diff --git a/Documentation/filesystems/zonefs.txt b/Documentation/filesystems/zonefs.txt new file mode 100644 index 000000000000..935bf22031ca --- /dev/null +++ b/Documentation/filesystems/zonefs.txt @@ -0,0 +1,404 @@ +ZoneFS - Zone filesystem for Zoned block devices + +Introduction +============ + +zonefs is a very simple file system exposing each zone of a zoned block device +as a file. Unlike a regular POSIX-compliant file system with native zoned block +device support (e.g. f2fs), zonefs does not hide the sequential write +constraint of zoned block devices to the user. Files representing sequential +write zones of the device must be written sequentially starting from the end +of the file (append only writes). + +As such, zonefs is in essence closer to a raw block device access interface +than to a full-featured POSIX file system. The goal of zonefs is to simplify +the implementation of zoned block device support in applications by replacing +raw block device file accesses with a richer file API, avoiding relying on +direct block device file ioctls which may be more obscure to developers. One +example of this approach is the implementation of LSM (log-structured merge) +tree structures (such as used in RocksDB and LevelDB) on zoned block devices +by allowing SSTables to be stored in a zone file similarly to a regular file +system rather than as a range of sectors of the entire disk. The introduction +of the higher level construct "one file is one zone" can help reducing the +amount of changes needed in the application as well as introducing support for +different application programming languages. + +Zoned block devices +------------------- + +Zoned storage devices belong to a class of storage devices with an address +space that is divided into zones. A zone is a group of consecutive LBAs and all +zones are contiguous (there are no LBA gaps). Zones may have different types. +* Conventional zones: there are no access constraints to LBAs belonging to + conventional zones. Any read or write access can be executed, similarly to a + regular block device. +* Sequential zones: these zones accept random reads but must be written + sequentially. Each sequential zone has a write pointer maintained by the + device that keeps track of the mandatory start LBA position of the next write + to the device. As a result of this write constraint, LBAs in a sequential zone + cannot be overwritten. Sequential zones must first be erased using a special + command (zone reset) before rewriting. + +Zoned storage devices can be implemented using various recording and media +technologies. The most common form of zoned storage today uses the SCSI Zoned +Block Commands (ZBC) and Zoned ATA Commands (ZAC) interfaces on Shingled +Magnetic Recording (SMR) HDDs. + +Solid State Disks (SSD) storage devices can also implement a zoned interface +to, for instance, reduce internal write amplification due to garbage collection. +The NVMe Zoned NameSpace (ZNS) is a technical proposal of the NVMe standard +committee aiming at adding a zoned storage interface to the NVMe protocol. + +Zonefs Overview +=============== + +Zonefs exposes the zones of a zoned block device as files. The files +representing zones are grouped by zone type, which are themselves represented +by sub-directories. This file structure is built entirely using zone information +provided by the device and so does not require any complex on-disk metadata +structure. + +On-disk metadata +---------------- + +zonefs on-disk metadata is reduced to an immutable super block which +persistently stores a magic number and optional feature flags and values. On +mount, zonefs uses blkdev_report_zones() to obtain the device zone configuration +and populates the mount point with a static file tree solely based on this +information. File sizes come from the device zone type and write pointer +position managed by the device itself. + +The super block is always written on disk at sector 0. The first zone of the +device storing the super block is never exposed as a zone file by zonefs. If +the zone containing the super block is a sequential zone, the mkzonefs format +tool always "finishes" the zone, that is, it transitions the zone to a full +state to make it read-only, preventing any data write. + +Zone type sub-directories +------------------------- + +Files representing zones of the same type are grouped together under the same +sub-directory automatically created on mount. + +For conventional zones, the sub-directory "cnv" is used. This directory is +however created if and only if the device has usable conventional zones. If +the device only has a single conventional zone at sector 0, the zone will not +be exposed as a file as it will be used to store the zonefs super block. For +such devices, the "cnv" sub-directory will not be created. + +For sequential write zones, the sub-directory "seq" is used. + +These two directories are the only directories that exist in zonefs. Users +cannot create other directories and cannot rename nor delete the "cnv" and +"seq" sub-directories. + +The size of the directories indicated by the st_size field of struct stat, +obtained with the stat() or fstat() system calls, indicates the number of files +existing under the directory. + +Zone files +---------- + +Zone files are named using the number of the zone they represent within the set +of zones of a particular type. That is, both the "cnv" and "seq" directories +contain files named "0", "1", "2", ... The file numbers also represent +increasing zone start sector on the device. + +All read and write operations to zone files are not allowed beyond the file +maximum size, that is, beyond the zone size. Any access exceeding the zone +size is failed with the -EFBIG error. + +Creating, deleting, renaming or modifying any attribute of files and +sub-directories is not allowed. + +The number of blocks of a file as reported by stat() and fstat() indicates the +size of the file zone, or in other words, the maximum file size. + +Conventional zone files +----------------------- + +The size of conventional zone files is fixed to the size of the zone they +represent. Conventional zone files cannot be truncated. + +These files can be randomly read and written using any type of I/O operation: +buffered I/Os, direct I/Os, memory mapped I/Os (mmap), etc. There are no I/O +constraint for these files beyond the file size limit mentioned above. + +Sequential zone files +--------------------- + +The size of sequential zone files grouped in the "seq" sub-directory represents +the file's zone write pointer position relative to the zone start sector. + +Sequential zone files can only be written sequentially, starting from the file +end, that is, write operations can only be append writes. Zonefs makes no +attempt at accepting random writes and will fail any write request that has a +start offset not corresponding to the end of the file, or to the end of the last +write issued and still in-flight (for asynchrnous I/O operations). + +Since dirty page writeback by the page cache does not guarantee a sequential +write pattern, zonefs prevents buffered writes and writeable shared mappings +on sequential files. Only direct I/O writes are accepted for these files. +zonefs relies on the sequential delivery of write I/O requests to the device +implemented by the block layer elevator. An elevator implementing the sequential +write feature for zoned block device (ELEVATOR_F_ZBD_SEQ_WRITE elevator feature) +must be used. This type of elevator (e.g. mq-deadline) is the set by default +for zoned block devices on device initialization. + +There are no restrictions on the type of I/O used for read operations in +sequential zone files. Buffered I/Os, direct I/Os and shared read mappings are +all accepted. + +Truncating sequential zone files is allowed only down to 0, in which case, the +zone is reset to rewind the file zone write pointer position to the start of +the zone, or up to the zone size, in which case the file's zone is transitioned +to the FULL state (finish zone operation). + +Format options +-------------- + +Several optional features of zonefs can be enabled at format time. +* Conventional zone aggregation: ranges of contiguous conventional zones can be + aggregated into a single larger file instead of the default one file per zone. +* File ownership: The owner UID and GID of zone files is by default 0 (root) + but can be changed to any valid UID/GID. +* File access permissions: the default 640 access permissions can be changed. + +IO error handling +----------------- + +Zoned block devices may fail I/O requests for reasons similar to regular block +devices, e.g. due to bad sectors. However, in addition to such known I/O +failure pattern, the standards governing zoned block devices behavior define +additional conditions that result in I/O errors. + +* A zone may transition to the read-only condition (BLK_ZONE_COND_READONLY): + While the data already written in the zone is still readable, the zone can + no longer be written. No user action on the zone (zone management command or + read/write access) can change the zone condition back to a normal read/write + state. While the reasons for the device to transition a zone to read-only + state are not defined by the standards, a typical cause for such transition + would be a defective write head on an HDD (all zones under this head are + changed to read-only). + +* A zone may transition to the offline condition (BLK_ZONE_COND_OFFLINE): + An offline zone cannot be read nor written. No user action can transition an + offline zone back to an operational good state. Similarly to zone read-only + transitions, the reasons for a drive to transition a zone to the offline + condition are undefined. A typical cause would be a defective read-write head + on an HDD causing all zones on the platter under the broken head to be + inaccessible. + +* Unaligned write errors: These errors result from the host issuing write + requests with a start sector that does not correspond to a zone write pointer + position when the write request is executed by the device. Even though zonefs + enforces sequential file write for sequential zones, unaligned write errors + may still happen in the case of a partial failure of a very large direct I/O + operation split into multiple BIOs/requests or asynchronous I/O operations. + If one of the write request within the set of sequential write requests + issued to the device fails, all write requests after queued after it will + become unaligned and fail. + +* Delayed write errors: similarly to regular block devices, if the device side + write cache is enabled, write errors may occur in ranges of previously + completed writes when the device write cache is flushed, e.g. on fsync(). + Similarly to the previous immediate unaligned write error case, delayed write + errors can propagate through a stream of cached sequential data for a zone + causing all data to be dropped after the sector that caused the error. + +All I/O errors detected by zonefs are notified to the user with an error code +return for the system call that trigered or detected the error. The recovery +actions taken by zonefs in response to I/O errors depend on the I/O type (read +vs write) and on the reason for the error (bad sector, unaligned writes or zone +condition change). + +* For read I/O errors, zonefs does not execute any particular recovery action, + but only if the file zone is still in a good condition and there is no + inconsistency between the file inode size and its zone write pointer position. + If a problem is detected, I/O error recovery is executed (see below table). + +* For write I/O errors, zonefs I/O error recovery is always executed. + +* A zone condition change to read-only or offline also always triggers zonefs + I/O error recovery. + +Zonefs minimal I/O error recovery may change a file size and a file access +permissions. + +* File size changes: + Immediate or delayed write errors in a sequential zone file may cause the file + inode size to be inconsistent with the amount of data successfully written in + the file zone. For instance, the partial failure of a multi-BIO large write + operation will cause the zone write pointer to advance partially, even though + the entire write operation will be reported as failed to the user. In such + case, the file inode size must be advanced to reflect the zone write pointer + change and eventually allow the user to restart writing at the end of the + file. + A file size may also be reduced to reflect a delayed write error detected on + fsync(): in this case, the amount of data effectively written in the zone may + be less than originally indicated by the file inode size. After such I/O + error, zonefs always fixes a file inode size to reflect the amount of data + persistently stored in the file zone. + +* Access permission changes: + A zone condition change to read-only is indicated with a change in the file + access permissions to render the file read-only. This disables changes to the + file attributes and data modification. For offline zones, all permissions + (read and write) to the file are disabled. + +Further action taken by zonefs I/O error recovery can be controlled by the user +with the "errors=xxx" mount option. The table below summarizes the result of +zonefs I/O error processing depending on the mount option and on the zone +conditions. + + +--------------+-----------+-----------------------------------------+ + | | | Post error state | + | "errors=xxx" | device | access permissions | + | mount | zone | file file device zone | + | option | condition | size read write read write | + +--------------+-----------+-----------------------------------------+ + | | good | fixed yes no yes yes | + | remount-ro | read-only | fixed yes no yes no | + | (default) | offline | 0 no no no no | + +--------------+-----------+-----------------------------------------+ + | | good | fixed yes no yes yes | + | zone-ro | read-only | fixed yes no yes no | + | | offline | 0 no no no no | + +--------------+-----------+-----------------------------------------+ + | | good | 0 no no yes yes | + | zone-offline | read-only | 0 no no yes no | + | | offline | 0 no no no no | + +--------------+-----------+-----------------------------------------+ + | | good | fixed yes yes yes yes | + | repair | read-only | fixed yes no yes no | + | | offline | 0 no no no no | + +--------------+-----------+-----------------------------------------+ + +Further notes: +* The "errors=remount-ro" mount option is the default behavior of zonefs I/O + error processing if no errors mount option is specified. +* With the "errors=remount-ro" mount option, the change of the file access + permissions to read-only applies to all files. The file system is remounted + read-only. +* Access permission and file size changes due to the device transitioning zones + to the offline condition are permanent. Remounting or reformating the device + with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good + state. +* File access permission changes to read-only due to the device transitioning + zones to the read-only condition are permanent. Remounting or reformating + the device will not re-enable file write access. +* File access permission changes implied by the remount-ro, zone-ro and + zone-offline mount options are temporary for zones in a good condition. + Unmounting and remounting the file system will restore the previous default + (format time values) access rights to the files affected. +* The repair mount option triggers only the minimal set of I/O error recovery + actions, that is, file size fixes for zones in a good condition. Zones + indicated as being read-only or offline by the device still imply changes to + the zone file access permissions as noted in the table above. + +Mount options +------------- + +zonefs define the "errors=" mount option to allow the user to specify +zonefs behavior in response to I/O errors, inode size inconsistencies or zone +condition chages. The defined behaviors are as follow: +* remount-ro (default) +* zone-ro +* zone-offline +* repair + +The I/O error actions defined for each behavior is detailed in the previous +section. + +Zonefs User Space Tools +======================= + +The mkzonefs tool is used to format zoned block devices for use with zonefs. +This tool is available on Github at: + +https://github.com/damien-lemoal/zonefs-tools + +zonefs-tools also includes a test suite which can be run against any zoned +block device, including null_blk block device created with zoned mode. + +Examples +-------- + +The following formats a 15TB host-managed SMR HDD with 256 MB zones +with the conventional zones aggregation feature enabled. + +# mkzonefs -o aggr_cnv /dev/sdX +# mount -t zonefs /dev/sdX /mnt +# ls -l /mnt/ +total 0 +dr-xr-xr-x 2 root root 1 Nov 25 13:23 cnv +dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq + +The size of the zone files sub-directories indicate the number of files +existing for each type of zones. In this example, there is only one +conventional zone file (all conventional zones are aggregated under a single +file). + +# ls -l /mnt/cnv +total 137101312 +-rw-r----- 1 root root 140391743488 Nov 25 13:23 0 + +This aggregated conventional zone file can be used as a regular file. + +# mkfs.ext4 /mnt/cnv/0 +# mount -o loop /mnt/cnv/0 /data + +The "seq" sub-directory grouping files for sequential write zones has in this +example 55356 zones. + +# ls -lv /mnt/seq +total 14511243264 +-rw-r----- 1 root root 0 Nov 25 13:23 0 +-rw-r----- 1 root root 0 Nov 25 13:23 1 +-rw-r----- 1 root root 0 Nov 25 13:23 2 +... +-rw-r----- 1 root root 0 Nov 25 13:23 55354 +-rw-r----- 1 root root 0 Nov 25 13:23 55355 + +For sequential write zone files, the file size changes as data is appended at +the end of the file, similarly to any regular file system. + +# dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct +1+0 records in +1+0 records out +4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s + +# ls -l /mnt/seq/0 +-rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0 + +The written file can be truncated to the zone size, preventing any further +write operation. + +# truncate -s 268435456 /mnt/seq/0 +# ls -l /mnt/seq/0 +-rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0 + +Truncation to 0 size allows freeing the file zone storage space and restart +append-writes to the file. + +# truncate -s 0 /mnt/seq/0 +# ls -l /mnt/seq/0 +-rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0 + +Since files are statically mapped to zones on the disk, the number of blocks of +a file as reported by stat() and fstat() indicates the size of the file zone. + +# stat /mnt/seq/0 + File: /mnt/seq/0 + Size: 0 Blocks: 524288 IO Block: 4096 regular empty file +Device: 870h/2160d Inode: 50431 Links: 1 +Access: (0640/-rw-r-----) Uid: ( 0/ root) Gid: ( 0/ root) +Access: 2019-11-25 13:23:57.048971997 +0900 +Modify: 2019-11-25 13:52:25.553805765 +0900 +Change: 2019-11-25 13:52:25.553805765 +0900 + Birth: - + +The number of blocks of the file ("Blocks") in units of 512B blocks gives the +maximum file size of 524288 * 512 B = 256 MB, corresponding to the device zone +size in this example. Of note is that the "IO block" field always indicates the +minimum I/O size for writes and corresponds to the device physical sector size. diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index d7e6534a8505..0e0eb2c8da7d 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -28,7 +28,6 @@ This document describes the Linux kernel Makefiles. --- 4.3 Using C++ for host programs --- 4.4 Controlling compiler options for host programs --- 4.5 When host programs are actually built - --- 4.6 Using hostprogs-$(CONFIG_FOO) === 5 Kbuild clean infrastructure @@ -595,11 +594,11 @@ compilation stage. Two steps are required in order to use a host executable. The first step is to tell kbuild that a host program exists. This is -done utilising the variable hostprogs-y. +done utilising the variable "hostprogs". The second step is to add an explicit dependency to the executable. This can be done in two ways. Either add the dependency in a rule, -or utilise the variable $(always). +or utilise the variable "always-y". Both possibilities are described in the following. 4.1 Simple Host Program @@ -612,7 +611,7 @@ Both possibilities are described in the following. Example:: - hostprogs-y := bin2hex + hostprogs := bin2hex Kbuild assumes in the above example that bin2hex is made from a single c-source file named bin2hex.c located in the same directory as @@ -630,7 +629,7 @@ Both possibilities are described in the following. Example:: #scripts/lxdialog/Makefile - hostprogs-y := lxdialog + hostprogs := lxdialog lxdialog-objs := checklist.o lxdialog.o Objects with extension .o are compiled from the corresponding .c @@ -650,7 +649,7 @@ Both possibilities are described in the following. Example:: #scripts/kconfig/Makefile - hostprogs-y := qconf + hostprogs := qconf qconf-cxxobjs := qconf.o In the example above the executable is composed of the C++ file @@ -662,7 +661,7 @@ Both possibilities are described in the following. Example:: #scripts/kconfig/Makefile - hostprogs-y := qconf + hostprogs := qconf qconf-cxxobjs := qconf.o qconf-objs := check.o @@ -710,7 +709,7 @@ Both possibilities are described in the following. Example:: #drivers/pci/Makefile - hostprogs-y := gen-devlist + hostprogs := gen-devlist $(obj)/devlist.h: $(src)/pci.ids $(obj)/gen-devlist ( cd $(obj); ./gen-devlist ) < $< @@ -718,47 +717,31 @@ Both possibilities are described in the following. $(obj)/gen-devlist is updated. Note that references to the host programs in special rules must be prefixed with $(obj). - (2) Use $(always) + (2) Use always-y When there is no suitable special rule, and the host program - shall be built when a makefile is entered, the $(always) + shall be built when a makefile is entered, the always-y variable shall be used. Example:: #scripts/lxdialog/Makefile - hostprogs-y := lxdialog - always := $(hostprogs-y) + hostprogs := lxdialog + always-y := $(hostprogs) This will tell kbuild to build lxdialog even if not referenced in any rule. -4.6 Using hostprogs-$(CONFIG_FOO) ---------------------------------- - - A typical pattern in a Kbuild file looks like this: - - Example:: - - #scripts/Makefile - hostprogs-$(CONFIG_KALLSYMS) += kallsyms - - Kbuild knows about both 'y' for built-in and 'm' for module. - So if a config symbol evaluates to 'm', kbuild will still build - the binary. In other words, Kbuild handles hostprogs-m exactly - like hostprogs-y. But only hostprogs-y is recommended to be used - when no CONFIG symbols are involved. - 5 Kbuild clean infrastructure ============================= "make clean" deletes most generated files in the obj tree where the kernel is compiled. This includes generated files such as host programs. -Kbuild knows targets listed in $(hostprogs-y), $(hostprogs-m), $(always), -$(extra-y) and $(targets). They are all deleted during "make clean". -Files matching the patterns "*.[oas]", "*.ko", plus some additional files -generated by kbuild are deleted all over the kernel src tree when -"make clean" is executed. +Kbuild knows targets listed in $(hostprogs), $(always-y), $(always-m), +$(always-), $(extra-y), $(extra-) and $(targets). They are all deleted +during "make clean". Files matching the patterns "*.