summaryrefslogtreecommitdiffstats
path: root/fs
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag '5.7-rc-smb3-fixes-part2' of git://git.samba.org/sfrench/cifs-2.6Linus Torvalds2020-04-1212-238/+272
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull cifs fixes from Steve French: "Ten cifs/smb fixes: - five RDMA (smbdirect) related fixes - add experimental support for swap over SMB3 mounts - also a fix which improves performance of signed connections" * tag '5.7-rc-smb3-fixes-part2' of git://git.samba.org/sfrench/cifs-2.6: smb3: enable swap on SMB3 mounts smb3: change noisy error message to FYI smb3: smbdirect support can be configured by default cifs: smbd: Do not schedule work to send immediate packet on every receive cifs: smbd: Properly process errors on ib_post_send cifs: Allocate crypto structures on the fly for calculating signatures of incoming packets cifs: smbd: Update receive credits before sending and deal with credits roll back on failure before sending cifs: smbd: Check send queue size before posting a send cifs: smbd: Merge code to track pending packets cifs: ignore cached share root handle closing errors
| * smb3: enable swap on SMB3 mountsSteve French2020-04-104-0/+70
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add experimental support for allowing a swap file to be on an SMB3 mount. There are use cases where swapping over a secure network filesystem is preferable. In some cases there are no local block devices large enough, and network block devices can be hard to setup and secure. And in some cases there are no local block devices at all (e.g. with the recent addition of remote boot over SMB3 mounts). There are various enhancements that can be added later e.g.: - doing a mandatory byte range lock over the swapfile (until the Linux VFS is modified to notify the file system that an open is for a swapfile, when the file can be opened "DENY_ALL" to prevent others from opening it). - pinning more buffers in the underlying transport to minimize memory allocations in the TCP stack under the fs - documenting how to create ACLs (on the server) to secure the swapfile (or adding additional tools to cifs-utils to make it easier) Signed-off-by: Steve French <stfrench@microsoft.com> Acked-by: Pavel Shilovsky <pshilov@microsoft.com> Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
| * smb3: change noisy error message to FYISteve French2020-04-091-1/+1
| | | | | | | | | | | | | | | | | | The noisy posix error message in readdir was supposed to be an FYI (not enabled by default) CIFS VFS: XXX dev 66306, reparse 0, mode 755 Signed-off-by: Steve French <stfrench@microsoft.com> Reviewed-by: Aurelien Aptel <aaptel@suse.com>
| * smb3: smbdirect support can be configured by defaultSteve French2020-04-071-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | smbdirect support (SMB3 over RDMA) should be enabled by default in many configurations. It is not experimental and is stable enough and has enough performance benefits to recommend that it be configured by default. Change the "If unsure N" to "If unsure Y" in the description of the configuration parameter. Acked-by: Aurelien Aptel <aaptel@suse.com> Reviewed-by: Long Li <longli@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: smbd: Do not schedule work to send immediate packet on every receiveLong Li2020-04-072-52/+10
| | | | | | | | | | | | | | | | | | | | | | Immediate packets should only be sent to peer when there are new receive credits made available. New credits show up on freeing receive buffer, not on receiving data. Fix this by avoid unnenecessary work schedules. Signed-off-by: Long Li <longli@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: smbd: Properly process errors on ib_post_sendLong Li2020-04-071-123/+97
| | | | | | | | | | | | | | | | | | | | When processing errors from ib_post_send(), the transport state needs to be rolled back to the condition before the error. Refactor the old code to make it easy to roll back on IB errors, and fix this. Signed-off-by: Long Li <longli@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: Allocate crypto structures on the fly for calculating signatures of ↵Long Li2020-04-073-36/+60
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | incoming packets CIFS uses pre-allocated crypto structures to calculate signatures for both incoming and outgoing packets. In this way it doesn't need to allocate crypto structures for every packet, but it requires a lock to prevent concurrent access to crypto structures. Remove the lock by allocating crypto structures on the fly for incoming packets. At the same time, we can still use pre-allocated crypto structures for outgoing packets, as they are already protected by transport lock srv_mutex. Signed-off-by: Long Li <longli@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: smbd: Update receive credits before sending and deal with credits roll ↵Long Li2020-04-071-7/+18
| | | | | | | | | | | | | | | | | | | | | | | | back on failure before sending Recevie credits should be updated before sending the packet, not before a work is scheduled. Also, the value needs roll back if something fails and cannot send. Signed-off-by: Long Li <longli@microsoft.com> Reported-by: kbuild test robot <lkp@intel.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: smbd: Check send queue size before posting a sendLong Li2020-04-072-1/+11
