diff --git a/Makefile b/Makefile index 560a7e2b5efc2..82fc1c7475926 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 277 +SUBLEVEL = 278 EXTRAVERSION = NAME = Roaring Lionus diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 00d7d28e86f0b..4633b79bf5ea6 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -154,16 +154,15 @@ #size-cells = <1>; ranges; - vic: intc@10140000 { + vic: interrupt-controller@10140000 { compatible = "arm,versatile-vic"; interrupt-controller; #interrupt-cells = <1>; reg = <0x10140000 0x1000>; - clear-mask = <0xffffffff>; valid-mask = <0xffffffff>; }; - sic: intc@10003000 { + sic: interrupt-controller@10003000 { compatible = "arm,versatile-sic"; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index 33a8eb28374ea..3a23164c2c2d4 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -6,7 +6,7 @@ amba { /* The Versatile PB is using more SIC IRQ lines than the AB */ - sic: intc@10003000 { + sic: interrupt-controller@10003000 { clear-mask = <0xffffffff>; /* * Valid interrupt lines mask according to diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 0a066f03b5ec9..180c1782ad63d 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -625,18 +625,20 @@ struct page *get_signal_page(void) addr = page_address(page); + /* Poison the entire page */ + memset32(addr, __opcode_to_mem_arm(0xe7fddef1), + PAGE_SIZE / sizeof(u32)); + /* Give the signal return code some randomness */ offset = 0x200 + (get_random_int() & 0x7fc); signal_return_offset = offset; - /* - * Copy signal return handlers into the vector page, and - * set sigreturn to be a pointer to these. - */ + /* Copy signal return handlers into the page */ memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes)); - ptr = (unsigned long)addr + offset; - flush_icache_range(ptr, ptr + sizeof(sigreturn_codes)); + /* Flush out all instructions in this page */ + ptr = (unsigned long)addr; + flush_icache_range(ptr, ptr + PAGE_SIZE); return page; } diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 9b9b30b194418..36a7a3f11839a 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -3,6 +3,8 @@ #include +struct task_struct; + /* misc architecture specific prototypes */ void syscall_init(void); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index aa34b16e62c24..a069d0dd3ded4 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 1cc6e54436dba..2f3df43489f22 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -42,13 +42,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID]; + u8 vectors[KVM_MAX_VCPU_ID + 1]; }; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 8377bd388d673..14e9b06829d54 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1333,7 +1333,7 @@ static void increase_address_space(struct protection_domain *domain, pte = (void *)get_zeroed_page(gfp); if (!pte) - goto out; + return; spin_lock_irqsave(&domain->lock, flags); diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 022a9b3c7d4e8..d62d61d734ea1 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -267,6 +267,8 @@ struct ems_usb { unsigned int free_slots; /* remember number of available slots */ struct ems_cpc_msg active_params; /* active controller parameters */ + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; static void ems_usb_read_interrupt_callback(struct urb *urb) @@ -598,6 +600,7 @@ static int ems_usb_start(struct ems_usb *dev) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -607,7 +610,7 @@ static int ems_usb_start(struct ems_usb *dev) } buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -615,6 +618,8 @@ static int ems_usb_start(struct ems_usb *dev) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 2), buf, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); @@ -630,6 +635,9 @@ static int ems_usb_start(struct ems_usb *dev) break; } + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -695,6 +703,10 @@ static void unlink_all_urbs(struct ems_usb *dev) usb_kill_anchored_urbs(&dev->rx_submitted); + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + usb_kill_anchored_urbs(&dev->tx_submitted); atomic_set(&dev->active_tx_urbs, 0); diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index c6dcf93675c00..592c6e7f3dca4 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -207,6 +207,8 @@ struct esd_usb2 { int net_count; u32 version; int rxinitdone; + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; struct esd_usb2_net_priv { @@ -556,6 +558,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -565,7 +568,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) } buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { dev_warn(dev->udev->dev.parent, "No memory left for USB buffer\n"); @@ -573,6 +576,8 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) goto freeurb; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), buf, RX_BUFFER_SIZE, @@ -585,8 +590,12 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) usb_unanchor_urb(urb); usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf, urb->transfer_dma); + goto freeurb; } + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + freeurb: /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); @@ -674,6 +683,11 @@ static void unlink_all_urbs(struct esd_usb2 *dev) int i, j; usb_kill_anchored_urbs(&dev->rx_submitted); + + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + for (i = 0; i < dev->net_count; i++) { priv = dev->nets[i]; if (priv) { diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 3e44164736079..df99354ec12aa 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -148,7 +148,8 @@ struct usb_8dev_priv { u8 *cmd_msg_buffer; struct mutex usb_8dev_cmd_lock; - + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; /* tx frame */ @@ -744,6 +745,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -753,7 +755,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) } buf = usb_alloc_coherent(priv->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -761,6 +763,8 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, priv->udev, usb_rcvbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_RX), @@ -778,6 +782,9 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) break; } + priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -847,6 +854,10 @@ static void unlink_all_urbs(struct usb_8dev_priv *priv) usb_kill_anchored_urbs(&priv->rx_submitted); + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, RX_BUFFER_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); atomic_set(&priv->active_tx_urbs, 0); diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 1f62b94238510..31dfb695ededa 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -368,7 +368,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0; void __iomem *ioaddr; - i = pci_enable_device(pdev); + i = pcim_enable_device(pdev); if (i) return i; pci_set_master(pdev); @@ -390,7 +390,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size); if (!ioaddr) - goto err_out_free_res; + goto err_out_netdev; for (i = 0; i < 3; i++) ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i)); @@ -469,8 +469,6 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) err_out_cleardev: pci_iounmap(pdev, ioaddr); -err_out_free_res: - pci_release_regions(pdev); err_out_netdev: free_netdev (dev); return -ENODEV; @@ -1537,7 +1535,6 @@ static void w840_remove1(struct pci_dev *pdev) if (dev) { struct netdev_private *np = netdev_priv(dev); unregister_netdev(dev); - pci_release_regions(pdev); pci_iounmap(pdev, np->base_addr); free_netdev(dev); } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 9b6a96074df80..78b04f2713440 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3445,6 +3445,7 @@ slave_start: if (!SRIOV_VALID_STATE(dev->flags)) { mlx4_err(dev, "Invalid SRIOV state\n"); + err = -EINVAL; goto err_close; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 13dfc197bdd8d..6c092dc41c82e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -701,17 +701,19 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev, static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { - struct mlx5_flow_table *next_ft; + struct mlx5_flow_table *next_ft, *first_ft; int err = 0; /* Connect_prev_fts and update_root_ft_create are mutually exclusive */ - if (list_empty(&prio->node.children)) { + first_ft = list_first_entry_or_null(&prio->node.children, + struct mlx5_flow_table, node.list); + if (!first_ft || first_ft->level > ft->level) { err = connect_prev_fts(dev, ft, prio); if (err) return err; - next_ft = find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(prio); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1357,7 +1359,7 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft) node.list) == ft)) return 0; - next_ft = find_next_chained_ft(prio); + next_ft = find_next_ft(ft); err = connect_fwd_rules(dev, next_ft, ft); if (err) return err; diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index ae9b983e8e5c9..4a0e69a2d4f58 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -442,7 +442,7 @@ static int sis900_probe(struct pci_dev *pci_dev, #endif /* setup various bits in PCI command register */ - ret = pci_enable_device(pci_dev); + ret = pcim_enable_device(pci_dev); if(ret) return ret; i = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); @@ -468,7 +468,7 @@ static int sis900_probe(struct pci_dev *pci_dev, ioaddr = pci_iomap(pci_dev, 0, 0); if (!ioaddr) { ret = -ENOMEM; - goto err_out_cleardev; + goto err_out; } sis_priv = netdev_priv(net_dev); @@ -576,8 +576,6 @@ err_unmap_tx: sis_priv->tx_ring_dma); err_out_unmap: pci_iounmap(pci_dev, ioaddr); -err_out_cleardev: - pci_release_regions(pci_dev); err_out: free_netdev(net_dev); return ret; @@ -2425,7 +2423,6 @@ static void sis900_remove(struct pci_dev *pci_dev) sis_priv->tx_ring_dma); pci_iounmap(pci_dev, sis_priv->ioaddr); free_netdev(net_dev); - pci_release_regions(pci_dev); } #ifdef CONFIG_PM diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 306d5d08141ee..f3aed26656a39 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8213,8 +8213,9 @@ static int niu_pci_vpd_fetch(struct niu *np, u32 start) err = niu_pci_vpd_scan_props(np, here, end); if (err < 0) return err; + /* ret == 1 is not an error */ if (err == 1) - return -EINVAL; + return 0; } return 0; } diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index a466e79784668..11aa6a04ff466 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -201,8 +201,7 @@ static void nfcsim_recv_wq(struct work_struct *work) if (!IS_ERR(skb)) dev_kfree_skb(skb); - - skb = ERR_PTR(-ENODEV); + return; } dev->cb(dev->nfc_digital_dev, dev->arg, skb); diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index de69d8a24f6d7..7f2ef95dcd055 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -24,7 +24,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + return -EINVAL; + } return 0; } diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index d77d844b668b1..1ff979c9d0a36 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -14,16 +14,31 @@ #include "btree.h" -void hfs_bnode_read(struct hfs_bnode *node, void *buf, - int off, int len) +void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; + int pagenum; + int bytes_read; + int bytes_to_read; + void *vaddr; off += node->page_offset; - page = node->page[0]; + pagenum = off >> PAGE_SHIFT; + off &= ~PAGE_MASK; /* compute page offset for the first page */ - memcpy(buf, kmap(page) + off, len); - kunmap(page); + for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) { + if (pagenum >= node->tree->pages_per_bnode) + break; + page = node->page[pagenum]; + bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off); + + vaddr = kmap_atomic(page); + memcpy(buf + bytes_read, vaddr + off, bytes_to_read); + kunmap_atomic(vaddr); + + pagenum++; + off = 0; /* page offset only applies to the first page */ + } } u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off) diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index 2715f416b5a80..308b5f1af65ba 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -12,6 +12,13 @@ typedef int (*btree_keycmp)(const btree_key *, const btree_key *); #define NODE_HASH_SIZE 256 +/* B-tree mutex nested subclasses */ +enum hfs_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* A HFS BTree held in memory */ struct hfs_btree { struct super_block *sb; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index bf6304a350a6b..c2a5a0ca39486 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -427,14 +427,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { res = -EIO; - goto bail; + goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); } - if (res) { - hfs_find_exit(&fd); - goto bail_no_root; - } + if (res) + goto bail_hfs_find; res = -EINVAL; root_inode = hfs_iget(sb, &fd.search_key->cat, &rec); hfs_find_exit(&fd); @@ -450,6 +448,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) /* everything's okay */ return 0; +bail_hfs_find: + hfs_find_exit(&fd); bail_no_root: pr_err("get root inode failed\n"); bail: diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 3aa4441f5ab50..d526e86cf5bbe 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1511,6 +1511,45 @@ static void ocfs2_truncate_cluster_pages(struct inode *inode, u64 byte_start, } } +/* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { @@ -1520,6 +1559,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; + loff_t isize = i_size_read(inode); /* * The "start" and "end" values are NOT necessarily part of @@ -1540,6 +1580,26 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0) goto out; + /* No page cache for EOF blocks, issue zero out to disk. */ + if (end > isize) { + /* + * zeroout eof blocks in last cluster starting from + * "isize" even "start" > "isize" because it is + * complicated to zeroout just at "start" as "start" + * may be not aligned with block size, buffer write + * would be required to do that, but out of eof buffer + * write is not supported. + */ + ret = ocfs2_zeroout_partial_cluster(inode, isize, + end - isize); + if (ret) { + mlog_errno(ret); + goto out; + } + if (start >= isize) + goto out; + end = isize; + } handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -1838,45 +1898,6 @@ out: return ret; } -/* - * zero out partial blocks of one cluster. - * - * start: file offset where zero starts, will be made upper block aligned. - * len: it will be trimmed to the end of current cluster if "start + len" - * is bigger than it. - */ -static int ocfs2_zeroout_partial_cluster(struct inode *inode, - u64 start, u64 len) -{ - int ret; - u64 start_block, end_block, nr_blocks; - u64 p_block, offset; - u32 cluster, p_cluster, nr_clusters; - struct super_block *sb = inode->i_sb; - u64 end = ocfs2_align_bytes_to_clusters(sb, start); - - if (start + len < end) - end = start + len; - - start_block = ocfs2_blocks_for_bytes(sb, start); - end_block = ocfs2_blocks_for_bytes(sb, end); - nr_blocks = end_block - start_block; - if (!nr_blocks) - return 0; - - cluster = ocfs2_bytes_to_clusters(sb, start); - ret = ocfs2_get_clusters(inode, cluster, &p_cluster, - &nr_clusters, NULL); - if (ret) - return ret; - if (!p_cluster) - return 0; - - offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); - p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; - return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); -} - /* * Parts of this function taken from xfs_change_file_space() */ @@ -1918,7 +1939,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } - orig_isize = i_size_read(inode); switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; @@ -1926,7 +1946,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, sr->l_start += f_pos; break; case 2: /*SEEK_END*/ - sr->l_start += orig_isize; + sr->l_start += i_size_read(inode); break; default: ret = -EINVAL; @@ -1981,6 +2001,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, ret = -EINVAL; } + orig_isize = i_size_read(inode); /* zeroout eof blocks in the cluster. */ if (!ret && change_size && orig_isize < size) { ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, diff --git a/include/linux/string.h b/include/linux/string.h index 66a91f5a34499..dd810d4739ee9 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -103,6 +103,36 @@ extern __kernel_size_t strcspn(const char *,const char *); #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif + +#ifndef __HAVE_ARCH_MEMSET16 +extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); +#endif + +static inline void *memset_l(unsigned long *p, unsigned long v, + __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, v, n); + else + return memset64((uint64_t *)p, v, n); +} + +static inline void *memset_p(void **p, void *v, __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, (uintptr_t)v, n); + else + return memset64((uint64_t *)p, (uintptr_t)v, n); +} + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif diff --git a/include/net/af_unix.h b/include/net/af_unix.h index fd60eccb59a67..79f2e1ccfcfb8 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -8,6 +8,7 @@ void unix_inflight(struct user_struct *user, struct file *fp); void unix_notinflight(struct user_struct *user, struct file *fp); +void unix_destruct_scm(struct sk_buff *skb); void unix_gc(void); void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index c0f0a13ed8183..49aa79c7b278a 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -15,9 +15,11 @@ #include /* Lengths of frame formats */ -#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ -#define LLC_PDU_LEN_S 4 -#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ +#define LLC_PDU_LEN_S 4 +#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +/* header and 1 control byte and XID info */ +#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ @@ -50,9 +52,10 @@ #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03 -#define LLC_PDU_TYPE_I 0 /* first bit */ -#define LLC_PDU_TYPE_S 1 /* first two bits */ -#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_I 0 /* first bit */ +#define LLC_PDU_TYPE_S 1 /* first two bits */ +#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */ #define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) @@ -230,9 +233,18 @@ static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { - const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; + int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu; + switch (type) { + case LLC_PDU_TYPE_U: + hlen = 3; + break; + case LLC_PDU_TYPE_U_XID: + hlen = 6; + break; + } + skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); @@ -374,7 +386,10 @@ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ - skb_put(skb, sizeof(struct llc_xid_info)); + + /* no need to push/put since llc_pdu_header_init() has already + * pushed 3 + 3 bytes + */ } /** diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 8890fd66021dd..9799c300603a9 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -344,8 +344,7 @@ typedef enum { } sctp_scope_policy_t; /* Based on IPv4 scoping , - * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24, - * 192.88.99.0/24. + * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24. * Also, RFC 8.4, non-unicast addresses are not considered valid SCTP * addresses. */ @@ -353,7 +352,6 @@ typedef enum { ((htonl(INADDR_BROADCAST) == a) || \ ipv4_is_multicast(a) || \ ipv4_is_zeronet(a) || \ - ipv4_is_test_198(a) || \ ipv4_is_anycast_6to4(a)) /* Flags used for the bind address copy functions. */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a410d5827a73f..b3476a21a7b31 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3397,15 +3397,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work) unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; - bool is_last; + bool is_last = false; - if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) - return; + /* + * when @pwq is not linked, it doesn't hold any reference to the + * @wq, and @wq is invalid to access. + */ + if (!list_empty(&pwq->pwqs_node)) { + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return; - mutex_lock(&wq->mutex); - list_del_rcu(&pwq->pwqs_node); - is_last = list_empty(&wq->pwqs); - mutex_unlock(&wq->mutex); + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); diff --git a/lib/string.c b/lib/string.c index 8fe13371aed7a..ec1ba61b358f2 100644 --- a/lib/string.c +++ b/lib/string.c @@ -754,6 +754,72 @@ void memzero_explicit(void *s, size_t count) } EXPORT_SYMBOL(memzero_explicit); +#ifndef __HAVE_ARCH_MEMSET16 +/** + * memset16() - Fill a memory area with a