[oas]", "*.ko", plus +some additional files generated by kbuild are deleted all over the kernel +source tree when "make clean" is executed. Additional files or directories can be specified in kbuild makefiles by use of $(clean-files). @@ -1269,12 +1252,12 @@ When kbuild executes, the following steps are followed (roughly): Example:: #arch/x86/kernel/Makefile - always := vmlinux.lds + extra-y := vmlinux.lds #Makefile export CPPFLAGS_vmlinux.lds += -P -C -U$(ARCH) - The assignment to $(always) is used to tell kbuild to build the + The assignment to extra-y is used to tell kbuild to build the target vmlinux.lds. The assignment to $(CPPFLAGS_vmlinux.lds) tells kbuild to use the specified options when building the target vmlinux.lds. diff --git a/Kbuild b/Kbuild index 3109ac786e76..fa441b98c9f6 100644 --- a/Kbuild +++ b/Kbuild @@ -7,7 +7,7 @@ bounds-file := include/generated/bounds.h -always := $(bounds-file) +always-y := $(bounds-file) targets := kernel/bounds.s $(bounds-file): kernel/bounds.s FORCE @@ -28,7 +28,7 @@ $(timeconst-file): kernel/time/timeconst.bc FORCE offsets-file := include/generated/asm-offsets.h -always += $(offsets-file) +always-y += $(offsets-file) targets += arch/$(SRCARCH)/kernel/asm-offsets.s arch/$(SRCARCH)/kernel/asm-offsets.s: $(timeconst-file) $(bounds-file) @@ -39,7 +39,7 @@ $(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE ##### # Check for missing system calls -always += missing-syscalls +always-y += missing-syscalls quiet_cmd_syscalls = CALL $< cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags) $(missing_syscalls_flags) @@ -50,7 +50,7 @@ missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE ##### # Check atomic headers are up-to-date -always += old-atomics +always-y += old-atomics quiet_cmd_atomics = CALL $< cmd_atomics = $(CONFIG_SHELL) $< diff --git a/MAINTAINERS b/MAINTAINERS index e7874c4d83f0..38fe2f3f7b6f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13360,7 +13360,7 @@ S: Maintained F: fs/timerfd.c F: include/linux/timer* F: include/linux/time_namespace.h -F: kernel/time_namespace.c +F: kernel/time/namespace.c F: kernel/time/*timer* POWER MANAGEMENT CORE @@ -17138,7 +17138,6 @@ F: drivers/staging/unisys/ UNIVERSAL FLASH STORAGE HOST CONTROLLER DRIVER R: Alim Akhtar R: Avri Altman -R: Pedro Sousa L: linux-scsi@vger.kernel.org S: Supported F: Documentation/scsi/ufs.txt @@ -17792,6 +17791,12 @@ F: include/linux/vbox_utils.h F: include/uapi/linux/vbox*.h F: drivers/virt/vboxguest/ +VIRTUAL BOX SHARED FOLDER VFS DRIVER: +M: Hans de Goede +L: linux-fsdevel@vger.kernel.org +S: Maintained +F: fs/vboxsf/* + VIRTUAL SERIO DEVICE DRIVER M: Stephen Chandler Paul S: Maintained @@ -18491,6 +18496,16 @@ L: linux-kernel@vger.kernel.org S: Maintained F: arch/x86/kernel/cpu/zhaoxin.c +ZONEFS FILESYSTEM +M: Damien Le Moal +M: Naohiro Aota +R: Johannes Thumshirn +L: linux-fsdevel@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs.git +S: Maintained +F: fs/zonefs/ +F: Documentation/filesystems/zonefs.txt + ZPOOL COMPRESSED PAGE STORAGE API M: Dan Streetman L: linux-mm@kvack.org diff --git a/Makefile b/Makefile index 65a5dc653deb..84b71845c43f 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 -PATCHLEVEL = 5 +PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -1679,7 +1679,7 @@ PHONY += descend $(build-dirs) descend: $(build-dirs) $(build-dirs): prepare $(Q)$(MAKE) $(build)=$@ \ - single-build=$(if $(filter-out $@/, $(single-no-ko)),1) \ + single-build=$(if $(filter-out $@/, $(filter $@/%, $(single-no-ko))),1) \ need-builtin=1 need-modorder=1 clean-dirs := $(addprefix _clean_, $(clean-dirs)) diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile index 991e023a6fc4..d8dba85e606c 100644 --- a/arch/alpha/boot/Makefile +++ b/arch/alpha/boot/Makefile @@ -8,7 +8,7 @@ # Copyright (C) 1994 by Linus Torvalds # -hostprogs-y := tools/mkbb tools/objstrip +hostprogs := tools/mkbb tools/objstrip targets := vmlinux.gz vmlinux \ vmlinux.nh tools/lxboot tools/bootlx tools/bootph \ tools/bootpzh bootloader bootpheader bootpzheader diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index b5752f0e8936..c815477b4303 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -326,16 +326,16 @@ static inline u64 __gic_readq_nonatomic(const volatile void __iomem *addr) #define gits_write_cwriter(v, c) __gic_writeq_nonatomic(v, c) /* - * GITS_VPROPBASER - hi and lo bits may be accessed independently. + * GICR_VPROPBASER - hi and lo bits may be accessed independently. */ -#define gits_read_vpropbaser(c) __gic_readq_nonatomic(c) -#define gits_write_vpropbaser(v, c) __gic_writeq_nonatomic(v, c) +#define gicr_read_vpropbaser(c) __gic_readq_nonatomic(c) +#define gicr_write_vpropbaser(v, c) __gic_writeq_nonatomic(v, c) /* - * GITS_VPENDBASER - the Valid bit must be cleared before changing + * GICR_VPENDBASER - the Valid bit must be cleared before changing * anything else. */ -static inline void gits_write_vpendbaser(u64 val, void __iomem *addr) +static inline void gicr_write_vpendbaser(u64 val, void __iomem *addr) { u32 tmp; @@ -352,7 +352,7 @@ static inline void gits_write_vpendbaser(u64 val, void __iomem *addr) __gic_writeq_nonatomic(val, addr); } -#define gits_read_vpendbaser(c) __gic_readq_nonatomic(c) +#define gicr_read_vpendbaser(c) __gic_readq_nonatomic(c) static inline bool gic_prio_masking_enabled(void) { diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 1babb392e70a..d3c9f03e7e79 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -5,7 +5,7 @@ ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32 include $(srctree)/lib/vdso/Makefile -hostprogs-y := vdsomunge +hostprogs := vdsomunge obj-vdso := vgettimeofday.o datapage.o note.o diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 4750fc8030c3..25fec4bde43a 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -140,11 +140,11 @@ static inline u32 gic_read_rpr(void) #define gicr_write_pendbaser(v, c) writeq_relaxed(v, c) #define gicr_read_pendbaser(c) readq_relaxed(c) -#define gits_write_vpropbaser(v, c) writeq_relaxed(v, c) -#define gits_read_vpropbaser(c) readq_relaxed(c) +#define gicr_write_vpropbaser(v, c) writeq_relaxed(v, c) +#define gicr_read_vpropbaser(c) readq_relaxed(c) -#define gits_write_vpendbaser(v, c) writeq_relaxed(v, c) -#define gits_read_vpendbaser(c) readq_relaxed(c) +#define gicr_write_vpendbaser(v, c) writeq_relaxed(v, c) +#define gicr_read_vpendbaser(c) readq_relaxed(c) static inline bool gic_prio_masking_enabled(void) { diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 76b327f88fbb..04df57b43cb1 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -115,9 +115,9 @@ VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd) # Borrow vdsomunge.c from the arm vDSO # We have to use a relative path because scripts/Makefile.host prefixes -# $(hostprogs-y) with $(obj) +# $(hostprogs) with $(obj) munge := ../../../arm/vdso/vdsomunge -hostprogs-y := $(munge) +hostprogs := $(munge) c-obj-vdso := note.o c-obj-vdso-gettimeofday := vgettimeofday.o diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index 4ed45ade32a1..a3da2c5d63c2 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -21,7 +21,7 @@ endif drop-sections := .reginfo .mdebug .comment .note .pdr .options .MIPS.options strip-flags := $(addprefix --remove-section=,$(drop-sections)) -hostprogs-y := elf2ecoff +hostprogs := elf2ecoff suffix-y := bin suffix-$(CONFIG_KERNEL_BZIP2) := bz2 diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index d859f079b771..0df0ee8a298d 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -84,7 +84,7 @@ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE HOSTCFLAGS_calc_vmlinuz_load_addr.o += $(LINUXINCLUDE) # Calculate the load address of the compressed kernel image -hostprogs-y := calc_vmlinuz_load_addr +hostprogs := calc_vmlinuz_load_addr ifneq ($(zload-y),) VMLINUZ_LOAD_ADDRESS := $(zload-y) @@ -112,7 +112,7 @@ ifdef CONFIG_MACH_DECSTATION endif # elf2ecoff can only handle 32bit image -hostprogs-y += ../elf2ecoff +hostprogs += ../elf2ecoff ifdef CONFIG_32BIT VMLINUZ = vmlinuz diff --git a/arch/mips/boot/tools/Makefile b/arch/mips/boot/tools/Makefile index 5f8e737348eb..592e05a51a4a 100644 --- a/arch/mips/boot/tools/Makefile +++ b/arch/mips/boot/tools/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -hostprogs-y += relocs +hostprogs += relocs relocs-objs += relocs_32.o relocs-objs += relocs_64.o relocs-objs += relocs_main.o diff --git a/arch/mips/tools/Makefile b/arch/mips/tools/Makefile index aaef688749f5..b851e5dcc65a 100644 --- a/arch/mips/tools/Makefile +++ b/arch/mips/tools/Makefile @@ -1,10 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -hostprogs-y := elf-entry +hostprogs := elf-entry PHONY += elf-entry elf-entry: $(obj)/elf-entry @: -hostprogs-$(CONFIG_CPU_LOONGSON3_WORKAROUNDS) += loongson3-llsc-check +hostprogs += loongson3-llsc-check PHONY += loongson3-llsc-check loongson3-llsc-check: $(obj)/loongson3-llsc-check @: diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index b2a2e032dc99..aa89a41dc5dd 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -100,7 +100,7 @@ $(obj)/%.so.raw: OBJCOPYFLAGS := -S $(obj)/%.so.raw: $(obj)/%.so.dbg.raw FORCE $(call if_changed,objcopy) -hostprogs-y := genvdso +hostprogs := genvdso quiet_cmd_genvdso = GENVDSO $@ define cmd_genvdso diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index dfbd7f22eef5..0556bf4fc9e9 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -224,7 +224,7 @@ $(patsubst %.S,%.o, $(filter %.S, $(src-boot))): %.o: %.S FORCE $(obj)/wrapper.a: $(obj-wlib) FORCE $(call if_changed,bootar) -hostprogs-y := addnote hack-coff mktree +hostprogs := addnote hack-coff mktree targets += $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) extra-y := $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \ @@ -464,7 +464,7 @@ WRAPPER_BINDIR := /usr/sbin INSTALL := install extra-installed := $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(extra-y)) -hostprogs-installed := $(patsubst %, $(DESTDIR)$(WRAPPER_BINDIR)/%, $(hostprogs-y)) +hostprogs-installed := $(patsubst %, $(DESTDIR)$(WRAPPER_BINDIR)/%, $(hostprogs)) wrapper-installed := $(DESTDIR)$(WRAPPER_BINDIR)/wrapper dts-installed := $(patsubst $(dtstree)/%, $(DESTDIR)$(WRAPPER_DTSDIR)/%, $(wildcard $(dtstree)/*.dts)) diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index eea28ca679db..bc7d9d06a6d9 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -35,7 +35,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; - allow_write_to_user(uaddr, sizeof(*uaddr)); + allow_read_write_user(uaddr, uaddr, sizeof(*uaddr)); pagefault_disable(); switch (op) { @@ -62,7 +62,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, *oval = oldval; - prevent_write_to_user(uaddr, sizeof(*uaddr)); + prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr)); return ret; } @@ -76,7 +76,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(uaddr, sizeof(u32))) return -EFAULT; - allow_write_to_user(uaddr, sizeof(*uaddr)); + allow_read_write_user(uaddr, uaddr, sizeof(*uaddr)); + __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\ @@ -97,7 +98,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "cc", "memory"); *uval = prev; - prevent_write_to_user(uaddr, sizeof(*uaddr)); + prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr)); + return ret; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 77abbc34bbe0..0713daa651d9 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -214,7 +214,7 @@ transfer_to_handler_cont: * To speed up the syscall path where interrupts stay on, let's check * first if we are changing the MSR value at all. */ - tophys(r12, r1) + tophys_novmstack r12, r1 lwz r12,_MSR(r12) andi. r12,r12,MSR_EE bne 1f diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile index b5e35e8f999a..f9dd47ff9ac4 100644 --- a/arch/s390/tools/Makefile +++ b/arch/s390/tools/Makefile @@ -10,8 +10,8 @@ PHONY += kapi kapi: $(kapi-hdrs-y) -hostprogs-y += gen_facilities -hostprogs-y += gen_opcode_table +hostprogs += gen_facilities +hostprogs += gen_opcode_table HOSTCFLAGS_gen_facilities.o += $(LINUXINCLUDE) diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile index ec8cd703b708..380e2b018992 100644 --- a/arch/sparc/boot/Makefile +++ b/arch/sparc/boot/Makefile @@ -7,7 +7,7 @@ ROOT_IMG := /usr/src/root.img ELFTOAOUT := elftoaout -hostprogs-y := piggyback +hostprogs := piggyback targets := tftpboot.img image zImage vmlinux.aout clean-files := System.map diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 997ffe46e953..708cb6304c2d 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -41,7 +41,7 @@ $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) HOST_EXTRACFLAGS += -I$(srctree)/tools/include -hostprogs-y += vdso2c +hostprogs += vdso2c quiet_cmd_vdso2c = VDSO2C $@ cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 748b6d28a91d..012b82fc8617 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -45,8 +45,8 @@ setup-y += video-vesa.o setup-y += video-bios.o targets += $(setup-y) -hostprogs-y := tools/build -hostprogs-$(CONFIG_X86_FEATURE_NAMES) += mkcpustr +hostprogs := tools/build +hostprogs += mkcpustr HOST_EXTRACFLAGS += -I$(srctree)/tools/include \ -include include/generated/autoconf.h \ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 56aa5fa0a66b..26050ae0b27e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -58,7 +58,7 @@ KBUILD_LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \ endif LDFLAGS_vmlinux := -T -hostprogs-y := mkpiggy +hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 25019d42ae93..ef2ad7253cd5 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -393,7 +393,13 @@ int count_immovable_mem_regions(void) table = table_addr + sizeof(struct acpi_table_srat); while (table + sizeof(struct acpi_subtable_header) < table_end) { + sub_table = (struct acpi_subtable_header *)table; + if (!sub_table->length) { + debug_putstr("Invalid zero length SRAT subtable.\n"); + return 0; + } + if (sub_table->type == ACPI_SRAT_TYPE_MEMORY_AFFINITY) { struct acpi_srat_mem_affinity *ma; diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 2b75e80f6b41..433a1259f61d 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -59,7 +59,7 @@ $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso_and_check) HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi -hostprogs-y += vdso2c +hostprogs += vdso2c quiet_cmd_vdso2c = VDSO2C $@ cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index caaf4dce99bf..b0da5320bcff 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -21,11 +21,15 @@ #include #include #include +#include #include void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); +/* Storage to save the hypercall page temporarily for hibernation */ +static void *hv_hypercall_pg_saved; + u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); @@ -246,6 +250,48 @@ static int __init hv_pci_init(void) return 1; } +static int hv_suspend(void) +{ + union hv_x64_msr_hypercall_contents hypercall_msr; + + /* + * Reset the hypercall page as it is going to be invalidated + * accross hibernation. Setting hv_hypercall_pg to NULL ensures + * that any subsequent hypercall operation fails safely instead of + * crashing due to an access of an invalid page. The hypercall page + * pointer is restored on resume. + */ + hv_hypercall_pg_saved = hv_hypercall_pg; + hv_hypercall_pg = NULL; + + /* Disable the hypercall page in the hypervisor */ + rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.enable = 0; + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + return 0; +} + +static void hv_resume(void) +{ + union hv_x64_msr_hypercall_contents hypercall_msr; + + /* Re-enable the hypercall page */ + rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.enable = 1; + hypercall_msr.guest_physical_address = + vmalloc_to_pfn(hv_hypercall_pg_saved); + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + hv_hypercall_pg = hv_hypercall_pg_saved; + hv_hypercall_pg_saved = NULL; +} + +static struct syscore_ops hv_syscore_ops = { + .suspend = hv_suspend, + .resume = hv_resume, +}; + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -330,6 +376,8 @@ void __init hyperv_init(void) x86_init.pci.arch_init = hv_pci_init; + register_syscore_ops(&hv_syscore_ops); + return; remove_cpuhp_state: @@ -349,6 +397,8 @@ void hyperv_cleanup(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + unregister_syscore_ops(&hv_syscore_ops); + /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 2ebc17d9c72c..19e94af9cc5d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -140,6 +140,7 @@ extern void apic_soft_disable(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); +extern void apic_intr_mode_select(void); extern void apic_intr_mode_init(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); @@ -188,6 +189,7 @@ static inline void disable_local_APIC(void) { } # define setup_secondary_APIC_clock x86_init_noop static inline void lapic_update_tsc_freq(void) { } static inline void init_bsp_APIC(void) { } +static inline void apic_intr_mode_select(void) { } static inline void apic_intr_mode_init(void) { } static inline void lapic_assign_system_vectors(void) { } static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } @@ -452,6 +454,14 @@ static inline void ack_APIC_irq(void) apic_eoi(); } + +static inline bool lapic_vector_set_in_irr(unsigned int vector) +{ + u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + + return !!(irr & (1U << (vector % 32))); +} + static inline unsigned default_get_apic_id(unsigned long x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 19435858df5f..96d9cd208610 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -51,12 +51,14 @@ struct x86_init_resources { * are set up. * @intr_init: interrupt init code * @trap_init: platform specific trap setup + * @intr_mode_select: interrupt delivery mode selection * @intr_mode_init: interrupt delivery mode setup */ struct x86_init_irqs { void (*pre_vector_init)(void); void (*intr_init)(void); void (*trap_init)(void); + void (*intr_mode_select)(void); void (*intr_mode_init)(void); }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 28446fa6bf18..5f973fed3c9f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -830,8 +830,17 @@ bool __init apic_needs_pit(void) if (!tsc_khz || !cpu_khz) return true; - /* Is there an APIC at all? */ - if (!boot_cpu_has(X86_FEATURE_APIC)) + /* Is there an APIC at all or is it disabled? */ + if (!boot_cpu_has(X86_FEATURE_APIC) || disable_apic) + return true; + + /* + * If interrupt delivery mode is legacy PIC or virtual wire without + * configuration, the local APIC timer wont be set up. Make sure + * that the PIT is initialized. + */ + if (apic_intr_mode == APIC_PIC || + apic_intr_mode == APIC_VIRTUAL_WIRE_NO_CONFIG) return true; /* Virt guests may lack ARAT, but still have DEADLINE */ @@ -1322,7 +1331,7 @@ void __init sync_Arb_IDs(void) enum apic_intr_mode_id apic_intr_mode __ro_after_init; -static int __init apic_intr_mode_select(void) +static int __init __apic_intr_mode_select(void) { /* Check kernel option */ if (disable_apic) { @@ -1384,6 +1393,12 @@ static int __init apic_intr_mode_select(void) return APIC_SYMMETRIC_IO; } +/* Select the interrupt delivery mode for the BSP */ +void __init apic_intr_mode_select(void) +{ + apic_intr_mode = __apic_intr_mode_select(); +} + /* * An initial setup of the virtual wire mode. */ @@ -1440,8 +1455,6 @@ void __init apic_intr_mode_init(void) { bool upmode = IS_ENABLED(CONFIG_UP_LATE_INIT); - apic_intr_mode = apic_intr_mode_select(); - switch (apic_intr_mode) { case APIC_PIC: pr_info("APIC: Keep in PIC mode(8259)\n"); @@ -2626,6 +2639,13 @@ static int lapic_suspend(void) #endif local_irq_save(flags); + + /* + * Mask IOAPIC before disabling the local APIC to prevent stale IRR + * entries on some implementations. + */ + mask_ioapic_entries(); + disable_local_APIC(); irq_remapping_disable(); diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 7f7533462474..159bd0cb8548 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -23,10 +23,8 @@ static struct irq_domain *msi_default_domain; -static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) @@ -47,6 +45,127 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) MSI_DATA_VECTOR(cfg->vector); } +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + __irq_msi_compose_msg(irqd_cfg(data), msg); +} + +static void irq_msi_update_msg(struct irq_data *irqd, struct irq_cfg *cfg) +{ + struct msi_msg msg[2] = { [1] = { }, }; + + __irq_msi_compose_msg(cfg, msg); + irq_data_get_irq_chip(irqd)->irq_write_msi_msg(irqd, msg); +} + +static int +msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) +{ + struct irq_cfg old_cfg, *cfg = irqd_cfg(irqd); + struct irq_data *parent = irqd->parent_data; + unsigned int cpu; + int ret; + + /* Save the current configuration */ + cpu = cpumask_first(irq_data_get_effective_affinity_mask(irqd)); + old_cfg = *cfg; + + /* Allocate a new target vector */ + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + /* + * For non-maskable and non-remapped MSI interrupts the migration + * to a different destination CPU and a different vector has to be + * done careful to handle the possible stray interrupt which can be + * caused by the non-atomic update of the address/data pair. + * + * Direct update is possible when: + * - The MSI is maskable (remapped MSI does not use this code path)). + * The quirk bit is not set in this case. + * - The new vector is the same as the old vector + * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The new destination CPU is the same as the old destination CPU + */ + if (!irqd_msi_nomask_quirk(irqd) || + cfg->vector == old_cfg.vector || + old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + cfg->dest_apicid == old_cfg.dest_apicid) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Paranoia: Validate that the interrupt target is the local + * CPU. + */ + if (WARN_ON_ONCE(cpu != smp_processor_id())) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Redirect the interrupt to the new vector on the current CPU + * first. This might cause a spurious interrupt on this vector if + * the device raises an interrupt right between this update and the + * update to the final destination CPU. + * + * If the vector is in use then the installed device handler will + * denote it as spurious which is no harm as this is a rare event + * and interrupt handlers have to cope with spurious interrupts + * anyway. If the vector is unused, then it is marked so it won't + * trigger the 'No irq handler for vector' warning in do_IRQ(). + * + * This requires to hold vector lock to prevent concurrent updates to + * the affected vector. + */ + lock_vector_lock(); + + /* + * Mark the new target vector on the local CPU if it is currently + * unused. Reuse the VECTOR_RETRIGGERED state which is also used in + * the CPU hotplug path for a similar purpose. This cannot be + * undone here as the current CPU has interrupts disabled and + * cannot handle the interrupt before the whole set_affinity() + * section is done. In the CPU unplug case, the current CPU is + * about to vanish and will not handle any interrupts anymore. The + * vector is cleaned up when the CPU comes online again. + */ + if (IS_ERR_OR_NULL(this_cpu_read(vector_irq[cfg->vector]))) + this_cpu_write(vector_irq[cfg->vector], VECTOR_RETRIGGERED); + + /* Redirect it to the new vector on the local CPU temporarily */ + old_cfg.vector = cfg->vector; + irq_msi_update_msg(irqd, &old_cfg); + + /* Now transition it to the target CPU */ + irq_msi_update_msg(irqd, cfg); + + /* + * All interrupts after this point are now targeted at the new + * vector/CPU. + * + * Drop vector lock before testing whether the temporary assignment + * to the local CPU was hit by an interrupt raised in the device, + * because the retrigger function acquires vector lock again. + */ + unlock_vector_lock(); + + /* + * Check whether the transition raced with a device interrupt and + * is pending in the local APICs IRR. It is safe to do this outside + * of vector lock as the irq_desc::lock of this interrupt is still + * held and interrupts are disabled: The check is not accessing the + * underlying vector store. It's just checking the local APIC's + * IRR. + */ + if (lapic_vector_set_in_irr(cfg->vector)) + irq_data_get_irq_chip(irqd)->irq_retrigger(irqd); + + return ret; +} + /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, * which implement the MSI or MSI-X Capability Structure. @@ -58,6 +177,7 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_set_affinity = msi_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -146,6 +266,8 @@ void __init arch_init_msi_domain(struct irq_domain *parent) } if (!msi_default_domain) pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); + else + msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; } #ifdef CONFIG_IRQ_REMAP diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 7ce29cee9f9e..d8673d8a779b 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -91,10 +91,18 @@ void __init hpet_time_init(void) static __init void x86_late_time_init(void) { - x86_init.timers.timer_init(); /* - * After PIT/HPET timers init, select and setup - * the final interrupt mode for delivering IRQs. + * Before PIT/HPET init, select the interrupt mode. This is required + * to make the decision whether PIT should be initialized correct. + */ + x86_init.irqs.intr_mode_select(); + + /* Setup the legacy timers */ + x86_init.timers.timer_init(); + + /* + * After PIT/HPET timers init, set up the final interrupt mode for + * delivering IRQs. */ x86_init.irqs.intr_mode_init(); tsc_init(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 23e25f3034c2..85f1a90c55cd 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -80,6 +80,7 @@ struct x86_init_ops x86_init __initdata = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .trap_init = x86_init_noop, + .intr_mode_select = apic_intr_mode_select, .intr_mode_init = apic_intr_mode_init }, diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 59f7f6d60cf6..ae923ee8e2b4 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -308,7 +308,7 @@ static void __init efi_clean_memmap(void) .phys_map = efi.memmap.phys_map, .desc_version = efi.memmap.desc_version, .desc_size = efi.memmap.desc_size, - .size = data.desc_size * (efi.memmap.nr_map - n_removal), + .size = efi.memmap.desc_size * (efi.memmap.nr_map - n_removal), .flags = 0, }; diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index f60501a384f9..99b6332ba540 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -12,7 +12,7 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -always := realmode.bin realmode.relocs +always-y := realmode.bin realmode.relocs wakeup-objs := wakeup_asm.o wakemain.o video-mode.o wakeup-objs += copy.o bioscall.o regs.o diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 09af7ff53044..55b1ab378974 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -26,7 +26,7 @@ posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity $(call cmd,posttest) $(call cmd,sanitytest) -hostprogs-y += insn_decoder_test insn_sanity +hostprogs += insn_decoder_test insn_sanity # -I needed for generated C source and C source which in the kernel tree. HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/ @@ -39,7 +39,7 @@ $(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/l $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c HOST_EXTRACFLAGS += -I$(srctree)/tools/include -hostprogs-y += relocs +hostprogs += relocs relocs-objs := relocs_32.o relocs_64.o relocs_common.o PHONY += relocs relocs: $(obj)/relocs diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index ae4a41ca19f6..1f756ffffe8b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1205,6 +1205,7 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_platform.get_nmi_reason = xen_get_nmi_reason; x86_init.resources.memory_setup = xen_memory_setup; + x86_init.irqs.intr_mode_select = x86_init_noop; x86_init.irqs.intr_mode_init = x86_init_noop; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile index 92ccd7aed0d4..c693b2ca0329 100644 --- a/drivers/gpu/drm/radeon/Makefile +++ b/drivers/gpu/drm/radeon/Makefile @@ -5,7 +5,7 @@ ccflags-y := -Idrivers/gpu/drm/amd/include -hostprogs-y := mkregtable +hostprogs := mkregtable clean-files := rn50_reg_safe.h r100_reg_safe.h r200_reg_safe.h rv515_reg_safe.h r300_reg_safe.h r420_reg_safe.h rs600_reg_safe.h r600_reg_safe.h evergreen_reg_safe.h cayman_reg_safe.h quiet_cmd_mkregtable = MKREGTABLE $@ diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 1006c694d9fb..6d397732138d 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -438,7 +438,7 @@ config CSKY_MPINTC help Say yes here to enable C-SKY SMP interrupt controller driver used for C-SKY SMP system. - In fact it's not mmio map in hw and it use ld/st to visit the + In fact it's not mmio map in hardware and it uses ld/st to visit the controller's register inside CPU. config CSKY_APB_INTC @@ -446,7 +446,7 @@ config CSKY_APB_INTC depends on CSKY help Say yes here to enable C-SKY APB interrupt controller driver used - by C-SKY single core SOC system. It use mmio map apb-bus to visit + by C-SKY single core SOC system. It uses mmio map apb-bus to visit the controller's register. config IMX_IRQSTEER diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index f71758632f8d..83b1186ffcad 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -661,7 +661,7 @@ static struct its_collection *its_build_invall_cmd(struct its_node *its, struct its_cmd_desc *desc) { its_encode_cmd(cmd, GITS_CMD_INVALL); - its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id); + its_encode_collection(cmd, desc->its_invall_cmd.col->col_id); its_fixup_cmd(cmd); @@ -2376,6 +2376,8 @@ static u64 inherit_vpe_l1_table_from_its(void) continue; /* We have a winner! */ + gic_data_rdist()->vpe_l1_base = its->tables[2].base; + val = GICR_VPROPBASER_4_1_VALID; if (baser & GITS_BASER_INDIRECT) val |= GICR_VPROPBASER_4_1_INDIRECT; @@ -2413,14 +2415,12 @@ static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask) for_each_possible_cpu(cpu) { void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base; - u32 tmp; if (!base || cpu == smp_processor_id()) continue; val = gic_read_typer(base + GICR_TYPER); - tmp = compute_common_aff(val); - if (tmp != aff) + if (aff != compute_common_aff(val)) continue; /* @@ -2429,9 +2429,10 @@ static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask) * ours wrt CommonLPIAff. Let's use its own VPROPBASER. * Make sure we don't write the Z bit in that case. */ - val = gits_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER); + val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER); val &= ~GICR_VPROPBASER_4_1_Z; + gic_data_rdist()->vpe_l1_base = gic_data_rdist_cpu(cpu)->vpe_l1_base; *mask = gic_data_rdist_cpu(cpu)->vpe_table_mask; return val; @@ -2440,6 +2441,72 @@ static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask) return 0; } +static bool allocate_vpe_l2_table(int cpu, u32 id) +{ + void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base; + unsigned int psz, esz, idx, npg, gpsz; + u64 val; + struct page *page; + __le64 *table; + + if (!gic_rdists->has_rvpeid) + return true; + + val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER); + + esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val) + 1; + gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val); + npg = FIELD_GET(GICR_VPROPBASER_4_1_SIZE, val) + 1; + + switch (gpsz) { + default: + WARN_ON(1); + /* fall through */ + case GIC_PAGE_SIZE_4K: + psz = SZ_4K; + break; + case GIC_PAGE_SIZE_16K: + psz = SZ_16K; + break; + case GIC_PAGE_SIZE_64K: + psz = SZ_64K; + break; + } + + /* Don't allow vpe_id that exceeds single, flat table limit */ + if (!