| | | | | | | | | | | | | | | | | | | | | | Sometimes the remote peer may return more send credits than the send queue depth. If all the send credits are used to post senasd, we may overflow the send queue. Fix this by checking the send queue size before posting a send. Signed-off-by: Long Li <longli@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: smbd: Merge code to track pending packetsLong Li2020-04-073-39/+12
| | | | | | | | | | | | | | | | | | | | | | As an optimization, SMBD tries to track two types of packets: packets with payload and without payload. There is no obvious benefit or performance gain to separately track two types of packets. Just treat them as pending packets and merge the tracking code. Signed-off-by: Long Li <longli@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
| * cifs: ignore cached share root handle closing errorsAurelien Aptel2020-04-071-0/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix tcon use-after-free and NULL ptr deref. Customer system crashes with the following kernel log: [462233.169868] CIFS VFS: Cancelling wait for mid 4894753 cmd: 14 => a QUERY DIR [462233.228045] CIFS VFS: cifs_put_smb_ses: Session Logoff failure rc=-4 [462233.305922] CIFS VFS: cifs_put_smb_ses: Session Logoff failure rc=-4 [462233.306205] CIFS VFS: cifs_put_smb_ses: Session Logoff failure rc=-4 [462233.347060] CIFS VFS: cifs_put_smb_ses: Session Logoff failure rc=-4 [462233.347107] CIFS VFS: Close unmatched open [462233.347113] BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 ... [exception RIP: cifs_put_tcon+0xa0] (this is doing tcon->ses->server) #6 [...] smb2_cancelled_close_fid at ... [cifs] #7 [...] process_one_work at ... #8 [...] worker_thread at ... #9 [...] kthread at ... The most likely explanation we have is: * When we put the last reference of a tcon (refcount=0), we close the cached share root handle. * If closing a handle is interrupted, SMB2_close() will queue a SMB2_close() in a work thread. * The queued object keeps a tcon ref so we bump the tcon refcount, jumping from 0 to 1. * We reach the end of cifs_put_tcon(), we free the tcon object despite it now having a refcount of 1. * The queued work now runs, but the tcon, ses & server was freed in the meantime resulting in a crash. THREAD 1 ======== cifs_put_tcon => tcon refcount reach 0 SMB2_tdis close_shroot_lease close_shroot_lease_locked => if cached root has lease && refcount = 0 smb2_close_cached_fid => if cached root valid SMB2_close => retry close in a thread if interrupted smb2_handle_cancelled_close __smb2_handle_cancelled_close => !! tcon refcount bump 0 => 1 !! INIT_WORK(&cancelled->work, smb2_cancelled_close_fid); queue_work(cifsiod_wq, &cancelled->work) => queue work tconInfoFree(tcon); ==> freed! cifs_put_smb_ses(ses); ==> freed! THREAD 2 (workqueue) ======== smb2_cancelled_close_fid SMB2_close(0, cancelled->tcon, ...); => use-after-free of tcon cifs_put_tcon(cancelled->tcon); => tcon refcount reach 0 second time *CRASH* Fixes: d9191319358d ("CIFS: Close cached root handle only if it has a lease") Signed-off-by: Aurelien Aptel <aaptel@suse.com> Signed-off-by: Steve French <stfrench@microsoft.com> Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
* | Merge tag 'nfs-for-5.7-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfsLinus Torvalds2020-04-121-0/+1
|\ \ | | | | | | | | | | | | | | | | | | | | | Pull NFS client bugfix from Trond Myklebust: "Fix an RCU read lock leakage in pnfs_alloc_ds_commits_list()" * tag 'nfs-for-5.7-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: pNFS: Fix RCU lock leakage
| * | pNFS: Fix RCU lock leakageTrond Myklebust2020-04-111-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | Another brown paper bag moment. pnfs_alloc_ds_commits_list() is leaking the RCU lock. Fixes: a9901899b649 ("pNFS: Add infrastructure for cleaning up per-layout commit structures") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
* | | Merge branch 'akpm' (patches from Andrew)Linus Torvalds2020-04-106-5/+18
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Merge yet more updates from Andrew Morton: - Almost all of the rest of MM (memcg, slab-generic, slab, pagealloc, gup, hugetlb, pagemap, memremap) - Various other things (hfs, ocfs2, kmod, misc, seqfile) * akpm: (34 commits) ipc/util.c: sysvipc_find_ipc() should increase position index kernel/gcov/fs.c: gcov_seq_next() should increase position index fs/seq_file.c: seq_read(): add info message about buggy .next functions drivers/dma/tegra20-apb-dma.c: fix platform_get_irq.cocci warnings change email address for Pali Rohár selftests: kmod: test disabling module autoloading selftests: kmod: fix handling test numbers above 9 docs: admin-guide: document the kernel.modprobe sysctl fs/filesystems.c: downgrade user-reachable WARN_ONCE() to pr_warn_once() kmod: make request_module() return an error when autoloading is disabled mm/memremap: set caching mode for PCI P2PDMA memory to WC mm/memory_hotplug: add pgprot_t to mhp_params powerpc/mm: thread pgprot_t through create_section_mapping() x86/mm: introduce __set_memory_prot() x86/mm: thread pgprot_t through init_memory_mapping() mm/memory_hotplug: rename mhp_restrictions to mhp_params mm/memory_hotplug: drop the flags field from struct mhp_restrictions mm/special: create generic fallbacks for pte_special() and pte_mkspecial() mm/vma: introduce VM_ACCESS_FLAGS mm/vma: define a default value for VM_DATA_DEFAULT_FLAGS ...
