used_address { unsigned int name_len; }; +static int copy_msghdr_from_user(struct msghdr *kmsg, + struct msghdr __user *umsg) +{ + if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) + return -EFAULT; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + return -EINVAL; + return 0; +} + static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address) @@ -1991,8 +2001,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; @@ -2200,8 +2213,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c4ce243824bb..e64bbcf5fb2c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1246,6 +1246,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) return 0; } +static void unix_sock_inherit_flags(const struct socket *old, + struct socket *new) +{ + if (test_bit(SOCK_PASSCRED, &old->flags)) + set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSSEC, &old->flags)) + set_bit(SOCK_PASSSEC, &new->flags); +} + static int unix_accept(struct socket *sock, struct socket *newsock, int flags) { struct sock *sk = sock->sk; @@ -1280,6 +1289,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags) /* attach accepted sock to socket */ unix_state_lock(tsk); newsock->state = SS_CONNECTED; + unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); unix_state_unlock(tsk); return 0; diff --git a/net/unix/diag.c b/net/unix/diag.c index d591091603bf..86fa0f3b2caf 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep->udiag_family = AF_UNIX; rep->udiag_type = sk->sk_type; rep->udiag_state = sk->sk_state; + rep->pad = 0; rep->udiag_ino = sk_ino; sock_diag_save_cookie(sk, rep->udiag_cookie); diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 7d604c06c3dc..a271c27fac77 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init( struct ieee80211_radiotap_header *radiotap_header, int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns) { + /* check the radiotap header can actually be present */ + if (max_length < sizeof(struct ieee80211_radiotap_header)) + return -EINVAL; + /* Linux only supports version 0 radiotap format */ if (radiotap_header->it_version) return -EINVAL; @@ -131,7 +135,8 @@ int ieee80211_radiotap_iterator_init( */ if ((unsigned long)iterator->_arg - - (unsigned long)iterator->_rtheader > + (unsigned long)iterator->_rtheader + + sizeof(uint32_t) > (unsigned long)iterator->_max_length) return -EINVAL; } diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index e3c7ba8d7582..adabdeb7b15d 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3505,7 +3505,7 @@ static int create_capture_mixers(struct hda_codec *codec) if (!multi) err = create_single_cap_vol_ctl(codec, n, vol, sw, inv_dmic); - else if (!multi_cap_vol) + else if (!multi_cap_vol && !inv_dmic) err = create_bind_cap_vol_ctl(codec, n, vol, sw); else err = create_multi_cap_vol_ctl(codec); diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index d0323a693ba2..999550bbad40 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -262,7 +262,9 @@ static int usb_stream_hwdep_mmap(struct snd_hwdep *hw, } area->vm_ops = &usb_stream_hwdep_vm_ops; - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + area->vm_flags |= VM_DONTDUMP; + if (!read) + area->vm_flags |= VM_DONTEXPAND; area->vm_private_data = us122l; atomic_inc(&us122l->mmap_count); out: