diff options
94 files changed, 746 insertions, 411 deletions
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt index aed082f49d0..737988fca64 100644 --- a/Documentation/cpu-freq/governors.txt +++ b/Documentation/cpu-freq/governors.txt @@ -145,8 +145,8 @@ show_sampling_rate_max: THIS INTERFACE IS DEPRECATED, DON'T USE IT. up_threshold: defines what the average CPU usage between the samplings of 'sampling_rate' needs to be for the kernel to make a decision on whether it should increase the frequency. For example when it is set -to its default value of '80' it means that between the checking -intervals the CPU needs to be on average more than 80% in use to then +to its default value of '95' it means that between the checking +intervals the CPU needs to be on average more than 95% in use to then decide that the CPU frequency needs to be increased. ignore_nice_load: this parameter takes a value of '0' or '1'. When diff --git a/MAINTAINERS b/MAINTAINERS index 03f38c18f32..602022d2c7a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3836,6 +3836,7 @@ NETWORKING DRIVERS L: netdev@vger.kernel.org W: http://www.linuxfoundation.org/en/Net T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6.git S: Odd Fixes F: drivers/net/ F: include/linux/if_* diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index 1aa1ea5e921..b13d1879e51 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1325,7 +1325,7 @@ struct platform_device *__init at32_add_device_mci(unsigned int id, struct mci_platform_data *data) { struct platform_device *pdev; - struct mci_dma_slave *slave; + struct mci_dma_data *slave; u32 pioa_mask; u32 piob_mask; @@ -1344,7 +1344,9 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data) ARRAY_SIZE(atmel_mci0_resource))) goto fail; - slave = kzalloc(sizeof(struct mci_dma_slave), GFP_KERNEL); + slave = kzalloc(sizeof(struct mci_dma_data), GFP_KERNEL); + if (!slave) + goto fail; slave->sdata.dma_dev = &dw_dmac0_device.dev; slave->sdata.reg_width = DW_DMA_SLAVE_WIDTH_32BIT; @@ -1357,7 +1359,7 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data) if (platform_device_add_data(pdev, data, sizeof(struct mci_platform_data))) - goto fail; + goto fail_free; /* CLK line is common to both slots */ pioa_mask = 1 << 10; @@ -1381,7 +1383,7 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data) /* Slot is unused */ break; default: - goto fail; + goto fail_free; } select_peripheral(PIOA, pioa_mask, PERIPH_A, 0); @@ -1408,7 +1410,7 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data) break; default: if (!data->slot[0].bus_width) - goto fail; + goto fail_free; data->slot[1].bus_width = 0; break; @@ -1419,9 +1421,10 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data) platform_device_add(pdev); return pdev; +fail_free: + kfree(slave); fail: data->dma_slave = NULL; - kfree(slave); platform_device_put(pdev); return NULL; } diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 5372b24ad04..bb8c4b9ccb8 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -54,6 +54,7 @@ void __init setup_arch(char **cmdline_p) microblaze_cache_init(); + invalidate_dcache(); enable_dcache(); invalidate_icache(); diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 282d9306361..1ec06576f61 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -63,15 +63,21 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, if (huge) { #ifdef CONFIG_HUGETLB_PAGE psize = get_slice_psize(mm, addr); + /* Mask the address for the correct page size */ + addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1); #else BUG(); psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */ #endif - } else + } else { psize = pte_pagesize_index(mm, addr, pte); + /* Mask the address for the standard page size. If we + * have a 64k page kernel, but the hardware does not + * support 64k pages, this might be different from the + * hardware page size encoded in the slice table. */ + addr &= PAGE_MASK; + } - /* Mask the address for the correct page size */ - addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1); /* Build full vaddr */ if (!is_kernel_addr(addr)) { diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 1ee66db003b..f5f79196721 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -784,9 +784,13 @@ static void xics_set_cpu_priority(unsigned char cppr) { struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); - BUG_ON(os_cppr->index != 0); + /* + * we only really want to set the priority when there's + * just one cppr value on the stack + */ + WARN_ON(os_cppr->index != 0); - os_cppr->stack[os_cppr->index] = cppr; + os_cppr->stack[0] = cppr; if (firmware_has_feature(FW_FEATURE_LPAR)) lpar_cppr_info(cppr); @@ -821,8 +825,14 @@ void xics_setup_cpu(void) void xics_teardown_cpu(void) { + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); int cpu = smp_processor_id(); + /* + * we have to reset the cppr index to 0 because we're + * not going to return from the IPI + */ + os_cppr->index = 0; xics_set_cpu_priority(0); /* Clear any pending IPI request */ diff --git a/arch/sh/kernel/cpu/sh3/entry.S b/arch/sh/kernel/cpu/sh3/entry.S index 3f7e2a22c7c..f6a389c996c 100644 --- a/arch/sh/kernel/cpu/sh3/entry.S +++ b/arch/sh/kernel/cpu/sh3/entry.S @@ -132,7 +132,6 @@ ENTRY(tlb_protection_violation_store) mov #1, r5 call_handle_tlbmiss: - setup_frame_reg mov.l 1f, r0 mov r5, r8 mov.l @r0, r6 @@ -365,6 +364,8 @@ handle_exception: mov.l @k2, k2 ! read out vector and keep in k2 handle_exception_special: + setup_frame_reg + ! Setup return address and jump to exception handler mov.l 7f, r9 ! fetch return address stc r2_bank, r0 ! k2 (vector) diff --git a/arch/sh/kernel/dwarf.c b/arch/sh/kernel/dwarf.c index 88d28ec3780..e51168064e5 100644 --- a/arch/sh/kernel/dwarf.c +++ b/arch/sh/kernel/dwarf.c @@ -540,6 +540,8 @@ void dwarf_free_frame(struct dwarf_frame *frame) mempool_free(frame, dwarf_frame_pool); } +extern void ret_from_irq(void); + /** * dwarf_unwind_stack - unwind the stack * @@ -678,6 +680,24 @@ struct dwarf_frame * dwarf_unwind_stack(unsigned long pc, addr = frame->cfa + reg->addr; frame->return_addr = __raw_readl(addr); + /* + * Ah, the joys of unwinding through interrupts. + * + * Interrupts are tricky - the DWARF info needs to be _really_ + * accurate and unfortunately I'm seeing a lot of bogus DWARF + * info. For example, I've seen interrupts occur in epilogues + * just after the frame pointer (r14) had been restored. The + * problem was that the DWARF info claimed that the CFA could be + * reached by using the value of the frame pointer before it was + * restored. + * + * So until the compiler can be trusted to produce reliable + * DWARF info when it really matters, let's stop unwinding once + * we've calculated the function that was interrupted. + */ + if (prev && prev->pc == (unsigned long)ret_from_irq) + frame->return_addr = 0; + return frame; bail: diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index f0abd58c3a6..2b15ae60c3a 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -70,8 +70,14 @@ ret_from_exception: CFI_STARTPROC simple CFI_DEF_CFA r14, 0 CFI_REL_OFFSET 17, 64 - CFI_REL_OFFSET 15, 0 + CFI_REL_OFFSET 15, 60 CFI_REL_OFFSET 14, 56 + CFI_REL_OFFSET 13, 52 + CFI_REL_OFFSET 12, 48 + CFI_REL_OFFSET 11, 44 + CFI_REL_OFFSET 10, 40 + CFI_REL_OFFSET 9, 36 + CFI_REL_OFFSET 8, 32 preempt_stop() ENTRY(ret_from_irq) ! diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index f125e5c551c..6e44519960c 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1356,6 +1356,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol) kfree(data->powernow_table); kfree(data); + per_cpu(powernow_data, pol->cpu) = NULL; return 0; } @@ -1375,7 +1376,7 @@ static unsigned int powernowk8_get(unsigned int cpu) int err; if (!data) - return -EINVAL; + return 0; smp_call_function_single(cpu, query_values_on_cpu, &err, true); if (err) diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index f36defa3776..57d965b7f52 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -808,6 +808,7 @@ static int btmrvl_sdio_host_to_card(struct btmrvl_private *priv, exit: sdio_release_host(card->func); + kfree(tmpbuf); return ret; } diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 4b34ade2332..bd444dc93cf 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -554,6 +554,9 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) (dbs_tuners_ins.up_threshold - dbs_tuners_ins.down_differential); + if (freq_next < policy->min) + freq_next = policy->min; + if (!dbs_tuners_ins.powersave_bias) { __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L); diff --git a/drivers/md/md.c b/drivers/md/md.c index dd3dfe42d5a..a20a71e5efd 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4075,8 +4075,10 @@ static void mddev_delayed_delete(struct work_struct *ws) { mddev_t *mddev = container_of(ws, mddev_t, del_work); - if (mddev->private == &md_redundancy_group) { + if (mddev->private) { sysfs_remove_group(&mddev->kobj, &md_redundancy_group); + if (mddev->private != (void*)1) + sysfs_remove_group(&mddev->kobj, mddev->private); if (mddev->sysfs_action) sysfs_put(mddev->sysfs_action); mddev->sysfs_action = NULL; @@ -4287,10 +4289,7 @@ static int do_md_run(mddev_t * mddev) sysfs_notify_dirent(rdev->sysfs_state); } - md_probe(mddev->unit, NULL, NULL); disk = mddev->gendisk; - if (!disk) - return -ENOMEM; spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); @@ -4530,8 +4529,8 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) mddev->queue->unplug_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; module_put(mddev->pers->owner); - if (mddev->pers->sync_request) - mddev->private = &md_redundancy_group; + if (mddev->pers->sync_request && mddev->private == NULL) + mddev->private = (void*)1; mddev->pers = NULL; /* tell userspace to handle 'inactive' */ sysfs_notify_dirent(mddev->sysfs_state); @@ -4578,9 +4577,6 @@ out: } mddev->bitmap_info.offset = 0; - /* make sure all md_delayed_delete calls have finished */ - flush_scheduled_work(); - export_array(mddev); mddev->array_sectors = 0; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e84204eb12d..ceb24afdc14 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5136,9 +5136,8 @@ static int stop(mddev_t *mddev) mddev->thread = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ - sysfs_remove_group(&mddev->kobj, &raid5_attrs_group); free_conf(conf); - mddev->private = NULL; + mddev->private = &raid5_attrs_group; return 0; } @@ -5464,11 +5463,11 @@ static int raid5_start_reshape(mddev_t *mddev) !test_bit(Faulty, &rdev->flags)) { if (raid5_add_disk(mddev, rdev) == 0) { char nm[20]; - if (rdev->raid_disk >= conf->previous_raid_disks) + if (rdev->raid_disk >= conf->previous_raid_disks) { set_bit(In_sync, &rdev->flags); - else + added_devices++; + } else rdev->recovery_offset = 0; - added_devices++; sprintf(nm, "rd%d", rdev->raid_disk); if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm)) @@ -5480,9 +5479,12 @@ static int raid5_start_reshape(mddev_t *mddev) break; } + /* When a reshape changes the number of devices, ->degraded + * is measured against the large of the pre and post number of + * devices.*/ if (mddev->delta_disks > 0) { spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) + mddev->degraded += (conf->raid_disks - conf->previous_raid_disks) - added_devices; spin_unlock_irqrestore(&conf->device_lock, flags); } diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c index c37790ad92d..9ddc57909d4 100644 --- a/drivers/media/dvb/dvb-core/dmxdev.c +++ b/drivers/media/dvb/dvb-core/dmxdev.c @@ -761,7 +761,6 @@ static int dvb_demux_open(struct inode *inode, struct file *file) dvb_ringbuffer_init(&dmxdevfilter->buffer, NULL, 8192); dmxdevfilter->type = DMXDEV_TYPE_NONE; dvb_dmxdev_filter_state_set(dmxdevfilter, DMXDEV_STATE_ALLOCATED); - INIT_LIST_HEAD(&dmxdevfilter->feed.ts); init_timer(&dmxdevfilter->timer); dvbdev->users++; @@ -887,6 +886,7 @@ static int dvb_dmxdev_pes_filter_set(struct dmxdev *dmxdev, dmxdevfilter->type = DMXDEV_TYPE_PES; memcpy(&dmxdevfilter->params, params, sizeof(struct dmx_pes_filter_params)); + INIT_LIST_HEAD(&dmxdevfilter->feed.ts); dvb_dmxdev_filter_state_set(dmxdevfilter, DMXDEV_STATE_SET); diff --git a/drivers/media/dvb/dvb-core/dvb_demux.c b/drivers/media/dvb/dvb-core/dvb_demux.c index b78cfb7d189..67f189b7aa1 100644 --- a/drivers/media/dvb/dvb-core/dvb_demux.c +++ b/drivers/media/dvb/dvb-core/dvb_demux.c @@ -426,16 +426,7 @@ static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf) }; }; - if (dvb_demux_tscheck) { - if (!demux->cnt_storage) - demux->cnt_storage = vmalloc(MAX_PID + 1); - - if (!demux->cnt_storage) { - printk(KERN_WARNING "Couldn't allocate memory for TS/TEI check. Disabling it\n"); - dvb_demux_tscheck = 0; - goto no_dvb_demux_tscheck; - } - + if (demux->cnt_storage) { /* check pkt counter */ if (pid < MAX_PID) { if (buf[1] & 0x80) @@ -454,7 +445,6 @@ static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf) }; /* end check */ }; -no_dvb_demux_tscheck: list_for_each_entry(feed, &demux->feed_list, list_head) { if ((feed->pid != pid) && (feed->pid != 0x2000)) @@ -1246,6 +1236,7 @@ int dvb_dmx_init(struct dvb_demux *dvbdemux) dvbdemux->feed = vmalloc(dvbdemux->feednum * sizeof(struct dvb_demux_feed)); if (!dvbdemux->feed) { vfree(dvbdemux->filter); + dvbdemux->filter = NULL; return -ENOMEM; } for (i = 0; i < dvbdemux->filternum; i++) { @@ -1257,6 +1248,13 @@ int dvb_dmx_init(struct dvb_demux *dvbdemux) dvbdemux->feed[i].index = i; } + if (dvb_demux_tscheck) { + dvbdemux->cnt_storage = vmalloc(MAX_PID + 1); + + if (!dvbdemux->cnt_storage) + printk(KERN_WARNING "Couldn't allocate memory for TS/TEI check. Disabling it\n"); + } + INIT_LIST_HEAD(&dvbdemux->frontend_list); for (i = 0; i < DMX_TS_PES_OTHER; i++) { diff --git a/drivers/net/ax88796.c b/drivers/net/ax88796.c index 62d9c9cc567..1dd4403247c 100644 --- a/drivers/net/ax88796.c +++ b/drivers/net/ax88796.c @@ -921,7 +921,7 @@ static int ax_probe(struct platform_device *pdev) size = (res->end - res->start) + 1; ax->mem2 = request_mem_region(res->start, size, pdev->name); - if (ax->mem == NULL) { + if (ax->mem2 == NULL) { dev_err(&pdev->dev, "cannot reserve registers\n"); ret = -ENXIO; goto exit_mem1; diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c index bdbd14727e4..318a018ca7c 100644 --- a/drivers/net/cxgb3/sge.c +++ b/drivers/net/cxgb3/sge.c @@ -2079,6 +2079,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, struct sge_fl *fl, int len, int complete) { struct rx_sw_desc *sd = &fl->sdesc[fl->cidx]; + struct port_info *pi = netdev_priv(qs->netdev); struct sk_buff *skb = NULL; struct cpl_rx_pkt *cpl; struct skb_frag_struct *rx_frag; @@ -2116,11 +2117,18 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, if (!nr_frags) { offset = 2 + sizeof(struct cpl_rx_pkt); - qs->lro_va = sd->pg_chunk.va + 2; - } - len -= offset; + cpl = qs->lro_va = sd->pg_chunk.va + 2; - prefetch(qs->lro_va); + if ((pi->rx_offload & T3_RX_CSUM) && + cpl->csum_valid && cpl->csum == htons(0xffff)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + qs->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++; + } else + skb->ip_summed = CHECKSUM_NONE; + } else + cpl = qs->lro_va; + + len -= offset; rx_frag += nr_frags; rx_frag->page = sd->pg_chunk.page; @@ -2136,12 +2144,8 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, return; skb_record_rx_queue(skb, qs - &adap->sge.qs[0]); - skb->ip_summed = CHECKSUM_UNNECESSARY; - cpl = qs->lro_va; if (unlikely(cpl->vlan_valid)) { - struct net_device *dev = qs->netdev; - struct port_info *pi = netdev_priv(dev); struct vlan_group *grp = pi->vlan_grp; if (likely(grp != NULL)) { diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 997124d2992..c881347cb26 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -421,6 +421,8 @@ static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) msixbm = E1000_EICR_RX_QUEUE0 << rx_queue; if (tx_queue > IGB_N0_QUEUE) msixbm |= E1000_EICR_TX_QUEUE0 << tx_queue; + if (!adapter->msix_entries && msix_vector == 0) + msixbm |= E1000_EIMS_OTHER; array_wr32(E1000_MSIXBM(0), msix_vector, msixbm); q_vector->eims_value = msixbm; break; @@ -877,7 +879,6 @@ static int igb_request_irq(struct igb_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; - struct e1000_hw *hw = &adapter->hw; int err = 0; if (adapter->msix_entries) { @@ -909,20 +910,7 @@ static int igb_request_irq(struct igb_adapter *adapter) igb_setup_all_tx_resources(adapter); igb_setup_all_rx_resources(adapter); } else { - switch (hw->mac.type) { - case e1000_82575: - wr32(E1000_MSIXBM(0), - (E1000_EICR_RX_QUEUE0 | - E1000_EICR_TX_QUEUE0 | - E1000_EIMS_OTHER)); - break; - case e1000_82580: - case e1000_82576: - wr32(E1000_IVAR0, E1000_IVAR_VALID); - break; - default: - break; - } + igb_assign_vector(adapter->q_vector[0], 0); } if (adapter->flags & IGB_FLAG_HAS_MSI) { @@ -1140,6 +1128,8 @@ int igb_up(struct igb_adapter *adapter) } if (adapter->msix_entries) igb_configure_msix(adapter); + else + igb_assign_vector(adapter->q_vector[0], 0); /* Clear any pending interrupts. */ rd32(E1000_ICR); diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index b5f64ad6797..7b7c8486c0b 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -5179,7 +5179,7 @@ dma_error: ixgbe_unmap_and_free_tx_resource(adapter, tx_buffer_info); } - return count; + return 0; } static void ixgbe_tx_queue(struct ixgbe_adapter *adapter, @@ -5329,8 +5329,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) struct ixgbe_adapter *adapter = netdev_priv(dev); int txq = smp_processor_id(); - if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + while (unlikely(txq >= dev->real_num_tx_queues)) + txq -= dev->real_num_tx_queues; return txq; + } #ifdef IXGBE_FCOE if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index 9f9d6081959..24279e6e55f 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -1941,7 +1941,7 @@ static void netxen_tx_timeout_task(struct work_struct *work) netif_wake_queue(adapter->netdev); clear_bit(__NX_RESETTING, &adapter->state); - + return; } else { clear_bit(__NX_RESETTING, &adapter->state); if (!netxen_nic_reset_context(adapter)) { @@ -2240,7 +2240,9 @@ netxen_detach_work(struct work_struct *work) netxen_nic_down(adapter, netdev); + rtnl_lock(); netxen_nic_detach(adapter); + rtnl_unlock(); status = NXRD32(adapter, NETXEN_PEG_HALT_STATUS1); diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index d760650c5c0..67249c3c9f5 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -1025,11 +1025,8 @@ static void sky2_prefetch_init(struct sky2_hw *hw, u32 qaddr, static inline struct sky2_tx_le *get_tx_le(struct sky2_port *sky2, u16 *slot) { struct sky2_tx_le *le = sky2->tx_le + *slot; - struct tx_ring_info *re = sky2->tx_ring + *slot; *slot = RING_NEXT(*slot, sky2->tx_ring_size); - re->flags = 0; - re->skb = NULL; le->ctrl = 0; return le; } @@ -1622,8 +1619,7 @@ static unsigned tx_le_req(const struct sk_buff *skb) return count; } -static void sky2_tx_unmap(struct pci_dev *pdev, - const struct tx_ring_info *re) +static void sky2_tx_unmap(struct pci_dev *pdev, struct tx_ring_info *re) { if (re->flags & TX_MAP_SINGLE) pci_unmap_single(pdev, pci_unmap_addr(re, mapaddr), @@ -1633,6 +1629,7 @@ static void sky2_tx_unmap(struct pci_dev *pdev, pci_unmap_page(pdev, pci_unmap_addr(re, mapaddr), pci_unmap_len(re, maplen), PCI_DMA_TODEVICE); + re->flags = 0; } /* @@ -1839,6 +1836,7 @@ static void sky2_tx_complete(struct sky2_port *sky2, u16 done) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + re->skb = NULL; dev_kfree_skb_any(skb); sky2->tx_next = RING_NEXT(idx, sky2->tx_ring_size); diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c index 0ceec123ddf..bee558aed42 100644 --- a/drivers/usb/host/r8a66597-hcd.c +++ b/drivers/usb/host/r8a66597-hcd.c @@ -35,7 +35,9 @@ #include <linux/usb.h> #include <linux/platform_device.h> #include <linux/io.h> +#include <linux/mm.h> #include <linux/irq.h> +#include <asm/cacheflush.h> #include "../core/hcd.h" #include "r8a66597.h" @@ -820,6 +822,26 @@ static void enable_r8a66597_pipe(struct r8a66597 *r8a66597, struct urb *urb, enable_r8a66597_pipe_dma(r8a66597, dev, pipe, urb); } +static void r8a66597_urb_done(struct r8a66597 *r8a66597, struct urb *urb, + int status) +__releases(r8a66597->lock) +__acquires(r8a66597->lock) +{ + if (usb_pipein(urb->pipe) && usb_pipetype(urb->pipe) != PIPE_CONTROL) { + void *ptr; + + for (ptr = urb->transfer_buffer; + ptr < urb->transfer_buffer + urb->transfer_buffer_length; + ptr += PAGE_SIZE) + flush_dcache_page(virt_to_page(ptr)); + } + + usb_hcd_unlink_urb_from_ep(r8a66597_to_hcd(r8a66597), urb); + spin_unlock(&r8a66597->lock); + usb_hcd_giveback_urb(r8a66597_to_hcd(r8a66597), urb, status); + spin_lock(&r8a66597->lock); +} + /* this function must be called with interrupt disabled */ static void force_dequeue(struct r8a66597 *r8a66597, u16 pipenum, u16 address) { @@ -838,15 +860,9 @@ static void force_dequeue(struct r8a66597 *r8a66597, u16 pipenum, u16 address) list_del(&td->queue); kfree(td); - if (urb) { - usb_hcd_unlink_urb_from_ep(r8a66597_to_hcd(r8a66597), - urb); + if (urb) + r8a66597_urb_done(r8a66597, urb, -ENODEV); - spin_unlock(&r8a66597->lock); - usb_hcd_giveback_urb(r8a66597_to_hcd(r8a66597), urb, - -ENODEV); - spin_lock(&r8a66597->lock); - } break; } } @@ -1006,6 +1022,8 @@ static void start_root_hub_sampling(struct r8a66597 *r8a66597, int port, /* this function must be called with interrupt disabled */ static void r8a66597_check_syssts(struct r8a66597 *r8a66597, int port, u16 syssts) +__releases(r8a66597->lock) +__acquires(r8a66597->lock) { if (syssts == SE0) { r8a66597_write(r8a66597, ~ATTCH, get_intsts_reg(port)); @@ -1023,7 +1041,9 @@ static void r8a66597_check_syssts(struct r8a66597 *r8a66597, int port, usb_hcd_resume_root_hub(r8a66597_to_hcd(r8a66597)); } + spin_unlock(&r8a66597->lock); usb_hcd_poll_rh_status(r8a66597_to_hcd(r8a66597)); + spin_lock(&r8a66597->lock); } /* this function must be called with interrupt disabled */ @@ -1283,10 +1303,7 @@ __releases(r8a66597->lock) __acquires(r8a66597->lock) if (usb_pipeisoc(urb->pipe)) urb->start_frame = r8a66597_get_frame(hcd); - usb_hcd_unlink_urb_from_ep(r8a66597_to_hcd(r8a66597), urb); - spin_unlock(&r8a66597->lock); - usb_hcd_giveback_urb(hcd, urb, status); - spin_lock(&r8a66597->lock); + r8a66597_urb_done(r8a66597, urb, status); } if (restart) { diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index cf62b05e296..7d6c2139891 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -84,7 +84,7 @@ static const match_table_t tokens = { static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) { - char *options; + char *options, *tmp_options; substring_t args[MAX_OPT_ARGS]; char *p; int option = 0; @@ -102,9 +102,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) if (!opts) return 0; - options = kstrdup(opts, GFP_KERNEL); - if (!options) + tmp_options = kstrdup(opts, GFP_KERNEL); + if (!tmp_options) { + ret = -ENOMEM; goto fail_option_alloc; + } + options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -159,8 +162,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) break; case Opt_cache: s = match_strdup(&args[0]); - if (!s) - goto fail_option_alloc; + if (!s) { + ret = -ENOMEM; + P9_DPRINTK(P9_DEBUG_ERROR, + "problem allocating copy of cache arg\n"); + goto free_and_return; + } if (strcmp(s, "loose") == 0) v9ses->cache = CACHE_LOOSE; @@ -173,8 +180,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) case Opt_access: s = match_strdup(&args[0]); - if (!s) - goto fail_option_alloc; + if (!s) { + ret = -ENOMEM; + P9_DPRINTK(P9_DEBUG_ERROR, + "problem allocating copy of access arg\n"); + goto free_and_return; + } v9ses->flags &= ~V9FS_ACCESS_MASK; if (strcmp(s, "user") == 0) @@ -194,13 +205,11 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) continue; } } - kfree(options); - return ret; +free_and_return: + kfree(tmp_options); fail_option_alloc: - P9_DPRINTK(P9_DEBUG_ERROR, - "failed to allocate copy of option argument\n"); - return -ENOMEM; + return ret; } /** diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 3a7560e3586..ed835836e0d 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -60,3 +60,4 @@ void v9fs_dentry_release(struct dentry *); int v9fs_uflags2omode(int uflags, int extended); ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64); +void v9fs_blank_wstat(struct p9_wstat *wstat); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 3902bf43a08..74a0461a9ac 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -257,6 +257,23 @@ v9fs_file_write(struct file *filp, const char __user * data, return total; } +static int v9fs_file_fsync(struct file *filp, struct dentry *dentry, + int datasync) +{ + struct p9_fid *fid; + struct p9_wstat wstat; + int retval; + + P9_DPRINTK(P9_DEBUG_VFS, "filp %p dentry %p datasync %x\n", filp, + dentry, datasync); + + fid = filp->private_data; + v9fs_blank_wstat(&wstat); + + retval = p9_client_wstat(fid, &wstat); + return retval; +} + static const struct file_operations v9fs_cached_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, @@ -266,6 +283,7 @@ static const struct file_operations v9fs_cached_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, + .fsync = v9fs_file_fsync, }; const struct file_operations v9fs_file_operations = { @@ -276,4 +294,5 @@ const struct file_operations v9fs_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, + .fsync = v9fs_file_fsync, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 9d03d1ebca6..a407fa3388c 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -176,7 +176,7 @@ int v9fs_uflags2omode(int uflags, int extended) * */ -static void +void v9fs_blank_wstat(struct p9_wstat *wstat) { wstat->type = ~0; diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 7b2600b380d..49503d2edc7 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,7 @@ +Version 1.62 +------------ +Add sockopt=TCP_NODELAY mount option. + Version 1.61 ------------ Fix append problem to Samba servers (files opened with O_APPEND could diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index ac2b24c192f..78c1b86d55f 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -113,5 +113,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* EXPERIMENTAL */ -#define CIFS_VERSION "1.61" +#define CIFS_VERSION "1.62" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 4b35f7ec058..ed751bb657d 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -149,6 +149,7 @@ struct TCP_Server_Info { bool svlocal:1; /* local server or remote */ bool noblocksnd; /* use blocking sendmsg */ bool noautotune; /* do not autotune send buf sizes */ + bool tcp_nodelay; atomic_t inFlight; /* number of requests on the wire to server */ #ifdef CONFIG_CIFS_STATS2 atomic_t inSend; /* requests trying to send */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 3bbcaa716b3..2e9e09ca0e3 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -98,7 +98,7 @@ struct smb_vol { bool nostrictsync:1; /* do not force expensive SMBflush on every sync */ unsigned int rsize; unsigned int wsize; - unsigned int sockopt; + bool sockopt_tcp_nodelay:1; unsigned short int port; char *prepath; }; @@ -1142,9 +1142,11 @@ cifs_parse_mount_options(char *options, const char *devname, simple_strtoul(value, &value, 0); } } else if (strnicmp(data, "sockopt", 5) == 0) { - if (value && *value) { - vol->sockopt = - simple_strtoul(value, &value, 0); + if (!value || !*value) { + cERROR(1, ("no socket option specified")); + continue; + } else if (strnicmp(value, "TCP_NODELAY", 11) == 0) { + vol->sockopt_tcp_nodelay = 1; } } else if (strnicmp(data, "netbiosname", 4) == 0) { if (!value || !*value || (*value == ' ')) { @@ -1514,6 +1516,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) tcp_ses->noblocksnd = volume_info->noblocksnd; tcp_ses->noautotune = volume_info->noautotune; + tcp_ses->tcp_nodelay = volume_info->sockopt_tcp_nodelay; atomic_set(&tcp_ses->inFlight, 0); init_waitqueue_head(&tcp_ses->response_q); init_waitqueue_head(&tcp_ses->request_q); @@ -1764,6 +1767,7 @@ static int ipv4_connect(struct TCP_Server_Info *server) { int rc = 0; + int val; bool connected = false; __be16 orig_port = 0; struct socket *socket = server->ssocket; @@ -1845,6 +1849,14 @@ ipv4_connect(struct TCP_Server_Info *server) socket->sk->sk_rcvbuf = 140 * 1024; } + if (server->tcp_nodelay) { + val = 1; + rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY, + (char *)&val, sizeof(val)); + if (rc) + cFYI(1, ("set TCP_NODELAY socket option error %d", rc)); + } + cFYI(1, ("sndbuf %d rcvbuf %d rcvtimeo 0x%lx", socket->sk->sk_sndbuf, socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo)); @@ -1916,6 +1928,7 @@ static int ipv6_connect(struct TCP_Server_Info *server) { int rc = 0; + int val; bool connected = false; __be16 orig_port = 0; struct socket *socket = server->ssocket; @@ -1987,6 +2000,15 @@ ipv6_connect(struct TCP_Server_Info *server) */ socket->sk->sk_rcvtimeo = 7 * HZ; socket->sk->sk_sndtimeo = 5 * HZ; + + if (server->tcp_nodelay) { + val = 1; + rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY, + (char *)&val, sizeof(val)); + if (rc) + cFYI(1, ("set TCP_NODELAY socket option error %d", rc)); + } + server->ssocket = socket; return rc; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index cf18ee76559..e3fda978f48 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1762,8 +1762,18 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) CIFS_MOUNT_MAP_SPECIAL_CHR); } - if (!rc) + if (!rc) { rc = inode_setattr(inode, attrs); + + /* force revalidate when any of these times are set since some + of the fs types (eg ext3, fat) do not have fine enough + time granularity to match protocol, and we do not have a + a way (yet) to query the server fs's time granularity (and + whether it rounds times down). + */ + if (!rc && (attrs->ia_valid & (ATTR_MTIME | ATTR_CTIME))) + cifsInode->time = 0; + } out: kfree(args); kfree(full_path); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index f84062f9a98..c343b14ba2d 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -77,6 +77,11 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, cFYI(1, ("For %s", name->name)); + if (parent->d_op && parent->d_op->d_hash) + parent->d_op->d_hash(parent, name); + else + name->hash = full_name_hash(name->name, name->len); + dentry = d_lookup(parent, name); if (dentry) { /* FIXME: check for inode number changes? */ @@ -666,12 +671,11 @@ static int cifs_get_name_from_search_buf(struct qstr *pqst, min(len, max_len), nlt, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + pqst->len -= nls_nullsize(nlt); } else { pqst->name = filename; pqst->len = len; } - pqst->hash = full_name_hash(pqst->name, pqst->len); -/* cFYI(1, ("filldir on %s",pqst->name)); */ return rc; } diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 7085a6275c4..aaa9c1c5a5b 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -223,9 +223,9 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, /* null user mount */ *bcc_ptr = 0; *(bcc_ptr+1) = 0; - } else { /* 300 should be long enough for any conceivable user name */ + } else { bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->userName, - 300, nls_cp); + MAX_USERNAME_SIZE, nls_cp); } bcc_ptr += 2 * bytes_ret; bcc_ptr += 2; /* account for null termination */ @@ -246,11 +246,10 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, /* copy user */ if (ses->userName == NULL) { /* BB what about null user mounts - check that we do this BB */ - } else { /* 300 should be long enough for any conceivable user name */ - strncpy(bcc_ptr, ses->userName, 300); + } else { + strncpy(bcc_ptr, ses->userName, MAX_USERNAME_SIZE); } - /* BB improve check for overflow */ - bcc_ptr += strnlen(ses->userName, 300); + bcc_ptr += strnlen(ses->userName, MAX_USERNAME_SIZE); *bcc_ptr = 0; bcc_ptr++; /* account for null termination */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index c487810a236..a0c4016413f 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1316,19 +1316,11 @@ rqst_exp_parent(struct svc_rqst *rqstp, struct path *path) static struct svc_export *find_fsidzero_export(struct svc_rqst *rqstp) { - struct svc_export *exp; u32 fsidv[2]; mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); - exp = rqst_exp_find(rqstp, FSID_NUM, fsidv); - /* - * We shouldn't have accepting an nfsv4 request at all if we - * don't have a pseudoexport!: - */ - if (IS_ERR(exp) && PTR_ERR(exp) == -ENOENT) - exp = ERR_PTR(-ESERVERFAULT); - return exp; + return rqst_exp_find(rqstp, FSID_NUM, fsidv); } /* diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 3dae4a13f6e..7e9df11260f 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -599,7 +599,7 @@ bail: return ret; } -/* +/* * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're * particularly interested in the aio/dio case. Like the core uses * i_alloc_sem, we use the rw_lock DLM lock to protect io on one node from @@ -670,7 +670,7 @@ static ssize_t ocfs2_direct_IO(int rw, ret = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, - nr_segs, + nr_segs, ocfs2_direct_IO_get_blocks, ocfs2_dio_end_io); diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index d43d34a1dd3..21c808f752d 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -368,7 +368,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, } ocfs2_metadata_cache_io_unlock(ci); - mlog(ML_BH_IO, "block=(%llu), nr=(%d), cached=%s, flags=0x%x\n", + mlog(ML_BH_IO, "block=(%llu), nr=(%d), cached=%s, flags=0x%x\n", (unsigned long long)block, nr, ((flags & OCFS2_BH_IGNORE_CACHE) || ignore_cache) ? "no" : "yes", flags); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index eda5b8bcddd..5c989000670 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -78,7 +78,7 @@ static struct o2hb_callback *hbcall_from_type(enum o2hb_callback_type type); unsigned int o2hb_dead_threshold = O2HB_DEFAULT_DEAD_THRESHOLD; -/* Only sets a new threshold if there are no active regions. +/* Only sets a new threshold if there are no active regions. * * No locking or otherwise interesting code is required for reading * o2hb_dead_threshold as it can't change once regions are active and @@ -170,7 +170,7 @@ static void o2hb_write_timeout(struct work_struct *work) mlog(ML_ERROR, "Heartbeat write timeout to device %s after %u " "milliseconds\n", reg->hr_dev_name, - jiffies_to_msecs(jiffies - reg->hr_last_timeout_start)); + jiffies_to_msecs(jiffies - reg->hr_last_timeout_start)); o2quo_disk_timeout(); } @@ -624,7 +624,7 @@ static int o2hb_check_slot(struct o2hb_region *reg, "seq %llu last %llu changed %u equal %u\n", slot->ds_node_num, (long long)slot->ds_last_generation, le32_to_cpu(hb_block->hb_cksum), - (unsigned long long)le64_to_cpu(hb_block->hb_seq), + (unsigned long long)le64_to_cpu(hb_block->hb_seq), (unsigned long long)slot->ds_last_time, slot->ds_changed_samples, slot->ds_equal_samples); diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 334f231a422..d8d0c65ac03 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -485,7 +485,7 @@ static void o2net_set_nn_state(struct o2net_node *nn, } if (was_valid && !valid) { - printk(KERN_INFO "o2net: no longer connected to " + printk(KERN_NOTICE "o2net: no longer connected to " SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc)); o2net_complete_nodes_nsw(nn); } @@ -493,7 +493,7 @@ static void o2net_set_nn_state(struct o2net_node *nn, if (!was_valid && valid) { o2quo_conn_up(o2net_num_from_nn(nn)); cancel_delayed_work(&nn->nn_connect_expired); - printk(KERN_INFO "o2net: %s " SC_NODEF_FMT "\n", + printk(KERN_NOTICE "o2net: %s " SC_NODEF_FMT "\n", o2nm_this_node() > sc->sc_node->nd_num ? "connected to" : "accepted connection from", SC_NODEF_ARGS(sc)); @@ -930,7 +930,7 @@ static void o2net_sendpage(struct o2net_sock_container *sc, cond_resched(); continue; } - mlog(ML_ERROR, "sendpage of size %zu to " SC_NODEF_FMT + mlog(ML_ERROR, "sendpage of size %zu to " SC_NODEF_FMT " failed with %zd\n", size, SC_NODEF_ARGS(sc), ret); o2net_ensure_shutdown(nn, sc, 0); break; @@ -1476,14 +1476,14 @@ static void o2net_idle_timer(unsigned long data) do_gettimeofday(&now); - printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT " has been idle for %u.%u " + printk(KERN_NOTICE "o2net: connection to " SC_NODEF_FMT " has been idle for %u.%u " "seconds, shutting it down.\n", SC_NODEF_ARGS(sc), o2net_idle_timeout() / 1000, o2net_idle_timeout() % 1000); mlog(ML_NOTICE, "here are some times that might help debug the " "situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv " "%ld.%ld:%ld.%ld func (%08x:%u) %ld.%ld:%ld.%ld)\n", - sc->sc_tv_timer.tv_sec, (long) sc->sc_tv_timer.tv_usec, + sc->sc_tv_timer.tv_sec, (long) sc->sc_tv_timer.tv_usec, now.tv_sec, (long) now.tv_usec, sc->sc_tv_data_ready.tv_sec, (long) sc->sc_tv_data_ready.tv_usec, sc->sc_tv_advance_start.tv_sec, diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h index 8d58cfe410b..96fa7ebc530 100644 --- a/fs/ocfs2/cluster/tcp_internal.h +++ b/fs/ocfs2/cluster/tcp_internal.h @@ -32,10 +32,10 @@ * on their number */ #define O2NET_QUORUM_DELAY_MS ((o2hb_dead_threshold + 2) * O2HB_REGION_TIMEOUT_MS) -/* +/* * This version number represents quite a lot, unfortunately. It not * only represents the raw network message protocol on the wire but also - * locking semantics of the file system using the protocol. It should + * locking semantics of the file system using the protocol. It should * be somewhere else, I'm sure, but right now it isn't. * * With version 11, we separate out the filesystem locking portion. The diff --git a/fs/ocfs2/dlm/dlmapi.h b/fs/ocfs2/dlm/dlmapi.h index b5786a787fa..3cfa114aa39 100644 --- a/fs/ocfs2/dlm/dlmapi.h +++ b/fs/ocfs2/dlm/dlmapi.h @@ -95,7 +95,7 @@ const char *dlm_errname(enum dlm_status err); mlog(ML_ERROR, "dlm status = %s\n", dlm_errname((st))); \ } while (0) -#define DLM_LKSB_UNUSED1 0x01 +#define DLM_LKSB_UNUSED1 0x01 #define DLM_LKSB_PUT_LVB 0x02 #define DLM_LKSB_GET_LVB 0x04 #define DLM_LKSB_UNUSED2 0x08 diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index 01cf8cc3d28..dccc439fa08 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -123,7 +123,7 @@ static void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock) dlm_lock_put(lock); /* free up the reserved bast that we are cancelling. * guaranteed that this will not be the last reserved - * ast because *both* an ast and a bast were reserved + * ast because *both* an ast and a bast were reserved * to get to this point. the res->spinlock will not be * taken here */ dlm_lockres_release_ast(dlm, res); diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index ca96bce50e1..f283bce776b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -396,7 +396,7 @@ static enum dlm_status dlm_send_remote_convert_request(struct dlm_ctxt *dlm, /* instead of logging the same network error over * and over, sleep here and wait for the heartbeat * to notice the node is dead. times out after 5s. */ - dlm_wait_for_node_death(dlm, res->owner, + dlm_wait_for_node_death(dlm, res->owner, DLM_NODE_DEATH_WAIT_MAX); ret = DLM_RECOVERING; mlog(0, "node %u died so returning DLM_RECOVERING " diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index 42b0bad7a61..0cd24cf5439 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -102,7 +102,7 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res) assert_spin_locked(&res->spinlock); stringify_lockname(res->lockname.name, res->lockname.len, - buf, sizeof(buf) - 1); + buf, sizeof(buf)); printk("lockres: %s, owner=%u, state=%u\n", buf, res->owner, res->state); printk(" last used: %lu, refcnt: %u, on purge list: %s\n", diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 0334000676d..988c9055fd4 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -816,7 +816,7 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, } /* Once the dlm ctxt is marked as leaving then we don't want - * to be put in someone's domain map. + * to be put in someone's domain map. * Also, explicitly disallow joining at certain troublesome * times (ie. during recovery). */ if (dlm && dlm->dlm_state != DLM_CTXT_LEAVING) { diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 437698e9465..73333777267 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -269,7 +269,7 @@ static enum dlm_status dlmlock_remote(struct dlm_ctxt *dlm, } dlm_revert_pending_lock(res, lock); dlm_lock_put(lock); - } else if (dlm_is_recovery_lock(res->lockname.name, + } else if (dlm_is_recovery_lock(res->lockname.name, res->lockname.len)) { /* special case for the $RECOVERY lock. * there will never be an AST delivered to put diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 03ccf9a7b1f..a659606dcb9 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -366,7 +366,7 @@ void dlm_hb_event_notify_attached(struct dlm_ctxt *dlm, int idx, int node_up) struct dlm_master_list_entry *mle; assert_spin_locked(&dlm->spinlock); - + list_for_each_entry(mle, &dlm->mle_hb_events, hb_events) { if (node_up) dlm_mle_node_up(dlm, mle, NULL, idx); @@ -833,7 +833,7 @@ lookup: __dlm_insert_mle(dlm, mle); /* still holding the dlm spinlock, check the recovery map - * to see if there are any nodes that still need to be + * to see if there are any nodes that still need to be * considered. these will not appear in the mle nodemap * but they might own this lockres. wait on them. */ bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0); @@ -883,7 +883,7 @@ redo_request: msleep(500); } continue; - } + } dlm_kick_recovery_thread(dlm); msleep(1000); @@ -939,8 +939,8 @@ wait: res->lockname.name, blocked); if (++tries > 20) { mlog(ML_ERROR, "%s:%.