| * | | fs/seq_file.c: seq_read(): add info message about buggy .next functionsVasily Averin2020-04-101-2/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch series "seq_file .next functions should increase position index". In Aug 2018 NeilBrown noticed commit 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code and interface") "Some ->next functions do not increment *pos when they return NULL... Note that such ->next functions are buggy and should be fixed. A simple demonstration is dd if=/proc/swaps bs=1000 skip=1 Choose any block size larger than the size of /proc/swaps. This will always show the whole last line of /proc/swaps" Described problem is still actual. If you make lseek into middle of last output line following read will output end of last line and whole last line once again. $ dd if=/proc/swaps bs=1 # usual output Filename Type Size Used Priority /dev/dm-0 partition 4194812 97536 -2 104+0 records in 104+0 records out 104 bytes copied $ dd if=/proc/swaps bs=40 skip=1 # last line was generated twice dd: /proc/swaps: cannot skip to specified offset v/dm-0 partition 4194812 97536 -2 /dev/dm-0 partition 4194812 97536 -2 3+1 records in 3+1 records out 131 bytes copied There are lot of other affected files, I've found 30+ including /proc/net/ip_tables_matches and /proc/sysvipc/* I've sent patches into maillists of affected subsystems already, this patch-set fixes the problem in files related to pstore, tracing, gcov, sysvipc and other subsystems processed via linux-kernel@ mailing list directly https://bugzilla.kernel.org/show_bug.cgi?id=206283 This patch (of 4): Add debug code to seq_read() to detect missed or out-of-tree incorrect .next seq_file functions. [akpm@linux-foundation.org: s/pr_info/pr_info_ratelimited/, per Qian Cai] https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: NeilBrown <neilb@suse.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Peter Oberparleiter <oberpar@linux.ibm.com> Cc: Waiman Long <longman@redhat.com> Link: http://lkml.kernel.org/r/244674e5-760c-86bd-d08a-047042881748@virtuozzo.com Link: http://lkml.kernel.org/r/7c24087c-e280-e580-5b0c-0cdaeb14cd18@virtuozzo.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| * | | change email address for Pali RohárPali Rohár2020-04-102-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For security reasons I stopped using gmail account and kernel address is now up-to-date alias to my personal address. People periodically send me emails to address which they found in source code of drivers, so this change reflects state where people can contact me. [ Added .mailmap entry as per Joe Perches - Linus ] Signed-off-by: Pali Rohár <pali@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joe Perches <joe@perches.com> Link: http://lkml.kernel.org/r/20200307104237.8199-1-pali@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| * | | fs/filesystems.c: downgrade user-reachable WARN_ONCE() to pr_warn_once()Eric Biggers2020-04-101-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After request_module(), nothing is stopping the module from being unloaded until someone takes a reference to it via try_get_module(). The WARN_ONCE() in get_fs_type() is thus user-reachable, via userspace running 'rmmod' concurrently. Since WARN_ONCE() is for kernel bugs only, not for user-reachable situations, downgrade this warning to pr_warn_once(). Keep it printed once only, since the intent of this warning is to detect a bug in modprobe at boot time. Printing the warning more than once wouldn't really provide any useful extra information. Fixes: 41124db869b7 ("fs: warn in case userspace lied about modprobe return") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jessica Yu <jeyu@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jeff Vander Stoep <jeffv@google.com> Cc: Jessica Yu <jeyu@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: NeilBrown <neilb@suse.com> Cc: <stable@vger.kernel.org> [4.13+] Link: http://lkml.kernel.org/r/20200312202552.241885-3-ebiggers@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| * | | ocfs2: no need try to truncate file beyond i_sizeChangwei Ge2020-04-101-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Linux fallocate(2) with FALLOC_FL_PUNCH_HOLE mode set, its offset can exceed the inode size. Ocfs2 now doesn't allow that offset beyond inode size. This restriction is not necessary and violates fallocate(2) semantics. If fallocate(2) offset is beyond inode size, just return success and do nothing further. Otherwise, ocfs2 will crash the kernel. kernel BUG at fs/ocfs2//alloc.c:7264! ocfs2_truncate_inline+0x20f/0x360 [ocfs2] ocfs2_remove_inode_range+0x23c/0xcb0 [ocfs2] __ocfs2_change_file_space+0x4a5/0x650 [ocfs2] ocfs2_fallocate+0x83/0xa0 [ocfs2] vfs_fallocate+0x148/0x230 SyS_fallocate+0x48/0x80 do_syscall_64+0x79/0x170 Signed-off-by: Changwei Ge <chge@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Mark Fasheh <mark@fasheh.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Junxiao Bi <junxiao.bi@oracle.com> Cc: Changwei Ge <gechangwei@live.cn> Cc: Gang He <ghe@suse.com> Cc: Jun Piao <piaojun@huawei.com> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/20200407082754.17565-1-chge@linux.alibaba.