uint16_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint16_t instead + * of a byte. Remember that @count is the number of uint16_ts to + * store, not the number of bytes. + */ +void *memset16(uint16_t *s, uint16_t v, size_t count) +{ + uint16_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset16); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +/** + * memset32() - Fill a memory area with a uint32_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint32_t instead + * of a byte. Remember that @count is the number of uint32_ts to + * store, not the number of bytes. + */ +void *memset32(uint32_t *s, uint32_t v, size_t count) +{ + uint32_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset32); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +/** + * memset64() - Fill a memory area with a uint64_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint64_t instead + * of a byte. Remember that @count is the number of uint64_ts to + * store, not the number of bytes. + */ +void *memset64(uint64_t *s, uint64_t v, size_t count) +{ + uint64_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset64); +#endif + #ifndef __HAVE_ARCH_MEMCPY /** * memcpy - Copy one area of memory to another diff --git a/net/802/garp.c b/net/802/garp.c index b38ee6dcba45f..5239b8f244e75 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -206,6 +206,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); } +static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -612,6 +625,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/802/mrp.c b/net/802/mrp.c index 72db2785ef2c0..4ee3af3d400b1 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -295,6 +295,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) kfree(attr); } +static void mrp_attr_destroy_all(struct mrp_applicant *app) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_destroy(app, attr); + } +} + static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; @@ -900,6 +913,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); + mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/Makefile b/net/Makefile index 4cafaa2b4667e..1955d89de75bb 100644 --- a/net/Makefile +++ b/net/Makefile @@ -16,7 +16,7 @@ obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX) += unix/ +obj-$(CONFIG_UNIX_SCM) += unix/ obj-$(CONFIG_NET) += ipv6/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 1a77d0687d743..a8866455e8b2a 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -96,8 +96,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; - if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index 7ae4cc684d3ab..9fa3342c7a829 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc; - llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ddd90a3820d39..d03f067178445 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -491,8 +491,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false; tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + } if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index d2510e432c183..d338d69a0e0bb 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -157,7 +157,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index b2c242facf1b9..b1932fd125dad 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -413,7 +413,8 @@ static sctp_scope_t sctp_v4_scope(union sctp_addr *addr) retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || - ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { + ipv4_is_private_192(addr->v4.sin_addr.s_addr) || + ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; diff --git a/net/tipc/link.c b/net/tipc/link.c index 06327f78f2032..6fc2fa75503d2 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -893,6 +893,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (pkt_cnt <= 0) return 0; + hdr = buf_msg(skb_peek(list)); imp = msg_importance(hdr); /* Match msg importance against this and all higher backlog limits: */ if (!skb_queue_empty(backlogq)) { @@ -902,7 +903,6 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, } } - hdr = buf_msg(skb_peek(list)); if (unlikely(msg_size(hdr) > mtu)) { skb_queue_purge(list); return -EMSGSIZE; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c1b9074f3325e..6077850774454 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1985,7 +1985,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; /* True wake-one mechanism for incoming connections: only @@ -1994,12 +1994,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2014,7 +2014,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; } diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 8b31ab85d050f..3b9e450656a4d 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -19,6 +19,11 @@ config UNIX Say Y unless you know what you are doing. +config UNIX_SCM + bool + depends on UNIX + default y + config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index b663c607b1c61..dc686c6757fb5 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -9,3 +9,5 @@ unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o + +obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 8bbaa35937dd9..bfdfb958a37d6 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -118,6 +118,8 @@ #include #include +#include "scm.h" + struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); DEFINE_SPINLOCK(unix_table_lock); @@ -1505,78 +1507,51 @@ out: return err; } -static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} - -static void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -#define MAX_RECURSION_LEVEL 4 - -static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { - int i; - unsigned char max_level = 0; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - for (i = scm->fp->count - 1; i >= 0; i--) { - struct sock *sk = unix_get_socket(scm->fp->fp[i]); - - if (sk) - max_level = max(max_level, - unix_sk(sk)->recursion_level); - } - if (unlikely(max_level > MAX_RECURSION_LEVEL)) - return -ETOOMANYREFS; + scm->fp = scm_fp_dup(UNIXCB(skb).fp); /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return max_level; + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -2212,7 +2187,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2457,7 +2432,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c36757e728442..8bbe1b8e4ff7f 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -86,77 +86,13 @@ #include #include +#include "scm.h" + /* Internal data structures and random procedures: */ -static LIST_HEAD(gc_inflight_list); static LIST_HEAD(gc_candidates); -static DEFINE_SPINLOCK(unix_gc_lock); static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); -unsigned int unix_tot_inflight; - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) - u_sock = s; - } - return u_sock; -} - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ - -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (atomic_long_inc_return(&u->inflight) == 1) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - unix_tot_inflight++; - } - user->unix_inflight++; - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!atomic_long_read(&u->inflight)); - BUG_ON(list_empty(&u->link)); - - if (atomic_long_dec_and_test(&u->inflight)) - list_del_init(&u->link); - unix_tot_inflight--; - } - user->unix_inflight--; - spin_unlock(&unix_gc_lock); -} - static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { diff --git a/net/unix/scm.c b/net/unix/scm.c new file mode 100644 index 0000000000000..df8f636ab1d8c --- /dev/null +++ b/net/unix/scm.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "scm.h" + +unsigned int unix_tot_inflight; +EXPORT_SYMBOL(unix_tot_inflight); + +LIST_HEAD(gc_inflight_list); +EXPORT_SYMBOL(gc_inflight_list); + +DEFINE_SPINLOCK(unix_gc_lock); +EXPORT_SYMBOL(unix_gc_lock); + +struct sock *unix_get_socket(struct file *filp) +{ + struct sock *u_sock = NULL; + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + struct sock *s = sock->sk; + + /* PF_UNIX ? */ + if (s && sock->ops && sock->ops->family == PF_UNIX) + u_sock = s; + } + return u_sock; +} +EXPORT_SYMBOL(unix_get_socket); + +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. + */ +void unix_inflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + if (atomic_long_inc_return(&u->inflight) == 1) { + BUG_ON(!list_empty(&u->link)); + list_add_tail(&u->link, &gc_inflight_list); + } else { + BUG_ON(list_empty(&u->link)); + } + unix_tot_inflight++; + } + user->unix_inflight++; + spin_unlock(&unix_gc_lock); +} + +void unix_notinflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(list_empty(&u->link)); + + if (atomic_long_dec_and_test(&u->inflight)) + list_del_init(&u->link); + unix_tot_inflight--; + } + user->unix_inflight--; + spin_unlock(&unix_gc_lock); +} + +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +#define MAX_RECURSION_LEVEL 4 + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + unsigned char max_level = 0; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + for (i = scm->fp->count - 1; i >= 0; i--) { + struct sock *sk = unix_get_socket(scm->fp->fp[i]); + + if (sk) + max_level = max(max_level, + unix_sk(sk)->recursion_level); + } + if (unlikely(max_level > MAX_RECURSION_LEVEL)) + return -ETOOMANYREFS; + + /* + * Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); + return max_level; +} +EXPORT_SYMBOL(unix_attach_fds); + +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + for (i = scm->fp->count-1; i >= 0; i--) + unix_notinflight(scm->fp->user, scm->fp->fp[i]); +} +EXPORT_SYMBOL(unix_detach_fds); + +void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); +} +EXPORT_SYMBOL(unix_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h new file mode 100644 index 0000000000000..5a255a477f160 --- /dev/null +++ b/net/unix/scm.h @@ -0,0 +1,10 @@ +#ifndef NET_UNIX_SCM_H +#define NET_UNIX_SCM_H + +extern struct list_head gc_inflight_list; +extern spinlock_t unix_gc_lock; + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); + +#endif diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 71a8e6980e2fc..901a8742a28dc 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -949,16 +949,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } } if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - if (!list_empty(&new->hidden_list)) - list_del(&new->hidden_list); - kfree(new); + bss_ref_put(rdev, new); goto drop; }