diff options
276 files changed, 6471 insertions, 5163 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX deleted file mode 100644 index 2754fe83f0d4..000000000000 --- a/Documentation/00-INDEX +++ /dev/null @@ -1,428 +0,0 @@ - -This is a brief list of all the files in ./linux/Documentation and what -they contain. If you add a documentation file, please list it here in -alphabetical order as well, or risk being hunted down like a rabid dog. -Please keep the descriptions small enough to fit on one line. - Thanks -- Paul G. - -Following translations are available on the WWW: - - - Japanese, maintained by the JF Project ([email protected]), at - http://linuxjf.sourceforge.jp/ - -00-INDEX - - this file. -ABI/ - - info on kernel <-> userspace ABI and relative interface stability. -CodingStyle - - nothing here, just a pointer to process/coding-style.rst. -DMA-API.txt - - DMA API, pci_ API & extensions for non-consistent memory machines. -DMA-API-HOWTO.txt - - Dynamic DMA mapping Guide -DMA-ISA-LPC.txt - - How to do DMA with ISA (and LPC) devices. -DMA-attributes.txt - - listing of the various possible attributes a DMA region can have -EDID/ - - directory with info on customizing EDID for broken gfx/displays. -IPMI.txt - - info on Linux Intelligent Platform Management Interface (IPMI) Driver. -IRQ-affinity.txt - - how to select which CPU(s) handle which interrupt events on SMP. -IRQ-domain.txt - - info on interrupt numbering and setting up IRQ domains. -IRQ.txt - - description of what an IRQ is. -Intel-IOMMU.txt - - basic info on the Intel IOMMU virtualization support. -Makefile - - It's not of interest for those who aren't touching the build system. -PCI/ - - info related to PCI drivers. -RCU/ - - directory with info on RCU (read-copy update). -SAK.txt - - info on Secure Attention Keys. -SM501.txt - - Silicon Motion SM501 multimedia companion chip -SubmittingPatches - - nothing here, just a pointer to process/coding-style.rst. -accounting/ - - documentation on accounting and taskstats. -acpi/ - - info on ACPI-specific hooks in the kernel. -admin-guide/ - - info related to Linux users and system admins. -aoe/ - - description of AoE (ATA over Ethernet) along with config examples. -arm/ - - directory with info about Linux on the ARM architecture. -arm64/ - - directory with info about Linux on the 64 bit ARM architecture. -auxdisplay/ - - misc. LCD driver documentation (cfag12864b, ks0108). -backlight/ - - directory with info on controlling backlights in flat panel displays -block/ - - info on the Block I/O (BIO) layer. -blockdev/ - - info on block devices & drivers -bt8xxgpio.txt - - info on how to modify a bt8xx video card for GPIO usage. -btmrvl.txt - - info on Marvell Bluetooth driver usage. -bus-devices/ - - directory with info on TI GPMC (General Purpose Memory Controller) -bus-virt-phys-mapping.txt - - how to access I/O mapped memory from within device drivers. -cdrom/ - - directory with information on the CD-ROM drivers that Linux has. -cgroup-v1/ - - cgroups v1 features, including cpusets and memory controller. -cma/ - - Continuous Memory Area (CMA) debugfs interface. -conf.py - - It's not of interest for those who aren't touching the build system. -connector/ - - docs on the netlink based userspace<->kernel space communication mod. -console/ - - documentation on Linux console drivers. -core-api/ - - documentation on kernel core components. -cpu-freq/ - - info on CPU frequency and voltage scaling. -cpu-hotplug.txt - - document describing CPU hotplug support in the Linux kernel. -cpu-load.txt - - document describing how CPU load statistics are collected. -cpuidle/ - - info on CPU_IDLE, CPU idle state management subsystem. -cputopology.txt - - documentation on how CPU topology info is exported via sysfs. -crc32.txt - - brief tutorial on CRC computation -crypto/ - - directory with info on the Crypto API. -dcdbas.txt - - information on the Dell Systems Management Base Driver. -debugging-modules.txt - - some notes on debugging modules after Linux 2.6.3. -debugging-via-ohci1394.txt - - how to use firewire like a hardware debugger memory reader. -dell_rbu.txt - - document demonstrating the use of the Dell Remote BIOS Update driver. -dev-tools/ - - directory with info on development tools for the kernel. -device-mapper/ - - directory with info on Device Mapper. -dmaengine/ - - the DMA engine and controller API guides. -devicetree/ - - directory with info on device tree files used by OF/PowerPC/ARM -digsig.txt - -info on the Digital Signature Verification API -dma-buf-sharing.txt - - the DMA Buffer Sharing API Guide -docutils.conf - - nothing here. Just a configuration file for docutils. -dontdiff - - file containing a list of files that should never be diff'ed. -driver-api/ - - the Linux driver implementer's API guide. -driver-model/ - - directory with info about Linux driver model. -early-userspace/ - - info about initramfs, klibc, and userspace early during boot. -efi-stub.txt - - How to use the EFI boot stub to bypass GRUB or elilo on EFI systems. -eisa.txt - - info on EISA bus support. -extcon/ - - directory with porting guide for Android kernel switch driver. -isa.txt - - info on EISA bus support. -fault-injection/ - - dir with docs about the fault injection capabilities infrastructure. -fb/ - - directory with info on the frame buffer graphics abstraction layer. -features/ - - status of feature implementation on different architectures. -filesystems/ - - info on the vfs and the various filesystems that Linux supports. -firmware_class/ - - request_firmware() hotplug interface info. -flexible-arrays.txt - - how to make use of flexible sized arrays in linux -fmc/ - - information about the FMC bus abstraction -fpga/ - - FPGA Manager Core. -futex-requeue-pi.txt - - info on requeueing of tasks from a non-PI futex to a PI futex -gcc-plugins.txt - - GCC plugin infrastructure. -gpio/ - - gpio related documentation -gpu/ - - directory with information on GPU driver developer's guide. -hid/ - - directory with information on human interface devices -highuid.txt - - notes on the change from 16 bit to 32 bit user/group IDs. -hwspinlock.txt - - hardware spinlock provides hardware assistance for synchronization -timers/ - - info on the timer related topics -hw_random.txt - - info on Linux support for random number generator in i8xx chipsets. -hwmon/ - - directory with docs on various hardware monitoring drivers. -i2c/ - - directory with info about the I2C bus/protocol (2 wire, kHz speed). -x86/i386/ - - directory with info about Linux on Intel 32 bit architecture. -ia64/ - - directory with info about Linux on Intel 64 bit architecture. -ide/ - - Information regarding the Enhanced IDE drive. -iio/ - - info on industrial IIO configfs support. -index.rst - - main index for the documentation at ReST format. -infiniband/ - - directory with documents concerning Linux InfiniBand support. -input/ - - info on Linux input device support. -intel_txt.txt - - info on intel Trusted Execution Technology (intel TXT). -io-mapping.txt - - description of io_mapping functions in linux/io-mapping.h -io_ordering.txt - - info on ordering I/O writes to memory-mapped addresses. -ioctl/ - - directory with documents describing various IOCTL calls. -iostats.txt - - info on I/O statistics Linux kernel provides. -irqflags-tracing.txt - - how to use the irq-flags tracing feature. -isapnp.txt - - info on Linux ISA Plug & Play support. -isdn/ - - directory with info on the Linux ISDN support, and supported cards. -kbuild/ - - directory with info about the kernel build process. -kdump/ - - directory with mini HowTo on getting the crash dump code to work. -doc-guide/ - - how to write and format reStructuredText kernel documentation -kernel-per-CPU-kthreads.txt - - List of all per-CPU kthreads and how they introduce jitter. -kobject.txt - - info of the kobject infrastructure of the Linux kernel. -kprobes.txt - - documents the kernel probes debugging feature. -kref.txt - - docs on adding reference counters (krefs) to kernel objects. -laptops/ - - directory with laptop related info and laptop driver documentation. -ldm.txt - - a brief description of LDM (Windows Dynamic Disks). -leds/ - - directory with info about LED handling under Linux. -livepatch/ - - info on kernel live patching. -locking/ - - directory with info about kernel locking primitives -lockup-watchdogs.txt - - info on soft and hard lockup detectors (aka nmi_watchdog). -logo.gif - - full colour GIF image of Linux logo (penguin - Tux). -logo.txt - - info on creator of above logo & site to get additional images from. -lsm.txt - - Linux Security Modules: General Security Hooks for Linux -lzo.txt - - kernel LZO decompressor input formats -m68k/ - - directory with info about Linux on Motorola 68k architecture. -mailbox.txt - - How to write drivers for the common mailbox framework (IPC). -md/ - - directory with info about Linux Software RAID -media/ - - info on media drivers: uAPI, kAPI and driver documentation. -memory-barriers.txt - - info on Linux kernel memory barriers. -memory-devices/ - - directory with info on parts like the Texas Instruments EMIF driver -memory-hotplug.txt - - Hotpluggable memory support, how to use and current status. -men-chameleon-bus.txt - - info on MEN chameleon bus. -mic/ - - Intel Many Integrated Core (MIC) architecture device driver. -mips/ - - directory with info about Linux on MIPS architecture. -misc-devices/ - - directory with info about devices using the misc dev subsystem -mmc/ - - directory with info about the MMC subsystem -mtd/ - - directory with info about memory technology devices (flash) -namespaces/ - - directory with various information about namespaces -netlabel/ - - directory with information on the NetLabel subsystem. -networking/ - - directory with info on various aspects of networking with Linux. -nfc/ - - directory relating info about Near Field Communications support. -nios2/ - - Linux on the Nios II architecture. -nommu-mmap.txt - - documentation about no-mmu memory mapping support. -numastat.txt - - info on how to read Numa policy hit/miss statistics in sysfs. -ntb.txt - - info on Non-Transparent Bridge (NTB) drivers. -nvdimm/ - - info on non-volatile devices. -nvmem/ - - info on non volatile memory framework. -output/ - - default directory where html/LaTeX/pdf files will be written. -padata.txt - - An introduction to the "padata" parallel execution API -parisc/ - - directory with info on using Linux on PA-RISC architecture. -parport-lowlevel.txt - - description and usage of the low level parallel port functions. -pcmcia/ - - info on the Linux PCMCIA driver. -percpu-rw-semaphore.txt - - RCU based read-write semaphore optimized for locking for reading -perf/ - - info about the APM X-Gene SoC Performance Monitoring Unit (PMU). -phy/ - - ino on Samsung USB 2.0 PHY adaptation layer. -phy.txt - - Description of the generic PHY framework. -pi-futex.txt - - documentation on lightweight priority inheritance futexes. -pinctrl.txt - - info on pinctrl subsystem and the PINMUX/PINCONF and drivers -platform/ - - List of supported hardware by compal and Dell laptop. -pnp.txt - - Linux Plug and Play documentation. -power/ - - directory with info on Linux PCI power management. -powerpc/ - - directory with info on using Linux with the PowerPC. -prctl/ - - directory with info on the priveledge control subsystem -preempt-locking.txt - - info on locking under a preemptive kernel. -process/ - - how to work with the mainline kernel development process. -pps/ - - directory with information on the pulse-per-second support -pti/ - - directory with info on Intel MID PTI. -ptp/ - - directory with info on support for IEEE 1588 PTP clocks in Linux. -pwm.txt - - info on the pulse width modulation driver subsystem -rapidio/ - - directory with info on RapidIO packet-based fabric interconnect -rbtree.txt - - info on what red-black trees are and what they are for. -remoteproc.txt - - info on how to handle remote processor (e.g. AMP) offloads/usage. -rfkill.txt - - info on the radio frequency kill switch subsystem/support. -robust-futex-ABI.txt - - documentation of the robust futex ABI. -robust-futexes.txt - - a description of what robust futexes are. -rpmsg.txt - - info on the Remote Processor Messaging (rpmsg) Framework -rtc.txt - - notes on how to use the Real Time Clock (aka CMOS clock) driver. -s390/ - - directory with info on using Linux on the IBM S390. -scheduler/ - - directory with info on the scheduler. -scsi/ - - directory with info on Linux scsi support. -security/ - - directory that contains security-related info -serial/ - - directory with info on the low level serial API. -sgi-ioc4.txt - - description of the SGI IOC4 PCI (multi function) device. -sh/ - - directory with info on porting Linux to a new architecture. -smsc_ece1099.txt - -info on the smsc Keyboard Scan Expansion/GPIO Expansion device. -sound/ - - directory with info on sound card support. -spi/ - - overview of Linux kernel Serial Peripheral Interface (SPI) support. -sphinx/ - - no documentation here, just files required by Sphinx toolchain. -sphinx-static/ - - no documentation here, just files required by Sphinx toolchain. -static-keys.txt - - info on how static keys allow debug code in hotpaths via patching -svga.txt - - short guide on selecting video modes at boot via VGA BIOS. -sync_file.txt - - Sync file API guide. -sysctl/ - - directory with info on the /proc/sys/* files. -target/ - - directory with info on generating TCM v4 fabric .ko modules -tee.txt - - info on the TEE subsystem and drivers -this_cpu_ops.txt - - List rationale behind and the way to use this_cpu operations. -thermal/ - - directory with information on managing thermal issues (CPU/temp) -trace/ - - directory with info on tracing technologies within linux -translations/ - - translations of this document from English to another language -unaligned-memory-access.txt - - info on how to avoid arch breaking unaligned memory access in code. -unshare.txt - - description of the Linux unshare system call. -usb/ - - directory with info regarding the Universal Serial Bus. -vfio.txt - - info on Virtual Function I/O used in guest/hypervisor instances. -video-output.txt - - sysfs class driver interface to enable/disable a video output device. -virtual/ - - directory with information on the various linux virtualizations. -vm/ - - directory with info on the Linux vm code. -w1/ - - directory with documents regarding the 1-wire (w1) subsystem. -watchdog/ - - how to auto-reboot Linux if it has "fallen and can't get up". ;-) -wimax/ - - directory with info about Intel Wireless Wimax Connections -core-api/workqueue.rst - - information on the Concurrency Managed Workqueue implementation -x86/x86_64/ - - directory with info on Linux support for AMD x86-64 (Hammer) machines. -xillybus.txt - - Overview and basic ui of xillybus driver -xtensa/ - - directory with documents relating to arch/xtensa port/implementation -xz.txt - - how to make use of the XZ data compression within linux kernel -zorro.txt - - info on writing drivers for Zorro bus devices found on Amigas. diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 94a24aedcdb2..3ac41774ad3c 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -121,7 +121,22 @@ What: /sys/fs/f2fs/<disk>/idle_interval Date: January 2016 Contact: "Jaegeuk Kim" <[email protected]> Description: - Controls the idle timing. + Controls the idle timing for all paths other than + discard and gc path. + +What: /sys/fs/f2fs/<disk>/discard_idle_interval +Date: September 2018 +Contact: "Chao Yu" <[email protected]> +Contact: "Sahitya Tummala" <[email protected]> +Description: + Controls the idle timing for discard path. + +What: /sys/fs/f2fs/<disk>/gc_idle_interval +Date: September 2018 +Contact: "Chao Yu" <[email protected]> +Contact: "Sahitya Tummala" <[email protected]> +Description: + Controls the idle timing for gc path. What: /sys/fs/f2fs/<disk>/iostat_enable Date: August 2017 diff --git a/Documentation/PCI/00-INDEX b/Documentation/PCI/00-INDEX deleted file mode 100644 index 206b1d5c1e71..000000000000 --- a/Documentation/PCI/00-INDEX +++ /dev/null @@ -1,26 +0,0 @@ -00-INDEX - - this file -acpi-info.txt - - info on how PCI host bridges are represented in ACPI -MSI-HOWTO.txt - - the Message Signaled Interrupts (MSI) Driver Guide HOWTO and FAQ. -PCIEBUS-HOWTO.txt - - a guide describing the PCI Express Port Bus driver -pci-error-recovery.txt - - info on PCI error recovery -pci-iov-howto.txt - - the PCI Express I/O Virtualization HOWTO -pci.txt - - info on the PCI subsystem for device driver authors -pcieaer-howto.txt - - the PCI Express Advanced Error Reporting Driver Guide HOWTO -endpoint/pci-endpoint.txt - - guide to add endpoint controller driver and endpoint function driver. -endpoint/pci-endpoint-cfs.txt - - guide to use configfs to configure the PCI endpoint function. -endpoint/pci-test-function.txt - - specification of *PCI test* function device. -endpoint/pci-test-howto.txt - - userguide for PCI endpoint test function. -endpoint/function/binding/ - - binding documentation for PCI endpoint function diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX deleted file mode 100644 index f46980c060aa..000000000000 --- a/Documentation/RCU/00-INDEX +++ /dev/null @@ -1,34 +0,0 @@ -00-INDEX - - This file -arrayRCU.txt - - Using RCU to Protect Read-Mostly Arrays -checklist.txt - - Review Checklist for RCU Patches -listRCU.txt - - Using RCU to Protect Read-Mostly Linked Lists -lockdep.txt - - RCU and lockdep checking -lockdep-splat.txt - - RCU Lockdep splats explained. -NMI-RCU.txt - - Using RCU to Protect Dynamic NMI Handlers -rcu_dereference.txt - - Proper care and feeding of return values from rcu_dereference() -rcubarrier.txt - - RCU and Unloadable Modules -rculist_nulls.txt - - RCU list primitives for use with SLAB_TYPESAFE_BY_RCU -rcuref.txt - - Reference-count design for elements of lists/arrays protected by RCU -rcu.txt - - RCU Concepts -RTFP.txt - - List of RCU papers (bibliography) going back to 1980. -stallwarn.txt - - RCU CPU stall warnings (module parameter rcu_cpu_stall_suppress) -torture.txt - - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST) -UP.txt - - RCU on Uniprocessor Systems -whatisRCU.txt - - What is RCU? diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt index 7d4ae110c2c9..721b3e426515 100644 --- a/Documentation/RCU/rcu.txt +++ b/Documentation/RCU/rcu.txt @@ -87,7 +87,3 @@ o Where can I find more information on RCU? See the RTFP.txt file in this directory. Or point your browser at http://www.rdrop.com/users/paulmck/RCU/. - -o What are all these files in this directory? - - See 00-INDEX for the list. diff --git a/Documentation/admin-guide/LSM/Yama.rst b/Documentation/admin-guide/LSM/Yama.rst index 13468ea696b7..d0a060de3973 100644 --- a/Documentation/admin-guide/LSM/Yama.rst +++ b/Documentation/admin-guide/LSM/Yama.rst @@ -64,8 +64,8 @@ The sysctl settings (writable only with ``CAP_SYS_PTRACE``) are: Using ``PTRACE_TRACEME`` is unchanged. 2 - admin-only attach: - only processes with ``CAP_SYS_PTRACE`` may use ptrace - with ``PTRACE_ATTACH``, or through children calling ``PTRACE_TRACEME``. + only processes with ``CAP_SYS_PTRACE`` may use ptrace, either with + ``PTRACE_ATTACH`` or through children calling ``PTRACE_TRACEME``. 3 - no attach: no processes may use ptrace with ``PTRACE_ATTACH`` nor via diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 15ea785b2dfa..0797eec76be1 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -51,8 +51,7 @@ Documentation - There are various README files in the Documentation/ subdirectory: these typically contain kernel-specific installation notes for some - drivers for example. See Documentation/00-INDEX for a list of what - is contained in each file. Please read the + drivers for example. Please read the :ref:`Documentation/process/changes.rst <changes>` file, as it contains information about the problems, which may result by upgrading your kernel. diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst new file mode 100644 index 000000000000..e506d3dae510 --- /dev/null +++ b/Documentation/admin-guide/ext4.rst @@ -0,0 +1,574 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +ext4 General Information +======================== + +Ext4 is an advanced level of the ext3 filesystem which incorporates +scalability and reliability enhancements for supporting large filesystems +(64 bit) in keeping with increasing disk capacities and state-of-the-art +feature requirements. + +Mailing list: [email protected] +Web site: http://ext4.wiki.kernel.org + + +Quick usage instructions +======================== + +Note: More extensive information for getting started with ext4 can be +found at the ext4 wiki site at the URL: +http://ext4.wiki.kernel.org/index.php/Ext4_Howto + + - The latest version of e2fsprogs can be found at: + + https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/ + + or + + http://sourceforge.net/project/showfiles.php?group_id=2406 + + or grab the latest git repository from: + + https://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git + + - Create a new filesystem using the ext4 filesystem type: + + # mke2fs -t ext4 /dev/hda1 + + Or to configure an existing ext3 filesystem to support extents: + + # tune2fs -O extents /dev/hda1 + + If the filesystem was created with 128 byte inodes, it can be + converted to use 256 byte for greater efficiency via: + + # tune2fs -I 256 /dev/hda1 + + - Mounting: + + # mount -t ext4 /dev/hda1 /wherever + + - When comparing performance with other filesystems, it's always + important to try multiple workloads; very often a subtle change in a + workload parameter can completely change the ranking of which + filesystems do well compared to others. When comparing versus ext3, + note that ext4 enables write barriers by default, while ext3 does + not enable write barriers by default. So it is useful to use + explicitly specify whether barriers are enabled or not when via the + '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems + for a fair comparison. When tuning ext3 for best benchmark numbers, + it is often worthwhile to try changing the data journaling mode; '-o + data=writeback' can be faster for some workloads. (Note however that + running mounted with data=writeback can potentially leave stale data + exposed in recently written files in case of an unclean shutdown, + which could be a security exposure in some situations.) Configuring + the filesystem with a large journal can also be helpful for + metadata-intensive workloads. + +Features +======== + +Currently Available +------------------- + +* ability to use filesystems > 16TB (e2fsprogs support not available yet) +* extent format reduces metadata overhead (RAM, IO for access, transactions) +* extent format more robust in face of on-disk corruption due to magics, +* internal redundancy in tree +* improved file allocation (multi-block alloc) +* lift 32000 subdirectory limit imposed by i_links_count[1] +* nsec timestamps for mtime, atime, ctime, create time +* inode version field on disk (NFSv4, Lustre) +* reduced e2fsck time via uninit_bg feature +* journal checksumming for robustness, performance +* persistent file preallocation (e.g for streaming media, databases) +* ability to pack bitmaps and inode tables into larger virtual groups via the + flex_bg feature +* large file support +* inode allocation using large virtual block groups via flex_bg +* delayed allocation +* large block (up to pagesize) support +* efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force + the ordering) + +[1] Filesystems with a block size of 1k may see a limit imposed by the +directory hash tree having a maximum depth of two. + +Options +======= + +When mounting an ext4 filesystem, the following option are accepted: +(*) == default + + ro + Mount filesystem read only. Note that ext4 will replay the journal (and + thus write to the partition) even when mounted "read only". The mount + options "ro,noload" can be used to prevent writes to the filesystem. + + journal_checksum + Enable checksumming of the journal transactions. This will allow the + recovery code in e2fsck and the kernel to detect corruption in the + kernel. It is a compatible change and will be ignored by older + kernels. + + journal_async_commit + Commit block can be written to disk without waiting for descriptor + blocks. If enabled older kernels cannot mount the device. This will + enable 'journal_checksum' internally. + + journal_path=path, journal_dev=devnum + When the external journal device's major/minor numbers have changed, + these options allow the user to specify the new journal location. The + journal device is identified through either its new major/minor numbers + encoded in devnum, or via a path to the device. + + norecovery, noload + Don't load the journal on mounting. Note that if the filesystem was + not unmounted cleanly, skipping the journal replay will lead to the + filesystem containing inconsistencies that can lead to any number of + problems. + + data=journal + All data are committed into the journal prior to being written into the + main file system. Enabling this mode will disable delayed allocation + and O_DIRECT support. + + data=ordered (*) + All data are forced directly out to the main file system prior to its + metadata being committed to the journal. + + data=writeback + Data ordering is not preserved, data may be written into the main file + system after its metadata has been committed to the journal. + + commit=nrsec (*) + Ext4 can be told to sync all its data and metadata every 'nrsec' + seconds. The default value is 5 seconds. This means that if you lose + your power, you will lose as much as the latest 5 seconds of work (your + filesystem will not be damaged though, thanks to the journaling). This + default value (or any low value) will hurt performance, but it's good + for data-safety. Setting it to 0 will have the same effect as leaving + it at the default (5 seconds). Setting it to very large values will + improve performance. + + barrier=<0|1(*)>, barrier(*), nobarrier + This enables/disables the use of write barriers in the jbd code. + barrier=0 disables, barrier=1 enables. This also requires an IO stack + which can support barriers, and if jbd gets an error on a barrier + write, it will disable again with a warning. Write barriers enforce + proper on-disk ordering of journal commits, making volatile disk write + caches safe to use, at some performance penalty. If your disks are + battery-backed in one way or another, disabling barriers may safely + improve performance. The mount options "barrier" and "nobarrier" can + also be used to enable or disable barriers, for consistency with other + ext4 mount options. + + inode_readahead_blks=n + This tuning parameter controls the maximum number of inode table blocks + that ext4's inode table readahead algorithm will pre-read into the + buffer cache. The default value is 32 blocks. + + nouser_xattr + Disables Extended User Attributes. See the attr(5) manual page for + more information about extended attributes. + + noacl + This option disables POSIX Access Control List support. If ACL support + is enabled in the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL + is enabled by default on mount. See the acl(5) manual page for more + information about acl. + + bsddf (*) + Make 'df' act like BSD. + + minixdf + Make 'df' act like Minix. + + debug + Extra debugging information is sent to syslog. + + abort + Simulate the effects of calling ext4_abort() for debugging purposes. + This is normally used while remounting a filesystem which is already + mounted. + + errors=remount-ro + Remount the filesystem read-only on an error. + + errors=continue + Keep going on a filesystem error. + + errors=panic + Panic and halt the machine if an error occurs. (These mount options + override the errors behavior specified in the superblock, which can be + configured using tune2fs) + + data_err=ignore(*) + Just print an error message if an error occurs in a file data buffer in + ordered mode. + data_err=abort + Abort the journal if an error occurs in a file data buffer in ordered + mode. + + grpid | bsdgroups + New objects have the group ID of their parent. + + nogrpid (*) | sysvgroups + New objects have the group ID of their creator. + + resgid=n + The group ID which may use the reserved blocks. + + resuid=n + The user ID which may use the reserved blocks. + + sb= + Use alternate superblock at this location. + + quota, noquota, grpquota, usrquota + These options are ignored by the filesystem. They are used only by + quota tools to recognize volumes where quota should be turned on. See + documentation in the quota-tools package for more details + (http://sourceforge.net/projects/linuxquota). + + jqfmt=<quota type>, usrjquota=<file>, grpjquota=<file> + These options tell filesystem details about quota so that quota + information can be properly updated during journal replay. They replace + the above quota options. See documentation in the quota-tools package + for more details (http://sourceforge.net/projects/linuxquota). + + stripe=n + Number of filesystem blocks that mballoc will try to use for allocation + size and alignment. For RAID5/6 systems this should be the number of + data disks * RAID chunk size in file system blocks. + + delalloc (*) + Defer block allocation until just before ext4 writes out the block(s) + in question. This allows ext4 to better allocation decisions more + efficiently. + + nodelalloc + Disable delayed allocation. Blocks are allocated when the data is + copied from userspace to the page cache, either via the write(2) system + call or when an mmap'ed page which was previously unallocated is + written for the first time. + + max_batch_time=usec + Maximum amount of time ext4 should wait for additional filesystem + operations to be batch together with a synchronous write operation. + Since a synchronous write operation is going to force a commit and then + a wait for the I/O complete, it doesn't cost much, and can be a huge + throughput win, we wait for a small amount of time to see if any other + transactions can piggyback on the synchronous write. The algorithm + used is designed to automatically tune for the speed of the disk, by + measuring the amount of time (on average) that it takes to finish + committing a transaction. Call this time the "commit time". If the + time that the transaction has been running is less than the commit + time, ext4 will try sleeping for the commit time to see if other + operations will join the transaction. The commit time is capped by + the max_batch_time, which defaults to 15000us (15ms). This + optimization can be turned off entirely by setting max_batch_time to 0. + + min_batch_time=usec + This parameter sets the commit time (as described above) to be at least + min_batch_time. It defaults to zero microseconds. Increasing this + parameter may improve the throughput of multi-threaded, synchronous + workloads on very fast disks, at the cost of increasing latency. + + journal_ioprio=prio + The I/O priority (from 0 to 7, where 0 is the highest priority) which + should be used for I/O operations submitted by kjournald2 during a + commit operation. This defaults to 3, which is a slightly higher + priority than the default I/O priority. + + auto_da_alloc(*), noauto_da_alloc + Many broken applications don't use fsync() when replacing existing + files via patterns such as fd = open("foo.new")/write(fd,..)/close(fd)/ + rename("foo.new", "foo"), or worse yet, fd = open("foo", + O_TRUNC)/write(fd,..)/close(fd). If auto_da_alloc is enabled, ext4 + will detect the replace-via-rename and replace-via-truncate patterns + and force that any delayed allocation blocks are allocated such that at + the next journal commit, in the default data=ordered mode, the data + blocks of the new file are forced to disk before the rename() operation + is committed. This provides roughly the same level of guarantees as + ext3, and avoids the "zero-length" problem that can happen when a + system crashes before the delayed allocation blocks are forced to disk. + + noinit_itable + Do not initialize any uninitialized inode table blocks in the + background. This feature may be used by installation CD's so that the + install process can complete as quickly as possible; the inode table + initialization process would then be deferred until the next time the + file system is unmounted. + + init_itable=n + The lazy itable init code will wait n times the number of milliseconds + it took to zero out the previous block group's inode table. This + minimizes the impact on the system performance while file system's + inode table is being initialized. + + discard, nodiscard(*) + Controls whether ext4 should issue discard/TRIM commands to the + underlying block device when blocks are freed. This is useful for SSD + devices and sparse/thinly-provisioned LUNs, but it is off by default + until sufficient testing has been done. + + nouid32 + Disables 32-bit UIDs and GIDs. This is for interoperability with + older kernels which only store and expect 16-bit values. + + block_validity(*), noblock_validity + These options enable or disable the in-kernel facility for tracking + filesystem metadata blocks within internal data structures. This + allows multi- block allocator and other routines to notice bugs or + corrupted allocation bitmaps which cause blocks to be allocated which + overlap with filesystem metadata blocks. + + dioread_lock, dioread_nolock + Controls whether or not ext4 should use the DIO read locking. If the + dioread_nolock option is specified ext4 will allocate uninitialized + extent before buffer write and convert the extent to initialized after + IO completes. This approach allows ext4 code to avoid using inode + mutex, which improves scalability on high speed storages. However this + does not work with data journaling and dioread_nolock option will be + ignored with kernel warning. Note that dioread_nolock code path is only + used for extent-based files. Because of the restrictions this options + comprises it is off by default (e.g. dioread_lock). + + max_dir_size_kb=n + This limits the size of directories so that any attempt to expand them + beyond the specified limit in kilobytes will cause an ENOSPC error. + This is useful in memory constrained environments, where a very large + directory can cause severe performance problems or even provoke the Out + Of Memory killer. (For example, if there is only 512mb memory + available, a 176mb directory may seriously cramp the system's style.) + + i_version + Enable 64-bit inode version support. This option is off by default. + + dax + Use direct access (no page cache). See + Documentation/filesystems/dax.txt. Note that this option is + incompatible with data=journal. + +Data Mode +========= +There are 3 different data modes: + +* writeback mode + + In data=writeback mode, ext4 does not journal data at all. This mode provides + a similar level of journaling as that of XFS, JFS, and ReiserFS in its default + mode - metadata journaling. A crash+recovery can cause incorrect data to + appear in files which were written shortly before the crash. This mode will + typically provide the best ext4 performance. + +* ordered mode + + In data=ordered mode, ext4 only officially journals metadata, but it logically + groups metadata information related to data changes with the data blocks into + a single unit called a transaction. When it's time to write the new metadata + out to disk, the associated data blocks are written first. In general, this + mode performs slightly slower than writeback but significantly faster than + journal mode. + +* journal mode + + data=journal mode provides full data and metadata journaling. All new data is + written to the journal first, and then to its final location. In the event of + a crash, the journal can be replayed, bringing both data and metadata into a + consistent state. This mode is the slowest except when data needs to be read + from and written to disk at the same time where it outperforms all others + modes. Enabling this mode will disable delayed allocation and O_DIRECT + support. + +/proc entries +============= + +Information about mounted ext4 file systems can be found in +/proc/fs/ext4. Each mounted filesystem will have a directory in +/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or +/proc/fs/ext4/dm-0). The files in each per-device directory are shown +in table below. + +Files in /proc/fs/ext4/<devname> + + mb_groups + details of multiblock allocator buddy cache of free blocks + +/sys entries +============ + +Information about mounted ext4 file systems can be found in +/sys/fs/ext4. Each mounted filesystem will have a directory in +/sys/fs/ext4 based on its device name (i.e., /sys/fs/ext4/hdc or +/sys/fs/ext4/dm-0). The files in each per-device directory are shown +in table below. + +Files in /sys/fs/ext4/<devname>: + +(see also Documentation/ABI/testing/sysfs-fs-ext4) + + delayed_allocation_blocks + This file is read-only and shows the number of blocks that are dirty in + the page cache, but which do not have their location in the filesystem + allocated yet. + + inode_goal + Tuning parameter which (if non-zero) controls the goal inode used by + the inode allocator in preference to all other allocation heuristics. + This is intended for debugging use only, and should be 0 on production + systems. + + inode_readahead_blks + Tuning parameter which controls the maximum number of inode table + blocks that ext4's inode table readahead algorithm will pre-read into + the buffer cache. + + lifetime_write_kbytes + This file is read-only and shows the number of kilobytes of data that + have been written to this filesystem since it was created. + + max_writeback_mb_bump + The maximum number of megabytes the writeback code will try to write + out before move on to another inode. + + mb_group_prealloc + The multiblock allocator will round up allocation requests to a + multiple of this tuning parameter if the stripe size is not set in the + ext4 superblock + + mb_max_to_scan + The maximum number of extents the multiblock allocator will search to + find the best extent. + + mb_min_to_scan + The minimum number of extents the multiblock allocator will search to + find the best extent. + + mb_order2_req + Tuning parameter which controls the minimum size for requests (as a + power of 2) where the buddy cache is used. + + mb_stats + Controls whether the multiblock allocator should collect statistics, + which are shown during the unmount. 1 means to collect statistics, 0 + means not to collect statistics. + + mb_stream_req + Files which have fewer blocks than this tunable parameter will have + their blocks allocated out of a block group specific preallocation + pool, so that small files are packed closely together. Each large file + will have its blocks allocated out of its own unique preallocation + pool. + + session_write_kbytes + This file is read-only and shows the number of kilobytes of data that + have been written to this filesystem since it was mounted. + + reserved_clusters + This is RW file and contains number of reserved clusters in the file + system which will be used in the specific situations to avoid costly + zeroout, unexpected ENOSPC, or possible data loss. The default is 2% or + 4096 clusters, whichever is smaller and this can be changed however it + can never exceed number of clusters in the file system. If there is not + enough space for the reserved space when mounting the file mount will + _not_ fail. + +Ioctls +====== + +There is some Ext4 specific functionality which can be accessed by applications +through the system call interfaces. The list of all Ext4 specific ioctls are +shown in the table below. + +Table of Ext4 specific ioctls + + EXT4_IOC_GETFLAGS + Get additional attributes associated with inode. The ioctl argument is + an integer bitfield, with bit values described in ext4.h. This ioctl is + an alias for FS_IOC_GETFLAGS. + + EXT4_IOC_SETFLAGS + Set additional attributes associated with inode. The ioctl argument is + an integer bitfield, with bit values described in ext4.h. This ioctl is + an alias for FS_IOC_SETFLAGS. + + EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD + Get the inode i_generation number stored for each inode. The + i_generation number is normally changed only when new inode is created + and it is particularly useful for network filesystems. The '_OLD' + version of this ioctl is an alias for FS_IOC_GETVERSION. + + EXT4_IOC_SETVERSION, EXT4_IOC_SETVERSION_OLD + Set the inode i_generation number stored for each inode. The '_OLD' + version of this ioctl is an alias for FS_IOC_SETVERSION. + + EXT4_IOC_GROUP_EXTEND + This ioctl has the same purpose as the resize mount option. It allows + to resize filesystem to the end of the last existing block group, + further resize has to be done with resize2fs, either online, or + offline. The argument points to the unsigned logn number representing + the filesystem new block count. + + EXT4_IOC_MOVE_EXT + Move the block extents from orig_fd (the one this ioctl is pointing to) + to the donor_fd (the one specified in move_extent structure passed as + an argument to this ioctl). Then, exchange inode metadata between + orig_fd and donor_fd. This is especially useful for online + defragmentation, because the allocator has the opportunity to allocate + moved blocks better, ideally into one contiguous extent. + + EXT4_IOC_GROUP_ADD + Add a new group descriptor to an existing or new group descriptor + block. The new group descriptor is described by ext4_new_group_input + structure, which is passed as an argument to this ioctl. This is + especially useful in conjunction with EXT4_IOC_GROUP_EXTEND, which + allows online resize of the filesystem to the end of the last existing + block group. Those two ioctls combined is used in userspace online + resize tool (e.g. resize2fs). + + EXT4_IOC_MIGRATE + This ioctl operates on the filesystem itself. It converts (migrates) + ext3 indirect block mapped inode to ext4 extent mapped inode by walking + through indirect block mapping of the original inode and converting + contiguous block ranges into ext4 extents of the temporary inode. Then, + inodes are swapped. This ioctl might help, when migrating from ext3 to + ext4 filesystem, however suggestion is to create fresh ext4 filesystem + and copy data from the backup. Note, that filesystem has to support + extents for this ioctl to work. + + EXT4_IOC_ALLOC_DA_BLKS + Force all of the delay allocated blocks to be allocated to preserve + application-expected ext3 behaviour. Note that this will also start + triggering a write of the data blocks, but this behaviour may change in + the future as it is not necessary and has been done this way only for + sake of simplicity. + + EXT4_IOC_RESIZE_FS + Resize the filesystem to a new size. The number of blocks of resized + filesystem is passed in via 64 bit integer argument. The kernel + allocates bitmaps and inode table, the userspace tool thus just passes + the new number of blocks. + + EXT4_IOC_SWAP_BOOT + Swap i_blocks and associated attributes (like i_blocks, i_size, + i_flags, ...) from the specified inode with inode EXT4_BOOT_LOADER_INO + (#5). This is typically used to store a boot loader in a secure part of + the filesystem, where it can't be changed by a normal user by accident. + The data blocks of the previous boot loader will be associated with the + given inode. + +References +========== + +kernel source: <file:fs/ext4/> + <file:fs/jbd2/> + +programs: http://e2fsprogs.sourceforge.net/ + +useful links: http://fedoraproject.org/wiki/ext3-devel + http://www.bullopensource.org/ext4/ + http://ext4.wiki.kernel.org/index.php/Main_Page + http://fedoraproject.org/wiki/Features/Ext4 diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index 0873685bab0f..965745d5fb9a 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -71,6 +71,7 @@ configure specific aspects of kernel behavior to your liking. java ras bcache + ext4 pm/index thunderbolt LSM/index diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 4cdcd1a1bbc3..e129cd8a6dcc 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1764,7 +1764,7 @@ Format: { "0" | "1" } 0 - Use IOMMU translation for DMA. 1 - Bypass the IOMMU for DMA. - unset - Use IOMMU translation for DMA. + unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. io7= [HW] IO7 for Marvel based alpha systems See comment before marvel_specify_io7 in diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst index bae52b845de0..b85dd80510b0 100644 --- a/Documentation/admin-guide/l1tf.rst +++ b/Documentation/admin-guide/l1tf.rst @@ -553,7 +553,7 @@ When nested virtualization is in use, three operating systems are involved: the bare metal hypervisor, the nested hypervisor and the nested virtual machine. VMENTER operations from the nested hypervisor into the nested guest will always be processed by the bare metal hypervisor. If KVM is the -bare metal hypervisor it wiil: +bare metal hypervisor it will: - Flush the L1D cache on every switch from the nested hypervisor to the nested virtual machine, so that the nested hypervisor's secrets are not diff --git a/Documentation/admin-guide/mm/index.rst b/Documentation/admin-guide/mm/index.rst index ceead68c2df7..8edb35f11317 100644 --- a/Documentation/admin-guide/mm/index.rst +++ b/Documentation/admin-guide/mm/index.rst @@ -29,6 +29,7 @@ the Linux memory management. hugetlbpage idle_page_tracking ksm + memory-hotplug numa_memory_policy pagemap soft-dirty diff --git a/Documentation/memory-hotplug.txt b/Documentation/admin-guide/mm/memory-hotplug.rst index 7f49ebf3ddb2..25157aec5b31 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -1,3 +1,5 @@ +.. _admin_guide_memory_hotplug: + ============== Memory Hotplug ============== @@ -9,39 +11,19 @@ This document is about memory hotplug including how-to-use and current status. Because Memory Hotplug is still under development, contents of this text will be changed often. -.. CONTENTS - - 1. Introduction - 1.1 purpose of memory hotplug - 1.2. Phases of memory hotplug - 1.3. Unit of Memory online/offline operation - 2. Kernel Configuration - 3. sysfs files for memory hotplug - 4. Physical memory hot-add phase - 4.1 Hardware(Firmware) Support - 4.2 Notify memory hot-add event by hand - 5. Logical Memory hot-add phase - 5.1. State of memory - 5.2. How to online memory - 6. Logical memory remove - 6.1 Memory offline and ZONE_MOVABLE - 6.2. How to offline memory - 7. Physical memory remove - 8. Memory hotplug event notifier - 9. Future Work List - +.. contents:: :local: .. note:: (1) x86_64's has special implementation for memory hotplug. This text does not describe it. - (2) This text assumes that sysfs is mounted at /sys. + (2) This text assumes that sysfs is mounted at ``/sys``. Introduction ============ -purpose of memory hotplug +Purpose of memory hotplug ------------------------- Memory Hotplug allows users to increase/decrease the amount of memory. @@ -57,7 +39,6 @@ hardware which supports memory power management. Linux memory hotplug is designed for both purpose. - Phases of memory hotplug ------------------------ @@ -92,7 +73,6 @@ phase by hand. (However, if you writes udev's hotplug scripts for memory hotplug, these phases can be execute in seamless way.) - Unit of Memory online/offline operation --------------------------------------- @@ -107,10 +87,9 @@ unit upon which memory online/offline operations are to be performed. The default size of a memory block is the same as memory section size unless an architecture specifies otherwise. (see :ref:`memory_hotplug_sysfs_files`.) -To determine the size (in bytes) of a memory block please read this file: - -/sys/devices/system/memory/block_size_bytes +To determine the size (in bytes) of a memory block please read this file:: + /sys/devices/system/memory/block_size_bytes Kernel Configuration ==================== @@ -119,22 +98,22 @@ To use memory hotplug feature, kernel must be compiled with following config options. - For all memory hotplug: - - Memory model -> Sparse Memory (CONFIG_SPARSEMEM) - - Allow for memory hot-add (CONFIG_MEMORY_HOTPLUG) + - Memory model -> Sparse Memory (``CONFIG_SPARSEMEM``) + - Allow for memory hot-add (``CONFIG_MEMORY_HOTPLUG``) - To enable memory removal, the following are also necessary: - - Allow for memory hot remove (CONFIG_MEMORY_HOTREMOVE) - - Page Migration (CONFIG_MIGRATION) + - Allow for memory hot remove (``CONFIG_MEMORY_HOTREMOVE``) + - Page Migration (``CONFIG_MIGRATION``) - For ACPI memory hotplug, the following are also necessary: - - Memory hotplug (under ACPI Support menu) (CONFIG_ACPI_HOTPLUG_MEMORY) + - Memory hotplug (under ACPI Support menu) (``CONFIG_ACPI_HOTPLUG_MEMORY``) - This option can be kernel module. - As a related configuration, if your box has a feature of NUMA-node hotplug via ACPI, then this option is necessary too. - ACPI0004,PNP0A05 and PNP0A06 Container Driver (under ACPI Support menu) - (CONFIG_ACPI_CONTAINER). + (``CONFIG_ACPI_CONTAINER``). This option can be kernel module too. @@ -145,10 +124,11 @@ sysfs files for memory hotplug ============================== All memory blocks have their device information in sysfs. Each memory block -is described under /sys/devices/system/memory as: +is described under ``/sys/devices/system/memory`` as:: /sys/devices/system/memory/memoryXXX - (XXX is the memory block id.) + +where XXX is the memory block id. For the memory block covered by the sysfs directory. It is expected that all memory sections in this range are present and no memory holes exist in the @@ -157,7 +137,7 @@ the existence of one should not affect the hotplug capabilities of the memory block. For example, assume 1GiB memory block size. A device for a memory starting at -0x100000000 is /sys/device/system/memory/memory4:: +0x100000000 is ``/sys/device/system/memory/memory4``:: (0x100000000 / 1Gib = 4) @@ -165,11 +145,11 @@ This device covers address range [0x100000000 ... 0x140000000) Under each memory block, you can see 5 files: -- /sys/devices/system/memory/memoryXXX/phys_index -- /sys/devices/system/memory/memoryXXX/phys_device -- /sys/devices/system/memory/memoryXXX/state -- /sys/devices/system/memory/memoryXXX/removable -- /sys/devices/system/memory/memoryXXX/valid_zones +- ``/sys/devices/system/memory/memoryXXX/phys_index`` +- ``/sys/devices/system/memory/memoryXXX/phys_device`` +- ``/sys/devices/system/memory/memoryXXX/state`` +- ``/sys/devices/system/memory/memoryXXX/removable`` +- ``/sys/devices/system/memory/memoryXXX/valid_zones`` =================== ============================================================ ``phys_index`` read-only and contains memory block id, same as XXX. @@ -207,13 +187,15 @@ Under each memory block, you can see 5 files: These directories/files appear after physical memory hotplug phase. If CONFIG_NUMA is enabled the memoryXXX/ directories can also be accessed -via symbolic links located in the /sys/devices/system/node/node* directories. +via symbolic links located in the ``/sys/devices/system/node/node*`` directories. + +For example:: -For example: -/sys/devices/system/node/node0/memory9 -> ../../memory/memory9 + /sys/devices/system/node/node0/memory9 -> ../../memory/memory9 -A backlink will also be created: -/sys/devices/system/memory/memory9/node0 -> ../../node/node0 +A backlink will also be created:: + + /sys/devices/system/memory/memory9/node0 -> ../../node/node0 .. _memory_hotplug_physical_mem: @@ -240,7 +222,6 @@ If firmware supports NUMA-node hotplug, and defines an object _HID "ACPI0004", calls hotplug code for all of objects which are defined in it. If memory device is found, memory hotplug code will be called. - Notify memory hot-add event by hand ----------------------------------- @@ -251,8 +232,9 @@ CONFIG_ARCH_MEMORY_PROBE and can be configured on powerpc, sh, and x86 if hotplug is supported, although for x86 this should be handled by ACPI notification. -Probe interface is located at -/sys/devices/system/memory/probe +Probe interface is located at:: + + /sys/devices/system/memory/probe You can tell the physical address of new memory to the kernel by:: @@ -263,7 +245,6 @@ memory_block_size] memory range is hot-added. In this case, hotplug script is not called (in current implementation). You'll have to online memory by yourself. Please see :ref:`memory_hotplug_how_to_online_memory`. - Logical Memory hot-add phase ============================ @@ -301,7 +282,7 @@ This sets a global policy and impacts all memory blocks that will subsequently be hotplugged. Currently offline blocks keep their state. It is possible, under certain circumstances, that some memory blocks will be added but will fail to online. User space tools can check their "state" files -(/sys/devices/system/memory/memoryXXX/state) and try to online them manually. +(``/sys/devices/system/memory/memoryXXX/state``) and try to online them manually. If the automatic onlining wasn't requested, failed, or some memory block was offlined it is possible to change the individual block's state by writing to the @@ -334,8 +315,6 @@ available memory will be increased. This may be changed in future. - - Logical memory remove ===================== @@ -413,88 +392,6 @@ Need more implementation yet.... - Notification completion of remove works by OS to firmware. - Guard from remove if not yet. -Memory hotplug event notifier -============================= - -Hotplugging events are sent to a notification queue. - -There are six types of notification defined in include/linux/memory.h: - -MEM_GOING_ONLINE - Generated before new memory becomes available in order to be able to - prepare subsystems to handle memory. The page allocator is still unable - to allocate from the new memory. - -MEM_CANCEL_ONLINE - Generated if MEMORY_GOING_ONLINE fails. - -MEM_ONLINE - Generated when memory has successfully brought online. The callback may - allocate pages from the new memory. - -MEM_GOING_OFFLINE - Generated to begin the process of offlining memory. Allocations are no - longer possible from the memory but some of the memory to be offlined - is still in use. The callback can be used to free memory known to a - subsystem from the indicated memory block. - -MEM_CANCEL_OFFLINE - Generated if MEMORY_GOING_OFFLINE fails. Memory is available again from - the memory block that we attempted to offline. - -MEM_OFFLINE - Generated after offlining memory is complete. - -A callback routine can be registered by calling:: - - hotplug_memory_notifier(callback_func, priority) - -Callback functions with higher values of priority are called before callback -functions with lower values. - -A callback function must have the following prototype:: - - int callback_func( - struct notifier_block *self, unsigned long action, void *arg); - -The first argument of the callback function (self) is a pointer to the block -of the notifier chain that points to the callback function itself. -The second argument (action) is one of the event types described above. -The third argument (arg) passes a pointer of struct memory_notify:: - - struct memory_notify { - unsigned long start_pfn; - unsigned long nr_pages; - int status_change_nid_normal; - int status_change_nid_high; - int status_change_nid; - } - -- start_pfn is start_pfn of online/offline memory. -- nr_pages is # of pages of online/offline memory. -- status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask - is (will be) set/clear, if this is -1, then nodemask status is not changed. -- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask - is (will be) set/clear, if this is -1, then nodemask status is not changed. -- status_change_nid is set node id when N_MEMORY of nodemask is (will be) - set/clear. It means a new(memoryless) node gets new memory by online and a - node loses all memory. If this is -1, then nodemask status is not changed. - - If status_changed_nid* >= 0, callback should create/discard structures for the - node if necessary. - -The callback routine shall return one of the values -NOTIFY_DONE, NOTIFY_OK, NOTIFY_BAD, NOTIFY_STOP -defined in include/linux/notifier.h - -NOTIFY_DONE and NOTIFY_OK have no effect on the further processing. - -NOTIFY_BAD is used as response to the MEM_GOING_ONLINE, MEM_GOING_OFFLINE, -MEM_ONLINE, or MEM_OFFLINE action to cancel hotplugging. It stops -further processing of the notification queue. - -NOTIFY_STOP stops further processing of the notification queue. - Future Work =========== diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX deleted file mode 100644 index b6e69fd371c4..000000000000 --- a/Documentation/arm/00-INDEX +++ /dev/null @@ -1,50 +0,0 @@ -00-INDEX - - this file -Booting - - requirements for booting -CCN.txt - - Cache Coherent Network ring-bus and perf PMU driver. -Interrupts - - ARM Interrupt subsystem documentation -IXP4xx - - Intel IXP4xx Network processor. -Netwinder - - Netwinder specific documentation -Porting - - Symbol definitions for porting Linux to a new ARM machine. -Setup - - Kernel initialization parameters on ARM Linux -README - - General ARM documentation -SA1100/ - - SA1100 documentation -Samsung-S3C24XX/ - - S3C24XX ARM Linux Overview -SPEAr/ - - ST SPEAr platform Linux Overview -VFP/ - - Release notes for Linux Kernel Vector Floating Point support code -cluster-pm-race-avoidance.txt - - Algorithm for CPU and Cluster setup/teardown -empeg/ - - Ltd's Empeg MP3 Car Audio Player -firmware.txt - - Secure firmware registration and calling. -kernel_mode_neon.txt - - How to use NEON instructions in kernel mode -kernel_user_helpers.txt - - Helper functions in kernel space made available for userspace. -mem_alignment - - alignment abort handler documentation -memory.txt - - description of the virtual memory layout -nwfpe/ - - NWFPE floating point emulator documentation -swp_emulation - - SWP/SWPB emulation handler/logging description -tcm.txt - - ARM Tightly Coupled Memory -uefi.txt - - [U]EFI configuration and runtime services documentation -vlocks.txt - - Voting locks, low-level mechanism relying on memory system atomic writes. diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX deleted file mode 100644 index 8d55b4bbb5e2..000000000000 --- a/Documentation/block/00-INDEX +++ /dev/null @@ -1,34 +0,0 @@ -00-INDEX - - This file -bfq-iosched.txt - - BFQ IO scheduler and its tunables -biodoc.txt - - Notes on the Generic Block Layer Rewrite in Linux 2.5 -biovecs.txt - - Immutable biovecs and biovec iterators -capability.txt - - Generic Block Device Capability (/sys/block/<device>/capability) -cfq-iosched.txt - - CFQ IO scheduler tunables -cmdline-partition.txt - - how to specify block device partitions on kernel command line -data-integrity.txt - - Block data integrity -deadline-iosched.txt - - Deadline IO scheduler tunables -ioprio.txt - - Block io priorities (in CFQ scheduler) -pr.txt - - Block layer support for Persistent Reservations -null_blk.txt - - Null block for block-layer benchmarking. -queue-sysfs.txt - - Queue's sysfs entries -request.txt - - The members of struct request (in include/linux/blkdev.h) -stat.txt - - Block layer statistics in /sys/block/<device>/stat -switching-sched.txt - - Switching I/O schedulers at runtime -writeback_cache_control.txt - - Control of volatile write back caches diff --git a/Documentation/blockdev/00-INDEX b/Documentation/blockdev/00-INDEX deleted file mode 100644 index c08df56dd91b..000000000000 --- a/Documentation/blockdev/00-INDEX +++ /dev/null @@ -1,18 +0,0 @@ -00-INDEX - - this file -README.DAC960 - - info on Mylex DAC960/DAC1100 PCI RAID Controller Driver for Linux. -cciss.txt - - info, major/minor #'s for Compaq's SMART Array Controllers. -cpqarray.txt - - info on using Compaq's SMART2 Intelligent Disk Array Controllers. -floppy.txt - - notes and driver options for the floppy disk driver. -mflash.txt - - info on mGine m(g)flash driver for linux. -nbd.txt - - info on a TCP implementation of a network block device. -paride.txt - - information about the parallel port IDE subsystem. -ramdisk.txt - - short guide on how to set up and use the RAM disk. diff --git a/Documentation/cdrom/00-INDEX b/Documentation/cdrom/00-INDEX deleted file mode 100644 index 433edf23dc49..000000000000 --- a/Documentation/cdrom/00-INDEX +++ /dev/null @@ -1,11 +0,0 @@ -00-INDEX - - this file (info on CD-ROMs and Linux) -Makefile - - only used to generate TeX output from the documentation. -cdrom-standard.tex - - LaTeX document on standardizing the CD-ROM programming interface. -ide-cd - - info on setting up and using ATAPI (aka IDE) CD-ROMs. -packet-writing.txt - - Info on the CDRW packet writing module - diff --git a/Documentation/cgroup-v1/00-INDEX b/Documentation/cgroup-v1/00-INDEX deleted file mode 100644 index 13e0c85e7b35..000000000000 --- a/Documentation/cgroup-v1/00-INDEX +++ /dev/null @@ -1,26 +0,0 @@ -00-INDEX - - this file -blkio-controller.txt - - Description for Block IO Controller, implementation and usage details. -cgroups.txt - - Control Groups definition, implementation details, examples and API. -cpuacct.txt - - CPU Accounting Controller; account CPU usage for groups of tasks. -cpusets.txt - - documents the cpusets feature; assign CPUs and Mem to a set of tasks. -admin-guide/devices.rst - - Device Whitelist Controller; description, interface and security. -freezer-subsystem.txt - - checkpointing; rationale to not use signals, interface. -hugetlb.txt - - HugeTLB Controller implementation and usage details. -memcg_test.txt - - Memory Resource Controller; implementation details. -memory.txt - - Memory Resource Controller; design, accounting, interface, testing. -net_cls.txt - - Network classifier cgroups details and usages. -net_prio.txt - - Network priority cgroups details and usages. -pids.txt - - Process number cgroups details and usages. diff --git a/Documentation/conf.py b/Documentation/conf.py index b691af4831fa..72647a38b5c2 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -259,7 +259,7 @@ latex_elements = { 'papersize': 'a4paper', # The font size ('10pt', '11pt' or '12pt'). -'pointsize': '8pt', +'pointsize': '11pt', # Latex figure (float) alignment #'figure_align': 'htbp', @@ -272,8 +272,8 @@ latex_elements = { 'preamble': ''' % Use some font with UTF-8 support with XeLaTeX \\usepackage{fontspec} - \\setsansfont{DejaVu Serif} - \\setromanfont{DejaVu Sans} + \\setsansfont{DejaVu Sans} + \\setromanfont{DejaVu Serif} \\setmonofont{DejaVu Sans Mono} ''' @@ -383,6 +383,10 @@ latex_documents = [ 'The kernel development community', 'manual'), ('filesystems/index', 'filesystems.tex', 'Linux Filesystems API', 'The kernel development community', 'manual'), + ('admin-guide/ext4', 'ext4-admin-guide.tex', 'ext4 Administration Guide', + 'ext4 Community', 'manual'), + ('filesystems/ext4/index', 'ext4-data-structures.tex', + 'ext4 Data Structures and Algorithms', 'ext4 Community', 'manual'), ('gpu/index', 'gpu.tex', 'Linux GPU Driver Developer\'s Guide', 'The kernel development community', 'manual'), ('input/index', 'linux-input.tex', 'The Linux input driver subsystem', diff --git a/Documentation/core-api/boot-time-mm.rst b/Documentation/core-api/boot-time-mm.rst index 03cb1643f46f..6e12e89a03e0 100644 --- a/Documentation/core-api/boot-time-mm.rst +++ b/Documentation/core-api/boot-time-mm.rst @@ -76,7 +76,7 @@ These interfaces available only with bootmem, i.e when ``CONFIG_NO_BOOTMEM=n`` .. kernel-doc:: include/linux/bootmem.h .. kernel-doc:: mm/bootmem.c - :nodocs: + :functions: Memblock specific API --------------------- @@ -89,4 +89,4 @@ really happens under the hood. .. kernel-doc:: include/linux/memblock.h .. kernel-doc:: mm/memblock.c - :nodocs: + :functions: diff --git a/Documentation/core-api/gfp_mask-from-fs-io.rst b/Documentation/core-api/gfp_mask-from-fs-io.rst index e0df8f416582..e7c32a8de126 100644 --- a/Documentation/core-api/gfp_mask-from-fs-io.rst +++ b/Documentation/core-api/gfp_mask-from-fs-io.rst @@ -1,3 +1,5 @@ +.. _gfp_mask_from_fs_io: + ================================= GFP masks used from FS/IO context ================================= diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 26b735cefb93..29c790f571a5 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -27,10 +27,13 @@ Core utilities errseq printk-formats circular-buffers + memory-allocation mm-api gfp_mask-from-fs-io timekeeping boot-time-mm + memory-hotplug + Interfaces for kernel debugging =============================== diff --git a/Documentation/core-api/memory-allocation.rst b/Documentation/core-api/memory-allocation.rst new file mode 100644 index 000000000000..f8bb9aa120c4 --- /dev/null +++ b/Documentation/core-api/memory-allocation.rst @@ -0,0 +1,122 @@ +======================= +Memory Allocation Guide +======================= + +Linux provides a variety of APIs for memory allocation. You can +allocate small chunks using `kmalloc` or `kmem_cache_alloc` families, +large virtually contiguous areas using `vmalloc` and its derivatives, +or you can directly request pages from the page allocator with +`alloc_pages`. It is also possible to use more specialized allocators, +for instance `cma_alloc` or `zs_malloc`. + +Most of the memory allocation APIs use GFP flags to express how that +memory should be allocated. The GFP acronym stands for "get free +pages", the underlying memory allocation function. + +Diversity of the allocation APIs combined with the numerous GFP flags +makes the question "How should I allocate memory?" not that easy to +answer, although very likely you should use + +:: + + kzalloc(<size>, GFP_KERNEL); + +Of course there are cases when other allocation APIs and different GFP +flags must be used. + +Get Free Page flags +=================== + +The GFP flags control the allocators behavior. They tell what memory +zones can be used, how hard the allocator should try to find free +memory, whether the memory can be accessed by the userspace etc. The +:ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` provides +reference documentation for the GFP flags and their combinations and +here we briefly outline their recommended usage: + + * Most of the time ``GFP_KERNEL`` is what you need. Memory for the + kernel data structures, DMAable memory, inode cache, all these and + many other allocations types can use ``GFP_KERNEL``. Note, that + using ``GFP_KERNEL`` implies ``GFP_RECLAIM``, which means that + direct reclaim may be triggered under memory pressure; the calling + context must be allowed to sleep. + * If the allocation is performed from an atomic context, e.g interrupt + handler, use ``GFP_NOWAIT``. This flag prevents direct reclaim and + IO or filesystem operations. Consequently, under memory pressure + ``GFP_NOWAIT`` allocation is likely to fail. Allocations which + have a reasonable fallback should be using ``GFP_NOWARN``. + * If you think that accessing memory reserves is justified and the kernel + will be stressed unless allocation succeeds, you may use ``GFP_ATOMIC``. + * Untrusted allocations triggered from userspace should be a subject + of kmem accounting and must have ``__GFP_ACCOUNT`` bit set. There + is the handy ``GFP_KERNEL_ACCOUNT`` shortcut for ``GFP_KERNEL`` + allocations that should be accounted. + * Userspace allocations should use either of the ``GFP_USER``, + ``GFP_HIGHUSER`` or ``GFP_HIGHUSER_MOVABLE`` flags. The longer + the flag name the less restrictive it is. + + ``GFP_HIGHUSER_MOVABLE`` does not require that allocated memory + will be directly accessible by the kernel and implies that the + data is movable. + + ``GFP_HIGHUSER`` means that the allocated memory is not movable, + but it is not required to be directly accessible by the kernel. An + example may be a hardware allocation that maps data directly into + userspace but has no addressing limitations. + + ``GFP_USER`` means that the allocated memory is not movable and it + must be directly accessible by the kernel. + +You may notice that quite a few allocations in the existing code +specify ``GFP_NOIO`` or ``GFP_NOFS``. Historically, they were used to +prevent recursion deadlocks caused by direct memory reclaim calling +back into the FS or IO paths and blocking on already held +resources. Since 4.12 the preferred way to address this issue is to +use new scope APIs described in +:ref:`Documentation/core-api/gfp_mask-from-fs-io.rst <gfp_mask_from_fs_io>`. + +Other legacy GFP flags are ``GFP_DMA`` and ``GFP_DMA32``. They are +used to ensure that the allocated memory is accessible by hardware +with limited addressing capabilities. So unless you are writing a +driver for a device with such restrictions, avoid using these flags. +And even with hardware with restrictions it is preferable to use +`dma_alloc*` APIs. + +Selecting memory allocator +========================== + +The most straightforward way to allocate memory is to use a function +from the :c:func:`kmalloc` family. And, to be on the safe size it's +best to use routines that set memory to zero, like +:c:func:`kzalloc`. If you need to allocate memory for an array, there +are :c:func:`kmalloc_array` and :c:func:`kcalloc` helpers. + +The maximal size of a chunk that can be allocated with `kmalloc` is +limited. The actual limit depends on the hardware and the kernel +configuration, but it is a good practice to use `kmalloc` for objects +smaller than page size. + +For large allocations you can use :c:func:`vmalloc` and +:c:func:`vzalloc`, or directly request pages from the page +allocator. The memory allocated by `vmalloc` and related functions is +not physically contiguous. + +If you are not sure whether the allocation size is too large for +`kmalloc`, it is possible to use :c:func:`kvmalloc` and its +derivatives. It will try to allocate memory with `kmalloc` and if the +allocation fails it will be retried with `vmalloc`. There are +restrictions on which GFP flags can be used with `kvmalloc`; please +see :c:func:`kvmalloc_node` reference documentation. Note that +`kvmalloc` may return memory that is not physically contiguous. + +If you need to allocate many identical objects you can use the slab +cache allocator. The cache should be set up with +:c:func:`kmem_cache_create` before it can be used. Afterwards +:c:func:`kmem_cache_alloc` and its convenience wrappers can allocate +memory from that cache. + +When the allocated memory is no longer needed it must be freed. You +can use :c:func:`kvfree` for the memory allocated with `kmalloc`, +`vmalloc` and `kvmalloc`. The slab caches should be freed with +:c:func:`kmem_cache_free`. And don't forget to destroy the cache with +:c:func:`kmem_cache_destroy`. diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst new file mode 100644 index 000000000000..de7467e48067 --- /dev/null +++ b/Documentation/core-api/memory-hotplug.rst @@ -0,0 +1,125 @@ +.. _memory_hotplug: + +============== +Memory hotplug +============== + +Memory hotplug event notifier +============================= + +Hotplugging events are sent to a notification queue. + +There are six types of notification defined in ``include/linux/memory.h``: + +MEM_GOING_ONLINE + Generated before new memory becomes available in order to be able to + prepare subsystems to handle memory. The page allocator is still unable + to allocate from the new memory. + +MEM_CANCEL_ONLINE + Generated if MEM_GOING_ONLINE fails. + +MEM_ONLINE + Generated when memory has successfully brought online. The callback may + allocate pages from the new memory. + +MEM_GOING_OFFLINE + Generated to begin the process of offlining memory. Allocations are no + longer possible from the memory but some of the memory to be offlined + is still in use. The callback can be used to free memory known to a + subsystem from the indicated memory block. + +MEM_CANCEL_OFFLINE + Generated if MEM_GOING_OFFLINE fails. Memory is available again from + the memory block that we attempted to offline. + +MEM_OFFLINE + Generated after offlining memory is complete. + +A callback routine can be registered by calling:: + + hotplug_memory_notifier(callback_func, priority) + +Callback functions with higher values of priority are called before callback +functions with lower values. + +A callback function must have the following prototype:: + + int callback_func( + struct notifier_block *self, unsigned long action, void *arg); + +The first argument of the callback function (self) is a pointer to the block +of the notifier chain that points to the callback function itself. +The second argument (action) is one of the event types described above. +The third argument (arg) passes a pointer of struct memory_notify:: + + struct memory_notify { + unsigned long start_pfn; + unsigned long nr_pages; + int status_change_nid_normal; + int status_change_nid_high; + int status_change_nid; + } + +- start_pfn is start_pfn of online/offline memory. +- nr_pages is # of pages of online/offline memory. +- status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask + is (will be) set/clear, if this is -1, then nodemask status is not changed. +- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask + is (will be) set/clear, if this is -1, then nodemask status is not changed. +- status_change_nid is set node id when N_MEMORY of nodemask is (will be) + set/clear. It means a new(memoryless) node gets new memory by online and a + node loses all memory. If this is -1, then nodemask status is not changed. + + If status_changed_nid* >= 0, callback should create/discard structures for the + node if necessary. + +The callback routine shall return one of the values +NOTIFY_DONE, NOTIFY_OK, NOTIFY_BAD, NOTIFY_STOP +defined in ``include/linux/notifier.h`` + +NOTIFY_DONE and NOTIFY_OK have no effect on the further processing. + +NOTIFY_BAD is used as response to the MEM_GOING_ONLINE, MEM_GOING_OFFLINE, +MEM_ONLINE, or MEM_OFFLINE action to cancel hotplugging. It stops +further processing of the notification queue. + +NOTIFY_STOP stops further processing of the notification queue. + +Locking Internals +================= + +When adding/removing memory that uses memory block devices (i.e. ordinary RAM), +the device_hotplug_lock should be held to: + +- synchronize against online/offline requests (e.g. via sysfs). This way, memory + block devices can only be accessed (.online/.state attributes) by user + space once memory has been fully added. And when removing memory, we + know nobody is in critical sections. +- synchronize against CPU hotplug and similar (e.g. relevant for ACPI and PPC) + +Especially, there is a possible lock inversion that is avoided using +device_hotplug_lock when adding memory and user space tries to online that +memory faster than expected: + +- device_online() will first take the device_lock(), followed by + mem_hotplug_lock +- add_memory_resource() will first take the mem_hotplug_lock, followed by + the device_lock() (while creating the devices, during bus_add_device()). + +As the device is visible to user space before taking the device_lock(), this +can result in a lock inversion. + +onlining/offlining of memory should be done via device_online()/ +device_offline() - to make sure it is properly synchronized to actions +via sysfs. Holding device_hotplug_lock is advised (to e.g. protect online_type) + +When adding/removing/onlining/offlining memory or adding/removing +heterogeneous/device memory, we should always hold the mem_hotplug_lock in +write mode to serialise memory hotplug (e.g. access to global/zone +variables). + +In addition, mem_hotplug_lock (in contrast to device_hotplug_lock) in read +mode allows for a quite efficient get_online_mems/put_online_mems +implementation, so code accessing memory can protect from that memory +vanishing. diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index 46ae3537fb12..5ce1ec1dd066 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -14,6 +14,8 @@ User Space Memory Access .. kernel-doc:: mm/util.c :functions: get_user_pages_fast +.. _mm-api-gfp-flags: + Memory Allocation Controls ========================== diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 25dc591cb110..86023c33906f 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -376,15 +376,15 @@ correctness of the format string and va_list arguments. Passed by reference. -kobjects --------- +Device tree nodes +----------------- :: %pOF[fnpPcCF] -For printing kobject based structs (device nodes). Default behaviour is +For printing device tree node structures. Default behaviour is equivalent to %pOFf. - f - device node full_name diff --git a/Documentation/dev-tools/coccinelle.rst b/Documentation/dev-tools/coccinelle.rst index 94f41c290bfc..aa14f05cabb1 100644 --- a/Documentation/dev-tools/coccinelle.rst +++ b/Documentation/dev-tools/coccinelle.rst @@ -30,18 +30,29 @@ of many distributions, e.g. : - NetBSD - FreeBSD -You can get the latest version released from the Coccinelle homepage at +Some distribution packages are obsolete and it is recommended +to use the latest version released from the Coccinelle homepage at http://coccinelle.lip6.fr/ -Once you have it, run the following command:: +Or from Github at: - ./configure +https://github.com/coccinelle/coccinelle + +Once you have it, run the following commands:: + + ./autogen + ./configure make as a regular user, and install it with:: sudo make install +More detailed installation instructions to build from source can be +found at: + +https://github.com/coccinelle/coccinelle/blob/master/install.txt + Supplemental documentation --------------------------- @@ -51,6 +62,10 @@ https://bottest.wiki.kernel.org/coccicheck The wiki documentation always refers to the linux-next version of the script. +For Semantic Patch Language(SmPL) grammar documentation refer to: + +http://coccinelle.lip6.fr/documentation.php + Using Coccinelle on the Linux kernel ------------------------------------ @@ -223,7 +238,7 @@ Since coccicheck runs through make, it naturally runs from the kernel proper dir, as such the second rule above would be implied for picking up a .cocciconfig when using ``make coccicheck``. -``make coccicheck`` also supports using M= targets.If you do not supply +``make coccicheck`` also supports using M= targets. If you do not supply any M= target, it is assumed you want to target the entire kernel. The kernel coccicheck script has:: diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst index 6f653acea248..dad1bb8711e2 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -159,7 +159,7 @@ Contributing new tests (details) * If a test needs specific kernel config options enabled, add a config file in the test directory to enable them. - e.g: tools/testing/selftests/android/ion/config + e.g: tools/testing/selftests/android/config Test Harness ============ diff --git a/Documentation/device-mapper/dm-flakey.txt b/Documentation/device-mapper/dm-flakey.txt index c43030718cef..9f0e247d0877 100644 --- a/Documentation/device-mapper/dm-flakey.txt +++ b/Documentation/device-mapper/dm-flakey.txt @@ -33,6 +33,10 @@ Optional feature parameters: All write I/O is silently ignored. Read I/O is handled correctly. + error_writes: + All write I/O is failed with an error signalled. + Read I/O is handled correctly. + corrupt_bio_byte <Nth_byte> <direction> <value> <flags>: During <down interval>, replace <Nth_byte> of the data of each matching bio with <value>. diff --git a/Documentation/devicetree/00-INDEX b/Documentation/devicetree/00-INDEX deleted file mode 100644 index 8c4102c6a5e7..000000000000 --- a/Documentation/devicetree/00-INDEX +++ /dev/null @@ -1,12 +0,0 @@ -Documentation for device trees, a data structure by which bootloaders pass -hardware layout to Linux in a device-independent manner, simplifying hardware -probing. This subsystem is maintained by Grant Likely -<[email protected]> and has a mailing list at -https://lists.ozlabs.org/listinfo/devicetree-discuss - -00-INDEX - - this file -booting-without-of.txt - - Booting Linux without Open Firmware, describes history and format of device trees. -usage-model.txt - - How Linux uses DT and what DT aims to solve.
\ No newline at end of file diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst index 826e85d50a16..e970fadf4d1a 100644 --- a/Documentation/driver-api/basics.rst +++ b/Documentation/driver-api/basics.rst @@ -121,6 +121,9 @@ Kernel utility functions .. kernel-doc:: kernel/rcu/update.c :export: +.. kernel-doc:: include/linux/overflow.h + :internal: + Device Resource Management -------------------------- diff --git a/Documentation/driver-api/firewire.rst b/Documentation/driver-api/firewire.rst new file mode 100644 index 000000000000..94a2d7f01d99 --- /dev/null +++ b/Documentation/driver-api/firewire.rst @@ -0,0 +1,48 @@ +=========================================== +Firewire (IEEE 1394) driver Interface Guide +=========================================== + +Introduction and Overview +========================= + +The Linux FireWire subsystem adds some interfaces into the Linux system to + use/maintain+any resource on IEEE 1394 bus. + +The main purpose of these interfaces is to access address space on each node +on IEEE 1394 bus by ISO/IEC 13213 (IEEE 1212) procedure, and to control +isochronous resources on the bus by IEEE 1394 procedure. + +Two types of interfaces are added, according to consumers of the interface. A +set of userspace interfaces is available via `firewire character devices`. A set +of kernel interfaces is available via exported symbols in `firewire-core` module. + +Firewire char device data structures +==================================== + +.. include:: /ABI/stable/firewire-cdev + :literal: + +.. kernel-doc:: include/uapi/linux/firewire-cdev.h + :internal: + +Firewire device probing and sysfs interfaces +============================================ + +.. include:: /ABI/stable/sysfs-bus-firewire + :literal: + +.. kernel-doc:: drivers/firewire/core-device.c + :export: + +Firewire core transaction interfaces +==================================== + +.. kernel-doc:: drivers/firewire/core-transaction.c + :export: + +Firewire Isochronous I/O interfaces +=================================== + +.. kernel-doc:: drivers/firewire/core-iso.c + :export: + diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 6d9f2f9fe20e..1f0cdba2b2bf 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -29,6 +29,7 @@ available subsections can be seen below. iio/index input usb/index + firewire pci spi i2c diff --git a/Documentation/efi-stub.txt b/Documentation/efi-stub.txt index 41df801f9a50..833edb0d0bc4 100644 --- a/Documentation/efi-stub.txt +++ b/Documentation/efi-stub.txt @@ -83,7 +83,18 @@ is passed to bzImage.efi. The "dtb=" option ----------------- -For the ARM and arm64 architectures, we also need to be able to provide a -device tree to the kernel. This is done with the "dtb=" command line option, -and is processed in the same manner as the "initrd=" option that is +For the ARM and arm64 architectures, a device tree must be provided to +the kernel. Normally firmware shall supply the device tree via the +EFI CONFIGURATION TABLE. However, the "dtb=" command line option can +be used to override the firmware supplied device tree, or to supply +one when firmware is unable to. + +Please note: Firmware adds runtime configuration information to the +device tree before booting the kernel. If dtb= is used to override +the device tree, then any runtime data provided by firmware will be +lost. The dtb= option should only be used either as a debug tool, or +as a last resort when a device tree is not provided in the EFI +CONFIGURATION TABLE. + +"dtb=" is processed in the same manner as the "initrd=" option that is described above. diff --git a/Documentation/fb/00-INDEX b/Documentation/fb/00-INDEX deleted file mode 100644 index fe85e7c5907a..000000000000 --- a/Documentation/fb/00-INDEX +++ /dev/null @@ -1,75 +0,0 @@ -Index of files in Documentation/fb. If you think something about frame -buffer devices needs an entry here, needs correction or you've written one -please mail me. - Geert Uytterhoeven <[email protected]> - -00-INDEX - - this file. -api.txt - - The frame buffer API between applications and buffer devices. -arkfb.txt - - info on the fbdev driver for ARK Logic chips. -aty128fb.txt - - info on the ATI Rage128 frame buffer driver. -cirrusfb.txt - - info on the driver for Cirrus Logic chipsets. -cmap_xfbdev.txt - - an introduction to fbdev's cmap structures. -deferred_io.txt - - an introduction to deferred IO. -efifb.txt - - info on the EFI platform driver for Intel based Apple computers. -ep93xx-fb.txt - - info on the driver for EP93xx LCD controller. -fbcon.txt - - intro to and usage guide for the framebuffer console (fbcon). -framebuffer.txt - - introduction to frame buffer devices. -gxfb.txt - - info on the framebuffer driver for AMD Geode GX2 based processors. -intel810.txt - - documentation for the Intel 810/815 framebuffer driver. -intelfb.txt - - docs for Intel 830M/845G/852GM/855GM/865G/915G/945G fb driver. -internals.txt - - quick overview of frame buffer device internals. -lxfb.txt - - info on the framebuffer driver for AMD Geode LX based processors. -matroxfb.txt - - info on the Matrox framebuffer driver for Alpha, Intel and PPC. -metronomefb.txt - - info on the driver for the Metronome display controller. -modedb.txt - - info on the video mode database. -pvr2fb.txt - - info on the PowerVR 2 frame buffer driver. -pxafb.txt - - info on the driver for the PXA25x LCD controller. -s3fb.txt - - info on the fbdev driver for S3 Trio/Virge chips. -sa1100fb.txt - - information about the driver for the SA-1100 LCD controller. -sh7760fb.txt - - info on the SH7760/SH7763 integrated LCDC Framebuffer driver. -sisfb.txt - - info on the framebuffer device driver for various SiS chips. -sm501.txt - - info on the framebuffer device driver for sm501 videoframebuffer. -sstfb.txt - - info on the frame buffer driver for 3dfx' Voodoo Graphics boards. -tgafb.txt - - info on the TGA (DECChip 21030) frame buffer driver. -tridentfb.txt - info on the framebuffer driver for some Trident chip based cards. -udlfb.txt - - Driver for DisplayLink USB 2.0 chips. -uvesafb.txt - - info on the userspace VESA (VBE2+ compliant) frame buffer device. -vesafb.txt - - info on the VESA frame buffer device. -viafb.modes - - list of modes for VIA Integration Graphic Chip. -viafb.txt - - info on the VIA Integration Graphic Chip console framebuffer driver. -vt8623fb.txt - - info on the fb driver for the graphics core in VIA VT8623 chipsets. diff --git a/Documentation/fb/vesafb.txt b/Documentation/fb/vesafb.txt index 950d5a658cb3..413bb73235be 100644 --- a/Documentation/fb/vesafb.txt +++ b/Documentation/fb/vesafb.txt @@ -114,11 +114,11 @@ to turn it on. You can pass options to vesafb using "video=vesafb:option" on the kernel command line. Multiple options should be separated -by comma, like this: "video=vesafb:ypan,invers" +by comma, like this: "video=vesafb:ypan,inverse" Accepted options: -invers no comment... +inverse use inverse color map ypan enable display panning using the VESA protected mode interface. The visible screen is just a window of the diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX deleted file mode 100644 index 0937bade1099..000000000000 --- a/Documentation/filesystems/00-INDEX +++ /dev/null @@ -1,153 +0,0 @@ -00-INDEX - - this file (info on some of the filesystems supported by linux). -Locking - - info on locking rules as they pertain to Linux VFS. -9p.txt - - 9p (v9fs) is an implementation of the Plan 9 remote fs protocol. -adfs.txt - - info and mount options for the Acorn Advanced Disc Filing System. -afs.txt - - info and examples for the distributed AFS (Andrew File System) fs. -affs.txt - - info and mount options for the Amiga Fast File System. -autofs-mount-control.txt - - info on device control operations for autofs module. -automount-support.txt - - information about filesystem automount support. -befs.txt - - information about the BeOS filesystem for Linux. -bfs.txt - - info for the SCO UnixWare Boot Filesystem (BFS). -btrfs.txt - - info for the BTRFS filesystem. -caching/ - - directory containing filesystem cache documentation. -ceph.txt - - info for the Ceph Distributed File System. -cifs/ - - directory containing CIFS filesystem documentation and example code. -coda.txt - - description of the CODA filesystem. -configfs/ - - directory containing configfs documentation and example code. -cramfs.txt - - info on the cram filesystem for small storage (ROMs etc). -dax.txt - - info on avoiding the page cache for files stored on CPU-addressable - storage devices. -debugfs.txt - - info on the debugfs filesystem. -devpts.txt - - info on the devpts filesystem. -directory-locking - - info about the locking scheme used for directory operations. -dlmfs.txt - - info on the userspace interface to the OCFS2 DLM. -dnotify.txt - - info about directory notification in Linux. -dnotify_test.c - - example program for dnotify. -ecryptfs.txt - - docs on eCryptfs: stacked cryptographic filesystem for Linux. -efivarfs.txt - - info for the efivarfs filesystem. -exofs.txt - - info, usage, mount options, design about EXOFS. -ext2.txt - - info, mount options and specifications for the Ext2 filesystem. -ext3.txt - - info, mount options and specifications for the Ext3 filesystem. -ext4.txt - - info, mount options and specifications for the Ext4 filesystem. -f2fs.txt - - info and mount options for the F2FS filesystem. -fiemap.txt - - info on fiemap ioctl. -files.txt - - info on file management in the Linux kernel. -fuse.txt - - info on the Filesystem in User SpacE including mount options. -gfs2-glocks.txt - - info on the Global File System 2 - Glock internal locking rules. -gfs2-uevents.txt - - info on the Global File System 2 - uevents. -gfs2.txt - - info on the Global File System 2. -hfs.txt - - info on the Macintosh HFS Filesystem for Linux. -hfsplus.txt - - info on the Macintosh HFSPlus Filesystem for Linux. -hpfs.txt - - info and mount options for the OS/2 HPFS. -inotify.txt - - info on the powerful yet simple file change notification system. -isofs.txt - - info and mount options for the ISO 9660 (CDROM) filesystem. -jfs.txt - - info and mount options for the JFS filesystem. -locks.txt - - info on file locking implementations, flock() vs. fcntl(), etc. -mandatory-locking.txt - - info on the Linux implementation of Sys V mandatory file locking. -nfs/ - - nfs-related documentation. -nilfs2.txt - - info and mount options for the NILFS2 filesystem. -ntfs.txt - - info and mount options for the NTFS filesystem (Windows NT). -ocfs2.txt - - info and mount options for the OCFS2 clustered filesystem. -omfs.txt - - info on the Optimized MPEG FileSystem. -path-lookup.txt - - info on path walking and name lookup locking. -pohmelfs/ - - directory containing pohmelfs filesystem documentation. -porting - - various information on filesystem porting. -proc.txt - - info on Linux's /proc filesystem. -qnx6.txt - - info on the QNX6 filesystem. -quota.txt - - info on Quota subsystem. -ramfs-rootfs-initramfs.txt - - info on the 'in memory' filesystems ramfs, rootfs and initramfs. -relay.txt - - info on relay, for efficient streaming from kernel to user space. -romfs.txt - - description of the ROMFS filesystem. -seq_file.txt - - how to use the seq_file API. -sharedsubtree.txt - - a description of shared subtrees for namespaces. -spufs.txt - - info and mount options for the SPU filesystem used on Cell. -squashfs.txt - - info on the squashfs filesystem. -sysfs-pci.txt - - info on accessing PCI device resources through sysfs. -sysfs-tagging.txt - - info on sysfs tagging to avoid duplicates. -sysfs.txt - - info on sysfs, a ram-based filesystem for exporting kernel objects. -sysv-fs.txt - - info on the SystemV/V7/Xenix/Coherent filesystem. -tmpfs.txt - - info on tmpfs, a filesystem that holds all files in virtual memory. -ubifs.txt - - info on the Unsorted Block Images FileSystem. -udf.txt - - info and mount options for the UDF filesystem. -ufs.txt - - info on the ufs filesystem. -vfat.txt - - info on using the VFAT filesystem used in Windows NT and Windows 95. -vfs.txt - - overview of the Virtual File System. -xfs-delayed-logging-design.txt - - info on the XFS Delayed Logging Design. -xfs-self-describing-metadata.txt - - info on XFS Self Describing Metadata. -xfs.txt - - info and mount options for the XFS filesystem. diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index 70cb68bed2e8..bc393e0a22b8 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -75,7 +75,7 @@ exposure of uninitialized data through mmap. These filesystems may be used for inspiration: - ext2: see Documentation/filesystems/ext2.txt -- ext4: see Documentation/filesystems/ext4.txt +- ext4: see Documentation/filesystems/ext4/ext4.rst - xfs: see Documentation/filesystems/xfs.txt diff --git a/Documentation/filesystems/ext2.txt b/Documentation/filesystems/ext2.txt index 81c0becab225..a45c9fc0747b 100644 --- a/Documentation/filesystems/ext2.txt +++ b/Documentation/filesystems/ext2.txt @@ -358,7 +358,7 @@ and are copied into the filesystem. If a transaction is incomplete at the time of the crash, then there is no guarantee of consistency for the blocks in that transaction so they are discarded (which means any filesystem changes they represent are also lost). -Check Documentation/filesystems/ext4.txt if you want to read more about +Check Documentation/filesystems/ext4/ext4.rst if you want to read more about ext4 and journaling. References diff --git a/Documentation/filesystems/ext4/ondisk/about.rst b/Documentation/filesystems/ext4/about.rst index 0aadba052264..0aadba052264 100644 --- a/Documentation/filesystems/ext4/ondisk/about.rst +++ b/Documentation/filesystems/ext4/about.rst diff --git a/Documentation/filesystems/ext4/ondisk/allocators.rst b/Documentation/filesystems/ext4/allocators.rst index 7aa85152ace3..7aa85152ace3 100644 --- a/Documentation/filesystems/ext4/ondisk/allocators.rst +++ b/Documentation/filesystems/ext4/allocators.rst diff --git a/Documentation/filesystems/ext4/ondisk/attributes.rst b/Documentation/filesystems/ext4/attributes.rst index 0b01b67b81fe..54386a010a8d 100644 --- a/Documentation/filesystems/ext4/ondisk/attributes.rst +++ b/Documentation/filesystems/ext4/attributes.rst @@ -30,7 +30,7 @@ Extended attributes, when stored after the inode, have a header ``ext4_xattr_ibody_header`` that is 4 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -47,7 +47,7 @@ The beginning of an extended attribute block is in ``struct ext4_xattr_header``, which is 32 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -92,7 +92,7 @@ entries must be stored in sorted order. The sort order is Attributes stored inside an inode do not need be stored in sorted order. .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -157,7 +157,7 @@ attribute name index field is set, and matching string is removed from the key name. Here is a map of name index values to key prefixes: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Name Index diff --git a/Documentation/filesystems/ext4/ondisk/bigalloc.rst b/Documentation/filesystems/ext4/bigalloc.rst index c6d88557553c..c6d88557553c 100644 --- a/Documentation/filesystems/ext4/ondisk/bigalloc.rst +++ b/Documentation/filesystems/ext4/bigalloc.rst diff --git a/Documentation/filesystems/ext4/ondisk/bitmaps.rst b/Documentation/filesystems/ext4/bitmaps.rst index c7546dbc197a..c7546dbc197a 100644 --- a/Documentation/filesystems/ext4/ondisk/bitmaps.rst +++ b/Documentation/filesystems/ext4/bitmaps.rst diff --git a/Documentation/filesystems/ext4/ondisk/blockgroup.rst b/Documentation/filesystems/ext4/blockgroup.rst index baf888e4c06a..baf888e4c06a 100644 --- a/Documentation/filesystems/ext4/ondisk/blockgroup.rst +++ b/Documentation/filesystems/ext4/blockgroup.rst diff --git a/Documentation/filesystems/ext4/ondisk/blockmap.rst b/Documentation/filesystems/ext4/blockmap.rst index 30e25750d88a..30e25750d88a 100644 --- a/Documentation/filesystems/ext4/ondisk/blockmap.rst +++ b/Documentation/filesystems/ext4/blockmap.rst diff --git a/Documentation/filesystems/ext4/ondisk/blocks.rst b/Documentation/filesystems/ext4/blocks.rst index 73d4dc0f7bda..73d4dc0f7bda 100644 --- a/Documentation/filesystems/ext4/ondisk/blocks.rst +++ b/Documentation/filesystems/ext4/blocks.rst diff --git a/Documentation/filesystems/ext4/ondisk/checksums.rst b/Documentation/filesystems/ext4/checksums.rst index 9d6a793b2e03..5519e253810d 100644 --- a/Documentation/filesystems/ext4/ondisk/checksums.rst +++ b/Documentation/filesystems/ext4/checksums.rst @@ -28,7 +28,7 @@ of checksum. The checksum function is whatever the superblock describes (crc32c as of October 2013) unless noted otherwise. .. list-table:: - :widths: 1 1 4 + :widths: 20 8 50 :header-rows: 1 * - Metadata diff --git a/Documentation/filesystems/ext4/ondisk/directory.rst b/Documentation/filesystems/ext4/directory.rst index 8fcba68c2884..614034e24669 100644 --- a/Documentation/filesystems/ext4/ondisk/directory.rst +++ b/Documentation/filesystems/ext4/directory.rst @@ -34,7 +34,7 @@ is at most 263 bytes long, though on disk you'll need to reference ``dirent.rec_len`` to know for sure. .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -66,7 +66,7 @@ tree traversal. This format is ``ext4_dir_entry_2``, which is at most ``dirent.rec_len`` to know for sure. .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -99,7 +99,7 @@ tree traversal. This format is ``ext4_dir_entry_2``, which is at most The directory file type is one of the following values: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -130,7 +130,7 @@ in the place where the name normally goes. The structure is ``struct ext4_dir_entry_tail``: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -212,7 +212,7 @@ The root of the htree is in ``struct dx_root``, which is the full length of a data block: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -305,7 +305,7 @@ of a data block: The directory hash is one of the following values: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -327,7 +327,7 @@ Interior nodes of an htree are recorded as ``struct dx_node``, which is also the full length of a data block: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -375,7 +375,7 @@ The hash maps that exist in both ``struct dx_root`` and long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -405,7 +405,7 @@ directory index (which will ensure that there's space for the checksum. The dx\_tail structure is 8 bytes long and looks like this: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/dynamic.rst index bb0c84333341..bb0c84333341 100644 --- a/Documentation/filesystems/ext4/ondisk/dynamic.rst +++ b/Documentation/filesystems/ext4/dynamic.rst diff --git a/Documentation/filesystems/ext4/ondisk/eainode.rst b/Documentation/filesystems/ext4/eainode.rst index ecc0d01a0a72..ecc0d01a0a72 100644 --- a/Documentation/filesystems/ext4/ondisk/eainode.rst +++ b/Documentation/filesystems/ext4/eainode.rst diff --git a/Documentation/filesystems/ext4/ext4.rst b/Documentation/filesystems/ext4/ext4.rst deleted file mode 100644 index 9d4368d591fa..000000000000 --- a/Documentation/filesystems/ext4/ext4.rst +++ /dev/null @@ -1,613 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -======================== -General Information -======================== - -Ext4 is an advanced level of the ext3 filesystem which incorporates -scalability and reliability enhancements for supporting large filesystems -(64 bit) in keeping with increasing disk capacities and state-of-the-art -feature requirements. - -Mailing list: [email protected] -Web site: http://ext4.wiki.kernel.org - - -Quick usage instructions -======================== - -Note: More extensive information for getting started with ext4 can be -found at the ext4 wiki site at the URL: -http://ext4.wiki.kernel.org/index.php/Ext4_Howto - - - The latest version of e2fsprogs can be found at: - - https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/ - - or - - http://sourceforge.net/project/showfiles.php?group_id=2406 - - or grab the latest git repository from: - - https://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git - - - Create a new filesystem using the ext4 filesystem type: - - # mke2fs -t ext4 /dev/hda1 - - Or to configure an existing ext3 filesystem to support extents: - - # tune2fs -O extents /dev/hda1 - - If the filesystem was created with 128 byte inodes, it can be - converted to use 256 byte for greater efficiency via: - - # tune2fs -I 256 /dev/hda1 - - - Mounting: - - # mount -t ext4 /dev/hda1 /wherever - - - When comparing performance with other filesystems, it's always - important to try multiple workloads; very often a subtle change in a - workload parameter can completely change the ranking of which - filesystems do well compared to others. When comparing versus ext3, - note that ext4 enables write barriers by default, while ext3 does - not enable write barriers by default. So it is useful to use - explicitly specify whether barriers are enabled or not when via the - '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems - for a fair comparison. When tuning ext3 for best benchmark numbers, - it is often worthwhile to try changing the data journaling mode; '-o - data=writeback' can be faster for some workloads. (Note however that - running mounted with data=writeback can potentially leave stale data - exposed in recently written files in case of an unclean shutdown, - which could be a security exposure in some situations.) Configuring - the filesystem with a large journal can also be helpful for - metadata-intensive workloads. - -Features -======== - -Currently Available -------------------- - -* ability to use filesystems > 16TB (e2fsprogs support not available yet) -* extent format reduces metadata overhead (RAM, IO for access, transactions) -* extent format more robust in face of on-disk corruption due to magics, -* internal redundancy in tree -* improved file allocation (multi-block alloc) -* lift 32000 subdirectory limit imposed by i_links_count[1] -* nsec timestamps for mtime, atime, ctime, create time -* inode version field on disk (NFSv4, Lustre) -* reduced e2fsck time via uninit_bg feature -* journal checksumming for robustness, performance -* persistent file preallocation (e.g for streaming media, databases) -* ability to pack bitmaps and inode tables into larger virtual groups via the - flex_bg feature -* large file support -* inode allocation using large virtual block groups via flex_bg -* delayed allocation -* large block (up to pagesize) support -* efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force - the ordering) - -[1] Filesystems with a block size of 1k may see a limit imposed by the -directory hash tree having a maximum depth of two. - -Options -======= - -When mounting an ext4 filesystem, the following option are accepted: -(*) == default - -======================= ======================================================= -Mount Option Description -======================= ======================================================= -ro Mount filesystem read only. Note that ext4 will - replay the journal (and thus write to the - partition) even when mounted "read only". The - mount options "ro,noload" can be used to prevent - writes to the filesystem. - -journal_checksum Enable checksumming of the journal transactions. - This will allow the recovery code in e2fsck and the - kernel to detect corruption in the kernel. It is a - compatible change and will be ignored by older kernels. - -journal_async_commit Commit block can be written to disk without waiting - for descriptor blocks. If enabled older kernels cannot - mount the device. This will enable 'journal_checksum' - internally. - -journal_path=path -journal_dev=devnum When the external journal device's major/minor numbers - have changed, these options allow the user to specify - the new journal location. The journal device is - identified through either its new major/minor numbers - encoded in devnum, or via a path to the device. - -norecovery Don't load the journal on mounting. Note that -noload if the filesystem was not unmounted cleanly, - skipping the journal replay will lead to the - filesystem containing inconsistencies that can - lead to any number of problems. - -data=journal All data are committed into the journal prior to being - written into the main file system. Enabling - this mode will disable delayed allocation and - O_DIRECT support. - -data=ordered (*) All data are forced directly out to the main file - system prior to its metadata being committed to the - journal. - -data=writeback Data ordering is not preserved, data may be written - into the main file system after its metadata has been - committed to the journal. - -commit=nrsec (*) Ext4 can be told to sync all its data and metadata - every 'nrsec' seconds. The default value is 5 seconds. - This means that if you lose your power, you will lose - as much as the latest 5 seconds of work (your - filesystem will not be damaged though, thanks to the - journaling). This default value (or any low value) - will hurt performance, but it's good for data-safety. - Setting it to 0 will have the same effect as leaving - it at the default (5 seconds). - Setting it to very large values will improve - performance. - -barrier=<0|1(*)> This enables/disables the use of write barriers in -barrier(*) the jbd code. barrier=0 disables, barrier=1 enables. -nobarrier This also requires an IO stack which can support - barriers, and if jbd gets an error on a barrier - write, it will disable again with a warning. - Write barriers enforce proper on-disk ordering - of journal commits, making volatile disk write caches - safe to use, at some performance penalty. If - your disks are battery-backed in one way or another, - disabling barriers may safely improve performance. - The mount options "barrier" and "nobarrier" can - also be used to enable or disable barriers, for - consistency with other ext4 mount options. - -inode_readahead_blks=n This tuning parameter controls the maximum - number of inode table blocks that ext4's inode - table readahead algorithm will pre-read into - the buffer cache. The default value is 32 blocks. - -nouser_xattr Disables Extended User Attributes. See the - attr(5) manual page for more information about - extended attributes. - -noacl This option disables POSIX Access Control List - support. If ACL support is enabled in the kernel - configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is - enabled by default on mount. See the acl(5) manual - page for more information about acl. - -bsddf (*) Make 'df' act like BSD. -minixdf Make 'df' act like Minix. - -debug Extra debugging information is sent to syslog. - -abort Simulate the effects of calling ext4_abort() for - debugging purposes. This is normally used while - remounting a filesystem which is already mounted. - -errors=remount-ro Remount the filesystem read-only on an error. -errors=continue Keep going on a filesystem error. -errors=panic Panic and halt the machine if an error occurs. - (These mount options override the errors behavior - specified in the superblock, which can be configured - using tune2fs) - -data_err=ignore(*) Just print an error message if an error occurs - in a file data buffer in ordered mode. -data_err=abort Abort the journal if an error occurs in a file - data buffer in ordered mode. - -grpid New objects have the group ID of their parent. -bsdgroups - -nogrpid (*) New objects have the group ID of their creator. -sysvgroups - -resgid=n The group ID which may use the reserved blocks. - -resuid=n The user ID which may use the reserved blocks. - -sb=n Use alternate superblock at this location. - -quota These options are ignored by the filesystem. They -noquota are used only by quota tools to recognize volumes -grpquota where quota should be turned on. See documentation -usrquota in the quota-tools package for more details - (http://sourceforge.net/projects/linuxquota). - -jqfmt=<quota type> These options tell filesystem details about quota -usrjquota=<file> so that quota information can be properly updated -grpjquota=<file> during journal replay. They replace the above - quota options. See documentation in the quota-tools - package for more details - (http://sourceforge.net/projects/linuxquota). - -stripe=n Number of filesystem blocks that mballoc will try - to use for allocation size and alignment. For RAID5/6 - systems this should be the number of data - disks * RAID chunk size in file system blocks. - -delalloc (*) Defer block allocation until just before ext4 - writes out the block(s) in question. This - allows ext4 to better allocation decisions - more efficiently. -nodelalloc Disable delayed allocation. Blocks are allocated - when the data is copied from userspace to the - page cache, either via the write(2) system call - or when an mmap'ed page which was previously - unallocated is written for the first time. - -max_batch_time=usec Maximum amount of time ext4 should wait for - additional filesystem operations to be batch - together with a synchronous write operation. - Since a synchronous write operation is going to - force a commit and then a wait for the I/O - complete, it doesn't cost much, and can be a - huge throughput win, we wait for a small amount - of time to see if any other transactions can - piggyback on the synchronous write. The - algorithm used is designed to automatically tune - for the speed of the disk, by measuring the - amount of time (on average) that it takes to - finish committing a transaction. Call this time - the "commit time". If the time that the - transaction has been running is less than the - commit time, ext4 will try sleeping for the - commit time to see if other operations will join - the transaction. The commit time is capped by - the max_batch_time, which defaults to 15000us - (15ms). This optimization can be turned off - entirely by setting max_batch_time to 0. - -min_batch_time=usec This parameter sets the commit time (as - described above) to be at least min_batch_time. - It defaults to zero microseconds. Increasing - this parameter may improve the throughput of - multi-threaded, synchronous workloads on very - fast disks, at the cost of increasing latency. - -journal_ioprio=prio The I/O priority (from 0 to 7, where 0 is the - highest priority) which should be used for I/O - operations submitted by kjournald2 during a - commit operation. This defaults to 3, which is - a slightly higher priority than the default I/O - priority. - -auto_da_alloc(*) Many broken applications don't use fsync() when -noauto_da_alloc replacing existing files via patterns such as - fd = open("foo.new")/write(fd,..)/close(fd)/ - rename("foo.new", "foo"), or worse yet, - fd = open("foo", O_TRUNC)/write(fd,..)/close(fd). - If auto_da_alloc is enabled, ext4 will detect - the replace-via-rename and replace-via-truncate - patterns and force that any delayed allocation - blocks are allocated such that at the next - journal commit, in the default data=ordered - mode, the data blocks of the new file are forced - to disk before the rename() operation is - committed. This provides roughly the same level - of guarantees as ext3, and avoids the - "zero-length" problem that can happen when a - system crashes before the delayed allocation - blocks are forced to disk. - -noinit_itable Do not initialize any uninitialized inode table - blocks in the background. This feature may be - used by installation CD's so that the install - process can complete as quickly as possible; the - inode table initialization process would then be - deferred until the next time the file system - is unmounted. - -init_itable=n The lazy itable init code will wait n times the - number of milliseconds it took to zero out the - previous block group's inode table. This - minimizes the impact on the system performance - while file system's inode table is being initialized. - -discard Controls whether ext4 should issue discard/TRIM -nodiscard(*) commands to the underlying block device when - blocks are freed. This is useful for SSD devices - and sparse/thinly-provisioned LUNs, but it is off - by default until sufficient testing has been done. - -nouid32 Disables 32-bit UIDs and GIDs. This is for - interoperability with older kernels which only - store and expect 16-bit values. - -block_validity(*) These options enable or disable the in-kernel -noblock_validity facility for tracking filesystem metadata blocks - within internal data structures. This allows multi- - block allocator and other routines to notice - bugs or corrupted allocation bitmaps which cause - blocks to be allocated which overlap with - filesystem metadata blocks. - -dioread_lock Controls whether or not ext4 should use the DIO read -dioread_nolock locking. If the dioread_nolock option is specified - ext4 will allocate uninitialized extent before buffer - write and convert the extent to initialized after IO - completes. This approach allows ext4 code to avoid - using inode mutex, which improves scalability on high - speed storages. However this does not work with - data journaling and dioread_nolock option will be - ignored with kernel warning. Note that dioread_nolock - code path is only used for extent-based files. - Because of the restrictions this options comprises - it is off by default (e.g. dioread_lock). - -max_dir_size_kb=n This limits the size of directories so that any - attempt to expand them beyond the specified - limit in kilobytes will cause an ENOSPC error. - This is useful in memory constrained - environments, where a very large directory can - cause severe performance problems or even - provoke the Out Of Memory killer. (For example, - if there is only 512mb memory available, a 176mb - directory may seriously cramp the system's style.) - -i_version Enable 64-bit inode version support. This option is - off by default. - -dax Use direct access (no page cache). See - Documentation/filesystems/dax.txt. Note that - this option is incompatible with data=journal. -======================= ======================================================= - -Data Mode -========= -There are 3 different data modes: - -* writeback mode - - In data=writeback mode, ext4 does not journal data at all. This mode provides - a similar level of journaling as that of XFS, JFS, and ReiserFS in its default - mode - metadata journaling. A crash+recovery can cause incorrect data to - appear in files which were written shortly before the crash. This mode will - typically provide the best ext4 performance. - -* ordered mode - - In data=ordered mode, ext4 only officially journals metadata, but it logically - groups metadata information related to data changes with the data blocks into - a single unit called a transaction. When it's time to write the new metadata - out to disk, the associated data blocks are written first. In general, this - mode performs slightly slower than writeback but significantly faster than - journal mode. - -* journal mode - - data=journal mode provides full data and metadata journaling. All new data is - written to the journal first, and then to its final location. In the event of - a crash, the journal can be replayed, bringing both data and metadata into a - consistent state. This mode is the slowest except when data needs to be read - from and written to disk at the same time where it outperforms all others - modes. Enabling this mode will disable delayed allocation and O_DIRECT - support. - -/proc entries -============= - -Information about mounted ext4 file systems can be found in -/proc/fs/ext4. Each mounted filesystem will have a directory in -/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or -/proc/fs/ext4/dm-0). The files in each per-device directory are shown -in table below. - -Files in /proc/fs/ext4/<devname> - -================ ======= - File Content -================ ======= - mb_groups details of multiblock allocator buddy cache of free blocks -================ ======= - -/sys entries -============ - -Information about mounted ext4 file systems can be found in -/sys/fs/ext4. Each mounted filesystem will have a directory in -/sys/fs/ext4 based on its device name (i.e., /sys/fs/ext4/hdc or -/sys/fs/ext4/dm-0). The files in each per-device directory are shown -in table below. - -Files in /sys/fs/ext4/<devname>: - -(see also Documentation/ABI/testing/sysfs-fs-ext4) - -============================= ================================================= -File Content -============================= ================================================= - delayed_allocation_blocks This file is read-only and shows the number of - blocks that are dirty in the page cache, but - which do not have their location in the - filesystem allocated yet. - -inode_goal Tuning parameter which (if non-zero) controls - the goal inode used by the inode allocator in - preference to all other allocation heuristics. - This is intended for debugging use only, and - should be 0 on production systems. - -inode_readahead_blks Tuning parameter which controls the maximum - number of inode table blocks that ext4's inode - table readahead algorithm will pre-read into - the buffer cache - -lifetime_write_kbytes This file is read-only and shows the number of - kilobytes of data that have been written to this - filesystem since it was created. - - max_writeback_mb_bump The maximum number of megabytes the writeback - code will try to write out before move on to - another inode. - - mb_group_prealloc The multiblock allocator will round up allocation - requests to a multiple of this tuning parameter if - the stripe size is not set in the ext4 superblock - - mb_max_to_scan The maximum number of extents the multiblock - allocator will search to find the best extent - - mb_min_to_scan The minimum number of extents the multiblock - allocator will search to find the best extent - - mb_order2_req Tuning parameter which controls the minimum size - for requests (as a power of 2) where the buddy - cache is used - - mb_stats Controls whether the multiblock allocator should - collect statistics, which are shown during the - unmount. 1 means to collect statistics, 0 means - not to collect statistics - - mb_stream_req Files which have fewer blocks than this tunable - parameter will have their blocks allocated out - of a block group specific preallocation pool, so - that small files are packed closely together. - Each large file will have its blocks allocated - out of its own unique preallocation pool. - - session_write_kbytes This file is read-only and shows the number of - kilobytes of data that have been written to this - filesystem since it was mounted. - - reserved_clusters This is RW file and contains number of reserved - clusters in the file system which will be used - in the specific situations to avoid costly - zeroout, unexpected ENOSPC, or possible data - loss. The default is 2% or 4096 clusters, - whichever is smaller and this can be changed - however it can never exceed number of clusters - in the file system. If there is not enough space - for the reserved space when mounting the file - mount will _not_ fail. -============================= ================================================= - -Ioctls -====== - -There is some Ext4 specific functionality which can be accessed by applications -through the system call interfaces. The list of all Ext4 specific ioctls are -shown in the table below. - -Table of Ext4 specific ioctls - -============================= ================================================= -Ioctl Description -============================= ================================================= - EXT4_IOC_GETFLAGS Get additional attributes associated with inode. - The ioctl argument is an integer bitfield, with - bit values described in ext4.h. This ioctl is an - alias for FS_IOC_GETFLAGS. - - EXT4_IOC_SETFLAGS Set additional attributes associated with inode. - The ioctl argument is an integer bitfield, with - bit values described in ext4.h. This ioctl is an - alias for FS_IOC_SETFLAGS. - - EXT4_IOC_GETVERSION - EXT4_IOC_GETVERSION_OLD - Get the inode i_generation number stored for - each inode. The i_generation number is normally - changed only when new inode is created and it is - particularly useful for network filesystems. The - '_OLD' version of this ioctl is an alias for - FS_IOC_GETVERSION. - - EXT4_IOC_SETVERSION - EXT4_IOC_SETVERSION_OLD - Set the inode i_generation number stored for - each inode. The '_OLD' version of this ioctl - is an alias for FS_IOC_SETVERSION. - - EXT4_IOC_GROUP_EXTEND This ioctl has the same purpose as the resize - mount option. It allows to resize filesystem - to the end of the last existing block group, - further resize has to be done with resize2fs, - either online, or offline. The argument points - to the unsigned logn number representing the - filesystem new block count. - - EXT4_IOC_MOVE_EXT Move the block extents from orig_fd (the one - this ioctl is pointing to) to the donor_fd (the - one specified in move_extent structure passed - as an argument to this ioctl). Then, exchange - inode metadata between orig_fd and donor_fd. - This is especially useful for online - defragmentation, because the allocator has the - opportunity to allocate moved blocks better, - ideally into one contiguous extent. - - EXT4_IOC_GROUP_ADD Add a new group descriptor to an existing or - new group descriptor block. The new group - descriptor is described by ext4_new_group_input - structure, which is passed as an argument to - this ioctl. This is especially useful in - conjunction with EXT4_IOC_GROUP_EXTEND, - which allows online resize of the filesystem - to the end of the last existing block group. - Those two ioctls combined is used in userspace - online resize tool (e.g. resize2fs). - - EXT4_IOC_MIGRATE This ioctl operates on the filesystem itself. - It converts (migrates) ext3 indirect block mapped - inode to ext4 extent mapped inode by walking - through indirect block mapping of the original - inode and converting contiguous block ranges - into ext4 extents of the temporary inode. Then, - inodes are swapped. This ioctl might help, when - migrating from ext3 to ext4 filesystem, however - suggestion is to create fresh ext4 filesystem - and copy data from the backup. Note, that - filesystem has to support extents for this ioctl - to work. - - EXT4_IOC_ALLOC_DA_BLKS Force all of the delay allocated blocks to be - allocated to preserve application-expected ext3 - behaviour. Note that this will also start - triggering a write of the data blocks, but this - behaviour may change in the future as it is - not necessary and has been done this way only - for sake of simplicity. - - EXT4_IOC_RESIZE_FS Resize the filesystem to a new size. The number - of blocks of resized filesystem is passed in via - 64 bit integer argument. The kernel allocates - bitmaps and inode table, the userspace tool thus - just passes the new number of blocks. - - EXT4_IOC_SWAP_BOOT Swap i_blocks and associated attributes - (like i_blocks, i_size, i_flags, ...) from - the specified inode with inode - EXT4_BOOT_LOADER_INO (#5). This is typically - used to store a boot loader in a secure part of - the filesystem, where it can't be changed by a - normal user by accident. - The data blocks of the previous boot loader - will be associated with the given inode. -============================= ================================================= - -References -========== - -kernel source: <file:fs/ext4/> - <file:fs/jbd2/> - -programs: http://e2fsprogs.sourceforge.net/ - -useful links: http://fedoraproject.org/wiki/ext3-devel - http://www.bullopensource.org/ext4/ - http://ext4.wiki.kernel.org/index.php/Main_Page - http://fedoraproject.org/wiki/Features/Ext4 diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/globals.rst index 368bf7662b96..368bf7662b96 100644 --- a/Documentation/filesystems/ext4/ondisk/globals.rst +++ b/Documentation/filesystems/ext4/globals.rst diff --git a/Documentation/filesystems/ext4/ondisk/group_descr.rst b/Documentation/filesystems/ext4/group_descr.rst index 759827e5d2cf..0f783ed88592 100644 --- a/Documentation/filesystems/ext4/ondisk/group_descr.rst +++ b/Documentation/filesystems/ext4/group_descr.rst @@ -43,7 +43,7 @@ entire bitmap. The block group descriptor is laid out in ``struct ext4_group_desc``. .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -157,7 +157,7 @@ The block group descriptor is laid out in ``struct ext4_group_desc``. Block group flags can be any combination of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value diff --git a/Documentation/filesystems/ext4/ondisk/ifork.rst b/Documentation/filesystems/ext4/ifork.rst index 5dbe3b2b121a..b9816d5a896b 100644 --- a/Documentation/filesystems/ext4/ondisk/ifork.rst +++ b/Documentation/filesystems/ext4/ifork.rst @@ -68,7 +68,7 @@ The extent tree header is recorded in ``struct ext4_extent_header``, which is 12 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -104,7 +104,7 @@ Internal nodes of the extent tree, also known as index nodes, are recorded as ``struct ext4_extent_idx``, and are 12 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -134,7 +134,7 @@ Leaf nodes of the extent tree are recorded as ``struct ext4_extent``, and are also 12 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -174,7 +174,7 @@ including) the checksum itself. ``struct ext4_extent_tail`` is 4 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset diff --git a/Documentation/filesystems/ext4/index.rst b/Documentation/filesystems/ext4/index.rst index 71121605558c..3be3e54d480d 100644 --- a/Documentation/filesystems/ext4/index.rst +++ b/Documentation/filesystems/ext4/index.rst @@ -1,17 +1,14 @@ .. SPDX-License-Identifier: GPL-2.0 -=============== -ext4 Filesystem -=============== - -General usage and on-disk artifacts writen by ext4. More documentation may -be ported from the wiki as time permits. This should be considered the -canonical source of information as the details here have been reviewed by -the ext4 community. +=================================== +ext4 Data Structures and Algorithms +=================================== .. toctree:: - :maxdepth: 5 + :maxdepth: 6 :numbered: - ext4 - ondisk/index + about.rst + overview.rst + globals.rst + dynamic.rst diff --git a/Documentation/filesystems/ext4/ondisk/inlinedata.rst b/Documentation/filesystems/ext4/inlinedata.rst index d1075178ce0b..d1075178ce0b 100644 --- a/Documentation/filesystems/ext4/ondisk/inlinedata.rst +++ b/Documentation/filesystems/ext4/inlinedata.rst diff --git a/Documentation/filesystems/ext4/ondisk/inodes.rst b/Documentation/filesystems/ext4/inodes.rst index 655ce898f3f5..6bd35e506b6f 100644 --- a/Documentation/filesystems/ext4/ondisk/inodes.rst +++ b/Documentation/filesystems/ext4/inodes.rst @@ -29,8 +29,9 @@ and the inode structure itself. The inode table entry is laid out in ``struct ext4_inode``. .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 + :class: longtable * - Offset - Size @@ -176,7 +177,7 @@ The inode table entry is laid out in ``struct ext4_inode``. The ``i_mode`` value is a combination of the following flags: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -227,7 +228,7 @@ The ``i_mode`` value is a combination of the following flags: The ``i_flags`` field is a combination of these values: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -314,7 +315,7 @@ The ``osd1`` field has multiple meanings depending on the creator: Linux: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -331,7 +332,7 @@ Linux: Hurd: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -346,7 +347,7 @@ Hurd: Masix: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -365,7 +366,7 @@ The ``osd2`` field has multiple meanings depending on the filesystem creator: Linux: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -402,7 +403,7 @@ Linux: Hurd: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -433,7 +434,7 @@ Hurd: Masix: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset diff --git a/Documentation/filesystems/ext4/ondisk/journal.rst b/Documentation/filesystems/ext4/journal.rst index e7031af86876..ea613ee701f5 100644 --- a/Documentation/filesystems/ext4/ondisk/journal.rst +++ b/Documentation/filesystems/ext4/journal.rst @@ -48,7 +48,7 @@ Layout Generally speaking, the journal has this format: .. list-table:: - :widths: 1 1 78 + :widths: 16 48 16 :header-rows: 1 * - Superblock @@ -76,7 +76,7 @@ The journal superblock will be in the next full block after the superblock. .. list-table:: - :widths: 1 1 1 1 76 + :widths: 12 12 12 32 12 :header-rows: 1 * - 1024 bytes of padding @@ -98,7 +98,7 @@ Every block in the journal starts with a common 12-byte header ``struct journal_header_s``: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -124,7 +124,7 @@ Every block in the journal starts with a common 12-byte header The journal block type can be any one of: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -154,7 +154,7 @@ The journal superblock is recorded as ``struct journal_superblock_s``, which is 1024 bytes long: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -264,7 +264,7 @@ which is 1024 bytes long: The journal compat features are any combination of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -278,7 +278,7 @@ The journal compat features are any combination of the following: The journal incompat features are any combination of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -306,7 +306,7 @@ Journal checksum type codes are one of the following. crc32 or crc32c are the most likely choices. .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -330,7 +330,7 @@ described by a data structure, but here is the block structure anyway. Descriptor blocks consume at least 36 bytes, but use a full block: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -355,7 +355,7 @@ defined as ``struct journal_block_tag3_s``, which looks like the following. The size is 16 or 32 bytes. .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -400,7 +400,7 @@ following. The size is 16 or 32 bytes. The journal tag flags are any combination of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -421,7 +421,7 @@ is defined as ``struct journal_block_tag_s``, which looks like the following. The size is 8, 12, 24, or 28 bytes: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -471,7 +471,7 @@ JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a ``struct jbd2_journal_block_tail``, which looks like this: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -513,7 +513,7 @@ Revocation blocks are described in length, but use a full block: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -543,7 +543,7 @@ JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the revocation block is a ``struct jbd2_journal_revoke_tail``, which has this format: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -567,7 +567,7 @@ The commit block is described by ``struct commit_header``, which is 32 bytes long (but uses a full block): .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset diff --git a/Documentation/filesystems/ext4/ondisk/mmp.rst b/Documentation/filesystems/ext4/mmp.rst index b7d7a3137f80..25660981d93c 100644 --- a/Documentation/filesystems/ext4/ondisk/mmp.rst +++ b/Documentation/filesystems/ext4/mmp.rst @@ -32,7 +32,7 @@ The checksum is calculated against the FS UUID and the MMP structure. The MMP structure (``struct mmp_struct``) is as follows: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 12 20 40 :header-rows: 1 * - Offset diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst deleted file mode 100644 index f7d082c3a435..000000000000 --- a/Documentation/filesystems/ext4/ondisk/index.rst +++ /dev/null @@ -1,9 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -============================== -Data Structures and Algorithms -============================== -.. include:: about.rst -.. include:: overview.rst -.. include:: globals.rst -.. include:: dynamic.rst diff --git a/Documentation/filesystems/ext4/ondisk/overview.rst b/Documentation/filesystems/ext4/overview.rst index cbab18baba12..cbab18baba12 100644 --- a/Documentation/filesystems/ext4/ondisk/overview.rst +++ b/Documentation/filesystems/ext4/overview.rst diff --git a/Documentation/filesystems/ext4/ondisk/special_inodes.rst b/Documentation/filesystems/ext4/special_inodes.rst index a82f70c9baeb..9061aabba827 100644 --- a/Documentation/filesystems/ext4/ondisk/special_inodes.rst +++ b/Documentation/filesystems/ext4/special_inodes.rst @@ -6,7 +6,7 @@ Special inodes ext4 reserves some inode for special features, as follows: .. list-table:: - :widths: 1 79 + :widths: 6 70 :header-rows: 1 * - inode Number diff --git a/Documentation/filesystems/ext4/ondisk/super.rst b/Documentation/filesystems/ext4/super.rst index 5f81dd87e0b9..04ff079a2acf 100644 --- a/Documentation/filesystems/ext4/ondisk/super.rst +++ b/Documentation/filesystems/ext4/super.rst @@ -19,7 +19,7 @@ The ext4 superblock is laid out as follows in ``struct ext4_super_block``: .. list-table:: - :widths: 1 1 1 77 + :widths: 8 8 24 40 :header-rows: 1 * - Offset @@ -483,7 +483,7 @@ The ext4 superblock is laid out as follows in The superblock state is some combination of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -500,7 +500,7 @@ The superblock state is some combination of the following: The superblock error policy is one of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -517,7 +517,7 @@ The superblock error policy is one of the following: The filesystem creator is one of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -538,7 +538,7 @@ The filesystem creator is one of the following: The superblock revision is one of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -556,7 +556,7 @@ The superblock compatible features field is a combination of any of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -595,7 +595,7 @@ The superblock incompatible features field is a combination of any of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -647,7 +647,7 @@ The superblock read-only compatible features field is a combination of any of the following: .. list-table:: - :widths: 1 79 + :widths: 16 64 :header-rows: 1 * - Value @@ -702,7 +702,7 @@ the following: The ``s_def_hash_version`` field is one of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -725,7 +725,7 @@ The ``s_def_hash_version`` field is one of the following: The ``s_default_mount_opts`` field is any combination of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -767,7 +767,7 @@ The ``s_default_mount_opts`` field is any combination of the following: The ``s_flags`` field is any combination of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value @@ -784,7 +784,7 @@ The ``s_flags`` field is any combination of the following: The ``s_encrypt_algos`` list can contain any of the following: .. list-table:: - :widths: 1 79 + :widths: 8 72 :header-rows: 1 * - Value diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index e5edd29687b5..e46c2147ddf8 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -172,9 +172,10 @@ fault_type=%d Support configuring fault injection type, should be FAULT_DIR_DEPTH 0x000000100 FAULT_EVICT_INODE 0x000000200 FAULT_TRUNCATE 0x000000400 - FAULT_IO 0x000000800 + FAULT_READ_IO 0x000000800 FAULT_CHECKPOINT 0x000001000 FAULT_DISCARD 0x000002000 + FAULT_WRITE_IO 0x000004000 mode=%s Control block allocation mode which supports "adaptive" and "lfs". In "lfs" mode, there should be no random writes towards main area. @@ -211,6 +212,11 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix", non-atomic files likewise "nobarrier" mount option. test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt context. The fake fscrypt context is used by xfstests. +checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable" + to reenable checkpointing. Is enabled by default. While + disabled, any unmounting or unexpected shutdowns will cause + the filesystem contents to appear as they did when the + filesystem was mounted with that option. ================================================================================ DEBUGFS ENTRIES diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX deleted file mode 100644 index 53f3b596ac0d..000000000000 --- a/Documentation/filesystems/nfs/00-INDEX +++ /dev/null @@ -1,26 +0,0 @@ -00-INDEX - - this file (nfs-related documentation). -Exporting - - explanation of how to make filesystems exportable. -fault_injection.txt - - information for using fault injection on the server -knfsd-stats.txt - - statistics which the NFS server makes available to user space. -nfs.txt - - nfs client, and DNS resolution for fs_locations. -nfs41-server.txt - - info on the Linux server implementation of NFSv4 minor version 1. -nfs-rdma.txt - - how to install and setup the Linux NFS/RDMA client and server software -nfsd-admin-interfaces.txt - - Administrative interfaces for nfsd. -nfsroot.txt - - short guide on setting up a diskless box with NFS root filesystem. -pnfs.txt - - short explanation of some of the internals of the pnfs client code -rpc-cache.txt - - introduction to the caching mechanisms in the sunrpc layer. -idmapper.txt - - information for configuring request-keys to be used by idmapper -rpc-server-gss.txt - - Information on GSS authentication support in the NFS Server diff --git a/Documentation/fmc/00-INDEX b/Documentation/fmc/00-INDEX deleted file mode 100644 index 431c69570f43..000000000000 --- a/Documentation/fmc/00-INDEX +++ /dev/null @@ -1,38 +0,0 @@ - -Documentation in this directory comes from sections of the manual we -wrote for the externally-developed fmc-bus package. The complete -manual as of today (2013-02) is available in PDF format at -http://www.ohwr.org/projects/fmc-bus/files - -00-INDEX - - this file. - -FMC-and-SDB.txt - - What are FMC and SDB, basic concepts for this framework - -API.txt - - The functions that are exported by the bus driver - -parameters.txt - - The module parameters - -carrier.txt - - writing a carrier (a device) - -mezzanine.txt - - writing code for your mezzanine (a driver) - -identifiers.txt - - how identification and matching works - -fmc-fakedev.txt - - about drivers/fmc/fmc-fakedev.ko - -fmc-trivial.txt - - about drivers/fmc/fmc-trivial.ko - -fmc-write-eeprom.txt - - about drivers/fmc/fmc-write-eeprom.ko - -fmc-chardev.txt - - about drivers/fmc/fmc-chardev.ko diff --git a/Documentation/gpio/00-INDEX b/Documentation/gpio/00-INDEX deleted file mode 100644 index 17e19a68058f..000000000000 --- a/Documentation/gpio/00-INDEX +++ /dev/null @@ -1,4 +0,0 @@ -00-INDEX - - This file -sysfs.txt - - Information about the GPIO sysfs interface diff --git a/Documentation/ide/00-INDEX b/Documentation/ide/00-INDEX deleted file mode 100644 index 22f98ca79539..000000000000 --- a/Documentation/ide/00-INDEX +++ /dev/null @@ -1,14 +0,0 @@ -00-INDEX - - this file -ChangeLog.ide-cd.1994-2004 - - ide-cd changelog -ChangeLog.ide-floppy.1996-2002 - - ide-floppy changelog -ChangeLog.ide-tape.1995-2002 - - ide-tape changelog -ide-tape.txt - - info on the IDE ATAPI streaming tape driver -ide.txt - - important info for users of ATA devices (IDE/EIDE disks and CD-ROMS). -warm-plug-howto.txt - - using sysfs to remove and add IDE devices.
\ No newline at end of file diff --git a/Documentation/index.rst b/Documentation/index.rst index 5db7e87c7cb1..c858c2e66e36 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -22,10 +22,7 @@ The following describes the license of the Linux kernel source code (GPLv2), how to properly mark the license of individual files in the source tree, as well as links to the full license text. -.. toctree:: - :maxdepth: 2 - - process/license-rules.rst +* :ref:`kernel_licensing` User-oriented documentation --------------------------- diff --git a/Documentation/ioctl/00-INDEX b/Documentation/ioctl/00-INDEX deleted file mode 100644 index c1a925787950..000000000000 --- a/Documentation/ioctl/00-INDEX +++ /dev/null @@ -1,12 +0,0 @@ -00-INDEX - - this file -botching-up-ioctls.txt - - how to avoid botching up ioctls -cdrom.txt - - summary of CDROM ioctl calls -hdio.txt - - summary of HDIO_ ioctl calls -ioctl-decoding.txt - - how to decode the bits of an IOCTL code -ioctl-number.txt - - how to implement and register device/driver ioctl calls diff --git a/Documentation/isdn/00-INDEX b/Documentation/isdn/00-INDEX deleted file mode 100644 index 2d1889b6c1fa..000000000000 --- a/Documentation/isdn/00-INDEX +++ /dev/null @@ -1,42 +0,0 @@ -00-INDEX - - this file (info on ISDN implementation for Linux) -CREDITS - - list of the kind folks that brought you this stuff. -HiSax.cert - - information about the ITU approval certification of the HiSax driver. -INTERFACE - - description of isdn4linux Link Level and Hardware Level interfaces. -INTERFACE.fax - - description of the fax subinterface of isdn4linux. -INTERFACE.CAPI - - description of kernel CAPI Link Level to Hardware Level interface. -README - - general info on what you need and what to do for Linux ISDN. -README.FAQ - - general info for FAQ. -README.HiSax - - info on the HiSax driver which replaces the old teles. -README.audio - - info for running audio over ISDN. -README.avmb1 - - info on driver for AVM-B1 ISDN card. -README.concap - - info on "CONCAP" encapsulation protocol interface used for X.25. -README.diversion - - info on module for isdn diversion services. -README.fax - - info for using Fax over ISDN. -README.gigaset - - info on the drivers for Siemens Gigaset ISDN adapters -README.hfc-pci - - info on hfc-pci based cards. -README.hysdn - - info on driver for Hypercope active HYSDN cards -README.mISDN - - info on the Modular ISDN subsystem (mISDN) -README.syncppp - - info on running Sync PPP over ISDN. -README.x25 - - info for running X.25 over ISDN. -syncPPP.FAQ - - frequently asked questions about running PPP over ISDN. diff --git a/Documentation/kbuild/00-INDEX b/Documentation/kbuild/00-INDEX deleted file mode 100644 index 8c5e6aa78004..000000000000 --- a/Documentation/kbuild/00-INDEX +++ /dev/null @@ -1,14 +0,0 @@ -00-INDEX - - this file: info on the kernel build process -headers_install.txt - - how to export Linux headers for use by userspace -kbuild.txt - - developer information on kbuild -kconfig.txt - - usage help for make *config -kconfig-language.txt - - specification of Config Language, the language in Kconfig files -makefiles.txt - - developer information for linux kernel makefiles -modules.txt - - how to build modules and to install them diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX deleted file mode 100644 index 86169dc766f7..000000000000 --- a/Documentation/laptops/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - This file -asus-laptop.txt - - information on the Asus Laptop Extras driver. -disk-shock-protection.txt - - information on hard disk shock protection. -laptop-mode.txt - - how to conserve battery power using laptop-mode. -sony-laptop.txt - - Sony Notebook Control Driver (SNC) Readme. -sonypi.txt - - info on Linux Sony Programmable I/O Device support. -thinkpad-acpi.txt - - information on the (IBM and Lenovo) ThinkPad ACPI Extras driver. -toshiba_haps.txt - - information on the Toshiba HDD Active Protection Sensor driver. diff --git a/Documentation/leds/00-INDEX b/Documentation/leds/00-INDEX deleted file mode 100644 index ae626b29a740..000000000000 --- a/Documentation/leds/00-INDEX +++ /dev/null @@ -1,32 +0,0 @@ -00-INDEX - - This file -leds-blinkm.txt - - Driver for BlinkM LED-devices. -leds-class.txt - - documents LED handling under Linux. -leds-class-flash.txt - - documents flash LED handling under Linux. -leds-lm3556.txt - - notes on how to use the leds-lm3556 driver. -leds-lp3944.txt - - notes on how to use the leds-lp3944 driver. -leds-lp5521.txt - - notes on how to use the leds-lp5521 driver. -leds-lp5523.txt - - notes on how to use the leds-lp5523 driver. -leds-lp5562.txt - - notes on how to use the leds-lp5562 driver. -leds-lp55xx.txt - - description about lp55xx common driver. -leds-lm3556.txt - - notes on how to use the leds-lm3556 driver. -leds-mlxcpld.txt - - notes on how to use the leds-mlxcpld driver. -ledtrig-oneshot.txt - - One-shot LED trigger for both sporadic and dense events. -ledtrig-transient.txt - - LED Transient Trigger, one shot timer activation. -ledtrig-usbport.txt - - notes on how to use the drivers/usb/core/ledtrig-usbport.c trigger. -uleds.txt - - notes on how to use the uleds driver. diff --git a/Documentation/locking/00-INDEX b/Documentation/locking/00-INDEX deleted file mode 100644 index c256c9bee2a4..000000000000 --- a/Documentation/locking/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - this file. -lockdep-design.txt - - documentation on the runtime locking correctness validator. -lockstat.txt - - info on collecting statistics on locks (and contention). -mutex-design.txt - - info on the generic mutex subsystem. -rt-mutex-design.txt - - description of the RealTime mutex implementation design. -rt-mutex.txt - - desc. of RT-mutex subsystem with PI (Priority Inheritance) support. -spinlocks.txt - - info on using spinlocks to provide exclusive access in kernel. -ww-mutex-design.txt - - Intro to Mutex wait/would deadlock handling.s diff --git a/Documentation/m68k/00-INDEX b/Documentation/m68k/00-INDEX deleted file mode 100644 index 2be8c6b00e74..000000000000 --- a/Documentation/m68k/00-INDEX +++ /dev/null @@ -1,7 +0,0 @@ -00-INDEX - - this file -README.buddha - - Amiga Buddha and Catweasel IDE Driver -kernel-options.txt - - command line options for Linux/m68k - diff --git a/Documentation/mips/00-INDEX b/Documentation/mips/00-INDEX deleted file mode 100644 index 8ae9cffc2262..000000000000 --- a/Documentation/mips/00-INDEX +++ /dev/null @@ -1,4 +0,0 @@ -00-INDEX - - this file. -AU1xxx_IDE.README - - README for MIPS AU1XXX IDE driver. diff --git a/Documentation/mmc/00-INDEX b/Documentation/mmc/00-INDEX deleted file mode 100644 index 4623bc0aa0bb..000000000000 --- a/Documentation/mmc/00-INDEX +++ /dev/null @@ -1,10 +0,0 @@ -00-INDEX - - this file -mmc-dev-attrs.txt - - info on SD and MMC device attributes -mmc-dev-parts.txt - - info on SD and MMC device partitions -mmc-async-req.txt - - info on mmc asynchronous requests -mmc-tools.txt - - info on mmc-utils tools diff --git a/Documentation/netlabel/00-INDEX b/Documentation/netlabel/00-INDEX deleted file mode 100644 index 837bf35990e2..000000000000 --- a/Documentation/netlabel/00-INDEX +++ /dev/null @@ -1,10 +0,0 @@ -00-INDEX - - this file. -cipso_ipv4.txt - - documentation on the IPv4 CIPSO protocol engine. -draft-ietf-cipso-ipsecurity-01.txt - - IETF draft of the CIPSO protocol, dated 16 July 1992. -introduction.txt - - NetLabel introduction, READ THIS FIRST. -lsm_interface.txt - - documentation on the NetLabel kernel security module API. diff --git a/Documentation/netlabel/cipso_ipv4.txt b/Documentation/netlabel/cipso_ipv4.txt index 93dacb132c3c..a6075481fd60 100644 --- a/Documentation/netlabel/cipso_ipv4.txt +++ b/Documentation/netlabel/cipso_ipv4.txt @@ -6,11 +6,12 @@ May 17, 2006 * Overview -The NetLabel CIPSO/IPv4 protocol engine is based on the IETF Commercial IP -Security Option (CIPSO) draft from July 16, 1992. A copy of this draft can be -found in this directory, consult '00-INDEX' for the filename. While the IETF -draft never made it to an RFC standard it has become a de-facto standard for -labeled networking and is used in many trusted operating systems. +The NetLabel CIPSO/IPv4 protocol engine is based on the IETF Commercial +IP Security Option (CIPSO) draft from July 16, 1992. A copy of this +draft can be found in this directory +(draft-ietf-cipso-ipsecurity-01.txt). While the IETF draft never made +it to an RFC standard it has become a de-facto standard for labeled +networking and is used in many trusted operating systems. * Outbound Packet Processing diff --git a/Documentation/netlabel/introduction.txt b/Documentation/netlabel/introduction.txt index 5ecd8d1dcf4e..3caf77bcff0f 100644 --- a/Documentation/netlabel/introduction.txt +++ b/Documentation/netlabel/introduction.txt @@ -22,7 +22,7 @@ refrain from calling the protocol engines directly, instead they should use the NetLabel kernel security module API described below. Detailed information about each NetLabel protocol engine can be found in this -directory, consult '00-INDEX' for filenames. +directory. * Communication Layer diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX deleted file mode 100644 index eb0754475dd0..000000000000 --- a/Documentation/networking/00-INDEX +++ /dev/null @@ -1,214 +0,0 @@ -00-INDEX - - this file -3c509.txt - - information on the 3Com Etherlink III Series Ethernet cards. -6pack.txt - - info on the 6pack protocol, an alternative to KISS for AX.25 -LICENSE.qla3xxx - - GPLv2 for QLogic Linux Networking HBA Driver -LICENSE.qlge - - GPLv2 for QLogic Linux qlge NIC Driver -LICENSE.qlcnic - - GPLv2 for QLogic Linux qlcnic NIC Driver -PLIP.txt - - PLIP: The Parallel Line Internet Protocol device driver -README.ipw2100 - - README for the Intel PRO/Wireless 2100 driver. -README.ipw2200 - - README for the Intel PRO/Wireless 2915ABG and 2200BG driver. -README.sb1000 - - info on General Instrument/NextLevel SURFboard1000 cable modem. -altera_tse.txt - - Altera Triple-Speed Ethernet controller. -arcnet-hardware.txt - - tons of info on ARCnet, hubs, jumper settings for ARCnet cards, etc. -arcnet.txt - - info on the using the ARCnet driver itself. -atm.txt - - info on where to get ATM programs and support for Linux. -ax25.txt - - info on using AX.25 and NET/ROM code for Linux -baycom.txt - - info on the driver for Baycom style amateur radio modems -bonding.txt - - Linux Ethernet Bonding Driver HOWTO: link aggregation in Linux. -bridge.txt - - where to get user space programs for ethernet bridging with Linux. -cdc_mbim.txt - - 3G/LTE USB modem (Mobile Broadband Interface Model) -checksum-offloads.txt - - Explanation of checksum offloads; LCO, RCO -cops.txt - - info on the COPS LocalTalk Linux driver -cs89x0.txt - - the Crystal LAN (CS8900/20-based) Ethernet ISA adapter driver -cxacru.txt - - Conexant AccessRunner USB ADSL Modem -cxacru-cf.py - - Conexant AccessRunner USB ADSL Modem configuration file parser -cxgb.txt - - Release Notes for the Chelsio N210 Linux device driver. -dccp.txt - - the Datagram Congestion Control Protocol (DCCP) (RFC 4340..42). -dctcp.txt - - DataCenter TCP congestion control -de4x5.txt - - the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver -decnet.txt - - info on using the DECnet networking layer in Linux. -defza.txt - - the DEC FDDIcontroller 700 (DEFZA-xx) TURBOchannel FDDI driver -dl2k.txt - - README for D-Link DL2000-based Gigabit Ethernet Adapters (dl2k.ko). -dm9000.txt - - README for the Simtec DM9000 Network driver. -dmfe.txt - - info on the Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver. -dns_resolver.txt - - The DNS resolver module allows kernel servies to make DNS queries. -driver.txt - - Softnet driver issues. -ena.txt - - info on Amazon's Elastic Network Adapter (ENA) -eql.txt - - serial IP load balancing -fib_trie.txt - - Level Compressed Trie (LC-trie) notes: a structure for routing. -filter.txt - - Linux Socket Filtering -fore200e.txt - - FORE Systems PCA-200E/SBA-200E ATM NIC driver info. -framerelay.txt - - info on using Frame Relay/Data Link Connection Identifier (DLCI). -gen_stats.txt - - Generic networking statistics for netlink users. -generic-hdlc.txt - - The generic High Level Data Link Control (HDLC) layer. -generic_netlink.txt - - info on Generic Netlink -gianfar.txt - - Gianfar Ethernet Driver. -ieee802154.txt - - Linux IEEE 802.15.4 implementation, API and drivers -ip-sysctl.txt - - /proc/sys/net/ipv4/* variables -ip_dynaddr.txt - - IP dynamic address hack e.g. for auto-dialup links -ipddp.txt - - AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation -iphase.txt - - Interphase PCI ATM (i)Chip IA Linux driver info. -ipsec.txt - - Note on not compressing IPSec payload and resulting failed policy check. -ipv6.txt - - Options to the ipv6 kernel module. -ipvs-sysctl.txt - - Per-inode explanation of the /proc/sys/net/ipv4/vs interface. -irda.txt - - where to get IrDA (infrared) utilities and info for Linux. -l2tp.txt - - User guide to the L2TP tunnel protocol. -lapb-module.txt - - programming information of the LAPB module. -ltpc.txt - - the Apple or Farallon LocalTalk PC card driver -mac80211-auth-assoc-deauth.txt - - authentication and association / deauth-disassoc with max80211 -mac80211-injection.txt - - HOWTO use packet injection with mac80211 -multiqueue.txt - - HOWTO for multiqueue network device support. -netconsole.txt - - The network console module netconsole.ko: configuration and notes. -netdev-features.txt - - Network interface features API description. -netdevices.txt - - info on network device driver functions exported to the kernel. -netif-msg.txt - - Design of the network interface message level setting (NETIF_MSG_*). -netlink_mmap.txt - - memory mapped I/O with netlink -nf_conntrack-sysctl.txt - - list of netfilter-sysctl knobs. -nfc.txt - - The Linux Near Field Communication (NFS) subsystem. -openvswitch.txt - - Open vSwitch developer documentation. -operstates.txt - - Overview of network interface operational states. -packet_mmap.txt - - User guide to memory mapped packet socket rings (PACKET_[RT]X_RING). -phonet.txt - - The Phonet packet protocol used in Nokia cellular modems. -phy.txt - - The PHY abstraction layer. -pktgen.txt - - User guide to the kernel packet generator (pktgen.ko). -policy-routing.txt - - IP policy-based routing -ppp_generic.txt - - Information about the generic PPP driver. -proc_net_tcp.txt - - Per inode overview of the /proc/net/tcp and /proc/net/tcp6 interfaces. -radiotap-headers.txt - - Background on radiotap headers. -ray_cs.txt - - Raylink Wireless LAN card driver info. -rds.txt - - Background on the reliable, ordered datagram delivery method RDS. -regulatory.txt - - Overview of the Linux wireless regulatory infrastructure. -rxrpc.txt - - Guide to the RxRPC protocol. -s2io.txt - - Release notes for Neterion Xframe I/II 10GbE driver. -scaling.txt - - Explanation of network scaling techniques: RSS, RPS, RFS, aRFS, XPS. -sctp.txt - - Notes on the Linux kernel implementation of the SCTP protocol. -secid.txt - - Explanation of the secid member in flow structures. -skfp.txt - - SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info. -smc9.txt - - the driver for SMC's 9000 series of Ethernet cards -spider_net.txt - - README for the Spidernet Driver (as found in PS3 / Cell BE). -stmmac.txt - - README for the STMicro Synopsys Ethernet driver. -tc-actions-env-rules.txt - - rules for traffic control (tc) actions. -timestamping.txt - - overview of network packet timestamping variants. -tcp-thin.txt - - kernel tuning options for low rate 'thin' TCP streams. -team.txt - - pointer to information for ethernet teaming devices. -tlan.txt - - ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info. -tproxy.txt - - Transparent proxy support user guide. -tuntap.txt - - TUN/TAP device driver, allowing user space Rx/Tx of packets. -udplite.txt - - UDP-Lite protocol (RFC 3828) introduction. -vortex.txt - - info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards. -vxge.txt - - README for the Neterion X3100 PCIe Server Adapter. -vxlan.txt - - Virtual extensible LAN overview -x25.txt - - general info on X.25 development. -x25-iface.txt - - description of the X.25 Packet Layer to LAPB device interface. -xfrm_device.txt - - description of XFRM offload API -xfrm_proc.txt - - description of the statistics package for XFRM. -xfrm_sync.txt - - sync patches for XFRM enable migration of an SA between hosts. -xfrm_sysctl.txt - - description of the XFRM configuration options. -z8530drv.txt - - info about Linux driver for Z8530 based HDLC cards for AX.25 diff --git a/Documentation/parisc/00-INDEX b/Documentation/parisc/00-INDEX deleted file mode 100644 index cbd060961f43..000000000000 --- a/Documentation/parisc/00-INDEX +++ /dev/null @@ -1,6 +0,0 @@ -00-INDEX - - this file. -debugging - - some debugging hints for real-mode code -registers - - current/planned usage of registers diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX deleted file mode 100644 index 7f3c2def2cac..000000000000 --- a/Documentation/power/00-INDEX +++ /dev/null @@ -1,44 +0,0 @@ -00-INDEX - - This file -apm-acpi.txt - - basic info about the APM and ACPI support. -basic-pm-debugging.txt - - Debugging suspend and resume -charger-manager.txt - - Battery charger management. -admin-guide/devices.rst - - How drivers interact with system-wide power management -drivers-testing.txt - - Testing suspend and resume support in device drivers -freezing-of-tasks.txt - - How processes and controlled during suspend -interface.txt - - Power management user interface in /sys/power -opp.txt - - Operating Performance Point library -pci.txt - - How the PCI Subsystem Does Power Management -pm_qos_interface.txt - - info on Linux PM Quality of Service interface -power_supply_class.txt - - Tells userspace about battery, UPS, AC or DC power supply properties -runtime_pm.txt - - Power management framework for I/O devices. -s2ram.txt - - How to get suspend to ram working (and debug it when it isn't) -states.txt - - System power management states -suspend-and-cpuhotplug.txt - - Explains the interaction between Suspend-to-RAM (S3) and CPU hotplug -swsusp-and-swap-files.txt - - Using swap files with software suspend (to disk) -swsusp-dmcrypt.txt - - How to use dm-crypt and software suspend (to disk) together -swsusp.txt - - Goals, implementation, and usage of software suspend (ACPI S3) -tricks.txt - - How to trick software suspend (to disk) into working when it isn't -userland-swsusp.txt - - Experimental implementation of software suspend in userspace -video.txt - - Video issues during resume from suspend diff --git a/Documentation/powerpc/00-INDEX b/Documentation/powerpc/00-INDEX deleted file mode 100644 index 9dc845cf7d88..000000000000 --- a/Documentation/powerpc/00-INDEX +++ /dev/null @@ -1,34 +0,0 @@ -Index of files in Documentation/powerpc. If you think something about -Linux/PPC needs an entry here, needs correction or you've written one -please mail me. - Cort Dougan ([email protected]) - -00-INDEX - - this file -bootwrapper.txt - - Information on how the powerpc kernel is wrapped for boot on various - different platforms. -cpu_features.txt - - info on how we support a variety of CPUs with minimal compile-time - options. -cxl.txt - - Overview of the CXL driver. -eeh-pci-error-recovery.txt - - info on PCI Bus EEH Error Recovery -firmware-assisted-dump.txt - - Documentation on the firmware assisted dump mechanism "fadump". -hvcs.txt - - IBM "Hypervisor Virtual Console Server" Installation Guide -mpc52xx.txt - - Linux 2.6.x on MPC52xx family -pmu-ebb.txt - - Description of the API for using the PMU with Event Based Branches. -qe_firmware.txt - - describes the layout of firmware binaries for the Freescale QUICC - Engine and the code that parses and uploads the microcode therein. -ptrace.txt - - Information on the ptrace interfaces for hardware debug registers. -transactional_memory.txt - - Overview of the Power8 transactional memory support. -dscr.txt - - Overview DSCR (Data Stream Control Register) support. diff --git a/Documentation/preempt-locking.txt b/Documentation/preempt-locking.txt index c945062be66c..509f5a422d57 100644 --- a/Documentation/preempt-locking.txt +++ b/Documentation/preempt-locking.txt @@ -3,7 +3,6 @@ Proper Locking Under a Preemptible Kernel: Keeping Kernel Code Preempt-Safe =========================================================================== :Author: Robert Love <[email protected]> -:Last Updated: 28 Aug 2002 Introduction @@ -92,11 +91,12 @@ any locks or interrupts are disabled, since preemption is implicitly disabled in those cases. But keep in mind that 'irqs disabled' is a fundamentally unsafe way of -disabling preemption - any spin_unlock() decreasing the preemption count -to 0 might trigger a reschedule. A simple printk() might trigger a reschedule. -So use this implicit preemption-disabling property only if you know that the -affected codepath does not do any of this. Best policy is to use this only for -small, atomic code that you wrote and which calls no complex functions. +disabling preemption - any cond_resched() or cond_resched_lock() might trigger +a reschedule if the preempt count is 0. A simple printk() might trigger a +reschedule. So use this implicit preemption-disabling property only if you +know that the affected codepath does not do any of this. Best policy is to use +this only for small, atomic code that you wrote and which calls no complex +functions. Example:: diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst index 51d0349c7809..ae020d84d7c4 100644 --- a/Documentation/process/2.Process.rst +++ b/Documentation/process/2.Process.rst @@ -82,7 +82,7 @@ As an example, here is how the 4.16 development cycle went (all dates in March 11 4.16-rc5 March 18 4.16-rc6 March 25 4.16-rc7 - April 1 4.17 stable release + April 1 4.16 stable release ============== =============================== How do the developers decide when to close the development cycle and create diff --git a/Documentation/process/adding-syscalls.rst b/Documentation/process/adding-syscalls.rst index 0d4f29bc798b..88a7d5c8bb2f 100644 --- a/Documentation/process/adding-syscalls.rst +++ b/Documentation/process/adding-syscalls.rst @@ -232,7 +232,7 @@ normally be optional, so add a ``CONFIG`` option (typically to by the option. - Make the option depend on EXPERT if it should be hidden from normal users. - Make any new source files implementing the function dependent on the CONFIG - option in the Makefile (e.g. ``obj-$(CONFIG_XYZZY_SYSCALL) += xyzzy.c``). + option in the Makefile (e.g. ``obj-$(CONFIG_XYZZY_SYSCALL) += xyzzy.o``). - Double check that the kernel still builds with the new CONFIG option turned off. diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst new file mode 100644 index 000000000000..0ef5a63c06ba --- /dev/null +++ b/Documentation/process/deprecated.rst @@ -0,0 +1,119 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================================================================== +Deprecated Interfaces, Language Features, Attributes, and Conventions +===================================================================== + +In a perfect world, it would be possible to convert all instances of +some deprecated API into the new API and entirely remove the old API in +a single development cycle. However, due to the size of the kernel, the +maintainership hierarchy, and timing, it's not always feasible to do these +kinds of conversions at once. This means that new instances may sneak into +the kernel while old ones are being removed, only making the amount of +work to remove the API grow. In order to educate developers about what +has been deprecated and why, this list has been created as a place to +point when uses of deprecated things are proposed for inclusion in the +kernel. + +__deprecated +------------ +While this attribute does visually mark an interface as deprecated, +it `does not produce warnings during builds any more +<https://git.kernel.org/linus/771c035372a036f83353eef46dbb829780330234>`_ +because one of the standing goals of the kernel is to build without +warnings and no one was actually doing anything to remove these deprecated +interfaces. While using `__deprecated` is nice to note an old API in +a header file, it isn't the full solution. Such interfaces must either +be fully removed from the kernel, or added to this file to discourage +others from using them in the future. + +open-coded arithmetic in allocator arguments +-------------------------------------------- +Dynamic size calculations (especially multiplication) should not be +performed in memory allocator (or similar) function arguments due to the +risk of them overflowing. This could lead to values wrapping around and a +smaller allocation being made than the caller was expecting. Using those +allocations could lead to linear overflows of heap memory and other +misbehaviors. (One exception to this is literal values where the compiler +can warn if they might overflow. Though using literals for arguments as +suggested below is also harmless.) + +For example, do not use ``count * size`` as an argument, as in:: + + foo = kmalloc(count * size, GFP_KERNEL); + +Instead, the 2-factor form of the allocator