*s: spinning on " - "dlm_wait_for_lock_mastery, blocked=%d\n", - dlm->name, res->lockname.len, + "dlm_wait_for_lock_mastery, blocked=%d\n", + dlm->name, res->lockname.len, res->lockname.name, blocked); dlm_print_one_lock_resource(res); dlm_print_one_mle(mle); @@ -1029,7 +1029,7 @@ recheck: ret = dlm_restart_lock_mastery(dlm, res, mle, *blocked); b = (mle->type == DLM_MLE_BLOCK); if ((*blocked && !b) || (!*blocked && b)) { - mlog(0, "%s:%.*s: status change: old=%d new=%d\n", + mlog(0, "%s:%.*s: status change: old=%d new=%d\n", dlm->name, res->lockname.len, res->lockname.name, *blocked, b); *blocked = b; @@ -1602,7 +1602,7 @@ send_response: } mlog(0, "%u is the owner of %.*s, cleaning everyone else\n", dlm->node_num, res->lockname.len, res->lockname.name); - ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx, + ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx, DLM_ASSERT_MASTER_MLE_CLEANUP); if (ret < 0) { mlog(ML_ERROR, "failed to dispatch assert master work\n"); @@ -1701,7 +1701,7 @@ again: if (r & DLM_ASSERT_RESPONSE_REASSERT) { mlog(0, "%.*s: node %u create mles on other " - "nodes and requests a re-assert\n", + "nodes and requests a re-assert\n", namelen, lockname, to); reassert = 1; } @@ -1812,7 +1812,7 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data, spin_unlock(&dlm->master_lock); spin_unlock(&dlm->spinlock); goto done; - } + } } } spin_unlock(&dlm->master_lock); @@ -1883,7 +1883,7 @@ ok: int extra_ref = 0; int nn = -1; int rr, err = 0; - + spin_lock(&mle->spinlock); if (mle->type == DLM_MLE_BLOCK || mle->type == DLM_MLE_MIGRATION) extra_ref = 1; @@ -1891,7 +1891,7 @@ ok: /* MASTER mle: if any bits set in the response map * then the calling node needs to re-assert to clear * up nodes that this node contacted */ - while ((nn = find_next_bit (mle->response_map, O2NM_MAX_NODES, + while ((nn = find_next_bit (mle->response_map, O2NM_MAX_NODES, nn+1)) < O2NM_MAX_NODES) { if (nn != dlm->node_num && nn != assert->node_idx) master_request = 1; @@ -2002,7 +2002,7 @@ kill: __dlm_print_one_lock_resource(res); spin_unlock(&res->spinlock); spin_unlock(&dlm->spinlock); - *ret_data = (void *)res; + *ret_data = (void *)res; dlm_put(dlm); return -EINVAL; } @@ -2040,10 +2040,10 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm, item->u.am.request_from = request_from; item->u.am.flags = flags; - if (ignore_higher) - mlog(0, "IGNORE HIGHER: %.*s\n", res->lockname.len, + if (ignore_higher) + mlog(0, "IGNORE HIGHER: %.*s\n", res->lockname.len, res->lockname.name); - + spin_lock(&dlm->work_lock); list_add_tail(&item->list, &dlm->work_list); spin_unlock(&dlm->work_lock); @@ -2133,7 +2133,7 @@ put: * think that $RECOVERY is currently mastered by a dead node. If so, * we wait a short time to allow that node to get notified by its own * heartbeat stack, then check again. All $RECOVERY lock resources - * mastered by dead nodes are purged when the hearbeat callback is + * mastered by dead nodes are purged when the hearbeat callback is * fired, so we can know for sure that it is safe to continue once * the node returns a live node or no node. */ static int dlm_pre_master_reco_lockres(struct dlm_ctxt *dlm, @@ -2174,7 +2174,7 @@ static int dlm_pre_master_reco_lockres(struct dlm_ctxt *dlm, ret = -EAGAIN; } spin_unlock(&dlm->spinlock); - mlog(0, "%s: reco lock master is %u\n", dlm->name, + mlog(0, "%s: reco lock master is %u\n", dlm->name, master); break; } @@ -2602,7 +2602,7 @@ fail: mlog(0, "%s:%.*s: timed out during migration\n", dlm->name, res->lockname.len, res->lockname.name); - /* avoid hang during shutdown when migrating lockres + /* avoid hang during shutdown when migrating lockres * to a node which also goes down */ if (dlm_is_node_dead(dlm, target)) { mlog(0, "%s:%.*s: expected migration " @@ -2738,7 +2738,7 @@ static int dlm_migration_can_proceed(struct dlm_ctxt *dlm, can_proceed = !!(res->state & DLM_LOCK_RES_MIGRATING); spin_unlock(&res->spinlock); - /* target has died, so make the caller break out of the + /* target has died, so make the caller break out of the * wait_event, but caller must recheck the domain_map */ spin_lock(&dlm->spinlock); if (!test_bit(mig_target, dlm->domain_map)) diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 2f9e4e19a4f..344bcf90cbf 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1050,7 +1050,7 @@ static void dlm_move_reco_locks_to_list(struct dlm_ctxt *dlm, if (lock->ml.node == dead_node) { mlog(0, "AHA! there was " "a $RECOVERY lock for dead " - "node %u (%s)!\n", + "node %u (%s)!\n", dead_node, dlm->name); list_del_init(&lock->list); dlm_lock_put(lock); @@ -1164,6 +1164,39 @@ static void dlm_init_migratable_lockres(struct dlm_migratable_lockres *mres, mres->master = master; } +static void dlm_prepare_lvb_for_migration(struct dlm_lock *lock, + struct dlm_migratable_lockres *mres, + int queue) +{ + if (!lock->lksb) + return; + + /* Ignore lvb in all locks in the blocked list */ + if (queue == DLM_BLOCKED_LIST) + return; + + /* Only consider lvbs in locks with granted EX or PR lock levels */ + if (lock->ml.type != LKM_EXMODE && lock->ml.type != LKM_PRMODE) + return; + + if (dlm_lvb_is_empty(mres->lvb)) { + memcpy(mres->lvb, lock->lksb->lvb, DLM_LVB_LEN); + return; + } + + /* Ensure the lvb copied for migration matches in other valid locks */ + if (!memcmp(mres->lvb, lock->lksb->lvb, DLM_LVB_LEN)) + return; + + mlog(ML_ERROR, "Mismatched lvb in lock cookie=%u:%llu, name=%.*s, " + "node=%u\n", + dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), + dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), + lock->lockres->lockname.len, lock->lockres->lockname.name, + lock->ml.node); + dlm_print_one_lock_resource(lock->lockres); + BUG(); +} /* returns 1 if this lock fills the network structure, * 0 otherwise */ @@ -1181,20 +1214,7 @@ static int dlm_add_lock_to_array(struct dlm_lock *lock, ml->list = queue; if (lock->lksb) { ml->flags = lock->lksb->flags; - /* send our current lvb */ - if (ml->type == LKM_EXMODE || - ml->type == LKM_PRMODE) { - /* if it is already set, this had better be a PR - * and it has to match */ - if (!dlm_lvb_is_empty(mres->lvb) && - (ml->type == LKM_EXMODE || - memcmp(mres->lvb, lock->lksb->lvb, DLM_LVB_LEN))) { - mlog(ML_ERROR, "mismatched lvbs!\n"); - dlm_print_one_lock_resource(lock->lockres); - BUG(); - } - memcpy(mres->lvb, lock->lksb->lvb, DLM_LVB_LEN); - } + dlm_prepare_lvb_for_migration(lock, mres, queue); } ml->node = lock->ml.node; mres->num_locks++; @@ -1730,6 +1750,7 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, struct dlm_lock *lock = NULL; u8 from = O2NM_MAX_NODES; unsigned int added = 0; + __be64 c; mlog(0, "running %d locks for this lockres\n", mres->num_locks); for (i=0; i<mres->num_locks; i++) { @@ -1777,19 +1798,48 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, /* lock is always created locally first, and * destroyed locally last. it must be on the list */ if (!lock) { - __be64 c = ml->cookie; - mlog(ML_ERROR, "could not find local lock " - "with cookie %u:%llu!\n", + c = ml->cookie; + mlog(ML_ERROR, "Could not find local lock " + "with cookie %u:%llu, node %u, " + "list %u, flags 0x%x, type %d, " + "conv %d, highest blocked %d\n", dlm_get_lock_cookie_node(be64_to_cpu(c)), - dlm_get_lock_cookie_seq(be64_to_cpu(c))); + dlm_get_lock_cookie_seq(be64_to_cpu(c)), + ml->node, ml->list, ml->flags, ml->type, + ml->convert_type, ml->highest_blocked); + __dlm_print_one_lock_resource(res); + BUG(); + } + + if (lock->ml.node != ml->node) { + c = lock->ml.cookie; + mlog(ML_ERROR, "Mismatched node# in lock " + "cookie %u:%llu, name %.*s, node %u\n", + dlm_get_lock_cookie_node(be64_to_cpu(c)), + dlm_get_lock_cookie_seq(be64_to_cpu(c)), + res->lockname.len, res->lockname.name, + lock->ml.node); + c = ml->cookie; + mlog(ML_ERROR, "Migrate lock cookie %u:%llu, " + "node %u, list %u, flags 0x%x, type %d, " + "conv %d, highest blocked %d\n", + dlm_get_lock_cookie_node(be64_to_cpu(c)), + dlm_get_lock_cookie_seq(be64_to_cpu(c)), + ml->node, ml->list, ml->flags, ml->type, + ml->convert_type, ml->highest_blocked); __dlm_print_one_lock_resource(res); BUG(); } - BUG_ON(lock->ml.node != ml->node); if (tmpq != queue) { - mlog(0, "lock was on %u instead of %u for %.*s\n", - j, ml->list, res->lockname.len, res->lockname.name); + c = ml->cookie; + mlog(0, "Lock cookie %u:%llu was on list %u " + "instead of list %u for %.*s\n", + dlm_get_lock_cookie_node(be64_to_cpu(c)), + dlm_get_lock_cookie_seq(be64_to_cpu(c)), + j, ml->list, res->lockname.len, + res->lockname.name); + __dlm_print_one_lock_resource(res); spin_unlock(&res->spinlock); continue; } @@ -1839,7 +1889,7 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, * the lvb. */ memcpy(res->lvb, mres->lvb, DLM_LVB_LEN); } else { - /* otherwise, the node is sending its + /* otherwise, the node is sending its * most recent valid lvb info */ BUG_ON(ml->type != LKM_EXMODE && ml->type != LKM_PRMODE); @@ -1886,7 +1936,7 @@ skip_lvb: spin_lock(&res->spinlock); list_for_each_entry(lock, queue, list) { if (lock->ml.cookie == ml->cookie) { - __be64 c = lock->ml.cookie; + c = lock->ml.cookie; mlog(ML_ERROR, "%s:%.*s: %u:%llu: lock already " "exists on this lockres!\n", dlm->name, res->lockname.len, res->lockname.name, @@ -2114,7 +2164,7 @@ static void dlm_revalidate_lvb(struct dlm_ctxt *dlm, assert_spin_locked(&res->spinlock); if (res->owner == dlm->node_num) - /* if this node owned the lockres, and if the dead node + /* if this node owned the lockres, and if the dead node * had an EX when he died, blank out the lvb */ search_node = dead_node; else { @@ -2152,7 +2202,7 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, /* this node is the lockres master: * 1) remove any stale locks for the dead node - * 2) if the dead node had an EX when he died, blank out the lvb + * 2) if the dead node had an EX when he died, blank out the lvb */ assert_spin_locked(&dlm->spinlock); assert_spin_locked(&res->spinlock); @@ -2193,7 +2243,12 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, mlog(0, "%s:%.*s: freed %u locks for dead node %u, " "dropping ref from lockres\n", dlm->name, res->lockname.len, res->lockname.name, freed, dead_node); - BUG_ON(!test_bit(dead_node, res->refmap)); + if(!test_bit(dead_node, res->refmap)) { + mlog(ML_ERROR, "%s:%.*s: freed %u locks for dead node %u, " + "but ref was not set\n", dlm->name, + res->lockname.len, res->lockname.name, freed, dead_node); + __dlm_print_one_lock_resource(res); + } dlm_lockres_clear_refmap_bit(dead_node, res); } else if (test_bit(dead_node, res->refmap)) { mlog(0, "%s:%.*s: dead node %u had a ref, but had " @@ -2260,7 +2315,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) } spin_unlock(&res->spinlock); continue; - } + } spin_lock(&res->spinlock); /* zero the lvb if necessary */ dlm_revalidate_lvb(dlm, res, dead_node); @@ -2411,7 +2466,7 @@ static void dlm_reco_unlock_ast(void *astdata, enum dlm_status st) * this function on each node racing to become the recovery * master will not stop attempting this until either: * a) this node gets the EX (and becomes the recovery master), - * or b) dlm->reco.new_master gets set to some nodenum + * or b) dlm->reco.new_master gets set to some nodenum * != O2NM_INVALID_NODE_NUM (another node will do the reco). * so each time a recovery master is needed, the entire cluster * will sync at this point. if the new master dies, that will @@ -2424,7 +2479,7 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) mlog(0, "starting recovery of %s at %lu, dead=%u, this=%u\n", dlm->name, jiffies, dlm->reco.dead_node, dlm->node_num); -again: +again: memset(&lksb, 0, sizeof(lksb)); ret = dlmlock(dlm, LKM_EXMODE, &lksb, LKM_NOQUEUE|LKM_RECOVERY, @@ -2437,8 +2492,8 @@ again: if (ret == DLM_NORMAL) { mlog(0, "dlm=%s dlmlock says I got it (this=%u)\n", dlm->name, dlm->node_num); - - /* got the EX lock. check to see if another node + + /* got the EX lock. check to see if another node * just became the reco master */ if (dlm_reco_master_ready(dlm)) { mlog(0, "%s: got reco EX lock, but %u will " @@ -2451,12 +2506,12 @@ again: /* see if recovery was already finished elsewhere */ spin_lock(&dlm->spinlock); if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) { - status = -EINVAL; + status = -EINVAL; mlog(0, "%s: got reco EX lock, but " "node got recovered already\n", dlm->name); if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) { mlog(ML_ERROR, "%s: new master is %u " - "but no dead node!