(val & GICR_VPROPBASER_4_1_INDIRECT)) + return (id < (npg * psz / (esz * SZ_8))); + + /* Compute 1st level table index & check if that exceeds table limit */ + idx = id >> ilog2(psz / (esz * SZ_8)); + if (idx >= (npg * psz / GITS_LVL1_ENTRY_SIZE)) + return false; + + table = gic_data_rdist_cpu(cpu)->vpe_l1_base; + + /* Allocate memory for 2nd level table */ + if (!table[idx]) { + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz)); + if (!page) + return false; + + /* Flush Lvl2 table to PoC if hw doesn't support coherency */ + if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK)) + gic_flush_dcache_to_poc(page_address(page), psz); + + table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID); + + /* Flush Lvl1 entry to PoC if hw doesn't support coherency */ + if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK)) + gic_flush_dcache_to_poc(table + idx, GITS_LVL1_ENTRY_SIZE); + + /* Ensure updated table contents are visible to RD hardware */ + dsb(sy); + } + + return true; +} + static int allocate_vpe_l1_table(void) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -2457,8 +2524,8 @@ static int allocate_vpe_l1_table(void) * effect of making sure no doorbell will be generated and we can * then safely clear VPROPBASER.Valid. */ - if (gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid) - gits_write_vpendbaser(GICR_VPENDBASER_PendingLast, + if (gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid) + gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast, vlpi_base + GICR_VPENDBASER); /* @@ -2481,8 +2548,8 @@ static int allocate_vpe_l1_table(void) /* First probe the page size */ val = FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, GIC_PAGE_SIZE_64K); - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); - val = gits_read_vpropbaser(vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + val = gicr_read_vpropbaser(vlpi_base + GICR_VPROPBASER); gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val); esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val); @@ -2531,7 +2598,7 @@ static int allocate_vpe_l1_table(void) npg = 1; } - val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg); + val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg - 1); /* Right, that's the number of CPU pages we need for L1 */ np = DIV_ROUND_UP(npg * psz, PAGE_SIZE); @@ -2542,7 +2609,7 @@ static int allocate_vpe_l1_table(void) if (!page) return -ENOMEM; - gic_data_rdist()->vpe_l1_page = page; + gic_data_rdist()->vpe_l1_base = page_address(page); pa = virt_to_phys(page_address(page)); WARN_ON(!IS_ALIGNED(pa, psz)); @@ -2553,7 +2620,7 @@ static int allocate_vpe_l1_table(void) val |= GICR_VPROPBASER_4_1_VALID; out: - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); cpumask_set_cpu(smp_processor_id(), gic_data_rdist()->vpe_table_mask); pr_debug("CPU%d: VPROPBASER = %llx %*pbl\n", @@ -2660,14 +2727,14 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) bool clean; u64 val; - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); val &= ~GICR_VPENDBASER_Valid; val &= ~clr; val |= set; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); do { - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); if (!clean) { count--; @@ -2782,7 +2849,7 @@ static void its_cpu_init_lpis(void) val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n", smp_processor_id(), val); - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); /* * Also clear Valid bit of GICR_VPENDBASER, in case some @@ -2790,7 +2857,6 @@ static void its_cpu_init_lpis(void) * corrupting memory. */ val = its_clear_vpend_valid(vlpi_base, 0, 0); - WARN_ON(val & GICR_VPENDBASER_Dirty); } if (allocate_vpe_l1_table()) { @@ -2954,6 +3020,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id) static bool its_alloc_vpe_table(u32 vpe_id) { struct its_node *its; + int cpu; /* * Make sure the L2 tables are allocated on *all* v4 ITSs. We @@ -2976,6 +3043,19 @@ static bool its_alloc_vpe_table(u32 vpe_id) return false; } + /* Non v4.1? No need to iterate RDs and go back early. */ + if (!gic_rdists->has_rvpeid) + return true; + + /* + * Make sure the L2 tables are allocated for all copies of + * the L1 table on *all* v4.1 RDs. + */ + for_each_possible_cpu(cpu) { + if (!allocate_vpe_l2_table(cpu, vpe_id)) + return false; + } + return true; } @@ -3443,7 +3523,7 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; val |= GICR_VPROPBASER_RaWb; val |= GICR_VPROPBASER_InnerShareable; - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); val = virt_to_phys(page_address(vpe->vpt_page)) & GENMASK_ULL(51, 16); @@ -3461,7 +3541,7 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= GICR_VPENDBASER_PendingLast; val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0; val |= GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); } static void its_vpe_deschedule(struct its_vpe *vpe) @@ -3661,7 +3741,7 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe, val |= info->g1en ? GICR_VPENDBASER_4_1_VGRP1EN : 0; val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id); - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); } static void its_vpe_4_1_deschedule(struct its_vpe *vpe, diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 286f98222878..c1f7af9d9ae7 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1839,6 +1839,7 @@ static struct struct redist_region *redist_regs; u32 nr_redist_regions; bool single_redist; + int enabled_rdists; u32 maint_irq; int maint_irq_mode; phys_addr_t vcpu_base; @@ -1933,8 +1934,10 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, * If GICC is enabled and has valid gicr base address, then it means * GICR base is presented via GICC */ - if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) + if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) { + acpi_data.enabled_rdists++; return 0; + } /* * It's perfectly valid firmware can pass disabled GICC entry, driver @@ -1964,8 +1967,10 @@ static int __init gic_acpi_count_gicr_regions(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_match_gicc, 0); - if (count > 0) + if (count > 0) { acpi_data.single_redist = true; + count = acpi_data.enabled_rdists; + } return count; } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 4f2e6910c623..1cc2cd894f87 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1383,26 +1383,31 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) bool do_tx_balance = true; u32 hash_index = 0; const u8 *hash_start = NULL; - struct ipv6hdr *ip6hdr; skb_reset_mac_header(skb); eth_data = eth_hdr(skb); switch (ntohs(skb->protocol)) { case ETH_P_IP: { - const struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph; if (is_broadcast_ether_addr(eth_data->h_dest) || - iph->daddr == ip_bcast || - iph->protocol == IPPROTO_IGMP) { + !pskb_network_may_pull(skb, sizeof(*iph))) { + do_tx_balance = false; + break; + } + iph = ip_hdr(skb); + if (iph->daddr == ip_bcast || iph->protocol == IPPROTO_IGMP) { do_tx_balance = false; break; } hash_start = (char *)&(iph->daddr); hash_size = sizeof(iph->daddr); - } break; - case ETH_P_IPV6: + } + case ETH_P_IPV6: { + const struct ipv6hdr *ip6hdr; + /* IPv6 doesn't really use broadcast mac address, but leave * that here just in case. */ @@ -1419,7 +1424,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) break; } - /* Additianally, DAD probes should not be tx-balanced as that + if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) { + do_tx_balance = false; + break; + } + /* Additionally, DAD probes should not be tx-balanced as that * will lead to false positives for duplicate addresses and * prevent address configuration from working. */ @@ -1429,17 +1438,26 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) break; } - hash_start = (char *)&(ipv6_hdr(skb)->daddr); - hash_size = sizeof(ipv6_hdr(skb)->daddr); + hash_start = (char *)&ip6hdr->daddr; + hash_size = sizeof(ip6hdr->daddr); break; - case ETH_P_IPX: - if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) { + } + case ETH_P_IPX: { + const struct ipxhdr *ipxhdr; + + if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) { + do_tx_balance = false; + break; + } + ipxhdr = (struct ipxhdr *)skb_network_header(skb); + + if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) { /* something is wrong with this packet */ do_tx_balance = false; break; } - if (ipx_hdr(skb)->ipx_type != IPX_TYPE_NCP) { + if (ipxhdr->ipx_type != IPX_TYPE_NCP) { /* The only protocol worth balancing in * this family since it has an "ARP" like * mechanism @@ -1448,9 +1466,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) break; } + eth_data = eth_hdr(skb); hash_start = (char *)eth_data->h_dest; hash_size = ETH_ALEN; break; + } case ETH_P_ARP: do_tx_balance = false; if (bond_info->rlb_enabled) diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 060497512159..449a22172e07 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -693,7 +693,7 @@ int b53_configure_vlan(struct dsa_switch *ds) b53_do_vlan_op(dev, VTA_CMD_CLEAR); } - b53_enable_vlan(dev, false, ds->vlan_filtering); + b53_enable_vlan(dev, dev->vlan_enabled, ds->vlan_filtering); b53_for_each_port(dev, i) b53_write16(dev, B53_VLAN_PAGE, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 3e8635311d0d..d1955543acd1 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -68,7 +68,9 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) /* Force link status for IMP port */ reg = core_readl(priv, offset); - reg |= (MII_SW_OR | LINK_STS | GMII_SPEED_UP_2G); + reg |= (MII_SW_OR | LINK_STS); + if (priv->type == BCM7278_DEVICE_ID) + reg |= GMII_SPEED_UP_2G; core_writel(priv, reg, offset); /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index c5f64959a184..1142768969c2 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -101,6 +101,12 @@ static struct spi_driver ksz9477_spi_driver = { module_spi_driver(ksz9477_spi_driver); +MODULE_ALIAS("spi:ksz9477"); +MODULE_ALIAS("spi:ksz9897"); +MODULE_ALIAS("spi:ksz9893"); +MODULE_ALIAS("spi:ksz9563"); +MODULE_ALIAS("spi:ksz8563"); +MODULE_ALIAS("spi:ksz9567"); MODULE_AUTHOR("Woojung Huh "); MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch SPI access Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f07ac0e0af59..e0611cba87f9 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2736,6 +2736,9 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) umac_reset(priv); + /* Disable the UniMAC RX/TX */ + umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, 0); + /* We may have been suspended and never received a WOL event that * would turn off MPD detection, take care of that now */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 7a2fe63d1136..4508f0d150da 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -73,7 +73,11 @@ struct sifive_fu540_macb_mgmt { /* Max length of transmit frame must be a multiple of 8 bytes */ #define MACB_TX_LEN_ALIGN 8 #define MACB_MAX_TX_LEN ((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1))) -#define GEM_MAX_TX_LEN ((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1))) +/* Limit maximum TX length as per Cadence TSO errata. This is to avoid a + * false amba_error in TX path from the DMA assuming there is not enough + * space in the SRAM (16KB) even when there is. + */ +#define GEM_MAX_TX_LEN (unsigned int)(0x3FC0) #define GEM_MTU_MIN_SIZE ETH_MIN_MTU #define MACB_NETIF_LSO NETIF_F_TSO @@ -1791,16 +1795,14 @@ static netdev_features_t macb_features_check(struct sk_buff *skb, /* Validate LSO compatibility */ - /* there is only one buffer */ - if (!skb_is_nonlinear(skb)) + /* there is only one buffer or protocol is not UDP */ + if (!skb_is_nonlinear(skb) || (ip_hdr(skb)->protocol != IPPROTO_UDP)) return features; /* length of header */ hdrlen = skb_transport_offset(skb); - if (ip_hdr(skb)->protocol == IPPROTO_TCP) - hdrlen += tcp_hdrlen(skb); - /* For LSO: + /* For UFO only: * When software supplies two or more payload buffers all payload buffers * apart from the last must be a multiple of 8 bytes in size. */ diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index c4f6ec0cd183..17a4110c2e49 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1039,7 +1039,7 @@ static int phy_interface_mode(u8 lmac_type) if (lmac_type == BGX_MODE_QSGMII) return PHY_INTERFACE_MODE_QSGMII; if (lmac_type == BGX_MODE_RGMII) - return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_RGMII_RXID; return PHY_INTERFACE_MODE_SGMII; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 9d1f2f88b945..de30d61af065 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3403,6 +3403,13 @@ static int chcr_stats_show(struct seq_file *seq, void *v) atomic_read(&adap->chcr_stats.fallback)); seq_printf(seq, "IPSec PDU: %10u\n", atomic_read(&adap->chcr_stats.ipsec_cnt)); + seq_printf(seq, "TLS PDU Tx: %10u\n", + atomic_read(&adap->chcr_stats.tls_pdu_tx)); + seq_printf(seq, "TLS PDU Rx: %10u\n", + atomic_read(&adap->chcr_stats.tls_pdu_rx)); + seq_printf(seq, "TLS Keys (DDR) Count: %10u\n", + atomic_read(&adap->chcr_stats.tls_key)); + return 0; } DEFINE_SHOW_ATTRIBUTE(chcr_stats); diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index d305d1b24b0a..42b798a3fad4 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -417,7 +417,10 @@ static void de_rx (struct de_private *de) if (status & DescOwn) break; - len = ((status >> 16) & 0x7ff) - 4; + /* the length is actually a 15 bit value here according + * to Table 4-1 in the DE2104x spec so mask is 0x7fff + */ + len = ((status >> 16) & 0x7fff) - 4; mapping = de->rx_skb[rx_tail].mapping; if (unlikely(drop)) { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 09dbcd819d84..fd93d542f497 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2453,6 +2453,9 @@ static void dpaa_adjust_link(struct net_device *net_dev) mac_dev->adjust_link(mac_dev); } +/* The Aquantia PHYs are capable of performing rate adaptation */ +#define PHY_VEND_AQUANTIA 0x03a1b400 + static int dpaa_phy_init(struct net_device *net_dev) { __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; @@ -2471,9 +2474,14 @@ static int dpaa_phy_init(struct net_device *net_dev) return -ENODEV; } - /* Remove any features not supported by the controller */ - ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support); - linkmode_and(phy_dev->supported, phy_dev->supported, mask); + /* Unless the PHY is capable of rate adaptation */ + if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII || + ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) { + /* remove any features not supported by the controller */ + ethtool_convert_legacy_u32_to_link_mode(mask, + mac_dev->if_support); + linkmode_and(phy_dev->supported, phy_dev->supported, mask); + } phy_support_asym_pause(phy_dev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 42058fad6a3c..0b7d29192b2c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -791,7 +791,7 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) struct i40e_ring *ring; if (test_bit(__I40E_CONFIG_BUSY, pf->state)) - return -ENETDOWN; + return -EAGAIN; if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 037e054b01a2..98017e7d5dd0 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -401,6 +401,8 @@ struct mvneta_pcpu_stats { struct u64_stats_sync syncp; u64 rx_packets; u64 rx_bytes; + u64 rx_dropped; + u64 rx_errors; u64 tx_packets; u64 tx_bytes; }; @@ -738,6 +740,8 @@ mvneta_get_stats64(struct net_device *dev, struct mvneta_pcpu_stats *cpu_stats; u64 rx_packets; u64 rx_bytes; + u64 rx_dropped; + u64 rx_errors; u64 tx_packets; u64 tx_bytes; @@ -746,19 +750,20 @@ mvneta_get_stats64(struct net_device *dev, start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); rx_packets = cpu_stats->rx_packets; rx_bytes = cpu_stats->rx_bytes; + rx_dropped = cpu_stats->rx_dropped; + rx_errors = cpu_stats->rx_errors; tx_packets = cpu_stats->tx_packets; tx_bytes = cpu_stats->tx_bytes; } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; + stats->rx_dropped += rx_dropped; + stats->rx_errors += rx_errors; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; } - stats->rx_errors = dev->stats.rx_errors; - stats->rx_dropped = dev->stats.rx_dropped; - stats->tx_dropped = dev->stats.tx_dropped; } @@ -1736,8 +1741,14 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto, static void mvneta_rx_error(struct mvneta_port *pp, struct mvneta_rx_desc *rx_desc) { + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); u32 status = rx_desc->status; + /* update per-cpu counter */ + u64_stats_update_begin(&stats->syncp); + stats->rx_errors++; + u64_stats_update_end(&stats->syncp); + switch (status & MVNETA_RXD_ERR_CODE_MASK) { case MVNETA_RXD_ERR_CRC: netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n", @@ -2179,11 +2190,15 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, rxq->skb = build_skb(xdp->data_hard_start, PAGE_SIZE); if (unlikely(!rxq->skb)) { - netdev_err(dev, - "Can't allocate skb on queue %d\n", - rxq->id); - dev->stats.rx_dropped++; + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); + + netdev_err(dev, "Can't allocate skb on queue %d\n", rxq->id); rxq->skb_alloc_err++; + + u64_stats_update_begin(&stats->syncp); + stats->rx_dropped++; + u64_stats_update_end(&stats->syncp); + return -ENOMEM; } page_pool_release_page(rxq->page_pool, page); @@ -2270,7 +2285,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi, /* Check errors only for FIRST descriptor */ if (rx_status & MVNETA_RXD_ERR_SUMMARY) { mvneta_rx_error(pp, rx_desc); - dev->stats.rx_errors++; /* leave the descriptor untouched */ continue; } @@ -2372,7 +2386,6 @@ static int mvneta_rx_hwbm(struct napi_struct *napi, mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool, rx_desc->buf_phys_addr); err_drop_frame: - dev->stats.rx_errors++; mvneta_rx_error(pp, rx_desc); /* leave the descriptor untouched */ continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h index d787bc0a4155..e09bc3858d57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h @@ -45,7 +45,7 @@ void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id); static inline bool mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev) { - if (!MLX5_CAP_GEN(mdev, tls)) + if (!MLX5_CAP_GEN(mdev, tls_tx)) return false; if (!MLX5_CAP_GEN(mdev, log_max_dek)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c index 71384ad1a443..ef1ed15a53b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -269,7 +269,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev, int datalen; u32 skb_seq; - if (MLX5_CAP_GEN(sq->channel->mdev, tls)) { + if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx)) { skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi); goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 9e9960146e5b..1c3ab69cbd96 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -613,13 +613,6 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) wqe_counter = be16_to_cpu(cqe->wqe_counter); - if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { - netdev_WARN_ONCE(cq->channel->netdev, - "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe)); - if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) - queue_work(cq->channel->priv->wq, &sq->recover_work); - break; - } do { struct mlx5e_sq_wqe_info *wi; u16 ci; @@ -629,6 +622,15 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); wi = &sq->db.ico_wqe[ci]; + if (last_wqe && unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { + netdev_WARN_ONCE(cq->channel->netdev, + "Bad OP in ICOSQ CQE: 0x%x\n", + get_cqe_opcode(cqe)); + if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + queue_work(cq->channel->priv->wq, &sq->recover_work); + break; + } + if (likely(wi->opcode == MLX5_OPCODE_UMR)) { sqcc += MLX5E_UMR_WQEBBS; wi->umr.rq->mpwqe.umr_completed++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2565ba8692d9..ee60383adc5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -451,34 +451,17 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) i = 0; do { + struct mlx5e_tx_wqe_info *wi; u16 wqe_counter; bool last_wqe; + u16 ci; mlx5_cqwq_pop(&cq->wq); wqe_counter = be16_to_cpu(cqe->wqe_counter); - if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) { - if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, - &sq->state)) { - struct mlx5e_tx_wqe_info *wi; - u16 ci; - - ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); - wi = &sq->db.wqe_info[ci]; - mlx5e_dump_error_cqe(sq, - (struct mlx5_err_cqe *)cqe); - mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs); - queue_work(cq->channel->priv->wq, - &sq->recover_work); - } - stats->cqe_err++; - } - do { - struct mlx5e_tx_wqe_info *wi; struct sk_buff *skb; - u16 ci; int j; last_wqe = (sqcc == wqe_counter); @@ -516,6 +499,18 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) napi_consume_skb(skb, napi_budget); } while (!last_wqe); + if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) { + if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, + &sq->state)) { + mlx5e_dump_error_cqe(sq, + (struct mlx5_err_cqe *)cqe); + mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs); + queue_work(cq->channel->priv->wq, + &sq->recover_work); + } + stats->cqe_err++; + } + } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); stats->cqes += i; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index e4ec0e03c289..4c61d25d2e88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -850,6 +850,7 @@ void mlx5_fpga_ipsec_delete_sa_ctx(void *context) mutex_lock(&fpga_xfrm->lock); if (!