should be used:: + + foo = kmalloc_array(count, size, GFP_KERNEL); + +If no 2-factor form is available, the saturate-on-overflow helpers should +be used:: + + bar = vmalloc(array_size(count, size)); + +Another common case to avoid is calculating the size of a structure with +a trailing array of others structures, as in:: + + header = kzalloc(sizeof(*header) + count * sizeof(*header->item), + GFP_KERNEL); + +Instead, use the helper:: + + header = kzalloc(struct_size(header, item, count), GFP_KERNEL); + +See :c:func:`array_size`, :c:func:`array3_size`, and :c:func:`struct_size`, +for more details as well as the related :c:func:`check_add_overflow` and +:c:func:`check_mul_overflow` family of functions. + +simple_strtol(), simple_strtoll(), simple_strtoul(), simple_strtoull() +---------------------------------------------------------------------- +The :c:func:`simple_strtol`, :c:func:`simple_strtoll`, +:c:func:`simple_strtoul`, and :c:func:`simple_strtoull` functions +explicitly ignore overflows, which may lead to unexpected results +in callers. The respective :c:func:`kstrtol`, :c:func:`kstrtoll`, +:c:func:`kstrtoul`, and :c:func:`kstrtoull` functions tend to be the +correct replacements, though note that those require the string to be +NUL or newline terminated. + +strcpy() +-------- +:c:func:`strcpy` performs no bounds checking on the destination +buffer. This could result in linear overflows beyond the +end of the buffer, leading to all kinds of misbehaviors. While +`CONFIG_FORTIFY_SOURCE=y` and various compiler flags help reduce the +risk of using this function, there is no good reason to add new uses of +this function. The safe replacement is :c:func:`strscpy`. + +strncpy() on NUL-terminated strings +----------------------------------- +Use of :c:func:`strncpy` does not guarantee that the destination buffer +will be NUL terminated. This can lead to various linear read overflows +and other misbehavior due to the missing termination. It also NUL-pads the +destination buffer if the source contents are shorter than the destination +buffer size, which may be a needless performance penalty for callers using +only NUL-terminated strings. The safe replacement is :c:func:`strscpy`. +(Users of :c:func:`strscpy` still needing NUL-padding will need an +explicit :c:func:`memset` added.) + +If a caller is using non-NUL-terminated strings, :c:func:`strncpy()` can +still be used, but destinations should be marked with the `__nonstring +<https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_ +attribute to avoid future compiler warnings. + +strlcpy() +--------- +:c:func:`strlcpy` reads the entire source buffer first, possibly exceeding +the given limit of bytes to copy. This is inefficient and can lead to +linear read overflows if a source string is not NUL-terminated. The +safe replacement is :c:func:`strscpy`. + +Variable Length Arrays (VLAs) +----------------------------- +Using stack VLAs produces much worse machine code than statically +sized stack arrays. While these non-trivial `performance issues +<https://git.kernel.org/linus/02361bc77888>`_ are reason enough to +eliminate VLAs, they are also a security risk. Dynamic growth of a stack +array may exceed the remaining memory in the stack segment. This could +lead to a crash, possible overwriting sensitive contents at the end of the +stack (when built without `CONFIG_THREAD_INFO_IN_TASK=y`), or overwriting +memory adjacent to the stack (when built without `CONFIG_VMAP_STACK=y`) diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst index 130bf0f48875..dcb25f94188e 100644 --- a/Documentation/process/howto.rst +++ b/Documentation/process/howto.rst @@ -57,12 +57,13 @@ of doing things. Legal Issues ------------ -The Linux kernel source code is released under the GPL. Please see the -file, COPYING, in the main directory of the source tree, for details on -the license. If you have further questions about the license, please -contact a lawyer, and do not ask on the Linux kernel mailing list. The -people on the mailing lists are not lawyers, and you should not rely on -their statements on legal matters. +The Linux kernel source code is released under the GPL. Please see the file +COPYING in the main directory of the source tree. The Linux kernel licensing +rules and how to use `SPDX <https://spdx.org/>`_ identifiers in source code are +descibed in :ref:`Documentation/process/license-rules.rst <kernel_licensing>`. +If you have further questions about the license, please contact a lawyer, and do +not ask on the Linux kernel mailing list. The people on the mailing lists are +not lawyers, and you should not rely on their statements on legal matters. For common questions and answers about the GPL, please see: diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 42691e2880eb..757808526d9a 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -19,6 +19,7 @@ Below are the essential guides that every developer should read. .. toctree:: :maxdepth: 1 + license-rules howto code-of-conduct code-of-conduct-interpretation @@ -42,6 +43,7 @@ Other guides to the community that are of interest to most developers are: stable-kernel-rules submit-checklist kernel-docs + deprecated These are some overall technical guides that have been put here for now for lack of a better place. diff --git a/Documentation/process/license-rules.rst b/Documentation/process/license-rules.rst index 8ea26325fe3f..2bb8c0fc2238 100644 --- a/Documentation/process/license-rules.rst +++ b/Documentation/process/license-rules.rst @@ -1,5 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 +.. _kernel_licensing: + Linux kernel licensing rules ============================ diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX deleted file mode 100644 index 317f0378ae01..000000000000 --- a/Documentation/s390/00-INDEX +++ /dev/null @@ -1,28 +0,0 @@ -00-INDEX - - this file. -3270.ChangeLog - - ChangeLog for the UTS Global 3270-support patch (outdated). -3270.txt - - how to use the IBM 3270 display system support. -cds.txt - - s390 common device support (common I/O layer). -CommonIO - - common I/O layer command line parameters, procfs and debugfs entries -config3270.sh - - example configuration for 3270 devices. -DASD - - information on the DASD disk device driver. -Debugging390.txt - - hints for debugging on s390 systems. -driver-model.txt - - information on s390 devices and the driver model. -monreader.txt - - information on accessing the z/VM monitor stream from Linux. -qeth.txt - - HiperSockets Bridge Port Support. -s390dbf.txt - - information on using the s390 debug feature. -vfio-ccw.txt - information on the vfio-ccw I/O subchannel driver. -zfcpdump.txt - - information on the s390 SCSI dump tool. diff --git a/Documentation/scheduler/00-INDEX b/Documentation/scheduler/00-INDEX deleted file mode 100644 index eccf7ad2e7f9..000000000000 --- a/Documentation/scheduler/00-INDEX +++ /dev/null @@ -1,18 +0,0 @@ -00-INDEX - - this file. -sched-arch.txt - - CPU Scheduler implementation hints for architecture specific code. -sched-bwc.txt - - CFS bandwidth control overview. -sched-design-CFS.txt - - goals, design and implementation of the Completely Fair Scheduler. -sched-domains.txt - - information on scheduling domains. -sched-nice-design.txt - - How and why the scheduler's nice levels are implemented. -sched-rt-group.txt - - real-time group scheduling. -sched-deadline.txt - - deadline scheduling. -sched-stats.txt - - information on schedstats (Linux Scheduler Statistics). diff --git a/Documentation/scheduler/completion.txt b/Documentation/scheduler/completion.txt index 2dbff579f957..e5b9df4d8078 100644 --- a/Documentation/scheduler/completion.txt +++ b/Documentation/scheduler/completion.txt @@ -267,7 +267,8 @@ queue spinlock. Any such concurrent calls to complete() or complete_all() probably are a design bug. Signaling completion from IRQ context is fine as it will appropriately -lock with spin_lock_irqsave()/spin_unlock_irqrestore() and it will never sleep. +lock with spin_lock_irqsave()/spin_unlock_irqrestore() and it will never +sleep. try_wait_for_completion()/completion_done(): diff --git a/Documentation/scsi/00-INDEX b/Documentation/scsi/00-INDEX deleted file mode 100644 index bb4a76f823e1..000000000000 --- a/Documentation/scsi/00-INDEX +++ /dev/null @@ -1,108 +0,0 @@ -00-INDEX - - this file -53c700.txt - - info on driver for 53c700 based adapters -BusLogic.txt - - info on driver for adapters with BusLogic chips -ChangeLog.1992-1997 - - Changes to scsi files, if not listed elsewhere -ChangeLog.arcmsr - - Changes to driver for ARECA's SATA RAID controller cards -ChangeLog.ips - - IBM ServeRAID driver Changelog -ChangeLog.lpfc - - Changes to lpfc driver -ChangeLog.megaraid - - Changes to LSI megaraid controller. -ChangeLog.megaraid_sas - - Changes to serial attached scsi version of LSI megaraid controller. -ChangeLog.ncr53c8xx - - Changes to ncr53c8xx driver -ChangeLog.sym53c8xx - - Changes to sym53c8xx driver -ChangeLog.sym53c8xx_2 - - Changes to second generation of sym53c8xx driver -FlashPoint.txt - - info on driver for BusLogic FlashPoint adapters -LICENSE.FlashPoint - - Licence of the Flashpoint driver -LICENSE.qla2xxx - - License for QLogic Linux Fibre Channel HBA Driver firmware. -LICENSE.qla4xxx - - License for QLogic Linux iSCSI HBA Driver. -Mylex.txt - - info on driver for Mylex adapters -NinjaSCSI.txt - - info on WorkBiT NinjaSCSI-32/32Bi driver -aacraid.txt - - Driver supporting Adaptec RAID controllers -advansys.txt - - List of Advansys Host Adapters -aha152x.txt - - info on driver for Adaptec AHA152x based adapters -aic79xx.txt - - Adaptec Ultra320 SCSI host adapters -aic7xxx.txt - - info on driver for Adaptec controllers -arcmsr_spec.txt - - ARECA FIRMWARE SPEC (for IOP331 adapter) -bfa.txt - - Brocade FC/FCOE adapter driver. -bnx2fc.txt - - FCoE hardware offload for Broadcom network interfaces. -cxgb3i.txt - - Chelsio iSCSI Linux Driver -dc395x.txt - - README file for the dc395x SCSI driver -dpti.txt - - info on driver for DPT SmartRAID and Adaptec I2O RAID based adapters -dtc3x80.txt - - info on driver for DTC 2x80 based adapters -g_NCR5380.txt - - info on driver for NCR5380 and NCR53c400 based adapters -hpsa.txt - - HP Smart Array Controller SCSI driver. -hptiop.txt - - HIGHPOINT ROCKETRAID 3xxx RAID DRIVER -libsas.txt - - Serial Attached SCSI management layer. -link_power_management_policy.txt - - Link power management options. -lpfc.txt - - LPFC driver release notes -megaraid.txt - - Common Management Module, shared code handling ioctls for LSI drivers -ncr53c8xx.txt - - info on driver for NCR53c8xx based adapters -osd.txt - Object-Based Storage Device, command set introduction. -osst.txt - - info on driver for OnStream SC-x0 SCSI tape -ppa.txt - - info on driver for IOmega zip drive -qlogicfas.txt - - info on driver for QLogic FASxxx based adapters -scsi-changer.txt - - README for the SCSI media changer driver -scsi-generic.txt - - info on the sg driver for generic (non-disk/CD/tape) SCSI devices. -scsi-parameters.txt - - List of SCSI-parameters to pass to the kernel at module load-time. -scsi.txt - - short blurb on using SCSI support as a module. -scsi_mid_low_api.txt - - info on API between SCSI layer and low level drivers -scsi_eh.txt - - info on SCSI midlayer error handling infrastructure -scsi_fc_transport.txt - - SCSI Fiber Channel Tansport -st.txt - - info on scsi tape driver -sym53c500_cs.txt - - info on PCMCIA driver for Symbios Logic 53c500 based adapters -sym53c8xx_2.txt - - info on second generation driver for sym53c8xx based adapters -tmscsim.txt - - info on driver for AM53c974 based adapters -ufs.txt - - info on Universal Flash Storage(UFS) and UFS host controller driver. diff --git a/Documentation/security/keys/ecryptfs.rst b/Documentation/security/keys/ecryptfs.rst index 4920f3a8ea75..0e2be0a6bb6a 100644 --- a/Documentation/security/keys/ecryptfs.rst +++ b/Documentation/security/keys/ecryptfs.rst @@ -5,10 +5,10 @@ Encrypted keys for the eCryptfs filesystem ECryptfs is a stacked filesystem which transparently encrypts and decrypts each file using a randomly generated File Encryption Key (FEK). -Each FEK is in turn encrypted with a File Encryption Key Encryption Key (FEFEK) +Each FEK is in turn encrypted with a File Encryption Key Encryption Key (FEKEK) either in kernel space or in user space with a daemon called 'ecryptfsd'. In the former case the operation is performed directly by the kernel CryptoAPI -using a key, the FEFEK, derived from a user prompted passphrase; in the latter +using a key, the FEKEK, derived from a user prompted passphrase; in the latter the FEK is encrypted by 'ecryptfsd' with the help of external libraries in order to support other mechanisms like public key cryptography, PKCS#11 and TPM based operations. @@ -22,12 +22,12 @@ by the userspace utility 'mount.ecryptfs' shipped with the package The 'encrypted' key type has been extended with the introduction of the new format 'ecryptfs' in order to be used in conjunction with the eCryptfs filesystem. Encrypted keys of the newly introduced format store an -authentication token in its payload with a FEFEK randomly generated by the +authentication token in its payload with a FEKEK randomly generated by the kernel and protected by the parent master key. In order to avoid known-plaintext attacks, the datablob obtained through commands 'keyctl print' or 'keyctl pipe' does not contain the overall -authentication token, which content is well known, but only the FEFEK in +authentication token, which content is well known, but only the FEKEK in encrypted form. The eCryptfs filesystem may really benefit from using encrypted keys in that the diff --git a/Documentation/serial/00-INDEX b/Documentation/serial/00-INDEX deleted file mode 100644 index 8021a9f29fc5..000000000000 --- a/Documentation/serial/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - this file. -README.cycladesZ - - info on Cyclades-Z firmware loading. -driver - - intro to the low level serial driver. -moxa-smartio - - file with info on installing/using Moxa multiport serial driver. -n_gsm.txt - - GSM 0710 tty multiplexer howto. -rocket.txt - - info on the Comtrol RocketPort multiport serial driver. -serial-rs485.txt - - info about RS485 structures and support in the kernel. -tty.txt - - guide to the locking policies of the tty layer. diff --git a/Documentation/sphinx-static/theme_overrides.css b/Documentation/sphinx-static/theme_overrides.css index 522b6d4c49d4..e21e36cd6761 100644 --- a/Documentation/sphinx-static/theme_overrides.css +++ b/Documentation/sphinx-static/theme_overrides.css @@ -4,6 +4,44 @@ * */ +/* Improve contrast and increase size for easier reading. */ + +body { + font-family: serif; + color: black; + font-size: 100%; +} + +h1, h2, .rst-content .toctree-wrapper p.caption, h3, h4, h5, h6, legend { + font-family: sans-serif; +} + +.wy-menu-vertical li.current a { + color: #505050; +} + +.wy-menu-vertical li.on a, .wy-menu-vertical li.current > a { + color: #303030; +} + +div[class^="highlight"] pre { + font-family: monospace; + color: black; + font-size: 100%; +} + +.wy-menu-vertical { + font-family: sans-serif; +} + +.c { + font-style: normal; +} + +p { + font-size: 100%; +} + /* Interim: Code-blocks with line nos - lines and line numbers don't line up. * see: https://github.com/rtfd/sphinx_rtd_theme/issues/419 */ diff --git a/Documentation/spi/00-INDEX b/Documentation/spi/00-INDEX deleted file mode 100644 index 8e4bb17d70eb..000000000000 --- a/Documentation/spi/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - this file. -butterfly - - AVR Butterfly SPI driver overview and pin configuration. -ep93xx_spi - - Basic EP93xx SPI driver configuration. -pxa2xx - - PXA2xx SPI master controller build by spi_message fifo wq -spidev - - Intro to the userspace API for spi devices -spi-lm70llp - - Connecting an LM70-LLP sensor to the kernel via the SPI subsys. -spi-sc18is602 - - NXP SC18IS602/603 I2C-bus to SPI bridge -spi-summary - - (Linux) SPI overview. If unsure about SPI or SPI in Linux, start here. diff --git a/Documentation/sysctl/00-INDEX b/Documentation/sysctl/00-INDEX deleted file mode 100644 index 8cf5d493fd03..000000000000 --- a/Documentation/sysctl/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - this file. -README - - general information about /proc/sys/ sysctl files. -abi.txt - - documentation for /proc/sys/abi/*. -fs.txt - - documentation for /proc/sys/fs/*. -kernel.txt - - documentation for /proc/sys/kernel/*. -net.txt - - documentation for /proc/sys/net/*. -sunrpc.txt - - documentation for /proc/sys/sunrpc/*. -vm.txt - - documentation for /proc/sys/vm/*. diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX deleted file mode 100644 index 3be05fe0f1f9..000000000000 --- a/Documentation/timers/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - this file -highres.txt - - High resolution timers and dynamic ticks design notes -hpet.txt - - High Precision Event Timer Driver for Linux -hrtimers.txt - - subsystem for high-resolution kernel timers -NO_HZ.txt - - Summary of the different methods for the scheduler clock-interrupts management. -timekeeping.txt - - Clock sources, clock events, sched_clock() and delay timer notes -timers-howto.txt - - how to insert delays in the kernel the right (tm) way. -timer_stats.txt - - timer usage statistics diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 7ea16a0ceffc..f82434f2795e 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -2987,6 +2987,9 @@ The following commands are supported: command, it only prints out the contents of the ring buffer for the CPU that executed the function that triggered the dump. +- stacktrace: + When the function is hit, a stack trace is recorded. + trace_pipe ---------- diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 5ac724baea7d..7dda76503127 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -1765,7 +1765,7 @@ For example, here's how a latency can be calculated:: # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger -In the first line above, the event's timetamp is saved into the +In the first line above, the event's timestamp is saved into the variable ts0. In the next line, ts0 is subtracted from the second event's timestamp to produce the latency, which is then assigned into yet another variable, 'wakeup_lat'. The hist trigger below in turn @@ -1811,7 +1811,7 @@ the command that defined it with a '!':: /sys/kernel/debug/tracing/synthetic_events At this point, there isn't yet an actual 'wakeup_latency' event -instantiated in the event subsytem - for this to happen, a 'hist +instantiated in the event subsystem - for this to happen, a 'hist trigger action' needs to be instantiated and bound to actual fields and variables defined on other events (see Section 2.2.3 below on how that is done using hist trigger 'onmatch' action). Once that is @@ -1837,7 +1837,7 @@ output can be displayed by reading the event's 'hist' file. A hist trigger 'action' is a function that's executed whenever a histogram entry is added or updated. -The default 'action' if no special function is explicity specified is +The default 'action' if no special function is explicitly specified is as it always has been, to simply update the set of values associated with an entry. Some applications, however, may want to perform additional actions at that point, such as generate another event, or diff --git a/Documentation/virtual/00-INDEX b/Documentation/virtual/00-INDEX deleted file mode 100644 index af0d23968ee7..000000000000 --- a/Documentation/virtual/00-INDEX +++ /dev/null @@ -1,11 +0,0 @@ -Virtualization support in the Linux kernel. - -00-INDEX - - this file. - -paravirt_ops.txt - - Describes the Linux kernel pv_ops to support different hypervisors -kvm/ - - Kernel Virtual Machine. See also http://linux-kvm.org -uml/ - - User Mode Linux, builds/runs Linux kernel as a userspace program. diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX deleted file mode 100644 index 3492458a4ae8..000000000000 --- a/Documentation/virtual/kvm/00-INDEX +++ /dev/null @@ -1,35 +0,0 @@ -00-INDEX - - this file. -amd-memory-encryption.rst - - notes on AMD Secure Encrypted Virtualization feature and SEV firmware - command description -api.txt - - KVM userspace API. -arm - - internal ABI between the kernel and HYP (for arm/arm64) -cpuid.txt - - KVM-specific cpuid leaves (x86). -devices/ - - KVM_CAP_DEVICE_CTRL userspace API. -halt-polling.txt - - notes on halt-polling -hypercalls.txt - - KVM hypercalls. -locking.txt - - notes on KVM locks. -mmu.txt - - the x86 kvm shadow mmu. -msr.txt - - KVM-specific MSRs (x86). -nested-vmx.txt - - notes on nested virtualization for Intel x86 processors. -ppc-pv.txt - - the paravirtualization interface on PowerPC. -review-checklist.txt - - review checklist for KVM patches. -s390-diag.txt - - Diagnose hypercall description (for IBM S/390) -timekeeping.txt - - timekeeping virtualization for x86-based architectures. -vcpu-requests.rst - - internal VCPU request API diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX deleted file mode 100644 index f4a4f3e884cf..000000000000 --- a/Documentation/vm/00-INDEX +++ /dev/null @@ -1,50 +0,0 @@ -00-INDEX - - this file. -active_mm.rst - - An explanation from Linus about tsk->active_mm vs tsk->mm. -balance.rst - - various information on memory balancing. -cleancache.rst - - Intro to cleancache and page-granularity victim cache. -frontswap.rst - - Outline frontswap, part of the transcendent memory frontend. -highmem.rst - - Outline of highmem and common issues. -hmm.rst - - Documentation of heterogeneous memory management -hugetlbfs_reserv.rst - - A brief overview of hugetlbfs reservation design/implementation. -hwpoison.rst - - explains what hwpoison is -ksm.rst - - how to use the Kernel Samepage Merging feature. -mmu_notifier.rst - - a note about clearing pte/pmd and mmu notifications -numa.rst - - information about NUMA specific code in the Linux vm. -overcommit-accounting.rst - - description of the Linux kernels overcommit handling modes. -page_frags.rst - - description of page fragments allocator -page_migration.rst - - description of page migration in NUMA systems. -page_owner.rst - - tracking about who allocated each page -remap_file_pages.rst - - a note about remap_file_pages() system call -slub.rst - - a short users guide for SLUB. -split_page_table_lock.rst - - Separate per-table lock to improve scalability of the old page_table_lock. -swap_numa.rst - - automatic binding of swap device to numa node -transhuge.rst - - Transparent Hugepage Support, alternative way of using hugepages. -unevictable-lru.rst - - Unevictable LRU infrastructure -z3fold.txt - - outline of z3fold allocator for storing compressed pages -zsmalloc.rst - - outline of zsmalloc allocator for storing compressed pages -zswap.rst - - Intro to compressed cache for swap pages diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index cdf3911582c8..44205f0b671f 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -194,13 +194,13 @@ use either:: unsigned long start, unsigned long end, hmm_pfn_t *pfns); - int hmm_vma_fault(struct vm_area_struct *vma, - struct hmm_range *range, - unsigned long start, - unsigned long end, - hmm_pfn_t *pfns, - bool write, - bool block); + int hmm_vma_fault(struct vm_area_struct *vma, + struct hmm_range *range, + unsigned long start, + unsigned long end, + hmm_pfn_t *pfns, + bool write, + bool block); The first one (hmm_vma_get_pfns()) will only fetch present CPU page table entries and will not trigger a page fault on missing or non-present entries. diff --git a/Documentation/w1/00-INDEX b/Documentation/w1/00-INDEX deleted file mode 100644 index cb49802745dc..000000000000 --- a/Documentation/w1/00-INDEX +++ /dev/null @@ -1,10 +0,0 @@ -00-INDEX - - This file -slaves/ - - Drivers that provide support for specific family codes. -masters/ - - Individual chips providing 1-wire busses. -w1.generic - - The 1-wire (w1) bus -w1.netlink - - Userspace communication protocol over connector [1]. diff --git a/Documentation/w1/masters/00-INDEX b/Documentation/w1/masters/00-INDEX deleted file mode 100644 index 8330cf9325f0..000000000000 --- a/Documentation/w1/masters/00-INDEX +++ /dev/null @@ -1,12 +0,0 @@ -00-INDEX - - This file -ds2482 - - The Maxim/Dallas Semiconductor DS2482 provides 1-wire busses. -ds2490 - - The Maxim/Dallas Semiconductor DS2490 builds USB <-> W1 bridges. -mxc-w1 - - W1 master controller driver found on Freescale MX2/MX3 SoCs -omap-hdq - - HDQ/1-wire module of TI OMAP 2430/3430. -w1-gpio - - GPIO 1-wire bus master driver. diff --git a/Documentation/w1/slaves/00-INDEX b/Documentation/w1/slaves/00-INDEX deleted file mode 100644 index 68946f83e579..000000000000 --- a/Documentation/w1/slaves/00-INDEX +++ /dev/null @@ -1,14 +0,0 @@ -00-INDEX - - This file -w1_therm - - The Maxim/Dallas Semiconductor ds18*20 temperature sensor. -w1_ds2413 - - The Maxim/Dallas Semiconductor ds2413 dual channel addressable switch. -w1_ds2423 - - The Maxim/Dallas Semiconductor ds2423 counter device. -w1_ds2438 - - The Maxim/Dallas Semiconductor ds2438 smart battery monitor. -w1_ds28e04 - - The Maxim/Dallas Semiconductor ds28e04 eeprom. -w1_ds28e17 - - The Maxim/Dallas Semiconductor ds28e17 1-Wire-to-I2C Master Bridge. diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX deleted file mode 100644 index 3bb2ee3edcd1..000000000000 --- a/Documentation/x86/00-INDEX +++ /dev/null @@ -1,20 +0,0 @@ -00-INDEX - - this file -boot.txt - - List of boot protocol versions -earlyprintk.txt - - Using earlyprintk with a USB2 debug port key. -entry_64.txt - - Describe (some of the) kernel entry points for x86. -exception-tables.txt - - why and how Linux kernel uses exception tables on x86 -microcode.txt - - How to load microcode from an initrd-CPIO archive early to fix CPU issues. -mtrr.txt - - how to use x86 Memory Type Range Registers to increase performance -pat.txt - - Page Attribute Table intro and API -usb-legacy-support.txt - - how to fix/avoid quirks when using emulated PS/2 mouse/keyboard. -zero-page.txt - - layout of the first page of memory. diff --git a/Documentation/x86/x86_64/00-INDEX b/Documentation/x86/x86_64/00-INDEX deleted file mode 100644 index 92fc20ab5f0e..000000000000 --- a/Documentation/x86/x86_64/00-INDEX +++ /dev/null @@ -1,16 +0,0 @@ -00-INDEX - - This file -boot-options.txt - - AMD64-specific boot options. -cpu-hotplug-spec - - Firmware support for CPU hotplug under Linux/x86-64 -fake-numa-for-cpusets - - Using numa=fake and CPUSets for Resource Management -kernel-stacks - - Context-specific per-processor interrupt stacks. -machinecheck - - Configurable sysfs parameters for the x86-64 machine check code. -mm.txt - - Memory layout of x86-64 (4 level page tables, 46 bits physical). -uefi.txt - - Booting Linux via Unified Extensible Firmware Interface. diff --git a/LICENSES/other/CDDL-1.0 b/LICENSES/other/CDDL-1.0 index 195a1687930a..25f614276ddd 100644 --- a/LICENSES/other/CDDL-1.0 +++ b/LICENSES/other/CDDL-1.0 @@ -1,10 +1,14 @@ Valid-License-Identifier: CDDL-1.0 SPDX-URL: https://spdx.org/licenses/CDDL-1.0.html Usage-Guide: + Do NOT use. The CDDL-1.0 is not GPL compatible. It may only be used for + dual-licensed files where the other license is GPL compatible. + If you end up using this it MUST be used together with a GPL2 compatible + license using "OR". To use the Common Development and Distribution License 1.0 put the following SPDX tag/value pair into a comment according to the placement guidelines in the licensing rules documentation: - SPDX-License-Identifier: CDDL-1.0 + SPDX-License-Identifier: ($GPL-COMPATIBLE-ID OR CDDL-1.0) License-Text: diff --git a/LICENSES/other/ISC b/LICENSES/other/ISC new file mode 100644 index 000000000000..8953c3142079 --- /dev/null +++ b/LICENSES/other/ISC @@ -0,0 +1,24 @@ +Valid-License-Identifier: ISC +SPDX-URL: https://spdx.org/licenses/ISC.html +Usage-Guide: + To use the ISC License put the following SPDX tag/value pair into a + comment according to the placement guidelines in the licensing rules + documentation: + SPDX-License-Identifier: ISC +License-Text: + +ISC License + +Copyright (c) <year> <copyright holders> + +Permission to use, copy, modify, and/or distribute this software for any +purpose with or without fee is hereby granted, provided that the above +copyright notice and this permission notice appear in all copies. + +THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES +WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY +SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION +OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN +CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. diff --git a/MAINTAINERS b/MAINTAINERS index af2a61a31a8e..49e8fa2e95d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -839,7 +839,7 @@ ANALOG DEVICES INC ADGS1408 DRIVER M: Mircea Caprioru <[email protected]> S: Supported F: drivers/mux/adgs1408.c -F: Documentation/devicetree/bindings/mux/adgs1408.txt +F: Documentation/devicetree/bindings/mux/adi,adgs1408.txt ANALOG DEVICES INC ADP5061 DRIVER M: Stefan Popa <[email protected]> @@ -4514,11 +4514,12 @@ S: Maintained F: Documentation/ F: scripts/kernel-doc X: Documentation/ABI/ +X: Documentation/acpi/ X: Documentation/devicetree/ -X: Documentation/acpi -X: Documentation/power -X: Documentation/spi -X: Documentation/media +X: Documentation/i2c/ +X: Documentation/media/ +X: Documentation/power/ +X: Documentation/spi/ T: git git://git.lwn.net/linux.git docs-next DOCUMENTATION/ITALIAN @@ -5548,7 +5549,7 @@ W: http://ext4.wiki.kernel.org Q: http://patchwork.ozlabs.org/project/linux-ext4/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git S: Maintained -F: Documentation/filesystems/ext4.txt +F: Documentation/filesystems/ext4/ext4.rst F: fs/ext4/ Extended Verification Module (EVM) @@ -12,7 +12,6 @@ In order to build the documentation, use ``make htmldocs`` or There are various text files in the Documentation/ subdirectory, several of them using the Restructured Text markup notation. -See Documentation/00-INDEX for a list of what is contained in each file. Please read the Documentation/process/changes.rst file, as it contains the requirements for building and running the kernel, and information about diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 051327a951b1..35e784cffc23 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -337,9 +337,16 @@ static void deallocate_channel(struct fw_card *card, int irm_id, /** * fw_iso_resource_manage() - Allocate or deallocate a channel and/or bandwidth + * @card: card interface for this action + * @generation: bus generation + * @channels_mask: bitmask for channel allocation + * @channel: pointer for returning channel allocation result + * @bandwidth: pointer for returning bandwidth allocation result + * @allocate: whether to allocate (true) or deallocate (false) * * In parameters: card, generation, channels_mask, bandwidth, allocate * Out parameters: channel, bandwidth + * * This function blocks (sleeps) during communication with the IRM. * * Allocates or deallocates at most one channel out of channels_mask. diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 4372f9e4b0da..50bf1fe1775f 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -410,6 +410,14 @@ static void transaction_callback(struct fw_card *card, int rcode, /** * fw_run_transaction() - send request and sleep until transaction is completed + * @card: card interface for this request + * @tcode: transaction code + * @destination_id: destination node ID, consisting of bus_ID and phy_ID + * @generation: bus generation in which request and response are valid + * @speed: transmission speed + * @offset: 48bit wide offset into destination's address space + * @payload: data payload for the request subaction + * @length: length of the payload, in bytes * * Returns the RCODE. See fw_send_request() for parameter documentation. * Unlike fw_send_request(), @data points to the payload of the request or/and @@ -604,6 +612,7 @@ EXPORT_SYMBOL(fw_core_add_address_handler); /** * fw_core_remove_address_handler() - unregister an address handler + * @handler: callback * * To be called in process context. * @@ -828,6 +837,7 @@ EXPORT_SYMBOL(fw_send_response); /** * fw_get_request_speed() - returns speed at which the @request was received + * @request: firewire request data */ int fw_get_request_speed(struct fw_request *request) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index f7e363b90fe0..dca6f2326c26 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -859,10 +859,12 @@ static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd, reset_level = HNAE3_FUNC_RESET; } - err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3; - if (err_sts) { - hclge_log_error(dev, hw_err_lst3, err_sts); - reset_level = HNAE3_FUNC_RESET; + if (cmd == HCLGE_PPP_CMD0_INT_CMD) { + err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3; + if (err_sts) { + hclge_log_error(dev, hw_err_lst3, err_sts); + reset_level = HNAE3_FUNC_RESET; + } } /* clear PPP INT */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 8890c95831ca..a4eac3b9ee72 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -573,7 +573,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, sizeof(struct nix_cq_ctx_s)); else if (req->ctype == NIX_AQ_CTYPE_RSS) memcpy(&rsp->rss, ctx, - sizeof(struct nix_cq_ctx_s)); + sizeof(struct nix_rsse_s)); else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(&rsp->mce, ctx, sizeof(struct nix_rx_mce_s)); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index ae750b1574a2..68ebe188446a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -112,11 +112,11 @@ static int find_extent_in_eb(const struct extent_buffer *eb, } struct preftree { - struct rb_root root; + struct rb_root_cached root; unsigned int count; }; -#define PREFTREE_INIT { .root = RB_ROOT, .count = 0 } +#define PREFTREE_INIT { .root = RB_ROOT_CACHED, .count = 0 } struct preftrees { struct preftree direct; /* BTRFS_SHARED_[DATA|BLOCK]_REF_KEY */ @@ -225,14 +225,15 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, struct prelim_ref *newref, struct share_check *sc) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node **p; struct rb_node *parent = NULL; struct prelim_ref *ref; int result; + bool leftmost = true; root = &preftree->root; - p = &root->rb_node; + p = &root->rb_root.rb_node; while (*p) { parent = *p; @@ -242,6 +243,7 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, p = &(*p)->rb_left; } else if (result > 0) { p = &(*p)->rb_right; + leftmost = false; } else { /* Identical refs, merge them and free @newref */ struct extent_inode_elem *eie = ref->inode_list; @@ -272,7 +274,7 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, preftree->count++; trace_btrfs_prelim_ref_insert(fs_info, newref, NULL, preftree->count); rb_link_node(&newref->rbnode, parent, p); - rb_insert_color(&newref->rbnode, root); + rb_insert_color_cached(&newref->rbnode, root, leftmost); } /* @@ -283,11 +285,11 @@ static void prelim_release(struct preftree *preftree) { struct prelim_ref *ref, *next_ref; - rbtree_postorder_for_each_entry_safe(ref, next_ref, &preftree->root, - rbnode) + rbtree_postorder_for_each_entry_safe(ref, next_ref, + &preftree->root.rb_root, rbnode) free_pref(ref); - preftree->root = RB_ROOT; + preftree->root = RB_ROOT_CACHED; preftree->count = 0; } @@ -627,7 +629,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, * freeing the entire indirect tree when we're done. In some test * cases, the tree can grow quite large (~200k objects). */ - while ((rnode = rb_first(&preftrees->indirect.root))) { + while ((rnode = rb_first_cached(&preftrees->indirect.root))) { struct prelim_ref *ref; ref = rb_entry(rnode, struct prelim_ref, rbnode); @@ -637,7 +639,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, goto out; } - rb_erase(&ref->rbnode, &preftrees->indirect.root); + rb_erase_cached(&ref->rbnode, &preftrees->indirect.root); preftrees->indirect.count--; if (ref->count == 0) { @@ -717,9 +719,9 @@ static int add_missing_keys(struct btrfs_fs_info *fs_info, struct preftree *tree = &preftrees->indirect_missing_keys; struct rb_node *node; - while ((node = rb_first(&tree->root))) { + while ((node = rb_first_cached(&tree->root))) { ref = rb_entry(node, struct prelim_ref, rbnode); - rb_erase(node, &tree->root); + rb_erase_cached(node, &tree->root); BUG_ON(ref->parent); /* should not be a direct ref */ BUG_ON(ref->key_for_search.type); @@ -769,7 +771,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); spin_lock(&head->lock); - for (n = rb_first(&head->ref_tree); n; n = rb_next(n)) { + for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, ref_node); if (node->seq > seq) @@ -1229,14 +1231,14 @@ again: if (ret) goto out; - WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root)); + WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root.rb_root)); ret = resolve_indirect_refs(fs_info, path, time_seq, &preftrees, extent_item_pos, total_refs, sc, ignore_offset); if (ret) goto out; - WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect.root)); + WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect.root.rb_root)); /* * This walks the tree of merged and resolved refs. Tree blocks are @@ -1245,7 +1247,7 @@ again: * * We release the entire tree in one go before returning. */ - node = rb_first(&preftrees.direct.root); + node = rb_first_cached(&preftrees.direct.root); while (node) { ref = rb_entry(node, struct prelim_ref, rbnode); node = rb_next(&ref->rbnode); @@ -1468,7 +1470,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) struct seq_list elem = SEQ_LIST_INIT(elem); int ret = 0; struct share_check shared = { - .root_objectid = root->objectid, + .root_objectid = root->root_key.objectid, .inum = inum, .share_count = 0, }; @@ -2031,7 +2033,8 @@ static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root, /* path must be released before calling iterate()! */ btrfs_debug(fs_root->fs_info, "following ref at offset %u for inode %llu in tree %llu", - cur, found_key.objectid, fs_root->objectid); + cur, found_key.objectid, + fs_root->root_key.objectid); ret = iterate(parent, name_len, (unsigned long)(iref + 1), eb, ctx); if (ret) diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 1343ac57b438..97d91e55b70a 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -206,7 +206,7 @@ static inline struct btrfs_inode *BTRFS_I(const struct inode *inode) static inline unsigned long btrfs_inode_hash(u64 objectid, const struct btrfs_root *root) { - u64 h = objectid ^ (root->objectid * GOLDEN_RATIO_PRIME); + u64 h = objectid ^ (root->root_key.objectid * GOLDEN_RATIO_PRIME); #if BITS_PER_LONG == 32 h = (h >> 32) ^ (h & 0xffffffff); @@ -339,15 +339,15 @@ static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode, struct btrfs_root *root = inode->root; /* Output minus objectid, which is more meaningful */ - if (root->objectid >= BTRFS_LAST_FREE_OBJECTID) + if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID) btrfs_warn_rl(root->fs_info, "csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d", - root->objectid, btrfs_ino(inode), + root->root_key.objectid, btrfs_ino(inode), logical_start, csum, csum_expected, mirror_num); else btrfs_warn_rl(root->fs_info, "csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d", - root->objectid, btrfs_ino(inode), + root->root_key.objectid, btrfs_ino(inode), logical_start, csum, csum_expected, mirror_num); } diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 833cf3c35b4d..2e43fba44035 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -1594,6 +1594,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, { unsigned int num_pages; unsigned int i; + size_t size; u64 dev_bytenr; int ret; @@ -1608,9 +1609,8 @@ static int btrfsic_read_block(struct btrfsic_state *state, num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >> PAGE_SHIFT; - block_ctx->mem_to_free = kcalloc(sizeof(*block_ctx->datav) + - sizeof(*block_ctx->pagev), - num_pages, GFP_NOFS); + size = sizeof(*block_ctx->datav) + sizeof(*block_ctx->pagev); + block_ctx->mem_to_free = kcalloc(num_pages, size, GFP_NOFS); if (!block_ctx->mem_to_free) return -ENOMEM; block_ctx->datav = block_ctx->mem_to_free; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 9bfa66592aa7..8703ce68fe9d 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -528,7 +528,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct extent_io_tree *tree; struct extent_map_tree *em_tree; struct compressed_bio *cb; unsigned long compressed_len; @@ -545,7 +544,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int faili = 0; u32 *sums; - tree = &BTRFS_I(inode)->io_tree; em_tree = &BTRFS_I(inode)->extent_tree; /* we need the actual starting offset of this extent in the file */ diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index d436fb4c002e..2ee43b6a4f09 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -52,42 +52,6 @@ noinline void btrfs_set_path_blocking(struct btrfs_path *p) } } -/* - * reset all the locked nodes in the patch to spinning locks. - * - * held is used to keep lockdep happy, when lockdep is enabled - * we set held to a blocking lock before we go around and - * retake all the spinlocks in the path. You can safely use NULL - * for held - */ -noinline void btrfs_clear_path_blocking(struct btrfs_path *p, - struct extent_buffer *held, int held_rw) -{ - int i; - - if (held) { - btrfs_set_lock_blocking_rw(held, held_rw); - if (held_rw == BTRFS_WRITE_LOCK) - held_rw = BTRFS_WRITE_LOCK_BLOCKING; - else if (held_rw == BTRFS_READ_LOCK) - held_rw = BTRFS_READ_LOCK_BLOCKING; - } - btrfs_set_path_blocking(p); - - for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) { - if (p->nodes[i] && p->locks[i]) { - btrfs_clear_lock_blocking_rw(p->nodes[i], p->locks[i]); - if (p->locks[i] == BTRFS_WRITE_LOCK_BLOCKING) - p->locks[i] = BTRFS_WRITE_LOCK; - else if (p->locks[i] == BTRFS_READ_LOCK_BLOCKING) - p->locks[i] = BTRFS_READ_LOCK; - } - } - - if (held) - btrfs_clear_lock_blocking_rw(held, held_rw); -} - /* this also releases the path */ void btrfs_free_path(struct btrfs_path *p) { @@ -207,7 +171,7 @@ static void add_root_to_dirty_list(struct btrfs_root *root) spin_lock(&fs_info->trans_lock); if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) { /* Want the extent tree to be the last on the list */ - if (root->objectid == BTRFS_EXTENT_TREE_OBJECTID) + if (root->root_key.objectid == BTRFS_EXTENT_TREE_OBJECTID) list_move_tail(&root->dirty_list, &fs_info->dirty_cowonly_roots); else @@ -1306,7 +1270,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, } } - btrfs_clear_path_blocking(path, NULL, BTRFS_READ_LOCK); btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); @@ -1815,8 +1778,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, int orig_slot = path->slots[level]; u64 orig_ptr; - if (level == 0) - return 0; + ASSERT(level > 0); mid = path->nodes[level]; @@ -2483,7 +2445,6 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans, btrfs_set_path_blocking(p); reada_for_balance(fs_info, p, level); sret = split_node(trans, root, p, level); - btrfs_clear_path_blocking(p, NULL, 0); BUG_ON(sret > 0); if (sret) { @@ -2504,7 +2465,6 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans, btrfs_set_path_blocking(p); reada_for_balance(fs_info, p, level); sret = balance_level(trans, root, p, level); - btrfs_clear_path_blocking(p, NULL, 0); if (sret) { ret = sret; @@ -2789,7 +2749,10 @@ again: } cow_done: p->nodes[level] = b; - btrfs_clear_path_blocking(p, NULL, 0); + /* + * Leave path with blocking locks to avoid massive + * lock context switch, this is made on purpose. + */ /* * we have a lock on b and as long as we aren't changing @@ -2871,8 +2834,6 @@ cow_done: if (!err) { btrfs_set_path_blocking(p); btrfs_tree_lock(b); - btrfs_clear_path_blocking(p, b, - BTRFS_WRITE_LOCK); } p->locks[level] = BTRFS_WRITE_LOCK; } else { @@ -2880,8 +2841,6 @@ cow_done: if (!err) { btrfs_set_path_blocking(p); btrfs_tree_read_lock(b); - btrfs_clear_path_blocking(p, b, - BTRFS_READ_LOCK); } p->locks[level] = BTRFS_READ_LOCK; } @@ -2900,7 +2859,6 @@ cow_done: btrfs_set_path_blocking(p); err = split_leaf(trans, root, key, p, ins_len, ret == 0); - btrfs_clear_path_blocking(p, NULL, 0); BUG_ON(err > 0); if (err) { @@ -2910,7 +2868,7 @@ cow_done: } if (!p->search_for_split) unlock_up(p, level, lowest_unlock, - min_write_lock_level, &write_lock_level); + min_write_lock_level, NULL); goto done; } } @@ -2961,13 +2919,16 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, again: b = get_old_root(root, time_seq); + if (!b) { + ret = -EIO; + goto done; + } level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; while (b) { level = btrfs_header_level(b); p->nodes[level] = b; - btrfs_clear_path_blocking(p, NULL, 0); /* * we have a lock on b and as long as we aren't changing @@ -3013,8 +2974,6 @@ again: if (!err) { btrfs_set_path_blocking(p); btrfs_tree_read_lock(b); - btrfs_clear_path_blocking(p, b, - BTRFS_READ_LOCK); } b = tree_mod_log_rewind(fs_info, p, b, time_seq); if (!b) { @@ -5198,7 +5157,6 @@ find_next_key: path->locks[level - 1] = BTRFS_READ_LOCK; path->nodes[level - 1] = cur; unlock_up(path, level, 1, 0, NULL); - btrfs_clear_path_blocking(path, NULL, 0); } out: path->keep_locks = keep_locks; @@ -5783,8 +5741,6 @@ again: if (!ret) { btrfs_set_path_blocking(path); btrfs_tree_read_lock(next); - btrfs_clear_path_blocking(path, next, - BTRFS_READ_LOCK); } next_rw_lock = BTRFS_READ_LOCK; } @@ -5820,8 +5776,6 @@ again: if (!ret) { btrfs_set_path_blocking(path); btrfs_tree_read_lock(next); - btrfs_clear_path_blocking(path, next, - BTRFS_READ_LOCK); } next_rw_lock = BTRFS_READ_LOCK; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2cddfe7806a4..68ca41dbbef3 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -41,12 +41,6 @@ extern struct kmem_cache *btrfs_path_cachep; extern struct kmem_cache *btrfs_free_space_cachep; struct btrfs_ordered_sum; -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -#define STATIC noinline -#else -#define STATIC static noinline -#endif - #define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */ #define BTRFS_MAX_MIRRORS 3 @@ -367,11 +361,13 @@ struct btrfs_dev_replace { struct mutex lock_finishing_cancel_unmount; rwlock_t lock; - atomic_t read_locks; atomic_t blocking_readers; wait_queue_head_t read_lock_wq; struct btrfs_scrub_progress scrub_progress; + + struct percpu_counter bio_counter; + wait_queue_head_t replace_wait; }; /* For raid type sysfs entries */ @@ -1094,9 +1090,6 @@ struct btrfs_fs_info { /* device replace state */ struct btrfs_dev_replace dev_replace; - struct percpu_counter bio_counter; - wait_queue_head_t replace_wait; - struct semaphore uuid_tree_rescan_sem; /* Used to reclaim the metadata space in the background. */ @@ -1202,18 +1195,12 @@ struct btrfs_root { int last_log_commit; pid_t log_start_pid; - u64 objectid; u64 last_trans; u32 type; u64 highest_objectid; -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS - /* only used with CONFIG_BTRFS_FS_RUN_SANITY_TESTS is enabled */ - u64 alloc_bytenr; -#endif - u64 defrag_trans_start; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; @@ -1286,6 +1273,10 @@ struct btrfs_root { spinlock_t qgroup_meta_rsv_lock; u64 qgroup_meta_rsv_pertrans; u64 qgroup_meta_rsv_prealloc; + +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + u64 alloc_bytenr; +#endif }; struct btrfs_file_private { @@ -2607,10 +2598,8 @@ static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info, return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items; } -int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); -int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); +int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans); +int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans); void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, const u64 start); void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg); @@ -2771,7 +2760,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root, enum btrfs_reserve_flush_enum flush); int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv, struct btrfs_block_rsv *dst_rsv, u64 num_bytes, - int update_size); + bool update_size); int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *dest, u64 num_bytes, int min_factor); @@ -2877,8 +2866,6 @@ void btrfs_release_path(struct btrfs_path *p); struct btrfs_path *btrfs_alloc_path(void); void btrfs_free_path(struct btrfs_path *p); void btrfs_set_path_blocking(struct btrfs_path *p); -void btrfs_clear_path_blocking(struct btrfs_path *p, - struct extent_buffer *held, int held_rw); void btrfs_unlock_up_safe(struct btrfs_path *p, int level); int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3021,8 +3008,7 @@ int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info, /* dir-item.c */ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, const char *name, int name_len); -int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, const char *name, +int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, int name_len, struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index); struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, @@ -3180,8 +3166,8 @@ void __cold btrfs_destroy_cachep(void); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *was_new); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, - struct page *page, size_t pg_offset, - u64 start, u64 end, int create); + struct page *page, size_t pg_offset, + u64 start, u64 end, int create); int btrfs_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); @@ -3201,9 +3187,6 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); extern const struct dentry_operations btrfs_dentry_operations; -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -void btrfs_test_inode_set_ops(struct inode *inode); -#endif /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -3716,18 +3699,19 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info) /* Sanity test specific functions */ #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +void btrfs_test_inode_set_ops(struct inode *inode); void btrfs_test_destroy_inode(struct inode *inode); -#endif static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info) { -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS - if (unlikely(test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, - &fs_info->fs_state))) - return 1; -#endif + return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state); +} +#else +static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info) +{ return 0; } +#endif static inline void cond_wake_up(struct wait_queue_head *wq) { diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index f51b509f2d9b..c669f250d4a0 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -42,8 +42,8 @@ static inline void btrfs_init_delayed_node( delayed_node->root = root; delayed_node->inode_id = inode_id; refcount_set(&delayed_node->refs, 0); - delayed_node->ins_root = RB_ROOT; - delayed_node->del_root = RB_ROOT; + delayed_node->ins_root = RB_ROOT_CACHED; + delayed_node->del_root = RB_ROOT_CACHED; mutex_init(&delayed_node->mutex); INIT_LIST_HEAD(&delayed_node->n_list); INIT_LIST_HEAD(&delayed_node->p_list); @@ -390,7 +390,7 @@ static struct btrfs_delayed_item *__btrfs_lookup_delayed_insertion_item( struct btrfs_delayed_node *delayed_node, struct btrfs_key *key) { - return __btrfs_lookup_delayed_item(&delayed_node->ins_root, key, + return __btrfs_lookup_delayed_item(&delayed_node->ins_root.rb_root, key, NULL, NULL); } @@ -400,9 +400,10 @@ static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node, { struct rb_node **p, *node; struct rb_node *parent_node = NULL; - struct rb_root *root; + struct rb_root_cached *root; struct btrfs_delayed_item *item; int cmp; + bool leftmost = true; if (action == BTRFS_DELAYED_INSERTION_ITEM) root = &delayed_node->ins_root; @@ -410,7 +411,7 @@ static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node, root = &delayed_node->del_root; else BUG(); - p = &root->rb_node; + p = &root->rb_root.rb_node; node = &ins->rb_node; while (*p) { @@ -419,16 +420,18 @@ static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node, rb_node); cmp = btrfs_comp_cpu_keys(&item->key, &ins->key); - if (cmp < 0) + if (cmp < 0) { p = &(*p)->rb_right; - else if (cmp > 0) + leftmost = false; + } else if (cmp > 0) { p = &(*p)->rb_left; - else + } else { return -EEXIST; + } } rb_link_node(node, parent_node, p); - rb_insert_color(node, root); + rb_insert_color_cached(node, root, leftmost); ins->delayed_node = delayed_node; ins->ins_or_del = action; @@ -468,7 +471,7 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root) static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) { - struct rb_root *root; + struct rb_root_cached *root; struct btrfs_delayed_root *delayed_root; delayed_root = delayed_item->delayed_node->root->fs_info->delayed_root; @@ -482,7 +485,7 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) else root = &delayed_item->delayed_node->del_root; - rb_erase(&delayed_item->rb_node, root); + rb_erase_cached(&delayed_item->rb_node, root); delayed_item->delayed_node->count--; finish_one_item(delayed_root); @@ -503,7 +506,7 @@ static struct btrfs_delayed_item *__btrfs_first_delayed_insertion_item( struct rb_node *p; struct btrfs_delayed_item *item = NULL; - p = rb_first(&delayed_node->ins_root); + p = rb_first_cached(&delayed_node->ins_root); if (p) item = rb_entry(p, struct btrfs_delayed_item, rb_node); @@ -516,7 +519,7 @@ static struct btrfs_delayed_item *__btrfs_first_delayed_deletion_item( struct rb_node *p; struct btrfs_delayed_item *item = NULL; - p = rb_first(&delayed_node->del_root); + p = rb_first_cached(&delayed_node->del_root); if (p) item = rb_entry(p, struct btrfs_delayed_item, rb_node); @@ -559,7 +562,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans, * reserved space when starting a transaction. So no need to reserve * qgroup space here. */ - ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1); + ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, true); if (!ret) { trace_btrfs_space_reservation(fs_info, "delayed_item", item->key.objectid, @@ -647,7 +650,7 @@ static int btrfs_delayed_inode_reserve_metadata( return ret; } - ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1); + ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, true); if (!ret) { trace_btrfs_space_reservation(fs_info, "delayed_inode", btrfs_ino(inode), num_bytes, 1); @@ -762,9 +765,6 @@ static int btrfs_batch_insert_items(struct btrfs_root *root, i++; } - /* reset all the locked nodes in the patch to spinning locks. */ - btrfs_clear_path_blocking(path, NULL, 0); - /* insert the keys of the items */ setup_items_for_insert(root, path, keys, data_size, total_data_size, total_size, nitems); @@ -1462,7 +1462,7 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, if (unlikely(ret)) { btrfs_err(trans->fs_info, "err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)", - name_len, name, delayed_node->root->objectid, + name_len, name, delayed_node->root->root_key.objectid, delayed_node->inode_id, ret); BUG(); } @@ -1533,7 +1533,8 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, if (unlikely(ret)) { btrfs_err(trans->fs_info, "err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)", - index, node->root->objectid, node->inode_id, ret); + index, node->root->root_key.objectid, + node->inode_id, ret); BUG(); } mutex_unlock(&node->mutex); diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 33536cd681d4..74ae226ffaf0 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -50,8 +50,8 @@ struct btrfs_delayed_node { * is waiting to be dealt with by the async worker. */ struct list_head p_list; - struct rb_root ins_root; - struct rb_root del_root; + struct rb_root_cached ins_root; + struct rb_root_cached del_root; struct mutex mutex; struct btrfs_inode_item inode_item; refcount_t refs; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 62ff545ba1f7..5149165b49a4 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -101,14 +101,15 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1, } /* insert a new ref to head ref rbtree */ -static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root, +static struct btrfs_delayed_ref_head *htree_insert(struct rb_root_cached *root, struct rb_node *node) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent_node = NULL; struct btrfs_delayed_ref_head *entry; struct btrfs_delayed_ref_head *ins; u64 bytenr; + bool leftmost = true; ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node); bytenr = ins->bytenr; @@ -117,26 +118,29 @@ static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root, entry = rb_entry(parent_node, struct btrfs_delayed_ref_head, href_node); - if (bytenr < entry->bytenr) + if (bytenr < entry->bytenr) { p = &(*p)->rb_left; - else if (bytenr > entry->bytenr) + } else if (bytenr > entry->bytenr) { p = &(*p)->rb_right; - else + leftmost = false; + } else { return entry; + } } rb_link_node(node, parent_node, p); - rb_insert_color(node, root); + rb_insert_color_cached(node, root, leftmost); return NULL; } -static struct btrfs_delayed_ref_node* tree_insert(struct rb_root *root, +static struct btrfs_delayed_ref_node* tree_insert(struct rb_root_cached *root, struct btrfs_delayed_ref_node *ins) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *node = &ins->ref_node; struct rb_node *parent_node = NULL; struct btrfs_delayed_ref_node *entry; + bool leftmost = true; while (*p) { int comp; @@ -145,16 +149,18 @@ static struct btrfs_delayed_ref_node* tree_insert(struct rb_root *root, entry = rb_entry(parent_node, struct btrfs_delayed_ref_node, ref_node); comp = comp_refs(ins, entry, true); - if (comp < 0) + if (comp < 0) { p = &(*p)->rb_left; - else if (comp > 0) + } else if (comp > 0) { p = &(*p)->rb_right; - else + leftmost = false; + } else { return entry; + } } rb_link_node(node, parent_node, p); - rb_insert_color(node, root); + rb_insert_color_cached(node, root, leftmost); return NULL; } @@ -162,12 +168,14 @@ static struct btrfs_delayed_ref_node* tree_insert(struct rb_root *root, * find an head entry based on bytenr. This returns the delayed ref * head if it was able to find one, or NULL if nothing was in that spot. * If return_bigger is given, the next bigger entry is returned if no exact - * match is found. + * match is found. But if no bigger one is found then the first node of the + * ref head tree will be returned. */ -static struct btrfs_delayed_ref_head * -find_ref_head(struct rb_root *root, u64 bytenr, - int return_bigger) +static struct btrfs_delayed_ref_head* find_ref_head( + struct btrfs_delayed_ref_root *dr, u64 bytenr, + bool return_bigger) { + struct rb_root *root = &dr->href_root.rb_root; struct rb_node *n; struct btrfs_delayed_ref_head *entry; @@ -187,7 +195,7 @@ find_ref_head(struct rb_root *root, u64 bytenr, if (bytenr > entry->bytenr) { n = rb_next(&entry->href_node); if (!n) - n = rb_first(root); + n = rb_first_cached(&dr->href_root); entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node); return entry; @@ -197,12 +205,9 @@ find_ref_head(struct rb_root *root, u64 bytenr, return NULL; } -int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, +int btrfs_delayed_ref_lock(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { - struct btrfs_delayed_ref_root *delayed_refs; - - delayed_refs = &trans->transaction->delayed_refs; lockdep_assert_held(&delayed_refs->lock); if (mutex_trylock(&head->mutex)) return 0; @@ -227,7 +232,7 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref) { lockdep_assert_held(&head->lock); - rb_erase(&ref->ref_node, &head->ref_tree); + rb_erase_cached(&ref->ref_node, &head->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); @@ -296,7 +301,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, lockdep_assert_held(&head->lock); - if (RB_EMPTY_ROOT(&head->ref_tree)) + if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) return; /* We don't have too many refs to merge for data. */ @@ -314,7 +319,8 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, spin_unlock(&fs_info->tree_mod_seq_lock); again: - for (node = rb_first(&head->ref_tree); node; node = rb_next(node)) { + for (node = rb_first_cached(&head->ref_tree); node; + node = rb_next(node)) { ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); if (seq && ref->seq >= seq) continue; @@ -345,24 +351,21 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq) return ret; } -struct btrfs_delayed_ref_head * -btrfs_select_ref_head(struct btrfs_trans_handle *trans) +struct btrfs_delayed_ref_head *btrfs_select_ref_head( + struct btrfs_delayed_ref_root *delayed_refs) { - struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_head *head; u64 start; bool loop = false; - delayed_refs = &trans->transaction->delayed_refs; - again: start = delayed_refs->run_delayed_start; - head = find_ref_head(&delayed_refs->href_root, start, 1); + head = find_ref_head(delayed_refs, start, true); if (!head && !loop) { delayed_refs->run_delayed_start = 0; start = 0; loop = true; - head = find_ref_head(&delayed_refs->href_root, start, 1); + head = find_ref_head(delayed_refs, start, true); if (!head) return NULL; } else if (!head && loop) { @@ -569,7 +572,7 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref, head_ref->must_insert_reserved = must_insert_reserved; head_ref->is_data = is_data; head_ref->is_system = is_system; - head_ref->ref_tree = RB_ROOT; + head_ref->ref_tree = RB_ROOT_CACHED; INIT_LIST_HEAD(&head_ref->ref_add_list); RB_CLEAR_NODE(&head_ref->href_node); head_ref->processing = 0; @@ -903,7 +906,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head * btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr) { - return find_ref_head(&delayed_refs->href_root, bytenr, 0); + return find_ref_head(delayed_refs, bytenr, false); } void __cold btrfs_delayed_ref_exit(void) diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index d9f2a4ebd5db..8e20c5cb5404 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -79,7 +79,7 @@ struct btrfs_delayed_ref_head { struct mutex mutex; spinlock_t lock; - struct rb_root ref_tree; + struct rb_root_cached ref_tree; /* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */ struct list_head ref_add_list; @@ -148,7 +148,7 @@ struct btrfs_delayed_data_ref { struct btrfs_delayed_ref_root { /* head ref rbtree */ - struct rb_root href_root; + struct rb_root_cached href_root; /* dirty extent records */ struct rb_root dirty_extent_root; @@ -255,7 +255,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head * btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr); -int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, +int btrfs_delayed_ref_lock(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head) { @@ -263,8 +263,8 @@ static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head) } -struct btrfs_delayed_ref_head * -btrfs_select_ref_head(struct btrfs_trans_handle *trans); +struct btrfs_delayed_ref_head *btrfs_select_ref_head( + struct btrfs_delayed_ref_root *delayed_refs); int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index dec01970d8c5..2aa48aecc52b 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -382,14 +382,6 @@ out: return ret; } -void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info) -{ - struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; - - dev_replace->committed_cursor_left = - dev_replace->cursor_left_last_write_of_item; -} - static char* btrfs_dev_name(struct btrfs_device *device) { if (!device || test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) @@ -408,11 +400,12 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, int ret; struct btrfs_device *tgt_device = NULL; struct btrfs_device *src_device = NULL; + bool need_unlock; - ret = btrfs_find_device_by_devspec(fs_info, srcdevid, - srcdev_name, &src_device); - if (ret) - return ret; + src_device = btrfs_find_device_by_devspec(fs_info, srcdevid, + srcdev_name); + if (IS_ERR(src_device)) + return PTR_ERR(src_device); ret = btrfs_init_dev_replace_tgtdev(fs_info, tgtdev_name, src_device, &tgt_device); @@ -432,6 +425,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, return PTR_ERR(trans); } + need_unlock = true; btrfs_dev_replace_write_lock(dev_replace); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: @@ -440,6 +434,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: + ASSERT(0); ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED; goto leave; } @@ -470,6 +465,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, atomic64_set(&dev_replace->num_write_errors, 0); atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0); btrfs_dev_replace_write_unlock(dev_replace); + need_unlock = false; ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device); if (ret) @@ -481,7 +477,12 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + need_unlock = true; btrfs_dev_replace_write_lock(dev_replace); + dev_replace->replace_state = + BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; goto leave; } @@ -503,9 +504,8 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, return ret; leave: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; - btrfs_dev_replace_write_unlock(dev_replace); + if (need_unlock) + btrfs_dev_replace_write_unlock(dev_replace); btrfs_destroy_dev_replace_tgtdev(tgt_device); return ret; } @@ -545,8 +545,8 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info) { set_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state); - wait_event(fs_info->replace_wait, !percpu_counter_sum( - &fs_info->bio_counter)); + wait_event(fs_info->dev_replace.replace_wait, !percpu_counter_sum( + &fs_info->dev_replace.bio_counter)); } /* @@ -555,7 +555,7 @@ static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info) static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info) { clear_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state); - wake_up(&fs_info->replace_wait); + wake_up(&fs_info->dev_replace.replace_wait); } static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, @@ -961,13 +961,10 @@ int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace) void btrfs_dev_replace_read_lock(struct btrfs_dev_replace *dev_replace) { read_lock(&dev_replace->lock); - atomic_inc(&dev_replace->read_locks); } void btrfs_dev_replace_read_unlock(struct btrfs_dev_replace *dev_replace) { - ASSERT(atomic_read(&dev_replace->read_locks) > 0); - atomic_dec(&dev_replace->read_locks); read_unlock(&dev_replace->lock); } @@ -985,7 +982,6 @@ again: void btrfs_dev_replace_write_unlock(struct btrfs_dev_replace *dev_replace) { - ASSERT(atomic_read(&dev_replace->blocking_readers) == 0); write_unlock(&dev_replace->lock); } @@ -994,45 +990,31 @@ void btrfs_dev_replace_set_lock_blocking( struct btrfs_dev_replace *dev_replace) { /* only set blocking for read lock */ - ASSERT(atomic_read(&dev_replace->read_locks) > 0); atomic_inc(&dev_replace->blocking_readers); read_unlock(&dev_replace->lock); } -/* acquire read lock and dec blocking cnt */ -void btrfs_dev_replace_clear_lock_blocking( - struct btrfs_dev_replace *dev_replace) -{ - /* only set blocking for read lock */ - ASSERT(atomic_read(&dev_replace->read_locks) > 0); - ASSERT(atomic_read(&dev_replace->blocking_readers) > 0); - read_lock(&dev_replace->lock); - /* Barrier implied by atomic_dec_and_test */ - if (atomic_dec_and_test(&dev_replace->blocking_readers)) - cond_wake_up_nomb(&dev_replace->read_lock_wq); -} - void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info) { - percpu_counter_inc(&fs_info->bio_counter); + percpu_counter_inc(&fs_info->dev_replace.bio_counter); } void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount) { - percpu_counter_sub(&fs_info->bio_counter, amount); - cond_wake_up_nomb(&fs_info->replace_wait); + percpu_counter_sub(&fs_info->dev_replace.bio_counter, amount); + cond_wake_up_nomb(&fs_info->dev_replace.replace_wait); } void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info) { while (1) { - percpu_counter_inc(&fs_info->bio_counter); + percpu_counter_inc(&fs_info->dev_replace.bio_counter); if (likely(!test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state))) break; btrfs_bio_counter_dec(fs_info); - wait_event(fs_info->replace_wait, + wait_event(fs_info->dev_replace.replace_wait, !test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state)); } diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index b6d4206188bb..795c551f5b5e 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -11,7 +11,6 @@ struct btrfs_ioctl_dev_replace_args; int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info); int btrfs_run_dev_replace(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info); int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args); int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, @@ -28,12 +27,5 @@ void btrfs_dev_replace_read_unlock(struct btrfs_dev_replace *dev_replace); void btrfs_dev_replace_write_lock(struct btrfs_dev_replace *dev_replace); void btrfs_dev_replace_write_unlock(struct btrfs_dev_replace *dev_replace); void btrfs_dev_replace_set_lock_blocking(struct btrfs_dev_replace *dev_replace); -void btrfs_dev_replace_clear_lock_blocking( - struct btrfs_dev_replace *dev_replace); - -static inline void btrfs_dev_replace_stats_inc(atomic64_t *stat_value) -{ - atomic64_inc(stat_value); -} #endif diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index a678b07fcf01..8de74d835dba 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -105,13 +105,13 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, * to use for the second index (if one is created). * Will return 0 or -ENOMEM */ -int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root - *root, const char *name, int name_len, - struct btrfs_inode *dir, struct btrfs_key *location, - u8 type, u64 index) +int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, + int name_len, struct btrfs_inode *dir, + struct btrfs_key *location, u8 type, u64 index) { int ret = 0; int ret2 = 0; + struct btrfs_root *root = dir->root; struct btrfs_path *path; struct btrfs_dir_item *dir_item; struct extent_buffer *leaf; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 05dc3c17cb62..b0ab41da91d1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -125,8 +125,8 @@ struct async_submit_bio { * Different roots are used for different purposes and may nest inside each * other and they require separate keysets. As lockdep keys should be * static, assign keysets according to the purpose of the root as indicated - * by btrfs_root->objectid. This ensures that all special purpose roots - * have separate keysets. + * by btrfs_root->root_key.objectid. This ensures that all special purpose + * roots have separate keysets. * * Lock-nesting across peer nodes is always done with the immediate parent * node locked thus preventing deadlock. As lockdep doesn't know this, use @@ -1148,7 +1148,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->state = 0; root->orphan_cleanup_state = 0; - root->objectid = objectid; root->last_trans = 0; root->highest_objectid = 0; root->nr_delalloc_inodes = 0; @@ -2156,9 +2155,8 @@ static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) { mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); rwlock_init(&fs_info->dev_replace.lock); - atomic_set(&fs_info->dev_replace.read_locks, 0); atomic_set(&fs_info->dev_replace.blocking_readers, 0); - init_waitqueue_head(&fs_info->replace_wait); + init_waitqueue_head(&fs_info->dev_replace.replace_wait); init_waitqueue_head(&fs_info->dev_replace.read_lock_wq); } @@ -2648,7 +2646,8 @@ int open_ctree(struct super_block *sb, goto fail_dirty_metadata_bytes; } - ret = percpu_counter_init(&fs_info->bio_counter, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0, + GFP_KERNEL); if (ret) { err = ret; goto fail_delalloc_bytes; @@ -3309,7 +3308,7 @@ fail_iput: iput(fs_info->btree_inode); fail_bio_counter: - percpu_counter_destroy(&fs_info->bio_counter); + percpu_counter_destroy(&fs_info->dev_replace.bio_counter); fail_delalloc_bytes: percpu_counter_destroy(&fs_info->delalloc_bytes); fail_dirty_metadata_bytes: @@ -3977,6 +3976,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); + ASSERT(list_empty(&fs_info->delayed_iputs)); set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); btrfs_free_qgroup_config(fs_info); @@ -4018,7 +4018,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); - percpu_counter_destroy(&fs_info->bio_counter); + percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); btrfs_free_stripe_hash_table(fs_info); @@ -4204,7 +4204,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, return ret; } - while ((node = rb_first(&delayed_refs->href_root)) != NULL) { + while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) { struct btrfs_delayed_ref_head *head; struct rb_node *n; bool pin_bytes = false; @@ -4222,11 +4222,11 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, continue; } spin_lock(&head->lock); - while ((n = rb_first(&head->ref_tree)) != NULL) { + while ((n = rb_first_cached(&head->ref_tree)) != NULL) { ref = rb_entry(n, struct btrfs_delayed_ref_node, ref_node); ref->in_tree = 0; - rb_erase(&ref->ref_node, &head->ref_tree); + rb_erase_cached(&ref->ref_node, &head->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); @@ -4240,7 +4240,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, if (head->processing == 0) delayed_refs->num_heads_ready--; atomic_dec(&delayed_refs->num_entries); - rb_erase(&head->href_node, &delayed_refs->href_root); + rb_erase_cached(&head->href_node, &delayed_refs->href_root); RB_CLEAR_NODE(&head->href_node); spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1f3755b3a37a..ddf28ecf17f9 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -33,7 +33,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, type = FILEID_BTRFS_WITHOUT_PARENT; fid->objectid = btrfs_ino(BTRFS_I(inode)); - fid->root_objectid = BTRFS_I(inode)->root->objectid; + fid->root_objectid = BTRFS_I(inode)->root->root_key.objectid; fid->gen = inode->i_generation; if (parent) { @@ -41,7 +41,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, fid->parent_objectid = BTRFS_I(parent)->location.objectid; fid->parent_gen = parent->i_generation; - parent_root_id = BTRFS_I(parent)->root->objectid; + parent_root_id = BTRFS_I(parent)->root->root_key.objectid; if (parent_root_id != fid->root_objectid) { fid->parent_root_objectid = parent_root_id; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2d9074295d7f..a4cd0221bc8d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2374,7 +2374,7 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head) { struct btrfs_delayed_ref_node *ref; - if (RB_EMPTY_ROOT(&head->ref_tree)) + if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) return NULL; /* @@ -2387,7 +2387,7 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head) return list_first_entry(&head->ref_add_list, struct btrfs_delayed_ref_node, add_list); - ref = rb_entry(rb_first(&head->ref_tree), + ref = rb_entry(rb_first_cached(&head->ref_tree), struct btrfs_delayed_ref_node, ref_node); ASSERT(list_empty(&ref->add_list)); return ref; @@ -2448,13 +2448,13 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, spin_unlock(&head->lock); spin_lock(&delayed_refs->lock); spin_lock(&head->lock); - if (!RB_EMPTY_ROOT(&head->ref_tree) || head->extent_op) { + if (!RB_EMPTY_ROOT(&head->ref_tree.rb_root) || head->extent_op) { spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); return 1; } delayed_refs->num_heads--; - rb_erase(&head->href_node, &delayed_refs->href_root); + rb_erase_cached(&head->href_node, &delayed_refs->href_root); RB_CLEAR_NODE(&head->href_node); spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); @@ -2502,102 +2502,66 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, return 0; } -/* - * Returns 0 on success or if called with an already aborted transaction. - * Returns -ENOMEM or -EIO on failure and will abort the transaction. - */ -static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, - unsigned long nr) +static struct btrfs_delayed_ref_head *btrfs_obtain_ref_head( + struct btrfs_trans_handle *trans) +{ + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + struct btrfs_delayed_ref_head *head = NULL; + int ret; + + spin_lock(&delayed_refs->lock); + head = btrfs_select_ref_head(delayed_refs); + if (!head) { + spin_unlock(&delayed_refs->lock); + return head; + } + + /* + * Grab the lock that says we are going to process all the refs for + * this head + */ + ret = btrfs_delayed_ref_lock(delayed_refs, head); + spin_unlock(&delayed_refs->lock); + + /* + * We may have dropped the spin lock to get the head mutex lock, and + * that might have given someone else time to free the head. If that's + * true, it has been removed from our list and we can move on. + */ + if (ret == -EAGAIN) + head = ERR_PTR(-EAGAIN); + + return head; +} + +static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_head *locked_ref, + unsigned long *run_refs) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_delayed_ref_node *ref; - struct btrfs_delayed_ref_head *locked_ref = NULL; struct btrfs_delayed_extent_op *extent_op; - ktime_t start = ktime_get(); - int ret; - unsigned long count = 0; - unsigned long actual_count = 0; + struct btrfs_delayed_ref_node *ref; int must_insert_reserved = 0; + int ret; delayed_refs = &trans->transaction->delayed_refs; - while (1) { - if (!locked_ref) { - if (count >= nr) - break; - spin_lock(&delayed_refs->lock); - locked_ref = btrfs_select_ref_head(trans); - if (!locked_ref) { - spin_unlock(&delayed_refs->lock); - break; - } + lockdep_assert_held(&locked_ref->mutex); + lockdep_assert_held(&locked_ref->lock); - /* grab the lock that says we are going to process - * all the refs for this head */ - ret = btrfs_delayed_ref_lock(trans, locked_ref); - spin_unlock(&delayed_refs->lock); - /* - * we may have dropped the spin lock to get the head - * mutex lock, and that might have given someone else - * time to free the head. If that's true, it has been - * removed from our list and we can move on. - */ - if (ret == -EAGAIN) { - locked_ref = NULL; - count++; - continue; - } - } - - /* - * We need to try and merge add/drops of the same ref since we - * can run into issues with relocate dropping the implicit ref - * and then it being added back again before the drop can - * finish. If we merged anything we need to re-loop so we can - * get a good ref. - * Or we can get node references of the same type that weren't - * merged when created due to bumps in the tree mod seq, and - * we need to merge them to prevent adding an inline extent - * backref before dropping it (triggering a BUG_ON at - * insert_inline_extent_backref()). - */ - spin_lock(&locked_ref->lock); - btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref); - - ref = select_delayed_ref(locked_ref); - - if (ref && ref->seq && + while ((ref = select_delayed_ref(locked_ref))) { + if (ref->seq && btrfs_check_delayed_seq(fs_info, ref->seq)) { spin_unlock(&locked_ref->lock); unselect_delayed_ref_head(delayed_refs, locked_ref); - locked_ref = NULL; - cond_resched(); - count++; - continue; - } - - /* - * We're done processing refs in this ref_head, clean everything - * up and move on to the next ref_head. - */ - if (!ref) { - ret = cleanup_ref_head(trans, locked_ref); - if (ret > 0 ) { - /* We dropped our lock, we need to loop. */ - ret = 0; - continue; - } else if (ret) { - return ret; - } - locked_ref = NULL; - count++; - continue; + return -EAGAIN; } - actual_count++; + (*run_refs)++; ref->in_tree = 0; - rb_erase(&ref->ref_node, &locked_ref->ref_tree); + rb_erase_cached(&ref->ref_node, &locked_ref->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); @@ -2619,8 +2583,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, atomic_dec(&delayed_refs->num_entries); /* - * Record the must-insert_reserved flag before we drop the spin - * lock. + * Record the must_insert_reserved flag before we drop the + * spin lock. */ must_insert_reserved = locked_ref->must_insert_reserved; locked_ref->must_insert_reserved = 0; @@ -2642,10 +2606,90 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, } btrfs_put_delayed_ref(ref); - count++; cond_resched(); + + spin_lock(&locked_ref->lock); + btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref); } + return 0; +} + +/* + * Returns 0 on success or if called with an already aborted transaction. + * Returns -ENOMEM or -EIO on failure and will abort the transaction. + */ +static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, + unsigned long nr) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_head *locked_ref = NULL; + ktime_t start = ktime_get(); + int ret; + unsigned long count = 0; + unsigned long actual_count = 0; + + delayed_refs = &trans->transaction->delayed_refs; + do { + if (!locked_ref) { + locked_ref = btrfs_obtain_ref_head(trans); + if (IS_ERR_OR_NULL(locked_ref)) { + if (PTR_ERR(locked_ref) == -EAGAIN) { + continue; + } else { + break; + } + } + count++; + } + /* + * We need to try and merge add/drops of the same ref since we + * can run into issues with relocate dropping the implicit ref + * and then it being added back again before the drop can + * finish. If we merged anything we need to re-loop so we can + * get a good ref. + * Or we can get node references of the same type that weren't + * merged when created due to bumps in the tree mod seq, and + * we need to merge them to prevent adding an inline extent + * backref before dropping it (triggering a BUG_ON at + * insert_inline_extent_backref()). + */ + spin_lock(&locked_ref->lock); + btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref); + + ret = btrfs_run_delayed_refs_for_head(trans, locked_ref, + &actual_count); + if (ret < 0 && ret != -EAGAIN) { + /* + * Error, btrfs_run_delayed_refs_for_head already + * unlocked everything so just bail out + */ + return ret; + } else if (!ret) { + /* + * Success, perform the usual cleanup of a processed + * head + */ + ret = cleanup_ref_head(trans, locked_ref); + if (ret > 0 ) { + /* We dropped our lock, we need to loop. */ + ret = 0; + continue; + } else if (ret) { + return ret; + } + } + + /* + * Either success case or btrfs_run_delayed_refs_for_head + * returned -EAGAIN, meaning we need to select another head + */ + + locked_ref = NULL; + cond_resched(); + } while ((nr != -1 && count < nr) || locked_ref); + /* * We don't want to include ref heads since we can have empty ref heads * and those will drastically skew our runtime down since we just do @@ -2745,9 +2789,9 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes) return num_csums; } -int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_rsv *global_rsv; u64 num_heads = trans->transaction->delayed_refs.num_heads_ready; u64 csum_bytes = trans->transaction->delayed_refs.pending_csums; @@ -2782,8 +2826,7 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, return ret; } -int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans) { u64 num_entries = atomic_read(&trans->transaction->delayed_refs.num_entries); @@ -2791,14 +2834,14 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, u64 val; smp_mb(); - avg_runtime = fs_info->avg_delayed_ref_runtime; + avg_runtime = trans->fs_info->avg_delayed_ref_runtime; val = num_entries * avg_runtime; if (val >= NSEC_PER_SEC) return 1; if (val >= NSEC_PER_SEC / 2) return 2; - return btrfs_check_space_for_delayed_refs(trans, fs_info); + return btrfs_check_space_for_delayed_refs(trans); } struct async_delayed_refs { @@ -2940,7 +2983,7 @@ again: btrfs_create_pending_block_groups(trans); spin_lock(&delayed_refs->lock); - node = rb_first(&delayed_refs->href_root); + node = rb_first_cached(&delayed_refs->href_root); if (!node) { spin_unlock(&delayed_refs->lock); goto out; @@ -3040,7 +3083,8 @@ static noinline int check_delayed_ref(struct btrfs_root *root, * XXX: We should replace this with a proper search function in the * future. */ - for (node = rb_first(&head->ref_tree); node; node = rb_next(node)) { + for (node = rb_first_cached(&head->ref_tree); node; + node = rb_next(node)) { ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); /* If it's a shared ref we know a cross reference exists */ if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) { @@ -3139,7 +3183,6 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, { struct btrfs_path *path; int ret; - int ret2; path = btrfs_alloc_path(); if (!path) @@ -3151,17 +3194,9 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, if (ret && ret != -ENOENT) goto out; - ret2 = check_delayed_ref(root, path, objectid, - offset, bytenr); - } while (ret2 == -EAGAIN); - - if (ret2 && ret2 != -ENOENT) { - ret = ret2; - goto out; - } + ret = check_delayed_ref(root, path, objectid, offset, bytenr); + } while (ret == -EAGAIN); - if (ret != -ENOENT || ret2 != -ENOENT) - ret = 0; out: btrfs_free_path(path); if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) @@ -5284,7 +5319,7 @@ static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, } static void block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv, - u64 num_bytes, int update_size) + u64 num_bytes, bool update_size) { spin_lock(&block_rsv->lock); block_rsv->reserved += num_bytes; @@ -5316,7 +5351,7 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info, global_rsv->full = 0; spin_unlock(&global_rsv->lock); - block_rsv_add_bytes(dest, num_bytes, 1); + block_rsv_add_bytes(dest, num_bytes, true); return 0; } @@ -5479,7 +5514,7 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info, int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src, struct btrfs_block_rsv *dst, u64 num_bytes, - int update_size) + bool update_size) { int ret; @@ -5539,10 +5574,8 @@ int btrfs_block_rsv_add(struct btrfs_root *root, return 0; ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush); - if (!ret) { - block_rsv_add_bytes(block_rsv, num_bytes, 1); - return 0; - } + if (!ret) + block_rsv_add_bytes(block_rsv, num_bytes, true); return ret; } @@ -5587,7 +5620,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root, ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush); if (!ret) { - block_rsv_add_bytes(block_rsv, num_bytes, 0); + block_rsv_add_bytes(block_rsv, num_bytes, false); return 0; } @@ -5629,7 +5662,7 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode, return ret; ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush); if (!ret) { - block_rsv_add_bytes(block_rsv, num_bytes, 0); + block_rsv_add_bytes(block_rsv, num_bytes, false); trace_btrfs_space_reservation(root->fs_info, "delalloc", btrfs_ino(inode), num_bytes, 1); @@ -5835,7 +5868,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, BTRFS_RESERVE_FLUSH_ALL); if (ret == -ENOSPC && use_global_rsv) - ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1); + ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, true); if (ret && qgroup_num_bytes) btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes); @@ -6399,10 +6432,6 @@ static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, } else { cache->reserved += num_bytes; space_info->bytes_reserved += num_bytes; - - trace_btrfs_space_reservation(cache->fs_info, - "space_info", space_info->flags, - ram_bytes, 0); space_info->bytes_may_use -= ram_bytes; if (delalloc) cache->delalloc_bytes += num_bytes; @@ -6424,11 +6453,10 @@ static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, * reserve set to 0 in order to clear the reservation. */ -static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int delalloc) +static void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; - int ret = 0; spin_lock(&space_info->lock); spin_lock(&cache->lock); @@ -6441,7 +6469,6 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, cache->delalloc_bytes -= num_bytes; spin_unlock(&cache->lock); spin_unlock(&space_info->lock); - return ret; } void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info) { @@ -6925,7 +6952,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, goto out_delayed_unlock; spin_lock(&head->lock); - if (!RB_EMPTY_ROOT(&head->ref_tree)) + if (!RB_EMPTY_ROOT(&head->ref_tree.rb_root)) goto out; if (head->extent_op) { @@ -6946,7 +6973,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, * at this point we have a head with no other entries. Go * ahead and process it. */ - rb_erase(&head->href_node, &delayed_refs->href_root); + rb_erase_cached(&head->href_node, &delayed_refs->href_root); RB_CLEAR_NODE(&head->href_node); atomic_dec(&delayed_refs->num_entries); @@ -8119,6 +8146,19 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, if (IS_ERR(buf)) return buf; + /* + * Extra safety check in case the extent tree is corrupted and extent + * allocator chooses to use a tree block which is already used and + * locked. + */ + if (buf->lock_owner == current->pid) { + btrfs_err_rl(fs_info, +"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected", + buf->start, btrfs_header_owner(buf), current->pid); + free_extent_buffer(buf); + return ERR_PTR(-EUCLEAN); + } + btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); clean_tree_block(fs_info, buf); @@ -8215,7 +8255,7 @@ try_reserve: static void unuse_block_rsv(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u32 blocksize) { - block_rsv_add_bytes(block_rsv, blocksize, 0); + block_rsv_add_bytes(block_rsv, blocksize, false); block_rsv_release_bytes(fs_info, block_rsv, NULL, 0, NULL); } @@ -8642,7 +8682,13 @@ skip: parent = 0; } - if (need_account) { + /* + * Reloc tree doesn't contribute to qgroup numbers, and we have + * already accounted them at merge time (replace_path), + * thus we could skip expensive subtree trace here. + */ + if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID && + need_account) { ret = btrfs_qgroup_trace_subtree(trans, next, generation, level - 1); if (ret) { @@ -8763,15 +8809,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (eb == root->node) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) parent = eb->start; - else - BUG_ON(root->root_key.objectid != - btrfs_header_owner(eb)); + else if (root->root_key.objectid != btrfs_header_owner(eb)) + goto owner_mismatch; } else { if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF) parent = path->nodes[level + 1]->start; - else - BUG_ON(root->root_key.objectid != - btrfs_header_owner(path->nodes[level + 1])); + else if (root->root_key.objectid != + btrfs_header_owner(path->nodes[level + 1])) + goto owner_mismatch; } btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); @@ -8779,6 +8824,11 @@ out: wc->refs[level] = 0; wc->flags[level] = 0; return 0; + +owner_mismatch: + btrfs_err_rl(fs_info, "unexpected tree owner, have %llu expect %llu", + btrfs_header_owner(eb), root->root_key.objectid); + return -EUCLEAN; } static noinline int walk_down_tree(struct btrfs_trans_handle *trans, @@ -8832,6 +8882,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, ret = walk_up_proc(trans, root, path, wc); if (ret > 0) return 0; + if (ret < 0) + return ret; if (path->locks[level]) { btrfs_tree_unlock_rw(path->nodes[level], @@ -8875,7 +8927,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int level; bool root_dropped = false; - btrfs_debug(fs_info, "Drop subvolume %llu", root->objectid); + btrfs_debug(fs_info, "Drop subvolume %llu", root->root_key.objectid); path = btrfs_alloc_path(); if (!path) { @@ -9613,6 +9665,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) block_group = btrfs_lookup_first_block_group(info, last); while (block_group) { + wait_block_group_cache_done(block_group); spin_lock(&block_group->lock); if (block_group->iref) break; @@ -10074,7 +10127,7 @@ error: void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *block_group, *tmp; + struct btrfs_block_group_cache *block_group; struct btrfs_root *extent_root = fs_info->extent_root; struct btrfs_block_group_item item; struct btrfs_key key; @@ -10082,7 +10135,10 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) bool can_flush_pending_bgs = trans->can_flush_pending_bgs; trans->can_flush_pending_bgs = false; - list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { + while (!list_empty(&trans->new_bgs)) { + block_group = list_first_entry(&trans->new_bgs, + struct btrfs_block_group_cache, + bg_list); if (ret) goto next; @@ -10753,14 +10809,16 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, * We don't want a transaction for this since the discard may take a * substantial amount of time. We don't require that a transaction be * running, but we do need to take a running transaction into account - * to ensure that we're not discarding chunks that were released in - * the current transaction. + * to ensure that we're not discarding chunks that were released or + * allocated in the current transaction. * * Holding the chunks lock will prevent other threads from allocating * or releasing chunks, but it won't prevent a running transaction * from committing and releasing the memory that the pending chunks * list head uses. For that, we need to take a reference to the - * transaction. + * transaction and hold the commit root sem. We only need to hold + * it while performing the free space search since we have already + * held back allocations. */ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 minlen, u64 *trimmed) @@ -10770,6 +10828,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, *trimmed = 0; + /* Discard not supported = nothing to do. */ + if (!blk_queue_discard(bdev_get_queue(device->bdev))) + return 0; + /* Not writeable = nothing to do. */ if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) return 0; @@ -10787,9 +10849,13 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, ret = mutex_lock_interruptible(&fs_info->chunk_mutex); if (ret) - return ret; + break; - down_read(&fs_info->commit_root_sem); + ret = down_read_killable(&fs_info->commit_root_sem); + if (ret) { + mutex_unlock(&fs_info->chunk_mutex); + break; + } spin_lock(&fs_info->trans_lock); trans = fs_info->running_transaction; @@ -10797,13 +10863,17 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, refcount_inc(&trans->use_count); spin_unlock(&fs_info->trans_lock); + if (!trans) + up_read(&fs_info->commit_root_sem); + ret = find_free_dev_extent_start(trans, device, minlen, start, &start, &len); - if (trans) + if (trans) { + up_read(&fs_info->commit_root_sem); btrfs_put_transaction(trans); + } if (ret) { - up_read(&fs_info->commit_root_sem); mutex_unlock(&fs_info->chunk_mutex); if (ret == -ENOSPC) ret = 0; @@ -10811,7 +10881,6 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, } ret = btrfs_issue_discard(device->bdev, start, len, &bytes); - up_read(&fs_info->commit_root_sem); mutex_unlock(&fs_info->chunk_mutex); if (ret) @@ -10831,6 +10900,15 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, return ret; } +/* + * Trim the whole filesystem by: + * 1) trimming the free space in each block group + * 2) trimming the unallocated space on each device + * + * This will also continue trimming even if a block group or device encounters + * an error. The return value will be the last error, or 0 if nothing bad + * happens. + */ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) { struct btrfs_block_group_cache *cache = NULL; @@ -10840,18 +10918,14 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) u64 start; u64 end; u64 trimmed = 0; - u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); + u64 bg_failed = 0; + u64 dev_failed = 0; + int bg_ret = 0; + int dev_ret = 0; int ret = 0; - /* - * try to trim all FS space, our block group may start from non-zero. - */ - if (range->len == total_bytes) - cache = btrfs_lookup_first_block_group(fs_info, range->start); - else - cache = btrfs_lookup_block_group(fs_info, range->start); - - while (cache) { + cache = btrfs_lookup_first_block_group(fs_info, range->start); + for (; cache; cache = next_block_group(fs_info, cache)) { if (cache->key.objectid >= (range->start + range->len)) { btrfs_put_block_group(cache); break; @@ -10865,13 +10939,15 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) if (!block_group_cache_done(cache)) { ret = cache_block_group(cache, 0); if (ret) { - btrfs_put_block_group(cache); - break; + bg_failed++; + bg_ret = ret; + continue; } ret = wait_block_group_cache_done(cache); if (ret) { - btrfs_put_block_group(cache); - break; + bg_failed++; + bg_ret = ret; + continue; } } ret = btrfs_trim_block_group(cache, @@ -10882,28 +10958,40 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) trimmed += group_trimmed; if (ret) { - btrfs_put_block_group(cache); - break; + bg_failed++; + bg_ret = ret; + continue; } } - - cache = next_block_group(fs_info, cache); } + if (bg_failed) + btrfs_warn(fs_info, + "failed to trim %llu block group(s), last error %d", + bg_failed, bg_ret); mutex_lock(&fs_info->fs_devices->device_list_mutex); - devices = &fs_info->fs_devices->alloc_list; - list_for_each_entry(device, devices, dev_alloc_list) { + devices = &fs_info->fs_devices->devices; + list_for_each_entry(device, devices, dev_list) { ret = btrfs_trim_free_extents(device, range->minlen, &group_trimmed); - if (ret) + if (ret) { + dev_failed++; + dev_ret = ret; break; + } trimmed += group_trimmed; } mutex_unlock(&fs_info->fs_devices->device_list_mutex); + if (dev_failed) + btrfs_warn(fs_info, + "failed to trim %llu device(s), last error %d", + dev_failed, dev_ret); range->len = trimmed; - return ret; + if (bg_ret) + return bg_ret; + return dev_ret; } /* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4dd6faab02bb..6877a74c7469 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1424,20 +1424,15 @@ int find_first_extent_bit(struct extent_io_tree *tree, u64 start, struct extent_state **cached_state) { struct extent_state *state; - struct rb_node *n; int ret = 1; spin_lock(&tree->lock); if (cached_state && *cached_state) { state = *cached_state; if (state->end == start - 1 && extent_state_in_tree(state)) { - n = rb_next(&state->rb_node); - while (n) { - state = rb_entry(n, struct extent_state, - rb_node); + while ((state = next_state(state)) != NULL) { if (state->state & bits) goto got_it; - n = rb_next(n); } free_extent_state(*cached_state); *cached_state = NULL; @@ -1568,7 +1563,7 @@ static noinline int lock_delalloc_pages(struct inode *inode, * * 1 is returned if we find something, 0 if nothing was in the tree */ -STATIC u64 find_lock_delalloc_range(struct inode *inode, +static noinline_for_stack u64 find_lock_delalloc_range(struct inode *inode, struct extent_io_tree *tree, struct page *locked_page, u64 *start, u64 *end, u64 max_bytes) @@ -1648,6 +1643,17 @@ out_failed: return found; } +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +u64 btrfs_find_lock_delalloc_range(struct inode *inode, + struct extent_io_tree *tree, + struct page *locked_page, u64 *start, + u64 *end, u64 max_bytes) +{ + return find_lock_delalloc_range(inode, tree, locked_page, start, end, + max_bytes); +} +#endif + static int __process_pages_contig(struct address_space *mapping, struct page *locked_page, pgoff_t start_index, pgoff_t end_index, @@ -5165,11 +5171,11 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb) WARN_ON(atomic_read(&eb->refs) == 0); } -int set_extent_buffer_dirty(struct extent_buffer *eb) +bool set_extent_buffer_dirty(struct extent_buffer *eb) { int i; int num_pages; - int was_dirty = 0; + bool was_dirty; check_buffer_tree_ref(eb); @@ -5179,8 +5185,15 @@ int set_extent_buffer_dirty(struct extent_buffer *eb) WARN_ON(atomic_read(&eb->refs) == 0); WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)); + if (!was_dirty) + for (i = 0; i < num_pages; i++) + set_page_dirty(eb->pages[i]); + +#ifdef CONFIG_BTRFS_DEBUG for (i = 0; i < num_pages; i++) - set_page_dirty(eb->pages[i]); + ASSERT(PageDirty(eb->pages[i])); +#endif + return was_dirty; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index b4d03e677e1d..369daa5d4f73 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -479,7 +479,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start, void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start, unsigned long pos, unsigned long len); void clear_extent_buffer_dirty(struct extent_buffer *eb); -int set_extent_buffer_dirty(struct extent_buffer *eb); +bool set_extent_buffer_dirty(struct extent_buffer *eb); void set_extent_buffer_uptodate(struct extent_buffer *eb); void clear_extent_buffer_uptodate(struct extent_buffer *eb); int extent_buffer_under_io(struct extent_buffer *eb); @@ -546,7 +546,7 @@ int free_io_failure(struct extent_io_tree *failure_tree, struct extent_io_tree *io_tree, struct io_failure_record *rec); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -noinline u64 find_lock_delalloc_range(struct inode *inode, +u64 btrfs_find_lock_delalloc_range(struct inode *inode, struct extent_io_tree *tree, struct page *locked_page, u64 *start, u64 *end, u64 max_bytes); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 6648d55e5339..7eea8b6e2cd3 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -34,7 +34,7 @@ void __cold extent_map_exit(void) */ void extent_map_tree_init(struct extent_map_tree *tree) { - tree->map = RB_ROOT; + tree->map = RB_ROOT_CACHED; INIT_LIST_HEAD(&tree->modified_extents); rwlock_init(&tree->lock); } @@ -90,24 +90,27 @@ static u64 range_end(u64 start, u64 len) return start + len; } -static int tree_insert(struct rb_root *root, struct extent_map *em) +static int tree_insert(struct rb_root_cached *root, struct extent_map *em) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent = NULL; struct extent_map *entry = NULL; struct rb_node *orig_parent = NULL; u64 end = range_end(em->start, em->len); + bool leftmost = true; while (*p) { parent = *p; entry = rb_entry(parent, struct extent_map, rb_node); - if (em->start < entry->start) + if (em->start < entry->start) { p = &(*p)->rb_left; - else if (em->start >= extent_map_end(entry)) + } else if (em->start >= extent_map_end(entry)) { p = &(*p)->rb_right; - else + leftmost = false; + } else { return -EEXIST; + } } orig_parent = parent; @@ -130,7 +133,7 @@ static int tree_insert(struct rb_root *root, struct extent_map *em) return -EEXIST; rb_link_node(&em->rb_node, orig_parent, p); - rb_insert_color(&em->rb_node, root); + rb_insert_color_cached(&em->rb_node, root, leftmost); return 0; } @@ -242,7 +245,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) em->mod_start = merge->mod_start; em->generation = max(em->generation, merge->generation); - rb_erase(&merge->rb_node, &tree->map); + rb_erase_cached(&merge->rb_node, &tree->map); RB_CLEAR_NODE(&merge->rb_node); free_extent_map(merge); } @@ -254,7 +257,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) if (rb && mergable_maps(em, merge)) { em->len += merge->len; em->block_len += merge->block_len; - rb_erase(&merge->rb_node, &tree->map); + rb_erase_cached(&merge->rb_node, &tree->map); RB_CLEAR_NODE(&merge->rb_node); em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start; em->generation = max(em->generation, merge->generation); @@ -367,7 +370,7 @@ __lookup_extent_mapping(struct extent_map_tree *tree, struct rb_node *next = NULL; u64 end = range_end(start, len); - rb_node = __tree_search(&tree->map, start, &prev, &next); + rb_node = __tree_search(&tree->map.rb_root, start, &prev, &next); if (!rb_node) { if (prev) rb_node = prev; @@ -428,16 +431,13 @@ struct extent_map *search_extent_mapping(struct extent_map_tree *tree, * Removes @em from @tree. No reference counts are dropped, and no checks * are done to see if the range is in use */ -int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) +void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) { - int ret = 0; - WARN_ON(test_bit(EXTENT_FLAG_PINNED, &em->flags)); - rb_erase(&em->rb_node, &tree->map); + rb_erase_cached(&em->rb_node, &tree->map); if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) list_del_init(&em->list); RB_CLEAR_NODE(&em->rb_node); - return ret; } void replace_extent_mapping(struct extent_map_tree *tree, @@ -449,7 +449,7 @@ void replace_extent_mapping(struct extent_map_tree *tree, ASSERT(extent_map_in_tree(cur)); if (!test_bit(EXTENT_FLAG_LOGGING, &cur->flags)) list_del_init(&cur->list); - rb_replace_node(&cur->rb_node, &new->rb_node, &tree->map); + rb_replace_node_cached(&cur->rb_node, &new->rb_node, &tree->map); RB_CLEAR_NODE(&cur->rb_node); setup_extent_mapping(tree, new, modified); diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index 25d985e7532a..31977ffd6190 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -49,7 +49,7 @@ struct extent_map { }; struct extent_map_tree { - struct rb_root map; + struct rb_root_cached map; struct list_head modified_extents; rwlock_t lock; }; @@ -78,7 +78,7 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, u64 start, u64 len); int add_extent_mapping(struct extent_map_tree *tree, struct extent_map *em, int modified); -int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em); +void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em); void replace_extent_mapping(struct extent_map_tree *tree, struct extent_map *cur, struct extent_map *new, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 2be00e873e92..15b925142793 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -531,6 +531,14 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, end_of_last_block = start_pos + num_bytes - 1; + /* + * The pages may have already been dirty, clear out old accounting so + * we can set things up properly + */ + clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, end_of_last_block, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); + if (!btrfs_is_free_space_inode(BTRFS_I(inode))) { if (start_pos >= isize && !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) { @@ -1500,18 +1508,27 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } if (ordered) btrfs_put_ordered_extent(ordered); - clear_extent_bit(&inode->io_tree, start_pos, last_pos, - EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, - 0, 0, cached_state); + *lockstart = start_pos; *lockend = last_pos; ret = 1; } + /* + * It's possible the pages are dirty right now, but we don't want + * to clean them yet because copy_from_user may catch a page fault + * and we might have to fall back to one page at a time. If that + * happens, we'll unlock these pages and we'd have a window where + * reclaim could sneak in and drop the once-dirty page on the floor + * without writing it. + * + * We have the pages locked and the extent range locked, so there's + * no way someone can start IO on any dirty pages in this range. + * + * We'll call btrfs_dirty_pages() later on, and that will flip around + * delalloc bits and dirty the pages as required. + */ for (i = 0; i < num_pages; i++) { - if (clear_page_dirty_for_io(pages[i])) - account_page_redirty(pages[i]); set_page_extent_mapped(pages[i]); WARN_ON(!PageLocked(pages[i])); } @@ -2544,7 +2561,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) } ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, - min_size, 0); + min_size, false); BUG_ON(ret); trans->block_rsv = rsv; @@ -2594,7 +2611,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) } ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, - rsv, min_size, 0); + rsv, min_size, false); BUG_ON(ret); /* shouldn't happen */ trans->block_rsv = rsv; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 0adf38b00fa0..67441219d6c9 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -10,6 +10,7 @@ #include <linux/math64.h> #include <linux/ratelimit.h> #include <linux/error-injection.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "free-space-cache.h" #include "transaction.h" @@ -47,6 +48,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, struct btrfs_free_space_header *header; struct extent_buffer *leaf; struct inode *inode = NULL; + unsigned nofs_flag; int ret; key.objectid = BTRFS_FREE_SPACE_OBJECTID; @@ -68,7 +70,13 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, btrfs_disk_key_to_cpu(&location, &disk_key); btrfs_release_path(path); + /* + * We are often under a trans handle at this point, so we need to make + * sure NOFS is set to keep us from deadlocking. + */ + nofs_flag = memalloc_nofs_save(); inode = btrfs_iget(fs_info->sb, &location, root, NULL); + memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) return inode; @@ -1679,6 +1687,8 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, bitmap_clear(info->bitmap, start, count); info->bytes -= bytes; + if (info->max_extent_size > ctl->unit) + info->max_extent_size = 0; } static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, @@ -2110,8 +2120,7 @@ new_bitmap: out: if (info) { - if (info->bitmap) - kfree(info->bitmap); + kfree(info->bitmap); kmem_cache_free(btrfs_free_space_cachep, info); } @@ -3601,8 +3610,7 @@ again: if (info) kmem_cache_free(btrfs_free_space_cachep, info); - if (map) - kfree(map); + kfree(map); return 0; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3ea5339603cf..f22f77172c5f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -64,7 +64,6 @@ static const struct inode_operations btrfs_dir_ro_inode_operations; static const struct inode_operations btrfs_special_inode_operations; static const struct inode_operations btrfs_file_inode_operations; static const struct address_space_operations btrfs_aops; -static const struct address_space_operations btrfs_symlink_aops; static const struct file_operations btrfs_dir_file_operations; static const struct extent_io_ops btrfs_extent_io_ops; @@ -2750,12 +2749,9 @@ static void relink_file_extents(struct new_sa_defrag_extent *new) struct btrfs_path *path; struct sa_defrag_extent_backref *backref; struct sa_defrag_extent_backref *prev = NULL; - struct inode *inode; struct rb_node *node; int ret; - inode = new->inode; - path = btrfs_alloc_path(); if (!path) return; @@ -3471,8 +3467,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) /* this will do delete_inode and everything for us */ iput(inode); - if (ret) - goto out; } /* release the path since we're done with it */ btrfs_release_path(path); @@ -3738,7 +3732,7 @@ cache_acl: case S_IFLNK: inode->i_op = &btrfs_symlink_inode_operations; inode_nohighmem(inode); - inode->i_mapping->a_ops = &btrfs_symlink_aops; + inode->i_mapping->a_ops = &btrfs_aops; break; default: inode->i_op = &btrfs_special_inode_operations; @@ -3910,12 +3904,8 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, path->leave_spinning = 1; di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto err; - } - if (!di) { - ret = -ENOENT; + if (IS_ERR_OR_NULL(di)) { + ret = di ? PTR_ERR(di) : -ENOENT; goto err; } leaf = path->nodes[0]; @@ -4075,10 +4065,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, name_len, -1); if (IS_ERR_OR_NULL(di)) { - if (!di) - ret = -ENOENT; - else - ret = PTR_ERR(di); + ret = di ? PTR_ERR(di) : -ENOENT; goto out; } @@ -4270,18 +4257,17 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) * again is not run concurrently. */ spin_lock(&dest->root_item_lock); - root_flags = btrfs_root_flags(&dest->root_item); - if (dest->send_in_progress == 0) { - btrfs_set_root_flags(&dest->root_item, - root_flags | BTRFS_ROOT_SUBVOL_DEAD); - spin_unlock(&dest->root_item_lock); - } else { + if (dest->send_in_progress) { spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu during send", dest->root_key.objectid); return -EPERM; } + root_flags = btrfs_root_flags(&dest->root_item); + btrfs_set_root_flags(&dest->root_item, + root_flags | BTRFS_ROOT_SUBVOL_DEAD); + spin_unlock(&dest->root_item_lock); down_write(&fs_info->subvol_sem); @@ -4727,7 +4713,7 @@ delete: btrfs_abort_transaction(trans, ret); break; } - if (btrfs_should_throttle_delayed_refs(trans, fs_info)) + if (btrfs_should_throttle_delayed_refs(trans)) btrfs_async_run_delayed_refs(fs_info, trans->delayed_ref_updates * 2, trans->transid, 0); @@ -4736,8 +4722,7 @@ delete: extent_num_bytes)) { should_end = true; } - if (btrfs_should_throttle_delayed_refs(trans, - fs_info)) + if (btrfs_should_throttle_delayed_refs(trans)) should_throttle = true; } } @@ -5235,10 +5220,10 @@ static void evict_inode_truncate_pages(struct inode *inode) truncate_inode_pages_final(&inode->i_data); write_lock(&map_tree->lock); - while (!RB_EMPTY_ROOT(&map_tree->map)) { + while (!RB_EMPTY_ROOT(&map_tree->map.rb_root)) { struct extent_map *em; - node = rb_first(&map_tree->map); + node = rb_first_cached(&map_tree->map); em = rb_entry(node, struct extent_map, rb_node); clear_bit(EXTENT_FLAG_PINNED, &em->flags); clear_bit(EXTENT_FLAG_LOGGING, &em->flags); @@ -5306,8 +5291,7 @@ static void evict_inode_truncate_pages(struct inode *inode) } static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root, - struct btrfs_block_rsv *rsv, - u64 min_size) + struct btrfs_block_rsv *rsv) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; @@ -5317,7 +5301,7 @@ static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root, struct btrfs_trans_handle *trans; int ret; - ret = btrfs_block_rsv_refill(root, rsv, min_size, + ret = btrfs_block_rsv_refill(root, rsv, rsv->size, BTRFS_RESERVE_FLUSH_LIMIT); if (ret && ++failures > 2) { @@ -5334,8 +5318,8 @@ static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root, * Try to steal from the global reserve if there is space for * it. */ - if (!btrfs_check_space_for_delayed_refs(trans, fs_info) && - !btrfs_block_rsv_migrate(global_rsv, rsv, min_size, 0)) + if (!btrfs_check_space_for_delayed_refs(trans) && + !btrfs_block_rsv_migrate(global_rsv, rsv, rsv->size, false)) return trans; /* If not, commit and try again. */ @@ -5351,7 +5335,6 @@ void btrfs_evict_inode(struct inode *inode) struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_block_rsv *rsv; - u64 min_size; int ret; trace_btrfs_inode_evict(inode); @@ -5361,8 +5344,6 @@ void btrfs_evict_inode(struct inode *inode) return; } - min_size = btrfs_calc_trunc_metadata_size(fs_info, 1); - evict_inode_truncate_pages(inode); if (inode->i_nlink && @@ -5373,9 +5354,6 @@ void btrfs_evict_inode(struct inode *inode) if (is_bad_inode(inode)) goto no_delete; - /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */ - if (!special_file(inode->i_mode)) - btrfs_wait_ordered_range(inode, 0, (u64)-1); btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1); @@ -5395,13 +5373,13 @@ void btrfs_evict_inode(struct inode *inode) rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP); if (!rsv) goto no_delete; - rsv->size = min_size; + rsv->size = btrfs_calc_trunc_metadata_size(fs_info, 1); rsv->failfast = 1; btrfs_i_size_write(BTRFS_I(inode), 0); while (1) { - trans = evict_refill_and_join(root, rsv, min_size); + trans = evict_refill_and_join(root, rsv); if (IS_ERR(trans)) goto free_rsv; @@ -5426,7 +5404,7 @@ void btrfs_evict_inode(struct inode *inode) * If it turns out that we are dropping too many of these, we might want * to add a mechanism for retrying these after a commit. */ - trans = evict_refill_and_join(root, rsv, min_size); + trans = evict_refill_and_join(root, rsv); if (!IS_ERR(trans)) { trans->block_rsv = rsv; btrfs_orphan_del(trans, BTRFS_I(inode)); @@ -5471,12 +5449,8 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)), name, namelen, 0); - if (!di) { - ret = -ENOENT; - goto out; - } - if (IS_ERR(di)) { - ret = PTR_ERR(di); + if (IS_ERR_OR_NULL(di)) { + ret = di ? PTR_ERR(di) : -ENOENT; goto out; } @@ -6390,8 +6364,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = btrfs_insert_dir_item(trans, root, name, name_len, - parent_inode, &key, + ret = btrfs_insert_dir_item(trans, name, name_len, parent_inode, &key, btrfs_inode_type(&inode->vfs_inode), index); if (ret == -EEXIST || ret == -EOVERFLOW) goto fail_dir_item; @@ -6584,7 +6557,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, int drop_inode = 0; /* do not allow sys_link's with other subvols of the same device */ - if (root->objectid != BTRFS_I(inode)->root->objectid) + if (root->root_key.objectid != BTRFS_I(inode)->root->root_key.objectid) return -EXDEV; if (inode->i_nlink >= BTRFS_LINK_MAX) @@ -6777,9 +6750,9 @@ static noinline int uncompress_inline(struct btrfs_path *path, * This also copies inline extents directly into the page. */ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, - struct page *page, - size_t pg_offset, u64 start, u64 len, - int create) + struct page *page, + size_t pg_offset, u64 start, u64 len, + int create) { struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret; @@ -6823,19 +6796,21 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, em->len = (u64)-1; em->block_len = (u64)-1; + path = btrfs_alloc_path(); if (!path) { - path = btrfs_alloc_path(); - if (!path) { - err = -ENOMEM; - goto out; - } - /* - * Chances are we'll be called again, so go ahead and do - * readahead - */ - path->reada = READA_FORWARD; + err = -ENOMEM; + goto out; } + /* Chances are we'll be called again, so go ahead and do readahead */ + path->reada = READA_FORWARD; + + /* + * Unless we're going to uncompress the inline extent, no sleep would + * happen. + */ + path->leave_spinning = 1; + ret = btrfs_lookup_file_extent(NULL, root, path, objectid, start, 0); if (ret < 0) { err = ret; @@ -6938,6 +6913,8 @@ next: em->orig_block_len = em->len; em->orig_start = em->start; ptr = btrfs_file_extent_inline_start(item) + extent_offset; + + btrfs_set_path_blocking(path); if (!PageUptodate(page)) { if (btrfs_file_extent_compression(leaf, item) != BTRFS_COMPRESS_NONE) { @@ -6985,10 +6962,10 @@ insert: err = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len); write_unlock(&em_tree->lock); out: + btrfs_free_path(path); trace_btrfs_get_extent(root, inode, em); - btrfs_free_path(path); if (err) { free_extent_map(em); return ERR_PTR(err); @@ -9021,7 +8998,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) /* Migrate the slack space for the truncate to our reserve */ ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, - min_size, 0); + min_size, false); BUG_ON(ret); /* @@ -9058,7 +9035,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) btrfs_block_rsv_release(fs_info, rsv, -1); ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, - rsv, min_size, 0); + rsv, min_size, false); BUG_ON(ret); /* shouldn't happen */ trans->block_rsv = rsv; } @@ -10191,7 +10168,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &btrfs_symlink_inode_operations; inode_nohighmem(inode); - inode->i_mapping->a_ops = &btrfs_symlink_aops; + inode->i_mapping->a_ops = &btrfs_aops; inode_set_bytes(inode, name_len); btrfs_i_size_write(BTRFS_I(inode), name_len); err = btrfs_update_inode(trans, root, inode); @@ -10567,13 +10544,6 @@ static const struct address_space_operations btrfs_aops = { .error_remove_page = generic_error_remove_page, }; -static const struct address_space_operations btrfs_symlink_aops = { - .readpage = btrfs_readpage, - .writepage = btrfs_writepage, - .invalidatepage = btrfs_invalidatepage, - .releasepage = btrfs_releasepage, -}; - static const struct inode_operations btrfs_file_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d60b6caf09e8..a990a9045139 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -491,7 +491,6 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; - u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); int ret; if (!capable(CAP_SYS_ADMIN)) @@ -515,11 +514,15 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) return -EOPNOTSUPP; if (copy_from_user(&range, arg, sizeof(range))) return -EFAULT; - if (range.start > total_bytes || - range.len < fs_info->sb->s_blocksize) + + /* + * NOTE: Don't truncate the range using super->total_bytes. Bytenr of + * block group is in the logical address space, which can be any + * sectorsize aligned bytenr in the range [0, U64_MAX]. + */ + if (range.len < fs_info->sb->s_blocksize) return -EINVAL; - range.len = min(range.len, total_bytes - range.start); range.minlen = max(range.minlen, minlen); ret = btrfs_trim_fs(fs_info, &range); if (ret < 0) @@ -686,8 +689,7 @@ static noinline int create_subvol(struct inode *dir, goto fail; } - ret = btrfs_insert_dir_item(trans, root, - name, namelen, BTRFS_I(dir), &key, + ret = btrfs_insert_dir_item(trans, name, namelen, BTRFS_I(dir), &key, BTRFS_FT_DIR, index); if (ret) { btrfs_abort_transaction(trans, ret); @@ -1324,7 +1326,7 @@ again: if (i_done != page_cnt) { spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; + btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, @@ -4393,7 +4395,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } - if (!is_fstree(new_root->objectid)) { + if (!is_fstree(new_root->root_key.objectid)) { ret = -ENOENT; goto out; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d4917c0cddf5..45868fd76209 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1416,13 +1416,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) if (!qgroup) { ret = -ENOENT; goto out; - } else { - /* check if there are no children of this qgroup */ - if (!list_empty(&qgroup->members)) { - ret = -EBUSY; - goto out; - } } + + /* Check if there are no children of this qgroup */ + if (!list_empty(&qgroup->members)) { + ret = -EBUSY; + goto out; + } + ret = del_qgroup_item(trans, qgroupid); if (ret && ret != -ENOENT) goto out; @@ -1712,6 +1713,416 @@ static int adjust_slots_upwards(struct btrfs_path *path, int root_level) return 0; } +/* + * Helper function to trace a subtree tree block swap. + * + * The swap will happen in highest tree block, but there may be a lot of + * tree blocks involved. + * + * For example: + * OO = Old tree blocks + * NN = New tree blocks allocated during balance + * + * File tree (257) Reloc tree for 257 + * L2 OO NN + * / \ / \ + * L1 OO OO (a) OO NN (a) + * / \ / \ / \ / \ + * L0 OO OO OO OO OO OO NN NN + * (b) (c) (b) (c) + * + * When calling qgroup_trace_extent_swap(), we will pass: + * @src_eb = OO(a) + * @dst_path = [ nodes[1] = NN(a), nodes[0] = NN(c) ] + * @dst_level = 0 + * @root_level = 1 + * + * In that case, qgroup_trace_extent_swap() will search from OO(a) to + * reach OO(c), then mark both OO(c) and NN(c) as qgroup dirty. + * + * The main work of qgroup_trace_extent_swap() can be split into 3 parts: + * + * 1) Tree search from @src_eb + * It should acts as a simplified btrfs_search_slot(). + * The key for search can be extracted from @dst_path->nodes[dst_level] + * (first key). + * + * 2) Mark the final tree blocks in @src_path and @dst_path qgroup dirty + * NOTE: In above case, OO(a) and NN(a) won't be marked qgroup dirty. + * They should be marked during preivous (@dst_level = 1) iteration. + * + * 3) Mark file extents in leaves dirty + * We don't have good way to pick out new file extents only. + * So we still follow the old method by scanning all file extents in + * the leave. + * + * This function can free us from keeping two pathes, thus later we only need + * to care about how to iterate all new tree blocks in reloc tree. + */ +static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, + struct extent_buffer *src_eb, + struct btrfs_path *dst_path, + int dst_level, int root_level, + bool trace_leaf) +{ + struct btrfs_key key; + struct btrfs_path *src_path; + struct btrfs_fs_info *fs_info = trans->fs_info; + u32 nodesize = fs_info->nodesize; + int cur_level = root_level; + int ret; + + BUG_ON(dst_level > root_level); + /* Level mismatch */ + if (btrfs_header_level(src_eb) != root_level) + return -EINVAL; + + src_path = btrfs_alloc_path(); + if (!src_path) { + ret = -ENOMEM; + goto out; + } + + if (dst_level) + btrfs_node_key_to_cpu(dst_path->nodes[dst_level], &key, 0); + else + btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0); + + /* For src_path */ + extent_buffer_get(src_eb); + src_path->nodes[root_level] = src_eb; + src_path->slots[root_level] = dst_path->slots[root_level]; + src_path->locks[root_level] = 0; + + /* A simplified version of btrfs_search_slot() */ + while (cur_level >= dst_level) { + struct btrfs_key src_key; + struct btrfs_key dst_key; + + if (src_path->nodes[cur_level] == NULL) { + struct btrfs_key first_key; + struct extent_buffer *eb; + int parent_slot; + u64 child_gen; + u64 child_bytenr; + + eb = src_path->nodes[cur_level + 1]; + parent_slot = src_path->slots[cur_level + 1]; + child_bytenr = btrfs_node_blockptr(eb, parent_slot); + child_gen = btrfs_node_ptr_generation(eb, parent_slot); + btrfs_node_key_to_cpu(eb, &first_key, parent_slot); + + eb = read_tree_block(fs_info, child_bytenr, child_gen, + cur_level, &first_key); + if (IS_ERR(eb)) { + ret = PTR_ERR(eb); + goto out; + } else if (!extent_buffer_uptodate(eb)) { + free_extent_buffer(eb); + ret = -EIO; + goto out; + } + + src_path->nodes[cur_level] = eb; + + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + src_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING; + } + + src_path->slots[cur_level] = dst_path->slots[cur_level]; + if (cur_level) { + btrfs_node_key_to_cpu(dst_path->nodes[cur_level], + &dst_key, dst_path->slots[cur_level]); + btrfs_node_key_to_cpu(src_path->nodes[cur_level], + &src_key, src_path->slots[cur_level]); + } else { + btrfs_item_key_to_cpu(dst_path->nodes[cur_level], + &dst_key, dst_path->slots[cur_level]); + btrfs_item_key_to_cpu(src_path->nodes[cur_level], + &src_key, src_path->slots[cur_level]); + } + /* Content mismatch, something went wrong */ + if (btrfs_comp_cpu_keys(&dst_key, &src_key)) { + ret = -ENOENT; + goto out; + } + cur_level--; + } + + /* + * Now both @dst_path and @src_path have been populated, record the tree + * blocks for qgroup accounting. + */ + ret = btrfs_qgroup_trace_extent(trans, src_path->nodes[dst_level]->start, + nodesize, GFP_NOFS); + if (ret < 0) + goto out; + ret = btrfs_qgroup_trace_extent(trans, + dst_path->nodes[dst_level]->start, + nodesize, GFP_NOFS); + if (ret < 0) + goto out; + + /* Record leaf file extents */ + if (dst_level == 0 && trace_leaf) { + ret = btrfs_qgroup_trace_leaf_items(trans, src_path->nodes[0]); + if (ret < 0) + goto out; + ret = btrfs_qgroup_trace_leaf_items(trans, dst_path->nodes[0]); + } +out: + btrfs_free_path(src_path); + return ret; +} + +/* + * Helper function to do recursive generation-aware depth-first search, to + * locate all new tree blocks in a subtree of reloc tree. + * + * E.g. (OO = Old tree blocks, NN = New tree blocks, whose gen == last_snapshot) + * reloc tree + * L2 NN (a) + * / \ + * L1 OO NN (b) + * / \ / \ + * L0 OO OO OO NN + * (c) (d) + * If we pass: + * @dst_path = [ nodes[1] = NN(b), nodes[0] = NULL ], + * @cur_level = 1 + * @root_level = 1 + * + * We will iterate through tree blocks NN(b), NN(d) and info qgroup to trace + * above tree blocks along with their counter parts in file tree. + * While during search, old tree blocsk OO(c) will be skiped as tree block swap + * won't affect OO(c). + */ +static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans, + struct extent_buffer *src_eb, + struct btrfs_path *dst_path, + int cur_level, int root_level, + u64 last_snapshot, bool trace_leaf) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct extent_buffer *eb; + bool need_cleanup = false; + int ret = 0; + int i; + + /* Level sanity check */ + if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL || + root_level < 0 || root_level >= BTRFS_MAX_LEVEL || + root_level < cur_level) { + btrfs_err_rl(fs_info, + "%s: bad levels, cur_level=%d root_level=%d", + __func__, cur_level, root_level); + return -EUCLEAN; + } + + /* Read the tree block if needed */ + if (dst_path->nodes[cur_level] == NULL) { + struct btrfs_key first_key; + int parent_slot; + u64 child_gen; + u64 child_bytenr; + + /* + * dst_path->nodes[root_level] must be initialized before + * calling this function. + */ + if (cur_level == root_level) { + btrfs_err_rl(fs_info, + "%s: dst_path->nodes[%d] not initialized, root_level=%d cur_level=%d", + __func__, root_level, root_level, cur_level); + return -EUCLEAN; + } + + /* + * We need to get child blockptr/gen from parent before we can + * read it. + */ + eb = dst_path->nodes[cur_level + 1]; + parent_slot = dst_path->slots[cur_level + 1]; + child_bytenr = btrfs_node_blockptr(eb, parent_slot); + child_gen = btrfs_node_ptr_generation(eb, parent_slot); + btrfs_node_key_to_cpu(eb, &first_key, parent_slot); + + /* This node is old, no need to trace */ + if (child_gen < last_snapshot) + goto out; + + eb = read_tree_block(fs_info, child_bytenr, child_gen, + cur_level, &first_key); + if (IS_ERR(eb)) { + ret = PTR_ERR(eb); + goto out; + } else if (!extent_buffer_uptodate(eb)) { + free_extent_buffer(eb); + ret = -EIO; + goto out; + } + + dst_path->nodes[cur_level] = eb; + dst_path->slots[cur_level] = 0; + + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + dst_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING; + need_cleanup = true; + } + + /* Now record this tree block and its counter part for qgroups */ + ret = qgroup_trace_extent_swap(trans, src_eb, dst_path, cur_level, + root_level, trace_leaf); + if (ret < 0) + goto cleanup; + + eb = dst_path->nodes[cur_level]; + + if (cur_level > 0) { + /* Iterate all child tree blocks */ + for (i = 0; i < btrfs_header_nritems(eb); i++) { + /* Skip old tree blocks as they won't be swapped */ + if (btrfs_node_ptr_generation(eb, i) < last_snapshot) + continue; + dst_path->slots[cur_level] = i; + + /* Recursive call (at most 7 times) */ + ret = qgroup_trace_new_subtree_blocks(trans, src_eb, + dst_path, cur_level - 1, root_level, + last_snapshot, trace_leaf); + if (ret < 0) + goto cleanup; + } + } + +cleanup: + if (need_cleanup) { + /* Clean up */ + btrfs_tree_unlock_rw(dst_path->nodes[cur_level], + dst_path->locks[cur_level]); + free_extent_buffer(dst_path->nodes[cur_level]); + dst_path->nodes[cur_level] = NULL; + dst_path->slots[cur_level] = 0; + dst_path->locks[cur_level] = 0; + } +out: + return ret; +} + +/* + * Inform qgroup to trace subtree swap used in balance. + * + * Unlike btrfs_qgroup_trace_subtree(), this function will only trace + * new tree blocks whose generation is equal to (or larger than) @last_snapshot. + * + * Will go down the tree block pointed by @dst_eb (pointed by @dst_parent and + * @dst_slot), and find any tree blocks whose generation is at @last_snapshot, + * and then go down @src_eb (pointed by @src_parent and @src_slot) to find + * the conterpart of the tree block, then mark both tree blocks as qgroup dirty, + * and skip all tree blocks whose generation is smaller than last_snapshot. + * + * This would skip tons of tree blocks of original btrfs_qgroup_trace_subtree(), + * which could be the cause of very slow balance if the file tree is large. + * + * @src_parent, @src_slot: pointer to src (file tree) eb. + * @dst_parent, @dst_slot: pointer to dst (reloc tree) eb. + */ +int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *bg_cache, + struct extent_buffer *src_parent, int src_slot, + struct extent_buffer *dst_parent, int dst_slot, + u64 last_snapshot) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_path *dst_path = NULL; + struct btrfs_key first_key; + struct extent_buffer *src_eb = NULL; + struct extent_buffer *dst_eb = NULL; + bool trace_leaf = false; + u64 child_gen; + u64 child_bytenr; + int level; + int ret; + + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + return 0; + + /* Check parameter order */ + if (btrfs_node_ptr_generation(src_parent, src_slot) > + btrfs_node_ptr_generation(dst_parent, dst_slot)) { + btrfs_err_rl(fs_info, + "%s: bad parameter order, src_gen=%llu dst_gen=%llu", __func__, + btrfs_node_ptr_generation(src_parent, src_slot), + btrfs_node_ptr_generation(dst_parent, dst_slot)); + return -EUCLEAN; + } + + /* + * Only trace leaf if we're relocating data block groups, this could + * reduce tons of data extents tracing for meta/sys bg relocation. + */ + if (bg_cache->flags & BTRFS_BLOCK_GROUP_DATA) + trace_leaf = true; + /* Read out real @src_eb, pointed by @src_parent and @src_slot */ + child_bytenr = btrfs_node_blockptr(src_parent, src_slot); + child_gen = btrfs_node_ptr_generation(src_parent, src_slot); + btrfs_node_key_to_cpu(src_parent, &first_key, src_slot); + + src_eb = read_tree_block(fs_info, child_bytenr, child_gen, + btrfs_header_level(src_parent) - 1, &first_key); + if (IS_ERR(src_eb)) { + ret = PTR_ERR(src_eb); + goto out; + } + + /* Read out real @dst_eb, pointed by @src_parent and @src_slot */ + child_bytenr = btrfs_node_blockptr(dst_parent, dst_slot); + child_gen = btrfs_node_ptr_generation(dst_parent, dst_slot); + btrfs_node_key_to_cpu(dst_parent, &first_key, dst_slot); + + dst_eb = read_tree_block(fs_info, child_bytenr, child_gen, + btrfs_header_level(dst_parent) - 1, &first_key); + if (IS_ERR(dst_eb)) { + ret = PTR_ERR(dst_eb); + goto out; + } + + if (!extent_buffer_uptodate(src_eb) || !extent_buffer_uptodate(dst_eb)) { + ret = -EINVAL; + goto out; + } + + level = btrfs_header_level(dst_eb); + dst_path = btrfs_alloc_path(); + if (!dst_path) { + ret = -ENOMEM; + goto out; + } + + /* For dst_path */ + extent_buffer_get(dst_eb); + dst_path->nodes[level] = dst_eb; + dst_path->slots[level] = 0; + dst_path->locks[level] = 0; + + /* Do the generation-aware breadth-first search */ + ret = qgroup_trace_new_subtree_blocks(trans, src_eb, dst_path, level, + level, last_snapshot, trace_leaf); + if (ret < 0) + goto out; + ret = 0; + +out: + free_extent_buffer(src_eb); + free_extent_buffer(dst_eb); + btrfs_free_path(dst_path); + if (ret < 0) + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + return ret; +} + int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, struct extent_buffer *root_eb, u64 root_gen, int root_level) @@ -2132,6 +2543,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) struct btrfs_delayed_ref_root *delayed_refs; struct ulist *new_roots = NULL; struct rb_node *node; + u64 num_dirty_extents = 0; u64 qgroup_to_skip; int ret = 0; @@ -2141,6 +2553,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) record = rb_entry(node, struct btrfs_qgroup_extent_record, node); + num_dirty_extents++; trace_btrfs_qgroup_account_extents(fs_info, record); if (!ret) { @@ -2186,6 +2599,8 @@ cleanup: kfree(record); } + trace_qgroup_num_dirty_extents(fs_info, trans->transid, + num_dirty_extents); return ret; } @@ -2897,6 +3312,7 @@ qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info) qgroup->rfer_cmpr = 0; qgroup->excl = 0; qgroup->excl_cmpr = 0; + qgroup_dirty(fs_info, qgroup); } spin_unlock(&fs_info->qgroup_lock); } @@ -3004,7 +3420,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode, int ret; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) || - !is_fstree(root->objectid) || len == 0) + !is_fstree(root->root_key.objectid) || len == 0) return 0; /* @reserved parameter is mandatory for qgroup */ @@ -3090,7 +3506,7 @@ static int qgroup_free_reserved_data(struct inode *inode, goto out; freed += changeset.bytes_changed; } - btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed, + btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed, BTRFS_QGROUP_RSV_DATA); ret = freed; out: @@ -3106,6 +3522,10 @@ static int __btrfs_qgroup_release_data(struct inode *inode, int trace_op = QGROUP_RELEASE; int ret; + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, + &BTRFS_I(inode)->root->fs_info->flags)) + return 0; + /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) @@ -3122,7 +3542,7 @@ static int __btrfs_qgroup_release_data(struct inode *inode, changeset.bytes_changed, trace_op); if (free) btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, - BTRFS_I(inode)->root->objectid, + BTRFS_I(inode)->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); ret = changeset.bytes_changed; out: @@ -3215,7 +3635,7 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, int ret; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || - !is_fstree(root->objectid) || num_bytes == 0) + !is_fstree(root->root_key.objectid) || num_bytes == 0) return 0; BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); @@ -3240,13 +3660,13 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root) struct btrfs_fs_info *fs_info = root->fs_info; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || - !is_fstree(root->objectid)) + !is_fstree(root->root_key.objectid)) return; /* TODO: Update trace point to handle such free */ trace_qgroup_meta_free_all_pertrans(root); /* Special value -1 means to free all reserved space */ - btrfs_qgroup_free_refroot(fs_info, root->objectid, (u64)-1, + btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid, (u64)-1, BTRFS_QGROUP_RSV_META_PERTRANS); } @@ -3256,7 +3676,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, struct btrfs_fs_info *fs_info = root->fs_info; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || - !is_fstree(root->objectid)) + !is_fstree(root->root_key.objectid)) return; /* @@ -3267,7 +3687,8 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, num_bytes = sub_root_meta_rsv(root, num_bytes, type); BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); trace_qgroup_meta_reserve(root, type, -(s64)num_bytes); - btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes, type); + btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid, + num_bytes, type); } static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root, @@ -3321,13 +3742,13 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) struct btrfs_fs_info *fs_info = root->fs_info; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || - !is_fstree(root->objectid)) + !is_fstree(root->root_key.objectid)) return; /* Same as btrfs_qgroup_free_meta_prealloc() */ num_bytes = sub_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PREALLOC); trace_qgroup_meta_convert(root, num_bytes); - qgroup_convert_meta(fs_info, root->objectid, num_bytes); + qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes); } /* @@ -3354,7 +3775,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) inode->i_ino, unode->val, unode->aux); } btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, - BTRFS_I(inode)->root->objectid, + BTRFS_I(inode)->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 54b8bb282c0e..d8f78f5ab854 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -236,6 +236,12 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, struct extent_buffer *root_eb, u64 root_gen, int root_level); + +int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *bg_cache, + struct extent_buffer *src_parent, int src_slot, + struct extent_buffer *dst_parent, int dst_slot, + u64 last_snapshot); int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct ulist *old_roots, struct ulist *new_roots); @@ -249,6 +255,8 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info, u64 ref_root, u64 num_bytes) { + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + return; trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes); btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes, BTRFS_QGROUP_RSV_DATA); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index e5b9e596bb92..d69fbfb30aa9 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -732,7 +732,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, INIT_LIST_HEAD(&ra->list); ra->action = action; - ra->root = root->objectid; + ra->root = root->root_key.objectid; /* * This is an allocation, preallocate the block_entry in case we haven't @@ -787,8 +787,8 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, * one we want to lookup below when we modify the * re->num_refs. */ - ref_root = root->objectid; - re->root_objectid = root->objectid; + ref_root = root->root_key.objectid; + re->root_objectid = root->root_key.objectid; re->num_refs = 0; } @@ -862,7 +862,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, * didn't thik of some other corner case. */ btrfs_err(fs_info, "failed to find root %llu for %llu", - root->objectid, be->bytenr); + root->root_key.objectid, be->bytenr); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); kfree(ra); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 8783a1776540..924116f654a1 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -648,8 +648,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc, int level, u64 bytenr) { struct backref_cache *cache = &rc->backref_cache; - struct btrfs_path *path1; - struct btrfs_path *path2; + struct btrfs_path *path1; /* For searching extent root */ + struct btrfs_path *path2; /* For searching parent of TREE_BLOCK_REF */ struct extent_buffer *eb; struct btrfs_root *root; struct backref_node *cur; @@ -662,7 +662,7 @@ struct backref_node *build_backref_tree(struct reloc_control *rc, struct btrfs_key key; unsigned long end; unsigned long ptr; - LIST_HEAD(list); + LIST_HEAD(list); /* Pending edge list, upper node needs to be checked */ LIST_HEAD(useless); int cowonly; int ret; @@ -778,6 +778,10 @@ again: key.type != BTRFS_SHARED_BLOCK_REF_KEY); } + /* + * Parent node found and matches current inline ref, no need to + * rebuild this node for this inline ref. + */ if (exist && ((key.type == BTRFS_TREE_BLOCK_REF_KEY && exist->owner == key.offset) || @@ -787,11 +791,12 @@ again: goto next; } + /* SHARED_BLOCK_REF means key.offset is the parent bytenr */ if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) { if (key.objectid == key.offset) { /* - * only root blocks of reloc trees use - * backref of this type. + * Only root blocks of reloc trees use backref + * pointing to itself. */ root = find_reloc_root(rc, cur->bytenr); ASSERT(root); @@ -840,7 +845,11 @@ again: goto next; } - /* key.type == BTRFS_TREE_BLOCK_REF_KEY */ + /* + * key.type == BTRFS_TREE_BLOCK_REF_KEY, inline ref offset + * means the root objectid. We need to search the tree to get + * its parent bytenr. + */ root = read_fs_root(rc->extent_root->fs_info, key.offset); if (IS_ERR(root)) { err = PTR_ERR(root); @@ -863,10 +872,7 @@ again: level = cur->level + 1; - /* - * searching the tree to find upper level blocks - * reference the block. - */ + /* Search the tree to find parent blocks referring the block. */ path2->search_commit_root = 1; path2->skip_locking = 1; path2->lowest_level = level; @@ -884,7 +890,8 @@ again: cur->bytenr) { btrfs_err(root->fs_info, "couldn't find block (%llu) (level %d) in tree (%llu) with key (%llu %u %llu)", - cur->bytenr, level - 1, root->objectid, + cur->bytenr, level - 1, + root->root_key.objectid, node_key->objectid, node_key->type, node_key->offset); err = -ENOENT; @@ -892,6 +899,8 @@ again: } lower = cur; need_check = true; + + /* Add all nodes and edges in the path */ for (; level < BTRFS_MAX_LEVEL; level++) { if (!path2->nodes[level]) { ASSERT(btrfs_root_bytenr(&root->root_item) == @@ -1281,7 +1290,7 @@ static void __del_reloc_root(struct btrfs_root *root) struct mapping_node *node = NULL; struct reloc_control *rc = fs_info->reloc_ctl; - if (rc) { + if (rc && root->node) { spin_lock(&rc->reloc_root_tree.lock); rb_node = tree_search(&rc->reloc_root_tree.rb_root, root->node->start); @@ -1735,7 +1744,7 @@ int memcmp_node_keys(struct extent_buffer *eb, int slot, * errors, a negative error number is returned. */ static noinline_for_stack -int replace_path(struct btrfs_trans_handle *trans, +int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc, struct btrfs_root *dest, struct btrfs_root *src, struct btrfs_path *path, struct btrfs_key *next_key, int lowest_level, int max_level) @@ -1879,14 +1888,9 @@ again: * and tree block numbers, if current trans doesn't free * data reloc tree inode. */ - ret = btrfs_qgroup_trace_subtree(trans, parent, - btrfs_header_generation(parent), - btrfs_header_level(parent)); - if (ret < 0) - break; - ret = btrfs_qgroup_trace_subtree(trans, path->nodes[level], - btrfs_header_generation(path->nodes[level]), - btrfs_header_level(path->nodes[level])); + ret = btrfs_qgroup_trace_subtree_swap(trans, rc->block_group, + parent, slot, path->nodes[level], + path->slots[level], last_snapshot); if (ret < 0) break; @@ -2205,7 +2209,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, btrfs_comp_cpu_keys(&next_key, &key) >= 0) { ret = 0; } else { - ret = replace_path(trans, root, reloc_root, path, + ret = replace_path(trans, rc, root, reloc_root, path, &next_key, level, max_level); } if (ret < 0) { @@ -2911,7 +2915,6 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info, free_extent_buffer(eb); return -EIO; } - WARN_ON(btrfs_header_level(eb) != block->level); if (block->level == 0) btrfs_item_key_to_cpu(eb, &block->key, 0); else @@ -2987,7 +2990,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, struct backref_node *node; struct btrfs_path *path; struct tree_block *block; - struct rb_node *rb_node; + struct tree_block *next; int ret; int err = 0; @@ -2997,29 +3000,23 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, goto out_free_blocks; } - rb_node = rb_first(blocks); - while (rb_node) { - block = rb_entry(rb_node, struct tree_block, rb_node); + /* Kick in readahead for tree blocks with missing keys */ + rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { if (!block->key_ready) readahead_tree_block(fs_info, block->bytenr); - rb_node = rb_next(rb_node); } - rb_node = rb_first(blocks); - while (rb_node) { - block = rb_entry(rb_node, struct tree_block, rb_node); + /* Get first keys */ + rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { if (!block->key_ready) { err = get_tree_block_key(fs_info, block); if (err) goto out_free_path; } - rb_node = rb_next(rb_node); } - rb_node = rb_first(blocks); - while (rb_node) { - block = rb_entry(rb_node, struct tree_block, rb_node); - + /* Do tree relocation */ + rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { node = build_backref_tree(rc, &block->key, block->level, block->bytenr); if (IS_ERR(node)) { @@ -3030,11 +3027,10 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, ret = relocate_tree_block(trans, rc, node, &block->key, path); if (ret < 0) { - if (ret != -EAGAIN || rb_node == rb_first(blocks)) + if (ret != -EAGAIN || &block->rb_node == rb_first(blocks)) err = ret; goto out; } - rb_node = rb_next(rb_node); } out: err = finish_pending_nodes(trans, rc, path, err); @@ -4669,7 +4665,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans, if (rc->merge_reloc_tree) { ret = btrfs_block_rsv_migrate(&pending->block_rsv, rc->block_rsv, - rc->nodes_relocated, 1); + rc->nodes_relocated, true); if (ret) return ret; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 3be1456b5116..902819d3cf41 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1124,7 +1124,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) if (scrub_write_page_to_dev_replace(sblock_other, page_num) != 0) { - btrfs_dev_replace_stats_inc( + atomic64_inc( &fs_info->dev_replace.num_write_errors); success = 0; } @@ -1564,8 +1564,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, if (btrfsic_submit_bio_wait(bio)) { btrfs_dev_stat_inc_and_print(page_bad->dev, BTRFS_DEV_STAT_WRITE_ERRS); - btrfs_dev_replace_stats_inc( - &fs_info->dev_replace.num_write_errors); + atomic64_inc(&fs_info->dev_replace.num_write_errors); bio_put(bio); return -EIO; } @@ -1592,8 +1591,7 @@ static void scrub_write_block_to_dev_replace(struct scrub_block *sblock) ret = scrub_write_page_to_dev_replace(sblock, page_num); if (ret) - btrfs_dev_replace_stats_inc( - &fs_info->dev_replace.num_write_errors); + atomic64_inc(&fs_info->dev_replace.num_write_errors); } } @@ -1726,8 +1724,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work) struct scrub_page *spage = sbio->pagev[i]; spage->io_error = 1; - btrfs_dev_replace_stats_inc(&dev_replace-> - num_write_errors); + atomic64_inc(&dev_replace->num_write_errors); } } @@ -3022,8 +3019,7 @@ out: static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *scrub_dev, - int num, u64 base, u64 length, - int is_dev_replace) + int num, u64 base, u64 length) { struct btrfs_path *path, *ppath; struct btrfs_fs_info *fs_info = sctx->fs_info; @@ -3299,7 +3295,7 @@ again: extent_physical = extent_logical - logical + physical; extent_dev = scrub_dev; extent_mirror_num = mirror_num; - if (is_dev_replace) + if (sctx->is_dev_replace) scrub_remap_extent(fs_info, extent_logical, extent_len, &extent_physical, &extent_dev, @@ -3397,8 +3393,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 chunk_offset, u64 length, u64 dev_offset, - struct btrfs_block_group_cache *cache, - int is_dev_replace) + struct btrfs_block_group_cache *cache) { struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree; @@ -3435,8 +3430,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, if (map->stripes[i].dev->bdev == scrub_dev->bdev && map->stripes[i].physical == dev_offset) { ret = scrub_stripe(sctx, map, scrub_dev, i, - chunk_offset, length, - is_dev_replace); + chunk_offset, length); if (ret) goto out; } @@ -3449,8 +3443,7 @@ out: static noinline_for_stack int scrub_enumerate_chunks(struct scrub_ctx *sctx, - struct btrfs_device *scrub_dev, u64 start, u64 end, - int is_dev_replace) + struct btrfs_device *scrub_dev, u64 start, u64 end) { struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_path *path; @@ -3544,7 +3537,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, */ scrub_pause_on(fs_info); ret = btrfs_inc_block_group_ro(cache); - if (!ret && is_dev_replace) { + if (!ret && sctx->is_dev_replace) { /* * If we are doing a device replace wait for any tasks * that started dellaloc right before we set the block @@ -3609,7 +3602,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->item_needs_writeback = 1; btrfs_dev_replace_write_unlock(&fs_info->dev_replace); ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length, - found_key.offset, cache, is_dev_replace); + found_key.offset, cache); /* * flush, submit all pending read and write bios, afterwards @@ -3670,7 +3663,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, btrfs_put_block_group(cache); if (ret) break; - if (is_dev_replace && + if (sctx->is_dev_replace && atomic64_read(&dev_replace->num_write_errors) > 0) { ret = -EIO; break; @@ -3893,8 +3886,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, } if (!ret) - ret = scrub_enumerate_chunks(sctx, dev, start, end, - is_dev_replace); + ret = scrub_enumerate_chunks(sctx, dev, start, end); wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); atomic_dec(&fs_info->scrubs_running); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index ba8950bfd9c7..094cc1444a90 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1186,9 +1186,9 @@ static int __clone_root_cmp_bsearch(const void *key, const void *elt) u64 root = (u64)(uintptr_t)key; struct clone_root *cr = (struct clone_root *)elt; - if (root < cr->root->objectid) + if (root < cr->root->root_key.objectid) return -1; - if (root > cr->root->objectid) + if (root > cr->root->root_key.objectid) return 1; return 0; } @@ -1198,9 +1198,9 @@ static int __clone_root_cmp_sort(const void *e1, const void *e2) struct clone_root *cr1 = (struct clone_root *)e1; struct clone_root *cr2 = (struct clone_root *)e2; - if (cr1->root->objectid < cr2->root->objectid) + if (cr1->root->root_key.objectid < cr2->root->root_key.objectid) return -1; - if (cr1->root->objectid > cr2->root->objectid) + if (cr1->root->root_key.objectid > cr2->root->root_key.objectid) return 1; return 0; } @@ -1693,12 +1693,8 @@ static int lookup_dir_item_inode(struct btrfs_root *root, di = btrfs_lookup_dir_item(NULL, root, path, dir, name, name_len, 0); - if (!di) { - ret = -ENOENT; - goto out; - } - if (IS_ERR(di)) { - ret = PTR_ERR(di); + if (IS_ERR_OR_NULL(di)) { + ret = di ? PTR_ERR(di) : -ENOENT; goto out; } btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); @@ -2346,7 +2342,7 @@ static int send_subvol_begin(struct send_ctx *sctx) return -ENOMEM; } - key.objectid = send_root->objectid; + key.objectid = send_root->root_key.objectid; key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = 0; @@ -2362,7 +2358,7 @@ static int send_subvol_begin(struct send_ctx *sctx) leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.type != BTRFS_ROOT_BACKREF_KEY || - key.objectid != send_root->objectid) { + key.objectid != send_root->root_key.objectid) { ret = -ENOENT; goto out; } @@ -4907,8 +4903,8 @@ static int send_clone(struct send_ctx *sctx, btrfs_debug(sctx->send_root->fs_info, "send_clone offset=%llu, len=%d, clone_root=%llu, clone_inode=%llu, clone_offset=%llu", - offset, len, clone_root->root->objectid, clone_root->ino, - clone_root->offset); + offset, len, clone_root->root->root_key.objectid, + clone_root->ino, clone_root->offset); p = fs_path_alloc(); if (!p) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6601c9aa5e35..b362b45dd757 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2177,8 +2177,10 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]); buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]); /* Mask in the root object ID too, to disambiguate subvols */ - buf->f_fsid.val[0] ^= BTRFS_I(d_inode(dentry))->root->objectid >> 32; - buf->f_fsid.val[1] ^= BTRFS_I(d_inode(dentry))->root->objectid; + buf->f_fsid.val[0] ^= + BTRFS_I(d_inode(dentry))->root->root_key.objectid >> 32; + buf->f_fsid.val[1] ^= + BTRFS_I(d_inode(dentry))->root->root_key.objectid; return 0; } diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index d9269a531a4d..9e0f4a01be14 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -106,7 +106,7 @@ static int test_find_delalloc(u32 sectorsize) set_extent_delalloc(&tmp, 0, sectorsize - 1, 0, NULL); start = 0; end = 0; - found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, + found = btrfs_find_lock_delalloc_range(inode, &tmp, locked_page, &start, &end, max_bytes); if (!found) { test_err("should have found at least one delalloc"); @@ -137,7 +137,7 @@ static int test_find_delalloc(u32 sectorsize) set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, 0, NULL); start = test_start; end = 0; - found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, + found = btrfs_find_lock_delalloc_range(inode, &tmp, locked_page, &start, &end, max_bytes); if (!found) { test_err("couldn't find delalloc in our range"); @@ -171,7 +171,7 @@ static int test_find_delalloc(u32 sectorsize) } start = test_start; end = 0; - found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, + found = btrfs_find_lock_delalloc_range(inode, &tmp, locked_page, &start, &end, max_bytes); if (found) { test_err("found range when we shouldn't have"); @@ -192,7 +192,7 @@ static int test_find_delalloc(u32 sectorsize) set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, 0, NULL); start = test_start; end = 0; - found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, + found = btrfs_find_lock_delalloc_range(inode, &tmp, locked_page, &start, &end, max_bytes); if (!found) { test_err("didn't find our range"); @@ -233,7 +233,7 @@ static int test_find_delalloc(u32 sectorsize) * this changes at any point in the future we will need to fix this * tests expected behavior. */ - found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, + found = btrfs_find_lock_delalloc_range(inode, &tmp, locked_page, &start, &end, max_bytes); if (!found) { test_err("didn't find our range"); diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 385a5316e4bf..bf15d3a7f20e 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -12,8 +12,8 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree) struct extent_map *em; struct rb_node *node; - while (!RB_EMPTY_ROOT(&em_tree->map)) { - node = rb_first(&em_tree->map); + while (!RB_EMPTY_ROOT(&em_tree->map.rb_root)) { + node = rb_first_cached(&em_tree->map); em = rb_entry(node, struct extent_map, rb_node); remove_extent_mapping(em_tree, em); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3b84f5015029..5686290a50e1 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -44,7 +44,8 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) WARN_ON(refcount_read(&transaction->use_count) == 0); if (refcount_dec_and_test(&transaction->use_count)) { BUG_ON(!list_empty(&transaction->list)); - WARN_ON(!RB_EMPTY_ROOT(&transaction->delayed_refs.href_root)); + WARN_ON(!RB_EMPTY_ROOT( + &transaction->delayed_refs.href_root.rb_root)); if (transaction->delayed_refs.pending_csums) btrfs_err(transaction->fs_info, "pending csums is %llu", @@ -118,7 +119,7 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans) list_del_init(&root->dirty_list); free_extent_buffer(root->commit_root); root->commit_root = btrfs_root_node(root); - if (is_fstree(root->objectid)) + if (is_fstree(root->root_key.objectid)) btrfs_unpin_free_ino(root); clear_btree_io_tree(&root->dirty_log_pages); } @@ -245,7 +246,7 @@ loop: memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs)); - cur_trans->delayed_refs.href_root = RB_ROOT; + cur_trans->delayed_refs.href_root = RB_ROOT_CACHED; cur_trans->delayed_refs.dirty_extent_root = RB_ROOT; atomic_set(&cur_trans->delayed_refs.num_entries, 0); @@ -759,7 +760,7 @@ static int should_end_transaction(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - if (btrfs_check_space_for_delayed_refs(trans, fs_info)) + if (btrfs_check_space_for_delayed_refs(trans)) return 1; return !!btrfs_block_rsv_check(&fs_info->global_block_rsv, 5); @@ -834,7 +835,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, trans->delayed_ref_updates = 0; if (!trans->sync) { must_run_delayed_refs = - btrfs_should_throttle_delayed_refs(trans, info); + btrfs_should_throttle_delayed_refs(trans); cur = max_t(unsigned long, cur, 32); /* @@ -1197,7 +1198,10 @@ again: list_add_tail(&fs_info->extent_root->dirty_list, &trans->transaction->switch_commits); - btrfs_after_dev_replace_commit(fs_info); + + /* Update dev-replace pointer once everything is committed */ + fs_info->dev_replace.committed_cursor_left = + fs_info->dev_replace.cursor_left_last_write_of_item; return 0; } @@ -1613,10 +1617,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, if (ret < 0) goto fail; - ret = btrfs_insert_dir_item(trans, parent_root, - dentry->d_name.name, dentry->d_name.len, - BTRFS_I(parent_inode), &key, - BTRFS_FT_DIR, index); + ret = btrfs_insert_dir_item(trans, dentry->d_name.name, + dentry->d_name.len, BTRFS_I(parent_inode), + &key, BTRFS_FT_DIR, index); /* We have check then name at the beginning, so it is impossible. */ BUG_ON(ret == -EEXIST || ret == -EOVERFLOW); if (ret) { @@ -1929,6 +1932,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) return ret; } + btrfs_trans_release_metadata(trans); + trans->block_rsv = NULL; + /* make a pass through all the delayed refs we have so far * any runnings procs may add more while we are here */ @@ -1938,9 +1944,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) return ret; } - btrfs_trans_release_metadata(trans); - trans->block_rsv = NULL; - cur_trans = trans->transaction; /* @@ -2330,7 +2333,7 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root) list_del_init(&root->root_list); spin_unlock(&fs_info->trans_lock); - btrfs_debug(fs_info, "cleaner removing %llu", root->objectid); + btrfs_debug(fs_info, "cleaner removing %llu", root->root_key.objectid); btrfs_kill_all_delayed_nodes(root); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index db835635372f..cab0b1f1f741 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -487,6 +487,13 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, u32 nritems = btrfs_header_nritems(leaf); int slot; + if (btrfs_header_level(leaf) != 0) { + generic_err(fs_info, leaf, 0, + "invalid level for leaf, have %d expect 0", + btrfs_header_level(leaf)); + return -EUCLEAN; + } + /* * Extent buffers from a relocation tree have a owner field that * corresponds to the subvolume tree they are based on. So just from an @@ -645,9 +652,16 @@ int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node) unsigned long nr = btrfs_header_nritems(node); struct btrfs_key key, next_key; int slot; + int level = btrfs_header_level(node); u64 bytenr; int ret = 0; + if (level <= 0 || level >= BTRFS_MAX_LEVEL) { + generic_err(fs_info, node, 0, + "invalid level for node, have %d expect [1, %d]", + level, BTRFS_MAX_LEVEL - 1); + return -EUCLEAN; + } if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(fs_info)) { btrfs_crit(fs_info, "corrupt node: root=%llu block=%llu, nritems too %s, have %lu expect range [1,%u]", diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3c2ae0e4f25a..0dba09334a16 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -205,14 +205,11 @@ static int join_running_log_trans(struct btrfs_root *root) * until you call btrfs_end_log_trans() or it makes any future * log transactions wait until you call btrfs_end_log_trans() */ -int btrfs_pin_log_trans(struct btrfs_root *root) +void btrfs_pin_log_trans(struct btrfs_root *root) { - int ret = -ENOENT; - mutex_lock(&root->log_mutex); atomic_inc(&root->log_writers); mutex_unlock(&root->log_mutex); - return ret; } /* @@ -258,6 +255,13 @@ struct walk_control { /* what stage of the replay code we're currently in */ int stage; + /* + * Ignore any items from the inode currently being processed. Needs + * to be set every time we find a BTRFS_INODE_ITEM_KEY and we are in + * the LOG_WALK_REPLAY_INODES stage. + */ + bool ignore_cur_inode; + /* the root we are currently replaying */ struct btrfs_root *replay_dest; @@ -2487,6 +2491,20 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, inode_item = btrfs_item_ptr(eb, i, struct btrfs_inode_item); + /* + * If we have a tmpfile (O_TMPFILE) that got fsync'ed + * and never got linked before the fsync, skip it, as + * replaying it is pointless since it would be deleted + * later. We skip logging tmpfiles, but it's always + * possible we are replaying a log created with a kernel + * that used to log tmpfiles. + */ + if (btrfs_inode_nlink(eb, inode_item) == 0) { + wc->ignore_cur_inode = true; + continue; + } else { + wc->ignore_cur_inode = false; + } ret = replay_xattr_deletes(wc->trans, root, log, path, key.objectid); if (ret) @@ -2524,16 +2542,8 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, root->fs_info->sectorsize); ret = btrfs_drop_extents(wc->trans, root, inode, from, (u64)-1, 1); - /* - * If the nlink count is zero here, the iput - * will free the inode. We bump it to make - * sure it doesn't get freed until the link - * count fixup is done. - */ if (!ret) { - if (inode->i_nlink == 0) - inc_nlink(inode); - /* Update link count and nbytes. */ + /* Update the inode's nbytes. */ ret = btrfs_update_inode(wc->trans, root, inode); } @@ -2548,6 +2558,9 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, break; } + if (wc->ignore_cur_inode) + continue; + if (key.type == BTRFS_DIR_INDEX_KEY && wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { ret = replay_one_dir_item(wc->trans, root, path, @@ -3196,9 +3209,12 @@ static void free_log_tree(struct btrfs_trans_handle *trans, }; ret = walk_log_tree(trans, log, &wc); - /* I don't think this can happen but just in case */ - if (ret) - btrfs_abort_transaction(trans, ret); + if (ret) { + if (trans) + btrfs_abort_transaction(trans, ret); + else + btrfs_handle_fs_error(log->fs_info, ret, NULL); + } while (1) { ret = find_first_extent_bit(&log->dirty_log_pages, @@ -5564,9 +5580,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, dir_inode = btrfs_iget(fs_info->sb, &inode_key, root, NULL); - /* If parent inode was deleted, skip it. */ - if (IS_ERR(dir_inode)) - continue; + /* + * If the parent inode was deleted, return an error to + * fallback to a transaction commit. This is to prevent + * getting an inode that was moved from one parent A to + * a parent B, got its former parent A deleted and then + * it got fsync'ed, from existing at both parents after + * a log replay (and the old parent still existing). + * Example: + * + * mkdir /mnt/A + * mkdir /mnt/B + * touch /mnt/B/bar + * sync + * mv /mnt/B/bar /mnt/A/bar + * mv -T /mnt/A /mnt/B + * fsync /mnt/B/bar + * <power fail> + * + * If we ignore the old parent B which got deleted, + * after a log replay we would have file bar linked + * at both parents and the old parent B would still + * exist. + */ + if (IS_ERR(dir_inode)) { + ret = PTR_ERR(dir_inode); + goto out; + } if (ctx) ctx->log_new_dentries = false; @@ -5640,7 +5680,13 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (ret) goto end_no_trans; - if (btrfs_inode_in_log(inode, trans->transid)) { + /* + * Skip already logged inodes or inodes corresponding to tmpfiles + * (since logging them is pointless, a link count of 0 means they + * will never be accessible). + */ + if (btrfs_inode_in_log(inode, trans->transid) || + inode->vfs_inode.i_nlink == 0) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; } diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 7ab9bb88a639..767765031e59 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -65,7 +65,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, const char *name, int name_len, struct btrfs_inode *inode, u64 dirid); void btrfs_end_log_trans(struct btrfs_root *root); -int btrfs_pin_log_trans(struct btrfs_root *root); +void btrfs_pin_log_trans(struct btrfs_root *root); void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, int for_rename); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f4405e430da6..f435d397019e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1613,7 +1613,7 @@ static u64 find_next_chunk(struct btrfs_fs_info *fs_info) em_tree = &fs_info->mapping_tree.map_tree; read_lock(&em_tree->lock); - n = rb_last(&em_tree->map); + n = rb_last(&em_tree->map.rb_root); if (n) { em = rb_entry(n, struct extent_map, rb_node); ret = em->start + em->len; @@ -1854,6 +1854,24 @@ void btrfs_assign_next_active_device(struct btrfs_device *device, fs_info->fs_devices->latest_bdev = next_device->bdev; } +/* + * Return btrfs_fs_devices::num_devices excluding the device that's being + * currently replaced. + */ +static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info) +{ + u64 num_devices = fs_info->fs_devices->num_devices; + + btrfs_dev_replace_read_lock(&fs_info->dev_replace); + if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) { + ASSERT(num_devices > 1); + num_devices--; + } + btrfs_dev_replace_read_unlock(&fs_info->dev_replace); + + return num_devices; +} + int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, u64 devid) { @@ -1865,22 +1883,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, mutex_lock(&uuid_mutex); - num_devices = fs_devices->num_devices; - btrfs_dev_replace_read_lock(&fs_info->dev_replace); - if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) { - WARN_ON(num_devices < 1); - num_devices--; - } - btrfs_dev_replace_read_unlock(&fs_info->dev_replace); + num_devices = btrfs_num_devices(fs_info); ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1); if (ret) goto out; - ret = btrfs_find_device_by_devspec(fs_info, devid, device_path, - &device); - if (ret) + device = btrfs_find_device_by_devspec(fs_info, devid, device_path); + + if (IS_ERR(device)) { + if (PTR_ERR(device) == -ENOENT && + strcmp(device_path, "missing") == 0) + ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; + else + ret = PTR_ERR(device); goto out; + } if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { ret = BTRFS_ERROR_DEV_TGT_REPLACE; @@ -2096,9 +2114,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev) call_rcu(&tgtdev->rcu, free_device_rcu); } -static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info, - const char *device_path, - struct btrfs_device **device) +static struct btrfs_device *btrfs_find_device_by_path( + struct btrfs_fs_info *fs_info, const char *device_path) { int ret = 0; struct btrfs_super_block *disk_super; @@ -2106,28 +2123,27 @@ static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info, u8 *dev_uuid; struct block_device *bdev; struct buffer_head *bh; + struct btrfs_device *device; - *device = NULL; ret = btrfs_get_bdev_and_sb(device_path, FMODE_READ, fs_info->bdev_holder, 0, &bdev, &bh); if (ret) - return ret; + return ERR_PTR(ret); disk_super = (struct btrfs_super_block *)bh->b_data; devid = btrfs_stack_device_id(&disk_super->dev_item); dev_uuid = disk_super->dev_item.uuid; - *device = btrfs_find_device(fs_info, devid, dev_uuid, disk_super->fsid); + device = btrfs_find_device(fs_info, devid, dev_uuid, disk_super->fsid); brelse(bh); - if (!*device) - ret = -ENOENT; + if (!device) + device = ERR_PTR(-ENOENT); blkdev_put(bdev, FMODE_READ); - return ret; + return device; } -int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info, - const char *device_path, - struct btrfs_device **device) +static struct btrfs_device *btrfs_find_device_missing_or_by_path( + struct btrfs_fs_info *fs_info, const char *device_path) { - *device = NULL; + struct btrfs_device *device = NULL; if (strcmp(device_path, "missing") == 0) { struct list_head *devices; struct btrfs_device *tmp; @@ -2136,42 +2152,38 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info, list_for_each_entry(tmp, devices, dev_list) { if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &tmp->dev_state) && !tmp->bdev) { - *device = tmp; + device = tmp; break; } } - if (!*device) - return BTRFS_ERROR_DEV_MISSING_NOT_FOUND; - - return 0; + if (!device) + return ERR_PTR(-ENOENT); } else { - return btrfs_find_device_by_path(fs_info, device_path, device); + device = btrfs_find_device_by_path(fs_info, device_path); } + + return device; } /* * Lookup a device given by device id, or the path if the id is 0. */ -int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid, - const char *devpath, - struct btrfs_device **device) +struct btrfs_device *btrfs_find_device_by_devspec( + struct btrfs_fs_info *fs_info, u64 devid, const char *devpath) { - int ret; + struct btrfs_device *device; if (devid) { - ret = 0; - *device = btrfs_find_device(fs_info, devid, NULL, NULL); - if (!*device) - ret = -ENOENT; + device = btrfs_find_device(fs_info, devid, NULL, NULL); + if (!device) + return ERR_PTR(-ENOENT); } else { if (!devpath || !devpath[0]) - return -EINVAL; - - ret = btrfs_find_device_missing_or_by_path(fs_info, devpath, - device); + return ERR_PTR(-EINVAL); + device = btrfs_find_device_missing_or_by_path(fs_info, devpath); } - return ret; + return device; } /* @@ -3679,7 +3691,7 @@ static int alloc_profile_is_valid(u64 flags, int extended) return !extended; /* "0" is valid for usual profiles */ /* true if exactly one bit set */ - return (flags & (flags - 1)) == 0; + return is_power_of_2(flags); } static inline int balance_need_close(struct btrfs_fs_info *fs_info) @@ -3740,13 +3752,8 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, } } - num_devices = fs_info->fs_devices->num_devices; - btrfs_dev_replace_read_lock(&fs_info->dev_replace); - if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) { - BUG_ON(num_devices < 1); - num_devices--; - } - btrfs_dev_replace_read_unlock(&fs_info->dev_replace); + num_devices = btrfs_num_devices(fs_info); + allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP; if (num_devices > 1) allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1); @@ -5897,7 +5904,11 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, } out: if (dev_replace_is_ongoing) { - btrfs_dev_replace_clear_lock_blocking(dev_replace); + ASSERT(atomic_read(&dev_replace->blocking_readers) > 0); + btrfs_dev_replace_read_lock(dev_replace); + /* Barrier implied by atomic_dec_and_test */ + if (atomic_dec_and_test(&dev_replace->blocking_readers)) + cond_wake_up_nomb(&dev_replace->read_lock_wq); btrfs_dev_replace_read_unlock(dev_replace); } free_extent_map(em); @@ -7438,7 +7449,7 @@ static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info) int ret = 0; read_lock(&em_tree->lock); - for (node = rb_first(&em_tree->map); node; node = rb_next(node)) { + for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) { em = rb_entry(node, struct extent_map, rb_node); if (em->map_lookup->num_stripes != em->map_lookup->verified_stripes) { diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 23e9285d88de..aefce895e994 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -410,12 +410,9 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices); void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step); void btrfs_assign_next_active_device(struct btrfs_device *device, struct btrfs_device *this_dev); -int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info, - const char *device_path, - struct btrfs_device **device); -int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid, - const char *devpath, - struct btrfs_device **device); +struct btrfs_device *btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, + u64 devid, + const char *devpath); struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, const u64 *devid, const u8 *uuid); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 49121e5a8de2..5c36ceecb5c1 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -593,11 +593,16 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, lower_new_dir_dentry = dget_parent(lower_new_dentry); target_inode = d_inode(new_dentry); trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + rc = -EINVAL; + if (lower_old_dentry->d_parent != lower_old_dir_dentry) + goto out_lock; + if (lower_new_dentry->d_parent != lower_new_dir_dentry) + goto out_lock; + if (d_unhashed(lower_old_dentry) || d_unhashed(lower_new_dentry)) + goto out_lock; /* source should not be ancestor of target */ - if (trap == lower_old_dentry) { - rc = -EINVAL; + if (trap == lower_old_dentry) goto out_lock; - } /* target should not be ancestor of source */ if (trap == lower_new_dentry) { rc = -ENOTEMPTY; diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index fb50f9aa6ead..c1d570ee1d9f 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -284,12 +284,16 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT, default_acl, XATTR_CREATE); posix_acl_release(default_acl); + } else { + inode->i_default_acl = NULL; } if (acl) { if (!error) error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl, XATTR_CREATE); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } return error; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index caff935fbeb8..12f90d48ba61 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -628,6 +628,7 @@ enum { #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 +#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER 0x0040 /* * ioctl commands @@ -1030,6 +1031,9 @@ struct ext4_inode_info { ext4_lblk_t i_da_metadata_calc_last_lblock; int i_da_metadata_calc_len; + /* pending cluster reservations for bigalloc file systems */ + struct ext4_pending_tree i_pending_tree; + /* on-disk additional length */ __u16 i_extra_isize; @@ -1401,7 +1405,8 @@ struct ext4_sb_info { u32 s_min_batch_time; struct block_device *journal_bdev; #ifdef CONFIG_QUOTA - char *s_qf_names[EXT4_MAXQUOTAS]; /* Names of quota files with journalled quota */ + /* Names of quota files with journalled quota */ + char __rcu *s_qf_names[EXT4_MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ @@ -2483,10 +2488,11 @@ extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); -extern int ext4_page_mkwrite(struct vm_fault *vmf); -extern int ext4_filemap_fault(struct vm_fault *vmf); +extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf); +extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); +extern void ext4_da_release_space(struct inode *inode, int to_free); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, @@ -3142,10 +3148,6 @@ extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t, int flags); extern void ext4_ext_drop_refs(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); -extern int ext4_find_delalloc_range(struct inode *inode, - ext4_lblk_t lblk_start, - ext4_lblk_t lblk_end); -extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk); extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); @@ -3156,6 +3158,7 @@ extern int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int mark_unwritten,int *err); +extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu); /* move_extent.c */ extern void ext4_double_down_write_data_sem(struct inode *first, diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index adf6668b596f..98bd0e9ee7df 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -120,6 +120,19 @@ struct ext4_ext_path { }; /* + * Used to record a portion of a cluster found at the beginning or end + * of an extent while traversing the extent tree during space removal. + * A partial cluster may be removed if it does not contain blocks shared + * with extents that aren't being deleted (tofree state). Otherwise, + * it cannot be removed (nofree state). + */ +struct partial_cluster { + ext4_fsblk_t pclu; /* physical cluster number */ + ext4_lblk_t lblk; /* logical block number within logical cluster */ + enum {initial, tofree, nofree} state; +}; + +/* * structure for external API */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 72a361d5ef74..240b6dea5441 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2351,8 +2351,8 @@ ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, { struct extent_status es; - ext4_es_find_delayed_extent_range(inode, hole_start, - hole_start + hole_len - 1, &es); + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + hole_len - 1, &es); if (es.es_len) { /* There's delayed extent containing lblock? */ if (es.es_lblk <= hole_start) @@ -2490,106 +2490,157 @@ static inline int get_default_free_blocks_flags(struct inode *inode) return 0; } +/* + * ext4_rereserve_cluster - increment the reserved cluster count when + * freeing a cluster with a pending reservation + * + * @inode - file containing the cluster + * @lblk - logical block in cluster to be reserved + * + * Increments the reserved cluster count and adjusts quota in a bigalloc + * file system when freeing a partial cluster containing at least one + * delayed and unwritten block. A partial cluster meeting that + * requirement will have a pending reservation. If so, the + * RERESERVE_CLUSTER flag is used when calling ext4_free_blocks() to + * defer reserved and allocated space accounting to a subsequent call + * to this function. + */ +static void ext4_rereserve_cluster(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); + + dquot_reclaim_block(inode, EXT4_C2B(sbi, 1)); + + spin_lock(&ei->i_block_reservation_lock); + ei->i_reserved_data_blocks++; + percpu_counter_add(&sbi->s_dirtyclusters_counter, 1); + spin_unlock(&ei->i_block_reservation_lock); + + percpu_counter_add(&sbi->s_freeclusters_counter, 1); + ext4_remove_pending(inode, lblk); +} + static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_extent *ex, - long long *partial_cluster, + struct partial_cluster *partial, ext4_lblk_t from, ext4_lblk_t to) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); - ext4_fsblk_t pblk; - int flags = get_default_free_blocks_flags(inode); + ext4_fsblk_t last_pblk, pblk; + ext4_lblk_t num; + int flags; + + /* only extent tail removal is allowed */ + if (from < le32_to_cpu(ex->ee_block) || + to != le32_to_cpu(ex->ee_block) + ee_len - 1) { + ext4_error(sbi->s_sb, + "strange request: removal(2) %u-%u from %u:%u", + from, to, le32_to_cpu(ex->ee_block), ee_len); + return 0; + } + +#ifdef EXTENTS_STATS + spin_lock(&sbi->s_ext_stats_lock); + sbi->s_ext_blocks += ee_len; + sbi->s_ext_extents++; + if (ee_len < sbi->s_ext_min) + sbi->s_ext_min = ee_len; + if (ee_len > sbi->s_ext_max) + sbi->s_ext_max = ee_len; + if (ext_depth(inode) > sbi->s_depth_max) + sbi->s_depth_max = ext_depth(inode); + spin_unlock(&sbi->s_ext_stats_lock); +#endif + + trace_ext4_remove_blocks(inode, ex, from, to, partial); /* - * For bigalloc file systems, we never free a partial cluster - * at the beginning of the extent. Instead, we make a note - * that we tried freeing the cluster, and check to see if we - * need to free it on a subsequent call to ext4_remove_blocks, - * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space. + * if we have a partial cluster, and it's different from the + * cluster of the last block in the extent, we free it */ - flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; + last_pblk = ext4_ext_pblock(ex) + ee_len - 1; + + if (partial->state != initial && + partial->pclu != EXT4_B2C(sbi, last_pblk)) { + if (partial->state == tofree) { + flags = get_default_free_blocks_flags(inode); + if (ext4_is_pending(inode, partial->lblk)) + flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; + ext4_free_blocks(handle, inode, NULL, + EXT4_C2B(sbi, partial->pclu), + sbi->s_cluster_ratio, flags); + if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) + ext4_rereserve_cluster(inode, partial->lblk); + } + partial->state = initial; + } + + num = le32_to_cpu(ex->ee_block) + ee_len - from; + pblk = ext4_ext_pblock(ex) + ee_len - num; - trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster); /* - * If we have a partial cluster, and it's different from the - * cluster of the last block, we need to explicitly free the - * partial cluster here. + * We free the partial cluster at the end of the extent (if any), + * unless the cluster is used by another extent (partial_cluster + * state is nofree). If a partial cluster exists here, it must be + * shared with the last block in the extent. */ - pblk = ext4_ext_pblock(ex) + ee_len - 1; - if (*partial_cluster > 0 && - *partial_cluster != (long long) EXT4_B2C(sbi, pblk)) { + flags = get_default_free_blocks_flags(inode); + + /* partial, left end cluster aligned, right end unaligned */ + if ((EXT4_LBLK_COFF(sbi, to) != sbi->s_cluster_ratio - 1) && + (EXT4_LBLK_CMASK(sbi, to) >= from) && + (partial->state != nofree)) { + if (ext4_is_pending(inode, to)) + flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, - EXT4_C2B(sbi, *partial_cluster), + EXT4_PBLK_CMASK(sbi, last_pblk), sbi->s_cluster_ratio, flags); - *partial_cluster = 0; + if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) + ext4_rereserve_cluster(inode, to); + partial->state = initial; + flags = get_default_free_blocks_flags(inode); } -#ifdef EXTENTS_STATS - { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - spin_lock(&sbi->s_ext_stats_lock); - sbi->s_ext_blocks += ee_len; - sbi->s_ext_extents++; - if (ee_len < sbi->s_ext_min) - sbi->s_ext_min = ee_len; - if (ee_len > sbi->s_ext_max) - sbi->s_ext_max = ee_len; - if (ext_depth(inode) > sbi->s_depth_max) - sbi->s_depth_max = ext_depth(inode); - spin_unlock(&sbi->s_ext_stats_lock); - } -#endif - if (from >= le32_to_cpu(ex->ee_block) - && to == le32_to_cpu(ex->ee_block) + ee_len - 1) { - /* tail removal */ - ext4_lblk_t num; - long long first_cluster; - - num = le32_to_cpu(ex->ee_block) + ee_len - from; - pblk = ext4_ext_pblock(ex) + ee_len - num; - /* - * Usually we want to free partial cluster at the end of the - * extent, except for the situation when the cluster is still - * used by any other extent (partial_cluster is negative). - */ - if (*partial_cluster < 0 && - *partial_cluster == -(long long) EXT4_B2C(sbi, pblk+num-1)) - flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; + flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; - ext_debug("free last %u blocks starting %llu partial %lld\n", - num, pblk, *partial_cluster); - ext4_free_blocks(handle, inode, NULL, pblk, num, flags); - /* - * If the block range to be freed didn't start at the - * beginning of a cluster, and we removed the entire - * extent and the cluster is not used by any other extent, - * save the partial cluster here, since we might need to - * delete if we determine that the truncate or punch hole - * operation has removed all of the blocks in the cluster. - * If that cluster is used by another extent, preserve its - * negative value so it isn't freed later on. - * - * If the whole extent wasn't freed, we've reached the - * start of the truncated/punched region and have finished - * removing blocks. If there's a partial cluster here it's - * shared with the remainder of the extent and is no longer - * a candidate for removal. - */ - if (EXT4_PBLK_COFF(sbi, pblk) && ee_len == num) { - first_cluster = (long long) EXT4_B2C(sbi, pblk); - if (first_cluster != -*partial_cluster) - *partial_cluster = first_cluster; - } else { - *partial_cluster = 0; + /* + * For bigalloc file systems, we never free a partial cluster + * at the beginning of the extent. Instead, we check to see if we + * need to free it on a subsequent call to ext4_remove_blocks, + * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space. + */ + flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; + ext4_free_blocks(handle, inode, NULL, pblk, num, flags); + + /* reset the partial cluster if we've freed past it */ + if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, pblk)) + partial->state = initial; + + /* + * If we've freed the entire extent but the beginning is not left + * cluster aligned and is not marked as ineligible for freeing we + * record the partial cluster at the beginning of the extent. It + * wasn't freed by the preceding ext4_free_blocks() call, and we + * need to look farther to the left to determine if it's to be freed + * (not shared with another extent). Else, reset the partial + * cluster - we're either done freeing or the beginning of the + * extent is left cluster aligned. + */ + if (EXT4_LBLK_COFF(sbi, from) && num == ee_len) { + if (partial->state == initial) { + partial->pclu = EXT4_B2C(sbi, pblk); + partial->lblk = from; + partial->state = tofree; } - } else - ext4_error(sbi->s_sb, "strange request: removal(2) " - "%u-%u from %u:%u", - from, to, le32_to_cpu(ex->ee_block), ee_len); + } else { + partial->state = initial; + } + return 0; } - /* * ext4_ext_rm_leaf() Removes the extents associated with the * blocks appearing between "start" and "end". Both "start" @@ -2608,7 +2659,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, static int ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, - long long *partial_cluster, + struct partial_cluster *partial, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -2640,7 +2691,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); - trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster); + trace_ext4_ext_rm_leaf(inode, start, ex, partial); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { @@ -2671,8 +2722,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex); - *partial_cluster = - -(long long) EXT4_B2C(sbi, pblk); + partial->pclu = EXT4_B2C(sbi, pblk); + partial->state = nofree; } ex--; ex_ee_block = le32_to_cpu(ex->ee_block); @@ -2714,8 +2765,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, if (err) goto out; - err = ext4_remove_blocks(handle, inode, ex, partial_cluster, - a, b); + err = ext4_remove_blocks(handle, inode, ex, partial, a, b); if (err) goto out; @@ -2769,18 +2819,23 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * If there's a partial cluster and at least one extent remains in * the leaf, free the partial cluster if it isn't shared with the * current extent. If it is shared with the current extent - * we zero partial_cluster because we've reached the start of the + * we reset the partial cluster because we've reached the start of the * truncated/punched region and we're done removing blocks. */ - if (*partial_cluster > 0 && ex >= EXT_FIRST_EXTENT(eh)) { + if (partial->state == tofree && ex >= EXT_FIRST_EXTENT(eh)) { pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; - if (*partial_cluster != (long long) EXT4_B2C(sbi, pblk)) { + if (partial->pclu != EXT4_B2C(sbi, pblk)) { + int flags = get_default_free_blocks_flags(inode); + + if (ext4_is_pending(inode, partial->lblk)) + flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, - EXT4_C2B(sbi, *partial_cluster), - sbi->s_cluster_ratio, - get_default_free_blocks_flags(inode)); + EXT4_C2B(sbi, partial->pclu), + sbi->s_cluster_ratio, flags); + if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) + ext4_rereserve_cluster(inode, partial->lblk); } - *partial_cluster = 0; + partial->state = initial; } /* if this leaf is free, then we should @@ -2819,10 +2874,14 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int depth = ext_depth(inode); struct ext4_ext_path *path = NULL; - long long partial_cluster = 0; + struct partial_cluster partial; handle_t *handle; int i = 0, err = 0; + partial.pclu = 0; + partial.lblk = 0; + partial.state = initial; + ext_debug("truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ @@ -2882,8 +2941,8 @@ again: */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex) + end - ee_block + 2; - partial_cluster = - -(long long) EXT4_B2C(sbi, pblk); + partial.pclu = EXT4_B2C(sbi, pblk); + partial.state = nofree; } /* @@ -2911,9 +2970,10 @@ again: &ex); if (err) goto out; - if (pblk) - partial_cluster = - -(long long) EXT4_B2C(sbi, pblk); + if (pblk) { + partial.pclu = EXT4_B2C(sbi, pblk); + partial.state = nofree; + } } } /* @@ -2948,8 +3008,7 @@ again: if (i == depth) { /* this is leaf block */ err = ext4_ext_rm_leaf(handle, inode, path, - &partial_cluster, start, - end); + &partial, start, end); /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); path[i].p_bh = NULL; @@ -3021,21 +3080,24 @@ again: } } - trace_ext4_ext_remove_space_done(inode, start, end, depth, - partial_cluster, path->p_hdr->eh_entries); + trace_ext4_ext_remove_space_done(inode, start, end, depth, &partial, + path->p_hdr->eh_entries); /* - * If we still have something in the partial cluster and we have removed - * even the first extent, then we should free the blocks in the partial - * cluster as well. (This code will only run when there are no leaves - * to the immediate left of the truncated/punched region.) + * if there's a partial cluster and we have removed the first extent + * in the file, then we also free the partial cluster, if any */ - if (partial_cluster > 0 && err == 0) { - /* don't zero partial_cluster since it's not used afterwards */ + if (partial.state == tofree && err == 0) { + int flags = get_default_free_blocks_flags(inode); + + if (ext4_is_pending(inode, partial.lblk)) + flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, - EXT4_C2B(sbi, partial_cluster), - sbi->s_cluster_ratio, - get_default_free_blocks_flags(inode)); + EXT4_C2B(sbi, partial.pclu), + sbi->s_cluster_ratio, flags); + if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) + ext4_rereserve_cluster(inode, partial.lblk); + partial.state = initial; } /* TODO: flexible tree reduction should be here */ @@ -3819,114 +3881,6 @@ out: return ext4_mark_inode_dirty(handle, inode); } -/** - * ext4_find_delalloc_range: find delayed allocated block in the given range. - * - * Return 1 if there is a delalloc block in the range, otherwise 0. - */ -int ext4_find_delalloc_range(struct inode *inode, - ext4_lblk_t lblk_start, - ext4_lblk_t lblk_end) -{ - struct extent_status es; - - ext4_es_find_delayed_extent_range(inode, lblk_start, lblk_end, &es); - if (es.es_len == 0) - return 0; /* there is no delay extent in this tree */ - else if (es.es_lblk <= lblk_start && - lblk_start < es.es_lblk + es.es_len) - return 1; - else if (lblk_start <= es.es_lblk && es.es_lblk <= lblk_end) - return 1; - else - return 0; -} - -int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk) -{ - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - ext4_lblk_t lblk_start, lblk_end; - lblk_start = EXT4_LBLK_CMASK(sbi, lblk); - lblk_end = lblk_start + sbi->s_cluster_ratio - 1; - - return ext4_find_delalloc_range(inode, lblk_start, lblk_end); -} - -/** - * Determines how many complete clusters (out of those specified by the 'map') - * are under delalloc and were reserved quota for. - * This function is called when we are writing out the blocks that were - * originally written with their allocation delayed, but then the space was - * allocated using fallocate() before the delayed allocation could be resolved. - * The cases to look for are: - * ('=' indicated delayed allocated blocks - * '-' indicates non-delayed allocated blocks) - * (a) partial clusters towards beginning and/or end outside of allocated range - * are not delalloc'ed. - * Ex: - * |----c---=|====c====|====c====|===-c----| - * |++++++ allocated ++++++| - * ==> 4 complete clusters in above example - * - * (b) partial cluster (outside of allocated range) towards either end is - * marked for delayed allocation. In this case, we will exclude that - * cluster. - * Ex: - * |----====c========|========c========| - * |++++++ allocated ++++++| - * ==> 1 complete clusters in above example - * - * Ex: - * |================c================| - * |++++++ allocated ++++++| - * ==> 0 complete clusters in above example - * - * The ext4_da_update_reserve_space will be called only if we - * determine here that there were some "entire" clusters that span - * this 'allocated' range. - * In the non-bigalloc case, this function will just end up returning num_blks - * without ever calling ext4_find_delalloc_range. - */ -static unsigned int -get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, - unsigned int num_blks) -{ - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - ext4_lblk_t alloc_cluster_start, alloc_cluster_end; - ext4_lblk_t lblk_from, lblk_to, c_offset; - unsigned int allocated_clusters = 0; - - alloc_cluster_start = EXT4_B2C(sbi, lblk_start); - alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1); - - /* max possible clusters for this allocation */ - allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1; - - trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks); - - /* Check towards left side */ - c_offset = EXT4_LBLK_COFF(sbi, lblk_start); - if (c_offset) { - lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start); - lblk_to = lblk_from + c_offset - 1; - - if (ext4_find_delalloc_range(inode, lblk_from, lblk_to)) - allocated_clusters--; - } - - /* Now check towards right. */ - c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks); - if (allocated_clusters && c_offset) { - lblk_from = lblk_start + num_blks; - lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1; - - if (ext4_find_delalloc_range(inode, lblk_from, lblk_to)) - allocated_clusters--; - } - - return allocated_clusters; -} - static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -4108,23 +4062,6 @@ out: } map->m_len = allocated; - /* - * If we have done fallocate with the offset that is already - * delayed allocated, we would have block reservation - * and quota reservation done in the delayed write path. - * But fallocate would have already updated quota and block - * count for this offset. So cancel these reservation - */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { - unsigned int reserved_clusters; - reserved_clusters = get_reserved_cluster_alloc(inode, - map->m_lblk, map->m_len); - if (reserved_clusters) - ext4_da_update_reserve_space(inode, - reserved_clusters, - 0); - } - map_out: map->m_flags |= EXT4_MAP_MAPPED; if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) { @@ -4513,77 +4450,39 @@ got_allocated_blocks: map->m_flags |= EXT4_MAP_NEW; /* - * Update reserved blocks/metadata blocks after successful - * block allocation which had been deferred till now. + * Reduce the reserved cluster count to reflect successful deferred + * allocation of delayed allocated clusters or direct allocation of + * clusters discovered to be delayed allocated. Once allocated, a + * cluster is not included in the reserved count. */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { - unsigned int reserved_clusters; - /* - * Check how many clusters we had reserved this allocated range - */ - reserved_clusters = get_reserved_cluster_alloc(inode, - map->m_lblk, allocated); - if (!map_from_cluster) { - BUG_ON(allocated_clusters < reserved_clusters); - if (reserved_clusters < allocated_clusters) { - struct ext4_inode_info *ei = EXT4_I(inode); - int reservation = allocated_clusters - - reserved_clusters; - /* - * It seems we claimed few clusters outside of - * the range of this allocation. We should give - * it back to the reservation pool. This can - * happen in the following case: - * - * * Suppose s_cluster_ratio is 4 (i.e., each - * cluster has 4 blocks. Thus, the clusters - * are [0-3],[4-7],[8-11]... - * * First comes delayed allocation write for - * logical blocks 10 & 11. Since there were no - * previous delayed allocated blocks in the - * range [8-11], we would reserve 1 cluster - * for this write. - * * Next comes write for logical blocks 3 to 8. - * In this case, we will reserve 2 clusters - * (for [0-3] and [4-7]; and not for [8-11] as - * that range has a delayed allocated blocks. - * Thus total reserved clusters now becomes 3. - * * Now, during the delayed allocation writeout - * time, we will first write blocks [3-8] and - * allocate 3 clusters for writing these - * blocks. Also, we would claim all these - * three clusters above. - * * Now when we come here to writeout the - * blocks [10-11], we would expect to claim - * the reservation of 1 cluster we had made - * (and we would claim it since there are no - * more delayed allocated blocks in the range - * [8-11]. But our reserved cluster count had - * already gone to 0. - * - * Thus, at the step 4 above when we determine - * that there are still some unwritten delayed - * allocated blocks outside of our current - * block range, we should increment the - * reserved clusters count so that when the - * remaining blocks finally gets written, we - * could claim them. - */ - dquot_reserve_block(inode, - EXT4_C2B(sbi, reservation)); - spin_lock(&ei->i_block_reservation_lock); - ei->i_reserved_data_blocks += reservation; - spin_unlock(&ei->i_block_reservation_lock); - } + if (test_opt(inode->i_sb, DELALLOC) && !map_from_cluster) { + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { /* - * We will claim quota for all newly allocated blocks. - * We're updating the reserved space *after* the - * correction above so we do not accidentally free - * all the metadata reservation because we might - * actually need it later on. + * When allocating delayed allocated clusters, simply + * reduce the reserved cluster count and claim quota */ ext4_da_update_reserve_space(inode, allocated_clusters, 1); + } else { + ext4_lblk_t lblk, len; + unsigned int n; + + /* + * When allocating non-delayed allocated clusters + * (from fallocate, filemap, DIO, or clusters + * allocated when delalloc has been disabled by + * ext4_nonda_switch), reduce the reserved cluster + * count by the number of allocated clusters that + * have previously been delayed allocated. Quota + * has been claimed by ext4_mb_new_blocks() above, + * so release the quota reservations made for any + * previously delayed allocated clusters. + */ + lblk = EXT4_LBLK_CMASK(sbi, map->m_lblk); + len = allocated_clusters << sbi->s_cluster_bits; + n = ext4_es_delayed_clu(inode, lblk, len); + if (n > 0) + ext4_da_update_reserve_space(inode, (int) n, 0); } } @@ -5075,8 +4974,10 @@ static int ext4_find_delayed_extent(struct inode *inode, ext4_lblk_t block, next_del; if (newes->es_pblk == 0) { - ext4_es_find_delayed_extent_range(inode, newes->es_lblk, - newes->es_lblk + newes->es_len - 1, &es); + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, + newes->es_lblk, + newes->es_lblk + newes->es_len - 1, + &es); /* * No extent in extent-tree contains block @newes->es_pblk, @@ -5097,7 +4998,8 @@ static int ext4_find_delayed_extent(struct inode *inode, } block = newes->es_lblk + newes->es_len; - ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es); + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, block, + EXT_MAX_BLOCKS, &es); if (es.es_len == 0) next_del = EXT_MAX_BLOCKS; else @@ -5958,3 +5860,82 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, } return replaced_count; } + +/* + * ext4_clu_mapped - determine whether any block in a logical cluster has + * been mapped to a physical cluster + * + * @inode - file containing the logical cluster + * @lclu - logical cluster of interest + * + * Returns 1 if any block in the logical cluster is mapped, signifying + * that a physical cluster has been allocated for it. Otherwise, + * returns 0. Can also return negative error codes. Derived from + * ext4_ext_map_blocks(). + */ +int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_ext_path *path; + int depth, mapped = 0, err = 0; + struct ext4_extent *extent; + ext4_lblk_t first_lblk, first_lclu, last_lclu; + + /* search for the extent closest to the first block in the cluster */ + path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); + if (IS_ERR(path)) { + err = PTR_ERR(path); + path = NULL; + goto out; + } + + depth = ext_depth(inode); + + /* + * A consistent leaf must not be empty. This situation is possible, + * though, _during_ tree modification, and it's why an assert can't + * be put in ext4_find_extent(). + */ + if (unlikely(path[depth].p_ext == NULL && depth != 0)) { + EXT4_ERROR_INODE(inode, + "bad extent address - lblock: %lu, depth: %d, pblock: %lld", + (unsigned long) EXT4_C2B(sbi, lclu), + depth, path[depth].p_block); + err = -EFSCORRUPTED; + goto out; + } + + extent = path[depth].p_ext; + + /* can't be mapped if the extent tree is empty */ + if (extent == NULL) + goto out; + + first_lblk = le32_to_cpu(extent->ee_block); + first_lclu = EXT4_B2C(sbi, first_lblk); + + /* + * Three possible outcomes at this point - found extent spanning + * the target cluster, to the left of the target cluster, or to the + * right of the target cluster. The first two cases are handled here. + * The last case indicates the target cluster is not mapped. + */ + if (lclu >= first_lclu) { + last_lclu = EXT4_B2C(sbi, first_lblk + + ext4_ext_get_actual_len(extent) - 1); + if (lclu <= last_lclu) { + mapped = 1; + } else { + first_lblk = ext4_ext_next_allocated_block(path); + first_lclu = EXT4_B2C(sbi, first_lblk); + if (lclu == first_lclu) + mapped = 1; + } + } + +out: + ext4_ext_drop_refs(path); + kfree(path); + + return err ? err : mapped; +} diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index c4e6fb15101b..2b439afafe13 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -142,6 +142,7 @@ */ static struct kmem_cache *ext4_es_cachep; +static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, @@ -149,6 +150,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); +static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len); int __init ext4_init_es(void) { @@ -233,30 +236,38 @@ static struct extent_status *__es_tree_search(struct rb_root *root, } /* - * ext4_es_find_delayed_extent_range: find the 1st delayed extent covering - * @es->lblk if it exists, otherwise, the next extent after @es->lblk. + * ext4_es_find_extent_range - find extent with specified status within block + * range or next extent following block range in + * extents status tree * - * @inode: the inode which owns delayed extents - * @lblk: the offset where we start to search - * @end: the offset where we stop to search - * @es: delayed extent that we found + * @inode - file containing the range + * @matching_fn - pointer to function that matches extents with desired status + * @lblk - logical block defining start of range + * @end - logical block defining end of range + * @es - extent found, if any + * + * Find the first extent within the block range specified by @lblk and @end + * in the extents status tree that satisfies @matching_fn. If a match + * is found, it's returned in @es. If not, and a matching extent is found + * beyond the block range, it's returned in @es. If no match is found, an + * extent is returned in @es whose es_lblk, es_len, and es_pblk components + * are 0. */ -void ext4_es_find_delayed_extent_range(struct inode *inode, - ext4_lblk_t lblk, ext4_lblk_t end, - struct extent_status *es) +static void __es_find_extent_range(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk, ext4_lblk_t end, + struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; - BUG_ON(es == NULL); - BUG_ON(end < lblk); - trace_ext4_es_find_delayed_extent_range_enter(inode, lblk); + WARN_ON(es == NULL); + WARN_ON(end < lblk); - read_lock(&EXT4_I(inode)->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; - /* find extent in cache firstly */ + /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; if (tree->cache_es) { es1 = tree->cache_es; @@ -271,28 +282,133 @@ void ext4_es_find_delayed_extent_range(struct inode *inode, es1 = __es_tree_search(&tree->root, lblk); out: - if (es1 && !ext4_es_is_delayed(es1)) { + if (es1 && !matching_fn(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } - if (ext4_es_is_delayed(es1)) + if (matching_fn(es1)) break; } } - if (es1 && ext4_es_is_delayed(es1)) { + if (es1 && matching_fn(es1)) { tree->cache_es = es1; es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } +} + +/* + * Locking for __es_find_extent_range() for external use + */ +void ext4_es_find_extent_range(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk, ext4_lblk_t end, + struct extent_status *es) +{ + trace_ext4_es_find_extent_range_enter(inode, lblk); + + read_lock(&EXT4_I(inode)->i_es_lock); + __es_find_extent_range(inode, matching_fn, lblk, end, es); + read_unlock(&EXT4_I(inode)->i_es_lock); + + trace_ext4_es_find_extent_range_exit(inode, es); +} + +/* + * __es_scan_range - search block range for block with specified status + * in extents status tree + * + * @inode - file containing the range + * @matching_fn - pointer to function that matches extents with desired status + * @lblk - logical block defining start of range + * @end - logical block defining end of range + * + * Returns true if at least one block in the specified block range satisfies + * the criterion specified by @matching_fn, and false if not. If at least + * one extent has the specified status, then there is at least one block + * in the cluster with that status. Should only be called by code that has + * taken i_es_lock. + */ +static bool __es_scan_range(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t start, ext4_lblk_t end) +{ + struct extent_status es; + + __es_find_extent_range(inode, matching_fn, start, end, &es); + if (es.es_len == 0) + return false; /* no matching extent in the tree */ + else if (es.es_lblk <= start && + start < es.es_lblk + es.es_len) + return true; + else if (start <= es.es_lblk && es.es_lblk <= end) + return true; + else + return false; +} +/* + * Locking for __es_scan_range() for external use + */ +bool ext4_es_scan_range(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk, ext4_lblk_t end) +{ + bool ret; + + read_lock(&EXT4_I(inode)->i_es_lock); + ret = __es_scan_range(inode, matching_fn, lblk, end); read_unlock(&EXT4_I(inode)->i_es_lock); - trace_ext4_es_find_delayed_extent_range_exit(inode, es); + return ret; +} + +/* + * __es_scan_clu - search cluster for block with specified status in + * extents status tree + * + * @inode - file containing the cluster + * @matching_fn - pointer to function that matches extents with desired status + * @lblk - logical block in cluster to be searched + * + * Returns true if at least one extent in the cluster containing @lblk + * satisfies the criterion specified by @matching_fn, and false if not. If at + * least one extent has the specified status, then there is at least one block + * in the cluster with that status. Should only be called by code that has + * taken i_es_lock. + */ +static bool __es_scan_clu(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t lblk_start, lblk_end; + + lblk_start = EXT4_LBLK_CMASK(sbi, lblk); + lblk_end = lblk_start + sbi->s_cluster_ratio - 1; + + return __es_scan_range(inode, matching_fn, lblk_start, lblk_end); +} + +/* + * Locking for __es_scan_clu() for external use + */ +bool ext4_es_scan_clu(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk) +{ + bool ret; + + read_lock(&EXT4_I(inode)->i_es_lock); + ret = __es_scan_clu(inode, matching_fn, lblk); + read_unlock(&EXT4_I(inode)->i_es_lock); + + return ret; } static void ext4_es_list_add(struct inode *inode) @@ -694,6 +810,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err = 0; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); @@ -730,6 +847,11 @@ retry: if (err == -ENOMEM && !ext4_es_is_delayed(&newes)) err = 0; + if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && + (status & EXTENT_STATUS_WRITTEN || + status & EXTENT_STATUS_UNWRITTEN)) + __revise_pending(inode, lblk, len); + error: write_unlock(&EXT4_I(inode)->i_es_lock); @@ -1252,3 +1374,499 @@ static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) ei->i_es_tree.cache_es = NULL; return nr_shrunk; } + +#ifdef ES_DEBUG__ +static void ext4_print_pending_tree(struct inode *inode) +{ + struct ext4_pending_tree *tree; + struct rb_node *node; + struct pending_reservation *pr; + + printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino); + tree = &EXT4_I(inode)->i_pending_tree; + node = rb_first(&tree->root); + while (node) { + pr = rb_entry(node, struct pending_reservation, rb_node); + printk(KERN_DEBUG " %u", pr->lclu); + node = rb_next(node); + } + printk(KERN_DEBUG "\n"); +} +#else +#define ext4_print_pending_tree(inode) +#endif + +int __init ext4_init_pending(void) +{ + ext4_pending_cachep = kmem_cache_create("ext4_pending_reservation", + sizeof(struct pending_reservation), + 0, (SLAB_RECLAIM_ACCOUNT), NULL); + if (ext4_pending_cachep == NULL) + return -ENOMEM; + return 0; +} + +void ext4_exit_pending(void) +{ + kmem_cache_destroy(ext4_pending_cachep); +} + +void ext4_init_pending_tree(struct ext4_pending_tree *tree) +{ + tree->root = RB_ROOT; +} + +/* + * __get_pending - retrieve a pointer to a pending reservation + * + * @inode - file containing the pending cluster reservation + * @lclu - logical cluster of interest + * + * Returns a pointer to a pending reservation if it's a member of + * the set, and NULL if not. Must be called holding i_es_lock. + */ +static struct pending_reservation *__get_pending(struct inode *inode, + ext4_lblk_t lclu) +{ + struct ext4_pending_tree *tree; + struct rb_node *node; + struct pending_reservation *pr = NULL; + + tree = &EXT4_I(inode)->i_pending_tree; + node = (&tree->root)->rb_node; + + while (node) { + pr = rb_entry(node, struct pending_reservation, rb_node); + if (lclu < pr->lclu) + node = node->rb_left; + else if (lclu > pr->lclu) + node = node->rb_right; + else if (lclu == pr->lclu) + return pr; + } + return NULL; +} + +/* + * __insert_pending - adds a pending cluster reservation to the set of + * pending reservations + * + * @inode - file containing the cluster + * @lblk - logical block in the cluster to be added + * + * Returns 0 on successful insertion and -ENOMEM on failure. If the + * pending reservation is already in the set, returns successfully. + */ +static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; + struct rb_node **p = &tree->root.rb_node; + struct rb_node *parent = NULL; + struct pending_reservation *pr; + ext4_lblk_t lclu; + int ret = 0; + + lclu = EXT4_B2C(sbi, lblk); + /* search to find parent for insertion */ + while (*p) { + parent = *p; + pr = rb_entry(parent, struct pending_reservation, rb_node); + + if (lclu < pr->lclu) { + p = &(*p)->rb_left; + } else if (lclu > pr->lclu) { + p = &(*p)->rb_right; + } else { + /* pending reservation already inserted */ + goto out; + } + } + + pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); + if (pr == NULL) { + ret = -ENOMEM; + goto out; + } + pr->lclu = lclu; + + rb_link_node(&pr->rb_node, parent, p); + rb_insert_color(&pr->rb_node, &tree->root); + +out: + return ret; +} + +/* + * __remove_pending - removes a pending cluster reservation from the set + * of pending reservations + * + * @inode - file containing the cluster + * @lblk - logical block in the pending cluster reservation to be removed + * + * Returns successfully if pending reservation is not a member of the set. + */ +static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct pending_reservation *pr; + struct ext4_pending_tree *tree; + + pr = __get_pending(inode, EXT4_B2C(sbi, lblk)); + if (pr != NULL) { + tree = &EXT4_I(inode)->i_pending_tree; + rb_erase(&pr->rb_node, &tree->root); + kmem_cache_free(ext4_pending_cachep, pr); + } +} + +/* + * ext4_remove_pending - removes a pending cluster reservation from the set + * of pending reservations + * + * @inode - file containing the cluster + * @lblk - logical block in the pending cluster reservation to be removed + * + * Locking for external use of __remove_pending. + */ +void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + + write_lock(&ei->i_es_lock); + __remove_pending(inode, lblk); + write_unlock(&ei->i_es_lock); +} + +/* + * ext4_is_pending - determine whether a cluster has a pending reservation + * on it + * + * @inode - file containing the cluster + * @lblk - logical block in the cluster + * + * Returns true if there's a pending reservation for the cluster in the + * set of pending reservations, and false if not. + */ +bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); + bool ret; + + read_lock(&ei->i_es_lock); + ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL); + read_unlock(&ei->i_es_lock); + + return ret; +} + +/* + * ext4_es_insert_delayed_block - adds a delayed block to the extents status + * tree, adding a pending reservation where + * needed + * + * @inode - file containing the newly added block + * @lblk - logical block to be added + * @allocated - indicates whether a physical cluster has been allocated for + * the logical cluster that contains the block + * + * Returns 0 on success, negative error code on failure. + */ +int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, + bool allocated) +{ + struct extent_status newes; + int err = 0; + + es_debug("add [%u/1) delayed to extent status tree of inode %lu\n", + lblk, inode->i_ino); + + newes.es_lblk = lblk; + newes.es_len = 1; + ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED); + trace_ext4_es_insert_delayed_block(inode, &newes, allocated); + + ext4_es_insert_extent_check(inode, &newes); + + write_lock(&EXT4_I(inode)->i_es_lock); + + err = __es_remove_extent(inode, lblk, lblk); + if (err != 0) + goto error; +retry: + err = __es_insert_extent(inode, &newes); + if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb), + 128, EXT4_I(inode))) + goto retry; + if (err != 0) + goto error; + + if (allocated) + __insert_pending(inode, lblk); + +error: + write_unlock(&EXT4_I(inode)->i_es_lock); + + ext4_es_print_tree(inode); + ext4_print_pending_tree(inode); + + return err; +} + +/* + * __es_delayed_clu - count number of clusters containing blocks that + * are delayed only + * + * @inode - file containing block range + * @start - logical block defining start of range + * @end - logical block defining end of range + * + * Returns the number of clusters containing only delayed (not delayed + * and unwritten) blocks in the range specified by @start and @end. Any + * cluster or part of a cluster within the range and containing a delayed + * and not unwritten block within the range is counted as a whole cluster. + */ +static unsigned int __es_delayed_clu(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t end) +{ + struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; + struct extent_status *es; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct rb_node *node; + ext4_lblk_t first_lclu, last_lclu; + unsigned long long last_counted_lclu; + unsigned int n = 0; + + /* guaranteed to be unequal to any ext4_lblk_t value */ + last_counted_lclu = ~0ULL; + + es = __es_tree_search(&tree->root, start); + + while (es && (es->es_lblk <= end)) { + if (ext4_es_is_delonly(es)) { + if (es->es_lblk <= start) + first_lclu = EXT4_B2C(sbi, start); + else + first_lclu = EXT4_B2C(sbi, es->es_lblk); + + if (ext4_es_end(es) >= end) + last_lclu = EXT4_B2C(sbi, end); + else + last_lclu = EXT4_B2C(sbi, ext4_es_end(es)); + + if (first_lclu == last_counted_lclu) + n += last_lclu - first_lclu; + else + n += last_lclu - first_lclu + 1; + last_counted_lclu = last_lclu; + } + node = rb_next(&es->rb_node); + if (!node) + break; + es = rb_entry(node, struct extent_status, rb_node); + } + + return n; +} + +/* + * ext4_es_delayed_clu - count number of clusters containing blocks that + * are both delayed and unwritten + * + * @inode - file containing block range + * @lblk - logical block defining start of range + * @len - number of blocks in range + * + * Locking for external use of __es_delayed_clu(). + */ +unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + ext4_lblk_t end; + unsigned int n; + + if (len == 0) + return 0; + + end = lblk + len - 1; + WARN_ON(end < lblk); + + read_lock(&ei->i_es_lock); + + n = __es_delayed_clu(inode, lblk, end); + + read_unlock(&ei->i_es_lock); + + return n; +} + +/* + * __revise_pending - makes, cancels, or leaves unchanged pending cluster + * reservations for a specified block range depending + * upon the presence or absence of delayed blocks + * outside the range within clusters at the ends of the + * range + * + * @inode - file containing the range + * @lblk - logical block defining the start of range + * @len - length of range in blocks + * + * Used after a newly allocated extent is added to the extents status tree. + * Requires that the extents in the range have either written or unwritten + * status. Must be called while holding i_es_lock. + */ +static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t end = lblk + len - 1; + ext4_lblk_t first, last; + bool f_del = false, l_del = false; + + if (len == 0) + return; + + /* + * Two cases - block range within single cluster and block range + * spanning two or more clusters. Note that a cluster belonging + * to a range starting and/or ending on a cluster boundary is treated + * as if it does not contain a delayed extent. The new range may + * have allocated space for previously delayed blocks out to the + * cluster boundary, requiring that any pre-existing pending + * reservation be canceled. Because this code only looks at blocks + * outside the range, it should revise pending reservations + * correctly even if the extent represented by the range can't be + * inserted in the extents status tree due to ENOSPC. + */ + + if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) { + first = EXT4_LBLK_CMASK(sbi, lblk); + if (first != lblk) + f_del = __es_scan_range(inode, &ext4_es_is_delonly, + first, lblk - 1); + if (f_del) { + __insert_pending(inode, first); + } else { + last = EXT4_LBLK_CMASK(sbi, end) + + sbi->s_cluster_ratio - 1; + if (last != end) + l_del = __es_scan_range(inode, + &ext4_es_is_delonly, + end + 1, last); + if (l_del) + __insert_pending(inode, last); + else + __remove_pending(inode, last); + } + } else { + first = EXT4_LBLK_CMASK(sbi, lblk); + if (first != lblk) + f_del = __es_scan_range(inode, &ext4_es_is_delonly, + first, lblk - 1); + if (f_del) + __insert_pending(inode, first); + else + __remove_pending(inode, first); + + last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; + if (last != end) + l_del = __es_scan_range(inode, &ext4_es_is_delonly, + end + 1, last); + if (l_del) + __insert_pending(inode, last); + else + __remove_pending(inode, last); + } +} + +/* + * ext4_es_remove_blks - remove block range from extents status tree and + * reduce reservation count or cancel pending + * reservation as needed + * + * @inode - file containing range + * @lblk - first block in range + * @len - number of blocks to remove + * + */ +void ext4_es_remove_blks(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + unsigned int clu_size, reserved = 0; + ext4_lblk_t last_lclu, first, length, remainder, last; + bool delonly; + int err = 0; + struct pending_reservation *pr; + struct ext4_pending_tree *tree; + + /* + * Process cluster by cluster for bigalloc - there may be up to + * two clusters in a 4k page with a 1k block size and two blocks + * per cluster. Also necessary for systems with larger page sizes + * and potentially larger block sizes. + */ + clu_size = sbi->s_cluster_ratio; + last_lclu = EXT4_B2C(sbi, lblk + len - 1); + + write_lock(&EXT4_I(inode)->i_es_lock); + + for (first = lblk, remainder = len; + remainder > 0; + first += length, remainder -= length) { + + if (EXT4_B2C(sbi, first) == last_lclu) + length = remainder; + else + length = clu_size - EXT4_LBLK_COFF(sbi, first); + + /* + * The BH_Delay flag, which triggers calls to this function, + * and the contents of the extents status tree can be + * inconsistent due to writepages activity. So, note whether + * the blocks to be removed actually belong to an extent with + * delayed only status. + */ + delonly = __es_scan_clu(inode, &ext4_es_is_delonly, first); + + /* + * because of the writepages effect, written and unwritten + * blocks could be removed here + */ + last = first + length - 1; + err = __es_remove_extent(inode, first, last); + if (err) + ext4_warning(inode->i_sb, + "%s: couldn't remove page (err = %d)", + __func__, err); + + /* non-bigalloc case: simply count the cluster for release */ + if (sbi->s_cluster_ratio == 1 && delonly) { + reserved++; + continue; + } + + /* + * bigalloc case: if all delayed allocated only blocks have + * just been removed from a cluster, either cancel a pending + * reservation if it exists or count a cluster for release + */ + if (delonly && + !__es_scan_clu(inode, &ext4_es_is_delonly, first)) { + pr = __get_pending(inode, EXT4_B2C(sbi, first)); + if (pr != NULL) { + tree = &EXT4_I(inode)->i_pending_tree; + rb_erase(&pr->rb_node, &tree->root); + kmem_cache_free(ext4_pending_cachep, pr); + } else { + reserved++; + } + } + } + + write_unlock(&EXT4_I(inode)->i_es_lock); + + ext4_da_release_space(inode, reserved); +} diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index 8efdeb903d6b..131a8b7df265 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -78,6 +78,51 @@ struct ext4_es_stats { struct percpu_counter es_stats_shk_cnt; }; +/* + * Pending cluster reservations for bigalloc file systems + * + * A cluster with a pending reservation is a logical cluster shared by at + * least one extent in the extents status tree with delayed and unwritten + * status and at least one other written or unwritten extent. The + * reservation is said to be pending because a cluster reservation would + * have to be taken in the event all blocks in the cluster shared with + * written or unwritten extents were deleted while the delayed and + * unwritten blocks remained. + * + * The set of pending cluster reservations is an auxiliary data structure + * used with the extents status tree to implement reserved cluster/block + * accounting for bigalloc file systems. The set is kept in memory and + * records all pending cluster reservations. + * + * Its primary function is to avoid the need to read extents from the + * disk when invalidating pages as a result of a truncate, punch hole, or + * collapse range operation. Page invalidation requires a decrease in the + * reserved cluster count if it results in the removal of all delayed + * and unwritten extents (blocks) from a cluster that is not shared with a + * written or unwritten extent, and no decrease otherwise. Determining + * whether the cluster is shared can be done by searching for a pending + * reservation on it. + * + * Secondarily, it provides a potentially faster method for determining + * whether the reserved cluster count should be increased when a physical + * cluster is deallocated as a result of a truncate, punch hole, or + * collapse range operation. The necessary information is also present + * in the extents status tree, but might be more rapidly accessed in + * the pending reservation set in many cases due to smaller size. + * + * The pending cluster reservation set is implemented as a red-black tree + * with the goal of minimizing per page search time overhead. + */ + +struct pending_reservation { + struct rb_node rb_node; + ext4_lblk_t lclu; +}; + +struct ext4_pending_tree { + struct rb_root root; +}; + extern int __init ext4_init_es(void); extern void ext4_exit_es(void); extern void ext4_es_init_tree(struct ext4_es_tree *tree); @@ -90,11 +135,18 @@ extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, unsigned int status); extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); -extern void ext4_es_find_delayed_extent_range(struct inode *inode, - ext4_lblk_t lblk, ext4_lblk_t end, - struct extent_status *es); +extern void ext4_es_find_extent_range(struct inode *inode, + int (*match_fn)(struct extent_status *es), + ext4_lblk_t lblk, ext4_lblk_t end, + struct extent_status *es); extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es); +extern bool ext4_es_scan_range(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk, ext4_lblk_t end); +extern bool ext4_es_scan_clu(struct inode *inode, + int (*matching_fn)(struct extent_status *es), + ext4_lblk_t lblk); static inline unsigned int ext4_es_status(struct extent_status *es) { @@ -126,6 +178,16 @@ static inline int ext4_es_is_hole(struct extent_status *es) return (ext4_es_type(es) & EXTENT_STATUS_HOLE) != 0; } +static inline int ext4_es_is_mapped(struct extent_status *es) +{ + return (ext4_es_is_written(es) || ext4_es_is_unwritten(es)); +} + +static inline int ext4_es_is_delonly(struct extent_status *es) +{ + return (ext4_es_is_delayed(es) && !ext4_es_is_unwritten(es)); +} + static inline void ext4_es_set_referenced(struct extent_status *es) { es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT; @@ -175,4 +237,16 @@ extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi); extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v); +extern int __init ext4_init_pending(void); +extern void ext4_exit_pending(void); +extern void ext4_init_pending_tree(struct ext4_pending_tree *tree); +extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk); +extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk); +extern int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, + bool allocated); +extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len); +extern void ext4_es_remove_blks(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len); + #endif /* _EXT4_EXTENTS_STATUS_H */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 7b4736022761..9c4bac18cc6c 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -863,7 +863,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping, handle_t *handle; struct page *page; struct ext4_iloc iloc; - int retries; + int retries = 0; ret = ext4_get_inode_loc(inode, &iloc); if (ret) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d767e993591d..c3d9a42c561e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -577,8 +577,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && !(status & EXTENT_STATUS_WRITTEN) && - ext4_find_delalloc_range(inode, map->m_lblk, - map->m_lblk + map->m_len - 1)) + ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk, + map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); @@ -701,8 +701,8 @@ found: EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && !(status & EXTENT_STATUS_WRITTEN) && - ext4_find_delalloc_range(inode, map->m_lblk, - map->m_lblk + map->m_len - 1)) + ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk, + map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); @@ -1595,7 +1595,7 @@ static int ext4_da_reserve_space(struct inode *inode) return 0; /* success */ } -static void ext4_da_release_space(struct inode *inode, int to_free) +void ext4_da_release_space(struct inode *inode, int to_free) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); @@ -1634,13 +1634,11 @@ static void ext4_da_page_release_reservation(struct page *page, unsigned int offset, unsigned int length) { - int to_release = 0, contiguous_blks = 0; + int contiguous_blks = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; struct inode *inode = page->mapping->host; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int stop = offset + length; - int num_clusters; ext4_fsblk_t lblk; BUG_ON(stop > PAGE_SIZE || stop < length); @@ -1654,7 +1652,6 @@ static void ext4_da_page_release_reservation(struct page *page, break; if ((offset <= curr_off) && (buffer_delay(bh))) { - to_release++; contiguous_blks++; clear_buffer_delay(bh); } else if (contiguous_blks) { @@ -1662,7 +1659,7 @@ static void ext4_da_page_release_reservation(struct page *page, (PAGE_SHIFT - inode->i_blkbits); lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; - ext4_es_remove_extent(inode, lblk, contiguous_blks); + ext4_es_remove_blks(inode, lblk, contiguous_blks); contiguous_blks = 0; } curr_off = next_off; @@ -1671,21 +1668,9 @@ static void ext4_da_page_release_reservation(struct page *page, if (contiguous_blks) { lblk = page->index << (PAGE_SHIFT - inode->i_blkbits); lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; - ext4_es_remove_extent(inode, lblk, contiguous_blks); + ext4_es_remove_blks(inode, lblk, contiguous_blks); } - /* If we have released all the blocks belonging to a cluster, then we - * need to release the reserved space for that cluster. */ - num_clusters = EXT4_NUM_B2C(sbi, to_release); - while (num_clusters > 0) { - lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) + - ((num_clusters - 1) << sbi->s_cluster_bits); - if (sbi->s_cluster_ratio == 1 || - !ext4_find_delalloc_cluster(inode, lblk)) - ext4_da_release_space(inode, 1); - - num_clusters--; - } } /* @@ -1781,6 +1766,65 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) } /* + * ext4_insert_delayed_block - adds a delayed block to the extents status + * tree, incrementing the reserved cluster/block + * count or making a pending reservation + * where needed + * + * @inode - file containing the newly added block + * @lblk - logical block to be added + * + * Returns 0 on success, negative error code on failure. + */ +static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int ret; + bool allocated = false; + + /* + * If the cluster containing lblk is shared with a delayed, + * written, or unwritten extent in a bigalloc file system, it's + * already been accounted for and does not need to be reserved. + * A pending reservation must be made for the cluster if it's + * shared with a written or unwritten extent and doesn't already + * have one. Written and unwritten extents can be purged from the + * extents status tree if the system is under memory pressure, so + * it's necessary to examine the extent tree if a search of the + * extents status tree doesn't get a match. + */ + if (sbi->s_cluster_ratio == 1) { + ret = ext4_da_reserve_space(inode); + if (ret != 0) /* ENOSPC */ + goto errout; + } else { /* bigalloc */ + if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) { + if (!ext4_es_scan_clu(inode, + &ext4_es_is_mapped, lblk)) { + ret = ext4_clu_mapped(inode, + EXT4_B2C(sbi, lblk)); + if (ret < 0) + goto errout; + if (ret == 0) { + ret = ext4_da_reserve_space(inode); + if (ret != 0) /* ENOSPC */ + goto errout; + } else { + allocated = true; + } + } else { + allocated = true; + } + } + } + + ret = ext4_es_insert_delayed_block(inode, lblk, allocated); + +errout: + return ret; +} + +/* * This function is grabs code from the very beginning of * ext4_map_blocks, but assumes that the caller is from delayed write * time. This function looks up the requested blocks and sets the @@ -1859,28 +1903,14 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, add_delayed: if (retval == 0) { int ret; + /* * XXX: __block_prepare_write() unmaps passed block, * is it OK? */ - /* - * If the block was allocated from previously allocated cluster, - * then we don't need to reserve it again. However we still need - * to reserve metadata for every block we're going to write. - */ - if (EXT4_SB(inode->i_sb)->s_cluster_ratio == 1 || - !ext4_find_delalloc_cluster(inode, map->m_lblk)) { - ret = ext4_da_reserve_space(inode); - if (ret) { - /* not enough space to reserve */ - retval = ret; - goto out_unlock; - } - } - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - ~0, EXTENT_STATUS_DELAYED); - if (ret) { + ret = ext4_insert_delayed_block(inode, map->m_lblk); + if (ret != 0) { retval = ret; goto out_unlock; } @@ -3450,7 +3480,8 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, ext4_lblk_t end = map.m_lblk + map.m_len - 1; struct extent_status es; - ext4_es_find_delayed_extent_range(inode, map.m_lblk, end, &es); + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, + map.m_lblk, end, &es); if (!es.es_len || es.es_lblk > end) { /* entire range is a hole */ @@ -6153,13 +6184,14 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh) return !buffer_mapped(bh); } -int ext4_page_mkwrite(struct vm_fault *vmf) +vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; loff_t size; unsigned long len; - int ret; + int err; + vm_fault_t ret; struct file *file = vma->vm_file; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; @@ -6172,8 +6204,8 @@ int ext4_page_mkwrite(struct vm_fault *vmf) down_read(&EXT4_I(inode)->i_mmap_sem); - ret = ext4_convert_inline_data(inode); - if (ret) + err = ext4_convert_inline_data(inode); + if (err) goto out_ret; /* Delalloc case is easy... */ @@ -6181,9 +6213,9 @@ int ext4_page_mkwrite(struct vm_fault *vmf) !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { - ret = block_page_mkwrite(vma, vmf, + err = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); - } while (ret == -ENOSPC && + } while (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); goto out_ret; } @@ -6228,8 +6260,8 @@ retry_alloc: ret = VM_FAULT_SIGBUS; goto out; } - ret = block_page_mkwrite(vma, vmf, get_block); - if (!ret && ext4_should_journal_data(inode)) { + err = block_page_mkwrite(vma, vmf, get_block); + if (!err && ext4_should_journal_data(inode)) { if (ext4_walk_page_buffers(handle, page_buffers(page), 0, PAGE_SIZE, NULL, do_journal_get_write_access)) { unlock_page(page); @@ -6240,24 +6272,24 @@ retry_alloc: ext4_set_inode_state(inode, EXT4_STATE_JDATA); } ext4_journal_stop(handle); - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_alloc; out_ret: - ret = block_page_mkwrite_return(ret); + ret = block_page_mkwrite_return(err); out: up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; } -int ext4_filemap_fault(struct vm_fault *vmf) +vm_fault_t ext4_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); - int err; + vm_fault_t ret; down_read(&EXT4_I(inode)->i_mmap_sem); - err = filemap_fault(vmf); + ret = filemap_fault(vmf); up_read(&EXT4_I(inode)->i_mmap_sem); - return err; + return ret; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a7074115d6f6..0edee31913d1 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -67,7 +67,6 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); - swap(inode1->i_flags, inode2->i_flags); swap(inode1->i_version, inode2->i_version); swap(inode1->i_blocks, inode2->i_blocks); swap(inode1->i_bytes, inode2->i_bytes); @@ -85,6 +84,21 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) i_size_write(inode2, isize); } +static void reset_inode_seed(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + __le32 inum = cpu_to_le32(inode->i_ino); + __le32 gen = cpu_to_le32(inode->i_generation); + __u32 csum; + + if (!ext4_has_metadata_csum(inode->i_sb)) + return; + + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); + ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen)); +} + /** * Swap the information from the given @inode and the inode * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other @@ -102,10 +116,13 @@ static long swap_inode_boot_loader(struct super_block *sb, struct inode *inode_bl; struct ext4_inode_info *ei_bl; - if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) + if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || + IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || + ext4_has_inline_data(inode)) return -EINVAL; - if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) + if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || + !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) return -EPERM; inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO); @@ -120,13 +137,13 @@ static long swap_inode_boot_loader(struct super_block *sb, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); - truncate_inode_pages(&inode->i_data, 0); - truncate_inode_pages(&inode_bl->i_data, 0); - /* Wait for all existing dio workers */ inode_dio_wait(inode); inode_dio_wait(inode_bl); + truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages(&inode_bl->i_data, 0); + handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; @@ -159,6 +176,8 @@ static long swap_inode_boot_loader(struct super_block *sb, inode->i_generation = prandom_u32(); inode_bl->i_generation = prandom_u32(); + reset_inode_seed(inode); + reset_inode_seed(inode_bl); ext4_discard_preallocations(inode); @@ -169,6 +188,7 @@ static long swap_inode_boot_loader(struct super_block *sb, inode->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); + ext4_mark_inode_dirty(handle, inode); } else { err = ext4_mark_inode_dirty(handle, inode_bl); if (err < 0) { @@ -178,6 +198,7 @@ static long swap_inode_boot_loader(struct super_block *sb, /* Revert all changes: */ swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); + ext4_mark_inode_dirty(handle, inode_bl); } } ext4_journal_stop(handle); @@ -339,19 +360,14 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) if (projid_eq(kprojid, EXT4_I(inode)->i_projid)) return 0; - err = mnt_want_write_file(filp); - if (err) - return err; - err = -EPERM; - inode_lock(inode); /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) - goto out_unlock; + return err; err = ext4_get_inode_loc(inode, &iloc); if (err) - goto out_unlock; + return err; raw_inode = ext4_raw_inode(&iloc); if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) { @@ -359,20 +375,20 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) EXT4_SB(sb)->s_want_extra_isize, &iloc); if (err) - goto out_unlock; + return err; } else { brelse(iloc.bh); } - dquot_initialize(inode); + err = dquot_initialize(inode); + if (err) + return err; handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - goto out_unlock; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) @@ -400,9 +416,6 @@ out_dirty: err = rc; out_stop: ext4_journal_stop(handle); -out_unlock: - inode_unlock(inode); - mnt_drop_write_file(filp); return err; } #else @@ -626,6 +639,30 @@ group_add_out: return err; } +static int ext4_ioctl_check_project(struct inode *inode, struct fsxattr *fa) +{ + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() == &init_user_ns) + return 0; + + if (__kprojid_val(EXT4_I(inode)->i_projid) != fa->fsx_projid) + return -EINVAL; + + if (ext4_test_inode_flag(inode, EXT4_INODE_PROJINHERIT)) { + if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) + return -EINVAL; + } else { + if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) + return -EINVAL; + } + + return 0; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1025,19 +1062,19 @@ resizefs_out: return err; inode_lock(inode); + err = ext4_ioctl_check_project(inode, &fa); + if (err) + goto out; flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) | (flags & EXT4_FL_XFLAG_VISIBLE); err = ext4_ioctl_setflags(inode, flags); - inode_unlock(inode); - mnt_drop_write_file(filp); if (err) - return err; - + goto out; err = ext4_ioctl_setproject(filp, fa.fsx_projid); - if (err) - return err; - - return 0; +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return err; } case EXT4_IOC_SHUTDOWN: return ext4_shutdown(sb, arg); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e29fce2fbf25..e2248083cdca 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4915,9 +4915,17 @@ do_more: &sbi->s_flex_groups[flex_group].free_clusters); } - if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) - dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); - percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); + /* + * on a bigalloc file system, defer the s_freeclusters_counter + * update to the caller (ext4_remove_space and friends) so they + * can determine if a cluster freed here should be rereserved + */ + if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) { + if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) + dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); + percpu_counter_add(&sbi->s_freeclusters_counter, + count_clusters); + } ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index a409ff70d67b..2f5be02fc6f6 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -516,9 +516,13 @@ mext_check_arguments(struct inode *orig_inode, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - if (orig_eof < orig_start + *len - 1) + if (orig_eof <= orig_start) + *len = 0; + else if (orig_eof < orig_start + *len - 1) *len = orig_eof - orig_start; - if (donor_eof < donor_start + *len - 1) + if (donor_eof <= donor_start) + *len = 0; + else if (donor_eof < donor_start + *len - 1) *len = donor_eof - donor_start; if (!*len) { ext4_debug("ext4 move extent: len should not be 0 " diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 377d516c475f..67a38532032a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2261,7 +2261,7 @@ again: dxroot->info.indirect_levels += 1; dxtrace(printk(KERN_DEBUG "Creating %d level index...\n", - info->indirect_levels)); + dxroot->info.indirect_levels)); err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (err) goto journal_error; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1145109968ef..a221f1cdf704 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -914,6 +914,18 @@ static inline void ext4_quota_off_umount(struct super_block *sb) for (type = 0; type < EXT4_MAXQUOTAS; type++) ext4_quota_off(sb, type); } + +/* + * This is a helper function which is used in the mount/remount + * codepaths (which holds s_umount) to fetch the quota file name. + */ +static inline char *get_qf_name(struct super_block *sb, + struct ext4_sb_info *sbi, + int type) +{ + return rcu_dereference_protected(sbi->s_qf_names[type], + lockdep_is_held(&sb->s_umount)); +} #else static inline void ext4_quota_off_umount(struct super_block *sb) { @@ -965,7 +977,7 @@ static void ext4_put_super(struct super_block *sb) percpu_free_rwsem(&sbi->s_journal_flag_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list @@ -1040,6 +1052,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_da_metadata_calc_len = 0; ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); + ext4_init_pending_tree(&ei->i_pending_tree); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); @@ -1530,11 +1543,10 @@ static const char deprecated_msg[] = static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *qname; + char *qname, *old_qname = get_qf_name(sb, sbi, qtype); int ret = -1; - if (sb_any_quota_loaded(sb) && - !sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && !old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); @@ -1551,8 +1563,8 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "Not enough memory for storing quotafile name"); return -1; } - if (sbi->s_qf_names[qtype]) { - if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + if (old_qname) { + if (strcmp(old_qname, qname) == 0) ret = 1; else ext4_msg(sb, KERN_ERR, @@ -1565,7 +1577,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "quotafile must be on filesystem root"); goto errout; } - sbi->s_qf_names[qtype] = qname; + rcu_assign_pointer(sbi->s_qf_names[qtype], qname); set_opt(sb, QUOTA); return 1; errout: @@ -1577,15 +1589,16 @@ static int clear_qf_name(struct super_block *sb, int qtype) { struct ext4_sb_info *sbi = EXT4_SB(sb); + char *old_qname = get_qf_name(sb, sbi, qtype); - if (sb_any_quota_loaded(sb) && - sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -1; } - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + rcu_assign_pointer(sbi->s_qf_names[qtype], NULL); + synchronize_rcu(); + kfree(old_qname); return 1; } #endif @@ -1960,7 +1973,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *p; + char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name; substring_t args[MAX_OPT_ARGS]; int token; @@ -1991,11 +2004,13 @@ static int parse_options(char *options, struct super_block *sb, "Cannot enable project quota enforcement."); return 0; } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { - if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + usr_qf_name = get_qf_name(sb, sbi, USRQUOTA); + grp_qf_name = get_qf_name(sb, sbi, GRPQUOTA); + if (usr_qf_name || grp_qf_name) { + if (test_opt(sb, USRQUOTA) && usr_qf_name) clear_opt(sb, USRQUOTA); - if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + if (test_opt(sb, GRPQUOTA) && grp_qf_name) clear_opt(sb, GRPQUOTA); if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) { @@ -2029,6 +2044,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq, { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); + char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; @@ -2047,11 +2063,14 @@ static inline void ext4_show_quota_options(struct seq_file *seq, seq_printf(seq, ",jqfmt=%s", fmtname); } - if (sbi->s_qf_names[USRQUOTA]) - seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); - - if (sbi->s_qf_names[GRPQUOTA]) - seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + rcu_read_lock(); + usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); + grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); + if (usr_qf_name) + seq_show_option(seq, "usrjquota", usr_qf_name); + if (grp_qf_name) + seq_show_option(seq, "grpjquota", grp_qf_name); + rcu_read_unlock(); #endif } @@ -5103,6 +5122,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) int err = 0; #ifdef CONFIG_QUOTA int i, j; + char *to_free[EXT4_MAXQUOTAS]; #endif char *orig_data = kstrdup(data, GFP_KERNEL); @@ -5122,8 +5142,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { - old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i], - GFP_KERNEL); + char *qf_name = get_qf_name(sb, sbi, i); + + old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); @@ -5352,9 +5373,12 @@ restore_opts: #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { - kfree(sbi->s_qf_names[i]); - sbi->s_qf_names[i] = old_opts.s_qf_names[i]; + to_free[i] = get_qf_name(sb, sbi, i); + rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } + synchronize_rcu(); + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(to_free[i]); #endif kfree(orig_data); return err; @@ -5545,7 +5569,7 @@ static int ext4_write_info(struct super_block *sb, int type) */ static int ext4_quota_on_mount(struct super_block *sb, int type) { - return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], + return dquot_quota_on_mount(sb, get_qf_name(sb, EXT4_SB(sb), type), EXT4_SB(sb)->s_jquota_fmt, type); } @@ -5954,6 +5978,10 @@ static int __init ext4_init_fs(void) if (err) return err; + err = ext4_init_pending(); + if (err) + goto out6; + err = ext4_init_pageio(); if (err) goto out5; @@ -5992,6 +6020,8 @@ out3: out4: ext4_exit_pageio(); out5: + ext4_exit_pending(); +out6: ext4_exit_es(); return err; @@ -6009,6 +6039,7 @@ static void __exit ext4_exit_fs(void) ext4_exit_system_zone(); ext4_exit_pageio(); ext4_exit_es(); + ext4_exit_pending(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 111824199a88..fa707cdd4120 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/f2fs_fs.h> #include "f2fs.h" @@ -53,6 +50,9 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); const char *end = value + size; + if (size < sizeof(struct f2fs_acl_header)) + return ERR_PTR(-EINVAL); + if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) return ERR_PTR(-EINVAL); @@ -394,12 +394,16 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl, ipage); posix_acl_release(default_acl); + } else { + inode->i_default_acl = NULL; } if (acl) { if (!error) error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl, ipage); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } return error; diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 2c685185c24d..b96823c59b15 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.h * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.h * * Copyright (C) 2001-2003 Andreas Gruenbacher, <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_ACL_H__ #define __F2FS_ACL_H__ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index e8b6b89bddb8..9c28ea439e0b 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/checkpoint.