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| * | | hfsplus: fix crash and filesystem corruption when deleting filesSimon Gander2020-04-101-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When removing files containing extended attributes, the hfsplus driver may remove the wrong entries from the attributes b-tree, causing major filesystem damage and in some cases even kernel crashes. To remove a file, all its extended attributes have to be removed as well. The driver does this by looking up all keys in the attributes b-tree with the cnid of the file. Each of these entries then gets deleted using the key used for searching, which doesn't contain the attribute's name when it should. Since the key doesn't contain the name, the deletion routine will not find the correct entry and instead remove the one in front of it. If parent nodes have to be modified, these become corrupt as well. This causes invalid links and unsorted entries that not even macOS's fsck_hfs is able to fix. To fix this, modify the search key before an entry is deleted from the attributes b-tree by copying the found entry's key into the search key, therefore ensuring that the correct entry gets removed from the tree. Signed-off-by: Simon Gander <simon@tuxera.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Anton Altaparmakov <anton@tuxera.com> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/20200327155541.1521-1-simon@tuxera.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | | | Merge tag 'for-linus-5.7-ofs1' of ↵Linus Torvalds2020-04-103-70/+7
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux Pull orangefs updates from Mike Marshall: "A fix and two cleanups. Fix: - Christoph Hellwig noticed that some logic I added to orangefs_file_read_iter introduced a race condition, so he sent a reversion patch. I had to modify his patch since reverting at this point broke Orangefs. Cleanups: - Christoph Hellwig noticed that we were doing some unnecessary work in orangefs_flush, so he sent in a patch that removed the un-needed code. - Al Viro told me he had trouble building Orangefs. Orangefs should be easy to build, even for Al :-). I looked back at the test server build notes in orangefs.txt, just in case that's where the trouble really is, and found a couple of typos and made a couple of clarifications" * tag 'for-linus-5.7-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux: orangefs: clarify build steps for test server in orangefs.txt orangefs: don't mess with I_DIRTY_TIMES in orangefs_flush orangefs: get rid of knob code...
| * | | | orangefs: don't mess with I_DIRTY_TIMES in orangefs_flushMike Marshall2020-04-081-8/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Christoph Hellwig noticed that we were doing some unnecessary work in orangefs_flush: orangefs_flush just writes out data on every close(2) call. There is no need to change anything about the dirty state, especially as orangefs doesn't treat I_DIRTY_TIMES special in any way. The code seems to come from partially open coding vfs_fsync. He sent in a patch with the above commit message and also a patch that was a reversion of another Orangefs patch I had sent upstream a while ago. I had to fix his reversion patch so that it would compile which caused his "don't mess with I_DIRTY_TIMES" patch to fail to apply. So here I have just remade his patch and applied it after the fixed reversion patch. Signed-off-by: Mike Marshall <hubcap@omnibond.com>
| * | | | orangefs: get rid of knob code...Mike Marshall2020-04-083-62/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Christoph Hellwig sent in a reversion of "orangefs: remember count when reading." because: ->read_iter calls can race with each other and one or more ->flush calls. Remove the the scheme to store the read count in the file private data as is is completely racy and can cause use after free or double free conditions Christoph's reversion caused Orangefs not to work or to compile. I added a patch that fixed that, but intel's kbuild test robot pointed out that sending Christoph's patch followed by my patch upstream, it would break bisection because of the failure to compile. So I have combined the reversion plus my patch... here's the commit message that was in my patch: Logically, optimal Orangefs "pages" are 4 megabytes. Reading large Orangefs files 4096 bytes at a time is like trying to kick a dead whale down the beach. Before Christoph's "Revert orangefs: remember count when reading." I tried to give users a knob whereby they could, for example, use "count" in read(2) or bs with dd(1) to get whatever they considered an appropriate amount of bytes at a time from Orangefs and fill as many page cache pages as they could at once. Without the racy code that Christoph reverted Orangefs won't even compile, much less work. So this replaces the logic that used the private file data that Christoph reverted with a static number of bytes to read from Orangefs. I ran tests like the following to determine what a reasonable static number of bytes might be: dd if=/pvfsmnt/asdf of=/dev/null count=128 bs=4194304 dd if=/pvfsmnt/asdf of=/dev/null count=256 bs=2097152 dd if=/pvfsmnt/asdf of=/dev/null count=512 bs=1048576 . . . dd if=/pvfsmnt/asdf of=/dev/null count=4194304 bs=128 Reads seem faster using the static number, so my "knob code" wasn't just racy, it wasn't even a good idea... Signed-off-by: Mike Marshall <hubcap@omnibond.com> Reported-by: kbuild test robot <lkp@intel.com>
* | | | | Merge branch 'for-linus' of ↵Linus Torvalds2020-04-101-5/+5
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace Pull proc fix from Eric Biederman: "A brown paper bag slipped through my proc changes, and syzcaller caught it when the code ended up in your tree. I have opted to fix it the simplest cleanest way I know how, so there is no reasonable chance for the bug to repeat" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: proc: Use a dedicated lock in struct pid