--fpga_xfrm->num_rules) { mlx5_fpga_ipsec_release_sa_ctx(fpga_xfrm->sa_ctx); + kfree(fpga_xfrm->sa_ctx); fpga_xfrm->sa_ctx = NULL; } mutex_unlock(&fpga_xfrm->lock); @@ -1478,7 +1479,7 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, if (!memcmp(&xfrm->attrs, attrs, sizeof(xfrm->attrs))) return 0; - if (!mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) { + if (mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) { mlx5_core_warn(mdev, "Tried to create an esp with unsupported attrs\n"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c7a16ae05fa8..9dc24241dc91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1582,16 +1582,16 @@ struct match_list_head { struct match_list first; }; -static void free_match_list(struct match_list_head *head) +static void free_match_list(struct match_list_head *head, bool ft_locked) { if (!list_empty(&head->list)) { struct match_list *iter, *match_tmp; list_del(&head->first.list); - tree_put_node(&head->first.g->node, false); + tree_put_node(&head->first.g->node, ft_locked); list_for_each_entry_safe(iter, match_tmp, &head->list, list) { - tree_put_node(&iter->g->node, false); + tree_put_node(&iter->g->node, ft_locked); list_del(&iter->list); kfree(iter); } @@ -1600,7 +1600,8 @@ static void free_match_list(struct match_list_head *head) static int build_match_list(struct match_list_head *match_head, struct mlx5_flow_table *ft, - const struct mlx5_flow_spec *spec) + const struct mlx5_flow_spec *spec, + bool ft_locked) { struct rhlist_head *tmp, *list; struct mlx5_flow_group *g; @@ -1625,7 +1626,7 @@ static int build_match_list(struct match_list_head *match_head, curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { - free_match_list(match_head); + free_match_list(match_head, ft_locked); err = -ENOMEM; goto out; } @@ -1805,7 +1806,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, version = atomic_read(&ft->node.version); /* Collect all fgs which has a matching match_criteria */ - err = build_match_list(&match_head, ft, spec); + err = build_match_list(&match_head, ft, spec, take_write); if (err) { if (take_write) up_write_ref_node(&ft->node, false); @@ -1819,7 +1820,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest, dest_num, version); - free_match_list(&match_head); + free_match_list(&match_head, take_write); if (!IS_ERR(rule) || (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) { if (take_write) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index d89ff1d09119..909a7f284614 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -242,7 +242,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, tls)) { + if (MLX5_CAP_GEN(dev, tls_tx)) { err = mlx5_core_get_caps(dev, MLX5_CAP_TLS); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 9bf8da5f6daf..3fe878d7c94c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -573,6 +573,7 @@ static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon) static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon) { + enum mlxsw_reg_mgpir_device_type device_type; int index, max_index, sensor_index; char mgpir_pl[MLXSW_REG_MGPIR_LEN]; char mtmp_pl[MLXSW_REG_MTMP_LEN]; @@ -584,8 +585,9 @@ static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon) if (err) return err; - mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, NULL, NULL, NULL); - if (!gbox_num) + mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, &device_type, NULL, NULL); + if (device_type != MLXSW_REG_MGPIR_DEVICE_TYPE_GEARBOX_DIE || + !gbox_num) return 0; index = mlxsw_hwmon->module_sensor_max; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index c721b171bd8d..ce0a6837daa3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -895,8 +895,10 @@ static int mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core, struct mlxsw_thermal *thermal) { + enum mlxsw_reg_mgpir_device_type device_type; struct mlxsw_thermal_module *gearbox_tz; char mgpir_pl[MLXSW_REG_MGPIR_LEN]; + u8 gbox_num; int i; int err; @@ -908,11 +910,13 @@ mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core, if (err) return err; - mlxsw_reg_mgpir_unpack(mgpir_pl, &thermal->tz_gearbox_num, NULL, NULL, + mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, &device_type, NULL, NULL); - if (!thermal->tz_gearbox_num) + if (device_type != MLXSW_REG_MGPIR_DEVICE_TYPE_GEARBOX_DIE || + !gbox_num) return 0; + thermal->tz_gearbox_num = gbox_num; thermal->tz_gearbox_arr = kcalloc(thermal->tz_gearbox_num, sizeof(*thermal->tz_gearbox_arr), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 49933818c6f5..2dc0978428e6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -215,7 +215,7 @@ mlxsw_sp_dpipe_table_erif_entries_dump(void *priv, bool counters_enabled, start_again: err = devlink_dpipe_entry_ctx_prepare(dump_ctx); if (err) - return err; + goto err_ctx_prepare; j = 0; for (; i < rif_count; i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); @@ -247,6 +247,7 @@ mlxsw_sp_dpipe_table_erif_entries_dump(void *priv, bool counters_enabled, return 0; err_entry_append: err_entry_get: +err_ctx_prepare: rtnl_unlock(); devlink_dpipe_entry_clear(&entry); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index ce707723f8cf..4a77b511ead2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -4844,6 +4844,23 @@ mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, fib_node->fib_entry = NULL; } +static bool mlxsw_sp_fib4_allow_replace(struct mlxsw_sp_fib4_entry *fib4_entry) +{ + struct mlxsw_sp_fib_node *fib_node = fib4_entry->common.fib_node; + struct mlxsw_sp_fib4_entry *fib4_replaced; + + if (!fib_node->fib_entry) + return true; + + fib4_replaced = container_of(fib_node->fib_entry, + struct mlxsw_sp_fib4_entry, common); + if (fib4_entry->tb_id == RT_TABLE_MAIN && + fib4_replaced->tb_id == RT_TABLE_LOCAL) + return false; + + return true; +} + static int mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info) @@ -4872,6 +4889,12 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, goto err_fib4_entry_create; } + if (!mlxsw_sp_fib4_allow_replace(fib4_entry)) { + mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); + return 0; + } + replaced = fib_node->fib_entry; err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib4_entry->common); if (err) { @@ -4908,7 +4931,7 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, return; fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info); - if (WARN_ON(!fib4_entry)) + if (!fib4_entry) return; fib_node = fib4_entry->common.fib_node; @@ -4970,6 +4993,9 @@ static void mlxsw_sp_rt6_release(struct fib6_info *rt) static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) { + struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh; + + fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; mlxsw_sp_rt6_release(mlxsw_sp_rt6->rt); kfree(mlxsw_sp_rt6); } @@ -5408,6 +5434,27 @@ mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp, return NULL; } +static bool mlxsw_sp_fib6_allow_replace(struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; + struct mlxsw_sp_fib6_entry *fib6_replaced; + struct fib6_info *rt, *rt_replaced; + + if (!fib_node->fib_entry) + return true; + + fib6_replaced = container_of(fib_node->fib_entry, + struct mlxsw_sp_fib6_entry, + common); + rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + rt_replaced = mlxsw_sp_fib6_entry_rt(fib6_replaced); + if (rt->fib6_table->tb6_id == RT_TABLE_MAIN && + rt_replaced->fib6_table->tb6_id == RT_TABLE_LOCAL) + return false; + + return true; +} + static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, struct fib6_info **rt_arr, unsigned int nrt6) @@ -5442,6 +5489,12 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, goto err_fib6_entry_create; } + if (!mlxsw_sp_fib6_allow_replace(fib6_entry)) { + mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); + return 0; + } + replaced = fib_node->fib_entry; err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib6_entry->common); if (err) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c index 0dacf2c18c09..3e613058e225 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c @@ -44,8 +44,8 @@ /* Add/subtract the Adjustment_Value when making a Drift adjustment */ #define QED_DRIFT_CNTR_DIRECTION_SHIFT 31 #define QED_TIMESTAMP_MASK BIT(16) -/* Param mask for Hardware to detect/timestamp the unicast PTP packets */ -#define QED_PTP_UCAST_PARAM_MASK 0xF +/* Param mask for Hardware to detect/timestamp the L2/L4 unicast PTP packets */ +#define QED_PTP_UCAST_PARAM_MASK 0x70F static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn) { diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index aaa316be6183..a2168a14794c 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2477,15 +2477,18 @@ static void rtl_hw_jumbo_enable(struct rtl8169_private *tp) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_12: case RTL_GIGA_MAC_VER_17: + pcie_set_readrq(tp->pci_dev, 512); r8168b_1_hw_jumbo_enable(tp); break; case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26: + pcie_set_readrq(tp->pci_dev, 512); r8168c_hw_jumbo_enable(tp); break; case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28: r8168dp_hw_jumbo_enable(tp); break; case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33: + pcie_set_readrq(tp->pci_dev, 512); r8168e_hw_jumbo_enable(tp); break; default: @@ -2515,6 +2518,9 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) break; } rtl_lock_config_regs(tp); + + if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii) + pcie_set_readrq(tp->pci_dev, 4096); } static void rtl_jumbo_config(struct rtl8169_private *tp, int mtu) diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index e61eb891c0f7..db6b2988e632 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -823,7 +823,6 @@ static int ioc3_close(struct net_device *dev) netif_stop_queue(dev); ioc3_stop(ip); - free_irq(dev->irq, dev); ioc3_free_rx_bufs(ip); ioc3_clean_tx_ring(ip); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 7ec895407d23..e0a5fe83d8e0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -413,6 +413,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos) dll_lock = rgmii_readl(ethqos, SDC4_STATUS); if (dll_lock & SDC4_STATUS_DLL_LOCK) break; + retry--; } while (retry > 0); if (!retry) dev_err(ðqos->pdev->dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f0c0ea616032..dc09d2131e40 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -420,7 +420,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw, value |= GMAC_PACKET_FILTER_PM; /* Set all the bits of the HASH tab */ memset(mc_filter, 0xff, sizeof(mc_filter)); - } else if (!netdev_mc_empty(dev)) { + } else if (!netdev_mc_empty(dev) && (dev->flags & IFF_MULTICAST)) { struct netdev_hw_addr *ha; /* Hash filter for multicast */ @@ -736,11 +736,14 @@ static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash, __le16 perfect_match, bool is_double) { void __iomem *ioaddr = hw->pcsr; + u32 value; writel(hash, ioaddr + GMAC_VLAN_HASH_TABLE); + value = readl(ioaddr + GMAC_VLAN_TAG); + if (hash) { - u32 value = GMAC_VLAN_VTHM | GMAC_VLAN_ETV; + value |= GMAC_VLAN_VTHM | GMAC_VLAN_ETV; if (is_double) { value |= GMAC_VLAN_EDVLP; value |= GMAC_VLAN_ESVL; @@ -759,8 +762,6 @@ static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash, writel(value | perfect_match, ioaddr + GMAC_VLAN_TAG); } else { - u32 value = readl(ioaddr + GMAC_VLAN_TAG); - value &= ~(GMAC_VLAN_VTHM | GMAC_VLAN_ETV); value &= ~(GMAC_VLAN_EDVLP | GMAC_VLAN_ESVL); value &= ~GMAC_VLAN_DOVLTC; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 2af3ac5409b7..67b754a56288 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -458,7 +458,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw, for (i = 0; i < XGMAC_MAX_HASH_TABLE; i++) writel(~0x0, ioaddr + XGMAC_HASH_TABLE(i)); - } else if (!netdev_mc_empty(dev)) { + } else if (!netdev_mc_empty(dev) && (dev->flags & IFF_MULTICAST)) { struct netdev_hw_addr *ha; value |= XGMAC_FILTER_HMC; @@ -569,7 +569,9 @@ static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash, writel(value, ioaddr + XGMAC_PACKET_FILTER); - value = XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV; + value = readl(ioaddr + XGMAC_VLAN_TAG); + + value |= XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV; if (is_double) { value |= XGMAC_VLAN_EDVLP; value |= XGMAC_VLAN_ESVL; @@ -584,7 +586,9 @@ static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash, writel(value, ioaddr + XGMAC_PACKET_FILTER); - value = XGMAC_VLAN_ETV; + value = readl(ioaddr + XGMAC_VLAN_TAG); + + value |= XGMAC_VLAN_ETV; if (is_double) { value |= XGMAC_VLAN_EDVLP; value |= XGMAC_VLAN_ESVL; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 623521052152..fe2c9fa6a71c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -95,7 +95,7 @@ static int stmmac_default_data(struct pci_dev *pdev, plat->bus_id = 1; plat->phy_addr = 0; - plat->interface = PHY_INTERFACE_MODE_GMII; + plat->phy_interface = PHY_INTERFACE_MODE_GMII; plat->dma_cfg->pbl = 32; plat->dma_cfg->pblx8 = true; @@ -217,7 +217,8 @@ static int ehl_sgmii_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_addr = 0; - plat->interface = PHY_INTERFACE_MODE_SGMII; + plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + return ehl_common_data(pdev, plat); } @@ -230,7 +231,8 @@ static int ehl_rgmii_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_addr = 0; - plat->interface = PHY_INTERFACE_MODE_RGMII; + plat->phy_interface = PHY_INTERFACE_MODE_RGMII; + return ehl_common_data(pdev, plat); } @@ -258,7 +260,7 @@ static int tgl_sgmii_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_addr = 0; - plat->interface = PHY_INTERFACE_MODE_SGMII; + plat->phy_interface = PHY_INTERFACE_MODE_SGMII; return tgl_common_data(pdev, plat); } @@ -358,7 +360,7 @@ static int quark_default_data(struct pci_dev *pdev, plat->bus_id = pci_dev_id(pdev); plat->phy_addr = ret; - plat->interface = PHY_INTERFACE_MODE_RMII; + plat->phy_interface = PHY_INTERFACE_MODE_RMII; plat->dma_cfg->pbl = 16; plat->dma_cfg->pblx8 = true; @@ -415,7 +417,7 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, plat->bus_id = 1; plat->phy_addr = -1; - plat->interface = PHY_INTERFACE_MODE_GMII; + plat->phy_interface = PHY_INTERFACE_MODE_GMII; plat->dma_cfg->pbl = 32; plat->dma_cfg->pblx8 = true; diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index 20adfe544294..b86611041db6 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -120,7 +120,7 @@ int netvsc_xdp_set(struct net_device *dev, struct bpf_prog *prog, } if (prog) - bpf_prog_add(prog, nvdev->num_chn); + bpf_prog_add(prog, nvdev->num_chn - 1); for (i = 0; i < nvdev->num_chn; i++) rcu_assign_pointer(nvdev->chan_table[i].bpf_prog, prog); @@ -136,6 +136,7 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog) { struct netdev_bpf xdp; bpf_op_t ndo_bpf; + int ret; ASSERT_RTNL(); @@ -148,10 +149,18 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog) memset(&xdp, 0, sizeof(xdp)); + if (prog) + bpf_prog_inc(prog); + xdp.command = XDP_SETUP_PROG; xdp.prog = prog; - return ndo_bpf(vf_netdev, &xdp); + ret = ndo_bpf(vf_netdev, &xdp); + + if (ret && prog) + bpf_prog_put(prog); + + return ret; } static u32 netvsc_xdp_query(struct netvsc_device *nvdev) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 8fc71bd49894..65e12cb07f45 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1059,9 +1059,12 @@ static int netvsc_attach(struct net_device *ndev, prog = dev_info->bprog; if (prog) { + bpf_prog_inc(prog); ret = netvsc_xdp_set(ndev, prog, NULL, nvdev); - if (ret) + if (ret) { + bpf_prog_put(prog); goto err1; + } } /* In any case device is now ready */ diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 5c5427c840b6..d7706a0346f2 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -934,9 +934,7 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, int nsim_dev_init(void) { nsim_dev_ddir = debugfs_create_dir(DRV_NAME, NULL); - if (IS_ERR(nsim_dev_ddir)) - return PTR_ERR(nsim_dev_ddir); - return 0; + return PTR_ERR_OR_ZERO(nsim_dev_ddir); } void nsim_dev_exit(void) diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 121d9ea0f135..3725e9cd85f4 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -263,6 +263,7 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, } else { node = kzalloc(sizeof(*node), GFP_KERNEL); if (unlikely(!node)) { + list_del(&newnode->peer_list); kfree(newnode); return -ENOMEM; } diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 0fdbd1c45977..bda26405497c 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -569,10 +569,8 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) private_key); list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) { - if (wg_noise_precompute_static_static(peer)) - wg_noise_expire_current_peer_keypairs(peer); - else - wg_peer_remove(peer); + BUG_ON(!wg_noise_precompute_static_static(peer)); + wg_noise_expire_current_peer_keypairs(peer); } wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); up_write(&wg->static_identity.lock); diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c index d71c8db68a8c..919d9d866446 100644 --- a/drivers/net/wireguard/noise.c +++ b/drivers/net/wireguard/noise.c @@ -46,17 +46,21 @@ void __init wg_noise_init(void) /* Must hold peer->handshake.static_identity->lock */ bool wg_noise_precompute_static_static(struct wg_peer *peer) { - bool ret = true; + bool ret; down_write(&peer->handshake.lock); - if (peer->handshake.static_identity->has_identity) + if (peer->handshake.static_identity->has_identity) { ret = curve25519( peer->handshake.precomputed_static_static, peer->handshake.static_identity->static_private, peer->handshake.remote_static); - else + } else { + u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 }; + + ret = curve25519(empty, empty, peer->handshake.remote_static); memset(peer->handshake.precomputed_static_static, 0, NOISE_PUBLIC_KEY_LEN); + } up_write(&peer->handshake.lock); return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 8878409d2f07..22a32eb10f01 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1897,27 +1897,55 @@ static void iwl_mvm_d3_disconnect_iter(void *data, u8 *mac, ieee80211_resume_disconnect(vif); } -static int iwl_mvm_check_rt_status(struct iwl_mvm *mvm, - struct ieee80211_vif *vif) +static bool iwl_mvm_rt_status(struct iwl_trans *trans, u32 base, u32 *err_id) { - u32 base = mvm->trans->dbg.lmac_error_event_table[0]; struct error_table_start { /* cf. struct iwl_error_event_table */ u32 valid; - u32 error_id; + __le32 err_id; } err_info; - iwl_trans_read_mem_bytes(mvm->trans, base, - &err_info, sizeof(err_info)); + if (!base) + return false; - if (err_info.valid && - err_info.error_id == RF_KILL_INDICATOR_FOR_WOWLAN) { - struct cfg80211_wowlan_wakeup wakeup = { - .rfkill_release = true, - }; - ieee80211_report_wowlan_wakeup(vif, &wakeup, GFP_KERNEL); + iwl_trans_read_mem_bytes(trans, base, + &err_info, sizeof(err_info)); + if (err_info.valid && err_id) + *err_id = le32_to_cpu(err_info.err_id); + + return !!err_info.valid; +} + +static bool iwl_mvm_check_rt_status(struct iwl_mvm *mvm, + struct ieee80211_vif *vif) +{ + u32 err_id; + + /* check for lmac1 error */ + if (iwl_mvm_rt_status(mvm->trans, + mvm->trans->dbg.lmac_error_event_table[0], + &err_id)) { + if (err_id == RF_KILL_INDICATOR_FOR_WOWLAN) { + struct cfg80211_wowlan_wakeup wakeup = { + .rfkill_release = true, + }; + ieee80211_report_wowlan_wakeup(vif, &wakeup, + GFP_KERNEL); + } + return true; } - return err_info.valid; + + /* check if we have lmac2 set and check for error */ + if (iwl_mvm_rt_status(mvm->trans, + mvm->trans->dbg.lmac_error_event_table[1], NULL)) + return true; + + /* check for umac error */ + if (iwl_mvm_rt_status(mvm->trans, + mvm->trans->dbg.umac_error_event_table, NULL)) + return true; + + return false; } static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index f783d6d53b6f..6e1ea921c299 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -8,6 +8,7 @@ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH * Copyright (C) 2018 Intel Corporation * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -30,6 +31,7 @@ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH * Copyright (C) 2018 Intel Corporation * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -528,6 +530,8 @@ void iwl_mvm_ftm_abort(struct iwl_mvm *mvm, struct cfg80211_pmsr_request *req) if (req != mvm->ftm_initiator.req) return; + iwl_mvm_ftm_reset(mvm); + if (iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_RANGE_ABORT_CMD, LOCATION_GROUP, 0), 0, sizeof(cmd), &cmd)) @@ -641,7 +645,6 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) lockdep_assert_held(&mvm->mutex); if (!mvm->ftm_initiator.req) { - IWL_ERR(mvm, "Got FTM response but have no request?\n"); return; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 6717f25c46b1..02df603b6400 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -5,10 +5,9 @@ * * GPL LICENSE SUMMARY * - * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -28,10 +27,9 @@ * * BSD LICENSE * - * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -2037,7 +2035,7 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm, rcu_read_lock(); sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_ctxt_cmd.sta_id]); - if (IS_ERR(sta)) { + if (IS_ERR_OR_NULL(sta)) { rcu_read_unlock(); WARN(1, "Can't find STA to configure HE\n"); return; @@ -3293,7 +3291,7 @@ static void iwl_mvm_mac_mgd_prepare_tx(struct ieee80211_hw *hw, if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) iwl_mvm_schedule_session_protection(mvm, vif, 900, - min_duration); + min_duration, false); else iwl_mvm_protect_session(mvm, vif, duration, min_duration, 500, false); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 7b35f416404c..64ef3f3ba23b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -3320,6 +3320,10 @@ static int iwl_mvm_send_sta_igtk(struct iwl_mvm *mvm, igtk_cmd.sta_id = cpu_to_le32(sta_id); if (remove_key) { + /* This is a valid situation for IGTK */ + if (sta_id == IWL_MVM_INVALID_STA) + return 0; + igtk_cmd.ctrl_flags |= cpu_to_le32(STA_KEY_NOT_VALID); } else { struct ieee80211_key_seq seq; @@ -3574,9 +3578,9 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm, IWL_DEBUG_WEP(mvm, "mvm remove dynamic key: idx=%d sta=%d\n", keyconf->keyidx, sta_id); - if (mvm_sta && (keyconf->cipher == WLAN_CIPHER_SUITE_AES_CMAC || - keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 || - keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256)) + if (keyconf->cipher == WLAN_CIPHER_SUITE_AES_CMAC || + keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 || + keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256) return iwl_mvm_send_sta_igtk(mvm, keyconf, sta_id, true); if (!__test_and_clear_bit(keyconf->hw_key_idx, mvm->fw_key_table)) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c index 1851719e9f4b..d781777b6b96 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c @@ -205,9 +205,15 @@ void iwl_mvm_mac_mgd_protect_tdls_discover(struct ieee80211_hw *hw, struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); u32 duration = 2 * vif->bss_conf.dtim_period * vif->bss_conf.beacon_int; - mutex_lock(&mvm->mutex); /* Protect the session to hear the TDLS setup response on the channel */ - iwl_mvm_protect_session(mvm, vif, duration, duration, 100, true); + mutex_lock(&mvm->mutex); + if (fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) + iwl_mvm_schedule_session_protection(mvm, vif, duration, + duration, true); + else + iwl_mvm_protect_session(mvm, vif, duration, + duration, 100, true); mutex_unlock(&mvm->mutex); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 51b138673ddb..c0b420fe5e48 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -1056,13 +1056,42 @@ int iwl_mvm_schedule_csa_period(struct iwl_mvm *mvm, return iwl_mvm_time_event_send_add(mvm, vif, te_data, &time_cmd); } +static bool iwl_mvm_session_prot_notif(struct iwl_notif_wait_data *notif_wait, + struct iwl_rx_packet *pkt, void *data) +{ + struct iwl_mvm *mvm = + container_of(notif_wait, struct iwl_mvm, notif_wait); + struct iwl_mvm_session_prot_notif *resp; + int resp_len = iwl_rx_packet_payload_len(pkt); + + if (WARN_ON(pkt->hdr.cmd != SESSION_PROTECTION_NOTIF || + pkt->hdr.group_id != MAC_CONF_GROUP)) + return true; + + if (WARN_ON_ONCE(resp_len != sizeof(*resp))) { + IWL_ERR(mvm, "Invalid SESSION_PROTECTION_NOTIF response\n"); + return true; + } + + resp = (void *)pkt->data; + + if (!resp->status) + IWL_ERR(mvm, + "TIME_EVENT_NOTIFICATION received but not executed\n"); + + return true; +} + void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, struct ieee80211_vif *vif, - u32 duration, u32 min_duration) + u32 duration, u32 min_duration, + bool wait_for_notif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_time_event_data *te_data = &mvmvif->time_event_data; - + const u16 notif[] = { iwl_cmd_id(SESSION_PROTECTION_NOTIF, + MAC_CONF_GROUP, 0) }; + struct iwl_notification_wait wait_notif; struct iwl_mvm_session_prot_cmd cmd = { .id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, @@ -1071,7 +1100,6 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, .conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC), .duration_tu = cpu_to_le32(MSEC_TO_TU(duration)), }; - int ret; lockdep_assert_held(&mvm->mutex); @@ -1092,14 +1120,35 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, IWL_DEBUG_TE(mvm, "Add new session protection, duration %d TU\n", le32_to_cpu(cmd.duration_tu)); - ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, - MAC_CONF_GROUP, 0), - 0, sizeof(cmd), &cmd); - if (ret) { + if (!wait_for_notif) { + if (iwl_mvm_send_cmd_pdu(mvm, + iwl_cmd_id(SESSION_PROTECTION_CMD, + MAC_CONF_GROUP, 0), + 0, sizeof(cmd), &cmd)) { + IWL_ERR(mvm, + "Couldn't send the SESSION_PROTECTION_CMD\n"); + spin_lock_bh(&mvm->time_event_lock); + iwl_mvm_te_clear_data(mvm, te_data); + spin_unlock_bh(&mvm->time_event_lock); + } + + return; + } + + iwl_init_notification_wait(&mvm->notif_wait, &wait_notif, + notif, ARRAY_SIZE(notif), + iwl_mvm_session_prot_notif, NULL); + + if (iwl_mvm_send_cmd_pdu(mvm, + iwl_cmd_id(SESSION_PROTECTION_CMD, + MAC_CONF_GROUP, 0), + 0, sizeof(cmd), &cmd)) { IWL_ERR(mvm, - "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret); - spin_lock_bh(&mvm->time_event_lock); - iwl_mvm_te_clear_data(mvm, te_data); - spin_unlock_bh(&mvm->time_event_lock); + "Couldn't send the SESSION_PROTECTION_CMD\n"); + iwl_remove_notification(&mvm->notif_wait, &wait_notif); + } else if (iwl_wait_notification(&mvm->notif_wait, &wait_notif, + TU_TO_JIFFIES(100))) { + IWL_ERR(mvm, + "Failed to protect session until session protection\n"); } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.h b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.h index df6832b79666..3186d7e40567 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.h @@ -250,10 +250,12 @@ iwl_mvm_te_scheduled(struct iwl_mvm_time_event_data *te_data) * @mvm: the mvm component * @vif: the virtual interface for which the protection issued * @duration: the duration of the protection + * @wait_for_notif: if true, will block until the start of the protection */ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, struct ieee80211_vif *vif, - u32 duration, u32 min_duration); + u32 duration, u32 min_duration, + bool wait_for_notif); /** * iwl_mvm_rx_session_protect_notif - handles %SESSION_PROTECTION_NOTIF diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c index b5a16f00bada..418e59b7c671 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c @@ -8,7 +8,7 @@ * Copyright(c) 2013 - 2014, 2019 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright(c) 2019 Intel Corporation + * Copyright(c) 2019 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2012 - 2014, 2019 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright(c) 2019 Intel Corporation + * Copyright(c) 2019 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -234,7 +234,7 @@ static int iwl_mvm_get_temp_cmd(struct iwl_mvm *mvm) .flags = cpu_to_le32(DTS_TRIGGER_CMD_FLAGS_TEMP), }; struct iwl_ext_dts_measurement_cmd extcmd = { - .control_mode = cpu_to_le32(DTS_AUTOMATIC), + .control_mode = cpu_to_le32(DTS_DIRECT_WITHOUT_MEASURE), }; u32 cmdid; @@ -734,7 +734,8 @@ static struct thermal_zone_device_ops tzone_ops = { static void iwl_mvm_thermal_zone_register(struct iwl_mvm *mvm) { int i; - char name[] = "iwlwifi"; + char name[16]; + static atomic_t counter = ATOMIC_INIT(0); if (!iwl_mvm_is_tt_in_fw(mvm)) { mvm->tz_device.tzone = NULL; @@ -744,6 +745,7 @@ static void iwl_mvm_thermal_zone_register(struct iwl_mvm *mvm) BUILD_BUG_ON(ARRAY_SIZE(name) >= THERMAL_NAME_LENGTH); + sprintf(name, "iwlwifi_%u", atomic_inc_return(&counter) & 0xFF); mvm->tz_device.tzone = thermal_zone_device_register(name, IWL_MAX_DTS_TRIPS, IWL_WRITABLE_TRIPS_MSK, diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c index c9401c121a14..4e3de684928b 100644 --- a/drivers/net/wireless/marvell/libertas/cfg.c +++ b/drivers/net/wireless/marvell/libertas/cfg.c @@ -1785,6 +1785,8 @@ static int lbs_ibss_join_existing(struct lbs_private *priv, rates_max = rates_eid[1]; if (rates_max > MAX_RATES) { lbs_deb_join("invalid rates"); + rcu_read_unlock(); + ret = -EINVAL; goto out; } rates = cmd.bss.rates; diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c index 98f942b797f7..a7968a84aaf8 100644 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@ -2884,6 +2884,13 @@ mwifiex_cmd_append_vsie_tlv(struct mwifiex_private *priv, vs_param_set->header.len = cpu_to_le16((((u16) priv->vs_ie[id].ie[1]) & 0x00FF) + 2); + if (le16_to_cpu(vs_param_set->header.len) > + MWIFIEX_MAX_VSIE_LEN) { + mwifiex_dbg(priv->adapter, ERROR, + "Invalid param length!