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/bio.h> @@ -122,11 +119,8 @@ retry: if (PTR_ERR(page) == -EIO && ++count <= DEFAULT_RETRY_IO_COUNT) goto retry; - f2fs_stop_checkpoint(sbi, false); - f2fs_bug_on(sbi, 1); } - return page; } @@ -282,8 +276,7 @@ static int __f2fs_write_meta_page(struct page *page, dec_page_count(sbi, F2FS_DIRTY_META); if (wbc->for_reclaim) - f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, META); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META); unlock_page(page); @@ -696,6 +689,8 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) /* clear Orphan Flag */ clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG); out: + set_sbi_flag(sbi, SBI_IS_RECOVERED); + #ifdef CONFIG_QUOTA /* Turn quotas off */ if (quota_enabled) @@ -1084,6 +1079,21 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi) ckpt->next_free_nid = cpu_to_le32(last_nid); } +static bool __need_flush_quota(struct f2fs_sb_info *sbi) +{ + if (!is_journalled_quota(sbi)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) + return true; + if (get_pages(sbi, F2FS_DIRTY_QDATA)) + return true; + return false; +} + /* * Freeze all the FS-operations for checkpoint. */ @@ -1095,12 +1105,36 @@ static int block_operations(struct f2fs_sb_info *sbi) .for_reclaim = 0, }; struct blk_plug plug; - int err = 0; + int err = 0, cnt = 0; blk_start_plug(&plug); -retry_flush_dents: +retry_flush_quotas: + if (__need_flush_quota(sbi)) { + int locked; + + if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) { + set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + f2fs_lock_all(sbi); + goto retry_flush_dents; + } + clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + /* only failed during mount/umount/freeze/quotactl */ + locked = down_read_trylock(&sbi->sb->s_umount); + f2fs_quota_sync(sbi->sb, -1); + if (locked) + up_read(&sbi->sb->s_umount); + } + f2fs_lock_all(sbi); + if (__need_flush_quota(sbi)) { + f2fs_unlock_all(sbi); + cond_resched(); + goto retry_flush_quotas; + } + +retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); @@ -1108,7 +1142,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } /* @@ -1117,6 +1151,12 @@ retry_flush_dents: */ down_write(&sbi->node_change); + if (__need_flush_quota(sbi)) { + up_write(&sbi->node_change); + f2fs_unlock_all(sbi); + goto retry_flush_quotas; + } + if (get_pages(sbi, F2FS_DIRTY_IMETA)) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1124,7 +1164,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } retry_flush_nodes: @@ -1215,6 +1255,19 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) __set_ckpt_flags(ckpt, CP_FSCK_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + __set_ckpt_flags(ckpt, CP_DISABLED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* set this flag to activate crc|cp_ver for recovery */ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG); @@ -1422,6 +1475,8 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); + clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + sbi->unusable_block_count = 0; __set_cp_next_pack(sbi); /* @@ -1446,6 +1501,12 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long long ckpt_ver; int err = 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (cpc->reason != CP_PAUSE) + return 0; + f2fs_msg(sbi->sb, KERN_WARNING, + "Start checkpoint disabled!"); + } mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && @@ -1497,7 +1558,10 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); /* write cached NAT/SIT entries to NAT/SIT area */ - f2fs_flush_nat_entries(sbi, cpc); + err = f2fs_flush_nat_entries(sbi, cpc); + if (err) + goto stop; + f2fs_flush_sit_entries(sbi, cpc); /* unlock all the fs_lock[] in do_checkpoint() */ @@ -1506,7 +1570,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) f2fs_release_discard_addrs(sbi); else f2fs_clear_prefree_segments(sbi, cpc); - +stop: unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 382c1ef9a9e4..106f116466bf 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/data.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -49,12 +46,29 @@ static bool __is_cp_guaranteed(struct page *page) inode->i_ino == F2FS_NODE_INO(sbi) || S_ISDIR(inode->i_mode) || (S_ISREG(inode->i_mode) && - is_inode_flag_set(inode, FI_ATOMIC_FILE)) || + (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) || is_cold_data(page)) return true; return false; } +static enum count_type __read_io_type(struct page *page) +{ + struct address_space *mapping = page->mapping; + + if (mapping) { + struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (inode->i_ino == F2FS_META_INO(sbi)) + return F2FS_RD_META; + + if (inode->i_ino == F2FS_NODE_INO(sbi)) + return F2FS_RD_NODE; + } + return F2FS_RD_DATA; +} + /* postprocessing steps for read bios */ enum bio_post_read_step { STEP_INITIAL = 0, @@ -80,10 +94,12 @@ static void __read_end_io(struct bio *bio) /* PG_error was set if any post_read step failed */ if (bio->bi_status || PageError(page)) { ClearPageUptodate(page); - SetPageError(page); + /* will re-read again later */ + ClearPageError(page); } else { SetPageUptodate(page); } + dec_page_count(F2FS_P_SB(page), __read_io_type(page)); unlock_page(page); } if (bio->bi_private) @@ -126,8 +142,9 @@ static bool f2fs_bio_post_read_required(struct bio *bio) static void f2fs_read_end_io(struct bio *bio) { - if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)), FAULT_IO)) { - f2fs_show_injection_info(FAULT_IO); + if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)), + FAULT_READ_IO)) { + f2fs_show_injection_info(FAULT_READ_IO); bio->bi_status = BLK_STS_IOERR; } @@ -148,6 +165,11 @@ static void f2fs_write_end_io(struct bio *bio) struct bio_vec *bvec; int i; + if (time_to_inject(sbi, FAULT_WRITE_IO)) { + f2fs_show_injection_info(FAULT_WRITE_IO); + bio->bi_status = BLK_STS_IOERR; + } + bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; enum count_type type = WB_DATA_TYPE(page); @@ -319,8 +341,8 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) io->bio = NULL; } -static bool __has_merged_page(struct f2fs_bio_info *io, - struct inode *inode, nid_t ino, pgoff_t idx) +static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, + struct page *page, nid_t ino) { struct bio_vec *bvec; struct page *target; @@ -329,7 +351,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, if (!io->bio) return false; - if (!inode && !ino) + if (!inode && !page && !ino) return true; bio_for_each_segment_all(bvec, io->bio, i) { @@ -339,11 +361,10 @@ static bool __has_merged_page(struct f2fs_bio_info *io, else target = fscrypt_control_page(bvec->bv_page); - if (idx != target->index) - continue; - if (inode && inode == target->mapping->host) return true; + if (page && page == target) + return true; if (ino && ino == ino_of_node(target)) return true; } @@ -352,7 +373,8 @@ static bool __has_merged_page(struct f2fs_bio_info *io, } static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, - nid_t ino, pgoff_t idx, enum page_type type) + struct page *page, nid_t ino, + enum page_type type) { enum page_type btype = PAGE_TYPE_OF_BIO(type); enum temp_type temp; @@ -363,7 +385,7 @@ static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, io = sbi->write_io[btype] + temp; down_read(&io->io_rwsem); - ret = __has_merged_page(io, inode, ino, idx); + ret = __has_merged_page(io, inode, page, ino); up_read(&io->io_rwsem); /* TODO: use HOT temp only for meta pages now. */ @@ -394,12 +416,12 @@ static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi, } static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type, bool force) + struct inode *inode, struct page *page, + nid_t ino, enum page_type type, bool force) { enum temp_type temp; - if (!force && !has_merged_page(sbi, inode, ino, idx, type)) + if (!force && !has_merged_page(sbi, inode, page, ino, type)) return; for (temp = HOT; temp < NR_TEMP_TYPE; temp++) { @@ -418,10 +440,10 @@ void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) } void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type) + struct inode *inode, struct page *page, + nid_t ino, enum page_type type) { - __submit_merged_write_cond(sbi, inode, ino, idx, type, false); + __submit_merged_write_cond(sbi, inode, page, ino, type, false); } void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) @@ -456,12 +478,16 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) bio_put(bio); return -EFAULT; } + + if (fio->io_wbc && !is_read_io(fio->op)) + wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + bio_set_op_attrs(bio, fio->op, fio->op_flags); - __submit_bio(fio->sbi, bio, fio->type); + inc_page_count(fio->sbi, is_read_io(fio->op) ? + __read_io_type(page): WB_DATA_TYPE(fio->page)); - if (!is_read_io(fio->op)) - inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page)); + __submit_bio(fio->sbi, bio, fio->type); return 0; } @@ -533,6 +559,9 @@ skip: if (fio->in_list) goto next; out: + if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || + f2fs_is_checkpoint_ready(sbi)) + __submit_merged_bio(io); up_write(&io->io_rwsem); } @@ -565,9 +594,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, ctx->bio = bio; ctx->enabled_steps = post_read_steps; bio->bi_private = ctx; - - /* wait the page to be moved by cleaning */ - f2fs_wait_on_block_writeback(sbi, blkaddr); } return bio; @@ -582,10 +608,15 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, if (IS_ERR(bio)) return PTR_ERR(bio); + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, blkaddr); + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; } + ClearPageError(page); + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); __submit_bio(F2FS_I_SB(inode), bio, DATA); return 0; } @@ -876,7 +907,6 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) struct f2fs_summary sum; struct node_info ni; block_t old_blkaddr; - pgoff_t fofs; blkcnt_t count = 1; int err; @@ -889,7 +919,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); - if (dn->data_blkaddr == NEW_ADDR) + if (dn->data_blkaddr != NULL_ADDR) goto alloc; if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) @@ -905,12 +935,10 @@ alloc: old_blkaddr, old_blkaddr); f2fs_set_data_blkaddr(dn); - /* update i_size */ - fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + - dn->ofs_in_node; - if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT)) - f2fs_i_size_write(dn->inode, - ((loff_t)(fofs + 1) << PAGE_SHIFT)); + /* + * i_size will be updated by direct_IO. Otherwise, we'll get stale + * data from unwritten block via dio_read. + */ return 0; } @@ -945,7 +973,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) if (direct_io) { map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint); - flag = f2fs_force_buffered_io(inode, WRITE) ? + flag = f2fs_force_buffered_io(inode, iocb, from) ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; goto map_blocks; @@ -970,7 +998,7 @@ map_blocks: return err; } -static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) +void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) { if (flag == F2FS_GET_BLOCK_PRE_AIO) { if (lock) @@ -1025,6 +1053,11 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, map->m_flags = F2FS_MAP_MAPPED; if (map->m_next_extent) *map->m_next_extent = pgofs + map->m_len; + + /* for hardware encryption, but to avoid potential issue in future */ + if (flag == F2FS_GET_BLOCK_DIO) + f2fs_wait_on_block_writeback_range(inode, + map->m_pblk, map->m_len); goto out; } @@ -1064,7 +1097,15 @@ next_block: goto sync_out; } - if (!is_valid_data_blkaddr(sbi, blkaddr)) { + if (is_valid_data_blkaddr(sbi, blkaddr)) { + /* use out-place-update for driect IO under LFS mode */ + if (test_opt(sbi, LFS) && create && + flag == F2FS_GET_BLOCK_DIO) { + err = __allocate_data_block(&dn, map->m_seg_type); + if (!err) + set_inode_flag(inode, FI_APPEND_WRITE); + } + } else { if (create) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; @@ -1076,6 +1117,8 @@ next_block: last_ofs_in_node = dn.ofs_in_node; } } else { + WARN_ON(flag != F2FS_GET_BLOCK_PRE_DIO && + flag != F2FS_GET_BLOCK_DIO); err = __allocate_data_block(&dn, map->m_seg_type); if (!err) @@ -1173,6 +1216,12 @@ skip: goto next_dnode; sync_out: + + /* for hardware encryption, but to avoid potential issue in future */ + if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) + f2fs_wait_on_block_writeback_range(inode, + map->m_pblk, map->m_len); + if (flag == F2FS_GET_BLOCK_PRECACHE) { if (map->m_flags & F2FS_MAP_MAPPED) { unsigned int ofs = start_pgofs - map->m_lblk; @@ -1255,7 +1304,7 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DEFAULT, NULL, + F2FS_GET_BLOCK_DIO, NULL, f2fs_rw_hint_to_seg_type( inode->i_write_hint)); } @@ -1558,9 +1607,17 @@ submit_and_realloc: } } + /* + * If the page is under writeback, we need to wait for + * its completion to see the correct decrypted data. + */ + f2fs_wait_on_block_writeback(inode, block_nr); + if (bio_add_page(bio, page, blocksize, 0) < blocksize) goto submit_and_realloc; + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + ClearPageError(page); last_block_in_bio = block_nr; goto next_page; set_error_page: @@ -1625,7 +1682,7 @@ static int encrypt_one_page(struct f2fs_io_info *fio) return 0; /* wait for GCed page writeback via META_MAPPING */ - f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr); + f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); retry_encrypt: fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page, @@ -1682,6 +1739,10 @@ static inline bool check_inplace_update_policy(struct inode *inode, is_inode_flag_set(inode, FI_NEED_IPU)) return true; + if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + !f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; + return false; } @@ -1705,6 +1766,8 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (S_ISDIR(inode->i_mode)) return true; + if (IS_NOQUOTA(inode)) + return true; if (f2fs_is_atomic_file(inode)) return true; if (fio) { @@ -1712,6 +1775,9 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (IS_ATOMIC_WRITTEN_PAGE(fio->page)) return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; } return false; } @@ -1763,6 +1829,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) /* This page is already truncated */ if (fio->old_blkaddr == NULL_ADDR) { ClearPageUptodate(page); + clear_cold_data(page); goto out_writepage; } got_it: @@ -1938,18 +2005,20 @@ done: out: inode_dec_dirty_pages(inode); - if (err) + if (err) { ClearPageUptodate(page); + clear_cold_data(page); + } if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA); clear_inode_flag(inode, FI_HOT_DATA); f2fs_remove_dirty_inode(inode); submitted = NULL; } unlock_page(page); - if (!S_ISDIR(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode)) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -2000,10 +2069,10 @@ static int f2fs_write_cache_pages(struct address_space *mapping, pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; - pgoff_t last_idx = ULONG_MAX; int cycled; int range_whole = 0; int tag; + int nwritten = 0; pagevec_init(&pvec); @@ -2106,7 +2175,7 @@ continue_unlock: done = 1; break; } else if (submitted) { - last_idx = page->index; + nwritten++; } if (--wbc->nr_to_write <= 0 && @@ -2128,9 +2197,9 @@ continue_unlock: if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; - if (last_idx != ULONG_MAX) + if (nwritten) f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host, - 0, last_idx, DATA); + NULL, 0, DATA); return ret; } @@ -2140,6 +2209,8 @@ static inline bool __should_serialize_io(struct inode *inode, { if (!S_ISREG(inode->i_mode)) return false; + if (IS_NOQUOTA(inode)) + return false; if (wbc->sync_mode != WB_SYNC_ALL) return true; if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) @@ -2169,7 +2240,8 @@ static int __f2fs_write_data_pages(struct address_space *mapping, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; - if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && + if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) && + wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && f2fs_available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; @@ -2234,7 +2306,7 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); - f2fs_truncate_blocks(inode, i_size, true); + f2fs_truncate_blocks(inode, i_size, true, true); up_write(&F2FS_I(inode)->i_mmap_sem); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -2332,6 +2404,10 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, trace_f2fs_write_begin(inode, pos, len, flags); + err = f2fs_is_checkpoint_ready(sbi); + if (err) + goto fail; + if ((f2fs_is_atomic_file(inode) && !f2fs_available_free_memory(sbi, INMEM_PAGES)) || is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { @@ -2369,7 +2445,8 @@ repeat: if (err) goto fail; - if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) { + if (need_balance && !IS_NOQUOTA(inode) && + has_not_enough_free_secs(sbi, 0, 0)) { unlock_page(page); f2fs_balance_fs(sbi, true); lock_page(page); @@ -2382,10 +2459,6 @@ repeat: f2fs_wait_on_page_writeback(page, DATA, false); - /* wait for GCed page writeback via META_MAPPING */ - if (f2fs_post_read_required(inode)) - f2fs_wait_on_block_writeback(sbi, blkaddr); - if (len == PAGE_SIZE || PageUptodate(page)) return 0; @@ -2480,36 +2553,53 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; int rw = iov_iter_rw(iter); int err; enum rw_hint hint = iocb->ki_hint; int whint_mode = F2FS_OPTION(sbi).whint_mode; + bool do_opu; err = check_direct_IO(inode, iter, offset); if (err) return err < 0 ? err : 0; - if (f2fs_force_buffered_io(inode, rw)) + if (f2fs_force_buffered_io(inode, iocb, iter)) return 0; + do_opu = allow_outplace_dio(inode, iocb, iter); + trace_f2fs_direct_IO_enter(inode, offset, count, rw); if (rw == WRITE && whint_mode == WHINT_MODE_OFF) iocb->ki_hint = WRITE_LIFE_NOT_SET; - if (!down_read_trylock(&F2FS_I(inode)->i_gc_rwsem[rw])) { - if (iocb->ki_flags & IOCB_NOWAIT) { + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!down_read_trylock(&fi->i_gc_rwsem[rw])) { iocb->ki_hint = hint; err = -EAGAIN; goto out; } - down_read(&F2FS_I(inode)->i_gc_rwsem[rw]); + if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) { + up_read(&fi->i_gc_rwsem[rw]); + iocb->ki_hint = hint; + err = -EAGAIN; + goto out; + } + } else { + down_read(&fi->i_gc_rwsem[rw]); + if (do_opu) + down_read(&fi->i_gc_rwsem[READ]); } err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio); - up_read(&F2FS_I(inode)->i_gc_rwsem[rw]); + + if (do_opu) + up_read(&fi->i_gc_rwsem[READ]); + + up_read(&fi->i_gc_rwsem[rw]); if (rw == WRITE) { if (whint_mode == WHINT_MODE_OFF) @@ -2517,7 +2607,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (err > 0) { f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO, err); - set_inode_flag(inode, FI_UPDATE_WRITE); + if (!do_opu) + set_inode_flag(inode, FI_UPDATE_WRITE); } else if (err < 0) { f2fs_write_failed(mapping, offset + count); } @@ -2550,6 +2641,8 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, } } + clear_cold_data(page); + /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); @@ -2568,6 +2661,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) if (IS_ATOMIC_WRITTEN_PAGE(page)) return 0; + clear_cold_data(page); set_page_private(page, 0); ClearPagePrivate(page); return 1; @@ -2583,10 +2677,6 @@ static int f2fs_set_data_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); - /* don't remain PG_checked flag which was set during GC */ - if (is_cold_data(page)) - clear_cold_data(page); - if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) { if (!IS_ATOMIC_WRITTEN_PAGE(page)) { f2fs_register_inmem_page(inode, page); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 214a968962a1..139b4d5c83d5 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs debugging statistics * @@ -5,10 +6,6 @@ * http://www.samsung.com/ * Copyright (c) 2012 Linux Foundation * Copyright (c) 2012 Greg Kroah-Hartman <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -58,6 +55,9 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt); si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA); si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA); + si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA); + si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE); + si->nr_rd_meta = get_pages(sbi, F2FS_RD_META); if (SM_I(sbi) && SM_I(sbi)->fcc_info) { si->nr_flushed = atomic_read(&SM_I(sbi)->fcc_info->issued_flush); @@ -104,6 +104,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->avail_nids = NM_I(sbi)->available_nids; si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID]; si->bg_gc = sbi->bg_gc; + si->io_skip_bggc = sbi->io_skip_bggc; + si->other_skip_bggc = sbi->other_skip_bggc; si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC]; si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC]; si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) @@ -121,6 +123,9 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]); } + for (i = META_CP; i < META_MAX; i++) + si->meta_count[i] = atomic_read(&sbi->meta_count[i]); + for (i = 0; i < 2; i++) { si->segment_count[i] = sbi->segment_count[i]; si->block_count[i] = sbi->block_count[i]; @@ -190,8 +195,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); - if (f2fs_discard_en(sbi)) - si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (sbi->segs_per_sec > 1) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); @@ -271,7 +275,8 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n", si->sbi->sb->s_bdev, i++, f2fs_readonly(si->sbi->sb) ? "RO": "RW", - f2fs_cp_error(si->sbi) ? "Error": "Good"); + is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ? + "Disabled": (f2fs_cp_error(si->sbi) ? "Error": "Good")); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", @@ -333,6 +338,13 @@ static int stat_show(struct seq_file *s, void *v) si->prefree_count, si->free_segs, si->free_secs); seq_printf(s, "CP calls: %d (BG: %d)\n", si->cp_count, si->bg_cp_count); + seq_printf(s, " - cp blocks : %u\n", si->meta_count[META_CP]); + seq_printf(s, " - sit blocks : %u\n", + si->meta_count[META_SIT]); + seq_printf(s, " - nat blocks : %u\n", + si->meta_count[META_NAT]); + seq_printf(s, " - ssa blocks : %u\n", + si->meta_count[META_SSA]); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); seq_printf(s, " - data segments : %d (%d)\n", @@ -349,6 +361,8 @@ static int stat_show(struct seq_file *s, void *v) si->skipped_atomic_files[BG_GC] + si->skipped_atomic_files[FG_GC], si->skipped_atomic_files[BG_GC]); + seq_printf(s, "BG skip : IO: %u, Other: %u\n", + si->io_skip_bggc, si->other_skip_bggc); seq_puts(s, "\nExtent Cache:\n"); seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", si->hit_largest, si->hit_cached, @@ -360,7 +374,9 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", si->ext_tree, si->zombie_tree, si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); - seq_printf(s, " - IO (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), " + seq_printf(s, " - IO_R (Data: %4d, Node: %4d, Meta: %4d\n", + si->nr_rd_data, si->nr_rd_node, si->nr_rd_meta); + seq_printf(s, " - IO_W (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), " "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n", si->nr_wb_cp_data, si->nr_wb_data, si->nr_flushing, si->nr_flushed, @@ -445,6 +461,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_stat_info *si; + int i; si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL); if (!si) @@ -470,6 +487,8 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) atomic_set(&sbi->inline_inode, 0); atomic_set(&sbi->inline_dir, 0); atomic_set(&sbi->inplace_count, 0); + for (i = META_CP; i < META_MAX; i++) + atomic_set(&sbi->meta_count[i], 0); atomic_set(&sbi->aw_cnt, 0); atomic_set(&sbi->vw_cnt, 0); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index ecc3a4e2be96..2ef84b4590ea 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/dir.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -658,9 +655,9 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) f2fs_put_page(page, 1); clear_inode_flag(inode, FI_NEW_INODE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); fail: up_write(&F2FS_I(inode)->i_sem); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return err; } @@ -733,6 +730,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); + clear_cold_data(page); inode_dec_dirty_pages(dir); f2fs_remove_dirty_inode(dir); } @@ -784,9 +782,15 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, struct f2fs_dir_entry *de = NULL; struct fscrypt_str de_name = FSTR_INIT(NULL, 0); struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode); + struct blk_plug plug; + bool readdir_ra = sbi->readdir_ra == 1; + int err = 0; bit_pos = ((unsigned long)ctx->pos % d->max); + if (readdir_ra) + blk_start_plug(&plug); + while (bit_pos < d->max) { bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos); if (bit_pos >= d->max) @@ -806,29 +810,33 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, if (f2fs_encrypted_inode(d->inode)) { int save_len = fstr->len; - int err; err = fscrypt_fname_disk_to_usr(d->inode, (u32)de->hash_code, 0, &de_name, fstr); if (err) - return err; + goto out; de_name = *fstr; fstr->len = save_len; } if (!dir_emit(ctx, de_name.name, de_name.len, - le32_to_cpu(de->ino), d_type)) - return 1; + le32_to_cpu(de->ino), d_type)) { + err = 1; + goto out; + } - if (sbi->readdir_ra == 1) + if (readdir_ra) f2fs_ra_node_page(sbi, le32_to_cpu(de->ino)); bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); ctx->pos = start_pos + bit_pos; } - return 0; +out: + if (readdir_ra) + blk_finish_plug(&plug); + return err; } static int f2fs_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 231b77ef5a53..1cb0fcc67d2d 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs extent cache support * @@ -5,10 +6,6 @@ * Copyright (c) 2015 Samsung Electronics * Authors: Jaegeuk Kim <[email protected]> * Chao Yu <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -30,10 +27,10 @@ static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re, return NULL; } -static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root, +static struct rb_entry *__lookup_rb_tree_slow(struct rb_root_cached *root, unsigned int ofs) { - struct rb_node *node = root->rb_node; + struct rb_node *node = root->rb_root.rb_node; struct rb_entry *re; while (node) { @@ -49,7 +46,7 @@ static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root, return NULL; } -struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs) { struct rb_entry *re; @@ -62,22 +59,25 @@ struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root, } struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, - struct rb_root *root, struct rb_node **parent, - unsigned int ofs) + struct rb_root_cached *root, + struct rb_node **parent, + unsigned int ofs, bool *leftmost) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_entry *re; while (*p) { *parent = *p; re = rb_entry(*parent, struct rb_entry, rb_node); - if (ofs < re->ofs) + if (ofs < re->ofs) { p = &(*p)->rb_left; - else if (ofs >= re->ofs + re->len) + } else if (ofs >= re->ofs + re->len) { p = &(*p)->rb_right; - else + *leftmost = false; + } else { f2fs_bug_on(sbi, 1); + } } return p; @@ -92,16 +92,16 @@ struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, * in order to simpfy the insertion after. * tree must stay unchanged between lookup and insertion. */ -struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs, struct rb_entry **prev_entry, struct rb_entry **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent, - bool force) + bool force, bool *leftmost) { - struct rb_node **pnode = &root->rb_node; + struct rb_node **pnode = &root->rb_root.rb_node; struct rb_node *parent = NULL, *tmp_node; struct rb_entry *re = cached_re; @@ -110,7 +110,7 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root, *prev_entry = NULL; *next_entry = NULL; - if (RB_EMPTY_ROOT(root)) + if (RB_EMPTY_ROOT(&root->rb_root)) return NULL; if (re) { @@ -118,16 +118,22 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root, goto lookup_neighbors; } + if (leftmost) + *leftmost = true; + while (*pnode) { parent = *pnode; re = rb_entry(*pnode, struct rb_entry, rb_node); - if (ofs < re->ofs) + if (ofs < re->ofs) { pnode = &(*pnode)->rb_left; - else if (ofs >= re->ofs + re->len) + } else if (ofs >= re->ofs + re->len) { pnode = &(*pnode)->rb_right; - else + if (leftmost) + *leftmost = false; + } else { goto lookup_neighbors; + } } *insert_p = pnode; @@ -160,10 +166,10 @@ lookup_neighbors: } bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, - struct rb_root *root) + struct rb_root_cached *root) { #ifdef CONFIG_F2FS_CHECK_FS - struct rb_node *cur = rb_first(root), *next; + struct rb_node *cur = rb_first_cached(root), *next; struct rb_entry *cur_re, *next_re; if (!cur) @@ -196,7 +202,8 @@ static struct kmem_cache *extent_node_slab; static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, - struct rb_node *parent, struct rb_node **p) + struct rb_node *parent, struct rb_node **p, + bool leftmost) { struct extent_node *en; @@ -209,7 +216,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, en->et = et; rb_link_node(&en->rb_node, parent, p); - rb_insert_color(&en->rb_node, &et->root); + rb_insert_color_cached(&en->rb_node, &et->root, leftmost); atomic_inc(&et->node_cnt); atomic_inc(&sbi->total_ext_node); return en; @@ -218,7 +225,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, static void __detach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_node *en) { - rb_erase(&en->rb_node, &et->root); + rb_erase_cached(&en->rb_node, &et->root); atomic_dec(&et->node_cnt); atomic_dec(&sbi->total_ext_node); @@ -257,7 +264,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode) f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et); memset(et, 0, sizeof(struct extent_tree)); et->ino = ino; - et->root = RB_ROOT; + et->root = RB_ROOT_CACHED; et->cached_en = NULL; rwlock_init(&et->lock); INIT_LIST_HEAD(&et->list); @@ -278,10 +285,10 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode) static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei) { - struct rb_node **p = &et->root.rb_node; + struct rb_node **p = &et->root.rb_root.rb_node; struct extent_node *en; - en = __attach_extent_node(sbi, et, ei, NULL, p); + en = __attach_extent_node(sbi, et, ei, NULL, p, true); if (!en) return NULL; @@ -297,7 +304,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, struct extent_node *en; unsigned int count = atomic_read(&et->node_cnt); - node = rb_first(&et->root); + node = rb_first_cached(&et->root); while (node) { next = rb_next(node); en = rb_entry(node, struct extent_node, rb_node); @@ -308,14 +315,13 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, return count - atomic_read(&et->node_cnt); } -static void __drop_largest_extent(struct inode *inode, +static void __drop_largest_extent(struct extent_tree *et, pgoff_t fofs, unsigned int len) { - struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest; - - if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) { - largest->len = 0; - f2fs_mark_inode_dirty_sync(inode, true); + if (fofs < et->largest.fofs + et->largest.len && + fofs + len > et->largest.fofs) { + et->largest.len = 0; + et->largest_updated = true; } } @@ -416,12 +422,11 @@ out: return ret; } -static struct extent_node *__try_merge_extent_node(struct inode *inode, +static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct extent_node *prev_ex, struct extent_node *next_ex) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_node *en = NULL; if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) { @@ -443,7 +448,7 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode, if (!en) return NULL; - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); spin_lock(&sbi->extent_lock); if (!list_empty(&en->list)) { @@ -454,12 +459,12 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode, return en; } -static struct extent_node *__insert_extent_tree(struct inode *inode, +static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct rb_node **insert_p, - struct rb_node *insert_parent) + struct rb_node *insert_parent, + bool leftmost) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct rb_node **p; struct rb_node *parent = NULL; struct extent_node *en = NULL; @@ -470,13 +475,16 @@ static struct extent_node *__insert_extent_tree(struct inode *inode, goto do_insert; } - p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs); + leftmost = true; + + p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent, + ei->fofs, &leftmost); do_insert: - en = __attach_extent_node(sbi, et, ei, parent, p); + en = __attach_extent_node(sbi, et, ei, parent, p, leftmost); if (!en) return NULL; - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); /* update in global extent list */ spin_lock(&sbi->extent_lock); @@ -497,6 +505,8 @@ static void f2fs_update_extent_tree_range(struct inode *inode, struct rb_node **insert_p = NULL, *insert_parent = NULL; unsigned int end = fofs + len; unsigned int pos = (unsigned int)fofs; + bool updated = false; + bool leftmost; if (!et) return; @@ -517,14 +527,15 @@ static void f2fs_update_extent_tree_range(struct inode *inode, * drop largest extent before lookup, in case it's already * been shrunk from extent tree */ - __drop_largest_extent(inode, fofs, len); + __drop_largest_extent(et, fofs, len); /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root, (struct rb_entry *)et->cached_en, fofs, (struct rb_entry **)&prev_en, (struct rb_entry **)&next_en, - &insert_p, &insert_parent, false); + &insert_p, &insert_parent, false, + &leftmost); if (!en) en = next_en; @@ -550,8 +561,8 @@ static void f2fs_update_extent_tree_range(struct inode *inode, set_extent_info(&ei, end, end - dei.fofs + dei.blk, org_end - end); - en1 = __insert_extent_tree(inode, et, &ei, - NULL, NULL); + en1 = __insert_extent_tree(sbi, et, &ei, + NULL, NULL, true); next_en = en1; } else { en->ei.fofs = end; @@ -570,7 +581,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, } if (parts) - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); else __release_extent_node(sbi, et, en); @@ -590,15 +601,16 @@ static void f2fs_update_extent_tree_range(struct inode *inode, if (blkaddr) { set_extent_info(&ei, fofs, blkaddr, len); - if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en)) - __insert_extent_tree(inode, et, &ei, - insert_p, insert_parent); + if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en)) + __insert_extent_tree(sbi, et, &ei, + insert_p, insert_parent, leftmost); /* give up extent_cache, if split and small updates happen */ if (dei.len >= 1 && prev.len < F2FS_MIN_EXTENT_LEN && et->largest.len < F2FS_MIN_EXTENT_LEN) { - __drop_largest_extent(inode, 0, UINT_MAX); + et->largest.len = 0; + et->largest_updated = true; set_inode_flag(inode, FI_NO_EXTENT); } } @@ -606,7 +618,15 @@ static void f2fs_update_extent_tree_range(struct inode *inode, if (is_inode_flag_set(inode, FI_NO_EXTENT)) __free_extent_tree(sbi, et); + if (et->largest_updated) { + et->largest_updated = false; + updated = true; + } + write_unlock(&et->lock); + + if (updated) + f2fs_mark_inode_dirty_sync(inode, true); } unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) @@ -705,6 +725,7 @@ void f2fs_drop_extent_tree(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree; + bool updated = false; if (!f2fs_may_extent_tree(inode)) return; @@ -713,8 +734,13 @@ void f2fs_drop_extent_tree(struct inode *inode) write_lock(&et->lock); __free_extent_tree(sbi, et); - __drop_largest_extent(inode, 0, UINT_MAX); + if (et->largest.len) { + et->largest.len = 0; + updated = true; + } write_unlock(&et->lock); + if (updated) + f2fs_mark_inode_dirty_sync(inode, true); } void f2fs_destroy_extent_tree(struct inode *inode) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index abf925664d9c..56204a8f8a12 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1,16 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/f2fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_H #define _LINUX_F2FS_H +#include <linux/uio.h> #include <linux/types.h> #include <linux/page-flags.h> #include <linux/buffer_head.h> @@ -53,9 +51,10 @@ enum { FAULT_DIR_DEPTH, FAULT_EVICT_INODE, FAULT_TRUNCATE, - FAULT_IO, + FAULT_READ_IO, FAULT_CHECKPOINT, FAULT_DISCARD, + FAULT_WRITE_IO, FAULT_MAX, }; @@ -100,6 +99,7 @@ extern char *f2fs_fault_name[FAULT_MAX]; #define F2FS_MOUNT_QUOTA 0x00400000 #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 #define F2FS_MOUNT_RESERVE_ROOT 0x01000000 +#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) @@ -150,6 +150,7 @@ struct f2fs_mount_info { #define F2FS_FEATURE_INODE_CRTIME 0x0100 #define F2FS_FEATURE_LOST_FOUND 0x0200 #define F2FS_FEATURE_VERITY 0x0400 /* reserved */ +#define F2FS_FEATURE_SB_CHKSUM 0x0800 #define F2FS_HAS_FEATURE(sb, mask) \ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) @@ -178,6 +179,7 @@ enum { #define CP_RECOVERY 0x00000008 #define CP_DISCARD 0x00000010 #define CP_TRIMMED 0x00000020 +#define CP_PAUSE 0x00000040 #define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ @@ -187,6 +189,7 @@ enum { #define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_INTERVAL 5 /* 5 secs */ struct cp_control { int reason; @@ -203,6 +206,7 @@ enum { META_NAT, META_SIT, META_SSA, + META_MAX, META_POR, DATA_GENERIC, META_GENERIC, @@ -324,7 +328,7 @@ struct discard_cmd_control { atomic_t issued_discard; /* # of issued discard */ atomic_t issing_discard; /* # of issing discard */ atomic_t discard_cmd_cnt; /* # of cached cmd count */ - struct rb_root root; /* root of discard rb-tree */ + struct rb_root_cached root; /* root of discard rb-tree */ bool rbtree_check; /* config for consistence check */ }; @@ -527,6 +531,9 @@ enum { #define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */ +/* maximum retry quota flush count */ +#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 + #define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ @@ -566,12 +573,13 @@ struct extent_node { struct extent_tree { nid_t ino; /* inode number */ - struct rb_root root; /* root of extent info rb-tree */ + struct rb_root_cached root; /* root of extent info rb-tree */ struct extent_node *cached_en; /* recently accessed extent node */ struct extent_info largest; /* largested extent info */ struct list_head list; /* to be used by sbi->zombie_list */ rwlock_t lock; /* protect extent info rb-tree */ atomic_t node_cnt; /* # of extent node in rb-tree*/ + bool largest_updated; /* largest extent updated */ }; /* @@ -600,6 +608,7 @@ enum { F2FS_GET_BLOCK_DEFAULT, F2FS_GET_BLOCK_FIEMAP, F2FS_GET_BLOCK_BMAP, + F2FS_GET_BLOCK_DIO, F2FS_GET_BLOCK_PRE_DIO, F2FS_GET_BLOCK_PRE_AIO, F2FS_GET_BLOCK_PRECACHE, @@ -754,12 +763,12 @@ static inline bool __is_front_mergeable(struct extent_info *cur, } extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); -static inline void __try_update_largest_extent(struct inode *inode, - struct extent_tree *et, struct extent_node *en) +static inline void __try_update_largest_extent(struct extent_tree *et, + struct extent_node *en) { if (en->ei.len > et->largest.len) { et->largest = en->ei; - f2fs_mark_inode_dirty_sync(inode, true); + et->largest_updated = true; } } @@ -944,6 +953,9 @@ enum count_type { F2FS_DIRTY_IMETA, F2FS_WB_CP_DATA, F2FS_WB_DATA, + F2FS_RD_DATA, + F2FS_RD_NODE, + F2FS_RD_META, NR_COUNT_TYPE, }; @@ -1088,11 +1100,19 @@ enum { SBI_NEED_SB_WRITE, /* need to recover superblock */ SBI_NEED_CP, /* need to checkpoint */ SBI_IS_SHUTDOWN, /* shutdown by ioctl */ + SBI_IS_RECOVERED, /* recovered orphan/data */ + SBI_CP_DISABLED, /* CP was disabled last mount */ + SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ + SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ + SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ }; enum { CP_TIME, REQ_TIME, + DISCARD_TIME, + GC_TIME, + DISABLE_TIME, MAX_TIME, }; @@ -1209,7 +1229,6 @@ struct f2fs_sb_info { unsigned int total_valid_node_count; /* valid node block count */ loff_t max_file_blocks; /* max block index of file */ int dir_level; /* directory level */ - unsigned int trigger_ssr_threshold; /* threshold to trigger ssr */ int readdir_ra; /* readahead inode in readdir */ block_t user_block_count; /* # of user blocks */ @@ -1219,6 +1238,9 @@ struct f2fs_sb_info { block_t reserved_blocks; /* configurable reserved blocks */ block_t current_reserved_blocks; /* current reserved blocks */ + /* Additional tracking for no checkpoint mode */ + block_t unusable_block_count; /* # of blocks saved by last cp */ + unsigned int nquota_files; /* # of quota sysfile */ u32 s_next_generation; /* for NFS support */ @@ -1257,6 +1279,7 @@ struct f2fs_sb_info { */ #ifdef CONFIG_F2FS_STAT_FS struct f2fs_stat_info *stat_info; /* FS status information */ + atomic_t meta_count[META_MAX]; /* # of meta blocks */ unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ atomic_t inplace_count; /* # of inplace update */ @@ -1272,6 +1295,8 @@ struct f2fs_sb_info { atomic_t max_aw_cnt; /* max # of atomic writes */ atomic_t max_vw_cnt; /* max # of volatile writes */ int bg_gc; /* background gc calls */ + unsigned int io_skip_bggc; /* skip background gc for in-flight IO */ + unsigned int other_skip_bggc; /* skip background gc for other reasons */ unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ #endif spinlock_t stat_lock; /* lock for stat operations */ @@ -1306,9 +1331,9 @@ struct f2fs_sb_info { }; #ifdef CONFIG_F2FS_FAULT_INJECTION -#define f2fs_show_injection_info(type) \ - printk("%sF2FS-fs : inject %s in %s of %pF\n", \ - KERN_INFO, f2fs_fault_name[type], \ +#define f2fs_show_injection_info(type) \ + printk_ratelimited("%sF2FS-fs : inject %s in %s of %pF\n", \ + KERN_INFO, f2fs_fault_name[type], \ __func__, __builtin_return_address(0)) static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) { @@ -1344,7 +1369,15 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) { - sbi->last_time[type] = jiffies; + unsigned long now = jiffies; + + sbi->last_time[type] = now; + + /* DISCARD_TIME and GC_TIME are based on REQ_TIME */ + if (type == REQ_TIME) { + sbi->last_time[DISCARD_TIME] = now; + sbi->last_time[GC_TIME] = now; + } } static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) @@ -1354,16 +1387,18 @@ static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) return time_after(jiffies, sbi->last_time[type] + interval); } -static inline bool is_idle(struct f2fs_sb_info *sbi) +static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, + int type) { - struct block_device *bdev = sbi->sb->s_bdev; - struct request_queue *q = bdev_get_queue(bdev); - struct request_list *rl = &q->root_rl; + unsigned long interval = sbi->interval_time[type] * HZ; + unsigned int wait_ms = 0; + long delta; - if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC]) - return false; + delta = (sbi->last_time[type] + interval) - jiffies; + if (delta > 0) + wait_ms = jiffies_to_msecs(delta); - return f2fs_time_over(sbi, REQ_TIME); + return wait_ms; } /* @@ -1704,7 +1739,8 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, true)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; - + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + avail_user_block_count -= sbi->unusable_block_count; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) @@ -1755,7 +1791,9 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) atomic_inc(&sbi->nr_pages[count_type]); if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES || - count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA) + count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA || + count_type == F2FS_RD_DATA || count_type == F2FS_RD_NODE || + count_type == F2FS_RD_META) return; set_sbi_flag(sbi, SBI_IS_DIRTY); @@ -1891,12 +1929,18 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, { block_t valid_block_count; unsigned int valid_node_count; - bool quota = inode && !is_inode; + int err; - if (quota) { - int ret = dquot_reserve_block(inode, 1); - if (ret) - return ret; + if (is_inode) { + if (inode) { + err = dquot_alloc_inode(inode); + if (err) + return err; + } + } else { + err = dquot_reserve_block(inode, 1); + if (err) + return err; } if (time_to_inject(sbi, FAULT_BLOCK)) { @@ -1911,6 +1955,8 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, false)) valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + valid_block_count += sbi->unusable_block_count; if (unlikely(valid_block_count > sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); @@ -1938,8 +1984,12 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, return 0; enospc: - if (quota) + if (is_inode) { + if (inode) + dquot_free_inode(inode); + } else { dquot_release_reservation_block(inode, 1); + } return -ENOSPC; } @@ -1960,7 +2010,9 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, spin_unlock(&sbi->stat_lock); - if (!is_inode) + if (is_inode) + dquot_free_inode(inode); + else f2fs_i_blocks_write(inode, 1, false, true); } @@ -2090,6 +2142,15 @@ static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, return bio_alloc(GFP_KERNEL, npages); } +static inline bool is_idle(struct f2fs_sb_info *sbi, int type) +{ + if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || + get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || + get_pages(sbi, F2FS_WB_CP_DATA)) + return false; + return f2fs_time_over(sbi, type); +} + static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { @@ -2739,7 +2800,8 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void f2fs_truncate_data_blocks(struct dnode_of_data *dn); -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, + bool buf_write); int f2fs_truncate(struct inode *inode); int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); @@ -2749,6 +2811,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); int f2fs_precache_extents(struct inode *inode); long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid); int f2fs_pin_file_control(struct inode *inode, bool inc); /* @@ -2827,6 +2890,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); +int f2fs_quota_sync(struct super_block *sb, int type); void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); @@ -2869,7 +2933,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs); void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); struct page *f2fs_get_node_page_ra(struct page *parent, int start); -void f2fs_move_node_page(struct page *node_page, int gc_type); +int f2fs_move_node_page(struct page *node_page, int gc_type); int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic, unsigned int *seq_id); @@ -2886,7 +2950,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page); int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum); -void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); +int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); int f2fs_build_node_manager(struct f2fs_sb_info *sbi); void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_node_manager_caches(void); @@ -2914,6 +2978,8 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi); void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); @@ -2942,7 +3008,9 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, struct f2fs_io_info *fio, bool add_list); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered); -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr); +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len); void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, @@ -3002,8 +3070,8 @@ int f2fs_init_post_read_processing(void); void f2fs_destroy_post_read_processing(void); void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type); + struct inode *inode, struct page *page, + nid_t ino, enum page_type type); void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); void f2fs_submit_page_write(struct f2fs_io_info *fio); @@ -3025,6 +3093,7 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size); int f2fs_do_write_data_page(struct f2fs_io_info *fio); +void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock); int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, @@ -3077,6 +3146,8 @@ struct f2fs_stat_info { int free_nids, avail_nids, alloc_nids; int total_count, utilization; int bg_gc, nr_wb_cp_data, nr_wb_data; + int nr_rd_data, nr_rd_node, nr_rd_meta; + unsigned int io_skip_bggc, other_skip_bggc; int nr_flushing, nr_flushed, flush_list_empty; int nr_discarding, nr_discarded; int nr_discard_cmd; @@ -3098,6 +3169,7 @@ struct f2fs_stat_info { int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; + unsigned int meta_count[META_MAX]; unsigned int segment_count[2]; unsigned int block_count[2]; unsigned int inplace_count; @@ -3113,6 +3185,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) #define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++) #define stat_inc_call_count(si) ((si)->call_count++) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) +#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++) +#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++) #define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) #define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) #define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) @@ -3149,6 +3223,17 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) if (f2fs_has_inline_dentry(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ } while (0) +#define stat_inc_meta_count(sbi, blkaddr) \ + do { \ + if (blkaddr < SIT_I(sbi)->sit_base_addr) \ + atomic_inc(&(sbi)->meta_count[META_CP]); \ + else if (blkaddr < NM_I(sbi)->nat_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_SIT]); \ + else if (blkaddr < SM_I(sbi)->ssa_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_NAT]); \ + else if (blkaddr < SM_I(sbi)->main_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_SSA]); \ + } while (0) #define stat_inc_seg_type(sbi, curseg) \ ((sbi)->segment_count[(curseg)->alloc_type]++) #define stat_inc_block_count(sbi, curseg) \ @@ -3218,6 +3303,8 @@ void f2fs_destroy_root_stats(void); #define stat_inc_bg_cp_count(si) do { } while (0) #define stat_inc_call_count(si) do { } while (0) #define stat_inc_bggc_count(si) do { } while (0) +#define stat_io_skip_bggc_count(sbi) do { } while (0) +#define stat_other_skip_bggc_count(sbi) do { } while (0) #define stat_inc_dirty_inode(sbi, type) do { } while (0) #define stat_dec_dirty_inode(sbi, type) do { } while (0) #define stat_inc_total_hit(sb) do { } while (0) @@ -3236,6 +3323,7 @@ void f2fs_destroy_root_stats(void); #define stat_inc_volatile_write(inode) do { } while (0) #define stat_dec_volatile_write(inode) do { } while (0) #define stat_update_max_volatile_write(inode) do { } while (0) +#define stat_inc_meta_count(sbi, blkaddr) do { } while (0) #define stat_inc_seg_type(sbi, curseg) do { } while (0) #define stat_inc_block_count(sbi, curseg) do { } while (0) #define stat_inc_inplace_blocks(sbi) do { } while (0) @@ -3305,18 +3393,19 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi); /* * extent_cache.c */ -struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs); struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, - struct rb_root *root, struct rb_node **parent, - unsigned int ofs); -struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root, + struct rb_root_cached *root, + struct rb_node **parent, + unsigned int ofs, bool *leftmost); +struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs, struct rb_entry **prev_entry, struct rb_entry **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent, - bool force); + bool force, bool *leftmost); bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, - struct rb_root *root); + struct rb_root_cached *root); unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink); bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext); void f2fs_drop_extent_tree(struct inode *inode); @@ -3356,7 +3445,7 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION file_set_encrypt(inode); - inode->i_flags |= S_ENCRYPTED; + f2fs_set_inode_flags(inode); #endif } @@ -3384,6 +3473,7 @@ F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); +F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); #ifdef CONFIG_BLK_DEV_ZONED static inline int get_blkz_type(struct f2fs_sb_info *sbi, @@ -3399,11 +3489,20 @@ static inline int get_blkz_type(struct f2fs_sb_info *sbi, } #endif -static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi) +static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) { - struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); + return f2fs_sb_has_blkzoned(sbi->sb); +} - return blk_queue_discard(q) || f2fs_sb_has_blkzoned(sbi->sb); +static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) +{ + return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)); +} + +static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) +{ + return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) || + f2fs_hw_should_discard(sbi); } static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) @@ -3432,11 +3531,50 @@ static inline bool f2fs_may_encrypt(struct inode *inode) #endif } -static inline bool f2fs_force_buffered_io(struct inode *inode, int rw) +static inline int block_unaligned_IO(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) { - return (f2fs_post_read_required(inode) || - (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || - F2FS_I_SB(inode)->s_ndevs); + unsigned int i_blkbits = READ_ONCE(inode->i_blkbits); + unsigned int blocksize_mask = (1 << i_blkbits) - 1; + loff_t offset = iocb->ki_pos; + unsigned long align = offset | iov_iter_alignment(iter); + + return align & blocksize_mask; +} + +static inline int allow_outplace_dio(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int rw = iov_iter_rw(iter); + + return (test_opt(sbi, LFS) && (rw == WRITE) && + !block_unaligned_IO(inode, iocb, iter)); +} + +static inline bool f2fs_force_buffered_io(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int rw = iov_iter_rw(iter); + + if (f2fs_post_read_required(inode)) + return true; + if (sbi->s_ndevs) + return true; + /* + * for blkzoned device, fallback direct IO to buffered IO, so + * all IOs can be serialized by log-structured write. + */ + if (f2fs_sb_has_blkzoned(sbi->sb)) + return true; + if (test_opt(sbi, LFS) && (rw == WRITE) && + block_unaligned_IO(inode, iocb, iter)) + return true; + if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) + return true; + + return false; } #ifdef CONFIG_F2FS_FAULT_INJECTION @@ -3447,3 +3585,16 @@ extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, #endif #endif + +static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) +{ +#ifdef CONFIG_QUOTA + if (f2fs_sb_has_quota_ino(sbi->sb)) + return true; + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) + return true; +#endif + return false; +} diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5474aaa274b9..88b124677189 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/file.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -50,7 +47,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct dnode_of_data dn; + struct dnode_of_data dn = { .node_changed = false }; int err; if (unlikely(f2fs_cp_error(sbi))) { @@ -62,19 +59,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); - /* block allocation */ - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = f2fs_reserve_block(&dn, page->index); - if (err) { - f2fs_unlock_op(sbi); - goto out; - } - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - - f2fs_balance_fs(sbi, dn.node_changed); - file_update_time(vmf->vma->vm_file); down_read(&F2FS_I(inode)->i_mmap_sem); lock_page(page); @@ -86,11 +70,28 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) goto out_sem; } + /* block allocation */ + __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_get_block(&dn, page->index); + f2fs_put_dnode(&dn); + __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + if (err) { + unlock_page(page); + goto out_sem; + } + + /* fill the page */ + f2fs_wait_on_page_writeback(page, DATA, false); + + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); + /* * check to see if the page is mapped already (no holes) */ if (PageMappedToDisk(page)) - goto mapped; + goto out_sem; /* page is wholly or partially inside EOF */ if (((loff_t)(page->index + 1) << PAGE_SHIFT) > @@ -105,21 +106,15 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) SetPageUptodate(page); f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE); + f2fs_update_time(sbi, REQ_TIME); trace_f2fs_vm_page_mkwrite(page, DATA); -mapped: - /* fill the page */ - f2fs_wait_on_page_writeback(page, DATA, false); - - /* wait for GCed page writeback via META_MAPPING */ - if (f2fs_post_read_required(inode)) - f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr); - out_sem: up_read(&F2FS_I(inode)->i_mmap_sem); -out: + + f2fs_balance_fs(sbi, dn.node_changed); + sb_end_pagefault(inode->i_sb); - f2fs_update_time(sbi, REQ_TIME); err: return block_page_mkwrite_return(err); } @@ -215,7 +210,8 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, }; unsigned int seq_id = 0; - if (unlikely(f2fs_readonly(inode->i_sb))) + if (unlikely(f2fs_readonly(inode->i_sb) || + is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; trace_f2fs_sync_file_enter(inode); @@ -590,7 +586,8 @@ truncate_out: return 0; } -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, + bool buf_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -598,6 +595,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) int count = 0, err = 0; struct page *ipage; bool truncate_page = false; + int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; trace_f2fs_truncate_blocks_enter(inode, from); @@ -607,7 +605,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) goto free_partial; if (lock) - f2fs_lock_op(sbi); + __do_map_lock(sbi, flag, true); ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { @@ -645,7 +643,7 @@ free_next: err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) - f2fs_unlock_op(sbi); + __do_map_lock(sbi, flag, false); free_partial: /* lastly zero out the first data page */ if (!err) @@ -680,7 +678,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = f2fs_truncate_blocks(inode, i_size_read(inode), true); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); if (err) return err; @@ -789,9 +787,24 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) !uid_eq(attr->ia_uid, inode->i_uid)) || (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { + f2fs_lock_op(F2FS_I_SB(inode)); err = dquot_transfer(inode, attr); - if (err) + if (err) { + set_sbi_flag(F2FS_I_SB(inode), + SBI_QUOTA_NEED_REPAIR); + f2fs_unlock_op(F2FS_I_SB(inode)); return err; + } + /* + * update uid/gid under lock_op(), so that dquot and inode can + * be updated atomically. + */ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (attr->ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + f2fs_mark_inode_dirty_sync(inode, true); + f2fs_unlock_op(F2FS_I_SB(inode)); } if (attr->ia_valid & ATTR_SIZE) { @@ -1246,7 +1259,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true); + ret = f2fs_truncate_blocks(inode, new_size, true, false); up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1431,7 +1444,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); up_write(&F2FS_I(inode)->i_mmap_sem); if (ret) return ret; @@ -1978,7 +1991,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!f2fs_hw_support_discard(F2FS_SB(sb))) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, @@ -2162,6 +2175,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + f2fs_msg(sbi->sb, KERN_INFO, + "Skipping Checkpoint. Checkpoints currently disabled."); + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -2533,6 +2552,9 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg, sizeof(range))) return -EFAULT; @@ -2591,13 +2613,29 @@ static int f2fs_ioc_get_features(struct file *filp, unsigned long arg) } #ifdef CONFIG_QUOTA +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) +{ + struct dquot *transfer_to[MAXQUOTAS] = {}; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct super_block *sb = sbi->sb; + int err = 0; + + transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); + if (!IS_ERR(transfer_to[PRJQUOTA])) { + err = __dquot_transfer(inode, transfer_to); + if (err) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + dqput(transfer_to[PRJQUOTA]); + } + return err; +} + static int f2fs_ioc_setproject(struct file *filp, __u32 projid) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct super_block *sb = sbi->sb; - struct dquot *transfer_to[MAXQUOTAS] = {}; struct page *ipage; kprojid_t kprojid; int err; @@ -2617,53 +2655,45 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) if (projid_eq(kprojid, F2FS_I(inode)->i_projid)) return 0; - err = mnt_want_write_file(filp); - if (err) - return err; - err = -EPERM; - inode_lock(inode); - /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) - goto out_unlock; + return err; ipage = f2fs_get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); - goto out_unlock; - } + if (IS_ERR(ipage)) + return PTR_ERR(ipage); if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize, i_projid)) { err = -EOVERFLOW; f2fs_put_page(ipage, 1); - goto out_unlock; + return err; } f2fs_put_page(ipage, 1); err = dquot_initialize(inode); if (err) - goto out_unlock; + return err; - transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); - if (!IS_ERR(transfer_to[PRJQUOTA])) { - err = __dquot_transfer(inode, transfer_to); - dqput(transfer_to[PRJQUOTA]); - if (err) - goto out_dirty; - } + f2fs_lock_op(sbi); + err = f2fs_transfer_project_quota(inode, kprojid); + if (err) + goto out_unlock; F2FS_I(inode)->i_projid = kprojid; inode->i_ctime = current_time(inode); -out_dirty: f2fs_mark_inode_dirty_sync(inode, true); out_unlock: - inode_unlock(inode); - mnt_drop_write_file(filp); + f2fs_unlock_op(sbi); return err; } #else +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) +{ + return 0; +} + static int f2fs_ioc_setproject(struct file *filp, __u32 projid) { if (projid != F2FS_DEF_PROJID) @@ -2736,6 +2766,30 @@ static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) return 0; } +static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa) +{ + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() == &init_user_ns) + return 0; + + if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid) + return -EINVAL; + + if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) { + if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) + return -EINVAL; + } else { + if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) + return -EINVAL; + } + + return 0; +} + static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -2763,19 +2817,20 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) return err; inode_lock(inode); + err = f2fs_ioctl_check_project(inode, &fa); + if (err) + goto out; flags = (fi->i_flags & ~F2FS_FL_XFLAG_VISIBLE) | (flags & F2FS_FL_XFLAG_VISIBLE); err = __f2fs_ioc_setflags(inode, flags); - inode_unlock(inode); - mnt_drop_write_file(filp); if (err) - return err; + goto out; err = f2fs_ioc_setproject(filp, fa.fsx_projid); - if (err) - return err; - - return 0; +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return err; } int f2fs_pin_file_control(struct inode *inode, bool inc) @@ -2992,7 +3047,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (!f2fs_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)) || f2fs_has_inline_data(inode) || - f2fs_force_buffered_io(inode, WRITE)) { + f2fs_force_buffered_io(inode, + iocb, from)) { clear_inode_flag(inode, FI_NO_PREALLOC); inode_unlock(inode); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5c8d00422237..a07241fb8537 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/module.h> @@ -43,13 +40,16 @@ static int gc_thread_func(void *data) if (gc_th->gc_wake) gc_th->gc_wake = 0; - if (try_to_freeze()) + if (try_to_freeze()) { + stat_other_skip_bggc_count(sbi); continue; + } if (kthread_should_stop()) break; if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) { increase_sleep_time(gc_th, &wait_ms); + stat_other_skip_bggc_count(sbi); continue; } @@ -58,8 +58,10 @@ static int gc_thread_func(void *data) f2fs_stop_checkpoint(sbi, false); } - if (!sb_start_write_trylock(sbi->sb)) + if (!sb_start_write_trylock(sbi->sb)) { + stat_other_skip_bggc_count(sbi); continue; + } /* * [GC triggering condition] @@ -80,12 +82,15 @@ static int gc_thread_func(void *data) goto do_gc; } - if (!mutex_trylock(&sbi->gc_mutex)) + if (!mutex_trylock(&sbi->gc_mutex)) { + stat_other_skip_bggc_count(sbi); goto next; + } - if (!is_idle(sbi)) { + if (!is_idle(sbi, GC_TIME)) { increase_sleep_time(gc_th, &wait_ms); mutex_unlock(&sbi->gc_mutex); + stat_io_skip_bggc_count(sbi); goto next; } @@ -365,6 +370,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (sec_usage_check(sbi, secno)) goto next; + /* Don't touch checkpointed data */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + get_ckpt_valid_blocks(sbi, segno))) + goto next; if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; @@ -464,7 +473,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi, * On validity, copy that node with cold status, otherwise (invalid node) * ignore that. */ -static void gc_node_segment(struct f2fs_sb_info *sbi, +static int gc_node_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, unsigned int segno, int gc_type) { struct f2fs_summary *entry; @@ -472,6 +481,7 @@ static void gc_node_segment(struct f2fs_sb_info *sbi, int off; int phase = 0; bool fggc = (gc_type == FG_GC); + int submitted = 0; start_addr = START_BLOCK(sbi, segno); @@ -485,10 +495,11 @@ next_step: nid_t nid = le32_to_cpu(entry->nid); struct page *node_page; struct node_info ni; + int err; /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) - return; + return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; @@ -525,7 +536,9 @@ next_step: continue; } - f2fs_move_node_page(node_page, gc_type); + err = f2fs_move_node_page(node_page, gc_type); + if (!err && gc_type == FG_GC) + submitted++; stat_inc_node_blk_count(sbi, 1, gc_type); } @@ -534,6 +547,7 @@ next_step: if (fggc) atomic_dec(&sbi->wb_sync_req[NODE]); + return submitted; } /* @@ -669,7 +683,7 @@ put_page: * Move data block via META_MAPPING while keeping locked data page. * This can be used to move blocks, aka LBAs, directly on disk. */ -static void move_data_block(struct inode *inode, block_t bidx, +static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct f2fs_io_info fio = { @@ -688,25 +702,29 @@ static void move_data_block(struct inode *inode, block_t bidx, struct node_info ni; struct page *page, *mpage; block_t newaddr; - int err; + int err = 0; bool lfs_mode = test_opt(fio.sbi, LFS); /* do not read out */ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); if (!page) - return; + return -ENOMEM; - if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { + err = -ENOENT; goto out; + } if (f2fs_is_atomic_file(inode)) { F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; + err = -EAGAIN; goto out; } if (f2fs_is_pinned_file(inode)) { f2fs_pin_file_control(inode, true); + err = -EAGAIN; goto out; } @@ -717,6 +735,7 @@ static void move_data_block(struct inode *inode, block_t bidx, if (unlikely(dn.data_blkaddr == NULL_ADDR)) { ClearPageUptodate(page); + err = -ENOENT; goto put_out; } @@ -799,6 +818,7 @@ write_page: fio.new_blkaddr = newaddr; f2fs_submit_page_write(&fio); if (fio.retry) { + err = -EAGAIN; if (PageWriteback(fio.encrypted_page)) end_page_writeback(fio.encrypted_page); goto put_page_out; @@ -822,34 +842,42 @@ put_out: f2fs_put_dnode(&dn); out: f2fs_put_page(page, 1); + return err; } -static void move_data_page(struct inode *inode, block_t bidx, int gc_type, +static int move_data_page(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct page *page; + int err = 0; page = f2fs_get_lock_data_page(inode, bidx, true); if (IS_ERR(page)) - return; + return PTR_ERR(page); - if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { + err = -ENOENT; goto out; + } if (f2fs_is_atomic_file(inode)) { F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; + err = -EAGAIN; goto out; } if (f2fs_is_pinned_file(inode)) { if (gc_type == FG_GC) f2fs_pin_file_control(inode, true); + err = -EAGAIN; goto out; } if (gc_type == BG_GC) { - if (PageWriteback(page)) + if (PageWriteback(page)) { + err = -EAGAIN; goto out; + } set_page_dirty(page); set_cold_data(page); } else { @@ -867,7 +895,6 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type, .io_type = FS_GC_DATA_IO, }; bool is_dirty = PageDirty(page); - int err; retry: set_page_dirty(page); @@ -892,6 +919,7 @@ retry: } out: f2fs_put_page(page, 1); + return err; } /* @@ -901,7 +929,7 @@ out: * If the parent node is not valid or the data block address is different, * the victim data block is ignored. */ -static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct gc_inode_list *gc_list, unsigned int segno, int gc_type) { struct super_block *sb = sbi->sb; @@ -909,6 +937,7 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t start_addr; int off; int phase = 0; + int submitted = 0; start_addr = START_BLOCK(sbi, segno); @@ -925,7 +954,7 @@ next_step: /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) - return; + return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; @@ -997,6 +1026,7 @@ next_step: if (inode) { struct f2fs_inode_info *fi = F2FS_I(inode); bool locked = false; + int err; if (S_ISREG(inode->i_mode)) { if (!down_write_trylock(&fi->i_gc_rwsem[READ])) @@ -1016,12 +1046,16 @@ next_step: start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; if (f2fs_post_read_required(inode)) - move_data_block(inode, start_bidx, gc_type, - segno, off); + err = move_data_block(inode, start_bidx, + gc_type, segno, off); else - move_data_page(inode, start_bidx, gc_type, + err = move_data_page(inode, start_bidx, gc_type, segno, off); + if (!err && (gc_type == FG_GC || + f2fs_post_read_required(inode))) + submitted++; + if (locked) { up_write(&fi->i_gc_rwsem[WRITE]); up_write(&fi->i_gc_rwsem[READ]); @@ -1033,6 +1067,8 @@ next_step: if (++phase < 5) goto next_step; + + return submitted; } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, @@ -1060,6 +1096,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, int seg_freed = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; + int submitted = 0; /* readahead multi ssa blocks those have contiguous address */ if (sbi->segs_per_sec > 1) @@ -1069,6 +1106,18 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, /* reference all summary page */ while (segno < end_segno) { sum_page = f2fs_get_sum_page(sbi, segno++); + if (IS_ERR(sum_page)) { + int err = PTR_ERR(sum_page); + + end_segno = segno - 1; + for (segno = start_segno; segno < end_segno; segno++) { + sum_page = find_get_page(META_MAPPING(sbi), + GET_SUM_BLOCK(sbi, segno)); + f2fs_put_page(sum_page, 0); + f2fs_put_page(sum_page, 0); + } + return err; + } unlock_page(sum_page); } @@ -1103,10 +1152,11 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, * - lock_page(sum_page) */ if (type == SUM_TYPE_NODE) - gc_node_segment(sbi, sum->entries, segno, gc_type); - else - gc_data_segment(sbi, sum->entries, gc_list, segno, + submitted += gc_node_segment(sbi, sum->entries, segno, gc_type); + else + submitted += gc_data_segment(sbi, sum->entries, gc_list, + segno, gc_type); stat_inc_seg_count(sbi, type, gc_type); @@ -1117,7 +1167,7 @@ next: f2fs_put_page(sum_page, 0); } - if (gc_type == FG_GC) + if (submitted) f2fs_submit_merged_write(sbi, (type == SUM_TYPE_NODE) ? NODE : DATA); @@ -1172,7 +1222,8 @@ gc_more: * threshold, we can make them free by checkpoint. Then, we * secure free segments which doesn't need fggc any more. */ - if (prefree_segments(sbi)) { + if (prefree_segments(sbi) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; @@ -1224,7 +1275,7 @@ gc_more: segno = NULL_SEGNO; goto gc_more; } - if (gc_type == FG_GC) + if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) ret = f2fs_write_checkpoint(sbi, &cpc); } stop: @@ -1244,7 +1295,7 @@ stop: put_gc_inode(&gc_list); - if (sync) + if (sync && !ret) ret = sec_freed ? 0 : -EAGAIN; return ret; } diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index c8619e408009..bbac9d3787bd 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #define GC_THREAD_MIN_WB_PAGES 1 /* * a threshold to determine diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index eb2e031ea887..cc82f142f811 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/hash.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext3/hash.c * * Copyright (C) 2002 by Theodore Ts'o - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/types.h> #include <linux/fs.h> diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 115dc219344b..cb31a719b048 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inline.c * Copyright (c) 2013, Intel Corporation * Authors: Huajun Li <[email protected]> * Haicheng Li <[email protected]> - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -300,7 +298,7 @@ process_inline: clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false)) + if (f2fs_truncate_blocks(inode, 0, false, false)) return false; goto process_inline; } @@ -472,7 +470,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - f2fs_truncate_blocks(dir, 0, false); + f2fs_truncate_blocks(dir, 0, false, false); f2fs_remove_dirty_inode(dir); return err; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 959df2249875..91ceee0ed4c4 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inode.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -368,6 +365,12 @@ static int do_read_inode(struct inode *inode) if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) __recover_inline_status(inode, node_page); + /* try to recover cold bit for non-dir inode */ + if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) { + set_cold_node(node_page, false); + set_page_dirty(node_page); + } + /* get rdev by using inline_info */ __get_inode_rdev(inode, ri); @@ -610,6 +613,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; + if (f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; + /* * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. @@ -648,7 +654,11 @@ void f2fs_evict_inode(struct inode *inode) if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; - dquot_initialize(inode); + err = dquot_initialize(inode); + if (err) { + err = 0; + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO); f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); @@ -680,9 +690,10 @@ retry: goto retry; } - if (err) + if (err) { f2fs_update_inode_page(inode); - dquot_free_inode(inode); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } sb_end_intwrite(inode->i_sb); no_delete: dquot_drop(inode); @@ -691,7 +702,8 @@ no_delete: stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); - if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG))) + if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED))) f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); else f2fs_inode_synced(inode); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 1f67e389169f..99299ede7429 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/namei.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -19,6 +16,7 @@ #include "f2fs.h" #include "node.h" +#include "segment.h" #include "xattr.h" #include "acl.h" #include <trace/events/f2fs.h> @@ -74,10 +72,6 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) goto fail_drop; - err = dquot_alloc_inode(inode); - if (err) - goto fail_drop; - set_inode_flag(inode, FI_NEW_INODE); /* If the directory encrypted, then we should encrypt the inode. */ @@ -124,6 +118,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); + f2fs_set_inode_flags(inode); + trace_f2fs_new_inode(inode, 0); return inode; @@ -184,16 +180,19 @@ static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode * hot_count = sbi->raw_super->hot_ext_count; for (i = 0; i < cold_count + hot_count; i++) { - if (!is_extension_exist(name, extlist[i])) - continue; - if (i < cold_count) - file_set_cold(inode); - else - file_set_hot(inode); - break; + if (is_extension_exist(name, extlist[i])) + break; } up_read(&sbi->sb_lock); + + if (i == cold_count + hot_count) + return; + + if (i < cold_count) + file_set_cold(inode); + else + file_set_hot(inode); } int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, @@ -272,6 +271,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -318,6 +320,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = fscrypt_prepare_link(old_dentry, dir, dentry); if (err) @@ -564,6 +569,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, &disk_link); @@ -693,6 +701,9 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -823,10 +834,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; bool is_old_inline = f2fs_has_inline_dentry(old_dir); - int err = -ENOENT; + int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, @@ -847,6 +861,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -983,6 +998,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); + + f2fs_update_time(sbi, REQ_TIME); return 0; put_out_dir: @@ -1012,10 +1029,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL; struct f2fs_dir_entry *old_entry, *new_entry; int old_nlink = 0, new_nlink = 0; - int err = -ENOENT; + int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, @@ -1033,6 +1053,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto out; + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -1136,6 +1157,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); + + f2fs_update_time(sbi, REQ_TIME); return 0; out_new_dir: if (new_dir_entry) { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index dd2e45a661aa..2b34206486d8 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -129,6 +126,8 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) /* get current nat block page with lock */ src_page = get_current_nat_page(sbi, nid); + if (IS_ERR(src_page)) + return src_page; dst_page = f2fs_grab_meta_page(sbi, dst_off); f2fs_bug_on(sbi, PageDirty(src_page)); @@ -1542,8 +1541,10 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, } if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + up_read(&sbi->node_write); goto redirty_out; + } if (atomic && !test_opt(sbi, NOBARRIER)) fio.op_flags |= REQ_PREFLUSH | REQ_FUA; @@ -1564,8 +1565,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, up_read(&sbi->node_write); if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0, - page->index, NODE); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, NODE); submitted = NULL; } @@ -1587,8 +1587,10 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } -void f2fs_move_node_page(struct page *node_page, int gc_type) +int f2fs_move_node_page(struct page *node_page, int gc_type) { + int err = 0; + if (gc_type == FG_GC) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, @@ -1600,12 +1602,16 @@ void f2fs_move_node_page(struct page *node_page, int gc_type) f2fs_wait_on_page_writeback(node_page, NODE, true); f2fs_bug_on(F2FS_P_SB(node_page), PageWriteback(node_page)); - if (!clear_page_dirty_for_io(node_page)) + if (!clear_page_dirty_for_io(node_page)) { + err = -EAGAIN; goto out_page; + } if (__write_node_page(node_page, false, NULL, - &wbc, false, FS_GC_NODE_IO, NULL)) + &wbc, false, FS_GC_NODE_IO, NULL)) { + err = -EAGAIN; unlock_page(node_page); + } goto release_page; } else { /* set page dirty and write it */ @@ -1616,6 +1622,7 @@ out_page: unlock_page(node_page); release_page: f2fs_put_page(node_page, 0); + return err; } static int f2fs_write_node_page(struct page *page, @@ -1630,13 +1637,13 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, unsigned int *seq_id) { pgoff_t index; - pgoff_t last_idx = ULONG_MAX; struct pagevec pvec; int ret = 0; struct page *last_page = NULL; bool marked = false; nid_t ino = inode->i_ino; int nr_pages; + int nwritten = 0; if (atomic) { last_page = last_fsync_dnode(sbi, ino); @@ -1714,7 +1721,7 @@ continue_unlock: f2fs_put_page(last_page, 0); break; } else if (submitted) { - last_idx = page->index; + nwritten++; } if (page == last_page) { @@ -1740,8 +1747,8 @@ continue_unlock: goto retry; } out: - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); + if (nwritten) + f2fs_submit_merged_write_cond(sbi, NULL, NULL, ino, NODE); return ret ? -EIO: 0; } @@ -2268,15 +2275,19 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, nm_i->nat_block_bitmap)) { struct page *page = get_current_nat_page(sbi, nid); - ret = scan_nat_page(sbi, page, nid); - f2fs_put_page(page, 1); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + } else { + ret = scan_nat_page(sbi, page, nid); + f2fs_put_page(page, 1); + } if (ret) { up_read(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, !mount); f2fs_msg(sbi->sb, KERN_ERR, "NAT is corrupt, run fsck to fix it"); - return -EINVAL; + return ret; } } @@ -2353,8 +2364,9 @@ retry: spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - f2fs_build_free_nids(sbi, true, false); - goto retry; + if (!f2fs_build_free_nids(sbi, true, false)) + goto retry; + return false; } /* @@ -2537,7 +2549,7 @@ retry: if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); - set_cold_node(page, false); + set_cold_node(ipage, false); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); @@ -2560,6 +2572,13 @@ retry: F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), i_projid)) dst->i_projid = src->i_projid; + + if (f2fs_sb_has_inode_crtime(sbi->sb) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_crtime_nsec)) { + dst->i_crtime = src->i_crtime; + dst->i_crtime_nsec = src->i_crtime_nsec; + } } new_ni = old_ni; @@ -2703,7 +2722,7 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, __clear_bit_le(nat_index, nm_i->full_nat_bits); } -static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, +static int __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct nat_entry_set *set, struct cp_control *cpc) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2727,6 +2746,9 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); + if (IS_ERR(page)) + return PTR_ERR(page); + nat_blk = page_address(page); f2fs_bug_on(sbi, !nat_blk); } @@ -2772,12 +2794,13 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); kmem_cache_free(nat_entry_set_slab, set); } + return 0; } /* * This function is called during the checkpointing process. */ -void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2787,6 +2810,7 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int found; nid_t set_idx = 0; LIST_HEAD(sets); + int err = 0; /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */ if (enabled_nat_bits(sbi, cpc)) { @@ -2796,7 +2820,7 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (!nm_i->dirty_nat_cnt) - return; + return 0; down_write(&nm_i->nat_tree_lock); @@ -2819,11 +2843,16 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* flush dirty nats in nat entry set */ - list_for_each_entry_safe(set, tmp, &sets, set_list) - __flush_nat_entry_set(sbi, set, cpc); + list_for_each_entry_safe(set, tmp, &sets, set_list) { + err = __flush_nat_entry_set(sbi, set, cpc); + if (err) + break; + } up_write(&nm_i->nat_tree_lock); /* Allow dirty nats by node block allocation in write_begin */ + + return err; } static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) @@ -2850,10 +2879,8 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) struct page *page; page = f2fs_get_meta_page(sbi, nat_bits_addr++); - if (IS_ERR(page)) { - disable_nat_bits(sbi, true); + if (IS_ERR(page)) return PTR_ERR(page); - } memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), page_address(page), F2FS_BLKSIZE); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 0f4db7a61254..1c73d879a9bc 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ /* start node id of a node block dedicated to the given node id */ #define START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 95511ed11a22..1dfb17f9f9ff 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/recovery.