| * | | | | proc: Use a dedicated lock in struct pidEric W. Biederman2020-04-091-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | syzbot wrote: > ======================================================== > WARNING: possible irq lock inversion dependency detected > 5.6.0-syzkaller #0 Not tainted > -------------------------------------------------------- > swapper/1/0 just changed the state of lock: > ffffffff898090d8 (tasklist_lock){.+.?}-{2:2}, at: send_sigurg+0x9f/0x320 fs/fcntl.c:840 > but this lock took another, SOFTIRQ-unsafe lock in the past: > (&pid->wait_pidfd){+.+.}-{2:2} > > > and interrupts could create inverse lock ordering between them. > > > other info that might help us debug this: > Possible interrupt unsafe locking scenario: > > CPU0 CPU1 > ---- ---- > lock(&pid->wait_pidfd); > local_irq_disable(); > lock(tasklist_lock); > lock(&pid->wait_pidfd); > <Interrupt> > lock(tasklist_lock); > > *** DEADLOCK *** > > 4 locks held by swapper/1/0: The problem is that because wait_pidfd.lock is taken under the tasklist lock. It must always be taken with irqs disabled as tasklist_lock can be taken from interrupt context and if wait_pidfd.lock was already taken this would create a lock order inversion. Oleg suggested just disabling irqs where I have added extra calls to wait_pidfd.lock. That should be safe and I think the code will eventually do that. It was rightly pointed out by Christian that sharing the wait_pidfd.lock was a premature optimization. It is also true that my pre-merge window testing was insufficient. So remove the premature optimization and give struct pid a dedicated lock of it's own for struct pid things. I have verified that lockdep sees all 3 paths where we take the new pid->lock and lockdep does not complain. It is my current day dream that one day pid->lock can be used to guard the task lists as well and then the tasklist_lock won't need to be held to deliver signals. That will require taking pid->lock with irqs disabled. Acked-by: Christian Brauner <christian.brauner@ubuntu.com> Link: https://lore.kernel.org/lkml/00000000000011d66805a25cd73f@google.com/ Cc: Oleg Nesterov <oleg@redhat.com> Cc: Christian Brauner <christian.brauner@ubuntu.com> Reported-by: syzbot+343f75cdeea091340956@syzkaller.appspotmail.com Reported-by: syzbot+832aabf700bc3ec920b9@syzkaller.appspotmail.com Reported-by: syzbot+f675f964019f884dbd0f@syzkaller.appspotmail.com Reported-by: syzbot+a9fb1457d720a55d6dc5@syzkaller.appspotmail.com Fixes: 7bc3e6e55acf ("proc: Use a list of inodes to flush from proc") Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
* | | | | | Merge tag 'io_uring-5.7-2020-04-09' of git://git.kernel.dk/linux-blockLinus Torvalds2020-04-103-173/+269
|\ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull io_uring fixes from Jens Axboe: "Here's a set of fixes that either weren't quite ready for the first, or came about from some intensive testing on memcached with 350K+ sockets. Summary: - Fixes for races or deadlocks around poll handling - Don't double account fixed files against RLIMIT_NOFILE - IORING_OP_OPENAT LFS fix - Poll retry handling (Bijan) - Missing finish_wait() for SQPOLL (Hillf) - Cleanup/split of io_kiocb alloc vs ctx references (Pavel) - Fixed file unregistration and init fixes (Xiaoguang) - Various little fixes (Xiaoguang, Pavel, Colin)" * tag 'io_uring-5.7-2020-04-09' of git://git.kernel.dk/linux-block: io_uring: punt final io_ring_ctx wait-and-free to workqueue io_uring: fix fs cleanup on cqe overflow io_uring: don't read user-shared sqe flags twice io_uring: remove req init from io_get_req() io_uring: alloc req only after getting sqe io_uring: simplify io_get_sqring io_uring: do not always copy iovec in io_req_map_rw() io_uring: ensure openat sets O_LARGEFILE if needed io_uring: initialize fixed_file_data lock io_uring: remove redundant variable pointer nxt and io_wq_assign_next call io_uring: fix ctx refcounting in io_submit_sqes() io_uring: process requests completed with -EAGAIN on poll list io_uring: remove bogus RLIMIT_NOFILE check in file registration io_uring: use io-wq manager as backup task if task is exiting io_uring: grab task reference for poll requests io_uring: retry poll if we got woken with non-matching mask io_uring: add missing finish_wait() in io_sq_thread() io_uring: refactor file register/unregister/update handling
| * | | | | | io_uring: punt final io_ring_ctx wait-and-free to workqueueJens Axboe2020-04-091-2/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We can't reliably wait in io_ring_ctx_wait_and_kill(), since the task_works list isn't ordered (in fact it's LIFO ordered). We could either fix this with a separate task_works list for io_uring work, or just punt the wait-and-free to async context. This ensures that task_work that comes in while we're shutting down is processed correctly. If we don't go async, we could have work past the fput() work for the ring that depends on work that won't be executed until after we're done with the wait-and-free. But as this operation is blocking, it'll never get a chance to run. This was reproduced with hundreds of thousands of sockets running memcached, haven't been able to reproduce this synthetically. Reported-by: Dan Melnic <dmm@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: fix fs cleanup on cqe overflowPavel Begunkov2020-04-091-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If completion queue overflow occurs, __io_cqring_fill_event() will update req->cflags, which is in a union with req->work and happens to be aliased to req->work.fs. Following io_free_req() -> io_req_work_drop_env() may get a bunch of different problems (miscount fs->users, segfault, etc) on cleaning @fs. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: don't read user-shared sqe flags twicePavel Begunkov2020-04-081-12/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Don't re-read userspace-shared sqe->flags, it can be exploited. sqe->flags are copied into req->flags in io_submit_sqe(), check them there instead. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: remove req init from io_get_req()Pavel Begunkov2020-04-081-26/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | io_get_req() do two different things: io_kiocb allocation and initialisation. Move init part out of it and rename into io_alloc_req(). It's simpler this way and also have better data locality. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: alloc req only after getting sqePavel Begunkov2020-04-081-15/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As io_get_sqe() split into 2 stage get/consume, get an sqe before allocating io_kiocb, so no free_req*() for a failure case is needed, and inline back __io_req_do_free(), which has only 1 user. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: simplify io_get_sqringPavel Begunkov2020-04-081-18/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make io_get_sqring() care only about sqes themselves, not initialising the io_kiocb. Also, split it into get + consume, that will be helpful in the future. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: do not always copy iovec in io_req_map_rw()Xiaoguang Wang2020-04-081-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In io_read_prep() or io_write_prep(), io_req_map_rw() takes struct io_async_rw's fast_iov as argument to call io_import_iovec(), and if io_import_iovec() uses struct io_async_rw's fast_iov as valid iovec array, later indeed io_req_map_rw() does not need to do the memcpy operation, because they are same pointers. Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: ensure openat sets O_LARGEFILE if neededJens Axboe2020-04-081-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | OPENAT2 correctly sets O_LARGEFILE if it has to, but that escaped the OPENAT opcode. Dmitry reports that his test case that compares openat() and IORING_OP_OPENAT sees failures on large files: *** sync openat openat succeeded sync write at offset 0 write succeeded sync write at offset 4294967296 write succeeded *** sync openat openat succeeded io_uring write at offset 0 write succeeded io_uring write at offset 4294967296 write succeeded *** io_uring openat openat succeeded sync write at offset 0 write succeeded sync write at offset 4294967296 write failed: File too large *** io_uring openat openat succeeded io_uring write at offset 0 write succeeded io_uring write at offset 4294967296 write failed: File too large Ensure we set O_LARGEFILE, if force_o_largefile() is true. Cc: stable@vger.kernel.org # v5.6 Fixes: 15b71abe7b52 ("io_uring: add support for IORING_OP_OPENAT") Reported-by: Dmitry Kadashev <dkadashev@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: initialize fixed_file_data lockXiaoguang Wang2020-04-071-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | syzbot reports below warning: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 1 PID: 7099 Comm: syz-executor897 Not tainted 5.6.0-next-20200406-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 assign_lock_key kernel/locking/lockdep.c:913 [inline] register_lock_class+0x1664/0x1760 kernel/locking/lockdep.c:1225 __lock_acquire+0x104/0x4e00 kernel/locking/lockdep.c:4223 lock_acquire+0x1f2/0x8f0 kernel/locking/lockdep.c:4923 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x8c/0xbf kernel/locking/spinlock.c:159 io_sqe_files_register fs/io_uring.c:6599 [inline] __io_uring_register+0x1fe8/0x2f00 fs/io_uring.c:8001 __do_sys_io_uring_register fs/io_uring.c:8081 [inline] __se_sys_io_uring_register fs/io_uring.c:8063 [inline] __x64_sys_io_uring_register+0x192/0x560 fs/io_uring.c:8063 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295 entry_SYSCALL_64_after_hwframe+0x49/0xb3 RIP: 0033:0x440289 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffff1bbf558 EFLAGS: 00000246 ORIG_RAX: 00000000000001ab RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000440289 RDX: 0000000020000280 RSI: 0000000000000002 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000000 R09: 00000000004002c8 R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000401b10 R13: 0000000000401ba0 R14: 0000000000000000 R15: 0000000000000000 Initialize struct fixed_file_data's lock to fix this issue. Reported-by: syzbot+e6eeca4a035da76b3065@syzkaller.appspotmail.com Fixes: 055895537302 ("io_uring: refactor file register/unregister/update handling") Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: remove redundant variable pointer nxt and io_wq_assign_next callColin Ian King2020-04-071-3/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | An earlier commit "io_uring: remove @nxt from handlers" removed the setting of pointer nxt and now it is always null, hence the non-null check and call to io_wq_assign_next is redundant and can be removed. Addresses-Coverity: ("'Constant' variable guard") Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: fix ctx refcounting in io_submit_sqes()Pavel Begunkov2020-04-051-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If io_get_req() fails, it drops a ref. Then, awhile keeping @submitted unmodified, io_submit_sqes() breaks the loop and puts @nr - @submitted refs. For each submitted req a ref is dropped in io_put_req() and friends. So, for @nr taken refs there will be (@nr - @submitted + @submitted + 1) dropped. Remove ctx refcounting from io_get_req(), that at the same time makes it clearer. Fixes: 2b85edfc0c90 ("io_uring: batch getting pcpu references") Cc: stable@vger.kernel.org # v5.6 Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: process requests completed with -EAGAIN on poll listBijan Mottahedeh2020-04-031-3/+26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A request that completes with an -EAGAIN result after it has been added to the poll list, will not be removed from that list in io_do_iopoll() because the f_op->iopoll() will not succeed for that request. Maintain a retryable local list similar to the done list, and explicity reissue requests with an -EAGAIN result. Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: remove bogus RLIMIT_NOFILE check in file registrationJens Axboe2020-04-031-7/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We already checked this limit when the file was opened, and we keep it open in the file table. Hence when we added unit_inflight to the count we want to register, we're doubly accounting these files. This results in -EMFILE for file registration, if we're at half the limit. Cc: stable@vger.kernel.org # v5.1+ Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: use io-wq manager as backup task if task is exitingJens Axboe2020-04-033-4/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the original task is (or has) exited, then the task work will not get queued properly. Allow for using the io-wq manager task to queue this work for execution, and ensure that the io-wq manager notices and runs this work if woken up (or exiting). Reported-by: Dan Melnic <dmm@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: grab task reference for poll requestsJens Axboe2020-04-031-12/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We can have a task exit if it's not the owner of the ring. Be safe and grab an actual reference to it, to avoid a potential use-after-free. Reported-by: Dan Melnic <dmm@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: retry poll if we got woken with non-matching maskJens Axboe2020-04-031-0/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we get woken and the poll doesn't match our mask, re-add the task to the poll waitqueue and try again instead of completing the request with a mask of 0. Reported-by: Dan Melnic <dmm@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: add missing finish_wait() in io_sq_thread()Hillf Danton2020-04-011-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add it to pair with prepare_to_wait() in an attempt to avoid anything weird in the field. Fixes: b41e98524e42 ("io_uring: add per-task callback handler") Reported-by: syzbot+0c3370f235b74b3cfd97@syzkaller.appspotmail.com Signed-off-by: Hillf Danton <hdanton@sina.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
| * | | | | | io_uring: refactor file register/unregister/update handlingXiaoguang Wang2020-03-311-80/+124
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While diving into io_uring fileset register/unregister/update codes, we found one bug in the fileset update handling. io_uring fileset update use a percpu_ref variable to check whether we can put the previously registered file, only when the refcnt of the perfcpu_ref variable reaches zero, can we safely put these files. But this doesn't work so well. If applications always issue requests continually, this perfcpu_ref will never have an chance to reach zero, and it'll always be in atomic mode, also will defeat the gains introduced by fileset register/unresiger/update feature, which are used to reduce the atomic operation overhead of fput/fget. To fix this issue, while applications do IORING_REGISTER_FILES or IORING_REGISTER_FILES_UPDATE operations, we allocate a new percpu_ref and kill the old percpu_ref, new requests will use the new percpu_ref. Once all previous old requests complete, old percpu_refs will be dropped and registered files will be put safely. Link: https://lore.kernel.org/io-uring/5a8dac33-4ca2-4847-b091-f7dcd3ad0ff3@linux.alibaba.com/T/#t Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
* | | | | | | Merge tag 'xfs-5.7-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linuxLinus Torvalds2020-04-1021-451/+512
|\ \ \ \ \ \ \ | |_|_|_|/ / / |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull more xfs updates from Darrick Wong: "As promised last week, this batch changes how xfs interacts with memory reclaim; how the log batches and throttles log items; how hard writes near ENOSPC will try to squeeze more space out of the filesystem; and hopefully fix the last of the umount hangs after a catastrophic failure. Summary: - Validate the realtime geometry in the superblock when mounting - Refactor a bunch of tricky flag handling in the log code - Flush the CIL more judiciously so that we don't wait until there are millions of log items consuming a lot of memory. - Throttle transaction commits to prevent the xfs frontend from flooding the CIL with too many log items. - Account metadata buffers correctly for memory reclaim. - Mark slabs properly for memory reclaim. These should help reclaim run more effectively when XFS is using a lot of memory. - Don't write a garbage log record at unmount time if we're trying to trigger summary counter recalculation at next mount. - Don't block the AIL on locked dquot/inode buffers; instead trigger its backoff mechanism to give the lock holder a chance to finish up. - Ratelimit writeback flushing when buffered writes