\n"); + break; + } + memcpy(vs_param_set->ie, priv->vs_ie[id].ie, le16_to_cpu(vs_param_set->header.len)); *buffer += le16_to_cpu(vs_param_set->header.len) + diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index 6dd835f1efc2..fbfa0b15d0c8 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -232,6 +232,7 @@ static int mwifiex_process_country_ie(struct mwifiex_private *priv, if (country_ie_len > (IEEE80211_COUNTRY_STRING_LEN + MWIFIEX_MAX_TRIPLET_802_11D)) { + rcu_read_unlock(); mwifiex_dbg(priv->adapter, ERROR, "11D: country_ie_len overflow!, deauth AP\n"); return -EINVAL; diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c index 41f0231376c0..132f9e8ed68c 100644 --- a/drivers/net/wireless/marvell/mwifiex/wmm.c +++ b/drivers/net/wireless/marvell/mwifiex/wmm.c @@ -970,6 +970,10 @@ int mwifiex_ret_wmm_get_status(struct mwifiex_private *priv, "WMM Parameter Set Count: %d\n", wmm_param_ie->qos_info_bitmap & mask); + if (wmm_param_ie->vend_hdr.len + 2 > + sizeof(struct ieee_types_wmm_parameter)) + break; + memcpy((u8 *) &priv->curr_bss_params.bss_descriptor. wmm_ie, wmm_param_ie, wmm_param_ie->vend_hdr.len + 2); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c index eccad4987ac8..17e277bf39e0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c @@ -92,8 +92,9 @@ static int mt7615_check_eeprom(struct mt76_dev *dev) static void mt7615_eeprom_parse_hw_cap(struct mt7615_dev *dev) { - u8 val, *eeprom = dev->mt76.eeprom.data; + u8 *eeprom = dev->mt76.eeprom.data; u8 tx_mask, rx_mask, max_nss; + u32 val; val = FIELD_GET(MT_EE_NIC_WIFI_CONF_BAND_SEL, eeprom[MT_EE_WIFI_CONF]); diff --git a/drivers/net/wireless/realtek/rtw88/wow.c b/drivers/net/wireless/realtek/rtw88/wow.c index af5c27e1bb07..4820dca958dd 100644 --- a/drivers/net/wireless/realtek/rtw88/wow.c +++ b/drivers/net/wireless/realtek/rtw88/wow.c @@ -281,27 +281,26 @@ static void rtw_wow_rx_dma_start(struct rtw_dev *rtwdev) rtw_write32_clr(rtwdev, REG_RXPKT_NUM, BIT_RW_RELEASE); } -static bool rtw_wow_check_fw_status(struct rtw_dev *rtwdev, bool wow_enable) +static int rtw_wow_check_fw_status(struct rtw_dev *rtwdev, bool wow_enable) { - bool ret; - /* wait 100ms for wow firmware to finish work */ msleep(100); if (wow_enable) { - if (!rtw_read8(rtwdev, REG_WOWLAN_WAKE_REASON)) - ret = 0; + if (rtw_read8(rtwdev, REG_WOWLAN_WAKE_REASON)) + goto wow_fail; } else { - if (rtw_read32_mask(rtwdev, REG_FE1IMR, BIT_FS_RXDONE) == 0 && - rtw_read32_mask(rtwdev, REG_RXPKT_NUM, BIT_RW_RELEASE) == 0) - ret = 0; + if (rtw_read32_mask(rtwdev, REG_FE1IMR, BIT_FS_RXDONE) || + rtw_read32_mask(rtwdev, REG_RXPKT_NUM, BIT_RW_RELEASE)) + goto wow_fail; } - if (ret) - rtw_err(rtwdev, "failed to check wow status %s\n", - wow_enable ? "enabled" : "disabled"); + return 0; - return ret; +wow_fail: + rtw_err(rtwdev, "failed to check wow status %s\n", + wow_enable ? "enabled" : "disabled"); + return -EBUSY; } static void rtw_wow_fw_security_type_iter(struct ieee80211_hw *hw, diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index acb82181f70f..fd4b5ac6ac5b 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -7604,7 +7604,6 @@ megasas_resume(struct pci_dev *pdev) int rval; struct Scsi_Host *host; struct megasas_instance *instance; - int irq_flags = PCI_IRQ_LEGACY; u32 status_reg; instance = pci_get_drvdata(pdev); @@ -7673,16 +7672,15 @@ megasas_resume(struct pci_dev *pdev) atomic_set(&instance->ldio_outstanding, 0); /* Now re-enable MSI-X */ - if (instance->msix_vectors) { - irq_flags = PCI_IRQ_MSIX; - if (instance->smp_affinity_enable) - irq_flags |= PCI_IRQ_AFFINITY; + if (instance->msix_vectors) + megasas_alloc_irq_vectors(instance); + + if (!instance->msix_vectors) { + rval = pci_alloc_irq_vectors(instance->pdev, 1, 1, + PCI_IRQ_LEGACY); + if (rval < 0) + goto fail_reenable_msix; } - rval = pci_alloc_irq_vectors(instance->pdev, 1, - instance->msix_vectors ? - instance->msix_vectors : 1, irq_flags); - if (rval < 0) - goto fail_reenable_msix; megasas_setup_reply_map(instance); diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 98dcdbd146d5..d1d95f1a2c6a 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2377,7 +2377,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) ts->buf_valid_size = sizeof(*resp); } else PM8001_IO_DBG(pm8001_ha, - pm8001_printk("response to large\n")); + pm8001_printk("response too large\n")); } if (pm8001_dev) pm8001_dev->running_req--; diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index e5500bba06ca..88a56e8480f7 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -2519,12 +2519,6 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked) /* Driver Debug Functions. */ /****************************************************************************/ -static inline int -ql_mask_match(uint level) -{ - return (level & ql2xextended_error_logging) == level; -} - /* * This function is for formatting and logging debug information. * It is to be used when vha is available. It formats the message diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h index bb01b680ce9f..433e95502808 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.h +++ b/drivers/scsi/qla2xxx/qla_dbg.h @@ -374,3 +374,9 @@ extern int qla24xx_dump_ram(struct qla_hw_data *, uint32_t, uint32_t *, extern void qla24xx_pause_risc(struct device_reg_24xx __iomem *, struct qla_hw_data *); extern int qla24xx_soft_reset(struct qla_hw_data *); + +static inline int +ql_mask_match(uint level) +{ + return (level & ql2xextended_error_logging) == level; +} diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index e7bad0bfffda..e40705d38cea 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1939,6 +1939,18 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, inbuf = (uint32_t *)&sts->nvme_ersp_data; outbuf = (uint32_t *)fd->rspaddr; iocb->u.nvme.rsp_pyld_len = le16_to_cpu(sts->nvme_rsp_pyld_len); + if (unlikely(iocb->u.nvme.rsp_pyld_len > + sizeof(struct nvme_fc_ersp_iu))) { + if (ql_mask_match(ql_dbg_io)) { + WARN_ONCE(1, "Unexpected response payload length %u.\n", + iocb->u.nvme.rsp_pyld_len); + ql_log(ql_log_warn, fcport->vha, 0x5100, + "Unexpected response payload length %u.\n", + iocb->u.nvme.rsp_pyld_len); + } + iocb->u.nvme.rsp_pyld_len = + sizeof(struct nvme_fc_ersp_iu); + } iter = iocb->u.nvme.rsp_pyld_len >> 2; for (; iter; iter--) *outbuf++ = swab32(*inbuf++); diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index dde2eb02f76f..cfe380348bf0 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -546,7 +546,7 @@ static inline bool ufs_is_valid_unit_desc_lun(struct ufs_dev_info *dev_info, u8 lun) { if (!dev_info || !dev_info->max_lu_supported) { - pr_err("Max General LU supported by UFS isn't initilized\n"); + pr_err("Max General LU supported by UFS isn't initialized\n"); return false; } diff --git a/drivers/tty/serial/8250/8250_ioc3.c b/drivers/tty/serial/8250/8250_ioc3.c index 4c405f1b9c67..d5a39e105a76 100644 --- a/drivers/tty/serial/8250/8250_ioc3.c +++ b/drivers/tty/serial/8250/8250_ioc3.c @@ -47,7 +47,7 @@ static int serial8250_ioc3_probe(struct platform_device *pdev) if (!data) return -ENOMEM; - membase = devm_ioremap_nocache(&pdev->dev, r->start, resource_size(r)); + membase = devm_ioremap(&pdev->dev, r->start, resource_size(r)); if (!membase) return -ENOMEM; diff --git a/drivers/tty/vt/Makefile b/drivers/tty/vt/Makefile index 329ca336b8ee..fe30ce512819 100644 --- a/drivers/tty/vt/Makefile +++ b/drivers/tty/vt/Makefile @@ -12,7 +12,7 @@ obj-$(CONFIG_HW_CONSOLE) += vt.o defkeymap.o # Files generated that shall be removed upon make clean clean-files := consolemap_deftbl.c defkeymap.c -hostprogs-y += conmakehash +hostprogs += conmakehash quiet_cmd_conmk = CONMK $@ cmd_conmk = $(obj)/conmakehash $< > $@ diff --git a/drivers/video/logo/Makefile b/drivers/video/logo/Makefile index bcda657493a4..895c60b8402e 100644 --- a/drivers/video/logo/Makefile +++ b/drivers/video/logo/Makefile @@ -18,7 +18,7 @@ obj-$(CONFIG_SPU_BASE) += logo_spe_clut224.o # How to generate logo's -hostprogs-y := pnmtologo +hostprogs := pnmtologo # Create commands like "pnmtologo -t mono -n logo_mac_mono -o ..." quiet_cmd_logo = LOGO $@ diff --git a/drivers/zorro/Makefile b/drivers/zorro/Makefile index b360ac4ea846..91ba82e633e7 100644 --- a/drivers/zorro/Makefile +++ b/drivers/zorro/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_ZORRO) += zorro.o zorro-driver.o zorro-sysfs.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_ZORRO_NAMES) += names.o -hostprogs-y := gen-devlist +hostprogs := gen-devlist # Files generated that shall be removed upon make clean clean-files := devlist.h diff --git a/fs/Kconfig b/fs/Kconfig index 7b623e9fc1b0..708ba336e689 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -40,6 +40,7 @@ source "fs/ocfs2/Kconfig" source "fs/btrfs/Kconfig" source "fs/nilfs2/Kconfig" source "fs/f2fs/Kconfig" +source "fs/zonefs/Kconfig" config FS_DAX bool "Direct Access (DAX) support" @@ -264,6 +265,7 @@ source "fs/pstore/Kconfig" source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/erofs/Kconfig" +source "fs/vboxsf/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Makefile b/fs/Makefile index 98be354fdb61..505e51166973 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -133,3 +133,5 @@ obj-$(CONFIG_CEPH_FS) += ceph/ obj-$(CONFIG_PSTORE) += pstore/ obj-$(CONFIG_EFIVAR_FS) += efivarfs/ obj-$(CONFIG_EROFS_FS) += erofs/ +obj-$(CONFIG_VBOXSF_FS) += vboxsf/ +obj-$(CONFIG_ZONEFS_FS) += zonefs/ diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index 0f0dc1c1fe41..153d5c842a9b 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -65,6 +65,11 @@ struct smb3_key_debug_info { __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE]; } __packed; +struct smb3_notify { + __u32 completion_filter; + bool watch_tree; +} __packed; + #define CIFS_IOCTL_MAGIC 0xCF #define CIFS_IOC_COPYCHUNK_FILE _IOW(CIFS_IOCTL_MAGIC, 3, int) #define CIFS_IOC_SET_INTEGRITY _IO(CIFS_IOCTL_MAGIC, 4) @@ -72,3 +77,4 @@ struct smb3_key_debug_info { #define CIFS_ENUMERATE_SNAPSHOTS _IOR(CIFS_IOCTL_MAGIC, 6, struct smb_snapshot_array) #define CIFS_QUERY_INFO _IOWR(CIFS_IOCTL_MAGIC, 7, struct smb_query_info) #define CIFS_DUMP_KEY _IOWR(CIFS_IOCTL_MAGIC, 8, struct smb3_key_debug_info) +#define CIFS_IOC_NOTIFY _IOW(CIFS_IOCTL_MAGIC, 9, struct smb3_notify) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index fb41e51dd574..440828afcdde 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1084,7 +1084,7 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, struct cifs_ntsd *pntsd = NULL; int oplock = 0; unsigned int xid; - int rc, create_options = 0; + int rc; struct cifs_tcon *tcon; struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); struct cifs_fid fid; @@ -1096,13 +1096,10 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, tcon = tlink_tcon(tlink); xid = get_xid(); - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = READ_CONTROL; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; @@ -1147,7 +1144,7 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, { int oplock = 0; unsigned int xid; - int rc, access_flags, create_options = 0; + int rc, access_flags; struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); @@ -1160,9 +1157,6 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, tcon = tlink_tcon(tlink); xid = get_xid(); - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP) access_flags = WRITE_OWNER; else @@ -1171,7 +1165,7 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = access_flags; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5492b9860baa..febab27cd838 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -275,7 +275,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_ffree = 0; /* unlimited */ if (server->ops->queryfs) - rc = server->ops->queryfs(xid, tcon, buf); + rc = server->ops->queryfs(xid, tcon, cifs_sb, buf); free_xid(xid); return 0; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 239338d57086..de82cfa44b1a 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -298,7 +298,8 @@ struct smb_version_operations { const char *, struct dfs_info3_param **, unsigned int *, const struct nls_table *, int); /* informational QFS call */ - void (*qfs_tcon)(const unsigned int, struct cifs_tcon *); + void (*qfs_tcon)(const unsigned int, struct cifs_tcon *, + struct cifs_sb_info *); /* check if a path is accessible or not */ int (*is_path_accessible)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const char *); @@ -409,7 +410,7 @@ struct smb_version_operations { struct cifsInodeInfo *); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, - struct kstatfs *); + struct cifs_sb_info *, struct kstatfs *); /* send mandatory brlock to the server */ int (*mand_lock)(const unsigned int, struct cifsFileInfo *, __u64, __u64, __u32, int, int, bool); @@ -430,6 +431,8 @@ struct smb_version_operations { struct cifsFileInfo *src_file); int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *src_file, void __user *); + int (*notify)(const unsigned int xid, struct file *pfile, + void __user *pbuf); int (*query_mf_symlink)(unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const unsigned char *, char *, unsigned int *); @@ -490,6 +493,7 @@ struct smb_version_operations { /* ioctl passthrough for query_info */ int (*ioctl_query_info)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, __le16 *path, int is_dir, unsigned long p); /* make unix special files (block, char, fifo, socket) */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 948bf3474db1..89eaaf46d1ca 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -612,4 +612,12 @@ static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses, } #endif +static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options) +{ + if (cifs_sb && (backup_cred(cifs_sb))) + return options | CREATE_OPEN_BACKUP_INTENT; + else + return options; +} + #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a481296f417f..3c89569e7210 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -260,7 +260,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) if (server->tcpStatus != CifsNeedReconnect) break; - if (--retries) + if (retries && --retries) continue; /* diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0aa3623ae0e1..a941ac7a659d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4365,7 +4365,7 @@ static int mount_get_conns(struct smb_vol *vol, struct cifs_sb_info *cifs_sb, /* do not care if a following call succeed - informational */ if (!tcon->pipe && server->ops->qfs_tcon) { - server->ops->qfs_tcon(*xid, tcon); + server->ops->qfs_tcon(*xid, tcon, cifs_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) { if (tcon->fsDevInfo.DeviceCharacteristics & cpu_to_le32(FILE_READ_ONLY_DEVICE)) diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f3b79012ff29..0ef099442f20 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -355,13 +355,10 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = desired_access; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, create_options); oparms.disposition = disposition; oparms.path = full_path; oparms.fid = fid; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index a4e8f7d445ac..bc9516ab4b34 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -222,9 +222,6 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, if (!buf) return -ENOMEM; - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (f_flags & O_SYNC) create_options |= CREATE_WRITE_THROUGH; @@ -235,7 +232,7 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = desired_access; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, create_options); oparms.disposition = disposition; oparms.path = full_path; oparms.fid = fid; @@ -752,9 +749,6 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) desired_access = cifs_convert_flags(cfile->f_flags); - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) create_options |= CREATE_WRITE_THROUGH; @@ -768,7 +762,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = desired_access; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, create_options); oparms.disposition = disposition; oparms.path = full_path; oparms.fid = &cfile->fid; @@ -2599,8 +2593,10 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); rc = file_write_and_wait_range(file, start, end); - if (rc) + if (rc) { + trace_cifs_fsync_err(inode->i_ino, rc); return rc; + } xid = get_xid(); @@ -2638,8 +2634,10 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); rc = file_write_and_wait_range(file, start, end); - if (rc) + if (rc) { + trace_cifs_fsync_err(file_inode(file)->i_ino, rc); return rc; + } xid = get_xid(); @@ -2672,7 +2670,8 @@ int cifs_flush(struct file *file, fl_owner_t id) rc = filemap_write_and_wait(inode->i_mapping); cifs_dbg(FYI, "Flush inode %p file %p rc %d\n", inode, file, rc); - + if (rc) + trace_cifs_flush_err(inode->i_ino, rc); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 676e96a7a9f0..9ba623b601ec 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -475,9 +475,7 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_READ; - oparms.create_options = CREATE_NOT_DIR; - if (backup_cred(cifs_sb)) - oparms.create_options |= CREATE_OPEN_BACKUP_INTENT; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; @@ -1285,7 +1283,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = DELETE | FILE_WRITE_ATTRIBUTES; - oparms.create_options = CREATE_NOT_DIR; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_OPEN; oparms.path = full_path; oparms.fid = &fid; @@ -1823,7 +1821,7 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, oparms.cifs_sb = cifs_sb; /* open the file to be renamed -- we need DELETE perms */ oparms.desired_access = DELETE; - oparms.create_options = CREATE_NOT_DIR; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_OPEN; oparms.path = from_path; oparms.fid = &fid; diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 1a01e108d75e..4a73e63c4d43 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -65,7 +65,7 @@ static long cifs_ioctl_query_info(unsigned int xid, struct file *filep, if (tcon->ses->server->ops->ioctl_query_info) rc = tcon->ses->server->ops->ioctl_query_info( - xid, tcon, utf16_path, + xid, tcon, cifs_sb, utf16_path, filep->private_data ? 0 : 1, p); else rc = -EOPNOTSUPP; @@ -169,6 +169,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) unsigned int xid; struct cifsFileInfo *pSMBFile = filep->private_data; struct cifs_tcon *tcon; + struct cifs_sb_info *cifs_sb; __u64 ExtAttrBits = 0; __u64 caps; @@ -299,6 +300,21 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) else rc = 0; break; + case CIFS_IOC_NOTIFY: + if (!S_ISDIR(inode->i_mode)) { + /* Notify can only be done on directories */ + rc = -EOPNOTSUPP; + break; + } + cifs_sb = CIFS_SB(inode->i_sb); + tcon = tlink_tcon(cifs_sb_tlink(cifs_sb)); + if (tcon && tcon->ses->server->ops->notify) { + rc = tcon->ses->server->ops->notify(xid, + filep, (void __user *)arg); + cifs_dbg(FYI, "ioctl notify rc %d\n", rc); + } else + rc = -EOPNOTSUPP; + break; default: cifs_dbg(FYI, "unsupported ioctl\n"); break; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index b736acd3917b..852aa00ec729 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -315,7 +315,7 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_READ; - oparms.create_options = CREATE_NOT_DIR; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; @@ -353,15 +353,11 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid fid; struct cifs_open_parms oparms; struct cifs_io_parms io_parms; - int create_options = CREATE_NOT_DIR; - - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_CREATE; oparms.path = path; oparms.fid = &fid; @@ -402,9 +398,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_READ; - oparms.create_options = CREATE_NOT_DIR; - if (backup_cred(cifs_sb)) - oparms.create_options |= CREATE_OPEN_BACKUP_INTENT; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_OPEN; oparms.fid = &fid; oparms.reconnect = false; @@ -457,14 +451,10 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid fid; struct cifs_open_parms oparms; struct cifs_io_parms io_parms; - int create_options = CREATE_NOT_DIR; __le16 *utf16_path; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct kvec iov[2]; - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - cifs_dbg(FYI, "%s: path: %s\n", __func__, path); utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); @@ -474,7 +464,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_CREATE; oparms.fid = &fid; oparms.reconnect = false; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index d17587c2c4ab..ba9dadf3be24 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -196,7 +196,8 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) * may look wrong since the inodes may not have timed out by the time * "ls" does a stat() call on them. */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) || + (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)) fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL && diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index f0795c856d8f..43a88e26d26b 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -101,7 +101,7 @@ int cifs_try_adding_channels(struct cifs_ses *ses) iface_count = ses->iface_count; if (iface_count <= 0) { spin_unlock(&ses->iface_lock); - cifs_dbg(FYI, "no iface list available to open channels\n"); + cifs_dbg(VFS, "no iface list available to open channels\n"); return 0; } ifaces = kmemdup(ses->iface_list, iface_count*sizeof(*ifaces), diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index d70a2bb062df..eb994e313c6a 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -504,7 +504,8 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) } static void -cifs_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) +cifs_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb) { CIFSSMBQFSDeviceInfo(xid, tcon); CIFSSMBQFSAttributeInfo(xid, tcon); @@ -565,7 +566,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = FILE_READ_ATTRIBUTES; - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.disposition = FILE_OPEN; oparms.path = full_path; oparms.fid = &fid; @@ -793,7 +794,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = SYNCHRONIZE | FILE_WRITE_ATTRIBUTES; - oparms.create_options = CREATE_NOT_DIR; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR); oparms.disposition = FILE_OPEN; oparms.path = full_path; oparms.fid = &fid; @@ -872,7 +873,7 @@ cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, static int cifs_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct kstatfs *buf) + struct cifs_sb_info *cifs_sb, struct kstatfs *buf) { int rc = -EOPNOTSUPP; @@ -970,7 +971,8 @@ cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = FILE_READ_ATTRIBUTES; - oparms.create_options = OPEN_REPARSE_POINT; + oparms.create_options = cifs_create_options(cifs_sb, + OPEN_REPARSE_POINT); oparms.disposition = FILE_OPEN; oparms.path = full_path; oparms.fid = &fid; @@ -1029,7 +1031,6 @@ cifs_make_node(unsigned int xid, struct inode *inode, struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct inode *newinode = NULL; int rc = -EPERM; - int create_options = CREATE_NOT_DIR | CREATE_OPTION_SPECIAL; FILE_ALL_INFO *buf = NULL; struct cifs_io_parms io_parms; __u32 oplock = 0; @@ -1090,13 +1091,11 @@ cifs_make_node(unsigned int xid, struct inode *inode, goto out; } - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR | + CREATE_OPTION_SPECIAL); oparms.disposition = FILE_CREATE; oparms.path = full_path; oparms.fid = &fid; diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 5ef5e97a6d13..1cf207564ff9 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -99,9 +99,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = desired_access; oparms.disposition = create_disposition; - oparms.create_options = create_options; - if (backup_cred(cifs_sb)) - oparms.create_options |= CREATE_OPEN_BACKUP_INTENT; + oparms.create_options = cifs_create_options(cifs_sb, create_options); oparms.fid = &fid; oparms.reconnect = false; oparms.mode = mode; @@ -457,7 +455,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, /* If it is a root and its handle is cached then use it */ if (!strlen(full_path) && !no_cached_open) { - rc = open_shroot(xid, tcon, &fid); + rc = open_shroot(xid, tcon, cifs_sb, &fid); if (rc) goto out; @@ -474,9 +472,6 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, goto out; } - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - cifs_get_readable_path(tcon, full_path, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 6787fce26f20..baa825f4cec0 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -655,7 +655,8 @@ smb2_cached_lease_break(struct work_struct *work) /* * Open the directory at the root of a share */ -int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) +int open_shroot(unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, struct cifs_fid *pfid) { struct cifs_ses *ses = tcon->ses; struct TCP_Server_Info *server = ses->server; @@ -702,7 +703,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; oparms.tcon = tcon; - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; oparms.fid = pfid; @@ -818,7 +819,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) } static void -smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) +smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb) { int