\n", + "but no dead node!\n", dlm->name, dlm->reco.new_master); BUG(); } @@ -2468,7 +2523,7 @@ again: * set the master and send the messages to begin recovery */ if (!status) { mlog(0, "%s: dead=%u, this=%u, sending " - "begin_reco now\n", dlm->name, + "begin_reco now\n", dlm->name, dlm->reco.dead_node, dlm->node_num); status = dlm_send_begin_reco_message(dlm, dlm->reco.dead_node); @@ -2501,7 +2556,7 @@ again: mlog(0, "dlm=%s dlmlock says another node got it (this=%u)\n", dlm->name, dlm->node_num); /* another node is master. wait on - * reco.new_master != O2NM_INVALID_NODE_NUM + * reco.new_master != O2NM_INVALID_NODE_NUM * for at most one second */ wait_event_timeout(dlm->dlm_reco_thread_wq, dlm_reco_master_ready(dlm), @@ -2589,7 +2644,13 @@ retry: "begin reco msg (%d)\n", dlm->name, nodenum, ret); ret = 0; } - if (ret == -EAGAIN) { + + /* + * Prior to commit aad1b15310b9bcd59fa81ab8f2b1513b59553ea8, + * dlm_begin_reco_handler() returned EAGAIN and not -EAGAIN. + * We are handling both for compatibility reasons. + */ + if (ret == -EAGAIN || ret == EAGAIN) { mlog(0, "%s: trying to start recovery of node " "%u, but node %u is waiting for last recovery " "to complete, backoff for a bit\n", dlm->name, @@ -2599,7 +2660,7 @@ retry: } if (ret < 0) { struct dlm_lock_resource *res; - /* this is now a serious problem, possibly ENOMEM + /* this is now a serious problem, possibly ENOMEM * in the network stack. must retry */ mlog_errno(ret); mlog(ML_ERROR, "begin reco of dlm %s to node %u " @@ -2612,7 +2673,7 @@ retry: } else { mlog(ML_ERROR, "recovery lock not found\n"); } - /* sleep for a bit in hopes that we can avoid + /* sleep for a bit in hopes that we can avoid * another ENOMEM */ msleep(100); goto retry; @@ -2664,7 +2725,7 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, } if (dlm->reco.dead_node != O2NM_INVALID_NODE_NUM) { mlog(ML_NOTICE, "%s: dead_node previously set to %u, " - "node %u changing it to %u\n", dlm->name, + "node %u changing it to %u\n", dlm->name, dlm->reco.dead_node, br->node_idx, br->dead_node); } dlm_set_reco_master(dlm, br->node_idx); @@ -2730,8 +2791,8 @@ stage2: if (ret < 0) { mlog_errno(ret); if (dlm_is_host_down(ret)) { - /* this has no effect on this recovery - * session, so set the status to zero to + /* this has no effect on this recovery + * session, so set the status to zero to * finish out the last recovery */ mlog(ML_ERROR, "node %u went down after this " "node finished recovery.\n", nodenum); @@ -2768,7 +2829,7 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data, mlog(0, "%s: node %u finalizing recovery stage%d of " "node %u (%u:%u)\n", dlm->name, fr->node_idx, stage, fr->dead_node, dlm->reco.dead_node, dlm->reco.new_master); - + spin_lock(&dlm->spinlock); if (dlm->reco.new_master != fr->node_idx) { diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 00f53b2aea7..49e29ecd020 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -190,8 +190,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, actions &= ~(DLM_UNLOCK_REMOVE_LOCK| DLM_UNLOCK_REGRANT_LOCK| DLM_UNLOCK_CLEAR_CONVERT_TYPE); - } else if (status == DLM_RECOVERING || - status == DLM_MIGRATING || + } else if (status == DLM_RECOVERING || + status == DLM_MIGRATING || status == DLM_FORWARD) { /* must clear the actions because this unlock * is about to be retried. cannot free or do @@ -661,14 +661,14 @@ retry: if (call_ast) { mlog(0, "calling unlockast(%p, %d)\n", data, status); if (is_master) { - /* it is possible that there is one last bast + /* it is possible that there is one last bast * pending. make sure it is flushed, then * call the unlockast. * not an issue if this is a mastered remotely, * since this lock has been removed from the * lockres queues and cannot be found. */ dlm_kick_thread(dlm, NULL); - wait_event(dlm->ast_wq, + wait_event(dlm->ast_wq, dlm_lock_basts_flushed(dlm, lock)); } (*unlockast)(data, status); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index c5e4a49e3a1..e044019cb3b 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -875,6 +875,14 @@ static inline void ocfs2_generic_handle_convert_action(struct ocfs2_lock_res *lo lockres_or_flags(lockres, OCFS2_LOCK_NEEDS_REFRESH); lockres->l_level = lockres->l_requested; + + /* + * We set the OCFS2_LOCK_UPCONVERT_FINISHING flag before clearing + * the OCFS2_LOCK_BUSY flag to prevent the dc thread from + * downconverting the lock before the upconvert has fully completed. + */ + lockres_or_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); + lockres_clear_flags(lockres, OCFS2_LOCK_BUSY); mlog_exit_void(); @@ -907,8 +915,6 @@ static int ocfs2_generic_handle_bast(struct ocfs2_lock_res *lockres, assert_spin_locked(&lockres->l_lock); - lockres_or_flags(lockres, OCFS2_LOCK_BLOCKED); - if (level > lockres->l_blocking) { /* only schedule a downconvert if we haven't already scheduled * one that goes low enough to satisfy the level we're @@ -921,6 +927,9 @@ static int ocfs2_generic_handle_bast(struct ocfs2_lock_res *lockres, lockres->l_blocking = level; } + if (needs_downconvert) + lockres_or_flags(lockres, OCFS2_LOCK_BLOCKED); + mlog_exit(needs_downconvert); return needs_downconvert; } @@ -1133,6 +1142,7 @@ static inline void ocfs2_recover_from_dlm_error(struct ocfs2_lock_res *lockres, mlog_entry_void(); spin_lock_irqsave(&lockres->l_lock, flags); lockres_clear_flags(lockres, OCFS2_LOCK_BUSY); + lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); if (convert) lockres->l_action = OCFS2_AST_INVALID; else @@ -1323,13 +1333,13 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb, again: wait = 0; + spin_lock_irqsave(&lockres->l_lock, flags); + if (catch_signals && signal_pending(current)) { ret = -ERESTARTSYS; - goto out; + goto unlock; } - spin_lock_irqsave(&lockres->l_lock, flags); - mlog_bug_on_msg(lockres->l_flags & OCFS2_LOCK_FREEING, "Cluster lock called on freeing lockres %s! flags " "0x%lx\n", lockres->l_name, lockres->l_flags); @@ -1346,6 +1356,25 @@ again: goto unlock; } + if (lockres->l_flags & OCFS2_LOCK_UPCONVERT_FINISHING) { + /* + * We've upconverted. If the lock now has a level we can + * work with, we take it. If, however, the lock is not at the + * required level, we go thru the full cycle. One way this could + * happen is if a process requesting an upconvert to PR is + * closely followed by another requesting upconvert to an EX. + * If the process requesting EX lands here, we want it to + * continue attempting to upconvert and let the process + * requesting PR take the lock. + * If multiple processes request upconvert to PR, the first one + * here will take the lock. The others will have to go thru the + * OCFS2_LOCK_BLOCKED check to ensure that there is no pending + * downconvert request. + */ + if (level <= lockres->l_level) + goto update_holders; + } + if (lockres->l_flags & OCFS2_LOCK_BLOCKED && !ocfs2_may_continue_on_blocked_lock(lockres, level)) { /* is the lock is currently blocked on behalf of @@ -1416,11 +1445,14 @@ again: goto again; } +update_holders: /* Ok, if we get here then we're good to go. */ ocfs2_inc_holders(lockres, level); ret = 0; unlock: + lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); + spin_unlock_irqrestore(&lockres->l_lock, flags); out: /* @@ -3155,7 +3187,7 @@ out: /* Mark the lockres as being dropped. It will no longer be * queued if blocking, but we still may have to wait on it * being dequeued from the downconvert thread before we can consider - * it safe to drop. + * it safe to drop. * * You can *not* attempt to call cluster_lock on this lockres anymore. */ void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres) @@ -3352,6 +3384,7 @@ static int ocfs2_unblock_lock(struct ocfs2_super *osb, unsigned long flags; int blocking; int new_level; + int level; int ret = 0; int set_lvb = 0; unsigned int gen; @@ -3360,9 +3393,17 @@ static int ocfs2_unblock_lock(struct ocfs2_super *osb, spin_lock_irqsave(&lockres->l_lock, flags); - BUG_ON(!(lockres->l_flags & OCFS2_LOCK_BLOCKED)); - recheck: + /* + * Is it still blocking? If not, we have no more work to do. + */ + if (!(lockres->l_flags & OCFS2_LOCK_BLOCKED)) { + BUG_ON(lockres->l_blocking != DLM_LOCK_NL); + spin_unlock_irqrestore(&lockres->l_lock, flags); + ret = 0; + goto leave; + } + if (lockres->l_flags & OCFS2_LOCK_BUSY) { /* XXX * This is a *big* race. The OCFS2_LOCK_PENDING flag @@ -3401,6 +3442,31 @@ recheck: goto leave; } + /* + * This prevents livelocks. OCFS2_LOCK_UPCONVERT_FINISHING flag is + * set when the ast is received for an upconvert just before the + * OCFS2_LOCK_BUSY flag is cleared. Now if the fs received a bast + * on the heels of the ast, we want to delay the downconvert just + * enough to allow the up requestor to do its task. Because this + * lock is in the blocked queue, the lock will be downconverted + * as soon as the requestor is done with the lock. + */ + if (lockres->l_flags & OCFS2_LOCK_UPCONVERT_FINISHING) + goto leave_requeue; + + /* + * How can we block and yet be at NL? We were trying to upconvert + * from NL and got canceled. The code comes back here, and now + * we notice and clear BLOCKING. + */ + if (lockres->l_level == DLM_LOCK_NL) { + BUG_ON(lockres->l_ex_holders || lockres->l_ro_holders); + lockres->l_blocking = DLM_LOCK_NL; + lockres_clear_flags(lockres, OCFS2_LOCK_BLOCKED); + spin_unlock_irqrestore(&lockres->l_lock, flags); + goto leave; + } + /* if we're blocking an exclusive and we have *any* holders, * then requeue. */ if ((lockres->l_blocking == DLM_LOCK_EX) @@ -3438,6 +3504,7 @@ recheck: * may sleep, so we save off a copy of what we're blocking as * it may change while we're not holding the spin lock. */ blocking = lockres->l_blocking; + level = lockres->l_level; spin_unlock_irqrestore(&lockres->l_lock, flags); ctl->unblock_action = lockres->l_ops->downconvert_worker(lockres, blocking); @@ -3446,7 +3513,7 @@ recheck: goto leave; spin_lock_irqsave(&lockres->l_lock, flags); - if (blocking != lockres->l_blocking) { + if ((blocking != lockres->l_blocking) || (level != lockres->l_level)) { /* If this changed underneath us, then we can't drop * it just yet. */ goto recheck; diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 15713cbb865..19ad145d2af 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -239,7 +239,7 @@ static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len, mlog(0, "Encoding parent: blkno: %llu, generation: %u\n", (unsigned long long)blkno, generation); } - + *max_len = len; bail: diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index d35a27f4523..5328529e7fd 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -192,7 +192,7 @@ static int ocfs2_try_to_merge_extent_map(struct ocfs2_extent_map_item *emi, emi->ei_clusters += ins->ei_clusters; return 1; } else if ((ins->ei_phys + ins->ei_clusters) == emi->ei_phys && - (ins->ei_cpos + ins->ei_clusters) == emi->ei_phys && + (ins->ei_cpos + ins->ei_clusters) == emi->ei_cpos && ins->ei_flags == emi->ei_flags) { emi->ei_phys = ins->ei_phys; emi->ei_cpos = ins->ei_cpos; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 06ccf6a86d3..558ce031242 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -749,7 +749,7 @@ static int ocfs2_write_zero_page(struct inode *inode, int ret; offset = (size & (PAGE_CACHE_SIZE-1)); /* Within page */ - /* ugh. in prepare/commit_write, if from==to==start of block, we + /* ugh. in prepare/commit_write, if from==to==start of block, we ** skip the prepare. make sure we never send an offset for the start ** of a block */ @@ -1779,7 +1779,7 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry, struct inode *inode = dentry->d_inode; loff_t saved_pos, end; - /* + /* * We start with a read level meta lock and only jump to an ex * if we need to make modifications here. */ @@ -2013,8 +2013,8 @@ out_dio: /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT)); - if ((file->f_flags & O_DSYNC && !direct_io) || IS_SYNC(inode) || - (file->f_flags & O_DIRECT && has_refcount)) { + if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || + ((file->f_flags & O_DIRECT) && has_refcount)) { ret = filemap_fdatawrite_range(file->f_mapping, pos, pos + count - 1); if (ret < 0) @@ -2033,7 +2033,7 @@ out_dio: pos + count - 1); } - /* + /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that * it can unlock our rw lock. (it's the clustered equivalent of @@ -2198,7 +2198,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, goto bail; } - /* + /* * buffered reads protect themselves in ->readpage(). O_DIRECT reads * need locks to protect pending reads from racing with truncate. */ @@ -2220,10 +2220,10 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, * We're fine letting folks race truncates and extending * writes with read across the cluster, just like they can * locally. Hence no rw_lock during read. - * + * * Take and drop the meta data lock to update inode fields * like i_size. This allows the checks down below - * generic_file_aio_read() a chance of actually working. + * generic_file_aio_read() a chance of actually working. */ ret = ocfs2_inode_lock_atime(inode, filp->f_vfsmnt, &lock_level); if (ret < 0) { @@ -2248,7 +2248,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, bail: if (have_alloc_sem) up_read(&inode->i_alloc_sem); - if (rw_level != -1) + if (rw_level != -1) ocfs2_rw_unlock(inode, rw_level); mlog_exit(ret); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 0297fb8982b..88459bdd1ff 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -475,7 +475,7 @@ static int ocfs2_read_locked_inode(struct inode *inode, if (args->fi_flags & OCFS2_FI_FLAG_ORPHAN_RECOVERY) { status = ocfs2_try_open_lock(inode, 0); if (status) { - make_bad_inode(inode); + make_bad_inode(inode); return status; } } @@ -684,7 +684,7 @@ bail: return status; } -/* +/* * Serialize with orphan dir recovery. If the process doing * recovery on this orphan dir does an iget() with the dir * i_mutex held, we'll deadlock here. Instead we detect this diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 31fbb061951..7d9d9c132ce 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/mount.h> +#include <linux/compat.h> #define MLOG_MASK_PREFIX ML_INODE #include <cluster/masklog.h> @@ -181,6 +182,10 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) #ifdef CONFIG_COMPAT long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg) { + bool preserve; + struct reflink_arguments args; + struct inode *inode = file->f_path.dentry->d_inode; + switch (cmd) { case OCFS2_IOC32_GETFLAGS: cmd = OCFS2_IOC_GETFLAGS; @@ -195,8 +200,15 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg) case OCFS2_IOC_GROUP_EXTEND: case OCFS2_IOC_GROUP_ADD: case OCFS2_IOC_GROUP_ADD64: - case OCFS2_IOC_REFLINK: break; + case OCFS2_IOC_REFLINK: + if (copy_from_user(&args, (struct reflink_arguments *)arg, + sizeof(args))) + return -EFAULT; + preserve = (args.preserve != 0); + + return ocfs2_reflink_ioctl(inode, compat_ptr(args.old_path), + compat_ptr(args.new_path), preserve); default: return -ENOIOCTLCMD; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index bf34c491ae9..9336c60e3a3 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -2034,7 +2034,7 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb, status = -ENOENT; mlog_errno(status); return status; - } + } mutex_lock(&orphan_dir_inode->i_mutex); status = ocfs2_inode_lock(orphan_dir_inode, NULL, 0); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 9362eea7424..740f448041e 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -136,6 +136,10 @@ enum ocfs2_unlock_action { #define OCFS2_LOCK_PENDING (0x00000400) /* This lockres is pending a call to dlm_lock. Only exists with BUSY set. */ +#define OCFS2_LOCK_UPCONVERT_FINISHING (0x00000800) /* blocks the dc thread + * from downconverting + * before the upconvert + * has completed */ struct ocfs2_lock_res_ops; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 1a1a679e51b..7638a38c32b 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -1417,9 +1417,16 @@ static inline int ocfs2_fast_symlink_chars(int blocksize) return blocksize - offsetof(struct ocfs2_dinode, id2.i_symlink); } -static inline int ocfs2_max_inline_data(int blocksize) +static inline int ocfs2_max_inline_data_with_xattr(int blocksize, + struct ocfs2_dinode *di) { - return blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data); + if (di && (di->i_dyn_features & OCFS2_INLINE_XATTR_FL)) + return blocksize - + offsetof(struct ocfs2_dinode, id2.i_data.id_data) - + di->i_xattr_inline_size; + else + return blocksize - + offsetof(struct ocfs2_dinode, id2.i_data.id_data); } static inline int ocfs2_extent_recs_per_inode(int blocksize) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 74db2be75dd..8ae65c9c020 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2945,7 +2945,7 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle, while (offset < end) { page_index = offset >> PAGE_CACHE_SHIFT; - map_end = (page_index + 1) << PAGE_CACHE_SHIFT; + map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT; if (map_end > end) map_end = end; @@ -2957,8 +2957,12 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle, page = grab_cache_page(mapping, page_index); - /* This page can't be dirtied before we CoW it out. */ - BUG_ON(PageDirty(page)); + /* + * In case PAGE_CACHE_SIZE <= CLUSTER_SIZE, This page + * can't be dirtied before we CoW it out. + */ + if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize) + BUG_ON(PageDirty(page)); if (!PageUptodate(page)) { ret = block_read_full_page(page, ocfs2_get_block); @@ -3170,7 +3174,7 @@ static int ocfs2_cow_sync_writeback(struct super_block *sb, while (offset < end) { page_index = offset >> PAGE_CACHE_SHIFT; - map_end = (page_index + 1) << PAGE_CACHE_SHIFT; + map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT; if (map_end > end) map_end = end; diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index e49c4105026..3038c92af49 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -277,7 +277,7 @@ static int o2cb_cluster_connect(struct ocfs2_cluster_connection *conn) u32 dlm_key; struct dlm_ctxt *dlm; struct o2dlm_private *priv; - struct dlm_protocol_version dlm_version; + struct dlm_protocol_version fs_version; BUG_ON(conn == NULL); BUG_ON(o2cb_stack.sp_proto == NULL); @@ -304,18 +304,18 @@ static int o2cb_cluster_connect(struct ocfs2_cluster_connection *conn) /* used by the dlm code to make message headers unique, each * node in this domain must agree on this. */ dlm_key = crc32_le(0, conn->cc_name, conn->cc_namelen); - dlm_version.pv_major = conn->cc_version.pv_major; - dlm_version.pv_minor = conn->cc_version.pv_minor; + fs_version.pv_major = conn->cc_version.pv_major; + fs_version.pv_minor = conn->cc_version.pv_minor; - dlm = dlm_register_domain(conn->cc_name, dlm_key, &dlm_version); + dlm = dlm_register_domain(conn->cc_name, dlm_key, &fs_version); if (IS_ERR(dlm)) { rc = PTR_ERR(dlm); mlog_errno(rc); goto out_free; } - conn->cc_version.pv_major = dlm_version.pv_major; - conn->cc_version.pv_minor = dlm_version.pv_minor; + conn->cc_version.pv_major = fs_version.pv_major; + conn->cc_version.pv_minor = fs_version.pv_minor; conn->cc_lockspace = dlm; dlm_register_eviction_cb(dlm, &priv->op_eviction_cb); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 26069917a9f..755cd49a5ef 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1062,7 +1062,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) "file system, but write access is " "unavailable.\n"); else - mlog_errno(status); + mlog_errno(status); goto read_super_error; } diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index 49b133ccbf1..32499d213fc 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -137,20 +137,20 @@ static void *ocfs2_fast_follow_link(struct dentry *dentry, } memcpy(link, target, len); - nd_set_link(nd, link); bail: + nd_set_link(nd, status ? ERR_PTR(status) : link); brelse(bh); mlog_exit(status); - return status ? ERR_PTR(status) : link; + return NULL; } static void ocfs2_fast_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) { - char *link = cookie; - - kfree(link); + char *link = nd_get_link(nd); + if (!IS_ERR(link)) + kfree(link); } const struct inode_operations ocfs2_symlink_inode_operations = { diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index c61369342a2..a0a120e82b9 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -267,8 +267,8 @@ static int ocfs2_buffer_cached(struct ocfs2_caching_info *ci, } /* Warning: even if it returns true, this does *not* guarantee that - * the block is stored in our inode metadata cache. - * + * the block is stored in our inode metadata cache. + * * This can be called under lock_buffer() */ int ocfs2_buffer_uptodate(struct ocfs2_caching_info *ci, diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index ba1ba0c5efd..63d449807d9 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -11,6 +11,8 @@ struct nf_conntrack_ecache; struct netns_ct { atomic_t count; unsigned int expect_count; + unsigned int htable_size; + struct kmem_cache *nf_conntrack_cachep; struct hlist_nulls_head *hash; struct hlist_head *expect_hash; struct hlist_nulls_head unconfirmed; @@ -28,5 +30,6 @@ struct netns_ct { #endif int hash_vmalloc; int expect_vmalloc; + char *slabname; }; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2eb3814d625..9a4b8b71407 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -40,6 +40,7 @@ struct netns_ipv4 { struct xt_table *iptable_security; struct xt_table *nat_table; struct hlist_head *nat_bysource; + unsigned int nat_htable_size; int nat_vmalloced; #endif diff --git a/net/9p/client.c b/net/9p/client.c index 8af95b2dddd..09d4f1e2e4a 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -69,7 +69,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...); static int parse_opts(char *opts, struct p9_client *clnt) { - char *options; + char *options, *tmp_options; char *p; substring_t args[MAX_OPT_ARGS]; int option; @@ -81,12 +81,13 @@ static int parse_opts(char *opts, struct p9_client *clnt) if (!opts) return 0; - options = kstrdup(opts, GFP_KERNEL); - if (!options) { + tmp_options = kstrdup(opts, GFP_KERNEL); + if (!tmp_options) { P9_DPRINTK(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } + options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -108,6 +109,13 @@ static int parse_opts(char *opts, struct p9_client *clnt) break; case Opt_trans: clnt->trans_mod = v9fs_get_trans_by_name(&args[0]); + if(clnt->trans_mod == NULL) { + P9_DPRINTK(P9_DEBUG_ERROR, + "Could not find request transport: %s\n", + (char *) &args[0]); + ret = -EINVAL; + goto free_and_return; + } break; case Opt_legacy: clnt->dotu = 0; @@ -117,7 +125,8 @@ static int parse_opts(char *opts, struct p9_client *clnt) } } - kfree(options); +free_and_return: + kfree(tmp_options); return ret; } @@ -667,18 +676,12 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) clnt->trans = NULL; spin_lock_init(&clnt->lock); INIT_LIST_HEAD(&clnt->fidlist); - clnt->fidpool = p9_idpool_create(); - if (IS_ERR(clnt->fidpool)) { - err = PTR_ERR(clnt->fidpool); - clnt->fidpool = NULL; - goto error; - } p9_tag_init(clnt); err = parse_opts(options, clnt); if (err < 0) - goto error; + goto free_client; if (!clnt->trans_mod) clnt->trans_mod = v9fs_get_default_trans(); @@ -687,7 +690,14 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) err = -EPROTONOSUPPORT; P9_DPRINTK(P9_DEBUG_ERROR, "No transport defined or default transport\n"); - goto error; + goto free_client; + } + + clnt->fidpool = p9_idpool_create(); + if (IS_ERR(clnt->fidpool)) { + err = PTR_ERR(clnt->fidpool); + clnt->fidpool = NULL; + goto put_trans; } P9_DPRINTK(P9_DEBUG_MUX, "clnt %p trans %p msize %d dotu %d\n", @@ -695,19 +705,25 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) err = clnt->trans_mod->create(clnt, dev_name, options); if (err) - goto error; + goto destroy_fidpool; if ((clnt->msize+P9_IOHDRSZ) > clnt->trans_mod->maxsize) clnt->msize = clnt->trans_mod->maxsize-P9_IOHDRSZ; err = p9_client_version(clnt); if (err) - goto error; + goto close_trans; return clnt; -error: - p9_client_destroy(clnt); +close_trans: + clnt->trans_mod->close(clnt); +destroy_fidpool: + p9_idpool_destroy(clnt->fidpool); +put_trans: + v9fs_put_trans(clnt->trans_mod); +free_client: + kfree(clnt); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_create); @@ -1214,10 +1230,11 @@ static int p9_client_statsize(struct p9_wstat *wst, int optional) { int ret; + /* NOTE: size shouldn't include its own length */ /* size[2] type[2] dev[4] qid[13] */ /* mode[4] atime[4] mtime[4] length[8]*/ /* name[s] uid[s] gid[s] muid[s] */ - ret = 2+2+4+13+4+4+4+8+2+2+2+2; + ret = 2+4+13+4+4+4+8+2+2+2+2; if (wst->name) ret += strlen(wst->name); @@ -1258,7 +1275,7 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) wst->name, wst->uid, wst->gid, wst->muid, wst->extension, wst->n_uid, wst->n_gid, wst->n_muid); - req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size, wst); + req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size+2, wst); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index be1cb909d8c..31d0b05582a 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -714,7 +714,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) char *p; substring_t args[MAX_OPT_ARGS]; int option; - char *options; + char *options, *tmp_options; int ret; opts->port = P9_PORT; @@ -724,12 +724,13 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) if (!params) return 0; - options = kstrdup(params, GFP_KERNEL); - if (!options) { + tmp_options = kstrdup(params, GFP_KERNEL); + if (!tmp_options) { P9_DPRINTK(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } + options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -760,7 +761,8 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) continue; } } - kfree(options); + + kfree(tmp_options); return 0; } diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 65cb29db03f..2c95a89c0f4 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -166,7 +166,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) char *p; substring_t args[MAX_OPT_ARGS]; int option; - char *options; + char *options, *tmp_options; int ret; opts->port = P9_PORT; @@ -177,12 +177,13 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) if (!params) return 0; - options = kstrdup(params, GFP_KERNEL); - if (!options) { + tmp_options = kstrdup(params, GFP_KERNEL); + if (!tmp_options) { P9_DPRINTK(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } + options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -216,7 +217,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) } /* RQ must be at least as large as the SQ */ opts->rq_depth = max(opts->rq_depth, opts->sq_depth); - kfree(options); + kfree(tmp_options); return 0; } diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index ea1e3daabef..cb50f4ae5ee 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -102,7 +102,8 @@ static void p9_virtio_close(struct p9_client *client) struct virtio_chan *chan = client->trans; mutex_lock(&virtio_9p_lock); - chan->inuse = false; + if (chan) + chan->inuse = false; mutex_unlock(&virtio_9p_lock); } @@ -311,6 +312,7 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) } client->trans = (void *)chan; + client->status = Connected; chan->client = client; return 0; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b7c4224f4e7..b10e3cdb08f 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -377,6 +377,9 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 if (acl->state == BT_CONNECTED && (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { + acl->power_save = 1; + hci_conn_enter_active_mode(acl); + if (lmp_esco_capable(hdev)) hci_setup_sync(sco, acl->handle); else diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 28517bad796..592da5c909c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1699,6 +1699,7 @@ static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_bu break; case 0x1c: /* SCO interval rejected */ + case 0x1a: /* Unsupported Remote Feature */ case 0x1f: /* Unspecified error */ if (conn->out && conn->attempt < 2) { conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 6cf526d06e2..fc6ec1e7265 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -703,29 +703,9 @@ static void hidp_close(struct hid_device *hid) static int hidp_parse(struct hid_device *hid) { struct hidp_session *session = hid->driver_data; - struct hidp_connadd_req *req = session->req; - unsigned char *buf; - int ret; - - buf = kmalloc(req->rd_size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (copy_from_user(buf, req->rd_data, req->rd_size)) { - kfree(buf); - return -EFAULT; - } - - ret = hid_parse_report(session->hid, buf, req->rd_size); - - kfree(buf); - - if (ret) - return ret; - - session->req = NULL; - return 0; + return hid_parse_report(session->hid, session->rd_data, + session->rd_size); } static int hidp_start(struct hid_device *hid) @@ -770,12 +750,24 @@ static int hidp_setup_hid(struct hidp_session *session, bdaddr_t src, dst; int err; + session->rd_data = kzalloc(req->rd_size, GFP_KERNEL); + if (!session->rd_data) + return -ENOMEM; + + if (copy_from_user(session->rd_data, req->rd_data, req->rd_size)) { + err = -EFAULT; + goto fault; + } + session->rd_size = req->rd_size; + hid = hid_allocate_device(); - if (IS_ERR(hid)) - return PTR_ERR(hid); + if (IS_ERR(hid)) { + err = PTR_ERR(hid); + goto fault; + } session->hid = hid; - session->req = req; + hid->driver_data = session; baswap(&src, &bt_sk(session->ctrl_sock->sk)->src); @@ -806,6 +798,10 @@ failed: hid_destroy_device(hid); session->hid = NULL; +fault: + kfree(session->rd_data); + session->rd_data = NULL; + return err; } @@ -900,6 +896,9 @@ unlink: session->hid = NULL; } + kfree(session->rd_data); + session->rd_data = NULL; + purge: skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index faf3d74c358..a4e215d50c1 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -154,7 +154,9 @@ struct hidp_session { struct sk_buff_head ctrl_transmit; struct sk_buff_head intr_transmit; - struct hidp_connadd_req *req; + /* Report descriptor */ + __u8 *rd_data; + uint rd_size; }; static inline void hidp_schedule(struct hidp_session *session) diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index fc5ee3296e2..89f4a59eb82 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -252,7 +252,6 @@ static void rfcomm_session_timeout(unsigned long arg) BT_DBG("session %p state %ld", s, s->state); set_bit(RFCOMM_TIMED_OUT, &s->flags); - rfcomm_session_put(s); rfcomm_schedule(RFCOMM_SCHED_TIMEO); } @@ -1151,7 +1150,11 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) break; case BT_DISCONN: - rfcomm_session_put(s); + /* When socket is closed and we are not RFCOMM + * initiator rfcomm_process_rx already calls + * rfcomm_session_put() */ + if (s->sock->sk->sk_state != BT_CLOSED) + rfcomm_session_put(s); break; } } @@ -1920,6 +1923,7 @@ static inline void rfcomm_process_sessions(void) if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); + rfcomm_session_put(s); continue; } diff --git a/net/core/dst.c b/net/core/dst.c index 57bc4d5b8d0..cb1b3488b73 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -17,6 +17,7 @@ #include <linux/string.h> #include <linux/types.h> #include <net/net_namespace.h> +#include <linux/sched.h> #include <net/dst.h> @@ -79,6 +80,7 @@ loop: while ((dst = next) != NULL) { next = dst->next; prefetch(&next->next); + cond_resched(); if (likely(atomic_read(&dst->__refcnt))) { last->next = dst; last = dst; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index de0c2c72642..2e692afdc55 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3524,6 +3524,7 @@ static int pktgen_thread_worker(void *arg) wait_event_interruptible_timeout(t->queue, t->control != 0, HZ/10); + try_to_freeze(); continue; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 57dfb9c8c4f..ff16e9df196 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -83,7 +83,7 @@ static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_f va_list args; va_start(args, fmt); - vsnprintf(slab_name_fmt, sizeof(slab_name_fmt), fmt, args); + vsnprintf(slab_name_fmt, CCID_SLAB_NAME_LENGTH, fmt, args); va_end(args); slab = kmem_cache_create(slab_name_fmt, sizeof(struct ccid) + obj_size, 0, diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 269958bf7fe..6df6f8ac963 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -19,7 +19,9 @@ #include <linux/list.h> #include <linux/module.h> -#define CCID_MAX 255 +/* maximum value for a CCID (RFC 4340, 19.5) */ +#define CCID_MAX 255 +#define CCID_SLAB_NAME_LENGTH 32 struct tcp_info; @@ -49,8 +51,8 @@ struct ccid_operations { const char *ccid_name; struct kmem_cache *ccid_hc_rx_slab, *ccid_hc_tx_slab; - char ccid_hc_rx_slab_name[32]; - char ccid_hc_tx_slab_name[32]; + char ccid_hc_rx_slab_name[CCID_SLAB_NAME_LENGTH]; + char ccid_hc_tx_slab_name[CCID_SLAB_NAME_LENGTH]; __u32 ccid_hc_rx_obj_size, ccid_hc_tx_obj_size; /* Interface Routines */ diff --git a/net/dccp/probe.c b/net/dccp/probe.c index bace1d8cbcf..f5b3464f124 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -161,8 +161,8 @@ static __init int dccpprobe_init(void) if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops)) goto err0; - ret = try_then_request_module((register_jprobe(&dccp_send_probe) == 0), - "dccp"); + try_then_request_module((ret = register_jprobe(&dccp_send_probe)) == 0, + "dccp"); if (ret) goto err1; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 06632762ba5..90203e1b918 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -925,10 +925,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(NFPROTO_ARP); private = &tmp; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 572330a552e..3ce53cf13d5 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1132,10 +1132,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET); private = &tmp; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index d171b123a65..d1ea38a7c49 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -210,7 +210,7 @@ static ctl_table ip_ct_sysctl_table[] = { }, { .procname = "ip_conntrack_buckets", - .data = &nf_conntrack_htable_size, + .data = &init_net.ct.htable_size, .maxlen = sizeof(unsigned int), .mode = 0444, .proc_handler = proc_dointvec, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 8668a3defda..2fb7b76da94 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -32,7 +32,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < net->ct.htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); if (!is_a_nulls(n)) @@ -50,7 +50,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(head->next); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= net->ct.htable_size) return NULL; } head = rcu_dereference(net->ct.hash[st->bucket].first); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index fe1a64479dd..26066a2327a 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -35,9 +35,6 @@ static DEFINE_SPINLOCK(nf_nat_lock); static struct nf_conntrack_l3proto *l3proto __read_mostly; -/* Calculated at init based on memory size */ -static unsigned int nf_nat_htable_size __read_mostly; - #define MAX_IP_NAT_PROTO 256 static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO] __read_mostly; @@ -72,7 +69,7 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put); /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int -hash_by_src(const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple) { unsigned int hash; @@ -80,7 +77,7 @@ hash_by_src(const struct nf_conntrack_tuple *tuple) hash = jhash_3words((__force u32)tuple->src.u3.ip, (__force u32)tuple->src.u.all, tuple->dst.protonum, 0); - return ((u64)hash * nf_nat_htable_size) >> 32; + return ((u64)hash * net->ipv4.nat_htable_size) >> 32; } /* Is this tuple already taken? (not by us) */ @@ -147,7 +144,7 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(tuple); + unsigned int h = hash_by_src(net, tuple); const struct nf_conn_nat *nat; const struct nf_conn *ct; const struct hlist_node *n; @@ -330,7 +327,7 @@ nf_nat_setup_info(struct nf_conn *ct, if (have_to_hash) { unsigned int srchash; - srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_lock); /* nf_conntrack_alter_reply might re-allocate exntension aera */ nat = nfct_nat(ct); @@ -679,8 +676,10 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, static int __net_init nf_nat_net_init(struct net *net) { - net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, - &net->ipv4.nat_vmalloced, 0); + /* Leave them the same for the moment. */ + net->ipv4.nat_htable_size = net->ct.htable_size; + net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, + &net->ipv4.nat_vmalloced, 0); if (!net->ipv4.nat_bysource) return -ENOMEM; return 0; @@ -703,7 +702,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) nf_ct_iterate_cleanup(net, &clean_nat, NULL); synchronize_rcu(); nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced, - nf_nat_htable_size); + net->ipv4.nat_htable_size); } static struct pernet_operations nf_nat_net_ops = { @@ -724,9 +723,6 @@ static int __init nf_nat_init(void) return ret; } - /* Leave them the same for the moment. */ - nf_nat_htable_size = nf_conntrack_htable_size; - ret = register_pernet_subsys(&nf_nat_net_ops); if (ret < 0) goto cleanup_extend; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 480d7f8c980..8a7e0f52e17 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1164,10 +1164,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 156020d138b..6b3602de359 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -698,15 +698,18 @@ dev_irnet_ioctl( /* Query PPP channel and unit number */ case PPPIOCGCHAN: + lock_kernel(); if(ap->ppp_open && !put_user(ppp_channel_index(&ap->chan), (int __user *)argp)) err = 0; + unlock_kernel(); break; case PPPIOCGUNIT: lock_kernel(); if(ap->ppp_open && !put_user(ppp_unit_number(&ap->chan), (int __user *)argp)) - err = 0; + err = 0; + unlock_kernel(); break; /* All these ioctls can be passed both directly and from ppp_generic, diff --git a/net/key/af_key.c b/net/key/af_key.c index 76fa6fef647..539f43bc97d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3794,9 +3794,9 @@ static struct pernet_operations pfkey_net_ops = { static void __exit ipsec_pfkey_exit(void) { - unregister_pernet_subsys(&pfkey_net_ops); xfrm_unregister_km(&pfkeyv2_mgr); sock_unregister(PF_KEY); + unregister_pernet_subsys(&pfkey_net_ops); proto_unregister(&key_proto); } @@ -3807,21 +3807,22 @@ static int __init ipsec_pfkey_init(void) if (err != 0) goto out; - err = sock_register(&pfkey_family_ops); + err = register_pernet_subsys(&pfkey_net_ops); if (err != 0) goto out_unregister_key_proto; + err = sock_register(&pfkey_family_ops); + if (err != 0) + goto out_unregister_pernet; err = xfrm_register_km(&pfkeyv2_mgr); if (err != 0) goto out_sock_unregister; - err = register_pernet_subsys(&pfkey_net_ops); - if (err != 0) - goto out_xfrm_unregister_km; out: return err; -out_xfrm_unregister_km: - xfrm_unregister_km(&pfkeyv2_mgr); + out_sock_unregister: sock_unregister(PF_KEY); +out_unregister_pernet: + unregister_pernet_subsys(&pfkey_net_ops); out_unregister_key_proto: proto_unregister(&key_proto); goto out; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0e98c3282d4..4d79e3c1616 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -30,6 +30,7 @@ #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/mm.h> +#include <linux/nsproxy.h> #include <linux/rculist_nulls.h> #include <net/netfilter/nf_conntrack.h> @@ -63,8 +64,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_max); struct nf_conn nf_conntrack_untracked __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_untracked); -static struct kmem_cache *nf_conntrack_cachep __read_mostly; - static int nf_conntrack_hash_rnd_initted; static unsigned int nf_conntrack_hash_rnd; @@ -86,9 +85,10 @@ static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, return ((u64)h * size) >> 