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -99,8 +96,12 @@ err_out: return ERR_PTR(err); } -static void del_fsync_inode(struct fsync_inode_entry *entry) +static void del_fsync_inode(struct fsync_inode_entry *entry, int drop) { + if (drop) { + /* inode should not be recovered, drop it */ + f2fs_inode_synced(entry->inode); + } iput(entry->inode); list_del(&entry->list); kmem_cache_free(fsync_entry_slab, entry); @@ -194,6 +195,33 @@ out: return err; } +static int recover_quota_data(struct inode *inode, struct page *page) +{ + struct f2fs_inode *raw = F2FS_INODE(page); + struct iattr attr; + uid_t i_uid = le32_to_cpu(raw->i_uid); + gid_t i_gid = le32_to_cpu(raw->i_gid); + int err; + + memset(&attr, 0, sizeof(attr)); + + attr.ia_uid = make_kuid(inode->i_sb->s_user_ns, i_uid); + attr.ia_gid = make_kgid(inode->i_sb->s_user_ns, i_gid); + + if (!uid_eq(attr.ia_uid, inode->i_uid)) + attr.ia_valid |= ATTR_UID; + if (!gid_eq(attr.ia_gid, inode->i_gid)) + attr.ia_valid |= ATTR_GID; + + if (!attr.ia_valid) + return 0; + + err = dquot_transfer(inode, &attr); + if (err) + set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); + return err; +} + static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) { if (ri->i_inline & F2FS_PIN_FILE) @@ -206,12 +234,41 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) clear_inode_flag(inode, FI_DATA_EXIST); } -static void recover_inode(struct inode *inode, struct page *page) +static int recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); char *name; + int err; inode->i_mode = le16_to_cpu(raw->i_mode); + + err = recover_quota_data(inode, page); + if (err) + return err; + + i_uid_write(inode, le32_to_cpu(raw->i_uid)); + i_gid_write(inode, le32_to_cpu(raw->i_gid)); + + if (raw->i_inline & F2FS_EXTRA_ATTR) { + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) && + F2FS_FITS_IN_INODE(raw, le16_to_cpu(raw->i_extra_isize), + i_projid)) { + projid_t i_projid; + kprojid_t kprojid; + + i_projid = (projid_t)le32_to_cpu(raw->i_projid); + kprojid = make_kprojid(&init_user_ns, i_projid); + + if (!projid_eq(kprojid, F2FS_I(inode)->i_projid)) { + err = f2fs_transfer_project_quota(inode, + kprojid); + if (err) + return err; + F2FS_I(inode)->i_projid = kprojid; + } + } + } + f2fs_i_size_write(inode, le64_to_cpu(raw->i_size)); inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime); inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime); @@ -221,9 +278,15 @@ static void recover_inode(struct inode *inode, struct page *page) inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); F2FS_I(inode)->i_advise = raw->i_advise; + F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags); + f2fs_set_inode_flags(inode); + F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = + le16_to_cpu(raw->i_gc_failures); recover_inline_flags(inode, raw); + f2fs_mark_inode_dirty_sync(inode, true); + if (file_enc_name(inode)) name = "<encrypted>"; else @@ -232,6 +295,7 @@ static void recover_inode(struct inode *inode, struct page *page) f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s, inline = %x", ino_of_node(page), name, raw->i_inline); + return 0; } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, @@ -320,12 +384,12 @@ next: return err; } -static void destroy_fsync_dnodes(struct list_head *head) +static void destroy_fsync_dnodes(struct list_head *head, int drop) { struct fsync_inode_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, head, list) - del_fsync_inode(entry); + del_fsync_inode(entry, drop); } static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, @@ -358,6 +422,8 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, } sum_page = f2fs_get_sum_page(sbi, segno); + if (IS_ERR(sum_page)) + return PTR_ERR(sum_page); sum_node = (struct f2fs_summary_block *)page_address(sum_page); sum = sum_node->entries[blkoff]; f2fs_put_page(sum_page, 1); @@ -560,7 +626,7 @@ out: } static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, - struct list_head *dir_list) + struct list_head *tmp_inode_list, struct list_head *dir_list) { struct curseg_info *curseg; struct page *page = NULL; @@ -598,8 +664,11 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, * In this case, we can lose the latest inode(x). * So, call recover_inode for the inode update. */ - if (IS_INODE(page)) - recover_inode(entry->inode, page); + if (IS_INODE(page)) { + err = recover_inode(entry->inode, page); + if (err) + break; + } if (entry->last_dentry == blkaddr) { err = recover_dentry(entry->inode, page, dir_list); if (err) { @@ -614,7 +683,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, } if (entry->blkaddr == blkaddr) - del_fsync_inode(entry); + list_move_tail(&entry->list, tmp_inode_list); next: /* check next segment */ blkaddr = next_blkaddr_of_node(page); @@ -627,7 +696,7 @@ next: int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) { - struct list_head inode_list; + struct list_head inode_list, tmp_inode_list; struct list_head dir_list; int err; int ret = 0; @@ -658,6 +727,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) } INIT_LIST_HEAD(&inode_list); + INIT_LIST_HEAD(&tmp_inode_list); INIT_LIST_HEAD(&dir_list); /* prevent checkpoint */ @@ -676,11 +746,16 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) need_writecp = true; /* step #2: recover data */ - err = recover_data(sbi, &inode_list, &dir_list); + err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); + else { + /* restore s_flags to let iput() trash data */ + sbi->sb->s_flags = s_flags; + } skip: - destroy_fsync_dnodes(&inode_list); + destroy_fsync_dnodes(&inode_list, err); + destroy_fsync_dnodes(&tmp_inode_list, err); /* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), @@ -689,19 +764,23 @@ skip: if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); truncate_inode_pages_final(META_MAPPING(sbi)); + } else { + clear_sbi_flag(sbi, SBI_POR_DOING); } - - clear_sbi_flag(sbi, SBI_POR_DOING); mutex_unlock(&sbi->cp_mutex); /* let's drop all the directory inodes for clean checkpoint */ - destroy_fsync_dnodes(&dir_list); + destroy_fsync_dnodes(&dir_list, err); - if (!err && need_writecp) { - struct cp_control cpc = { - .reason = CP_RECOVERY, - }; - err = f2fs_write_checkpoint(sbi, &cpc); + if (need_writecp) { + set_sbi_flag(sbi, SBI_IS_RECOVERED); + + if (!err) { + struct cp_control cpc = { + .reason = CP_RECOVERY, + }; + err = f2fs_write_checkpoint(sbi, &cpc); + } } kmem_cache_destroy(fsync_entry_slab); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 30779aaa9dba..6edcf8391dd3 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -179,6 +176,8 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi) return false; if (sbi->gc_mode == GC_URGENT) return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); @@ -267,8 +266,10 @@ retry: } next: /* we don't need to invalidate this in the sccessful status */ - if (drop || recover) + if (drop || recover) { ClearPageUptodate(page); + clear_cold_data(page); + } set_page_private(page, 0); ClearPagePrivate(page); f2fs_put_page(page, 1); @@ -374,7 +375,7 @@ static int __f2fs_commit_inmem_pages(struct inode *inode) .io_type = FS_DATA_IO, }; struct list_head revoke_list; - pgoff_t last_idx = ULONG_MAX; + bool submit_bio = false; int err = 0; INIT_LIST_HEAD(&revoke_list); @@ -409,14 +410,14 @@ retry: } /* record old blkaddr for revoking */ cur->old_addr = fio.old_blkaddr; - last_idx = page->index; + submit_bio = true; } unlock_page(page); list_move_tail(&cur->list, &revoke_list); } - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA); + if (submit_bio) + f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA); if (err) { /* @@ -483,6 +484,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi); + if (f2fs_is_checkpoint_ready(sbi)) + return; + /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. @@ -511,7 +515,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) else f2fs_build_free_nids(sbi, false, false); - if (!is_idle(sbi) && + if (!is_idle(sbi, REQ_TIME) && (!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi))) return; @@ -799,7 +803,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - unsigned short valid_blocks; + unsigned short valid_blocks, ckpt_valid_blocks; if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) return; @@ -807,8 +811,10 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_lock(&dirty_i->seglist_lock); valid_blocks = get_valid_blocks(sbi, segno, false); + ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno); - if (valid_blocks == 0) { + if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) || + ckpt_valid_blocks == sbi->blocks_per_seg)) { __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } else if (valid_blocks < sbi->blocks_per_seg) { @@ -821,6 +827,66 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_unlock(&dirty_i->seglist_lock); } +/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */ +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (IS_CURSEG(sbi, segno)) + continue; + __locate_dirty_segment(sbi, segno, PRE); + __remove_dirty_segment(sbi, segno, DIRTY); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + block_t ovp = overprovision_segments(sbi) << sbi->log_blocks_per_seg; + block_t holes[2] = {0, 0}; /* DATA and NODE */ + struct seg_entry *se; + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + se = get_seg_entry(sbi, segno); + if (IS_NODESEG(se->type)) + holes[NODE] += sbi->blocks_per_seg - se->valid_blocks; + else + holes[DATA] += sbi->blocks_per_seg - se->valid_blocks; + } + mutex_unlock(&dirty_i->seglist_lock); + + if (holes[DATA] > ovp || holes[NODE] > ovp) + return -EAGAIN; + return 0; +} + +/* This is only used by SBI_CP_DISABLED */ +static unsigned int get_free_segment(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno = 0; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (get_ckpt_valid_blocks(sbi, segno)) + continue; + mutex_unlock(&dirty_i->seglist_lock); + return segno; + } + mutex_unlock(&dirty_i->seglist_lock); + return NULL_SEGNO; +} + static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) @@ -856,7 +922,8 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len, - struct rb_node *parent, struct rb_node **p) + struct rb_node *parent, struct rb_node **p, + bool leftmost) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *dc; @@ -864,7 +931,7 @@ static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi, dc = __create_discard_cmd(sbi, bdev, lstart, start, len); rb_link_node(&dc->rb_node, parent, p); - rb_insert_color(&dc->rb_node, &dcc->root); + rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost); return dc; } @@ -876,7 +943,7 @@ static void __detach_discard_cmd(struct discard_cmd_control *dcc, atomic_sub(dc->issuing, &dcc->issing_discard); list_del(&dc->list); - rb_erase(&dc->rb_node, &dcc->root); + rb_erase_cached(&dc->rb_node, &dcc->root); dcc->undiscard_blks -= dc->len; kmem_cache_free(discard_cmd_slab, dc); @@ -905,9 +972,9 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, dc->error = 0; if (dc->error) - f2fs_msg(sbi->sb, KERN_INFO, - "Issue discard(%u, %u, %u) failed, ret: %d", - dc->lstart, dc->start, dc->len, dc->error); + printk_ratelimited( + "%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d", + KERN_INFO, dc->lstart, dc->start, dc->len, dc->error); __detach_discard_cmd(dcc, dc); } @@ -1113,6 +1180,7 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, struct rb_node **p; struct rb_node *parent = NULL; struct discard_cmd *dc = NULL; + bool leftmost = true; if (insert_p && insert_parent) { parent = insert_parent; @@ -1120,9 +1188,11 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, goto do_insert; } - p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart); + p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, + lstart, &leftmost); do_insert: - dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p); + dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, + p, leftmost); if (!dc) return NULL; @@ -1190,7 +1260,7 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, NULL, lstart, (struct rb_entry **)&prev_dc, (struct rb_entry **)&next_dc, - &insert_p, &insert_parent, true); + &insert_p, &insert_parent, true, NULL); if (dc) prev_dc = dc; @@ -1298,7 +1368,7 @@ static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, NULL, pos, (struct rb_entry **)&prev_dc, (struct rb_entry **)&next_dc, - &insert_p, &insert_parent, true); + &insert_p, &insert_parent, true, NULL); if (!dc) dc = next_dc; @@ -1311,7 +1381,7 @@ static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, if (dc->state != D_PREP) goto next; - if (dpolicy->io_aware && !is_idle(sbi)) { + if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; break; } @@ -1371,7 +1441,7 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, dc->state != D_PREP); if (dpolicy->io_aware && i < dpolicy->io_aware_gran && - !is_idle(sbi)) { + !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; break; } @@ -1600,7 +1670,9 @@ static int issue_discard_thread(void *data) __wait_all_discard_cmd(sbi, &dpolicy); wait_ms = dpolicy.min_interval; } else if (issued == -1){ - wait_ms = dpolicy.mid_interval; + wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME); + if (!wait_ms) + wait_ms = dpolicy.mid_interval; } else { wait_ms = dpolicy.max_interval; } @@ -1725,11 +1797,11 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i; - if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi)) + if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi)) return false; if (!force) { - if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks || SM_I(sbi)->dcc_info->nr_discards >= SM_I(sbi)->dcc_info->max_discards) return false; @@ -1835,7 +1907,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, dirty_i->nr_dirty[PRE]--; } - if (!test_opt(sbi, DISCARD)) + if (!f2fs_realtime_discard_enable(sbi)) continue; if (force && start >= cpc->trim_start && @@ -1928,7 +2000,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg; dcc->undiscard_blks = 0; dcc->next_pos = 0; - dcc->root = RB_ROOT; + dcc->root = RB_ROOT_CACHED; dcc->rbtree_check = false; init_waitqueue_head(&dcc->discard_wait_queue); @@ -2025,12 +2097,12 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) del = 0; } - if (f2fs_discard_en(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) + if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; /* don't overwrite by SSR to keep node chain */ - if (IS_NODESEG(se->type)) { + if (IS_NODESEG(se->type) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -2052,10 +2124,18 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; + } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + /* + * If checkpoints are off, we must not reuse data that + * was used in the previous checkpoint. If it was used + * before, we must track that to know how much space we + * really have. + */ + if (f2fs_test_bit(offset, se->ckpt_valid_map)) + sbi->unusable_block_count++; } - if (f2fs_discard_en(sbi) && - f2fs_test_and_clear_bit(offset, se->discard_map)) + if (f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -2335,6 +2415,9 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) if (sbi->segs_per_sec != 1) return CURSEG_I(sbi, type)->segno; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) return 0; @@ -2432,6 +2515,7 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type) __next_free_blkoff(sbi, curseg, 0); sum_page = f2fs_get_sum_page(sbi, new_segno); + f2fs_bug_on(sbi, IS_ERR(sum_page)); sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); @@ -2478,6 +2562,15 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) return 1; } } + + /* find valid_blocks=0 in dirty list */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + segno = get_free_segment(sbi); + if (segno != NULL_SEGNO) { + curseg->next_segno = segno; + return 1; + } + } return 0; } @@ -2495,7 +2588,8 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) && type == CURSEG_WARM_NODE) new_curseg(sbi, type, false); - else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) + else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) && + likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) new_curseg(sbi, type, false); else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) change_curseg(sbi, type); @@ -2570,7 +2664,7 @@ next: NULL, start, (struct rb_entry **)&prev_dc, (struct rb_entry **)&next_dc, - &insert_p, &insert_parent, true); + &insert_p, &insert_parent, true, NULL); if (!dc) dc = next_dc; @@ -2671,7 +2765,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) * discard option. User configuration looks like using runtime discard * or periodic fstrim instead of it. */ - if (test_opt(sbi, DISCARD)) + if (f2fs_realtime_discard_enable(sbi)) goto out; start_block = START_BLOCK(sbi, start_segno); @@ -3020,6 +3114,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, ClearPageError(page); f2fs_submit_page_write(&fio); + stat_inc_meta_count(sbi, page->index); f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE); } @@ -3182,8 +3277,7 @@ void f2fs_wait_on_page_writeback(struct page *page, if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); - f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, type); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type); if (ordered) wait_on_page_writeback(page); else @@ -3191,10 +3285,14 @@ void f2fs_wait_on_page_writeback(struct page *page, } } -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; + if (!f2fs_post_read_required(inode)) + return; + if (!is_valid_data_blkaddr(sbi, blkaddr)) return; @@ -3205,6 +3303,15 @@ void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) } } +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len) +{ + block_t i; + + for (i = 0; i < len; i++) + f2fs_wait_on_block_writeback(inode, blkaddr + i); +} + static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -3762,13 +3869,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi) return -ENOMEM; #endif - if (f2fs_discard_en(sbi)) { - sit_i->sentries[start].discard_map - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, - GFP_KERNEL); - if (!sit_i->sentries[start].discard_map) - return -ENOMEM; - } + sit_i->sentries[start].discard_map + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, + GFP_KERNEL); + if (!sit_i->sentries[start].discard_map) + return -ENOMEM; } sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); @@ -3904,6 +4009,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) se = &sit_i->sentries[start]; page = get_current_sit_page(sbi, start); + if (IS_ERR(page)) + return PTR_ERR(page); sit_blk = (struct f2fs_sit_block *)page_address(page); sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; f2fs_put_page(page, 1); @@ -3916,18 +4023,16 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) total_node_blocks += se->valid_blocks; /* build discard map only one time */ - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, - se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += - sbi->blocks_per_seg - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, + SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, + se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += + sbi->blocks_per_seg - + se->valid_blocks; } if (sbi->segs_per_sec > 1) @@ -3965,16 +4070,13 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (IS_NODESEG(se->type)) total_node_blocks += se->valid_blocks; - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += old_valid_blocks; - sbi->discard_blks -= se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += old_valid_blocks; + sbi->discard_blks -= se->valid_blocks; } if (sbi->segs_per_sec > 1) { diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index b3d9e317ff0c..ab3465faddf1 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/blkdev.h> #include <linux/backing-dev.h> @@ -342,6 +339,12 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, return get_seg_entry(sbi, segno)->valid_blocks; } +static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + return get_seg_entry(sbi, segno)->ckpt_valid_blocks; +} + static inline void seg_info_from_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { @@ -579,6 +582,15 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, reserved_sections(sbi) + needed); } +static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) +{ + if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (likely(!has_not_enough_free_secs(sbi, 0, 0))) + return 0; + return -ENOSPC; +} + static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) { return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments; diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index 36cfd816c160..9e13db994fdf 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs shrinker support * the basic infra was copied from fs/ubifs/shrinker.c * * Copyright (c) 2015 Motorola Mobility * Copyright (c) 2015 Jaegeuk Kim <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 896b885f504e..af58b2cc21b8 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/super.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/module.h> #include <linux/init.h> @@ -53,9 +50,10 @@ char *f2fs_fault_name[FAULT_MAX] = { [FAULT_DIR_DEPTH] = "too big dir depth", [FAULT_EVICT_INODE] = "evict_inode fail", [FAULT_TRUNCATE] = "truncate fail", - [FAULT_IO] = "IO error", + [FAULT_READ_IO] = "read IO error", [FAULT_CHECKPOINT] = "checkpoint error", [FAULT_DISCARD] = "discard error", + [FAULT_WRITE_IO] = "write IO error", }; void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, @@ -138,6 +136,7 @@ enum { Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, + Opt_checkpoint, Opt_err, }; @@ -196,6 +195,7 @@ static match_table_t f2fs_tokens = { {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_checkpoint, "checkpoint=%s"}, {Opt_err, NULL}, }; @@ -207,7 +207,7 @@ void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk_ratelimited("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); + printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); va_end(args); } @@ -360,7 +360,6 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) static int parse_options(struct super_block *sb, char *options) { struct f2fs_sb_info *sbi = F2FS_SB(sb); - struct request_queue *q; substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; @@ -415,14 +414,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; break; case Opt_discard: - q = bdev_get_queue(sb->s_bdev); - if (blk_queue_discard(q)) { - set_opt(sbi, DISCARD); - } else if (!f2fs_sb_has_blkzoned(sb)) { - f2fs_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + set_opt(sbi, DISCARD); break; case Opt_nodiscard: if (f2fs_sb_has_blkzoned(sb)) { @@ -602,28 +594,31 @@ static int parse_options(struct super_block *sb, char *options) } F2FS_OPTION(sbi).write_io_size_bits = arg; break; +#ifdef CONFIG_F2FS_FAULT_INJECTION case Opt_fault_injection: if (args->from && match_int(args, &arg)) return -EINVAL; -#ifdef CONFIG_F2FS_FAULT_INJECTION f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE); set_opt(sbi, FAULT_INJECTION); -#else - f2fs_msg(sb, KERN_INFO, - "FAULT_INJECTION was not selected"); -#endif break; + case Opt_fault_type: if (args->from && match_int(args, &arg)) return -EINVAL; -#ifdef CONFIG_F2FS_FAULT_INJECTION f2fs_build_fault_attr(sbi, 0, arg); set_opt(sbi, FAULT_INJECTION); + break; #else + case Opt_fault_injection: f2fs_msg(sb, KERN_INFO, - "FAULT_INJECTION was not selected"); -#endif + "fault_injection options not supported"); + break; + + case Opt_fault_type: + f2fs_msg(sb, KERN_INFO, + "fault_type options not supported"); break; +#endif case Opt_lazytime: sb->s_flags |= SB_LAZYTIME; break; @@ -776,6 +771,23 @@ static int parse_options(struct super_block *sb, char *options) "Test dummy encryption mount option ignored"); #endif break; + case Opt_checkpoint: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + + if (strlen(name) == 6 && + !strncmp(name, "enable", 6)) { + clear_opt(sbi, DISABLE_CHECKPOINT); + } else if (strlen(name) == 7 && + !strncmp(name, "disable", 7)) { + set_opt(sbi, DISABLE_CHECKPOINT); + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -834,6 +846,12 @@ static int parse_options(struct super_block *sb, char *options) } } + if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) { + f2fs_msg(sb, KERN_ERR, + "LFS not compatible with checkpoint=disable\n"); + return -EINVAL; + } + /* Not pass down write hints if the number of active logs is lesser * than NR_CURSEG_TYPE. */ @@ -1021,8 +1039,8 @@ static void f2fs_put_super(struct super_block *sb) * But, the previous checkpoint was not done by umount, it needs to do * clean checkpoint again. */ - if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || - !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) || + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) { struct cp_control cpc = { .reason = CP_UMOUNT, }; @@ -1032,7 +1050,8 @@ static void f2fs_put_super(struct super_block *sb) /* be sure to wait for any on-going discard commands */ dropped = f2fs_wait_discard_bios(sbi); - if (f2fs_discard_en(sbi) && !sbi->discard_blks && !dropped) { + if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) && + !sbi->discard_blks && !dropped) { struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; @@ -1093,6 +1112,8 @@ int f2fs_sync_fs(struct super_block *sb, int sync) if (unlikely(f2fs_cp_error(sbi))) return 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; trace_f2fs_sync_fs(sb, sync); @@ -1192,6 +1213,11 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; + if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) + buf->f_bfree = 0; + else + buf->f_bfree -= sbi->unusable_block_count; + if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) buf->f_bavail = buf->f_bfree - F2FS_OPTION(sbi).root_reserved_blocks; @@ -1336,7 +1362,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) from_kgid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resgid)); if (F2FS_IO_SIZE_BITS(sbi)) - seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi)); + seq_printf(seq, ",io_bits=%u", + F2FS_OPTION(sbi).write_io_size_bits); #ifdef CONFIG_F2FS_FAULT_INJECTION if (test_opt(sbi, FAULT_INJECTION)) { seq_printf(seq, ",fault_injection=%u", @@ -1370,6 +1397,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) seq_printf(seq, ",alloc_mode=%s", "reuse"); + if (test_opt(sbi, DISABLE_CHECKPOINT)) + seq_puts(seq, ",checkpoint=disable"); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) seq_printf(seq, ",fsync_mode=%s", "posix"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) @@ -1397,10 +1427,10 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, INLINE_DENTRY); set_opt(sbi, EXTENT_CACHE); set_opt(sbi, NOHEAP); + clear_opt(sbi, DISABLE_CHECKPOINT); sbi->sb->s_flags |= SB_LAZYTIME; set_opt(sbi, FLUSH_MERGE); - if (blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev))) - set_opt(sbi, DISCARD); + set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi->sb)) set_opt_mode(sbi, F2FS_MOUNT_LFS); else @@ -1419,6 +1449,57 @@ static void default_options(struct f2fs_sb_info *sbi) #ifdef CONFIG_QUOTA static int f2fs_enable_quotas(struct super_block *sb); #endif + +static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) +{ + struct cp_control cpc; + int err; + + sbi->sb->s_flags |= SB_ACTIVE; + + mutex_lock(&sbi->gc_mutex); + f2fs_update_time(sbi, DISABLE_TIME); + + while (!f2fs_time_over(sbi, DISABLE_TIME)) { + err = f2fs_gc(sbi, true, false, NULL_SEGNO); + if (err == -ENODATA) + break; + if (err && err != -EAGAIN) { + mutex_unlock(&sbi->gc_mutex); + return err; + } + } + mutex_unlock(&sbi->gc_mutex); + + err = sync_filesystem(sbi->sb); + if (err) + return err; + + if (f2fs_disable_cp_again(sbi)) + return -EAGAIN; + + mutex_lock(&sbi->gc_mutex); + cpc.reason = CP_PAUSE; + set_sbi_flag(sbi, SBI_CP_DISABLED); + f2fs_write_checkpoint(sbi, &cpc); + + sbi->unusable_block_count = 0; + mutex_unlock(&sbi->gc_mutex); + return 0; +} + +static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) +{ + mutex_lock(&sbi->gc_mutex); + f2fs_dirty_to_prefree(sbi); + + clear_sbi_flag(sbi, SBI_CP_DISABLED); + set_sbi_flag(sbi, SBI_IS_DIRTY); + mutex_unlock(&sbi->gc_mutex); + + f2fs_sync_fs(sbi->sb, 1); +} + static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -1428,6 +1509,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) bool need_restart_gc = false; bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); + bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT); + bool checkpoint_changed; #ifdef CONFIG_QUOTA int i, j; #endif @@ -1472,6 +1555,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) err = parse_options(sb, data); if (err) goto restore_opts; + checkpoint_changed = + disable_checkpoint != test_opt(sbi, DISABLE_CHECKPOINT); /* * Previous and new state of filesystem is RO, @@ -1485,7 +1570,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; - } else if (f2fs_readonly(sb) && !(*flags & MS_RDONLY)) { + } else if (f2fs_readonly(sb) && !(*flags & SB_RDONLY)) { /* dquot_resume needs RW */ sb->s_flags &= ~SB_RDONLY; if (sb_any_quota_suspended(sb)) { @@ -1505,6 +1590,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if ((*flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { + err = -EINVAL; + f2fs_msg(sbi->sb, KERN_WARNING, + "disabling checkpoint not compatible with read-only"); + goto restore_opts; + } + /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount @@ -1533,6 +1625,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_IS_CLOSE); } + if (checkpoint_changed) { + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto restore_gc; + } else { + f2fs_enable_checkpoint(sbi); + } + } + /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. @@ -1556,6 +1658,7 @@ skip: (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); limit_reserve_root(sbi); + *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); return 0; restore_gc: if (need_restart_gc) { @@ -1608,6 +1711,7 @@ repeat: congestion_wait(BLK_RW_ASYNC, HZ/50); goto repeat; } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return PTR_ERR(page); } @@ -1619,6 +1723,7 @@ repeat: } if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return -EIO; } @@ -1660,6 +1765,7 @@ retry: congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); break; } @@ -1696,6 +1802,12 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode) static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { + if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sbi->sb, KERN_ERR, + "quota sysfile may be corrupted, skip loading it"); + return 0; + } + return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type], F2FS_OPTION(sbi).s_jquota_fmt, type); } @@ -1766,7 +1878,14 @@ static int f2fs_enable_quotas(struct super_block *sb) test_opt(F2FS_SB(sb), PRJQUOTA), }; - sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; + if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sb, KERN_ERR, + "quota file may be corrupted, skip loading it"); + return 0; + } + + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + for (type = 0; type < MAXQUOTAS; type++) { qf_inum = f2fs_qf_ino(sb, type); if (qf_inum) { @@ -1780,6 +1899,8 @@ static int f2fs_enable_quotas(struct super_block *sb) "fsck to fix.", type, err); for (type--; type >= 0; type--) dquot_quota_off(sb, type); + set_sbi_flag(F2FS_SB(sb), + SBI_QUOTA_NEED_REPAIR); return err; } } @@ -1787,35 +1908,51 @@ static int f2fs_enable_quotas(struct super_block *sb) return 0; } -static int f2fs_quota_sync(struct super_block *sb, int type) +int f2fs_quota_sync(struct super_block *sb, int type) { + struct f2fs_sb_info *sbi = F2FS_SB(sb); struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret; ret = dquot_writeback_dquots(sb, type); if (ret) - return ret; + goto out; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + struct address_space *mapping; + if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; - ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping); + mapping = dqopt->files[cnt]->i_mapping; + + ret = filemap_fdatawrite(mapping); + if (ret) + goto out; + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + continue; + + ret = filemap_fdatawait(mapping); if (ret) - return ret; + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } - return 0; +out: + if (ret) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; } static int f2fs_quota_on(struct super_block *sb, int type, int format_id, @@ -1836,8 +1973,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, inode_lock(inode); F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL; - inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, - S_NOATIME | S_IMMUTABLE); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -1852,7 +1988,9 @@ static int f2fs_quota_off(struct super_block *sb, int type) if (!inode || !igrab(inode)) return dquot_quota_off(sb, type); - f2fs_quota_sync(sb, type); + err = f2fs_quota_sync(sb, type); + if (err) + goto out_put; err = dquot_quota_off(sb, type); if (err || f2fs_sb_has_quota_ino(sb)) @@ -1860,7 +1998,7 @@ static int f2fs_quota_off(struct super_block *sb, int type) inode_lock(inode); F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL); - inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); out_put: @@ -1871,9 +2009,88 @@ out_put: void f2fs_quota_off_umount(struct super_block *sb) { int type; + int err; + + for (type = 0; type < MAXQUOTAS; type++) { + err = f2fs_quota_off(sb, type); + if (err) { + int ret = dquot_quota_off(sb, type); + + f2fs_msg(sb, KERN_ERR, + "Fail to turn off disk quota " + "(type: %d, err: %d, ret:%d), Please " + "run fsck to fix it.", type, err, ret); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + } + } +} + +static void f2fs_truncate_quota_inode_pages(struct super_block *sb) +{ + struct quota_info *dqopt = sb_dqopt(sb); + int type; + + for (type = 0; type < MAXQUOTAS; type++) { + if (!dqopt->files[type]) + continue; + f2fs_inode_synced(dqopt->files[type]); + } +} + +static int f2fs_dquot_commit(struct dquot *dquot) +{ + int ret; + + ret = dquot_commit(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_acquire(struct dquot *dquot) +{ + int ret; + + ret = dquot_acquire(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + + return ret; +} + +static int f2fs_dquot_release(struct dquot *dquot) +{ + int ret; + + ret = dquot_release(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot) +{ + struct super_block *sb = dquot->dq_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int ret; + + ret = dquot_mark_dquot_dirty(dquot); + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + return ret; +} - for (type = 0; type < MAXQUOTAS; type++) - f2fs_quota_off(sb, type); +static int f2fs_dquot_commit_info(struct super_block *sb, int type) +{ + int ret; + + ret = dquot_commit_info(sb, type); + if (ret < 0) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; } static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) @@ -1884,11 +2101,11 @@ static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) static const struct dquot_operations f2fs_quota_operations = { .get_reserved_space = f2fs_get_reserved_space, - .write_dquot = dquot_commit, - .acquire_dquot = dquot_acquire, - .release_dquot = dquot_release, - .mark_dirty = dquot_mark_dquot_dirty, - .write_info = dquot_commit_info, + .write_dquot = f2fs_dquot_commit, + .acquire_dquot = f2fs_dquot_acquire, + .release_dquot = f2fs_dquot_release, + .mark_dirty = f2fs_dquot_mark_dquot_dirty, + .write_info = f2fs_dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = f2fs_get_projid, @@ -1906,6 +2123,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = { .get_nextdqblk = dquot_get_next_dqblk, }; #else +int f2fs_quota_sync(struct super_block *sb, int type) +{ + return 0; +} + void f2fs_quota_off_umount(struct super_block *sb) { } @@ -2170,6 +2392,26 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, (bh->b_data + F2FS_SUPER_OFFSET); struct super_block *sb = sbi->sb; unsigned int blocksize; + size_t crc_offset = 0; + __u32 crc = 0; + + /* Check checksum_offset and crc in superblock */ + if (le32_to_cpu(raw_super->feature) & F2FS_FEATURE_SB_CHKSUM) { + crc_offset = le32_to_cpu(raw_super->checksum_offset); + if (crc_offset != + offsetof(struct f2fs_super_block, crc)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum offset: %zu", + crc_offset); + return 1; + } + crc = le32_to_cpu(raw_super->crc); + if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum value: %u", crc); + return 1; + } + } if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { f2fs_msg(sb, KERN_INFO, @@ -2320,7 +2562,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count; - int i; + int i, j; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -2361,11 +2603,43 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_node_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Node segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_data_segno[i])); + return 1; + } + } + } + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + for (j = i; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u) and Data segment (%u)" + " has the same segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); @@ -2423,6 +2697,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) @@ -2453,8 +2730,12 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) if (err) return err; - return percpu_counter_init(&sbi->total_valid_inode_count, 0, + err = percpu_counter_init(&sbi->total_valid_inode_count, 0, GFP_KERNEL); + if (err) + percpu_counter_destroy(&sbi->alloc_valid_block_count); + + return err; } #ifdef CONFIG_BLK_DEV_ZONED @@ -2589,6 +2870,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { struct buffer_head *bh; + __u32 crc = 0; int err; if ((recover && f2fs_readonly(sbi->sb)) || @@ -2597,6 +2879,13 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return -EROFS; } + /* we should update superblock crc here */ + if (!recover && f2fs_sb_has_sb_chksum(sbi->sb)) { + crc = f2fs_crc32(sbi, F2FS_RAW_SUPER(sbi), + offsetof(struct f2fs_super_block, crc)); + F2FS_RAW_SUPER(sbi)->crc = cpu_to_le32(crc); + } + /* write back-up superblock first */ bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1); if (!bh) @@ -2866,7 +3155,7 @@ try_onemore: GFP_KERNEL); if (!sbi->write_io[i]) { err = -ENOMEM; - goto free_options; + goto free_bio_info; } for (j = HOT; j < n; j++) { @@ -2909,6 +3198,9 @@ try_onemore: goto free_meta_inode; } + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + /* Initialize device list */ err = f2fs_scan_devices(sbi); if (err) { @@ -3007,11 +3299,9 @@ try_onemore: /* Enable quota usage during mount */ if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) { err = f2fs_enable_quotas(sb); - if (err) { + if (err) f2fs_msg(sb, KERN_ERR, "Cannot turn on quotas: error %d", err); - goto free_sysfs; - } } #endif /* if there are nt orphan nodes free them */ @@ -3019,6 +3309,9 @@ try_onemore: if (err) goto free_meta; + if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) + goto skip_recovery; + /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { /* @@ -3058,6 +3351,14 @@ skip_recovery: /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto free_meta; + } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { + f2fs_enable_checkpoint(sbi); + } + /* * If filesystem is not mounted as read-only then * do start the gc_thread. @@ -3090,10 +3391,10 @@ skip_recovery: free_meta: #ifdef CONFIG_QUOTA + f2fs_truncate_quota_inode_pages(sb); if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) f2fs_quota_off_umount(sbi->sb); #endif - f2fs_sync_inode_meta(sbi); /* * Some dirty meta pages can be produced by f2fs_recover_orphan_inodes() * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() @@ -3101,9 +3402,6 @@ free_meta: * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); -#ifdef CONFIG_QUOTA -free_sysfs: -#endif f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); @@ -3175,6 +3473,9 @@ static void kill_f2fs_super(struct super_block *sb) }; f2fs_write_checkpoint(sbi, &cpc); } + + if (is_sbi_flag_set(sbi, SBI_IS_RECOVERED) && f2fs_readonly(sb)) + sb->s_flags &= ~SB_RDONLY; } kill_block_super(sb); } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 81c0e5337443..b777cbdd796b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs sysfs interface * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * Copyright (c) 2017 Chao Yu <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/compiler.h> #include <linux/proc_fs.h> @@ -120,6 +117,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_lost_found(sb)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "lost_found"); + if (f2fs_sb_has_sb_chksum(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "sb_checksum"); len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } @@ -337,6 +337,7 @@ enum feat_id { FEAT_QUOTA_INO, FEAT_INODE_CRTIME, FEAT_LOST_FOUND, + FEAT_SB_CHECKSUM, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -353,6 +354,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_QUOTA_INO: case FEAT_INODE_CRTIME: case FEAT_LOST_FOUND: + case FEAT_SB_CHECKSUM: return snprintf(buf, PAGE_SIZE, "supported\n"); } return 0; @@ -407,6 +409,9 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval, + interval_time[DISCARD_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); @@ -434,6 +439,7 @@ F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO); F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME); F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); +F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -460,6 +466,8 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(dirty_nats_ratio), ATTR_LIST(cp_interval), ATTR_LIST(idle_interval), + ATTR_LIST(discard_idle_interval), + ATTR_LIST(gc_idle_interval), ATTR_LIST(iostat_enable), ATTR_LIST(readdir_ra), ATTR_LIST(gc_pin_file_thresh), @@ -491,6 +499,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(quota_ino), ATTR_LIST(inode_crtime), ATTR_LIST(lost_found), + ATTR_LIST(sb_checksum), NULL, }; diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index a1fcd00bbb2b..ce2a5eb210b6 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h index 67db24ac1e85..e8075fc5b228 100644 --- a/fs/f2fs/trace.h +++ b/fs/f2fs/trace.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_TRACE_H__ #define __F2FS_TRACE_H__ diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 77a010e625f5..7261245c208d 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.c * @@ -13,10 +14,6 @@ * suggestion of Luka Renko <[email protected]>. * xattr consolidation Copyright (c) 2004 James Morris <[email protected]>, * Red Hat Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/rwsem.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index dbcd1d16e669..67db134da0f5 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.h * @@ -9,10 +10,6 @@ * On-disk format of extended attributes for the ext2 filesystem. * * (C) 2001 Andreas Gruenbacher, <[email protected]> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_XATTR_H__ #define __F2FS_XATTR_H__ diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 84544a4f012d..a683d9b27d76 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1566,7 +1566,7 @@ more_rgrps: continue; } if (bstart) { - __gfs2_free_blocks(ip, bstart, (u32)blen, meta); + __gfs2_free_blocks(ip, rgd, bstart, (u32)blen, meta); (*btotal) += blen; gfs2_add_inode_blocks(&ip->i_inode, -blen); } @@ -1574,7 +1574,7 @@ more_rgrps: blen = 1; } if (bstart) { - __gfs2_free_blocks(ip, bstart, (u32)blen, meta); + __gfs2_free_blocks(ip, rgd, bstart, (u32)blen, meta); (*btotal) += blen; gfs2_add_inode_blocks(&ip->i_inode, -blen); } diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index e37002560c11..daa14ab4e31b 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -506,7 +506,8 @@ static int gfs2_dirent_gather(const struct gfs2_dirent *dent, * For now the most important thing is to check that the various sizes * are correct. */ -static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset, +static int gfs2_check_dirent(struct gfs2_sbd *sdp, + struct gfs2_dirent *dent, unsigned int offset, unsigned int size, unsigned int len, int first) { const char *msg = "gfs2_dirent too small"; @@ -528,12 +529,12 @@ static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset, goto error; return 0; error: - pr_warn("%s: %s (%s)\n", + fs_warn(sdp, "%s: %s (%s)\n", __func__, msg, first ? "first in block" : "not first in block"); return -EIO; } -static int gfs2_dirent_offset(const void *buf) +static int gfs2_dirent_offset(struct gfs2_sbd *sdp, const void *buf) { const struct gfs2_meta_header *h = buf; int offset; @@ -552,7 +553,8 @@ static int gfs2_dirent_offset(const void *buf) } return offset; wrong_type: - pr_warn("%s: wrong block type %u\n", __func__, be32_to_cpu(h->mh_type)); + fs_warn(sdp, "%s: wrong block type %u\n", __func__, + be32_to_cpu(h->mh_type)); return -1; } @@ -566,7 +568,7 @@ static struct gfs2_dirent *gfs2_dirent_scan(struct inode *inode, void *buf, unsigned size; int ret = 0; - ret = gfs2_dirent_offset(buf); + ret = gfs2_dirent_offset(GFS2_SB(inode), buf); if (ret < 0) goto consist_inode; @@ -574,7 +576,7 @@ static struct gfs2_dirent *gfs2_dirent_scan(struct inode *inode, void *buf, prev = NULL; dent = buf + offset; size = be16_to_cpu(dent->de_rec_len); - if (gfs2_check_dirent(dent, offset, size, len, 1)) + if (gfs2_check_dirent(GFS2_SB(inode), dent, offset, size, len, 1)) goto consist_inode; do { ret = scan(dent, name, opaque); @@ -586,7 +588,8 @@ static struct gfs2_dirent *gfs2_dirent_scan(struct inode *inode, void *buf, prev = dent; dent = buf + offset; size = be16_to_cpu(dent->de_rec_len); - if (gfs2_check_dirent(dent, offset, size, len, 0)) + if (gfs2_check_dirent(GFS2_SB(inode), dent, offset, size, + len, 0)) goto consist_inode; } while(1); @@ -1043,7 +1046,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) len = BIT(dip->i_depth - be16_to_cpu(oleaf->lf_depth)); half_len = len >> 1; if (!half_len) { - pr_warn("i_depth %u lf_depth %u index %u\n", + fs_warn(GFS2_SB(inode), "i_depth %u lf_depth %u index %u\n", dip->i_depth, be16_to_cpu(oleaf->lf_depth), index); gfs2_consist_inode(dip); error = -EIO; @@ -1351,7 +1354,7 @@ static int gfs2_set_cookies(struct gfs2_sbd *sdp, struct buffer_head *bh, if (!sdp->sd_args.ar_loccookie) continue; offset = (char *)(darr[i]) - - (bh->b_data + gfs2_dirent_offset(bh->b_data)); + (bh->b_data + gfs2_dirent_offset(sdp, bh->b_data)); offset /= GFS2_MIN_DIRENT_SIZE; offset += leaf_nr * sdp->sd_max_dents_per_leaf; if (offset >= GFS2_USE_HASH_FLAG || @@ -2018,7 +2021,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, l_blocks++; } - gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); + gfs2_rlist_alloc(&rlist); for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); @@ -2039,6 +2042,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, bh = leaf_bh; for (blk = leaf_no; blk; blk = nblk) { + struct gfs2_rgrpd *rgd; + if (blk != leaf_no) { error = get_leaf(dip, blk, &bh); if (error) @@ -2049,7 +2054,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, if (blk != leaf_no) brelse(bh); - gfs2_free_meta(dip, blk, 1); + rgd = gfs2_blk2rgrpd(sdp, blk, true); + gfs2_free_meta(dip, rgd, blk, 1); gfs2_add_inode_blocks(&dip->i_inode, -1); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 08369c6cd127..45a17b770d97 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -314,6 +314,17 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr) return do_gfs2_set_flags(filp, gfsflags, mask); } +static int gfs2_getlabel(struct file *filp, char __user *label) +{ + struct inode *inode = file_inode(filp); + struct gfs2_sbd *sdp = GFS2_SB(inode); + + if (copy_to_user(label, sdp->sd_sb.sb_locktable, GFS2_LOCKNAME_LEN)) + return -EFAULT; + + return 0; +} + static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch(cmd) { @@ -323,7 +334,10 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return gfs2_set_flags(filp, (u32 __user *)arg); case FITRIM: return gfs2_fitrim(filp, (void __user *)arg); + case FS_IOC_GETFSLABEL: + return gfs2_getlabel(filp, (char __user *)arg); } + return -ENOTTY; } @@ -347,8 +361,8 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size) size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift; int hint = min_t(size_t, INT_MAX, blks); - if (hint > atomic_read(&ip->i_res.rs_sizehint)) - atomic_set(&ip->i_res.rs_sizehint, hint); + if (hint > atomic_read(&ip->i_sizehint)) + atomic_set(&ip->i_sizehint, hint); } /** diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 4614ee25f621..05431324b262 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -494,7 +494,8 @@ retry: do_xmote(gl, gh, LM_ST_UNLOCKED); break; default: /* Everything else */ - pr_err("wanted %u got %u\n", gl->gl_target, state); + fs_err(gl->gl_name.ln_sbd, "wanted %u got %u\n", + gl->gl_target, state); GLOCK_BUG_ON(gl, 1); } spin_unlock(&gl->gl_lockref.lock); @@ -577,7 +578,7 @@ __acquires(&gl->gl_lockref.lock) gfs2_glock_queue_work(gl, 0); } else if (ret) { - pr_err("lm_lock ret %d\n", ret); + fs_err(sdp, "lm_lock ret %d\n", ret); GLOCK_BUG_ON(gl, !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)); } @@ -1064,13 +1065,13 @@ do_cancel: return; trap_recursive: - pr_err("original: %pSR\n", (void *)gh2->gh_ip); - pr_err("pid: %d\n", pid_nr(gh2->gh_owner_pid)); - pr_err("lock type: %d req lock state : %d\n", + fs_err(sdp, "original: %pSR\n", (void *)gh2->gh_ip); + fs_err(sdp, "pid: %d\n", pid_nr(gh2->gh_owner_pid)); + fs_err(sdp, "lock type: %d req lock state : %d\n", gh2->gh_gl->gl_name.ln_type, gh2->gh_state); - pr_err("new: %pSR\n", (void *)gh->gh_ip); - pr_err("pid: %d\n", pid_nr(gh->gh_owner_pid)); - pr_err("lock type: %d req lock state : %d\n", + fs_err(sdp, "new: %pSR\n", (void *)gh->gh_ip); + fs_err(sdp, "pid: %d\n", pid_nr(gh->gh_owner_pid)); + fs_err(sdp, "lock type: %d req lock state : %d\n", gh->gh_gl->gl_name.ln_type, gh->gh_state); gfs2_dump_glock(NULL, gl); BUG(); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index b96d39c28e17..888b62cfd6d1 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -92,7 +92,7 @@ struct gfs2_bitmap { unsigned long bi_flags; u32 bi_offset; u32 bi_start; - u32 bi_len; + u32 bi_bytes; u32 bi_blocks; }; @@ -309,10 +309,6 @@ struct gfs2_qadata { /* quota allocation data */ */ struct gfs2_blkreserv { - /* components used during write (step 1): */ - atomic_t rs_sizehint; /* hint of the write size */ - - struct gfs2_holder rs_rgd_gh; /* Filled in by get_local_rgrp */ struct rb_node rs_node; /* link to other block reservations */ struct gfs2_rbm rs_rbm; /* Start of reservation */ u32 rs_free; /* how many blocks are still free */ @@ -417,8 +413,10 @@ struct gfs2_inode { struct gfs2_holder i_iopen_gh; struct gfs2_holder i_gh; /* for prepare/commit_write only */ struct gfs2_qadata *i_qadata; /* quota allocation data */ + struct gfs2_holder i_rgd_gh; struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */ u64 i_goal; /* goal block for allocations */ + atomic_t i_sizehint; /* hint of the write size */ struct rw_semaphore i_rw_mutex; struct list_head i_ordered; struct list_head i_trunc_list; @@ -623,6 +621,7 @@ enum { SDF_RORECOVERY = 7, /* read only recovery */ SDF_SKIP_DLM_UNLOCK = 8, SDF_FORCE_AIL_FLUSH = 9, + SDF_AIL1_IO_ERROR = 10, }; enum gfs2_freeze_state { diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index ac7caa267ed6..31df26ed7854 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -177,14 +177,14 @@ static void gdlm_bast(void *arg, int mode) gfs2_glock_cb(gl, LM_ST_SHARED); break; default: - pr_err("unknown bast mode %d\n", mode); + fs_err(gl->gl_name.ln_sbd, "unknown bast mode %d\n", mode); BUG(); } } /* convert gfs lock-state to dlm lock-mode */ -static int make_mode(const unsigned int lmstate) +static int make_mode(struct gfs2_sbd *sdp, const unsigned int lmstate) { switch (lmstate) { case LM_ST_UNLOCKED: @@ -196,7 +196,7 @@ static int make_mode(const unsigned int lmstate) case LM_ST_SHARED: return DLM_LOCK_PR; } - pr_err("unknown LM state %d\n", lmstate); + fs_err(sdp, "unknown LM state %d\n", lmstate); BUG(); return -1; } @@ -257,7 +257,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, u32 lkf; char strname[GDLM_STRNAME_BYTES] = ""; - req = make_mode(req_state); + req = make_mode(gl->gl_name.ln_sbd, req_state); lkf = make_flags(gl, flags, req); gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT); gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT); @@ -309,7 +309,7 @@ static void gdlm_put_lock(struct gfs2_glock *gl) error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK, NULL, gl); if (error) { - pr_err("gdlm_unlock %x,%llx err=%d\n", + fs_err(sdp, "gdlm_unlock %x,%llx err=%d\n", gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, error); return; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index ee20ea42e7b5..99dd58694ba1 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -108,7 +108,9 @@ __acquires(&sdp->sd_ail_lock) gfs2_assert(sdp, bd->bd_tr == tr); if (!buffer_busy(bh)) { - if (!buffer_uptodate(bh)) { + if (!buffer_uptodate(bh) && + !test_and_set_bit(SDF_AIL1_IO_ERROR, + &sdp->sd_flags)) { gfs2_io_error_bh(sdp, bh); *withdraw = true; } @@ -206,7 +208,8 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr, gfs2_assert(sdp, bd->bd_tr == tr); if (buffer_busy(bh)) continue; - if (!buffer_uptodate(bh)) { + if (!buffer_uptodate(bh) && + !test_and_set_bit(SDF_AIL1_IO_ERROR, &sdp->sd_flags)) { gfs2_io_error_bh(sdp, bh); *withdraw = true; } @@ -618,7 +621,7 @@ void gfs2_write_revokes(struct gfs2_sbd *sdp) gfs2_ail1_empty(sdp); spin_lock(&sdp->sd_ail_lock); - list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) { + list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) { list_for_each_entry(bd, &tr->tr_ail2_list, bd_ail_st_list) { if (list_empty(&bd->bd_list)) { have_revokes = 1; @@ -642,7 +645,7 @@ done: } gfs2_log_lock(sdp); spin_lock(&sdp->sd_ail_lock); - list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) { + list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) { list_for_each_entry_safe(bd, tmp, &tr->tr_ail2_list, bd_ail_st_list) { if (max_revokes == 0) goto out_of_blocks; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index f2567f958d00..4c7069b8f3c1 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -81,7 +81,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd) if (sdp->sd_args.ar_discard) gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL); memcpy(bi->bi_clone + bi->bi_offset, - bd->bd_bh->b_data + bi->bi_offset, bi->bi_len); + bd->bd_bh->b_data + bi->bi_offset, bi->bi_bytes); clear_bit(GBF_FULL, &bi->bi_flags); rgd->rd_free_clone = rgd->rd_free; rgd->rd_extfail_pt = rgd->rd_free; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 2d55e2c3333c..c7603063f861 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -39,9 +39,11 @@ static void gfs2_init_inode_once(void *foo) struct gfs2_inode *ip = foo; inode_init_once(&ip->i_inode); + atomic_set(&ip->i_sizehint, 0); init_rwsem(&ip->i_rw_mutex); INIT_LIST_HEAD(&ip->i_trunc_list); ip->i_qadata = NULL; + gfs2_holder_mark_uninitialized(&ip->i_rgd_gh); memset(&ip->i_res, 0, sizeof(ip->i_res)); RB_CLEAR_NODE(&ip->i_res.rs_node); ip->i_hash_cache = NULL; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c2469833b4fb..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -72,13 +72,13 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) if (!sdp) return NULL; - sb->s_fs_info = sdp; sdp->sd_vfs = sb; sdp->sd_lkstats = alloc_percpu(struct gfs2_pcpu_lkstats); if (!sdp->sd_lkstats) { kfree(sdp); return NULL; } + sb->s_fs_info = sdp; set_bit(SDF_NOJOURNALID, &sdp->sd_flags); gfs2_tune_init(&sdp->sd_tune); @@ -1333,6 +1333,9 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, struct path path; int error; + if (!dev_name || !*dev_name) + return ERR_PTR(-EINVAL); + error = kern_path(dev_name, LOOKUP_FOLLOW, &path); if (error) { pr_warn("path_lookup on %s returned error %d\n", diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 0efae7a0ee80..2ae5a109eea7 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1183,7 +1183,7 @@ static int print_message(struct gfs2_quota_data *qd, char *type) * * Returns: 0 on success. * min_req = ap->min_target ? ap->min_target : ap->target; - * quota must allow atleast min_req blks for success and + * quota must allow at least min_req blks for success and * ap->allowed is set to the number of blocks allowed * * -EDQUOT otherwise, quota violation. ap->allowed is set to number diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 1ad3256b9cbc..ffe3032b1043 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -90,7 +90,7 @@ static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone, { unsigned char *byte1, *byte2, *end, cur_state; struct gfs2_bitmap *bi = rbm_bi(rbm); - unsigned int buflen = bi->bi_len; + unsigned int buflen = bi->bi_bytes; const unsigned int bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE; byte1 = bi->bi_bh->b_data + bi->bi_offset + (rbm->offset / GFS2_NBBY); @@ -101,12 +101,16 @@ static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone, cur_state = (*byte1 >> bit) & GFS2_BIT_MASK; if (unlikely(!valid_change[new_state * 4 + cur_state])) { - pr_warn("buf_blk = 0x%x old_state=%d, new_state=%d\n", + struct gfs2_sbd *sdp = rbm->rgd->rd_sbd; + + fs_warn(sdp, "buf_blk = 0x%x old_state=%d, new_state=%d\n", rbm->offset, cur_state, new_state); - pr_warn("rgrp=0x%llx bi_start=0x%x\n", - (unsigned long long)rbm->rgd->rd_addr, bi->bi_start); - pr_warn("bi_offset=0x%x bi_len=0x%x\n", - bi->bi_offset, bi->bi_len); + fs_warn(sdp, "rgrp=0x%llx bi_start=0x%x biblk: 0x%llx\n", + (unsigned long long)rbm->rgd->rd_addr, bi->bi_start, + (unsigned long long)bi->bi_bh->b_blocknr); + fs_warn(sdp, "bi_offset=0x%x bi_bytes=0x%x block=0x%llx\n", + bi->bi_offset, bi->bi_bytes, + (unsigned long long)gfs2_rbm_to_block(rbm)); dump_stack(); gfs2_consist_rgrpd(rbm->rgd); return; @@ -269,15 +273,10 @@ static u32 gfs2_bitfit(const u8 *buf, const unsigned int len, static int gfs2_rbm_from_block(struct gfs2_rbm *rbm, u64 block) { - u64 rblock = block - rbm->rgd->rd_data0; - - if (WARN_ON_ONCE(rblock > UINT_MAX)) - return -EINVAL; - if (block >= rbm->rgd->rd_data0 + rbm->rgd->rd_data) + if (!rgrp_contains_block(rbm->rgd, block)) return -E2BIG; - rbm->bii = 0; - rbm->offset = (u32)(rblock); + rbm->offset = block - rbm->rgd->rd_data0; /* Check if the block is within the first block */ if (rbm->offset < rbm_bi(rbm)->bi_blocks) return 0; @@ -382,7 +381,7 @@ static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len) if (bi->bi_clone) start = bi->bi_clone; start += bi->bi_offset; - end = start + bi->bi_len; + end = start + bi->bi_bytes; BUG_ON(rbm.offset & 3); start += (rbm.offset / GFS2_NBBY); bytes = min_t(u32, len / GFS2_NBBY, (end - start)); @@ -467,7 +466,7 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd) count[x] += gfs2_bitcount(rgd, bi->bi_bh->b_data + bi->bi_offset, - bi->bi_len, x); + bi->bi_bytes, x); } if (count[0] != rgd->rd_free) { @@ -642,7 +641,10 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) RB_CLEAR_NODE(&rs->rs_node); if (rs->rs_free) { - struct gfs2_bitmap *bi = rbm_bi(&rs->rs_rbm); + u64 last_block = gfs2_rbm_to_block(&rs->rs_rbm) + + rs->rs_free - 1; + struct gfs2_rbm last_rbm = { .rgd = rs->rs_rbm.rgd, }; + struct gfs2_bitmap *start, *last; /* return reserved blocks to the rgrp */ BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free); @@ -653,7 +655,13 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) it will force the number to be recalculated later. */ rgd->rd_extfail_pt += rs->rs_free; rs->rs_free = 0; - clear_bit(GBF_FULL, &bi->bi_flags); + if (gfs2_rbm_from_block(&last_rbm, last_block)) + return; + start = rbm_bi(&rs->rs_rbm); + last = rbm_bi(&last_rbm); + do + clear_bit(GBF_FULL, &start->bi_flags); + while (start++ != last); } } @@ -738,11 +746,13 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd) { - pr_info("ri_addr = %llu\n", (unsigned long long)rgd->rd_addr); - pr_info("ri_length = %u\n", rgd->rd_length); - pr_info("ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0); - pr_info("ri_data = %u\n", rgd->rd_data); - pr_info("ri_bitbytes = %u\n", rgd->rd_bitbytes); + struct gfs2_sbd *sdp = rgd->rd_sbd; + + fs_info(sdp, "ri_addr = %llu\n", (unsigned long long)rgd->rd_addr); + fs_info(sdp, "ri_length = %u\n", rgd->rd_length); + fs_info(sdp, "ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0); + fs_info(sdp, "ri_data = %u\n", rgd->rd_data); + fs_info(sdp, "ri_bitbytes = %u\n", rgd->rd_bitbytes); } /** @@ -780,21 +790,21 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) bytes = bytes_left; bi->bi_offset = sizeof(struct gfs2_rgrp); bi->bi_start = 0; - bi->bi_len = bytes; + bi->bi_bytes = bytes; bi->bi_blocks = bytes * GFS2_NBBY; /* header block */ } else if (x == 0) { bytes = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_rgrp); bi->bi_offset = sizeof(struct gfs2_rgrp); bi->bi_start = 0; - bi->bi_len = bytes; + bi->bi_bytes = bytes; bi->bi_blocks = bytes * GFS2_NBBY; /* last block */ } else if (x + 1 == length) { bytes = bytes_left; bi->bi_offset = sizeof(struct gfs2_meta_header); bi->bi_start = rgd->rd_bitbytes - bytes_left; - bi->bi_len = bytes; + bi->bi_bytes = bytes; bi->bi_blocks = bytes * GFS2_NBBY; /* other blocks */ } else { @@ -802,7 +812,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) sizeof(struct gfs2_meta_header); bi->bi_offset = sizeof(struct gfs2_meta_header); bi->bi_start = rgd->rd_bitbytes - bytes_left; - bi->bi_len = bytes; + bi->bi_bytes = bytes; bi->bi_blocks = bytes * GFS2_NBBY; } @@ -814,11 +824,11 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) return -EIO; } bi = rgd->rd_bits + (length - 1); - if ((bi->bi_start + bi->bi_len) * GFS2_NBBY != rgd->rd_data) { + if ((bi->bi_start + bi->bi_bytes) * GFS2_NBBY != rgd->rd_data) { if (gfs2_consist_rgrpd(rgd)) { gfs2_rindex_print(rgd); fs_err(sdp, "start=%u len=%u offset=%u\n", - bi->bi_start, bi->bi_len, bi->bi_offset); + bi->bi_start, bi->bi_bytes, bi->bi_offset); } return -EIO; } @@ -1103,12 +1113,35 @@ static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd) { struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl; struct gfs2_rgrp *str = (struct gfs2_rgrp *)rgd->rd_bits[0].bi_bh->b_data; + int valid = 1; - if (rgl->rl_flags != str->rg_flags || rgl->rl_free != str->rg_free || - rgl->rl_dinodes != str->rg_dinodes || - rgl->rl_igeneration != str->rg_igeneration) - return 0; - return 1; + if (rgl->rl_flags != str->rg_flags) { + printk(KERN_WARNING "GFS2: rgd: %llu lvb flag mismatch %u/%u", + (unsigned long long)rgd->rd_addr, + be32_to_cpu(rgl->rl_flags), be32_to_cpu(str->rg_flags)); + valid = 0; + } + if (rgl->rl_free != str->rg_free) { + printk(KERN_WARNING "GFS2: rgd: %llu lvb free mismatch %u/%u", + (unsigned long long)rgd->rd_addr, + be32_to_cpu(rgl->rl_free), be32_to_cpu(str->rg_free)); + valid = 0; + } + if (rgl->rl_dinodes != str->rg_dinodes) { + printk(KERN_WARNING "GFS2: rgd: %llu lvb dinode mismatch %u/%u", + (unsigned long long)rgd->rd_addr, + be32_to_cpu(rgl->rl_dinodes), + be32_to_cpu(str->rg_dinodes)); + valid = 0; + } + if (rgl->rl_igeneration != str->rg_igeneration) { + printk(KERN_WARNING "GFS2: rgd: %llu lvb igen mismatch " + "%llu/%llu", (unsigned long long)rgd->rd_addr, + (unsigned long long)be64_to_cpu(rgl->rl_igeneration), + (unsigned long long)be64_to_cpu(str->rg_igeneration)); + valid = 0; + } + return valid; } static u32 count_unlinked(struct gfs2_rgrpd *rgd) @@ -1122,8 +1155,8 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd) goal = 0; buffer = bi->bi_bh->b_data + bi->bi_offset; WARN_ON(!buffer_uptodate(bi->bi_bh)); - while (goal < bi->bi_len * GFS2_NBBY) { - goal = gfs2_bitfit(buffer, bi->bi_len, goal, + while (goal < bi->bi_blocks) { + goal = gfs2_bitfit(buffer, bi->bi_bytes, goal, GFS2_BLKST_UNLINKED); if (goal == BFITNOENT) break; @@ -1226,7 +1259,7 @@ static int update_rgrp_lvb(struct gfs2_rgrpd *rgd) rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags); rl_flags &= ~GFS2_RDF_MASK; rgd->rd_flags &= GFS2_RDF_MASK; - rgd->rd_flags |= (rl_flags | GFS2_RDF_UPTODATE | GFS2_RDF_CHECK); + rgd->rd_flags |= (rl_flags | GFS2_RDF_CHECK); if (rgd->rd_rgl->rl_unlinked == 0) rgd->rd_flags &= ~GFS2_RDF_CHECK; rgd->rd_free = be32_to_cpu(rgd->rd_rgl->rl_free); @@ -1295,7 +1328,7 @@ int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, u32 trimmed = 0; u8 diff; - for (x = 0; x < bi->bi_len; x++) { + for (x = 0; x < bi->bi_bytes; x++) { const u8 *clone = bi->bi_clone ? bi->bi_clone : bi->bi_bh->b_data; clone += bi->bi_offset; clone += x; @@ -1541,8 +1574,8 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip, if (S_ISDIR(inode->i_mode)) extlen = 1; else { - extlen = max_t(u32, atomic_read(&rs->rs_sizehint), ap->target); - extlen = clamp(extlen, RGRP_RSRV_MINBLKS, free_blocks); + extlen = max_t(u32, atomic_read(&ip->i_sizehint), ap->target); + extlen = clamp(extlen, (u32)RGRP_RSRV_MINBLKS, free_blocks); } if ((rgd->rd_free_clone < rgd->rd_reserved) || (free_blocks < extlen)) return; @@ -1728,7 +1761,7 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, if (state != GFS2_BLKST_UNLINKED && bi->bi_clone) buffer = bi->bi_clone + bi->bi_offset; initial_offset = rbm->offset; - offset = gfs2_bitfit(buffer, bi->bi_len, rbm->offset, state); + offset = gfs2_bitfit(buffer, bi->bi_bytes, rbm->offset, state); if (offset == BFITNOENT) goto bitmap_full; rbm->offset = offset; @@ -1999,7 +2032,7 @@ static inline int fast_to_acquire(struct gfs2_rgrpd *rgd) * We try our best to find an rgrp that has at least ap->target blocks * available. After a couple of passes (loops == 2), the prospects of finding * such an rgrp diminish. At this stage, we return the first rgrp that has - * atleast ap->min_target blocks available. Either way, we set ap->allowed to + * at least ap->min_target blocks available. Either way, we set ap->allowed to * the number of blocks available in the chosen rgrp. * * Returns: 0 on success, @@ -2053,7 +2086,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap) } error = gfs2_glock_nq_init(rs->rs_rbm.rgd->rd_gl, LM_ST_EXCLUSIVE, flags, - &rs->rs_rgd_gh); + &ip->i_rgd_gh); if (unlikely(error)) return error; if (!gfs2_rs_active(rs) && (loops < 2) && @@ -2062,13 +2095,13 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap) if (sdp->sd_args.ar_rgrplvb) { error = update_rgrp_lvb(rs->rs_rbm.rgd); if (unlikely(error)) { - gfs2_glock_dq_uninit(&rs->rs_rgd_gh); + gfs2_glock_dq_uninit(&ip->i_rgd_gh); return error; } } } - /* Skip unuseable resource groups */ + /* Skip unusable resource groups */ if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) || (loops == 0 && ap->target > rs->rs_rbm.rgd->rd_extfail_pt)) @@ -2105,7 +2138,7 @@ skip_rgrp: /* Unlock rgrp if required */ if (!rg_locked) - gfs2_glock_dq_uninit(&rs->rs_rgd_gh); + gfs2_glock_dq_uninit(&ip->i_rgd_gh); next_rgrp: /* Find the next rgrp, and continue looking */ if (gfs2_select_rgrp(&rs->rs_rbm.rgd, begin)) @@ -2142,10 +2175,8 @@ next_rgrp: void gfs2_inplace_release(struct gfs2_inode *ip) { - struct gfs2_blkreserv *rs = &ip->i_res; - - if (gfs2_holder_initialized(&rs->rs_rgd_gh)) - gfs2_glock_dq_uninit(&rs->rs_rgd_gh); + if (gfs2_holder_initialized(&ip->i_rgd_gh)) + gfs2_glock_dq_uninit(&ip->i_rgd_gh); } /** @@ -2184,27 +2215,21 @@ static void gfs2_alloc_extent(const struct gfs2_rbm *rbm, bool dinode, /** * rgblk_free - Change alloc state of given block(s) * @sdp: the filesystem + * @rgd: the resource group the blocks are in * @bstart: the start of a run of blocks to free * @blen: the length of the block run (all must lie within ONE RG!) * @new_state: GFS2_BLKST_XXX the after-allocation block state - * - * Returns: Resource group containing the block(s) */ -static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, - u32 blen, unsigned char new_state) +static void rgblk_free(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd, + u64 bstart, u32 blen, unsigned char new_state) { struct gfs2_rbm rbm; struct gfs2_bitmap *bi, *bi_prev = NULL; - rbm.rgd = gfs2_blk2rgrpd(sdp, bstart, 1); - if (!rbm.rgd) { - if (gfs2_consist(sdp)) - fs_err(sdp, "block = %llu\n", (unsigned long long)bstart); - return NULL; - } - - gfs2_rbm_from_block(&rbm, bstart); + rbm.rgd = rgd; + if (WARN_ON_ONCE(gfs2_rbm_from_block(&rbm, bstart))) + return; while (blen--) { bi = rbm_bi(&rbm); if (bi != bi_prev) { @@ -2213,7 +2238,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, GFP_NOFS | __GFP_NOFAIL); memcpy(bi->bi_clone + bi->bi_offset, bi->bi_bh->b_data + bi->bi_offset, - bi->bi_len); + bi->bi_bytes); } gfs2_trans_add_meta(rbm.rgd->rd_gl, bi->bi_bh); bi_prev = bi; @@ -2221,8 +2246,6 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, gfs2_setbit(&rbm, false, new_state); gfs2_rbm_incr(&rbm); } - - return rbm.rgd; } /** @@ -2244,6 +2267,14 @@ void gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl) (unsigned long long)rgd->rd_addr, rgd->rd_flags, rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes, rgd->rd_reserved, rgd->rd_extfail_pt); + if (rgd->rd_sbd->sd_args.ar_rgrplvb) { + struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl; + + gfs2_print_dbg(seq, " L: f:%02x b:%u i:%u\n", + be32_to_cpu(rgl->rl_flags), + be32_to_cpu(rgl->rl_free), + be32_to_cpu(rgl->rl_dinodes)); + } spin_lock(&rgd->rd_rsspin); for (n = rb_first(&rgd->rd_rstree); n; n = rb_next(&trs->rs_node)) { trs = rb_entry(n, struct gfs2_blkreserv, rs_node); @@ -2295,7 +2326,7 @@ static void gfs2_adjust_reservation(struct gfs2_inode *ip, goto out; /* We used up our block reservation, so we should reserve more blocks next time. */ - atomic_add(RGRP_RSRV_ADDBLKS, &rs->rs_sizehint); + atomic_add(RGRP_RSRV_ADDBLKS, &ip->i_sizehint); } __rs_deltree(rs); } @@ -2329,7 +2360,10 @@ static void gfs2_set_alloc_start(struct gfs2_rbm *rbm, else goal = rbm->rgd->rd_last_alloc + rbm->rgd->rd_data0; - gfs2_rbm_from_block(rbm, goal); + if (WARN_ON_ONCE(gfs2_rbm_from_block(rbm, goal))) { + rbm->bii = 0; + rbm->offset = 0; + } } /** @@ -2392,7 +2426,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, } } if (rbm.rgd->rd_free < *nblocks) { - pr_warn("nblocks=%u\n", *nblocks); + fs_warn(sdp, "nblocks=%u\n", *nblocks); goto rgrp_error; } @@ -2427,20 +2461,19 @@ rgrp_error: /** * __gfs2_free_blocks - free a contiguous run of block(s) * @ip: the inode these blocks are being freed from + * @rgd: the resource group the blocks are in * @bstart: first block of a run of contiguous blocks * @blen: the length of the block run * @meta: 1 if the blocks represent metadata * */ -void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta) +void __gfs2_free_blocks(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, + u64 bstart, u32 blen, int meta) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_rgrpd *rgd; - rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE); - if (!rgd) - return; + rgblk_free(sdp, rgd, bstart, blen, GFS2_BLKST_FREE); trace_gfs2_block_alloc(ip, rgd, bstart, blen, GFS2_BLKST_FREE); rgd->rd_free += blen; rgd->rd_flags &= ~GFS2_RGF_TRIMMED; @@ -2455,16 +2488,18 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta) /** * gfs2_free_meta - free a contiguous run of data block(s) * @ip: the inode these blocks are being freed from + * @rgd: the resource group the blocks are in * @bstart: first block of a run of contiguous blocks * @blen: the length of the block run * */ -void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen) +void gfs2_free_meta(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, + u64 bstart, u32 blen) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - __gfs2_free_blocks(ip, bstart, blen, 1); + __gfs2_free_blocks(ip, rgd, bstart, blen, 1); gfs2_statfs_change(sdp, 0, +blen, 0); gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid); } @@ -2476,9 +2511,10 @@ void gfs2_unlink_di(struct inode *inode) struct gfs2_rgrpd *rgd; u64 blkno = ip->i_no_addr; - rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED); + rgd = gfs2_blk2rgrpd(sdp, blkno, true); if (!rgd) return; + rgblk_free(sdp, rgd, blkno, 1, GFS2_BLKST_UNLINKED); trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED); gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh); gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); @@ -2488,13 +2524,8 @@ void gfs2_unlink_di(struct inode *inode) void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) { struct gfs2_sbd *sdp = rgd->rd_sbd; - struct gfs2_rgrpd *tmp_rgd; - - tmp_rgd = rgblk_free(sdp, ip->i_no_addr, 1, GFS2_BLKST_FREE); - if (!tmp_rgd) - return; - gfs2_assert_withdraw(sdp, rgd == tmp_rgd); + rgblk_free(sdp, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE); if (!rgd->rd_dinodes) gfs2_consist_rgrpd(rgd); rgd->rd_dinodes--; @@ -2538,7 +2569,8 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) rbm.rgd = rgd; error = gfs2_rbm_from_block(&rbm, no_addr); - WARN_ON_ONCE(error != 0); + if (WARN_ON_ONCE(error)) + goto fail; if (gfs2_testbit(&rbm, false) != type) error = -ESTALE; @@ -2624,13 +2656,12 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, * gfs2_rlist_alloc - all RGs have been added to the rlist, now allocate * and initialize an array of glock holders for them * @rlist: the list of resource groups - * @state: the lock state to acquire the RG lock in * * FIXME: Don't use NOFAIL * */ -void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state) +void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist) { unsigned int x; @@ -2639,7 +2670,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state) GFP_NOFS | __GFP_NOFAIL); for (x = 0; x < rlist->rl_rgrps; x++) gfs2_holder_init(rlist->rl_rgd[x]->rd_gl, - state, 0, + LM_ST_EXCLUSIVE, 0, &rlist->rl_ghs[x]); } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index e90478e2f545..b596c3d17988 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -18,8 +18,7 @@ * By reserving 32 blocks at a time, we can optimize / shortcut how we search * through the bitmaps by looking a word at a time. */ -#define RGRP_RSRV_MINBYTES 8 -#define RGRP_RSRV_MINBLKS ((u32)(RGRP_RSRV_MINBYTES * GFS2_NBBY)) +#define RGRP_RSRV_MINBLKS 32 #define RGRP_RSRV_ADDBLKS 64 struct gfs2_rgrpd; @@ -52,8 +51,10 @@ extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, extern int gfs2_rsqa_alloc(struct gfs2_inode *ip); extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); extern void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount); -extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta); -extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern void __gfs2_free_blocks(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, + u64 bstart, u32 blen, int meta); +extern void gfs2_free_meta(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, + u64 bstart, u32 blen); extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); extern void gfs2_unlink_di(struct inode *inode); extern int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, @@ -68,7 +69,7 @@ struct gfs2_rgrp_list { extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, u64 block); -extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); +extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist); extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); extern u64 gfs2_ri_total(struct gfs2_sbd *sdp); extern void gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index c212893534ed..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -854,10 +854,10 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) return error; + flush_workqueue(gfs2_delete_workqueue); kthread_stop(sdp->sd_quotad_process); kthread_stop(sdp->sd_logd_process); - flush_workqueue(gfs2_delete_workqueue); gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); @@ -971,7 +971,7 @@ void gfs2_freeze_func(struct work_struct *work) error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, &freeze_gh); if (error) { - printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error); + printk(KERN_INFO "GFS2: couldn't get freeze lock : %d\n", error); gfs2_assert_withdraw(sdp, 0); } else { diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 064c9a0ef046..423bc2d03dd8 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -74,13 +74,13 @@ fail: return error; } -static void gfs2_print_trans(const struct gfs2_trans *tr) +static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr) { - pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip); - pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n", + fs_warn(sdp, "Transaction created at: %pSR\n", (void *)tr->tr_ip); + fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n", tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, test_bit(TR_TOUCHED, &tr->tr_flags)); - pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n", + fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n", tr->tr_num_buf_new, tr->tr_num_buf_rm, tr->tr_num_databuf_new, tr->tr_num_databuf_rm, tr->tr_num_revoke, tr->tr_num_revoke_rm); @@ -109,7 +109,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) && (tr->tr_num_revoke <= tr->tr_revokes))) - gfs2_print_trans(tr); + gfs2_print_trans(sdp, tr); gfs2_log_commit(sdp, tr); if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags)) @@ -225,12 +225,13 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) { - pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n", + fs_err(sdp, "Attempting to add uninitialised block to " + "journal (inplace block=%lld)\n", (unsigned long long)bd->bd_bh->b_blocknr); BUG(); } if (unlikely(state == SFS_FROZEN)) { - printk(KERN_INFO "GFS2:adding buf while frozen\n"); + fs_info(sdp, "GFS2:adding buf while frozen\n"); gfs2_assert_withdraw(sdp, 0); } gfs2_pin(sdp, bd->bd_bh); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 59c811de0dc7..0a814ccac41d 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -19,6 +19,7 @@ #include "gfs2.h" #include "incore.h" #include "glock.h" +#include "rgrp.h" #include "util.h" struct kmem_cache *gfs2_glock_cachep __read_mostly; @@ -181,6 +182,8 @@ int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide, { struct gfs2_sbd *sdp = rgd->rd_sbd; int rv; + + gfs2_rgrp_dump(NULL, rgd->rd_gl); rv = gfs2_lm_withdraw(sdp, "fatal: filesystem consistency error\n" " RG = %llu\n" @@ -256,12 +259,13 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh, const char *function, char *file, unsigned int line, bool withdraw) { - fs_err(sdp, - "fatal: I/O error\n" - " block = %llu\n" - " function = %s, file = %s, line = %u\n", - (unsigned long long)bh->b_blocknr, - function, file, line); + if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + fs_err(sdp, + "fatal: I/O error\n" + " block = %llu\n" + " function = %s, file = %s, line = %u\n", + (unsigned long long)bh->b_blocknr, + function, file, line); if (withdraw) gfs2_lm_withdraw(sdp, NULL); } diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index 96ac4aba4738..9278fecba632 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -86,7 +86,7 @@ static inline int gfs2_meta_check(struct gfs2_sbd *sdp, struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data; u32 magic = be32_to_cpu(mh->mh_magic); if (unlikely(magic != GFS2_MAGIC)) { - pr_err("Magic number missing at %llu\n", + fs_err(sdp, "Magic number missing at %llu\n", (unsigned long long)bh->b_blocknr); return -EIO; } diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 38515988aaf7..996c915a9c97 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -283,7 +283,7 @@ static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh, blen++; else { if (bstart) - gfs2_free_meta(ip, bstart, blen); + gfs2_free_meta(ip, rgd, bstart, blen); bstart = bn; blen = 1; } @@ -292,7 +292,7 @@ static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh, gfs2_add_inode_blocks(&ip->i_inode, -1); } if (bstart) - gfs2_free_meta(ip, bstart, blen); + gfs2_free_meta(ip, rgd, bstart, blen); if (prev && !leave) { u32 len; @@ -1250,6 +1250,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrp_list rlist; + struct gfs2_rgrpd *rgd; struct buffer_head *indbh, *dibh; __be64 *eablk, *end; unsigned int rg_blocks = 0; @@ -1299,11 +1300,10 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) else goto out; - gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); + gfs2_rlist_alloc(&rlist); for (x = 0; x < rlist.rl_rgrps; x++) { - struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); - + rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); rg_blocks += rgd->rd_length; } @@ -1320,6 +1320,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) eablk = (__be64 *)(indbh->b_data + sizeof(struct gfs2_meta_header)); bstart = 0; + rgd = NULL; blen = 0; for (; eablk < end; eablk++) { @@ -1333,8 +1334,9 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) blen++; else { if (bstart) - gfs2_free_meta(ip, bstart, blen); + gfs2_free_meta(ip, rgd, bstart, blen); bstart = bn; + rgd = gfs2_blk2rgrpd(sdp, bstart, true); blen = 1; } @@ -1342,7 +1344,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) gfs2_add_inode_blocks(&ip->i_inode, -1); } if (bstart) - gfs2_free_meta(ip, bstart, blen); + gfs2_free_meta(ip, rgd, bstart, blen); ip->i_diskflags &= ~GFS2_DIF_EA_INDIRECT; @@ -1391,7 +1393,7 @@ static int ea_dealloc_block(struct gfs2_inode *ip) if (error) goto out_gunlock; - gfs2_free_meta(ip, ip->i_eattr, 1); + gfs2_free_meta(ip, rgd, ip->i_eattr, 1); ip->i_eattr = 0; gfs2_add_inode_blocks(&ip->i_inode, -1); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index c125d662777c..26f8d7e46462 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -251,8 +251,8 @@ restart: bh = jh2bh(jh); if (buffer_locked(bh)) { - spin_unlock(&journal->j_list_lock); get_bh(bh); + spin_unlock(&journal->j_list_lock); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); @@ -333,8 +333,8 @@ restart2: jh = transaction->t_checkpoint_io_list; bh = jh2bh(jh); if (buffer_locked(bh)) { - spin_unlock(&journal->j_list_lock); get_bh(bh); + spin_unlock(&journal->j_list_lock); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 2e71b6e7e646..8c06a6ea862d 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -146,12 +146,16 @@ int jfs_init_acl(tid_t tid, struct inode *inode, struct inode *dir) if (default_acl) { rc = __jfs_set_acl(tid, inode, ACL_TYPE_DEFAULT, default_acl); posix_acl_release(default_acl); + } else { + inode->i_default_acl = NULL; } if (acl) { if (!rc) rc = __jfs_set_acl(tid, inode, ACL_TYPE_ACCESS, acl); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } JFS_IP(inode)->mode2 = (JFS_IP(inode)->mode2 & 0xffff0000) | diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 054cc761b426..805ae9e8944a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -166,7 +166,6 @@ void jfs_evict_inode(struct inode *inode) /* * Free the inode from the quota allocation. */ - dquot_initialize(inode); dquot_free_inode(inode); } } else { diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 09da5cf14e27..65d8fc87ab11 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -247,7 +247,7 @@ static const match_table_t tokens = { {Opt_resize_nosize, "resize"}, {Opt_errors, "errors=%s"}, {Opt_ignore, "noquota"}, - {Opt_ignore, "quota"}, + {Opt_quota, "quota"}, {Opt_usrquota, "usrquota"}, {Opt_grpquota, "grpquota"}, {Opt_uid, "uid=%u"}, diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index 10587413b20e..72d2ff17d27b 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -167,12 +167,16 @@ int orangefs_init_acl(struct inode *inode, struct inode *dir) error = __orangefs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); + } else { + inode->i_default_acl = NULL; } if (acl) { if (!error) error = __orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } /* If mode of the inode was changed, then do a forcible ->setattr */ diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 31932879b716..5e65d818937b 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -405,7 +405,11 @@ struct inode *orangefs_iget(struct super_block *sb, orangefs_test_inode, orangefs_set_inode, ref); - if (!inode || !