encounter ENOSPC. - Other minor cleanups. - Make reflink a synchronous operation when the fs is mounted with wsync or sync, which means that now we force the log to disk to record the changes" * tag 'xfs-5.7-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits) xfs: reflink should force the log out if mounted with wsync xfs: factor out a new xfs_log_force_inode helper xfs: fix inode number overflow in ifree cluster helper xfs: remove redundant variable assignment in xfs_symlink() xfs: ratelimit inode flush on buffered write ENOSPC xfs: return locked status of inode buffer on xfsaild push xfs: trylock underlying buffer on dquot flush xfs: remove unnecessary ternary from xfs_create xfs: don't write a corrupt unmount record to force summary counter recalc xfs: factor inode lookup from xfs_ifree_cluster xfs: tail updates only need to occur when LSN changes xfs: factor common AIL item deletion code xfs: correctly acount for reclaimable slabs xfs: Improve metadata buffer reclaim accountability xfs: don't allow log IO to be throttled xfs: Throttle commits on delayed background CIL push xfs: Lower CIL flush limit for large logs xfs: remove some stale comments from the log code xfs: refactor unmount record writing xfs: merge xlog_commit_record with xlog_write_done ...
| * | | | | | xfs: reflink should force the log out if mounted with wsyncChristoph Hellwig2020-04-061-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Reflink should force the log out to disk if the filesystem was mounted with wsync, the same as most other operations in xfs. [Note: XFS_MOUNT_WSYNC is set when the admin mounts the filesystem with either the 'wsync' or 'sync' mount options, which effectively means that we're classifying reflink/dedupe as IO operations and making them synchronous when required.] Fixes: 3fc9f5e409319 ("xfs: remove xfs_reflink_remap_range") Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Brian Foster <bfoster@redhat.com> [darrick: add more to the changelog] Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
| * | | | | | xfs: factor out a new xfs_log_force_inode helperChristoph Hellwig2020-04-064-24/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Create a new helper to force the log up to the last LSN touching an inode. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
| * | | | | | xfs: fix inode number overflow in ifree cluster helperBrian Foster2020-04-021-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Qian Cai reports seemingly random buffer read verifier errors during filesystem writeback. This was isolated to a recent patch that factored out some inode cluster freeing code and happened to cast an unsigned inode number type to a signed value. If the inode number value overflows, we can skip marking in-core inodes associated with the underlying buffer stale at the time the physical inodes are freed. If such an inode happens to be dirty, xfsaild will eventually attempt to write it back over non-inode blocks. The invalidation of the underlying inode buffer causes writeback to read the buffer from disk. This fails the read verifier (preventing eventual corruption) if the buffer no longer looks like an inode cluster. Analysis by Dave Chinner. Fix up the helper to use the proper type for inode number values. Fixes: 5806165a6663 ("xfs: factor inode lookup from xfs_ifree_cluster") Reported-by: Qian Cai <cai@lca.pw> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
| * | | | | | xfs: remove redundant variable assignment in xfs_symlink()Kaixu Xia2020-03-311-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The variables 'udqp' and 'gdqp' have been initialized, so remove redundant variable assignment in xfs_symlink(). Signed-off-by: Kaixu Xia <kaixuxia@tencent.com> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Dave Chinner <dchinner@redhat.com Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
| * | | | | | xfs: ratelimit inode flush on buffered write ENOSPCDarrick J. Wong2020-03-312-0/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A customer reported rcu stalls and softlockup warnings on a computer with many CPU cores and many many more IO threads trying to write to a filesystem that is totally out of space. Subsequent analysis pointed to the many many IO threads calling xfs_flush_inodes -> sync_inodes_sb, which causes a lot of wb_writeback_work to be queued. The writeback worker spends so much time trying to wake the many many threads waiting for writeback completion that it trips the softlockup detector, and (in this case) the system automatically reboots. In addition, they complain that the lengthy xfs_flush_inodes scan traps all of those threads in uninterruptible sleep, which hampers their ability to kill the program or do anything else to escape the situation. If there's thousands of threads trying to write to files on a full filesystem, each of those threads will start separate copies of the inode flush scan. This is kind of pointless since we only need one scan, so rate limit the inode flush. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
| * | | | | | xfs: return locked status of inode buffer on xfsaild pushBrian Foster2020-03-281-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the inode buffer backing a particular inode is locked, xfs_iflush() returns -EAGAIN and xfs_inode_item_push() skips the inode. It still returns success to xfsaild, however, which bypasses the xfsaild backoff heuristic. Update xfs_inode_item_push() to return locked status if the inode buffer couldn't be locked. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-09 13:31:06 +0000