32; } -static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple) +static inline u_int32_t hash_conntrack(const struct net *net, + const struct nf_conntrack_tuple *tuple) { - return __hash_conntrack(tuple, nf_conntrack_htable_size, + return __hash_conntrack(tuple, net->ct.htable_size, nf_conntrack_hash_rnd); } @@ -296,7 +296,7 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(tuple); + unsigned int hash = hash_conntrack(net, tuple); /* Disable BHs the entire time since we normally need to disable them * at least once for the stats anyway. @@ -366,10 +366,11 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, void nf_conntrack_hash_insert(struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; - hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); __nf_conntrack_hash_insert(ct, hash, repl_hash); } @@ -397,8 +398,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) return NF_ACCEPT; - hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); /* We're not in hash table, and we refuse to set up related connections for unconfirmed conns. But packet copies and @@ -468,7 +469,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, struct net *net = nf_ct_net(ignored_conntrack); struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(tuple); + unsigned int hash = hash_conntrack(net, tuple); /* Disable BHs the entire time since we need to disable them at * least once for the stats anyway. @@ -503,7 +504,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) int dropped = 0; rcu_read_lock(); - for (i = 0; i < nf_conntrack_htable_size; i++) { + for (i = 0; i < net->ct.htable_size; i++) { hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); @@ -523,7 +524,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) if (cnt >= NF_CT_EVICTION_RANGE) break; - hash = (hash + 1) % nf_conntrack_htable_size; + hash = (hash + 1) % net->ct.htable_size; } rcu_read_unlock(); @@ -557,7 +558,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { - unsigned int hash = hash_conntrack(orig); + unsigned int hash = hash_conntrack(net, orig); if (!early_drop(net, hash)) { atomic_dec(&net->ct.count); if (net_ratelimit()) @@ -572,7 +573,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, * Do not use kmem_cache_zalloc(), as this cache uses * SLAB_DESTROY_BY_RCU. */ - ct = kmem_cache_alloc(nf_conntrack_cachep, gfp); + ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp); if (ct == NULL) { pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n"); atomic_dec(&net->ct.count); @@ -611,7 +612,7 @@ void nf_conntrack_free(struct nf_conn *ct) nf_ct_ext_destroy(ct); atomic_dec(&net->ct.count); nf_ct_ext_free(ct); - kmem_cache_free(nf_conntrack_cachep, ct); + kmem_cache_free(net->ct.nf_conntrack_cachep, ct); } EXPORT_SYMBOL_GPL(nf_conntrack_free); @@ -1014,7 +1015,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), struct hlist_nulls_node *n; spin_lock_bh(&nf_conntrack_lock); - for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { + for (; *bucket < net->ct.htable_size; (*bucket)++) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) @@ -1113,9 +1114,12 @@ static void nf_ct_release_dying_list(struct net *net) static void nf_conntrack_cleanup_init_net(void) { + /* wait until all references to nf_conntrack_untracked are dropped */ + while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1) + schedule(); + nf_conntrack_helper_fini(); nf_conntrack_proto_fini(); - kmem_cache_destroy(nf_conntrack_cachep); } static void nf_conntrack_cleanup_net(struct net *net) @@ -1127,15 +1131,14 @@ static void nf_conntrack_cleanup_net(struct net *net) schedule(); goto i_see_dead_people; } - /* wait until all references to nf_conntrack_untracked are dropped */ - while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1) - schedule(); nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - nf_conntrack_htable_size); + net->ct.htable_size); nf_conntrack_ecache_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); + kmem_cache_destroy(net->ct.nf_conntrack_cachep); + kfree(net->ct.slabname); free_percpu(net->ct.stat); } @@ -1190,10 +1193,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) { int i, bucket, vmalloced, old_vmalloced; unsigned int hashsize, old_size; - int rnd; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; + if (current->nsproxy->net_ns != &init_net) + return -EOPNOTSUPP; + /* On boot, we can set this without any fancy locking. */ if (!nf_conntrack_htable_size) return param_set_uint(val, kp); @@ -1206,33 +1211,29 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hash) return -ENOMEM; - /* We have to rehahs for the new table anyway, so we also can - * use a newrandom seed */ - get_random_bytes(&rnd, sizeof(rnd)); - /* Lookups in the old hash might happen in parallel, which means we * might get false negatives during connection lookup. New connections * created because of a false negative won't make it into the hash * though since that required taking the lock. */ spin_lock_bh(&nf_conntrack_lock); - for (i = 0; i < nf_conntrack_htable_size; i++) { + for (i = 0; i < init_net.ct.htable_size; i++) { while (!hlist_nulls_empty(&init_net.ct.hash[i])) { h = hlist_nulls_entry(init_net.ct.hash[i].first, struct nf_conntrack_tuple_hash, hnnode); hlist_nulls_del_rcu(&h->hnnode); - bucket = __hash_conntrack(&h->tuple, hashsize, rnd); + bucket = __hash_conntrack(&h->tuple, hashsize, + nf_conntrack_hash_rnd); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } - old_size = nf_conntrack_htable_size; + old_size = init_net.ct.htable_size; old_vmalloced = init_net.ct.hash_vmalloc; old_hash = init_net.ct.hash; - nf_conntrack_htable_size = hashsize; + init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; init_net.ct.hash_vmalloc = vmalloced; init_net.ct.hash = hash; - nf_conntrack_hash_rnd = rnd; spin_unlock_bh(&nf_conntrack_lock); nf_ct_free_hashtable(old_hash, old_vmalloced, old_size); @@ -1271,15 +1272,6 @@ static int nf_conntrack_init_init_net(void) NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); - nf_conntrack_cachep = kmem_cache_create("nf_conntrack", - sizeof(struct nf_conn), - 0, SLAB_DESTROY_BY_RCU, NULL); - if (!nf_conntrack_cachep) { - printk(KERN_ERR "Unable to create nf_conn slab cache\n"); - ret = -ENOMEM; - goto err_cache; - } - ret = nf_conntrack_proto_init(); if (ret < 0) goto err_proto; @@ -1288,13 +1280,19 @@ static int nf_conntrack_init_init_net(void) if (ret < 0) goto err_helper; + /* Set up fake conntrack: to never be deleted, not in any hashes */ +#ifdef CONFIG_NET_NS + nf_conntrack_untracked.ct_net = &init_net; +#endif + atomic_set(&nf_conntrack_untracked.ct_general.use, 1); + /* - and look it like as a confirmed connection */ + set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status); + return 0; err_helper: nf_conntrack_proto_fini(); err_proto: - kmem_cache_destroy(nf_conntrack_cachep); -err_cache: return ret; } @@ -1316,7 +1314,24 @@ static int nf_conntrack_init_net(struct net *net) ret = -ENOMEM; goto err_stat; } - net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, + + net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); + if (!net->ct.slabname) { + ret = -ENOMEM; + goto err_slabname; + } + + net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname, + sizeof(struct nf_conn), 0, + SLAB_DESTROY_BY_RCU, NULL); + if (!net->ct.nf_conntrack_cachep) { + printk(KERN_ERR "Unable to create nf_conn slab cache\n"); + ret = -ENOMEM; + goto err_cache; + } + + net->ct.htable_size = nf_conntrack_htable_size; + net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, &net->ct.hash_vmalloc, 1); if (!net->ct.hash) { ret = -ENOMEM; @@ -1333,15 +1348,6 @@ static int nf_conntrack_init_net(struct net *net) if (ret < 0) goto err_ecache; - /* Set up fake conntrack: - - to never be deleted, not in any hashes */ -#ifdef CONFIG_NET_NS - nf_conntrack_untracked.ct_net = &init_net; -#endif - atomic_set(&nf_conntrack_untracked.ct_general.use, 1); - /* - and look it like as a confirmed connection */ - set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status); - return 0; err_ecache: @@ -1350,8 +1356,12 @@ err_acct: nf_conntrack_expect_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - nf_conntrack_htable_size); + net->ct.htable_size); err_hash: + kmem_cache_destroy(net->ct.nf_conntrack_cachep); +err_cache: + kfree(net->ct.slabname); +err_slabname: free_percpu(net->ct.stat); err_stat: return ret; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index fdf5d2a1d9b..2f25ff61098 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -569,7 +569,7 @@ static void exp_proc_remove(struct net *net) #endif /* CONFIG_PROC_FS */ } -module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0600); +module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); int nf_conntrack_expect_init(struct net *net) { @@ -577,7 +577,7 @@ int nf_conntrack_expect_init(struct net *net) if (net_eq(net, &init_net)) { if (!nf_ct_expect_hsize) { - nf_ct_expect_hsize = nf_conntrack_htable_size / 256; + nf_ct_expect_hsize = net->ct.htable_size / 256; if (!nf_ct_expect_hsize) nf_ct_expect_hsize = 1; } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 65c2a7bc3af..4b1a56bd074 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -192,7 +192,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, /* Get rid of expecteds, set helpers to NULL. */ hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) unhelp(h, me); - for (i = 0; i < nf_conntrack_htable_size; i++) { + for (i = 0; i < net->ct.htable_size; i++) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) unhelp(h, me); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 42f21c01a93..0ffe689dfe9 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -594,7 +594,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); last = (struct nf_conn *)cb->args[1]; - for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { + for (; cb->args[0] < init_net.ct.htable_size; cb->args[0]++) { restart: hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]], hnnode) { diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 028aba667ef..e310f1561bb 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -51,7 +51,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < net->ct.htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); if (!is_a_nulls(n)) @@ -69,7 +69,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(head->next); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= net->ct.htable_size) return NULL; } head = rcu_dereference(net->ct.hash[st->bucket].first); @@ -355,7 +355,7 @@ static ctl_table nf_ct_sysctl_table[] = { }, { .procname = "nf_conntrack_buckets", - .data = &nf_conntrack_htable_size, + .data = &init_net.ct.htable_size, .maxlen = sizeof(unsigned int), .mode = 0444, .proc_handler = proc_dointvec, @@ -421,6 +421,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) goto out_kmemdup; table[1].data = &net->ct.count; + table[2].data = &net->ct.htable_size; table[3].data = &net->ct.sysctl_checksum; table[4].data = &net->ct.sysctl_log_invalid; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a4957bf2ca6..4c5972ba8c7 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -455,9 +455,14 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; + else + err = -EPROTONOSUPPORT; cb_mutex = nl_table[protocol].cb_mutex; netlink_unlock_table(); + if (err < 0) + goto out; + err = __netlink_create(net, sock, cb_mutex, protocol); if (err < 0) goto out_module; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 929218a4762..21f9c7678aa 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -433,7 +433,7 @@ config NET_ACT_POLICE module. To compile this code as a module, choose M here: the - module will be called police. + module will be called act_police. config NET_ACT_GACT tristate "Generic actions" @@ -443,7 +443,7 @@ config NET_ACT_GACT accepting packets. To compile this code as a module, choose M here: the - module will be called gact. + module will be called act_gact. config GACT_PROB bool "Probability support" @@ -459,7 +459,7 @@ config NET_ACT_MIRRED other devices. To compile this code as a module, choose M here: the - module will be called mirred. + module will be called act_mirred. config NET_ACT_IPT tristate "IPtables targets" @@ -469,7 +469,7 @@ config NET_ACT_IPT classification. To compile this code as a module, choose M here: the - module will be called ipt. + module will be called act_ipt. config NET_ACT_NAT tristate "Stateless NAT" @@ -479,7 +479,7 @@ config NET_ACT_NAT netfilter for NAT unless you know what you are doing. To compile this code as a module, choose M here: the - module will be called nat. + module will be called act_nat. config NET_ACT_PEDIT tristate "Packet Editing" @@ -488,7 +488,7 @@ config NET_ACT_PEDIT Say Y here if you want to mangle the content of packets. To compile this code as a module, choose M here: the - module will be called pedit. + module will be called act_pedit. config NET_ACT_SIMP tristate "Simple Example (Debug)" @@ -502,7 +502,7 @@ config NET_ACT_SIMP If unsure, say N. To compile this code as a module, choose M here: the - module will be called simple. + module will be called act_simple. config NET_ACT_SKBEDIT tristate "SKB Editing" @@ -513,7 +513,7 @@ config NET_ACT_SKBEDIT If unsure, say N. To compile this code as a module, choose M here: the - module will be called skbedit. + module will be called act_skbedit. config NET_CLS_IND bool "Incoming device classification" |