(inode->i_state & I_NEW)) + + if (!inode) + return ERR_PTR(-ENOMEM); + + if (!(inode->i_state & I_NEW)) return inode; error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL); @@ -448,7 +452,7 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir, inode = new_inode(sb); if (!inode) - return NULL; + return ERR_PTR(-ENOMEM); orangefs_set_inode(inode, ref); inode->i_ino = hash; /* needed for stat etc */ diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index 625b0580f9be..c8676c996249 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -58,7 +58,6 @@ static int orangefs_create(struct inode *dir, goto out; ref = new_op->downcall.resp.create.refn; - op_release(new_op); inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0, &ref); if (IS_ERR(inode)) { @@ -92,6 +91,7 @@ static int orangefs_create(struct inode *dir, mark_inode_dirty_sync(dir); ret = 0; out: + op_release(new_op); gossip_debug(GOSSIP_NAME_DEBUG, "%s: %pd: returning %d\n", __func__, @@ -157,7 +157,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry, new_op->downcall.resp.lookup.refn.fs_id, ret); - if (ret >= 0) { + if (ret == 0) { orangefs_set_timeout(dentry); inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn); } else if (ret == -ENOENT) { @@ -269,7 +269,6 @@ static int orangefs_symlink(struct inode *dir, } ref = new_op->downcall.resp.sym.refn; - op_release(new_op); inode = orangefs_new_inode(dir->i_sb, dir, S_IFLNK | mode, 0, &ref); if (IS_ERR(inode)) { @@ -307,6 +306,7 @@ static int orangefs_symlink(struct inode *dir, mark_inode_dirty_sync(dir); ret = 0; out: + op_release(new_op); return ret; } @@ -346,7 +346,6 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode } ref = new_op->downcall.resp.mkdir.refn; - op_release(new_op); inode = orangefs_new_inode(dir->i_sb, dir, S_IFDIR | mode, 0, &ref); if (IS_ERR(inode)) { @@ -379,6 +378,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode orangefs_inode_setattr(dir, &iattr); mark_inode_dirty_sync(dir); out: + op_release(new_op); return ret; } diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c index dd28079f518c..19739aaee675 100644 --- a/fs/orangefs/orangefs-sysfs.c +++ b/fs/orangefs/orangefs-sysfs.c @@ -323,7 +323,7 @@ static ssize_t sysfs_service_op_show(struct kobject *kobj, /* Can't do a service_operation if the client is not running... */ rc = is_daemon_in_service(); if (rc) { - pr_info("%s: Client not running :%d:\n", + pr_info_ratelimited("%s: Client not running :%d:\n", __func__, is_daemon_in_service()); goto out; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index c6299f82a6e4..844ed87b1900 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -191,6 +191,128 @@ xfs_attr_calc_size( return nblks; } +STATIC int +xfs_attr_try_sf_addname( + struct xfs_inode *dp, + struct xfs_da_args *args) +{ + + struct xfs_mount *mp = dp->i_mount; + int error, error2; + + error = xfs_attr_shortform_addname(args); + if (error == -ENOSPC) + return error; + + /* + * Commit the shortform mods, and we're done. + * NOTE: this is also the error path (EEXIST, etc). + */ + if (!error && (args->flags & ATTR_KERNOTIME) == 0) + xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(args->trans); + + error2 = xfs_trans_commit(args->trans); + args->trans = NULL; + return error ? error : error2; +} + +/* + * Set the attribute specified in @args. + */ +int +xfs_attr_set_args( + struct xfs_da_args *args, + struct xfs_buf **leaf_bp) +{ + struct xfs_inode *dp = args->dp; + int error; + + /* + * If the attribute list is non-existent or a shortform list, + * upgrade it to a single-leaf-block attribute list. + */ + if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL || + (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS && + dp->i_d.di_anextents == 0)) { + + /* + * Build initial attribute list (if required). + */ + if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) + xfs_attr_shortform_create(args); + + /* + * Try to add the attr to the attribute list in the inode. + */ + error = xfs_attr_try_sf_addname(dp, args); + if (error != -ENOSPC) + return error; + + /* + * It won't fit in the shortform, transform to a leaf block. + * GROT: another possible req'mt for a double-split btree op. + */ + error = xfs_attr_shortform_to_leaf(args, leaf_bp); + if (error) + return error; + + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + */ + xfs_trans_bhold(args->trans, *leaf_bp); + + error = xfs_defer_finish(&args->trans); + if (error) + return error; + + /* + * Commit the leaf transformation. We'll need another + * (linked) transaction to add the new attribute to the + * leaf. + */ + error = xfs_trans_roll_inode(&args->trans, dp); + if (error) + return error; + xfs_trans_bjoin(args->trans, *leaf_bp); + *leaf_bp = NULL; + } + + if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) + error = xfs_attr_leaf_addname(args); + else + error = xfs_attr_node_addname(args); + return error; +} + +/* + * Remove the attribute specified in @args. + */ +int +xfs_attr_remove_args( + struct xfs_da_args *args) +{ + struct xfs_inode *dp = args->dp; + int error; + + if (!xfs_inode_hasattr(dp)) { + error = -ENOATTR; + } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { + ASSERT(dp->i_afp->if_flags & XFS_IFINLINE); + error = xfs_attr_shortform_remove(args); + } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { + error = xfs_attr_leaf_removename(args); + } else { + error = xfs_attr_node_removename(args); + } + + return error; +} + int xfs_attr_set( struct xfs_inode *dp, @@ -204,7 +326,7 @@ xfs_attr_set( struct xfs_da_args args; struct xfs_trans_res tres; int rsvd = (flags & ATTR_ROOT) != 0; - int error, err2, local; + int error, local; XFS_STATS_INC(mp, xs_attr_set); @@ -255,93 +377,17 @@ xfs_attr_set( error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0, rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES : XFS_QMOPT_RES_REGBLKS); - if (error) { - xfs_iunlock(dp, XFS_ILOCK_EXCL); - xfs_trans_cancel(args.trans); - return error; - } + if (error) + goto out_trans_cancel; xfs_trans_ijoin(args.trans, dp, 0); - - /* - * If the attribute list is non-existent or a shortform list, - * upgrade it to a single-leaf-block attribute list. - */ - if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL || - (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS && - dp->i_d.di_anextents == 0)) { - - /* - * Build initial attribute list (if required). - */ - if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) - xfs_attr_shortform_create(&args); - - /* - * Try to add the attr to the attribute list in - * the inode. - */ - error = xfs_attr_shortform_addname(&args); - if (error != -ENOSPC) { - /* - * Commit the shortform mods, and we're done. - * NOTE: this is also the error path (EEXIST, etc). - */ - ASSERT(args.trans != NULL); - - /* - * If this is a synchronous mount, make sure that - * the transaction goes to disk before returning - * to the user. - */ - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(args.trans); - - if (!error && (flags & ATTR_KERNOTIME) == 0) { - xfs_trans_ichgtime(args.trans, dp, - XFS_ICHGTIME_CHG); - } - err2 = xfs_trans_commit(args.trans); - xfs_iunlock(dp, XFS_ILOCK_EXCL); - - return error ? error : err2; - } - - /* - * It won't fit in the shortform, transform to a leaf block. - * GROT: another possible req'mt for a double-split btree op. - */ - error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); - if (error) - goto out; - /* - * Prevent the leaf buffer from being unlocked so that a - * concurrent AIL push cannot grab the half-baked leaf - * buffer and run into problems with the write verifier. - */ - xfs_trans_bhold(args.trans, leaf_bp); - error = xfs_defer_finish(&args.trans); - if (error) - goto out; - - /* - * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf, which - * means that we have to hold & join the leaf buffer here too. - */ - error = xfs_trans_roll_inode(&args.trans, dp); - if (error) - goto out; - xfs_trans_bjoin(args.trans, leaf_bp); - leaf_bp = NULL; - } - - if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) - error = xfs_attr_leaf_addname(&args); - else - error = xfs_attr_node_addname(&args); + error = xfs_attr_set_args(&args, &leaf_bp); if (error) - goto out; + goto out_release_leaf; + if (!args.trans) { + /* shortform attribute has already been committed */ + goto out_unlock; + } /* * If this is a synchronous mount, make sure that the @@ -358,17 +404,17 @@ xfs_attr_set( */ xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE); error = xfs_trans_commit(args.trans); +out_unlock: xfs_iunlock(dp, XFS_ILOCK_EXCL); - return error; -out: +out_release_leaf: if (leaf_bp) xfs_trans_brelse(args.trans, leaf_bp); +out_trans_cancel: if (args.trans) xfs_trans_cancel(args.trans); - xfs_iunlock(dp, XFS_ILOCK_EXCL); - return error; + goto out_unlock; } /* @@ -423,17 +469,7 @@ xfs_attr_remove( */ xfs_trans_ijoin(args.trans, dp, 0); - if (!xfs_inode_hasattr(dp)) { - error = -ENOATTR; - } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { - ASSERT(dp->i_afp->if_flags & XFS_IFINLINE); - error = xfs_attr_shortform_remove(&args); - } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { - error = xfs_attr_leaf_removename(&args); - } else { - error = xfs_attr_node_removename(&args); - } - + error = xfs_attr_remove_args(&args); if (error) goto out; diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 033ff8c478e2..bdf52a333f3f 100644 --- a/fs/xfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -140,7 +140,9 @@ int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name, unsigned char *value, int *valuelenp, int flags); int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name, unsigned char *value, int valuelen, int flags); +int xfs_attr_set_args(struct xfs_da_args *args, struct xfs_buf **leaf_bp); int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags); +int xfs_attr_remove_args(struct xfs_da_args *args); int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize, int flags, struct attrlist_cursor_kern *cursor); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index a47670332326..74d7228e755b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1019,6 +1019,34 @@ xfs_bmap_add_attrfork_local( return -EFSCORRUPTED; } +/* Set an inode attr fork off based on the format */ +int +xfs_bmap_set_attrforkoff( + struct xfs_inode *ip, + int size, + int *version) +{ + switch (ip->i_d.di_format) { + case XFS_DINODE_FMT_DEV: + ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; + break; + case XFS_DINODE_FMT_LOCAL: + case XFS_DINODE_FMT_EXTENTS: + case XFS_DINODE_FMT_BTREE: + ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size); + if (!ip->i_d.di_forkoff) + ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3; + else if ((ip->i_mount->m_flags & XFS_MOUNT_ATTR2) && version) + *version = 2; + break; + default: + ASSERT(0); + return -EINVAL; + } + + return 0; +} + /* * Convert inode from non-attributed to attributed. * Must not be in a transaction, ip must not be locked. @@ -1070,26 +1098,9 @@ xfs_bmap_add_attrfork( xfs_trans_ijoin(tp, ip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - switch (ip->i_d.di_format) { - case XFS_DINODE_FMT_DEV: - ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; - break; - case XFS_DINODE_FMT_LOCAL: - case XFS_DINODE_FMT_EXTENTS: - case XFS_DINODE_FMT_BTREE: - ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size); - if (!ip->i_d.di_forkoff) - ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3; - else if (mp->m_flags & XFS_MOUNT_ATTR2) - version = 2; - break; - default: - ASSERT(0); - error = -EINVAL; + error = xfs_bmap_set_attrforkoff(ip, size, &version); + if (error) goto trans_cancel; - } - ASSERT(ip->i_afp == NULL); ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP); ip->i_afp->if_flags = XFS_IFEXTENTS; @@ -4081,8 +4092,7 @@ xfs_bmapi_allocate( * extents to real extents when we're about to write the data. */ if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) && - (bma->flags & XFS_BMAPI_PREALLOC) && - xfs_sb_version_hasextflgbit(&mp->m_sb)) + (bma->flags & XFS_BMAPI_PREALLOC)) bma->got.br_state = XFS_EXT_UNWRITTEN; if (bma->wasdel) @@ -5245,8 +5255,7 @@ __xfs_bunmapi( * unmapping part of it. But we can't really * get rid of part of a realtime extent. */ - if (del.br_state == XFS_EXT_UNWRITTEN || - !xfs_sb_version_hasextflgbit(&mp->m_sb)) { + if (del.br_state == XFS_EXT_UNWRITTEN) { /* * This piece is unwritten, or we're not * using unwritten extents. Skip over it. @@ -5296,10 +5305,9 @@ __xfs_bunmapi( del.br_blockcount -= mod; del.br_startoff += mod; del.br_startblock += mod; - } else if ((del.br_startoff == start && - (del.br_state == XFS_EXT_UNWRITTEN || - tp->t_blk_res == 0)) || - !xfs_sb_version_hasextflgbit(&mp->m_sb)) { + } else if (del.br_startoff == start && + (del.br_state == XFS_EXT_UNWRITTEN || + tp->t_blk_res == 0)) { /* * Can't make it unwritten. There isn't * a full extent here so just skip it. @@ -6114,11 +6122,7 @@ xfs_bmap_validate_extent( XFS_FSB_TO_AGNO(mp, endfsb)) return __this_address; } - if (irec->br_state != XFS_EXT_NORM) { - if (whichfork != XFS_DATA_FORK) - return __this_address; - if (!xfs_sb_version_hasextflgbit(&mp->m_sb)) - return __this_address; - } + if (irec->br_state != XFS_EXT_NORM && whichfork != XFS_DATA_FORK) + return __this_address; return NULL; } diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index b6e9b639e731..488dc8860fd7 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -183,6 +183,7 @@ void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); +int xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void __xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, struct xfs_owner_info *oinfo, diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index afbe336600e1..9995d5ae380b 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -287,6 +287,8 @@ static inline bool xfs_sb_good_v4_features(struct xfs_sb *sbp) { if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT)) return false; + if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT)) + return false; /* check for unknown features in the fs */ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) || @@ -357,12 +359,6 @@ static inline bool xfs_sb_version_haslogv2(struct xfs_sb *sbp) (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT); } -static inline bool xfs_sb_version_hasextflgbit(struct xfs_sb *sbp) -{ - return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 || - (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT); -} - static inline bool xfs_sb_version_hassector(struct xfs_sb *sbp) { return (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 081f46e30556..b5a82acd7dfe 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1115,7 +1115,8 @@ xfs_fs_geometry( geo->version = XFS_FSOP_GEOM_VERSION; geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK | - XFS_FSOP_GEOM_FLAGS_DIRV2; + XFS_FSOP_GEOM_FLAGS_DIRV2 | + XFS_FSOP_GEOM_FLAGS_EXTFLG; if (xfs_sb_version_hasattr(sbp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR; if (xfs_sb_version_hasquota(sbp)) @@ -1124,8 +1125,6 @@ xfs_fs_geometry( geo->flags |= XFS_FSOP_GEOM_FLAGS_IALIGN; if (xfs_sb_version_hasdalign(sbp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_DALIGN; - if (xfs_sb_version_hasextflgbit(sbp)) - geo->flags |= XFS_FSOP_GEOM_FLAGS_EXTFLG; if (xfs_sb_version_hassector(sbp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR; if (xfs_sb_version_hasasciici(sbp)) diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 9f08dd9bf1d5..4fc0a5ea7673 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -29,6 +29,8 @@ #include "xfs_ag_resv.h" #include "xfs_trans_space.h" #include "xfs_quota.h" +#include "xfs_attr.h" +#include "xfs_reflink.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -692,13 +694,14 @@ xrep_findroot_block( struct xrep_find_ag_btree *fab, uint64_t owner, xfs_agblock_t agbno, - bool *found_it) + bool *done_with_block) { struct xfs_mount *mp = ri->sc->mp; struct xfs_buf *bp; struct xfs_btree_block *btblock; xfs_daddr_t daddr; - int error; + int block_level; + int error = 0; daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.agno, agbno); @@ -717,36 +720,111 @@ xrep_findroot_block( return error; } + /* + * Read the buffer into memory so that we can see if it's a match for + * our btree type. We have no clue if it is beforehand, and we want to + * avoid xfs_trans_read_buf's behavior of dumping the DONE state (which + * will cause needless disk reads in subsequent calls to this function) + * and logging metadata verifier failures. + * + * Therefore, pass in NULL buffer ops. If the buffer was already in + * memory from some other caller it will already have b_ops assigned. + * If it was in memory from a previous unsuccessful findroot_block + * call, the buffer won't have b_ops but it should be clean and ready + * for us to try to verify if the read call succeeds. The same applies + * if the buffer wasn't in memory at all. + * + * Note: If we never match a btree type with this buffer, it will be + * left in memory with NULL b_ops. This shouldn't be a problem unless + * the buffer gets written. + */ error = xfs_trans_read_buf(mp, ri->sc->tp, mp->m_ddev_targp, daddr, mp->m_bsize, 0, &bp, NULL); if (error) return error; - /* - * Does this look like a block matching our fs and higher than any - * other block we've found so far? If so, reattach buffer verifiers - * so the AIL won't complain if the buffer is also dirty. - */ + /* Ensure the block magic matches the btree type we're looking for. */ btblock = XFS_BUF_TO_BLOCK(bp); if (be32_to_cpu(btblock->bb_magic) != fab->magic) goto out; - if (xfs_sb_version_hascrc(&mp->m_sb) && - !uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) - goto out; - bp->b_ops = fab->buf_ops; - /* Ignore this block if it's lower in the tree than we've seen. */ - if (fab->root != NULLAGBLOCK && - xfs_btree_get_level(btblock) < fab->height) - goto out; + /* + * If the buffer already has ops applied and they're not the ones for + * this btree type, we know this block doesn't match the btree and we + * can bail out. + * + * If the buffer ops match ours, someone else has already validated + * the block for us, so we can move on to checking if this is a root + * block candidate. + * + * If the buffer does not have ops, nobody has successfully validated + * the contents and the buffer cannot be dirty. If the magic, uuid, + * and structure match this btree type then we'll move on to checking + * if it's a root block candidate. If there is no match, bail out. + */ + if (bp->b_ops) { + if (bp->b_ops != fab->buf_ops) + goto out; + } else { + ASSERT(!xfs_trans_buf_is_dirty(bp)); + if (!uuid_equal(&btblock->bb_u.s.bb_uuid, + &mp->m_sb.sb_meta_uuid)) + goto out; + fab->buf_ops->verify_read(bp); + if (bp->b_error) { + bp->b_error = 0; + goto out; + } - /* Make sure we pass the verifiers. */ - bp->b_ops->verify_read(bp); - if (bp->b_error) + /* + * Some read verifiers will (re)set b_ops, so we must be + * careful not to blow away any such assignment. + */ + if (!bp->b_ops) + bp->b_ops = fab->buf_ops; + } + + /* + * This block passes the magic/uuid and verifier tests for this btree + * type. We don't need the caller to try the other tree types. + */ + *done_with_block = true; + + /* + * Compare this btree block's level to the height of the current + * candidate root block. + * + * If the level matches the root we found previously, throw away both + * blocks because there can't be two candidate roots. + * + * If level is lower in the tree than the root we found previously, + * ignore this block. + */ + block_level = xfs_btree_get_level(btblock); + if (block_level + 1 == fab->height) { + fab->root = NULLAGBLOCK; goto out; - fab->root = agbno; - fab->height = xfs_btree_get_level(btblock) + 1; - *found_it = true; + } else if (block_level < fab->height) { + goto out; + } + + /* + * This is the highest block in the tree that we've found so far. + * Update the btree height to reflect what we've learned from this + * block. + */ + fab->height = block_level + 1; + + /* + * If this block doesn't have sibling pointers, then it's the new root + * block candidate. Otherwise, the root will be found farther up the + * tree. + */ + if (btblock->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) && + btblock->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK)) + fab->root = agbno; + else + fab->root = NULLAGBLOCK; trace_xrep_findroot_block(mp, ri->sc->sa.agno, agbno, be32_to_cpu(btblock->bb_magic), fab->height - 1); @@ -768,7 +846,7 @@ xrep_findroot_rmap( struct xrep_findroot *ri = priv; struct xrep_find_ag_btree *fab; xfs_agblock_t b; - bool found_it; + bool done; int error = 0; /* Ignore anything that isn't AG metadata. */ @@ -777,16 +855,16 @@ xrep_findroot_rmap( /* Otherwise scan each block + btree type. */ for (b = 0; b < rec->rm_blockcount; b++) { - found_it = false; + done = false; for (fab = ri->btree_info; fab->buf_ops; fab++) { if (rec->rm_owner != fab->rmap_owner) continue; error = xrep_findroot_block(ri, fab, rec->rm_owner, rec->rm_startblock + b, - &found_it); + &done); if (error) return error; - if (found_it) + if (done) break; } } diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 4bfae1e61d30..1b2344d00525 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -412,19 +412,6 @@ xchk_validate_inputs( goto out; } - error = -EOPNOTSUPP; - /* - * We won't scrub any filesystem that doesn't have the ability - * to record unwritten extents. The option was made default in - * 2003, removed from mkfs in 2007, and cannot be disabled in - * v5, so if we find a filesystem without this flag it's either - * really old or totally unsupported. Avoid it either way. - * We also don't support v1-v3 filesystems, which aren't - * mountable. - */ - if (!xfs_sb_version_hasextflgbit(&mp->m_sb)) - goto out; - /* * We only want to repair read-write v5+ filesystems. Defer the check * for ops->repair until after our scrub confirms that we need to diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 49f5f5896a43..338b9d9984e0 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -917,7 +917,7 @@ xfs_vm_writepage( struct writeback_control *wbc) { struct xfs_writepage_ctx wpc = { - .io_type = XFS_IO_INVALID, + .io_type = XFS_IO_HOLE, }; int ret; @@ -933,7 +933,7 @@ xfs_vm_writepages( struct writeback_control *wbc) { struct xfs_writepage_ctx wpc = { - .io_type = XFS_IO_INVALID, + .io_type = XFS_IO_HOLE, }; int ret; diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 9af867951a10..494b4338446e 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -12,21 +12,19 @@ extern struct bio_set xfs_ioend_bioset; * Types of I/O for bmap clustering and I/O completion tracking. */ enum { - XFS_IO_INVALID, /* initial state */ + XFS_IO_HOLE, /* covers region without any block allocation */ XFS_IO_DELALLOC, /* covers delalloc region */ XFS_IO_UNWRITTEN, /* covers allocated but uninitialized data */ XFS_IO_OVERWRITE, /* covers already allocated extent */ XFS_IO_COW, /* covers copy-on-write extent */ - XFS_IO_HOLE, /* covers region without any block allocation */ }; #define XFS_IO_TYPES \ - { XFS_IO_INVALID, "invalid" }, \ - { XFS_IO_DELALLOC, "delalloc" }, \ - { XFS_IO_UNWRITTEN, "unwritten" }, \ - { XFS_IO_OVERWRITE, "overwrite" }, \ - { XFS_IO_COW, "CoW" }, \ - { XFS_IO_HOLE, "hole" } + { XFS_IO_HOLE, "hole" }, \ + { XFS_IO_DELALLOC, "delalloc" }, \ + { XFS_IO_UNWRITTEN, "unwritten" }, \ + { XFS_IO_OVERWRITE, "overwrite" }, \ + { XFS_IO_COW, "CoW" } /* * Structure for buffered I/O completions. diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 6de8d90041ff..5d263dfdb3bc 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -406,10 +406,10 @@ xfs_getbmap_report_one( struct xfs_bmbt_irec *got) { struct kgetbmap *p = out + bmv->bmv_entries; - bool shared = false, trimmed = false; + bool shared = false; int error; - error = xfs_reflink_trim_around_shared(ip, got, &shared, &trimmed); + error = xfs_reflink_trim_around_shared(ip, got, &shared); if (error) return error; @@ -1043,44 +1043,6 @@ out_trans_cancel: } static int -xfs_adjust_extent_unmap_boundaries( - struct xfs_inode *ip, - xfs_fileoff_t *startoffset_fsb, - xfs_fileoff_t *endoffset_fsb) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_bmbt_irec imap; - int nimap, error; - xfs_extlen_t mod = 0; - - nimap = 1; - error = xfs_bmapi_read(ip, *startoffset_fsb, 1, &imap, &nimap, 0); - if (error) - return error; - - if (nimap && imap.br_startblock != HOLESTARTBLOCK) { - ASSERT(imap.br_startblock != DELAYSTARTBLOCK); - div_u64_rem(imap.br_startblock, mp->m_sb.sb_rextsize, &mod); - if (mod) - *startoffset_fsb += mp->m_sb.sb_rextsize - mod; - } - - nimap = 1; - error = xfs_bmapi_read(ip, *endoffset_fsb - 1, 1, &imap, &nimap, 0); - if (error) - return error; - - if (nimap && imap.br_startblock != HOLESTARTBLOCK) { - ASSERT(imap.br_startblock != DELAYSTARTBLOCK); - mod++; - if (mod && mod != mp->m_sb.sb_rextsize) - *endoffset_fsb -= mod; - } - - return 0; -} - -static int xfs_flush_unmap_range( struct xfs_inode *ip, xfs_off_t offset, @@ -1133,19 +1095,8 @@ xfs_free_file_space( endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len); /* - * Need to zero the stuff we're not freeing, on disk. If it's a RT file - * and we can't use unwritten extents then we actually need to ensure - * to zero the whole extent, otherwise we just need to take of block - * boundaries, and xfs_bunmapi will handle the rest. + * Need to zero the stuff we're not freeing, on disk. */ - if (XFS_IS_REALTIME_INODE(ip) && - !xfs_sb_version_hasextflgbit(&mp->m_sb)) { - error = xfs_adjust_extent_unmap_boundaries(ip, &startoffset_fsb, - &endoffset_fsb); - if (error) - return error; - } - if (endoffset_fsb > startoffset_fsb) { while (!done) { error = xfs_unmap_extent(ip, startoffset_fsb, @@ -1824,6 +1775,12 @@ xfs_swap_extents( if (error) goto out_unlock; + if (xfs_inode_has_cow_data(tip)) { + error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true); + if (error) + return error; + } + /* * Extent "swapping" with rmap requires a permanent reservation and * a block reservation because it's really just a remap operation diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index e839907e8492..b21ea2ba768d 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -37,6 +37,32 @@ static kmem_zone_t *xfs_buf_zone; #define xb_to_gfp(flags) \ ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN) +/* + * Locking orders + * + * xfs_buf_ioacct_inc: + * xfs_buf_ioacct_dec: + * b_sema (caller holds) + * b_lock + * + * xfs_buf_stale: + * b_sema (caller holds) + * b_lock + * lru_lock + * + * xfs_buf_rele: + * b_lock + * pag_buf_lock + * lru_lock + * + * xfs_buftarg_wait_rele + * lru_lock + * b_lock (trylock due to inversion) + * + * xfs_buftarg_isolate + * lru_lock + * b_lock (trylock due to inversion) + */ static inline int xfs_buf_is_vmapped( @@ -749,6 +775,30 @@ _xfs_buf_read( return xfs_buf_submit(bp); } +/* + * If the caller passed in an ops structure and the buffer doesn't have ops + * assigned, set the ops and use them to verify the contents. If the contents + * cannot be verified, we'll clear XBF_DONE. We assume the buffer has no + * recorded errors and is already in XBF_DONE state. + */ +int +xfs_buf_ensure_ops( + struct xfs_buf *bp, + const struct xfs_buf_ops *ops) +{ + ASSERT(bp->b_flags & XBF_DONE); + ASSERT(bp->b_error == 0); + + if (!ops || bp->b_ops) + return 0; + + bp->b_ops = ops; + bp->b_ops->verify_read(bp); + if (bp->b_error) + bp->b_flags &= ~XBF_DONE; + return bp->b_error; +} + xfs_buf_t * xfs_buf_read_map( struct xfs_buftarg *target, @@ -762,26 +812,32 @@ xfs_buf_read_map( flags |= XBF_READ; bp = xfs_buf_get_map(target, map, nmaps, flags); - if (bp) { - trace_xfs_buf_read(bp, flags, _RET_IP_); + if (!bp) + return NULL; - if (!(bp->b_flags & XBF_DONE)) { - XFS_STATS_INC(target->bt_mount, xb_get_read); - bp->b_ops = ops; - _xfs_buf_read(bp, flags); - } else if (flags & XBF_ASYNC) { - /* - * Read ahead call which is already satisfied, - * drop the buffer - */ - xfs_buf_relse(bp); - return NULL; - } else { - /* We do not want read in the flags */ - bp->b_flags &= ~XBF_READ; - } + trace_xfs_buf_read(bp, flags, _RET_IP_); + + if (!(bp->b_flags & XBF_DONE)) { + XFS_STATS_INC(target->bt_mount, xb_get_read); + bp->b_ops = ops; + _xfs_buf_read(bp, flags); + return bp; } + xfs_buf_ensure_ops(bp, ops); + + if (flags & XBF_ASYNC) { + /* + * Read ahead call which is already satisfied, + * drop the buffer + */ + xfs_buf_relse(bp); + return NULL; + } + + /* We do not want read in the flags */ + bp->b_flags &= ~XBF_READ; + ASSERT(bp->b_ops != NULL || ops == NULL); return bp; } @@ -1006,8 +1062,18 @@ xfs_buf_rele( ASSERT(atomic_read(&bp->b_hold) > 0); - release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); + /* + * We grab the b_lock here first to serialise racing xfs_buf_rele() + * calls. The pag_buf_lock being taken on the last reference only + * serialises against racing lookups in xfs_buf_find(). IOWs, the second + * to last reference we drop here is not serialised against the last + * reference until we take bp->b_lock. Hence if we don't grab b_lock + * first, the last "release" reference can win the race to the lock and + * free the buffer before the second-to-last reference is processed, + * leading to a use-after-free scenario. + */ spin_lock(&bp->b_lock); + release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); if (!release) { /* * Drop the in-flight state if the buffer is already on the LRU @@ -1989,6 +2055,13 @@ xfs_buf_delwri_submit_buffers( * is only safely useable for callers that can track I/O completion by higher * level means, e.g. AIL pushing as the @buffer_list is consumed in this * function. + * + * Note: this function will skip buffers it would block on, and in doing so + * leaves them on @buffer_list so they can be retried on a later pass. As such, + * it is up to the caller to ensure that the buffer list is fully submitted or + * cancelled appropriately when they are finished with the list. Failure to + * cancel or resubmit the list until it is empty will result in leaked buffers + * at unmount time. */ int xfs_buf_delwri_submit_nowait( diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 4e3171acd0f8..b9f5511ea998 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -385,4 +385,6 @@ extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int); #define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) +int xfs_buf_ensure_ops(struct xfs_buf *bp, const struct xfs_buf_ops *ops); + #endif /* __XFS_BUF_H__ */ diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 7c00b8bedfe3..093c2b8d7e20 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -470,20 +470,13 @@ xfs_fs_goingdown( */ void xfs_do_force_shutdown( - xfs_mount_t *mp, + struct xfs_mount *mp, int flags, char *fname, int lnnum) { - int logerror; - - logerror = flags & SHUTDOWN_LOG_IO_ERROR; + bool logerror = flags & SHUTDOWN_LOG_IO_ERROR; - if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { - xfs_notice(mp, - "%s(0x%x) called from line %d of file %s. Return address = "PTR_FMT, - __func__, flags, lnnum, fname, __return_address); - } /* * No need to duplicate efforts. */ @@ -499,27 +492,34 @@ xfs_do_force_shutdown( if (xfs_log_force_umount(mp, logerror)) return; + if (flags & SHUTDOWN_FORCE_UMOUNT) { + xfs_alert(mp, +"User initiated shutdown received. Shutting down filesystem"); + return; + } + + xfs_notice(mp, +"%s(0x%x) called from line %d of file %s. Return address = "PTR_FMT, + __func__, flags, lnnum, fname, __return_address); + if (flags & SHUTDOWN_CORRUPT_INCORE) { xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT, - "Corruption of in-memory data detected. Shutting down filesystem"); +"Corruption of in-memory data detected. Shutting down filesystem"); if (XFS_ERRLEVEL_HIGH <= xfs_error_level) xfs_stack_trace(); - } else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { - if (logerror) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR, - "Log I/O Error Detected. Shutting down filesystem"); - } else if (flags & SHUTDOWN_DEVICE_REQ) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, - "All device paths lost. Shutting down filesystem"); - } else if (!(flags & SHUTDOWN_REMOTE_REQ)) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, - "I/O Error Detected. Shutting down filesystem"); - } - } - if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { - xfs_alert(mp, - "Please umount the filesystem and rectify the problem(s)"); + } else if (logerror) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR, + "Log I/O Error Detected. Shutting down filesystem"); + } else if (flags & SHUTDOWN_DEVICE_REQ) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, + "All device paths lost. Shutting down filesystem"); + } else if (!(flags & SHUTDOWN_REMOTE_REQ)) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, + "I/O Error Detected. Shutting down filesystem"); } + + xfs_alert(mp, + "Please unmount the filesystem and rectify the problem(s)"); } /* diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0ef5ece5634c..6e2c08f30f60 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -604,14 +604,6 @@ xfs_ioc_space( uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; int error; - /* - * Only allow the sys admin to reserve space unless - * unwritten extents are enabled. - */ - if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) && - !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) return -EPERM; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 6320aca39f39..27c93b5f029d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -62,6 +62,21 @@ xfs_bmbt_to_iomap( iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip)); } +static void +xfs_hole_to_iomap( + struct xfs_inode *ip, + struct iomap *iomap, + xfs_fileoff_t offset_fsb, + xfs_fileoff_t end_fsb) +{ + iomap->addr = IOMAP_NULL_ADDR; + iomap->type = IOMAP_HOLE; + iomap->offset = XFS_FSB_TO_B(ip->i_mount, offset_fsb); + iomap->length = XFS_FSB_TO_B(ip->i_mount, end_fsb - offset_fsb); + iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip)); + iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip)); +} + xfs_extlen_t xfs_eof_alignment( struct xfs_inode *ip, @@ -502,6 +517,7 @@ xfs_file_iomap_begin_delay( struct inode *inode, loff_t offset, loff_t count, + unsigned flags, struct iomap *iomap) { struct xfs_inode *ip = XFS_I(inode); @@ -538,15 +554,23 @@ xfs_file_iomap_begin_delay( goto out_unlock; } + end_fsb = min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb); + eof = !xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got); - if (!eof && got.br_startoff <= offset_fsb) { - if (xfs_is_reflink_inode(ip)) { - bool shared; + if (eof) + got.br_startoff = end_fsb; /* fake hole until the end */ - end_fsb = min(XFS_B_TO_FSB(mp, offset + count), - maxbytes_fsb); + if (got.br_startoff <= offset_fsb) { + /* + * For reflink files we may need a delalloc reservation when + * overwriting shared extents. This includes zeroing of + * existing extents that contain data. + */ + if (xfs_is_reflink_inode(ip) && + ((flags & IOMAP_WRITE) || + got.br_state != XFS_EXT_UNWRITTEN)) { xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb); - error = xfs_reflink_reserve_cow(ip, &got, &shared); + error = xfs_reflink_reserve_cow(ip, &got); if (error) goto out_unlock; } @@ -555,6 +579,11 @@ xfs_file_iomap_begin_delay( goto done; } + if (flags & IOMAP_ZERO) { + xfs_hole_to_iomap(ip, iomap, offset_fsb, got.br_startoff); + goto out_unlock; + } + error = xfs_qm_dqattach_locked(ip, false); if (error) goto out_unlock; @@ -1003,16 +1032,17 @@ xfs_file_iomap_begin( struct xfs_bmbt_irec imap; xfs_fileoff_t offset_fsb, end_fsb; int nimaps = 1, error = 0; - bool shared = false, trimmed = false; + bool shared = false; unsigned lockmode; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) && + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && !(flags & IOMAP_DIRECT) && !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ - return xfs_file_iomap_begin_delay(inode, offset, length, iomap); + return xfs_file_iomap_begin_delay(inode, offset, length, flags, + iomap); } /* @@ -1038,8 +1068,7 @@ xfs_file_iomap_begin( if (flags & IOMAP_REPORT) { /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, - &trimmed); + error = xfs_reflink_trim_around_shared(ip, &imap, &shared); if (error) goto out_unlock; } @@ -1065,7 +1094,7 @@ xfs_file_iomap_begin( if (error) goto out_unlock; } else { - error = xfs_reflink_reserve_cow(ip, &imap, &shared); + error = xfs_reflink_reserve_cow(ip, &imap); if (error) goto out_unlock; } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 42ea7bab9144..8eaeec9d58ed 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -182,8 +182,7 @@ int xfs_reflink_trim_around_shared( struct xfs_inode *ip, struct xfs_bmbt_irec *irec, - bool *shared, - bool *trimmed) + bool *shared) { xfs_agnumber_t agno; xfs_agblock_t agbno; @@ -209,7 +208,7 @@ xfs_reflink_trim_around_shared( if (error) return error; - *shared = *trimmed = false; + *shared = false; if (fbno == NULLAGBLOCK) { /* No shared blocks at all. */ return 0; @@ -222,8 +221,6 @@ xfs_reflink_trim_around_shared( */ irec->br_blockcount = flen; *shared = true; - if (flen != aglen) - *trimmed = true; return 0; } else { /* @@ -233,7 +230,6 @@ xfs_reflink_trim_around_shared( * start of the shared region. */ irec->br_blockcount = fbno - agbno; - *trimmed = true; return 0; } } @@ -241,7 +237,7 @@ xfs_reflink_trim_around_shared( /* * Trim the passed in imap to the next shared/unshared extent boundary, and * if imap->br_startoff points to a shared extent reserve space for it in the - * COW fork. In this case *shared is set to true, else to false. + * COW fork. * * Note that imap will always contain the block numbers for the existing blocks * in the data fork, as the upper layers need them for read-modify-write @@ -250,14 +246,14 @@ xfs_reflink_trim_around_shared( int xfs_reflink_reserve_cow( struct xfs_inode *ip, - struct xfs_bmbt_irec *imap, - bool *shared) + struct xfs_bmbt_irec *imap) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); struct xfs_bmbt_irec got; int error = 0; - bool eof = false, trimmed; + bool eof = false; struct xfs_iext_cursor icur; + bool shared; /* * Search the COW fork extent list first. This serves two purposes: @@ -273,18 +269,16 @@ xfs_reflink_reserve_cow( if (!eof && got.br_startoff <= imap->br_startoff) { trace_xfs_reflink_cow_found(ip, imap); xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); - - *shared = true; return 0; } /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); + error = xfs_reflink_trim_around_shared(ip, imap, &shared); if (error) return error; /* Not shared? Just report the (potentially capped) extent. */ - if (!*shared) + if (!shared) return 0; /* @@ -368,7 +362,6 @@ xfs_find_trim_cow_extent( xfs_filblks_t count_fsb = imap->br_blockcount; struct xfs_iext_cursor icur; struct xfs_bmbt_irec got; - bool trimmed; *found = false; @@ -376,9 +369,13 @@ xfs_find_trim_cow_extent( * If we don't find an overlapping extent, trim the range we need to * allocate to fit the hole we found. */ - if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) || - got.br_startoff > offset_fsb) - return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); + if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got)) + got.br_startoff = offset_fsb + count_fsb; + if (got.br_startoff > offset_fsb) { + xfs_trim_extent(imap, imap->br_startoff, + got.br_startoff - imap->br_startoff); + return xfs_reflink_trim_around_shared(ip, imap, shared); + } *shared = true; if (isnullstartblock(got.br_startblock)) { diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index c585ad9552b2..7f47202b5639 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -10,10 +10,10 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal); extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, - struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed); + struct xfs_bmbt_irec *irec, bool *shared); extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, - struct xfs_bmbt_irec *imap, bool *shared); + struct xfs_bmbt_irec *imap); extern int xfs_reflink_allocate_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode); extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset, diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index 4e4423153071..cc509743facd 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -29,30 +29,30 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) char *desc; int endpoint; } xstats[] = { - { "extent_alloc", XFSSTAT_END_EXTENT_ALLOC }, - { "abt", XFSSTAT_END_ALLOC_BTREE }, - { "blk_map", XFSSTAT_END_BLOCK_MAPPING }, - { "bmbt", XFSSTAT_END_BLOCK_MAP_BTREE }, - { "dir", XFSSTAT_END_DIRECTORY_OPS }, - { "trans", XFSSTAT_END_TRANSACTIONS }, - { "ig", XFSSTAT_END_INODE_OPS }, - { "log", XFSSTAT_END_LOG_OPS }, - { "push_ail", XFSSTAT_END_TAIL_PUSHING }, - { "xstrat", XFSSTAT_END_WRITE_CONVERT }, - { "rw", XFSSTAT_END_READ_WRITE_OPS }, - { "attr", XFSSTAT_END_ATTRIBUTE_OPS }, - { "icluster", XFSSTAT_END_INODE_CLUSTER }, - { "vnodes", XFSSTAT_END_VNODE_OPS }, - { "buf", XFSSTAT_END_BUF }, - { "abtb2", XFSSTAT_END_ABTB_V2 }, - { "abtc2", XFSSTAT_END_ABTC_V2 }, - { "bmbt2", XFSSTAT_END_BMBT_V2 }, - { "ibt2", XFSSTAT_END_IBT_V2 }, - { "fibt2", XFSSTAT_END_FIBT_V2 }, - { "rmapbt", XFSSTAT_END_RMAP_V2 }, - { "refcntbt", XFSSTAT_END_REFCOUNT }, + { "extent_alloc", xfsstats_offset(xs_abt_lookup) }, + { "abt", xfsstats_offset(xs_blk_mapr) }, + { "blk_map", xfsstats_offset(xs_bmbt_lookup) }, + { "bmbt", xfsstats_offset(xs_dir_lookup) }, + { "dir", xfsstats_offset(xs_trans_sync) }, + { "trans", xfsstats_offset(xs_ig_attempts) }, + { "ig", xfsstats_offset(xs_log_writes) }, + { "log", xfsstats_offset(xs_try_logspace)}, + { "push_ail", xfsstats_offset(xs_xstrat_quick)}, + { "xstrat", xfsstats_offset(xs_write_calls) }, + { "rw", xfsstats_offset(xs_attr_get) }, + { "attr", xfsstats_offset(xs_iflush_count)}, + { "icluster", xfsstats_offset(vn_active) }, + { "vnodes", xfsstats_offset(xb_get) }, + { "buf", xfsstats_offset(xs_abtb_2) }, + { "abtb2", xfsstats_offset(xs_abtc_2) }, + { "abtc2", xfsstats_offset(xs_bmbt_2) }, + { "bmbt2", xfsstats_offset(xs_ibt_2) }, + { "ibt2", xfsstats_offset(xs_fibt_2) }, + { "fibt2", xfsstats_offset(xs_rmap_2) }, + { "rmapbt", xfsstats_offset(xs_refcbt_2) }, + { "refcntbt", xfsstats_offset(xs_qm_dqreclaims)}, /* we print both series of quota information together */ - { "qm", XFSSTAT_END_QM }, + { "qm", xfsstats_offset(xs_xstrat_bytes)}, }; /* Loop over all stats groups */ @@ -104,6 +104,10 @@ void xfs_stats_clearall(struct xfsstats __percpu *stats) #ifdef CONFIG_PROC_FS /* legacy quota interfaces */ #ifdef CONFIG_XFS_QUOTA + +#define XFSSTAT_START_XQMSTAT xfsstats_offset(xs_qm_dqreclaims) +#define XFSSTAT_END_XQMSTAT xfsstats_offset(xs_qm_dquot) + static int xqm_proc_show(struct seq_file *m, void *v) { /* maximum; incore; ratio free to inuse; freelist */ @@ -119,7 +123,7 @@ static int xqmstat_proc_show(struct seq_file *m, void *v) int j; seq_printf(m, "qm"); - for (j = XFSSTAT_END_IBT_V2; j < XFSSTAT_END_XQMSTAT; j++) + for (j = XFSSTAT_START_XQMSTAT; j < XFSSTAT_END_XQMSTAT; j++) seq_printf(m, " %u", counter_val(xfsstats.xs_stats, j)); seq_putc(m, '\n'); return 0; diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index 130db070e4d8..34d704f703d2 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -41,17 +41,14 @@ enum { * XFS global statistics */ struct __xfsstats { -# define XFSSTAT_END_EXTENT_ALLOC 4 uint32_t xs_allocx; uint32_t xs_allocb; uint32_t xs_freex; uint32_t xs_freeb; -# define XFSSTAT_END_ALLOC_BTREE (XFSSTAT_END_EXTENT_ALLOC+4) uint32_t xs_abt_lookup; uint32_t xs_abt_compare; uint32_t xs_abt_insrec; uint32_t xs_abt_delrec; -# define XFSSTAT_END_BLOCK_MAPPING (XFSSTAT_END_ALLOC_BTREE+7) uint32_t xs_blk_mapr; uint32_t xs_blk_mapw; uint32_t xs_blk_unmap; @@ -59,21 +56,17 @@ struct __xfsstats { uint32_t xs_del_exlist; uint32_t xs_look_exlist; uint32_t xs_cmp_exlist; -# define XFSSTAT_END_BLOCK_MAP_BTREE (XFSSTAT_END_BLOCK_MAPPING+4) uint32_t xs_bmbt_lookup; uint32_t xs_bmbt_compare; uint32_t xs_bmbt_insrec; uint32_t xs_bmbt_delrec; -# define XFSSTAT_END_DIRECTORY_OPS (XFSSTAT_END_BLOCK_MAP_BTREE+4) uint32_t xs_dir_lookup; uint32_t xs_dir_create; uint32_t xs_dir_remove; uint32_t xs_dir_getdents; -# define XFSSTAT_END_TRANSACTIONS (XFSSTAT_END_DIRECTORY_OPS+3) uint32_t xs_trans_sync; uint32_t xs_trans_async; uint32_t xs_trans_empty; -# define XFSSTAT_END_INODE_OPS (XFSSTAT_END_TRANSACTIONS+7) uint32_t xs_ig_attempts; uint32_t xs_ig_found; uint32_t xs_ig_frecycle; @@ -81,13 +74,11 @@ struct __xfsstats { uint32_t xs_ig_dup; uint32_t xs_ig_reclaims; uint32_t xs_ig_attrchg; -# define XFSSTAT_END_LOG_OPS (XFSSTAT_END_INODE_OPS+5) uint32_t xs_log_writes; uint32_t xs_log_blocks; uint32_t xs_log_noiclogs; uint32_t xs_log_force; uint32_t xs_log_force_sleep; -# define XFSSTAT_END_TAIL_PUSHING (XFSSTAT_END_LOG_OPS+10) uint32_t xs_try_logspace; uint32_t xs_sleep_logspace; uint32_t xs_push_ail; @@ -98,22 +89,17 @@ struct __xfsstats { uint32_t xs_push_ail_flushing; uint32_t xs_push_ail_restarts; uint32_t xs_push_ail_flush; -# define XFSSTAT_END_WRITE_CONVERT (XFSSTAT_END_TAIL_PUSHING+2) uint32_t xs_xstrat_quick; uint32_t xs_xstrat_split; -# define XFSSTAT_END_READ_WRITE_OPS (XFSSTAT_END_WRITE_CONVERT+2) uint32_t xs_write_calls; uint32_t xs_read_calls; -# define XFSSTAT_END_ATTRIBUTE_OPS (XFSSTAT_END_READ_WRITE_OPS+4) uint32_t xs_attr_get; uint32_t xs_attr_set; uint32_t xs_attr_remove; uint32_t xs_attr_list; -# define XFSSTAT_END_INODE_CLUSTER (XFSSTAT_END_ATTRIBUTE_OPS+3) uint32_t xs_iflush_count; uint32_t xs_icluster_flushcnt; uint32_t xs_icluster_flushinode; -# define XFSSTAT_END_VNODE_OPS (XFSSTAT_END_INODE_CLUSTER+8) uint32_t vn_active; /* # vnodes not on free lists */ uint32_t vn_alloc; /* # times vn_alloc called */ uint32_t vn_get; /* # times vn_get called */ @@ -122,7 +108,6 @@ struct __xfsstats { uint32_t vn_reclaim; /* # times vn_reclaim called */ uint32_t vn_remove; /* # times vn_remove called */ uint32_t vn_free; /* # times vn_free called */ -#define XFSSTAT_END_BUF (XFSSTAT_END_VNODE_OPS+9) uint32_t xb_get; uint32_t xb_create; uint32_t xb_get_locked; @@ -133,28 +118,19 @@ struct __xfsstats { uint32_t xb_page_found; uint32_t xb_get_read; /* Version 2 btree counters */ -#define XFSSTAT_END_ABTB_V2 (XFSSTAT_END_BUF + __XBTS_MAX) uint32_t xs_abtb_2[__XBTS_MAX]; -#define XFSSTAT_END_ABTC_V2 (XFSSTAT_END_ABTB_V2 + __XBTS_MAX) uint32_t xs_abtc_2[__XBTS_MAX]; -#define XFSSTAT_END_BMBT_V2 (XFSSTAT_END_ABTC_V2 + __XBTS_MAX) uint32_t xs_bmbt_2[__XBTS_MAX]; -#define XFSSTAT_END_IBT_V2 (XFSSTAT_END_BMBT_V2 + __XBTS_MAX) uint32_t xs_ibt_2[__XBTS_MAX]; -#define XFSSTAT_END_FIBT_V2 (XFSSTAT_END_IBT_V2 + __XBTS_MAX) uint32_t xs_fibt_2[__XBTS_MAX]; -#define XFSSTAT_END_RMAP_V2 (XFSSTAT_END_FIBT_V2 + __XBTS_MAX) uint32_t xs_rmap_2[__XBTS_MAX]; -#define XFSSTAT_END_REFCOUNT (XFSSTAT_END_RMAP_V2 + __XBTS_MAX) uint32_t xs_refcbt_2[__XBTS_MAX]; -#define XFSSTAT_END_XQMSTAT (XFSSTAT_END_REFCOUNT + 6) uint32_t xs_qm_dqreclaims; uint32_t xs_qm_dqreclaim_misses; uint32_t xs_qm_dquot_dups; uint32_t xs_qm_dqcachemisses; uint32_t xs_qm_dqcachehits; uint32_t xs_qm_dqwants; -#define XFSSTAT_END_QM (XFSSTAT_END_XQMSTAT+2) uint32_t xs_qm_dquot; uint32_t xs_qm_dquot_unused; /* Extra precision counters */ @@ -163,10 +139,12 @@ struct __xfsstats { uint64_t xs_read_bytes; }; +#define xfsstats_offset(f) (offsetof(struct __xfsstats, f)/sizeof(uint32_t)) + struct xfsstats { union { struct __xfsstats s; - uint32_t a[XFSSTAT_END_XQMSTAT]; + uint32_t a[xfsstats_offset(xs_qm_dquot)]; }; }; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 207ee302b1bb..d3e6cd063688 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -43,6 +43,7 @@ #include <linux/dax.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/magic.h> #include <linux/mount.h> #include <linux/mempool.h> #include <linux/writeback.h> @@ -933,6 +934,32 @@ xfs_fs_alloc_inode( return NULL; } +#ifdef DEBUG +static void +xfs_check_delalloc( + struct xfs_inode *ip, + int whichfork) +{ + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_bmbt_irec got; + struct xfs_iext_cursor icur; + + if (!ifp || !xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got)) + return; + do { + if (isnullstartblock(got.br_startblock)) { + xfs_warn(ip->i_mount, + "ino %llx %s fork has delalloc extent at [0x%llx:0x%llx]", + ip->i_ino, + whichfork == XFS_DATA_FORK ? "data" : "cow", + got.br_startoff, got.br_blockcount); + } + } while (xfs_iext_next_extent(ifp, &icur, &got)); +} +#else +#define xfs_check_delalloc(ip, whichfork) do { } while (0) +#endif + /* * Now that the generic code is guaranteed not to be accessing * the linux inode, we can inactivate and reclaim the inode. @@ -951,7 +978,12 @@ xfs_fs_destroy_inode( xfs_inactive(ip); - ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0); + if (!XFS_FORCED_SHUTDOWN(ip->i_mount) && ip->i_delayed_blks) { + xfs_check_delalloc(ip, XFS_DATA_FORK); + xfs_check_delalloc(ip, XFS_COW_FORK); + ASSERT(0); + } + XFS_STATS_INC(ip->i_mount, vn_reclaim); /* @@ -1097,7 +1129,7 @@ xfs_fs_statfs( xfs_extlen_t lsize; int64_t ffree; - statp->f_type = XFS_SB_MAGIC; + statp->f_type = XFS_SUPER_MAGIC; statp->f_namelen = MAXNAMELEN - 1; id = huge_encode_dev(mp->m_ddev_targp->bt_dev); @@ -1650,7 +1682,7 @@ xfs_fs_fill_super( * we must configure the block size in the superblock before we run the * full mount process as the mount process can lookup and cache inodes. */ - sb->s_magic = XFS_SB_MAGIC; + sb->s_magic = XFS_SUPER_MAGIC; sb->s_blocksize = mp->m_sb.sb_blocksize; sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1; sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits); diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index c3d278e96ad1..a0c5dbda18aa 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -220,6 +220,7 @@ void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint); void xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint, uint); void xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *); +bool xfs_trans_buf_is_dirty(struct xfs_buf *bp); void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint); void xfs_extent_free_init_defer_op(void); diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 55326f971cb3..d3a4e89bf4a0 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -531,17 +531,33 @@ xfsaild( set_current_state(TASK_INTERRUPTIBLE); /* - * Check kthread_should_stop() after we set the task state - * to guarantee that we either see the stop bit and exit or - * the task state is reset to runnable such that it's not - * scheduled out indefinitely and detects the stop bit at - * next iteration. - * + * Check kthread_should_stop() after we set the task state to + * guarantee that we either see the stop bit and exit or the + * task state is reset to runnable such that it's not scheduled + * out indefinitely and detects the stop bit at next iteration. * A memory barrier is included in above task state set to * serialize again kthread_stop(). */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); + + /* + * The caller forces out the AIL before stopping the + * thread in the common case, which means the delwri + * queue is drained. In the shutdown case, the queue may + * still hold relogged buffers that haven't been + * submitted because they were pinned since added to the + * queue. + * + * Log I/O error processing stales the underlying buffer + * and clears the delwri state, expecting the buf to be + * removed on the next submission attempt. That won't + * happen if we're shutting down, so this is the last + * opportunity to release such buffers from the queue. + */ + ASSERT(list_empty(&ailp->ail_buf_list) || + XFS_FORCED_SHUTDOWN(ailp->ail_mount)); + xfs_buf_delwri_cancel(&ailp->ail_buf_list); break; } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 286a287ac57a..629f1479c9d2 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -264,11 +264,39 @@ xfs_trans_read_buf_map( return -EIO; } + /* + * Check if the caller is trying to read a buffer that is + * already attached to the transaction yet has no buffer ops + * assigned. Ops are usually attached when the buffer is + * attached to the transaction, or by the read caller if + * special circumstances. That didn't happen, which is not + * how this is supposed to go. + * + * If the buffer passes verification we'll let this go, but if + * not we have to shut down. Let the transaction cleanup code + * release this buffer when it kills the tranaction. + */ + ASSERT(bp->b_ops != NULL); + error = xfs_buf_ensure_ops(bp, ops); + if (error) { + xfs_buf_ioerror_alert(bp, __func__); + + if (tp->t_flags & XFS_TRANS_DIRTY) + xfs_force_shutdown(tp->t_mountp, + SHUTDOWN_META_IO_ERROR); + + /* bad CRC means corrupted metadata */ + if (error == -EFSBADCRC) + error = -EFSCORRUPTED; + return error; + } + bip = bp->b_log_item; bip->bli_recur++; ASSERT(atomic_read(&bip->bli_refcount) > 0); trace_xfs_trans_read_buf_recur(bip); + ASSERT(bp->b_ops != NULL || ops == NULL); *bpp = bp; return 0; } @@ -316,11 +344,25 @@ xfs_trans_read_buf_map( _xfs_trans_bjoin(tp, bp, 1); trace_xfs_trans_read_buf(bp->b_log_item); } + ASSERT(bp->b_ops != NULL || ops == NULL); *bpp = bp; return 0; } +/* Has this buffer been dirtied by anyone? */ +bool +xfs_trans_buf_is_dirty( + struct xfs_buf *bp) +{ + struct xfs_buf_log_item *bip = bp->b_log_item; + + if (!bip) + return false; + ASSERT(bip->bli_item.li_type == XFS_LI_BUF); + return test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags); +} + /* * Release a buffer previously joined to the transaction. If the buffer is * modified within this transaction, decrement the recursion count but do not diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 96225a77c112..7b73ef7f902d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -242,7 +242,7 @@ int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ -static inline int block_page_mkwrite_return(int err) +static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f70f8ac9c4f4..d7711048ef93 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /** * include/linux/f2fs_fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_FS_H #define _LINUX_F2FS_FS_H @@ -112,12 +109,15 @@ struct f2fs_super_block { struct f2fs_device devs[MAX_DEVICES]; /* device list */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ __u8 hot_ext_count; /* # of hot file extension */ - __u8 reserved[314]; /* valid reserved region */ + __u8 reserved[310]; /* valid reserved region */ + __le32 crc; /* checksum of superblock */ } __packed; /* * For checkpoint */ +#define CP_DISABLED_FLAG 0x00001000 +#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index e8d9456bf36e..c5969762a8f4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -226,6 +226,7 @@ struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; + bool dump_all_families; unsigned char protocol; unsigned char rt_type; unsigned int flags; diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index b401c4e36394..8568946f491d 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -316,7 +316,7 @@ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular, ), TP_fast_assign_btrfs(bi->root->fs_info, - __entry->root_obj = bi->root->objectid; + __entry->root_obj = bi->root->root_key.objectid; __entry->ino = btrfs_ino(bi); __entry->isize = bi->vfs_inode.i_size; __entry->disk_isize = bi->disk_i_size; @@ -367,7 +367,7 @@ DECLARE_EVENT_CLASS( TP_fast_assign_btrfs( bi->root->fs_info, - __entry->root_obj = bi->root->objectid; + __entry->root_obj = bi->root->root_key.objectid; __entry->ino = btrfs_ino(bi); __entry->isize = bi->vfs_inode.i_size; __entry->disk_isize = bi->disk_i_size; @@ -1477,7 +1477,8 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, ), TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), - __entry->rootid = BTRFS_I(inode)->root->objectid; + __entry->rootid = + BTRFS_I(inode)->root->root_key.objectid; __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->start = start; __entry->len = len; @@ -1575,6 +1576,27 @@ DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_trace_extent, TP_ARGS(fs_info, rec) ); +TRACE_EVENT(qgroup_num_dirty_extents, + + TP_PROTO(const struct btrfs_fs_info *fs_info, u64 transid, + u64 num_dirty_extents), + + TP_ARGS(fs_info, transid, num_dirty_extents), + + TP_STRUCT__entry_btrfs( + __field( u64, transid ) + __field( u64, num_dirty_extents ) + ), + + TP_fast_assign_btrfs(fs_info, + __entry->transid = transid; + __entry->num_dirty_extents = num_dirty_extents; + ), + + TP_printk_btrfs("transid=%llu num_dirty_extents=%llu", + __entry->transid, __entry->num_dirty_extents) +); + TRACE_EVENT(btrfs_qgroup_account_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 transid, u64 bytenr, @@ -1675,7 +1697,7 @@ TRACE_EVENT(qgroup_meta_reserve, ), TP_fast_assign_btrfs(root->fs_info, - __entry->refroot = root->objectid; + __entry->refroot = root->root_key.objectid; __entry->diff = diff; ), @@ -1697,7 +1719,7 @@ TRACE_EVENT(qgroup_meta_convert, ), TP_fast_assign_btrfs(root->fs_info, - __entry->refroot = root->objectid; + __entry->refroot = root->root_key.objectid; __entry->diff = diff; ), @@ -1721,7 +1743,7 @@ TRACE_EVENT(qgroup_meta_free_all_pertrans, ), TP_fast_assign_btrfs(root->fs_info, - __entry->refroot = root->objectid; + __entry->refroot = root->root_key.objectid; spin_lock(&root->qgroup_meta_rsv_lock); __entry->diff = -(s64)root->qgroup_meta_rsv_pertrans; spin_unlock(&root->qgroup_meta_rsv_lock); @@ -1802,7 +1824,7 @@ TRACE_EVENT(btrfs_inode_mod_outstanding_extents, ), TP_fast_assign_btrfs(root->fs_info, - __entry->root_objectid = root->objectid; + __entry->root_objectid = root->root_key.objectid; __entry->ino = ino; __entry->mod = mod; ), diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 0e31eb136c57..698e0d8a5ca4 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -17,6 +17,7 @@ struct mpage_da_data; struct ext4_map_blocks; struct extent_status; struct ext4_fsmap; +struct partial_cluster; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) @@ -2035,21 +2036,23 @@ TRACE_EVENT(ext4_ext_show_extent, ); TRACE_EVENT(ext4_remove_blocks, - TP_PROTO(struct inode *inode, struct ext4_extent *ex, - ext4_lblk_t from, ext4_fsblk_t to, - long long partial_cluster), + TP_PROTO(struct inode *inode, struct ext4_extent *ex, + ext4_lblk_t from, ext4_fsblk_t to, + struct partial_cluster *pc), - TP_ARGS(inode, ex, from, to, partial_cluster), + TP_ARGS(inode, ex, from, to, pc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, from ) __field( ext4_lblk_t, to ) - __field( long long, partial ) __field( ext4_fsblk_t, ee_pblk ) __field( ext4_lblk_t, ee_lblk ) __field( unsigned short, ee_len ) + __field( ext4_fsblk_t, pc_pclu ) + __field( ext4_lblk_t, pc_lblk ) + __field( int, pc_state) ), TP_fast_assign( @@ -2057,14 +2060,16 @@ TRACE_EVENT(ext4_remove_blocks, __entry->ino = inode->i_ino; __entry->from = from; __entry->to = to; - __entry->partial = partial_cluster; __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_len = ext4_ext_get_actual_len(ex); + __entry->pc_pclu = pc->pclu; + __entry->pc_lblk = pc->lblk; + __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]" - "from %u to %u partial_cluster %lld", + "from %u to %u partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->ee_lblk, @@ -2072,45 +2077,53 @@ TRACE_EVENT(ext4_remove_blocks, (unsigned short) __entry->ee_len, (unsigned) __entry->from, (unsigned) __entry->to, - (long long) __entry->partial) + (long long) __entry->pc_pclu, + (unsigned int) __entry->pc_lblk, + (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_leaf, TP_PROTO(struct inode *inode, ext4_lblk_t start, struct ext4_extent *ex, - long long partial_cluster), + struct partial_cluster *pc), - TP_ARGS(inode, start, ex, partial_cluster), + TP_ARGS(inode, start, ex, pc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) - __field( long long, partial ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, ee_lblk ) __field( ext4_fsblk_t, ee_pblk ) __field( short, ee_len ) + __field( ext4_fsblk_t, pc_pclu ) + __field( ext4_lblk_t, pc_lblk ) + __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->partial = partial_cluster; __entry->start = start; __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_len = ext4_ext_get_actual_len(ex); + __entry->pc_pclu = pc->pclu; + __entry->pc_lblk = pc->lblk; + __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]" - "partial_cluster %lld", + "partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, - (long long) __entry->partial) + (long long) __entry->pc_pclu, + (unsigned int) __entry->pc_lblk, + (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_idx, @@ -2168,9 +2181,9 @@ TRACE_EVENT(ext4_ext_remove_space, TRACE_EVENT(ext4_ext_remove_space_done, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, - int depth, long long partial, __le16 eh_entries), + int depth, struct partial_cluster *pc, __le16 eh_entries), - TP_ARGS(inode, start, end, depth, partial, eh_entries), + TP_ARGS(inode, start, end, depth, pc, eh_entries), TP_STRUCT__entry( __field( dev_t, dev ) @@ -2178,7 +2191,9 @@ TRACE_EVENT(ext4_ext_remove_space_done, __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) - __field( long long, partial ) + __field( ext4_fsblk_t, pc_pclu ) + __field( ext4_lblk_t, pc_lblk ) + __field( int, pc_state ) __field( unsigned short, eh_entries ) ), @@ -2188,18 +2203,23 @@ TRACE_EVENT(ext4_ext_remove_space_done, __entry->start = start; __entry->end = end; __entry->depth = depth; - __entry->partial = partial; + __entry->pc_pclu = pc->pclu; + __entry->pc_lblk = pc->lblk; + __entry->pc_state = pc->state; __entry->eh_entries = le16_to_cpu(eh_entries); ), - TP_printk("dev %d,%d ino %lu since %u end %u depth %d partial %lld " + TP_printk("dev %d,%d ino %lu since %u end %u depth %d " + "partial [pclu %lld lblk %u state %d] " "remaining_entries %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth, - (long long) __entry->partial, + (long long) __entry->pc_pclu, + (unsigned int) __entry->pc_lblk, + (int) __entry->pc_state, (unsigned short) __entry->eh_entries) ); @@ -2270,7 +2290,7 @@ TRACE_EVENT(ext4_es_remove_extent, __entry->lblk, __entry->len) ); -TRACE_EVENT(ext4_es_find_delayed_extent_range_enter, +TRACE_EVENT(ext4_es_find_extent_range_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), @@ -2292,7 +2312,7 @@ TRACE_EVENT(ext4_es_find_delayed_extent_range_enter, (unsigned long) __entry->ino, __entry->lblk) ); -TRACE_EVENT(ext4_es_find_delayed_extent_range_exit, +TRACE_EVENT(ext4_es_find_extent_range_exit, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), @@ -2512,6 +2532,41 @@ TRACE_EVENT(ext4_es_shrink, __entry->scan_time, __entry->nr_skipped, __entry->retried) ); +TRACE_EVENT(ext4_es_insert_delayed_block, + TP_PROTO(struct inode *inode, struct extent_status *es, + bool allocated), + + TP_ARGS(inode, es, allocated), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( ext4_lblk_t, lblk ) + __field( ext4_lblk_t, len ) + __field( ext4_fsblk_t, pblk ) + __field( char, status ) + __field( bool, allocated ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->lblk = es->es_lblk; + __entry->len = es->es_len; + __entry->pblk = ext4_es_pblock(es); + __entry->status = ext4_es_status(es); + __entry->allocated = allocated; + ), + + TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s " + "allocated %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->lblk, __entry->len, + __entry->pblk, show_extent_status(__entry->status), + __entry->allocated) +); + /* fsmap traces */ DECLARE_EVENT_CLASS(ext4_fsmap_class, TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h index 1db453e4b550..1acd2b179aef 100644 --- a/include/uapi/linux/firewire-cdev.h +++ b/include/uapi/linux/firewire-cdev.h @@ -47,11 +47,11 @@ #define FW_CDEV_EVENT_ISO_INTERRUPT_MULTICHANNEL 0x09 /** - * struct fw_cdev_event_common - Common part of all fw_cdev_event_ types + * struct fw_cdev_event_common - Common part of all fw_cdev_event_* types * @closure: For arbitrary use by userspace - * @type: Discriminates the fw_cdev_event_ types + * @type: Discriminates the fw_cdev_event_* types * - * This struct may be used to access generic members of all fw_cdev_event_ + * This struct may be used to access generic members of all fw_cdev_event_* * types regardless of the specific type. * * Data passed in the @closure field for a request will be returned in the @@ -123,7 +123,13 @@ struct fw_cdev_event_response { /** * struct fw_cdev_event_request - Old version of &fw_cdev_event_request2 + * @closure: See &fw_cdev_event_common; set by %FW_CDEV_IOC_ALLOCATE ioctl * @type: See &fw_cdev_event_common; always %FW_CDEV_EVENT_REQUEST + * @tcode: Transaction code of the incoming request + * @offset: The offset into the 48-bit per-node address space + * @handle: Reference to the kernel-side pending request + * @length: Data length, i.e. the request's payload size in bytes + * @data: Incoming data, if any * * This event is sent instead of &fw_cdev_event_request2 if the kernel or * the client implements ABI version <= 3. &fw_cdev_event_request lacks @@ -353,7 +359,7 @@ struct fw_cdev_event_phy_packet { }; /** - * union fw_cdev_event - Convenience union of fw_cdev_event_ types + * union fw_cdev_event - Convenience union of fw_cdev_event_* types * @common: Valid for all types * @bus_reset: Valid if @common.type == %FW_CDEV_EVENT_BUS_RESET * @response: Valid if @common.type == %FW_CDEV_EVENT_RESPONSE @@ -735,7 +741,7 @@ struct fw_cdev_set_iso_channels { * @header: Header and payload in case of a transmit context. * * &struct fw_cdev_iso_packet is used to describe isochronous packet queues. - * Use the FW_CDEV_ISO_ macros to fill in @control. + * Use the FW_CDEV_ISO_* macros to fill in @control. * The @header array is empty in case of receive contexts. * * Context type %FW_CDEV_ISO_CONTEXT_TRANSMIT: @@ -842,7 +848,7 @@ struct fw_cdev_queue_iso { * the %FW_CDEV_ISO_SYNC bit set * @tags: Tag filter bit mask. Only valid for isochronous reception. * Determines the tag values for which packets will be accepted. - * Use FW_CDEV_ISO_CONTEXT_MATCH_ macros to set @tags. + * Use FW_CDEV_ISO_CONTEXT_MATCH_* macros to set @tags. * @handle: Isochronous context handle within which to transmit or receive */ struct fw_cdev_start_iso { @@ -1009,8 +1015,8 @@ struct fw_cdev_send_stream_packet { * on the same card as this device. After transmission, an * %FW_CDEV_EVENT_PHY_PACKET_SENT event is generated. * - * The payload @data[] shall be specified in host byte order. Usually, - * @data[1] needs to be the bitwise inverse of @data[0]. VersaPHY packets + * The payload @data\[\] shall be specified in host byte order. Usually, + * @data\[1\] needs to be the bitwise inverse of @data\[0\]. VersaPHY packets * are an exception to this rule. * * The ioctl is only permitted on device files which represent a local node. diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 1a6fee974116..96c24478d8ce 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -29,6 +29,7 @@ #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 #define JFFS2_SUPER_MAGIC 0x72b6 +#define XFS_SUPER_MAGIC 0x58465342 /* "XFSB" */ #define PSTOREFS_MAGIC 0x6165676C #define EFIVARFS_MAGIC 0xde5e81e4 #define HOSTFS_SUPER_MAGIC 0x00c0ffee diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 812e59e13fe6..376de10929b3 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1833,17 +1833,15 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec) * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long - * - 'O' For a kobject based struct. Must be one of the following: - * - 'OF[fnpPcCF]' For a device tree object - * Without any optional arguments prints the full_name - * f device node full_name - * n device node name - * p device node phandle - * P device node path spec (name + @unit) - * F device node flags - * c major compatible string - * C full compatible string - * + * - 'OF[fnpPcCF]' For a device tree object + * Without any optional arguments prints the full_name + * f device node full_name + * n device node name + * p device node phandle + * P device node path spec (name + @unit) + * F device node flags + * c major compatible string + * C full compatible string * - 'x' For printing the address. Equivalent to "%lx". * * ** When making changes please also update: diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index aa0d3b2f1bb7..3625d6ade45c 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -17,7 +17,7 @@ config BRIDGE other third party bridge products. In order to use the Ethernet bridge, you'll need the bridge - configuration tools; see <file:Documentation/networking/bridge.txt> + configuration tools; see <file:Documentation/networking/bridge.rst> for location. Please read the Bridge mini-HOWTO for more information. diff --git a/net/core/datagram.c b/net/core/datagram.c index 6a034eb538a1..57f3a6fcfc1e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -808,8 +808,9 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, return -EINVAL; } - if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) - netdev_rx_csum_fault(skb->dev); + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) + netdev_rx_csum_fault(NULL); } return 0; fault: diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0958c7be2c22..f679c7a7d761 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3333,6 +3333,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) int idx; int s_idx = cb->family; int type = cb->nlh->nlmsg_type - RTM_BASE; + int ret = 0; if (s_idx == 0) s_idx = 1; @@ -3365,12 +3366,13 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) cb->prev_seq = 0; cb->seq = 0; } - if (dumpit(skb, cb)) + ret = dumpit(skb, cb); + if (ret < 0) break; } cb->family = idx; - return skb->len; + return skb->len ? : ret; } struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 63d5b58fbfdb..9250b309c742 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1761,7 +1761,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct in_device *in_dev; struct hlist_head *head; - int err; + int err = 0; s_h = cb->args[0]; s_idx = idx = cb->args[1]; @@ -1771,12 +1771,15 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - return err; + goto put_tgt_net; + err = 0; if (fillargs.ifindex) { dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) - return -ENODEV; + if (!dev) { + err = -ENODEV; + goto put_tgt_net; + } in_dev = __in_dev_get_rtnl(dev); if (in_dev) { @@ -1821,7 +1824,7 @@ put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - return skb->len; + return err < 0 ? err : skb->len; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 5bf653f36911..6df95be96311 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -829,6 +829,7 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, return -EINVAL; } + filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC); filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; @@ -899,6 +900,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { + if (filter.dump_all_families) + return skb->len; + NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); return -ENOENT; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7a3e2acda94c..a6defbec4f1b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2542,6 +2542,9 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { + if (filter.dump_all_families) + return skb->len; + NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); return -ENOENT; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cf8252d05a01..7e048288fcab 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2120,8 +2120,24 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, /* Note, we are only interested in != 0 or == 0, thus the * force to int. */ - return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, - inet_compute_pseudo); + err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, + inet_compute_pseudo); + if (err) + return err; + + if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) { + /* If SW calculated the value, we know it's bad */ + if (skb->csum_complete_sw) + return 1; + + /* HW says the value is bad. Let's validate that. + * skb->csum is no longer the full packet checksum, + * so don't treat it as such. + */ + skb_checksum_complete_unset(skb); + } + + return 0; } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 45b84dd5c4eb..7eb09c86fa13 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5089,23 +5089,25 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; + int err = 0; s_h = cb->args[0]; s_idx = idx = cb->args[1]; s_ip_idx = cb->args[2]; if (cb->strict_check) { - int err; - err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - return err; + goto put_tgt_net; + err = 0; if (fillargs.ifindex) { dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) - return -ENODEV; + if (!dev) { + err = -ENODEV; + goto put_tgt_net; + } idev = __in6_dev_get(dev); if (idev) { err = in6_dump_addrs(idev, skb, cb, s_ip_idx, @@ -5144,7 +5146,7 @@ put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - return skb->len; + return err < 0 ? err : skb->len; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 547515e8450a..377717045f8f 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -88,8 +88,24 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) * Note, we are only interested in != 0 or == 0, thus the * force to int. */ - return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, - ip6_compute_pseudo); + err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, + ip6_compute_pseudo); + if (err) + return err; + + if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) { + /* If SW calculated the value, we know it's bad */ + if (skb->csum_complete_sw) + return 1; + + /* HW says the value is bad. Let's validate that. + * skb->csum is no longer the full packet checksum, + * so don't treat is as such. + */ + skb_checksum_complete_unset(skb); + } + + return 0; } EXPORT_SYMBOL(udp6_csum_init); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2a058b408a6a..1b8bc008b53b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -620,6 +620,9 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { + if (arg.filter.dump_all_families) + return skb->len; + NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); return -ENOENT; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c3317ffb09eb..e2ea691e42c6 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2473,6 +2473,9 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { + if (filter.dump_all_families) + return skb->len; + NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist"); return -ENOENT; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e3226284e480..2a7423c39456 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2745,6 +2745,8 @@ static int ip6_route_check_nh_onlink(struct net *net, grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { if (!grt->dst.error && + /* ignore match if it is the default route */ + grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) && (grt->rt6i_flags & flags || dev != grt->dst.dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 022bca98bde6..ca3b0f46de53 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1320,7 +1320,6 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { [TCA_KIND] = { .type = NLA_STRING }, - [TCA_OPTIONS] = { .type = NLA_NESTED }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, diff --git a/scripts/check_00index.sh b/scripts/check_00index.sh deleted file mode 100755 index aa47f5926c80..000000000000 --- a/scripts/check_00index.sh +++ /dev/null @@ -1,67 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -cd Documentation/ - -# Check entries that should be removed - -obsolete="" -for i in $(tail -n +12 00-INDEX |grep -E '^[a-zA-Z0-9]+'); do - if [ ! -e $i ]; then - obsolete="$obsolete $i" - fi -done - -# Check directory entries that should be added -search="" -dir="" -for i in $(find . -maxdepth 1 -type d); do - if [ "$i" != "." ]; then - new=$(echo $i|perl -ne 's,./(.*),$1/,; print $_') - search="$search $new" - fi -done - -for i in $search; do - if [ "$(grep -P "^$i" 00-INDEX)" == "" ]; then - dir="$dir $i" - fi -done - -# Check file entries that should be added -search="" -file="" -for i in $(find . -maxdepth 1 -type f); do - if [ "$i" != "./.gitignore" ]; then - new=$(echo $i|perl -ne 's,./(.*),$1,; print $_') - search="$search $new" - fi -done - -for i in $search; do - if [ "$(grep -P "^$i\$" 00-INDEX)" == "" ]; then - file="$file $i" - fi -done - -# Output its findings - -echo -e "Documentation/00-INDEX check results:\n" - -if [ "$obsolete" != "" ]; then - echo -e "- Should remove those entries:\n\t$obsolete\n" -else - echo -e "- No obsolete entries\n" -fi - -if [ "$dir" != "" ]; then - echo -e "- Should document those directories:\n\t$dir\n" -else - echo -e "- No new directories to add\n" -fi - -if [ "$file" != "" ]; then - echo -e "- Should document those files:\n\t$file" -else - echo "- No new files to add" -fi diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 8f0f508a78e9..ffbe901a37b5 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1904,13 +1904,13 @@ sub process_name($$) { ++$warnings; } - if ($identifier =~ m/^struct/) { + if ($identifier =~ m/^struct\b/) { $decl_type = 'struct'; - } elsif ($identifier =~ m/^union/) { + } elsif ($identifier =~ m/^union\b/) { $decl_type = 'union'; - } elsif ($identifier =~ m/^enum/) { + } elsif ($identifier =~ m/^enum\b/) { $decl_type = 'enum'; - } elsif ($identifier =~ m/^typedef/) { + } elsif ($identifier =~ m/^typedef\b/) { $decl_type = 'typedef'; } else { $decl_type = 'function'; diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh index 3991ad1a368d..864f865eee55 100755 --- a/tools/testing/selftests/net/fib-onlink-tests.sh +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -167,8 +167,8 @@ setup() # add vrf table ip li add ${VRF} type vrf table ${VRF_TABLE} ip li set ${VRF} up - ip ro add table ${VRF_TABLE} unreachable default - ip -6 ro add table ${VRF_TABLE} unreachable default + ip ro add table ${VRF_TABLE} unreachable default metric 8192 + ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192 # create test interfaces ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} @@ -185,20 +185,20 @@ setup() for n in 1 3 5 7; do ip li set ${NETIFS[p${n}]} up ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done # move peer interfaces to namespace and add addresses for n in 2 4 6 8; do ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done - set +e + ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} + ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} - # let DAD complete - assume default of 1 probe - sleep 1 + set +e } cleanup() |