/* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * mmap.c * * Code to deal with the mess that is clustered mmap. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public * License as published by the Free Software Foundation; either * version 2 of the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. * * You should have received a copy of the GNU General Public * License along with this program; if not, write to the * Free Software Foundation, Inc., 59 Temple Place - Suite 330, * Boston, MA 021110-1307, USA. */ #include #include #include #include #include #include #include #include #include "ocfs2.h" #include "aops.h" #include "dlmglue.h" #include "file.h" #include "inode.h" #include "mmap.h" #include "super.h" #include "ocfs2_trace.h" static int ocfs2_fault(struct vm_area_struct *area, struct vm_fault *vmf) { sigset_t oldset; int ret; ocfs2_block_signals(&oldset); ret = filemap_fault(area, vmf); ocfs2_unblock_signals(&oldset); trace_ocfs2_fault(OCFS2_I(area->vm_file->f_mapping->host)->ip_blkno, area, vmf->page, vmf->pgoff); return ret; } static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, struct page *page) { int ret = VM_FAULT_NOPAGE; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; loff_t pos = page_offset(page); unsigned int len = PAGE_SIZE; pgoff_t last_index; struct page *locked_page = NULL; void *fsdata; loff_t size = i_size_read(inode); last_index = (size - 1) >> PAGE_SHIFT; /* * There are cases that lead to the page no longer bebongs to the * mapping. * 1) pagecache truncates locally due to memory pressure. * 2) pagecache truncates when another is taking EX lock against * inode lock. see ocfs2_data_convert_worker. * * The i_size check doesn't catch the case where nodes truncated and * then re-extended the file. We'll re-check the page mapping after * taking the page lock inside of ocfs2_write_begin_nolock(). * * Let VM retry with these cases. */ if ((page->mapping != inode->i_mapping) || (!PageUptodate(page)) || (page_offset(page) >= size)) goto out; /* * Call ocfs2_write_begin() and ocfs2_write_end() to take * advantage of the allocation code there. We pass a write * length of the whole page (chopped to i_size) to make sure * the whole thing is allocated. * * Since we know the page is up to date, we don't have to * worry about ocfs2_write_begin() skipping some buffer reads * because the "write" would invalidate their data. */ if (page->index == last_index) len = ((size - 1) & ~PAGE_MASK) + 1; ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, &locked_page, &fsdata, di_bh, page); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); if (ret == -ENOMEM) ret = VM_FAULT_OOM; else ret = VM_FAULT_SIGBUS; goto out; } if (!locked_page) { ret = VM_FAULT_NOPAGE; goto out; } ret = ocfs2_write_end_nolock(mapping, pos, len, len, fsdata); BUG_ON(ret != len); ret = VM_FAULT_LOCKED; out: return ret; } static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); struct buffer_head *di_bh = NULL; sigset_t oldset; int ret; sb_start_pagefault(inode->i_sb); ocfs2_block_signals(&oldset); /* * The cluster locks taken will block a truncate from another * node. Taking the data lock will also ensure that we don't * attempt page truncation as part of a downconvert. */ ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); if (ret == -ENOMEM) ret = VM_FAULT_OOM; else ret = VM_FAULT_SIGBUS; goto out; } /* * The alloc sem should be enough to serialize with * ocfs2_truncate_file() changing i_size as well as any thread * modifying the inode btree. */ down_write(&OCFS2_I(inode)->ip_alloc_sem); ret = __ocfs2_page_mkwrite(vma->vm_file, di_bh, page); up_write(&OCFS2_I(inode)->ip_alloc_sem); brelse(di_bh); ocfs2_inode_unlock(inode, 1); out: ocfs2_unblock_signals(&oldset); sb_end_pagefault(inode->i_sb); return ret; } static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) { int ret = 0, lock_level = 0; ret = ocfs2_inode_lock_atime(file_inode(file), file->f_path.mnt, &lock_level); if (ret < 0) { mlog_errno(ret); goto out; } ocfs2_inode_unlock(file_inode(file), lock_level); out: vma->vm_ops = &ocfs2_file_vm_ops; return 0; } td>-0/+3 IPv6 does not set the NLM_F_APPEND flag in notifications to signal that a NEWROUTE is an append versus a new route or a replaced one. Add the flag if the request has it. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-01net: reduce skb_warn_bad_offload() noiseEric Dumazet1-3/+9 Dmitry reported warnings occurring in __skb_gso_segment() [1] All SKB_GSO_DODGY producers can allow user space to feed packets that trigger the current check. We could prevent them from doing so, rejecting packets, but this might add regressions to existing programs. It turns out our SKB_GSO_DODGY handlers properly set up checksum information that is needed anyway when packets needs to be segmented. By checking again skb_needs_check() after skb_mac_gso_segment(), we should remove these pesky warnings, at a very minor cost. With help from Willem de Bruijn [1] WARNING: CPU: 1 PID: 6768 at net/core/dev.c:2439 skb_warn_bad_offload+0x2af/0x390 net/core/dev.c:2434 lo: caps=(0x000000a2803b7c69, 0x0000000000000000) len=138 data_len=0 gso_size=15883 gso_type=4 ip_summed=0 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 6768 Comm: syz-executor1 Not tainted 4.9.0 #5 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ffff8801c063ecd8 ffffffff82346bdf ffffffff00000001 1ffff100380c7d2e ffffed00380c7d26 0000000041b58ab3 ffffffff84b37e38 ffffffff823468f1 ffffffff84820740 ffffffff84f289c0 dffffc0000000000 ffff8801c063ee20 Call Trace: [<ffffffff82346bdf>] __dump_stack lib/dump_stack.c:15 [inline] [<ffffffff82346bdf>] dump_stack+0x2ee/0x3ef lib/dump_stack.c:51 [<ffffffff81827e34>] panic+0x1fb/0x412 kernel/panic.c:179 [<ffffffff8141f704>] __warn+0x1c4/0x1e0 kernel/panic.c:542 [<ffffffff8141f7e5>] warn_slowpath_fmt+0xc5/0x100 kernel/panic.c:565 [<ffffffff8356cbaf>] skb_warn_bad_offload+0x2af/0x390 net/core/dev.c:2434 [<ffffffff83585cd2>] __skb_gso_segment+0x482/0x780 net/core/dev.c:2706 [<ffffffff83586f19>] skb_gso_segment include/linux/netdevice.h:3985 [inline] [<ffffffff83586f19>] validate_xmit_skb+0x5c9/0xc20 net/core/dev.c:2969 [<ffffffff835892bb>] __dev_queue_xmit+0xe6b/0x1e70 net/core/dev.c:3383 [<ffffffff8358a2d7>] dev_queue_xmit+0x17/0x20 net/core/dev.c:3424 [<ffffffff83ad161d>] packet_snd net/packet/af_packet.c:2930 [inline] [<ffffffff83ad161d>] packet_sendmsg+0x32ed/0x4d30 net/packet/af_packet.c:2955 [<ffffffff834f0aaa>] sock_sendmsg_nosec net/socket.c:621 [inline] [<ffffffff834f0aaa>] sock_sendmsg+0xca/0x110 net/socket.c:631 [<ffffffff834f329a>] ___sys_sendmsg+0x8fa/0x9f0 net/socket.c:1954 [<ffffffff834f5e58>] __sys_sendmsg+0x138/0x300 net/socket.c:1988 [<ffffffff834f604d>] SYSC_sendmsg net/socket.c:1999 [inline] [<ffffffff834f604d>] SyS_sendmsg+0x2d/0x50 net/socket.c:1995 [<ffffffff84371941>] entry_SYSCALL_64_fastpath+0x1f/0xc2 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-01rtnetlink: Handle IFLA_MASTER parameter when processing rtnl_newlinkTheuns Verwoerd1-1/+6 Allow a master interface to be specified as one of the parameters when creating a new interface via rtnl_newlink. Previously this would require invoking interface creation, waiting for it to complete, and then separately binding that new interface to a master. In particular, this is used when creating a macvlan child interface for VRRP in a VRF configuration, allowing the interface creator to specify directly what master interface should be inherited by the child, without having to deal with asynchronous complications and potential race conditions. Signed-off-by: Theuns Verwoerd <theuns.verwoerd@alliedtelesis.co.nz> Acked-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>