rc; __le16 srch_path = 0; /* Null - open root of share */ @@ -830,7 +832,7 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -838,7 +840,7 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL); else - rc = open_shroot(xid, tcon, &fid); + rc = open_shroot(xid, tcon, cifs_sb, &fid); if (rc) return; @@ -860,7 +862,8 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) } static void -smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) +smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb) { int rc; __le16 srch_path = 0; /* Null - open root of share */ @@ -871,7 +874,7 @@ smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -906,10 +909,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -1151,10 +1151,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_WRITE_EA; oparms.disposition = FILE_OPEN; - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -1422,6 +1419,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, static int smb2_ioctl_query_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, __le16 *path, int is_dir, unsigned long p) { @@ -1447,6 +1445,7 @@ smb2_ioctl_query_info(const unsigned int xid, struct kvec close_iov[1]; unsigned int size[2]; void *data[2]; + int create_options = is_dir ? CREATE_NOT_FILE : CREATE_NOT_DIR; memset(rqst, 0, sizeof(rqst)); resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; @@ -1477,10 +1476,7 @@ smb2_ioctl_query_info(const unsigned int xid, memset(&oparms, 0, sizeof(oparms)); oparms.tcon = tcon; oparms.disposition = FILE_OPEN; - if (is_dir) - oparms.create_options = CREATE_NOT_FILE; - else - oparms.create_options = CREATE_NOT_DIR; + oparms.create_options = cifs_create_options(cifs_sb, create_options); oparms.fid = &fid; oparms.reconnect = false; @@ -2049,6 +2045,66 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, return rc; } + + +static int +smb3_notify(const unsigned int xid, struct file *pfile, + void __user *ioc_buf) +{ + struct smb3_notify notify; + struct dentry *dentry = pfile->f_path.dentry; + struct inode *inode = file_inode(pfile); + struct cifs_sb_info *cifs_sb; + struct cifs_open_parms oparms; + struct cifs_fid fid; + struct cifs_tcon *tcon; + unsigned char *path = NULL; + __le16 *utf16_path = NULL; + u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + int rc = 0; + + path = build_path_from_dentry(dentry); + if (path == NULL) + return -ENOMEM; + + cifs_sb = CIFS_SB(inode->i_sb); + + utf16_path = cifs_convert_path_to_utf16(path + 1, cifs_sb); + if (utf16_path == NULL) { + rc = -ENOMEM; + goto notify_exit; + } + + if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify))) { + rc = -EFAULT; + goto notify_exit; + } + + tcon = cifs_sb_master_tcon(cifs_sb); + oparms.tcon = tcon; + oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.disposition = FILE_OPEN; + oparms.create_options = cifs_create_options(cifs_sb, 0); + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); + if (rc) + goto notify_exit; + + rc = SMB2_change_notify(xid, tcon, fid.persistent_fid, fid.volatile_fid, + notify.watch_tree, notify.completion_filter); + + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + + cifs_dbg(FYI, "change notify for path %s rc %d\n", path, rc); + +notify_exit: + kfree(path); + kfree(utf16_path); + return rc; +} + static int smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, const char *path, struct cifs_sb_info *cifs_sb, @@ -2086,10 +2142,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA; oparms.disposition = FILE_OPEN; - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = fid; oparms.reconnect = false; @@ -2343,10 +2396,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = desired_access; oparms.disposition = FILE_OPEN; - if (cifs_sb && backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -2402,7 +2452,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, static int smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct kstatfs *buf) + struct cifs_sb_info *cifs_sb, struct kstatfs *buf) { struct smb2_query_info_rsp *rsp; struct smb2_fs_full_size_info *info = NULL; @@ -2417,7 +2467,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, FS_FULL_SIZE_INFORMATION, SMB2_O_INFO_FILESYSTEM, sizeof(struct smb2_fs_full_size_info), - &rsp_iov, &buftype, NULL); + &rsp_iov, &buftype, cifs_sb); if (rc) goto qfs_exit; @@ -2439,7 +2489,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, static int smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct kstatfs *buf) + struct cifs_sb_info *cifs_sb, struct kstatfs *buf) { int rc; __le16 srch_path = 0; /* Null - open root of share */ @@ -2448,12 +2498,12 @@ smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid fid; if (!tcon->posix_extensions) - return smb2_queryfs(xid, tcon, buf); + return smb2_queryfs(xid, tcon, cifs_sb, buf); oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -2722,6 +2772,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct smb2_create_rsp *create_rsp; struct smb2_ioctl_rsp *ioctl_rsp; struct reparse_data_buffer *reparse_buf; + int create_options = is_reparse_point ? OPEN_REPARSE_POINT : 0; u32 plen; cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); @@ -2748,14 +2799,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; - if (is_reparse_point) - oparms.create_options = OPEN_REPARSE_POINT; - + oparms.create_options = cifs_create_options(cifs_sb, create_options); oparms.fid = &fid; oparms.reconnect = false; @@ -2934,11 +2978,6 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, tcon = tlink_tcon(tlink); xid = get_xid(); - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; - utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) { rc = -ENOMEM; @@ -2949,6 +2988,7 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, oparms.tcon = tcon; oparms.desired_access = READ_CONTROL; oparms.disposition = FILE_OPEN; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; oparms.reconnect = false; @@ -2990,11 +3030,6 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen, tcon = tlink_tcon(tlink); xid = get_xid(); - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; - if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP) access_flags = WRITE_OWNER; else @@ -3009,6 +3044,7 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen, oparms.tcon = tcon; oparms.desired_access = access_flags; + oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; @@ -4491,7 +4527,6 @@ smb2_make_node(unsigned int xid, struct inode *inode, { struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); int rc = -EPERM; - int create_options = CREATE_NOT_DIR | CREATE_OPTION_SPECIAL; FILE_ALL_INFO *buf = NULL; struct cifs_io_parms io_parms; __u32 oplock = 0; @@ -4527,13 +4562,11 @@ smb2_make_node(unsigned int xid, struct inode *inode, goto out; } - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; - oparms.create_options = create_options; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR | + CREATE_OPTION_SPECIAL); oparms.disposition = FILE_CREATE; oparms.path = full_path; oparms.fid = &fid; @@ -4868,6 +4901,7 @@ struct smb_version_operations smb30_operations = { .dir_needs_close = smb2_dir_needs_close, .fallocate = smb3_fallocate, .enum_snapshots = smb3_enum_snapshots, + .notify = smb3_notify, .init_transform_rq = smb3_init_transform_rq, .is_transform_hdr = smb3_is_transform_hdr, .receive_transform = smb3_receive_transform, @@ -4978,6 +5012,7 @@ struct smb_version_operations smb311_operations = { .dir_needs_close = smb2_dir_needs_close, .fallocate = smb3_fallocate, .enum_snapshots = smb3_enum_snapshots, + .notify = smb3_notify, .init_transform_rq = smb3_init_transform_rq, .is_transform_hdr = smb3_is_transform_hdr, .receive_transform = smb3_receive_transform, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 14f209f7376f..1234f9ccab03 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -350,9 +350,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) } rc = cifs_negotiate_protocol(0, tcon->ses); - if (!rc && tcon->ses->need_reconnect) + if (!rc && tcon->ses->need_reconnect) { rc = cifs_setup_session(0, tcon->ses, nls_codepage); - + if ((rc == -EACCES) && !tcon->retry) { + rc = -EHOSTDOWN; + mutex_unlock(&tcon->ses->session_mutex); + goto failed; + } + } if (rc || !tcon->need_reconnect) { mutex_unlock(&tcon->ses->session_mutex); goto out; @@ -397,6 +402,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) case SMB2_SET_INFO: rc = -EAGAIN; } +failed: unload_nls(nls_codepage); return rc; } @@ -1933,6 +1939,16 @@ parse_query_id_ctxt(struct create_context *cc, struct smb2_file_all_info *buf) buf->IndexNumber = pdisk_id->DiskFileId; } +static void +parse_posix_ctxt(struct create_context *cc, struct smb_posix_info *pposix_inf) +{ + /* struct smb_posix_info *ppinf = (struct smb_posix_info *)cc; */ + + /* TODO: Need to add parsing for the context and return */ + printk_once(KERN_WARNING + "SMB3 3.11 POSIX response context not completed yet\n"); +} + void smb2_parse_contexts(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, @@ -1944,6 +1960,9 @@ smb2_parse_contexts(struct TCP_Server_Info *server, unsigned int next; unsigned int remaining; char *name; + const char smb3_create_tag_posix[] = {0x93, 0xAD, 0x25, 0x50, 0x9C, + 0xB4, 0x11, 0xE7, 0xB4, 0x23, 0x83, + 0xDE, 0x96, 0x8B, 0xCD, 0x7C}; *oplock = 0; data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); @@ -1963,6 +1982,15 @@ smb2_parse_contexts(struct TCP_Server_Info *server, else if (buf && (le16_to_cpu(cc->NameLength) == 4) && strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) parse_query_id_ctxt(cc, buf); + else if ((le16_to_cpu(cc->NameLength) == 16)) { + if (memcmp(name, smb3_create_tag_posix, 16) == 0) + parse_posix_ctxt(cc, NULL); + } + /* else { + cifs_dbg(FYI, "Context not matched with len %d\n", + le16_to_cpu(cc->NameLength)); + cifs_dump_mem("Cctxt name: ", name, 4); + } */ next = le32_to_cpu(cc->Next); if (!next) @@ -3357,6 +3385,7 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst, req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; + /* See note 354 of MS-SMB2, 64K max */ req->OutputBufferLength = cpu_to_le32(SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE); req->CompletionFilter = cpu_to_le32(completion_filter); @@ -4023,6 +4052,9 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, wdata->offset, wdata->bytes, wdata->result); + if (wdata->result == -ENOSPC) + printk_once(KERN_WARNING "Out of space writing to %s\n", + tcon->treeName); } else trace_smb3_write_done(0 /* no xid */, wdata->cfile->fid.persistent_fid, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 4c43dbd1e089..fa03df130f1a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1519,6 +1519,7 @@ struct smb3_fs_vol_info { #define FILE_NORMALIZED_NAME_INFORMATION 48 #define FILEID_GLOBAL_TX_DIRECTORY_INFORMATION 50 #define FILE_STANDARD_LINK_INFORMATION 54 +#define FILE_ID_INFORMATION 59 struct smb2_file_internal_info { __le64 IndexNumber; @@ -1593,6 +1594,21 @@ struct smb2_file_network_open_info { __le32 Reserved; } __packed; /* level 34 Query also similar returned in close rsp and open rsp */ +/* See MS-FSCC 2.4.43 */ +struct smb2_file_id_information { + __le64 VolumeSerialNumber; + __u64 PersistentFileId; /* opaque endianness */ + __u64 VolatileFileId; /* opaque endianness */ +} __packed; /* level 59 */ + extern char smb2_padding[7]; +/* equivalent of the contents of SMB3.1.1 POSIX open context response */ +struct smb_posix_info { + __le32 nlink; + __le32 reparse_tag; + __le32 mode; + kuid_t uid; + kuid_t gid; +}; #endif /* _SMB2PDU_H */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 6c678e00046f..de6388ef344f 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -68,7 +68,7 @@ extern int smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid); extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon, - struct cifs_fid *pfid); + struct cifs_sb_info *cifs_sb, struct cifs_fid *pfid); extern void close_shroot(struct cached_fid *cfid); extern void close_shroot_lease(struct cached_fid *cfid); extern void close_shroot_lease_locked(struct cached_fid *cfid); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index fe6acfce3390..08b703b7a15e 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -104,13 +104,14 @@ int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) { struct cifs_chan *chan; struct cifs_ses *ses = NULL; + struct TCP_Server_Info *it = NULL; int i; int rc = 0; spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(it, &cifs_tcp_ses_list, tcp_ses_list) { + list_for_each_entry(ses, &it->smb_ses_list, smb_ses_list) { if (ses->Suid == ses_id) goto found; } diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index e7e350b13d6a..4cb0d5f7ce45 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -547,6 +547,33 @@ DEFINE_EVENT(smb3_exit_err_class, smb3_##name, \ DEFINE_SMB3_EXIT_ERR_EVENT(exit_err); + +DECLARE_EVENT_CLASS(smb3_sync_err_class, + TP_PROTO(unsigned long ino, + int rc), + TP_ARGS(ino, rc), + TP_STRUCT__entry( + __field(unsigned long, ino) + __field(int, rc) + ), + TP_fast_assign( + __entry->ino = ino; + __entry->rc = rc; + ), + TP_printk("\tino=%lu rc=%d", + __entry->ino, __entry->rc) +) + +#define DEFINE_SMB3_SYNC_ERR_EVENT(name) \ +DEFINE_EVENT(smb3_sync_err_class, cifs_##name, \ + TP_PROTO(unsigned long ino, \ + int rc), \ + TP_ARGS(ino, rc)) + +DEFINE_SMB3_SYNC_ERR_EVENT(fsync_err); +DEFINE_SMB3_SYNC_ERR_EVENT(flush_err); + + DECLARE_EVENT_CLASS(smb3_enter_exit_class, TP_PROTO(unsigned int xid, const char *func_name), diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index d46e9baee285..b88aecc86550 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -35,4 +35,4 @@ $(obj)/utf8data.h: $(src)/utf8data.h_shipped FORCE endif targets += utf8data.h -hostprogs-y += mkutf8data +hostprogs += mkutf8data diff --git a/fs/vboxsf/Kconfig b/fs/vboxsf/Kconfig new file mode 100644 index 000000000000..b84586ae08b3 --- /dev/null +++ b/fs/vboxsf/Kconfig @@ -0,0 +1,10 @@ +config VBOXSF_FS + tristate "VirtualBox guest shared folder (vboxsf) support" + depends on X86 && VBOXGUEST + select NLS + help + VirtualBox hosts can share folders with guests, this driver + implements the Linux-guest side of this allowing folders exported + by the host to be mounted under Linux. + + If you want to use shared folders in VirtualBox guests, answer Y or M. diff --git a/fs/vboxsf/Makefile b/fs/vboxsf/Makefile new file mode 100644 index 000000000000..9e4328e79623 --- /dev/null +++ b/fs/vboxsf/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: MIT + +obj-$(CONFIG_VBOXSF_FS) += vboxsf.o + +vboxsf-y := dir.o file.o utils.o vboxsf_wrappers.o super.o diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c new file mode 100644 index 000000000000..dd147b490982 --- /dev/null +++ b/fs/vboxsf/dir.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Directory inode and file operations + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include +#include +#include "vfsmod.h" + +static int vboxsf_dir_open(struct inode *inode, struct file *file) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); + struct shfl_createparms params = {}; + struct vboxsf_dir_info *sf_d; + int err; + + sf_d = vboxsf_dir_info_alloc(); + if (!sf_d) + return -ENOMEM; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_DIRECTORY | SHFL_CF_ACT_OPEN_IF_EXISTS | + SHFL_CF_ACT_FAIL_IF_NEW | SHFL_CF_ACCESS_READ; + + err = vboxsf_create_at_dentry(file_dentry(file), ¶ms); + if (err) + goto err_free_dir_info; + + if (params.result != SHFL_FILE_EXISTS) { + err = -ENOENT; + goto err_close; + } + + err = vboxsf_dir_read_all(sbi, sf_d, params.handle); + if (err) + goto err_close; + + vboxsf_close(sbi->root, params.handle); + file->private_data = sf_d; + return 0; + +err_close: + vboxsf_close(sbi->root, params.handle); +err_free_dir_info: + vboxsf_dir_info_free(sf_d); + return err; +} + +static int vboxsf_dir_release(struct inode *inode, struct file *file) +{ + if (file->private_data) + vboxsf_dir_info_free(file->private_data); + + return 0; +} + +static unsigned int vboxsf_get_d_type(u32 mode) +{ + unsigned int d_type; + + switch (mode & SHFL_TYPE_MASK) { + case SHFL_TYPE_FIFO: + d_type = DT_FIFO; + break; + case SHFL_TYPE_DEV_CHAR: + d_type = DT_CHR; + break; + case SHFL_TYPE_DIRECTORY: + d_type = DT_DIR; + break; + case SHFL_TYPE_DEV_BLOCK: + d_type = DT_BLK; + break; + case SHFL_TYPE_FILE: + d_type = DT_REG; + break; + case SHFL_TYPE_SYMLINK: + d_type = DT_LNK; + break; + case SHFL_TYPE_SOCKET: + d_type = DT_SOCK; + break; + case SHFL_TYPE_WHITEOUT: + d_type = DT_WHT; + break; + default: + d_type = DT_UNKNOWN; + break; + } + return d_type; +} + +static bool vboxsf_dir_emit(struct file *dir, struct dir_context *ctx) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(file_inode(dir)->i_sb); + struct vboxsf_dir_info *sf_d = dir->private_data; + struct shfl_dirinfo *info; + struct vboxsf_dir_buf *b; + unsigned int d_type; + loff_t i, cur = 0; + ino_t fake_ino; + void *end; + int err; + + list_for_each_entry(b, &sf_d->info_list, head) { +try_next_entry: + if (ctx->pos >= cur + b->entries) { + cur += b->entries; + continue; + } + + /* + * Note the vboxsf_dir_info objects we are iterating over here + * are variable sized, so the info pointer may end up being + * unaligned. This is how we get the data from the host. + * Since vboxsf is only supported on x86 machines this is not + * a problem. + */ + for (i = 0, info = b->buf; i < ctx->pos - cur; i++) { + end = &info->name.string.utf8[info->name.size]; + /* Only happens if the host gives us corrupt data */ + if (WARN_ON(end > (b->buf + b->used))) + return false; + info = end; + } + + end = &info->name.string.utf8[info->name.size]; + if (WARN_ON(end > (b->buf + b->used))) + return false; + + /* Info now points to the right entry, emit it. */ + d_type = vboxsf_get_d_type(info->info.attr.mode); + + /* + * On 32 bit systems pos is 64 signed, while ino is 32 bit + * unsigned so fake_ino may overflow, check for this. + */ + if ((ino_t)(ctx->pos + 1) != (u64)(ctx->pos + 1)) { + vbg_err("vboxsf: fake ino overflow, truncating dir\n"); + return false; + } + fake_ino = ctx->pos + 1; + + if (sbi->nls) { + char d_name[NAME_MAX]; + + err = vboxsf_nlscpy(sbi, d_name, NAME_MAX, + info->name.string.utf8, + info->name.length); + if (err) { + /* skip erroneous entry and proceed */ + ctx->pos += 1; + goto try_next_entry; + } + + return dir_emit(ctx, d_name, strlen(d_name), + fake_ino, d_type); + } + + return dir_emit(ctx, info->name.string.utf8, info->name.length, + fake_ino, d_type); + } + + return false; +} + +static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx) +{ + bool emitted; + + do { + emitted = vboxsf_dir_emit(dir, ctx); + if (emitted) + ctx->pos += 1; + } while (emitted); + + return 0; +} + +const struct file_operations vboxsf_dir_fops = { + .open = vboxsf_dir_open, + .iterate = vboxsf_dir_iterate, + .release = vboxsf_dir_release, + .read = generic_read_dir, + .llseek = generic_file_llseek, +}; + +/* + * This is called during name resolution/lookup to check if the @dentry in + * the cache is still valid. the job is handled by vboxsf_inode_revalidate. + */ +static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (d_really_is_positive(dentry)) + return vboxsf_inode_revalidate(dentry) == 0; + else + return vboxsf_stat_dentry(dentry, NULL) == -ENOENT; +} + +const struct dentry_operations vboxsf_dentry_ops = { + .d_revalidate = vboxsf_dentry_revalidate +}; + +/* iops */ + +static struct dentry *vboxsf_dir_lookup(struct inode *parent, + struct dentry *dentry, + unsigned int flags) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct shfl_fsobjinfo fsinfo; + struct inode *inode; + int err; + + dentry->d_time = jiffies; + + err = vboxsf_stat_dentry(dentry, &fsinfo); + if (err) { + inode = (err == -ENOENT) ? NULL : ERR_PTR(err); + } else { + inode = vboxsf_new_inode(parent->i_sb); + if (!IS_ERR(inode)) + vboxsf_init_inode(sbi, inode, &fsinfo); + } + + return d_splice_alias(inode, dentry); +} + +static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry, + struct shfl_fsobjinfo *info) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct vboxsf_inode *sf_i; + struct inode *inode; + + inode = vboxsf_new_inode(parent->i_sb); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + sf_i = VBOXSF_I(inode); + /* The host may have given us different attr then requested */ + sf_i->force_restat = 1; + vboxsf_init_inode(sbi, inode, info); + + d_instantiate(dentry, inode); + + return 0; +} + +static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, + umode_t mode, int is_dir) +{ + struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct shfl_createparms params = {}; + int err; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | + SHFL_CF_ACT_FAIL_IF_EXISTS | + SHFL_CF_ACCESS_READWRITE | + (is_dir ? SHFL_CF_DIRECTORY : 0); + params.info.attr.mode = (mode & 0777) | + (is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE); + params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING; + + err = vboxsf_create_at_dentry(dentry, ¶ms); + if (err) + return err; + + if (params.result != SHFL_FILE_CREATED) + return -EPERM; + + vboxsf_close(sbi->root, params.handle); + + err = vboxsf_dir_instantiate(parent, dentry, ¶ms.info); + if (err) + return err; + + /* parent directory access/change time changed */ + sf_parent_i->force_restat = 1; + + return 0; +} + +static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry, + umode_t mode, bool excl) +{ + return vboxsf_dir_create(parent, dentry, mode, 0); +} + +static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry, + umode_t mode) +{ + return vboxsf_dir_create(parent, dentry, mode, 1); +} + +static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); + struct inode *inode = d_inode(dentry); + struct shfl_string *path; + u32 flags; + int err; + + if (S_ISDIR(inode->i_mode)) + flags = SHFL_REMOVE_DIR; + else + flags = SHFL_REMOVE_FILE; + + if (S_ISLNK(inode->i_mode)) + flags |= SHFL_REMOVE_SYMLINK; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + err = vboxsf_remove(sbi->root, path, flags); + __putname(path); + if (err) + return err; + + /* parent directory access/change time changed */ + sf_parent_i->force_restat = 1; + + return 0; +} + +static int vboxsf_dir_rename(struct inode *old_parent, + struct dentry *old_dentry, + struct inode *new_parent, + struct dentry *new_dentry, + unsigned int flags) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(old_parent->i_sb); + struct vboxsf_inode *sf_old_parent_i = VBOXSF_I(old_parent); + struct vboxsf_inode *sf_new_parent_i = VBOXSF_I(new_parent); + u32 shfl_flags = SHFL_RENAME_FILE | SHFL_RENAME_REPLACE_IF_EXISTS; + struct shfl_string *old_path, *new_path; + int err; + + if (flags) + return -EINVAL; + + old_path = vboxsf_path_from_dentry(sbi, old_dentry); + if (IS_ERR(old_path)) + return PTR_ERR(old_path); + + new_path = vboxsf_path_from_dentry(sbi, new_dentry); + if (IS_ERR(new_path)) { + err = PTR_ERR(new_path); + goto err_put_old_path; + } + + if (d_inode(old_dentry)->i_mode & S_IFDIR) + shfl_flags = 0; + + err = vboxsf_rename(sbi->root, old_path, new_path, shfl_flags); + if (err == 0) { + /* parent directories access/change time changed */ + sf_new_parent_i->force_restat = 1; + sf_old_parent_i->force_restat = 1; + } + + __putname(new_path); +err_put_old_path: + __putname(old_path); + return err; +} + +static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry, + const char *symname) +{ + struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + int symname_size = strlen(symname) + 1; + struct shfl_string *path, *ssymname; + struct shfl_fsobjinfo info; + int err; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + ssymname = kmalloc(SHFLSTRING_HEADER_SIZE + symname_size, GFP_KERNEL); + if (!ssymname) { + __putname(path); + return -ENOMEM; + } + ssymname->length = symname_size - 1; + ssymname->size = symname_size; + memcpy(ssymname->string.utf8, symname, symname_size); + + err = vboxsf_symlink(sbi->root, path, ssymname, &info); + kfree(ssymname); + __putname(path); + if (err) { + /* -EROFS means symlinks are note support -> -EPERM */ + return (err == -EROFS) ? -EPERM : err; + } + + err = vboxsf_dir_instantiate(parent, dentry, &info); + if (err) + return err; + + /* parent directory access/change time changed */ + sf_parent_i->force_restat = 1; + return 0; +} + +const struct inode_operations vboxsf_dir_iops = { + .lookup = vboxsf_dir_lookup, + .create = vboxsf_dir_mkfile, + .mkdir = vboxsf_dir_mkdir, + .rmdir = vboxsf_dir_unlink, + .unlink = vboxsf_dir_unlink, + .rename = vboxsf_dir_rename, + .symlink = vboxsf_dir_symlink, + .getattr = vboxsf_getattr, + .setattr = vboxsf_setattr, +}; diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c new file mode 100644 index 000000000000..c4ab5996d97a --- /dev/null +++ b/fs/vboxsf/file.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Regular file inode and file ops. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include +#include +#include +#include +#include +#include "vfsmod.h" + +struct vboxsf_handle { + u64 handle; + u32 root; + u32 access_flags; + struct kref refcount; + struct list_head head; +}; + +static int vboxsf_file_open(struct inode *inode, struct file *file) +{ + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct shfl_createparms params = {}; + struct vboxsf_handle *sf_handle; + u32 access_flags = 0; + int err; + + sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL); + if (!sf_handle) + return -ENOMEM; + + /* + * We check the value of params.handle afterwards to find out if + * the call succeeded or failed, as the API does not seem to cleanly + * distinguish error and informational messages. + * + * Furthermore, we must set params.handle to SHFL_HANDLE_NIL to + * make the shared folders host service use our mode parameter. + */ + params.handle = SHFL_HANDLE_NIL; + if (file->f_flags & O_CREAT) { + params.create_flags |= SHFL_CF_ACT_CREATE_IF_NEW; + /* + * We ignore O_EXCL, as the Linux kernel seems to call create + * beforehand itself, so O_EXCL should always fail. + */ + if (file->f_flags & O_TRUNC) + params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS; + else + params.create_flags |= SHFL_CF_ACT_OPEN_IF_EXISTS; + } else { + params.create_flags |= SHFL_CF_ACT_FAIL_IF_NEW; + if (file->f_flags & O_TRUNC) + params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS; + } + + switch (file->f_flags & O_ACCMODE) { + case O_RDONLY: + access_flags |= SHFL_CF_ACCESS_READ; + break; + + case O_WRONLY: + access_flags |= SHFL_CF_ACCESS_WRITE; + break; + + case O_RDWR: + access_flags |= SHFL_CF_ACCESS_READWRITE; + break; + + default: + WARN_ON(1); + } + + if (file->f_flags & O_APPEND) + access_flags |= SHFL_CF_ACCESS_APPEND; + + params.create_flags |= access_flags; + params.info.attr.mode = inode->i_mode; + + err = vboxsf_create_at_dentry(file_dentry(file), ¶ms); + if (err == 0 && params.handle == SHFL_HANDLE_NIL) + err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT; + if (err) { + kfree(sf_handle); + return err; + } + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + + /* init our handle struct and add it to the inode's handles list */ + sf_handle->handle = params.handle; + sf_handle->root = VBOXSF_SBI(inode->i_sb)->root; + sf_handle->access_flags = access_flags; + kref_init(&sf_handle->refcount); + + mutex_lock(&sf_i->handle_list_mutex); + list_add(&sf_handle->head, &sf_i->handle_list); + mutex_unlock(&sf_i->handle_list_mutex); + + file->private_data = sf_handle; + return 0; +} + +static void vboxsf_handle_release(struct kref *refcount) +{ + struct vboxsf_handle *sf_handle = + container_of(refcount, struct vboxsf_handle, refcount); + + vboxsf_close(sf_handle->root, sf_handle->handle); + kfree(sf_handle); +} + +static int vboxsf_file_release(struct inode *inode, struct file *file) +{ + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct vboxsf_handle *sf_handle = file->private_data; + + /* + * When a file is closed on our (the guest) side, we want any subsequent + * accesses done on the host side to see all changes done from our side. + */ + filemap_write_and_wait(inode->i_mapping); + + mutex_lock(&sf_i->handle_list_mutex); + list_del(&sf_handle->head); + mutex_unlock(&sf_i->handle_list_mutex); + + kref_put(&sf_handle->refcount, vboxsf_handle_release); + return 0; +} + +/* + * Write back dirty pages now, because there may not be any suitable + * open files later + */ +static void vboxsf_vma_close(struct vm_area_struct *vma) +{ + filemap_write_and_wait(vma->vm_file->f_mapping); +} + +static const struct vm_operations_struct vboxsf_file_vm_ops = { + .close = vboxsf_vma_close, + .fault = filemap_fault, + .map_pages = filemap_map_pages, +}; + +static int vboxsf_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err; + + err = generic_file_mmap(file, vma); + if (!err) + vma->vm_ops = &vboxsf_file_vm_ops; + + return err; +} + +/* + * Note that since we are accessing files on the host's filesystem, files + * may always be changed underneath us by the host! + * + * The vboxsf API between the guest and the host does not offer any functions + * to deal with this. There is no inode-generation to check for changes, no + * events / callback on changes and no way to lock files. + * + * To avoid returning stale data when a file gets *opened* on our (the guest) + * side, we do a "stat" on the host side, then compare the mtime with the + * last known mtime and invalidate the page-cache if they differ. + * This is done from vboxsf_inode_revalidate(). + * + * When reads are done through the read_iter fop, it is possible to do + * further cache revalidation then, there are 3 options to deal with this: + * + * 1) Rely solely on the revalidation done at open time + * 2) Do another "stat" and compare mtime again. Unfortunately the vboxsf + * host API does not allow stat on handles, so we would need to use + * file->f_path.dentry and the stat will then fail if the file was unlinked + * or renamed (and there is no thing like NFS' silly-rename). So we get: + * 2a) "stat" and compare mtime, on stat failure invalidate the cache + * 2b) "stat" and compare mtime, on stat failure do nothing + * 3) Simply always call invalidate_inode_pages2_range on the range of the read + * + * Currently we are keeping things KISS and using option 1. this allows + * directly using generic_file_read_iter without wrapping it. + * + * This means that only data written on the host side before open() on + * the guest side is guaranteed to be seen by the guest. If necessary + * we may provide other read-cache strategies in the future and make this + * configurable through a mount option. + */ +const struct file_operations vboxsf_reg_fops = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .mmap = vboxsf_file_mmap, + .open = vboxsf_file_open, + .release = vboxsf_file_release, + .fsync = noop_fsync, + .splice_read = generic_file_splice_read, +}; + +const struct inode_operations vboxsf_reg_iops = { + .getattr = vboxsf_getattr, + .setattr = vboxsf_setattr +}; + +static int vboxsf_readpage(struct file *file, struct page *page) +{ + struct vboxsf_handle *sf_handle = file->private_data; + loff_t off = page_offset(page); + u32 nread = PAGE_SIZE; + u8 *buf; + int err; + + buf = kmap(page); + + err = vboxsf_read(sf_handle->root, sf_handle->handle, off, &nread, buf); + if (err == 0) { + memset(&buf[nread], 0, PAGE_SIZE - nread); + flush_dcache_page(page); + SetPageUptodate(page); + } else { + SetPageError(page); + } + + kunmap(page); + unlock_page(page); + return err; +} + +static struct vboxsf_handle *vboxsf_get_write_handle(struct vboxsf_inode *sf_i) +{ + struct vboxsf_handle *h, *sf_handle = NULL; + + mutex_lock(&sf_i->handle_list_mutex); + list_for_each_entry(h, &sf_i->handle_list, head) { + if (h->access_flags == SHFL_CF_ACCESS_WRITE || + h->access_flags == SHFL_CF_ACCESS_READWRITE) { + kref_get(&h->refcount); + sf_handle = h; + break; + } + } + mutex_unlock(&sf_i->handle_list_mutex); + + return sf_handle; +} + +static int vboxsf_writepage(struct page *page, struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct vboxsf_handle *sf_handle; + loff_t off = page_offset(page); + loff_t size = i_size_read(inode); + u32 nwrite = PAGE_SIZE; + u8 *buf; + int err; + + if (off + PAGE_SIZE > size) + nwrite = size & ~PAGE_MASK; + + sf_handle = vboxsf_get_write_handle(sf_i); + if (!sf_handle) + return -EBADF; + + buf = kmap(page); + err = vboxsf_write(sf_handle->root, sf_handle->handle, + off, &nwrite, buf); + kunmap(page); + + kref_put(&sf_handle->refcount, vboxsf_handle_release); + + if (err == 0) { + ClearPageError(page); + /* mtime changed */ + sf_i->force_restat = 1; + } else { + ClearPageUptodate(page); + } + + unlock_page(page); + return err; +} + +static int vboxsf_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + struct vboxsf_handle *sf_handle = file->private_data; + unsigned int from = pos & ~PAGE_MASK; + u32 nwritten = len; + u8 *buf; + int err; + + /* zero the stale part of the page if we did a short copy */ + if (!PageUptodate(page) && copied < len) + zero_user(page, from + copied, len - copied); + + buf = kmap(page); + err = vboxsf_write(sf_handle->root, sf_handle->handle, + pos, &nwritten, buf + from); + kunmap(page); + + if (err) { + nwritten = 0; + goto out; + } + + /* mtime changed */ + VBOXSF_I(inode)->force_restat = 1; + + if (!PageUptodate(page) && nwritten == PAGE_SIZE) + SetPageUptodate(page); + + pos += nwritten; + if (pos > inode->i_size) + i_size_write(inode, pos); + +out: + unlock_page(page); + put_page(page); + + return nwritten; +} + +/* + * Note simple_write_begin does not read the page from disk on partial writes + * this is ok since vboxsf_write_end only writes the written parts of the + * page and it does not call SetPageUptodate for partial writes. + */ +const struct address_space_operations vboxsf_reg_aops = { + .readpage = vboxsf_readpage, + .writepage = vboxsf_writepage, + .set_page_dirty = __set_page_dirty_nobuffers, + .write_begin = simple_write_begin, + .write_end = vboxsf_write_end, +}; + +static const char *vboxsf_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); + struct shfl_string *path; + char *link; + int err; + + if (!dentry) + return ERR_PTR(-ECHILD); + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return ERR_CAST(path); + + link = kzalloc(PATH_MAX, GFP_KERNEL); + if (!link) { + __putname(path); + return ERR_PTR(-ENOMEM); + } + + err = vboxsf_readlink(sbi->root, path, PATH_MAX, link); + __putname(path); + if (err) { + kfree(link); + return ERR_PTR(err); + } + + set_delayed_call(done, kfree_link, link); + return link; +} + +const struct inode_operations vboxsf_lnk_iops = { + .get_link = vboxsf_get_link +}; diff --git a/fs/vboxsf/shfl_hostintf.h b/fs/vboxsf/shfl_hostintf.h new file mode 100644 index 000000000000..aca829062c12 --- /dev/null +++ b/fs/vboxsf/shfl_hostintf.h @@ -0,0 +1,901 @@ +/* SPDX-License-Identifier: MIT */ +/* + * VirtualBox Shared Folders: host interface definition. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#ifndef SHFL_HOSTINTF_H +#define SHFL_HOSTINTF_H + +#include + +/* The max in/out buffer size for a FN_READ or FN_WRITE call */ +#define SHFL_MAX_RW_COUNT (16 * SZ_1M) + +/* + * Structures shared between guest and the service + * can be relocated and use offsets to point to variable + * length parts. + * + * Shared folders protocol works with handles. + * Before doing any action on a file system object, + * one have to obtain the object handle via a SHFL_FN_CREATE + * request. A handle must be closed with SHFL_FN_CLOSE. + */ + +enum { + SHFL_FN_QUERY_MAPPINGS = 1, /* Query mappings changes. */ + SHFL_FN_QUERY_MAP_NAME = 2, /* Query map name. */ + SHFL_FN_CREATE = 3, /* Open/create object. */ + SHFL_FN_CLOSE = 4, /* Close object handle. */ + SHFL_FN_READ = 5, /* Read object content. */ + SHFL_FN_WRITE = 6, /* Write new object content. */ + SHFL_FN_LOCK = 7, /* Lock/unlock a range in the object. */ + SHFL_FN_LIST = 8, /* List object content. */ + SHFL_FN_INFORMATION = 9, /* Query/set object information. */ + /* Note function number 10 is not used! */ + SHFL_FN_REMOVE = 11, /* Remove object */ + SHFL_FN_MAP_FOLDER_OLD = 12, /* Map folder (legacy) */ + SHFL_FN_UNMAP_FOLDER = 13, /* Unmap folder */ + SHFL_FN_RENAME = 14, /* Rename object */ + SHFL_FN_FLUSH = 15, /* Flush file */ + SHFL_FN_SET_UTF8 = 16, /* Select UTF8 filename encoding */ + SHFL_FN_MAP_FOLDER = 17, /* Map folder */ + SHFL_FN_READLINK = 18, /* Read symlink dest (as of VBox 4.0) */ + SHFL_FN_SYMLINK = 19, /* Create symlink (as of VBox 4.0) */ + SHFL_FN_SET_SYMLINKS = 20, /* Ask host to show symlinks (4.0+) */ +}; + +/* Root handles for a mapping are of type u32, Root handles are unique. */ +#define SHFL_ROOT_NIL UINT_MAX + +/* Shared folders handle for an opened object are of type u64. */ +#define SHFL_HANDLE_NIL ULLONG_MAX + +/* Hardcoded maximum length (in chars) of a shared folder name. */ +#define SHFL_MAX_LEN (256) +/* Hardcoded maximum number of shared folder mapping available to the guest. */ +#define SHFL_MAX_MAPPINGS (64) + +/** Shared folder string buffer structure. */ +struct shfl_string { + /** Allocated size of the string member in bytes. */ + u16 size; + + /** Length of string without trailing nul in bytes. */ + u16 length; + + /** UTF-8 or UTF-16 string. Nul terminated. */ + union { + u8 utf8[2]; + u16 utf16[1]; + u16 ucs2[1]; /* misnomer, use utf16. */ + } string; +}; +VMMDEV_ASSERT_SIZE(shfl_string, 6); + +/* The size of shfl_string w/o the string part. */ +#define SHFLSTRING_HEADER_SIZE 4 + +/* Calculate size of the string. */ +static inline u32 shfl_string_buf_size(const struct shfl_string *string) +{ + return string ? SHFLSTRING_HEADER_SIZE + string->size : 0; +} + +/* Set user id on execution (S_ISUID). */ +#define SHFL_UNIX_ISUID 0004000U +/* Set group id on execution (S_ISGID). */ +#define SHFL_UNIX_ISGID 0002000U +/* Sticky bit (S_ISVTX / S_ISTXT). */ +#define SHFL_UNIX_ISTXT 0001000U + +/* Owner readable (S_IRUSR). */ +#define SHFL_UNIX_IRUSR 0000400U +/* Owner writable (S_IWUSR). */ +#define SHFL_UNIX_IWUSR 0000200U +/* Owner executable (S_IXUSR). */ +#define SHFL_UNIX_IXUSR 0000100U + +/* Group readable (S_IRGRP). */ +#define SHFL_UNIX_IRGRP 0000040U +/* Group writable (S_IWGRP). */ +#define SHFL_UNIX_IWGRP 0000020U +/* Group executable (S_IXGRP). */ +#define SHFL_UNIX_IXGRP 0000010U + +/* Other readable (S_IROTH). */ +#define SHFL_UNIX_IROTH 0000004U +/* Other writable (S_IWOTH). */ +#define SHFL_UNIX_IWOTH 0000002U +/* Other executable (S_IXOTH). */ +#define SHFL_UNIX_IXOTH 0000001U + +/* Named pipe (fifo) (S_IFIFO). */ +#define SHFL_TYPE_FIFO 0010000U +/* Character device (S_IFCHR). */ +#define SHFL_TYPE_DEV_CHAR 0020000U +/* Directory (S_IFDIR). */ +#define SHFL_TYPE_DIRECTORY 0040000U +/* Block device (S_IFBLK). */ +#define SHFL_TYPE_DEV_BLOCK 0060000U +/* Regular file (S_IFREG). */ +#define SHFL_TYPE_FILE 0100000U +/* Symbolic link (S_IFLNK). */ +#define SHFL_TYPE_SYMLINK 0120000U +/* Socket (S_IFSOCK). */ +#define SHFL_TYPE_SOCKET 0140000U +/* Whiteout (S_IFWHT). */ +#define SHFL_TYPE_WHITEOUT 0160000U +/* Type mask (S_IFMT). */ +#define SHFL_TYPE_MASK 0170000U + +/* Checks the mode flags indicate a directory (S_ISDIR). */ +#define SHFL_IS_DIRECTORY(m) (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_DIRECTORY) +/* Checks the mode flags indicate a symbolic link (S_ISLNK). */ +#define SHFL_IS_SYMLINK(m) (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_SYMLINK) + +/** The available additional information in a shfl_fsobjattr object. */ +enum shfl_fsobjattr_add { + /** No additional information is available / requested. */ + SHFLFSOBJATTRADD_NOTHING = 1, + /** + * The additional unix attributes (shfl_fsobjattr::u::unix_attr) are + * available / requested. + */ + SHFLFSOBJATTRADD_UNIX, + /** + * The additional extended attribute size (shfl_fsobjattr::u::size) is + * available / requested. + */ + SHFLFSOBJATTRADD_EASIZE, + /** + * The last valid item (inclusive). + * The valid range is SHFLFSOBJATTRADD_NOTHING thru + * SHFLFSOBJATTRADD_LAST. + */ + SHFLFSOBJATTRADD_LAST = SHFLFSOBJATTRADD_EASIZE, + + /** The usual 32-bit hack. */ + SHFLFSOBJATTRADD_32BIT_SIZE_HACK = 0x7fffffff +}; + +/** + * Additional unix Attributes, these are available when + * shfl_fsobjattr.additional == SHFLFSOBJATTRADD_UNIX. + */ +struct shfl_fsobjattr_unix { + /** + * The user owning the filesystem object (st_uid). + * This field is ~0U if not supported. + */ + u32 uid; + + /** + * The group the filesystem object is assigned (st_gid). + * This field is ~0U if not supported. + */ + u32 gid; + + /** + * Number of hard links to this filesystem object (st_nlink). + * This field is 1 if the filesystem doesn't support hardlinking or + * the information isn't available. + */ + u32 hardlinks; + + /** + * The device number of the device which this filesystem object resides + * on (st_dev). This field is 0 if this information is not available. + */ + u32 inode_id_device; + + /** + * The unique identifier (within the filesystem) of this filesystem + * object (st_ino). Together with inode_id_device, this field can be + * used as a OS wide unique id, when both their values are not 0. + * This field is 0 if the information is not available. + */ + u64 inode_id; + + /** + * User flags (st_flags). + * This field is 0 if this information is not available. + */ + u32 flags; + + /** + * The current generation number (st_gen). + * This field is 0 if this information is not available. + */ + u32 generation_id; + + /** + * The device number of a char. or block device type object (st_rdev). + * This field is 0 if the file isn't a char. or block device or when + * the OS doesn't use the major+minor device idenfication scheme. + */ + u32 device; +} __packed; + +/** Extended attribute size. */ +struct shfl_fsobjattr_easize { + /** Size of EAs. */ + s64 cb; +} __packed; + +/** Shared folder filesystem object attributes. */ +struct shfl_fsobjattr { + /** Mode flags (st_mode). SHFL_UNIX_*, SHFL_TYPE_*, and SHFL_DOS_*. */ + u32 mode; + + /** The additional attributes available. */ + enum shfl_fsobjattr_add additional; + + /** + * Additional attributes. + * + * Unless explicitly specified to an API, the API can provide additional + * data as it is provided by the underlying OS. + */ + union { + struct shfl_fsobjattr_unix unix_attr; + struct shfl_fsobjattr_easize size; + } __packed u; +} __packed; +VMMDEV_ASSERT_SIZE(shfl_fsobjattr, 44); + +struct shfl_timespec { + s64 ns_relative_to_unix_epoch; +}; + +/** Filesystem object information structure. */ +struct shfl_fsobjinfo { + /** + * Logical size (st_size). + * For normal files this is the size of the file. + * For symbolic links, this is the length of the path name contained + * in the symbolic link. + * For other objects this fields needs to be specified. + */ + s64 size; + + /** Disk allocation size (st_blocks * DEV_BSIZE). */ + s64 allocated; + + /** Time of last access (st_atime). */ + struct shfl_timespec access_time; + + /** Time of last data modification (st_mtime). */ + struct shfl_timespec modification_time; + + /** + * Time of last status change (st_ctime). + * If not available this is set to modification_time. + */ + struct shfl_timespec change_time; + + /** + * Time of file birth (st_birthtime). + * If not available this is set to change_time. + */ + struct shfl_timespec birth_time; + + /** Attributes. */ + struct shfl_fsobjattr attr; + +} __packed; +VMMDEV_ASSERT_SIZE(shfl_fsobjinfo, 92); + +/** + * result of an open/create request. + * Along with handle value the result code + * identifies what has happened while + * trying to open the object. + */ +enum shfl_create_result { + SHFL_NO_RESULT, + /** Specified path does not exist. */ + SHFL_PATH_NOT_FOUND, + /** Path to file exists, but the last component does not. */ + SHFL_FILE_NOT_FOUND, + /** File already exists and either has been opened or not. */ + SHFL_FILE_EXISTS, + /** New file was created. */ + SHFL_FILE_CREATED, + /** Existing file was replaced or overwritten. */ + SHFL_FILE_REPLACED +}; + +/* No flags. Initialization value. */ +#define SHFL_CF_NONE (0x00000000) + +/* + * Only lookup the object, do not return a handle. When this is set all other + * flags are ignored. + */ +#define SHFL_CF_LOOKUP (0x00000001) + +/* + * Open parent directory of specified object. + * Useful for the corresponding Windows FSD flag + * and for opening paths like \\dir\\*.* to search the 'dir'. + */ +#define SHFL_CF_OPEN_TARGET_DIRECTORY (0x00000002) + +/* Create/open a directory. */ +#define SHFL_CF_DIRECTORY (0x00000004) + +/* + * Open/create action to do if object exists + * and if the object does not exists. + * REPLACE file means atomically DELETE and CREATE. + * OVERWRITE file means truncating the file to 0 and + * setting new size. + * When opening an existing directory REPLACE and OVERWRITE + * actions are considered invalid, and cause returning + * FILE_EXISTS with NIL handle. + */ +#define SHFL_CF_ACT_MASK_IF_EXISTS (0x000000f0) +#define SHFL_CF_ACT_MASK_IF_NEW (0x00000f00) + +/* What to do if object exists. */ +#define SHFL_CF_ACT_OPEN_IF_EXISTS (0x00000000) +#define SHFL_CF_ACT_FAIL_IF_EXISTS (0x00000010) +#define SHFL_CF_ACT_REPLACE_IF_EXISTS (0x00000020) +#define SHFL_CF_ACT_OVERWRITE_IF_EXISTS (0x00000030) + +/* What to do if object does not exist. */ +#define SHFL_CF_ACT_CREATE_IF_NEW (0x00000000) +#define SHFL_CF_ACT_FAIL_IF_NEW (0x00000100) + +/* Read/write requested access for the object. */ +#define SHFL_CF_ACCESS_MASK_RW (0x00003000) + +/* No access requested. */ +#define SHFL_CF_ACCESS_NONE (0x00000000) +/* Read access requested. */ +#define SHFL_CF_ACCESS_READ (0x00001000) +/* Write access requested. */ +#define SHFL_CF_ACCESS_WRITE (0x00002000) +/* Read/Write access requested. */ +#define SHFL_CF_ACCESS_READWRITE (0x00003000) + +/* Requested share access for the object. */ +#define SHFL_CF_ACCESS_MASK_DENY (0x0000c000) + +/* Allow any access. */ +#define SHFL_CF_ACCESS_DENYNONE (0x00000000) +/* Do not allow read. */ +#define SHFL_CF_ACCESS_DENYREAD (0x00004000) +/* Do not allow write. */ +#define SHFL_CF_ACCESS_DENYWRITE (0x00008000) +/* Do not allow access. */ +#define SHFL_CF_ACCESS_DENYALL (0x0000c000) + +/* Requested access to attributes of the object. */ +#define SHFL_CF_ACCESS_MASK_ATTR (0x00030000) + +/* No access requested. */ +#define SHFL_CF_ACCESS_ATTR_NONE (0x00000000) +/* Read access requested. */ +#define SHFL_CF_ACCESS_ATTR_READ (0x00010000) +/* Write access requested. */ +#define SHFL_CF_ACCESS_ATTR_WRITE (0x00020000) +/* Read/Write access requested. */ +#define SHFL_CF_ACCESS_ATTR_READWRITE (0x00030000) + +/* + * The file is opened in append mode. + * Ignored if SHFL_CF_ACCESS_WRITE is not set. + */ +#define SHFL_CF_ACCESS_APPEND (0x00040000) + +/** Create parameters buffer struct for SHFL_FN_CREATE call */ +struct shfl_createparms { + /** Returned handle of opened object. */ + u64 handle; + + /** Returned result of the operation */ + enum shfl_create_result result; + + /** SHFL_CF_* */ + u32 create_flags; + + /** + * Attributes of object to create and + * returned actual attributes of opened/created object. + */ + struct shfl_fsobjinfo info; +} __packed; + +/** Shared Folder directory information */ +struct shfl_dirinfo { + /** Full information about the object. */ + struct shfl_fsobjinfo info; + /** + * The length of the short field (number of UTF16 chars). + * It is 16-bit for reasons of alignment. + */ + u16 short_name_len; + /** + * The short name for 8.3 compatibility. + * Empty string if not available. + */ + u16 short_name[14]; + struct shfl_string name; +}; + +/** Shared folder filesystem properties. */ +struct shfl_fsproperties { + /** + * The maximum size of a filesystem object name. + * This does not include the '\\0'. + */ + u32 max_component_len; + + /** + * True if the filesystem is remote. + * False if the filesystem is local. + */ + bool remote; + + /** + * True if the filesystem is case sensitive. + * False if the filesystem is case insensitive. + */ + bool case_sensitive; + + /** + * True if the filesystem is mounted read only. + * False if the filesystem is mounted read write. + */ + bool read_only; + + /** + * True if the filesystem can encode unicode object names. + * False if it can't. + */ + bool supports_unicode; + + /** + * True if the filesystem is compresses. + * False if it isn't or we don't know. + */ + bool compressed; + + /** + * True if the filesystem compresses of individual files. + * False if it doesn't or we don't know. + */ + bool file_compression; +}; +VMMDEV_ASSERT_SIZE(shfl_fsproperties, 12); + +struct shfl_volinfo { + s64 total_allocation_bytes; + s64 available_allocation_bytes; + u32 bytes_per_allocation_unit; + u32 bytes_per_sector; + u32 serial; + struct shfl_fsproperties properties; +}; + + +/** SHFL_FN_MAP_FOLDER Parameters structure. */ +struct shfl_map_folder { + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, out: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: UTF16 + * Path delimiter + */ + struct vmmdev_hgcm_function_parameter delimiter; + + /** + * pointer, in: SHFLROOT (u32) + * Case senstive flag + */ + struct vmmdev_hgcm_function_parameter case_sensitive; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_MAP_FOLDER (4) + + +/** SHFL_FN_UNMAP_FOLDER Parameters structure. */ +struct shfl_unmap_folder { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_UNMAP_FOLDER (1) + + +/** SHFL_FN_CREATE Parameters structure. */ +struct shfl_create { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, in/out: + * Points to struct shfl_createparms buffer. + */ + struct vmmdev_hgcm_function_parameter parms; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_CREATE (3) + + +/** SHFL_FN_CLOSE Parameters structure. */ +struct shfl_close { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to close. + */ + struct vmmdev_hgcm_function_parameter handle; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_CLOSE (2) + + +/** SHFL_FN_READ Parameters structure. */ +struct shfl_read { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to read from. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value64, in: + * Offset to read from. + */ + struct vmmdev_hgcm_function_parameter offset; + + /** + * value64, in/out: + * Bytes to read/How many were read. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, out: + * Buffer to place data to. + */ + struct vmmdev_hgcm_function_parameter buffer; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_READ (5) + + +/** SHFL_FN_WRITE Parameters structure. */ +struct shfl_write { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to write to. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value64, in: + * Offset to write to. + */ + struct vmmdev_hgcm_function_parameter offset; + + /** + * value64, in/out: + * Bytes to write/How many were written. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, in: + * Data to write. + */ + struct vmmdev_hgcm_function_parameter buffer; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_WRITE (5) + + +/* + * SHFL_FN_LIST + * Listing information includes variable length RTDIRENTRY[EX] structures. + */ + +#define SHFL_LIST_NONE 0 +#define SHFL_LIST_RETURN_ONE 1 + +/** SHFL_FN_LIST Parameters structure. */ +struct shfl_list { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to be listed. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value32, in: + * List flags SHFL_LIST_*. + */ + struct vmmdev_hgcm_function_parameter flags; + + /** + * value32, in/out: + * Bytes to be used for listing information/How many bytes were used. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, in/optional + * Points to struct shfl_string buffer that specifies a search path. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, out: + * Buffer to place listing information to. (struct shfl_dirinfo) + */ + struct vmmdev_hgcm_function_parameter buffer; + + /** + * value32, in/out: + * Indicates a key where the listing must be resumed. + * in: 0 means start from begin of object. + * out: 0 means listing completed. + */ + struct vmmdev_hgcm_function_parameter resume_point; + + /** + * pointer, out: + * Number of files returned + */ + struct vmmdev_hgcm_function_parameter file_count; +}; + +/* Number of parameters */ +#define SHFL_CPARMS_LIST (8) + + +/** SHFL_FN_READLINK Parameters structure. */ +struct shfl_readLink { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, out: + * Buffer to place data to. + */ + struct vmmdev_hgcm_function_parameter buffer; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_READLINK (3) + + +/* SHFL_FN_INFORMATION */ + +/* Mask of Set/Get bit. */ +#define SHFL_INFO_MODE_MASK (0x1) +/* Get information */ +#define SHFL_INFO_GET (0x0) +/* Set information */ +#define SHFL_INFO_SET (0x1) + +/* Get name of the object. */ +#define SHFL_INFO_NAME (0x2) +/* Set size of object (extend/trucate); only applies to file objects */ +#define SHFL_INFO_SIZE (0x4) +/* Get/Set file object info. */ +#define SHFL_INFO_FILE (0x8) +/* Get volume information. */ +#define SHFL_INFO_VOLUME (0x10) + +/** SHFL_FN_INFORMATION Parameters structure. */ +struct shfl_information { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to be listed. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value32, in: + * SHFL_INFO_* + */ + struct vmmdev_hgcm_function_parameter flags; + + /** + * value32, in/out: + * Bytes to be used for information/How many bytes were used. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, in/out: + * Information to be set/get (shfl_fsobjinfo or shfl_string). Do not + * forget to set the shfl_fsobjinfo::attr::additional for a get + * operation as well. + */ + struct vmmdev_hgcm_function_parameter info; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_INFORMATION (5) + + +/* SHFL_FN_REMOVE */ + +#define SHFL_REMOVE_FILE (0x1) +#define SHFL_REMOVE_DIR (0x2) +#define SHFL_REMOVE_SYMLINK (0x4) + +/** SHFL_FN_REMOVE Parameters structure. */ +struct shfl_remove { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * value32, in: + * remove flags (file/directory) + */ + struct vmmdev_hgcm_function_parameter flags; + +}; + +#define SHFL_CPARMS_REMOVE (3) + + +/* SHFL_FN_RENAME */ + +#define SHFL_RENAME_FILE (0x1) +#define SHFL_RENAME_DIR (0x2) +#define SHFL_RENAME_REPLACE_IF_EXISTS (0x4) + +/** SHFL_FN_RENAME Parameters structure. */ +struct shfl_rename { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string src. + */ + struct vmmdev_hgcm_function_parameter src; + + /** + * pointer, in: + * Points to struct shfl_string dest. + */ + struct vmmdev_hgcm_function_parameter dest; + + /** + * value32, in: + * rename flags (file/directory) + */ + struct vmmdev_hgcm_function_parameter flags; + +}; + +#define SHFL_CPARMS_RENAME (4) + + +/** SHFL_FN_SYMLINK Parameters structure. */ +struct shfl_symlink { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string of path for the new symlink. + */ + struct vmmdev_hgcm_function_parameter new_path; + + /** + * pointer, in: + * Points to struct shfl_string of destination for symlink. + */ + struct vmmdev_hgcm_function_parameter old_path; + + /** + * pointer, out: + * Information about created symlink. + */ + struct vmmdev_hgcm_function_parameter info; + +}; + +#define SHFL_CPARMS_SYMLINK (4) + +#endif diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c new file mode 100644 index 000000000000..675e26989376 --- /dev/null +++ b/fs/vboxsf/super.c @@ -0,0 +1,491 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Virtual File System. + * + * Module initialization/finalization + * File system registration/deregistration + * Superblock reading + * Few utility functions + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include +#include +#include +#include +#include +#include +#include +#include "vfsmod.h" + +#define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */ + +#define VBSF_MOUNT_SIGNATURE_BYTE_0 ('\000') +#define VBSF_MOUNT_SIGNATURE_BYTE_1 ('\377') +#define VBSF_MOUNT_SIGNATURE_BYTE_2 ('\376') +#define VBSF_MOUNT_SIGNATURE_BYTE_3 ('\375') + +static int follow_symlinks; +module_param(follow_symlinks, int, 0444); +MODULE_PARM_DESC(follow_symlinks, + "Let host resolve symlinks rather than showing them"); + +static DEFINE_IDA(vboxsf_bdi_ida); +static DEFINE_MUTEX(vboxsf_setup_mutex); +static bool vboxsf_setup_done; +static struct super_operations vboxsf_super_ops; /* forward declaration */ +static struct kmem_cache *vboxsf_inode_cachep; + +static char * const vboxsf_default_nls = CONFIG_NLS_DEFAULT; + +enum { opt_nls, opt_uid, opt_gid, opt_ttl, opt_dmode, opt_fmode, + opt_dmask, opt_fmask }; + +static const struct fs_parameter_spec vboxsf_fs_parameters[] = { + fsparam_string ("nls", opt_nls), + fsparam_u32 ("uid", opt_uid), + fsparam_u32 ("gid", opt_gid), + fsparam_u32 ("ttl", opt_ttl), + fsparam_u32oct ("dmode", opt_dmode), + fsparam_u32oct ("fmode", opt_fmode), + fsparam_u32oct ("dmask", opt_dmask), + fsparam_u32oct ("fmask", opt_fmask), + {} +}; + +static int vboxsf_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct vboxsf_fs_context *ctx = fc->fs_private; + struct fs_parse_result result; + kuid_t uid; + kgid_t gid; + int opt; + + opt = fs_parse(fc, vboxsf_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case opt_nls: + if (ctx->nls_name || fc->purpose != FS_CONTEXT_FOR_MOUNT) { + vbg_err("vboxsf: Cannot reconfigure nls option\n"); + return -EINVAL; + } + ctx->nls_name = param->string; + param->string = NULL; + break; + case opt_uid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + return -EINVAL; + ctx->o.uid = uid; + break; + case opt_gid: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + return -EINVAL; + ctx->o.gid = gid; + break; + case opt_ttl: + ctx->o.ttl = msecs_to_jiffies(result.uint_32); + break; + case opt_dmode: + if (result.uint_32 & ~0777) + return -EINVAL; + ctx->o.dmode = result.uint_32; + ctx->o.dmode_set = true; + break; + case opt_fmode: + if (result.uint_32 & ~0777) + return -EINVAL; + ctx->o.fmode = result.uint_32; + ctx->o.fmode_set = true; + break; + case opt_dmask: + if (result.uint_32 & ~07777) + return -EINVAL; + ctx->o.dmask = result.uint_32; + break; + case opt_fmask: + if (result.uint_32 & ~07777) + return -EINVAL; + ctx->o.fmask = result.uint_32; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct vboxsf_fs_context *ctx = fc->fs_private; + struct shfl_string *folder_name, root_path; + struct vboxsf_sbi *sbi; + struct dentry *droot; + struct inode *iroot; + char *nls_name; + size_t size; + int err; + + if (!fc->source) + return -EINVAL; + + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + + sbi->o = ctx->o; + idr_init(&sbi->ino_idr); + spin_lock_init(&sbi->ino_idr_lock); + sbi->next_generation = 1; + sbi->bdi_id = -1; + + /* Load nls if not utf8 */ + nls_name = ctx->nls_name ? ctx->nls_name : vboxsf_default_nls; + if (strcmp(nls_name, "utf8") != 0) { + if (nls_name == vboxsf_default_nls) + sbi->nls = load_nls_default(); + else + sbi->nls = load_nls(nls_name); + + if (!sbi->nls) { + vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); + err = -EINVAL; + goto fail_free; + } + } + + sbi->bdi_id = ida_simple_get(&vboxsf_bdi_ida, 0, 0, GFP_KERNEL); + if (sbi->bdi_id < 0) { + err = sbi->bdi_id; + goto fail_free; + } + + err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id); + if (err) + goto fail_free; + + /* Turn source into a shfl_string and map the folder */ + size = strlen(fc->source) + 1; + folder_name = kmalloc(SHFLSTRING_HEADER_SIZE + size, GFP_KERNEL); + if (!folder_name) { + err = -ENOMEM; + goto fail_free; + } + folder_name->size = size; + folder_name->length = size - 1; + strlcpy(folder_name->string.utf8, fc->source, size); + err = vboxsf_map_folder(folder_name, &sbi->root); + kfree(folder_name); + if (err) { + vbg_err("vboxsf: Host rejected mount of '%s' with error %d\n", + fc->source, err); + goto fail_free; + } + + root_path.length = 1; + root_path.size = 2; + root_path.string.utf8[0] = '/'; + root_path.string.utf8[1] = 0; + err = vboxsf_stat(sbi, &root_path, &sbi->root_info); + if (err) + goto fail_unmap; + + sb->s_magic = VBOXSF_SUPER_MAGIC; + sb->s_blocksize = 1024; + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_op = &vboxsf_super_ops; + sb->s_d_op = &vboxsf_dentry_ops; + + iroot = iget_locked(sb, 0); + if (!iroot) { + err = -ENOMEM; + goto fail_unmap; + } + vboxsf_init_inode(sbi, iroot, &sbi->root_info); + unlock_new_inode(iroot); + + droot = d_make_root(iroot); + if (!droot) { + err = -ENOMEM; + goto fail_unmap; + } + + sb->s_root = droot; + sb->s_fs_info = sbi; + return 0; + +fail_unmap: + vboxsf_unmap_folder(sbi->root); +fail_free: + if (sbi->bdi_id >= 0) + ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); + if (sbi->nls) + unload_nls(sbi->nls); + idr_destroy(&sbi->ino_idr); + kfree(sbi); + return err; +} + +static void vboxsf_inode_init_once(void *data) +{ + struct vboxsf_inode *sf_i = data; + + mutex_init(&sf_i->handle_list_mutex); + inode_init_once(&sf_i->vfs_inode); +} + +static struct inode *vboxsf_alloc_inode(struct super_block *sb) +{ + struct vboxsf_inode *sf_i; + + sf_i = kmem_cache_alloc(vboxsf_inode_cachep, GFP_NOFS); + if (!sf_i) + return NULL; + + sf_i->force_restat = 0; + INIT_LIST_HEAD(&sf_i->handle_list); + + return &sf_i->vfs_inode; +} + +static void vboxsf_free_inode(struct inode *inode) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); + unsigned long flags; + + spin_lock_irqsave(&sbi->ino_idr_lock, flags); + idr_remove(&sbi->ino_idr, inode->i_ino); + spin_unlock_irqrestore(&sbi->ino_idr_lock, flags); + kmem_cache_free(vboxsf_inode_cachep, VBOXSF_I(inode)); +} + +static void vboxsf_put_super(struct super_block *sb) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(sb); + + vboxsf_unmap_folder(sbi->root); + if (sbi->bdi_id >= 0) + ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); + if (sbi->nls) + unload_nls(sbi->nls); + + /* + * vboxsf_free_inode uses the idr, make sure all delayed rcu free + * inodes are flushed. + */ + rcu_barrier(); + idr_destroy(&sbi->ino_idr); + kfree(sbi); +} + +static int vboxsf_statfs(struct dentry *dentry, struct kstatfs *stat) +{ + struct super_block *sb = dentry->d_sb; + struct shfl_volinfo shfl_volinfo; + struct vboxsf_sbi *sbi; + u32 buf_len; + int err; + + sbi = VBOXSF_SBI(sb); + buf_len = sizeof(shfl_volinfo); + err = vboxsf_fsinfo(sbi->root, 0, SHFL_INFO_GET | SHFL_INFO_VOLUME, + &buf_len, &shfl_volinfo); + if (err) + return err; + + stat->f_type = VBOXSF_SUPER_MAGIC; + stat->f_bsize = shfl_volinfo.bytes_per_allocation_unit; + + do_div(shfl_volinfo.total_allocation_bytes, + shfl_volinfo.bytes_per_allocation_unit); + stat->f_blocks = shfl_volinfo.total_allocation_bytes; + + do_div(shfl_volinfo.available_allocation_bytes, + shfl_volinfo.bytes_per_allocation_unit); + stat->f_bfree = shfl_volinfo.available_allocation_bytes; + stat->f_bavail = shfl_volinfo.available_allocation_bytes; + + stat->f_files = 1000; + /* + * Don't return 0 here since the guest may then think that it is not + * possible to create any more files. + */ + stat->f_ffree = 1000000; + stat->f_fsid.val[0] = 0; + stat->f_fsid.val[1] = 0; + stat->f_namelen = 255; + return 0; +} + +static struct super_operations vboxsf_super_ops = { + .alloc_inode = vboxsf_alloc_inode, + .free_inode = vboxsf_free_inode, + .put_super = vboxsf_put_super, + .statfs = vboxsf_statfs, +}; + +static int vboxsf_setup(void) +{ + int err; + + mutex_lock(&vboxsf_setup_mutex); + + if (vboxsf_setup_done) + goto success; + + vboxsf_inode_cachep = + kmem_cache_create("vboxsf_inode_cache", + sizeof(struct vboxsf_inode), 0, + (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | + SLAB_ACCOUNT), + vboxsf_inode_init_once); + if (!vboxsf_inode_cachep) { + err = -ENOMEM; + goto fail_nomem; + } + + err = vboxsf_connect(); + if (err) { + vbg_err("vboxsf: err %d connecting to guest PCI-device\n", err); + vbg_err("vboxsf: make sure you are inside a VirtualBox VM\n"); + vbg_err("vboxsf: and check dmesg for vboxguest errors\n"); + goto fail_free_cache; + } + + err = vboxsf_set_utf8(); + if (err) { + vbg_err("vboxsf_setutf8 error %d\n", err); + goto fail_disconnect; + } + + if (!follow_symlinks) { + err = vboxsf_set_symlinks(); + if (err) + vbg_warn("vboxsf: Unable to show symlinks: %d\n", err); + } + + vboxsf_setup_done = true; +success: + mutex_unlock(&vboxsf_setup_mutex); + return 0; + +fail_disconnect: + vboxsf_disconnect(); +fail_free_cache: + kmem_cache_destroy(vboxsf_inode_cachep); +fail_nomem: + mutex_unlock(&vboxsf_setup_mutex); + return err; +} + +static int vboxsf_parse_monolithic(struct fs_context *fc, void *data) +{ + char *options = data; + + if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 && + options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 && + options[2] == VBSF_MOUNT_SIGNATURE_BYTE_2 && + options[3] == VBSF_MOUNT_SIGNATURE_BYTE_3) { + vbg_err("vboxsf: Old binary mount data not supported, remove obsolete mount.vboxsf and/or update your VBoxService.\n"); + return -EINVAL; + } + + return generic_parse_monolithic(fc, data); +} + +static int vboxsf_get_tree(struct fs_context *fc) +{ + int err; + + err = vboxsf_setup(); + if (err) + return err; + + return get_tree_nodev(fc, vboxsf_fill_super); +} + +static int vboxsf_reconfigure(struct fs_context *fc) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(fc->root->d_sb); + struct vboxsf_fs_context *ctx = fc->fs_private; + struct inode *iroot = fc->root->d_sb->s_root->d_inode; + + /* Apply changed options to the root inode */ + sbi->o = ctx->o; + vboxsf_init_inode(sbi, iroot, &sbi->root_info); + + return 0; +} + +static void vboxsf_free_fc(struct fs_context *fc) +{ + struct vboxsf_fs_context *ctx = fc->fs_private; + + kfree(ctx->nls_name); + kfree(ctx); +} + +static const struct fs_context_operations vboxsf_context_ops = { + .free = vboxsf_free_fc, + .parse_param = vboxsf_parse_param, + .parse_monolithic = vboxsf_parse_monolithic, + .get_tree = vboxsf_get_tree, + .reconfigure = vboxsf_reconfigure, +}; + +static int vboxsf_init_fs_context(struct fs_context *fc) +{ + struct vboxsf_fs_context *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + current_uid_gid(&ctx->o.uid, &ctx->o.gid); + + fc->fs_private = ctx; + fc->ops = &vboxsf_context_ops; + return 0; +} + +static struct file_system_type vboxsf_fs_type = { + .owner = THIS_MODULE, + .name = "vboxsf", + .init_fs_context = vboxsf_init_fs_context, + .kill_sb = kill_anon_super +}; + +/* Module initialization/finalization handlers */ +static int __init vboxsf_init(void) +{ + return register_filesystem(&vboxsf_fs_type); +} + +static void __exit vboxsf_fini(void) +{ + unregister_filesystem(&vboxsf_fs_type); + + mutex_lock(&vboxsf_setup_mutex); + if (vboxsf_setup_done) { + vboxsf_disconnect(); + /* + * Make sure all delayed rcu free inodes are flushed + * before we destroy the cache. + */ + rcu_barrier(); + kmem_cache_destroy(vboxsf_inode_cachep); + } + mutex_unlock(&vboxsf_setup_mutex); +} + +module_init(vboxsf_init); +module_exit(vboxsf_fini); + +MODULE_DESCRIPTION("Oracle VM VirtualBox Module for Host File System Access"); +MODULE_AUTHOR("Oracle Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_FS("vboxsf"); diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c new file mode 100644 index 000000000000..96bd160da48b --- /dev/null +++ b/fs/vboxsf/utils.c @@ -0,0 +1,551 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Utility functions. + * Mainly conversion from/to VirtualBox/Linux data structures. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include +#include +#include +#include +#include "vfsmod.h" + +struct inode *vboxsf_new_inode(struct super_block *sb) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(sb); + struct inode *inode; + unsigned long flags; + int cursor, ret; + u32 gen; + + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + idr_preload(GFP_KERNEL); + spin_lock_irqsave(&sbi->ino_idr_lock, flags); + cursor = idr_get_cursor(&sbi->ino_idr); + ret = idr_alloc_cyclic(&sbi->ino_idr, inode, 1, 0, GFP_ATOMIC); + if (ret >= 0 && ret < cursor) + sbi->next_generation++; + gen = sbi->next_generation; + spin_unlock_irqrestore(&sbi->ino_idr_lock, flags); + idr_preload_end(); + + if (ret < 0) { + iput(inode); + return ERR_PTR(ret); + } + + inode->i_ino = ret; + inode->i_generation = gen; + return inode; +} + +/* set [inode] attributes based on [info], uid/gid based on [sbi] */ +void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, + const struct shfl_fsobjinfo *info) +{ + const struct shfl_fsobjattr *attr; + s64 allocated; + int mode; + + attr = &info->attr; + +#define mode_set(r) ((attr->mode & (SHFL_UNIX_##r)) ? (S_##r) : 0) + + mode = mode_set(IRUSR); + mode |= mode_set(IWUSR); + mode |= mode_set(IXUSR); + + mode |= mode_set(IRGRP); + mode |= mode_set(IWGRP); + mode |= mode_set(IXGRP); + + mode |= mode_set(IROTH); + mode |= mode_set(IWOTH); + mode |= mode_set(IXOTH); + +#undef mode_set + + /* We use the host-side values for these */ + inode->i_flags |= S_NOATIME | S_NOCMTIME; + inode->i_mapping->a_ops = &vboxsf_reg_aops; + + if (SHFL_IS_DIRECTORY(attr->mode)) { + inode->i_mode = sbi->o.dmode_set ? sbi->o.dmode : mode; + inode->i_mode &= ~sbi->o.dmask; + inode->i_mode |= S_IFDIR; + inode->i_op = &vboxsf_dir_iops; + inode->i_fop = &vboxsf_dir_fops; + /* + * XXX: this probably should be set to the number of entries + * in the directory plus two (. ..) + */ + set_nlink(inode, 1); + } else if (SHFL_IS_SYMLINK(attr->mode)) { + inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode; + inode->i_mode &= ~sbi->o.fmask; + inode->i_mode |= S_IFLNK; + inode->i_op = &vboxsf_lnk_iops; + set_nlink(inode, 1); + } else { + inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode; + inode->i_mode &= ~sbi->o.fmask; + inode->i_mode |= S_IFREG; + inode->i_op = &vboxsf_reg_iops; + inode->i_fop = &vboxsf_reg_fops; + set_nlink(inode, 1); + } + + inode->i_uid = sbi->o.uid; + inode->i_gid = sbi->o.gid; + + inode->i_size = info->size; + inode->i_blkbits = 12; + /* i_blocks always in units of 512 bytes! */ + allocated = info->allocated + 511; + do_div(allocated, 512); + inode->i_blocks = allocated; + + inode->i_atime = ns_to_timespec64( + info->access_time.ns_relative_to_unix_epoch); + inode->i_ctime = ns_to_timespec64( + info->change_time.ns_relative_to_unix_epoch); + inode->i_mtime = ns_to_timespec64( + info->modification_time.ns_relative_to_unix_epoch); +} + +int vboxsf_create_at_dentry(struct dentry *dentry, + struct shfl_createparms *params) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); + struct shfl_string *path; + int err; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + err = vboxsf_create(sbi->root, path, params); + __putname(path); + + return err; +} + +int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path, + struct shfl_fsobjinfo *info) +{ + struct shfl_createparms params = {}; + int err; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_LOOKUP | SHFL_CF_ACT_FAIL_IF_NEW; + + err = vboxsf_create(sbi->root, path, ¶ms); + if (err) + return err; + + if (params.result != SHFL_FILE_EXISTS) + return -ENOENT; + + if (info) + *info = params.info; + + return 0; +} + +int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); + struct shfl_string *path; + int err; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + err = vboxsf_stat(sbi, path, info); + __putname(path); + return err; +} + +int vboxsf_inode_revalidate(struct dentry *dentry) +{ + struct vboxsf_sbi *sbi; + struct vboxsf_inode *sf_i; + struct shfl_fsobjinfo info; + struct timespec64 prev_mtime; + struct inode *inode; + int err; + + if (!dentry || !d_really_is_positive(dentry)) + return -EINVAL; + + inode = d_inode(dentry); + prev_mtime = inode->i_mtime; + sf_i = VBOXSF_I(inode); + sbi = VBOXSF_SBI(dentry->d_sb); + if (!sf_i->force_restat) { + if (time_before(jiffies, dentry->d_time + sbi->o.ttl)) + return 0; + } + + err = vboxsf_stat_dentry(dentry, &info); + if (err) + return err; + + dentry->d_time = jiffies; + sf_i->force_restat = 0; + vboxsf_init_inode(sbi, inode, &info); + + /* + * If the file was changed on the host side we need to invalidate the + * page-cache for it. Note this also gets triggered by our own writes, + * this is unavoidable. + */ + if (timespec64_compare(&inode->i_mtime, &prev_mtime) > 0) + invalidate_inode_pages2(inode->i_mapping); + + return 0; +} + +int vboxsf_getattr(const struct path *path, struct kstat *kstat, + u32 request_mask, unsigned int flags) +{ + int err; + struct dentry *dentry = path->dentry; + struct inode *inode = d_inode(dentry); + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + + switch (flags & AT_STATX_SYNC_TYPE) { + case AT_STATX_DONT_SYNC: + err = 0; + break; + case AT_STATX_FORCE_SYNC: + sf_i->force_restat = 1; + /* fall-through */ + default: + err = vboxsf_inode_revalidate(dentry); + } + if (err) + return err; + + generic_fillattr(d_inode(dentry), kstat); + return 0; +} + +int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry)); + struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); + struct shfl_createparms params = {}; + struct shfl_fsobjinfo info = {}; + u32 buf_len; + int err; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_ACT_OPEN_IF_EXISTS | + SHFL_CF_ACT_FAIL_IF_NEW | + SHFL_CF_ACCESS_ATTR_WRITE; + + /* this is at least required for Posix hosts */ + if (iattr->ia_valid & ATTR_SIZE) + params.create_flags |= SHFL_CF_ACCESS_WRITE; + + err = vboxsf_create_at_dentry(dentry, ¶ms); + if (err || params.result != SHFL_FILE_EXISTS) + return err ? err : -ENOENT; + +#define mode_set(r) ((iattr->ia_mode & (S_##r)) ? SHFL_UNIX_##r : 0) + + /* + * Setting the file size and setting the other attributes has to + * be handled separately. + */ + if (iattr->ia_valid & (ATTR_MODE | ATTR_ATIME | ATTR_MTIME)) { + if (iattr->ia_valid & ATTR_MODE) { + info.attr.mode = mode_set(IRUSR); + info.attr.mode |= mode_set(IWUSR); + info.attr.mode |= mode_set(IXUSR); + info.attr.mode |= mode_set(IRGRP); + info.attr.mode |= mode_set(IWGRP); + info.attr.mode |= mode_set(IXGRP); + info.attr.mode |= mode_set(IROTH); + info.attr.mode |= mode_set(IWOTH); + info.attr.mode |= mode_set(IXOTH); + + if (iattr->ia_mode & S_IFDIR) + info.attr.mode |= SHFL_TYPE_DIRECTORY; + else + info.attr.mode |= SHFL_TYPE_FILE; + } + + if (iattr->ia_valid & ATTR_ATIME) + info.access_time.ns_relative_to_unix_epoch = + timespec64_to_ns(&iattr->ia_atime); + + if (iattr->ia_valid & ATTR_MTIME) + info.modification_time.ns_relative_to_unix_epoch = + timespec64_to_ns(&iattr->ia_mtime); + + /* + * Ignore ctime (inode change time) as it can't be set + * from userland anyway. + */ + + buf_len = sizeof(info); + err = vboxsf_fsinfo(sbi->root, params.handle, + SHFL_INFO_SET | SHFL_INFO_FILE, &buf_len, + &info); + if (err) { + vboxsf_close(sbi->root, params.handle); + return err; + } + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + } + +#undef mode_set + + if (iattr->ia_valid & ATTR_SIZE) { + memset(&info, 0, sizeof(info)); + info.size = iattr->ia_size; + buf_len = sizeof(info); + err = vboxsf_fsinfo(sbi->root, params.handle, + SHFL_INFO_SET | SHFL_INFO_SIZE, &buf_len, + &info); + if (err) { + vboxsf_close(sbi->root, params.handle); + return err; + } + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + } + + vboxsf_close(sbi->root, params.handle); + + /* Update the inode with what the host has actually given us. */ + if (sf_i->force_restat) + vboxsf_inode_revalidate(dentry); + + return 0; +} + +/* + * [dentry] contains string encoded in coding system that corresponds + * to [sbi]->nls, we must convert it to UTF8 here. + * Returns a shfl_string allocated through __getname (must be freed using + * __putname), or an ERR_PTR on error. + */ +struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi, + struct dentry *dentry) +{ + struct shfl_string *shfl_path; + int path_len, out_len, nb; + char *buf, *path; + wchar_t uni; + u8 *out; + + buf = __getname(); + if (!buf) + return ERR_PTR(-ENOMEM); + + path = dentry_path_raw(dentry, buf, PATH_MAX); + if (IS_ERR(path)) { + __putname(buf); + return ERR_CAST(path); + } + path_len = strlen(path); + + if (sbi->nls) { + shfl_path = __getname(); + if (!shfl_path) { + __putname(buf); + return ERR_PTR(-ENOMEM); + } + + out = shfl_path->string.utf8; + out_len = PATH_MAX - SHFLSTRING_HEADER_SIZE - 1; + + while (path_len) { + nb = sbi->nls->char2uni(path, path_len, &uni); + if (nb < 0) { + __putname(shfl_path); + __putname(buf); + return ERR_PTR(-EINVAL); + } + path += nb; + path_len -= nb; + + nb = utf32_to_utf8(uni, out, out_len); + if (nb < 0) { + __putname(shfl_path); + __putname(buf); + return ERR_PTR(-ENAMETOOLONG); + } + out += nb; + out_len -= nb; + } + *out = 0; + shfl_path->length = out - shfl_path->string.utf8; + shfl_path->size = shfl_path->length + 1; + __putname(buf); + } else { + if ((SHFLSTRING_HEADER_SIZE + path_len + 1) > PATH_MAX) { + __putname(buf); + return ERR_PTR(-ENAMETOOLONG); + } + /* + * dentry_path stores the name at the end of buf, but the + * shfl_string string we return must be properly aligned. + */ + shfl_path = (struct shfl_string *)buf; + memmove(shfl_path->string.utf8, path, path_len); + shfl_path->string.utf8[path_len] = 0; + shfl_path->length = path_len; + shfl_path->size = path_len + 1; + } + + return shfl_path; +} + +int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, + const unsigned char *utf8_name, size_t utf8_len) +{ + const char *in; + char *out; + size_t out_len; + size_t out_bound_len; + size_t in_bound_len; + + in = utf8_name; + in_bound_len = utf8_len; + + out = name; + out_len = 0; + /* Reserve space for terminating 0 */ + out_bound_len = name_bound_len - 1; + + while (in_bound_len) { + int nb; + unicode_t uni; + + nb = utf8_to_utf32(in, in_bound_len, &uni); + if (nb < 0) + return -EINVAL; + + in += nb; + in_bound_len -= nb; + + nb = sbi->nls->uni2char(uni, out, out_bound_len); + if (nb < 0) + return nb; + + out += nb; + out_bound_len -= nb; + out_len += nb; + } + + *out = 0; + + return 0; +} + +static struct vboxsf_dir_buf *vboxsf_dir_buf_alloc(struct list_head *list) +{ + struct vboxsf_dir_buf *b; + + b = kmalloc(sizeof(*b), GFP_KERNEL); + if (!b) + return NULL; + + b->buf = kmalloc(DIR_BUFFER_SIZE, GFP_KERNEL); + if (!b->buf) { + kfree(b); + return NULL; + } + + b->entries = 0; + b->used = 0; + b->free = DIR_BUFFER_SIZE; + list_add(&b->head, list); + + return b; +} + +static void vboxsf_dir_buf_free(struct vboxsf_dir_buf *b) +{ + list_del(&b->head); + kfree(b->buf); + kfree(b); +} + +struct vboxsf_dir_info *vboxsf_dir_info_alloc(void) +{ + struct vboxsf_dir_info *p; + + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return NULL; + + INIT_LIST_HEAD(&p->info_list); + return p; +} + +void vboxsf_dir_info_free(struct vboxsf_dir_info *p) +{ + struct list_head *list, *pos, *tmp; + + list = &p->info_list; + list_for_each_safe(pos, tmp, list) { + struct vboxsf_dir_buf *b; + + b = list_entry(pos, struct vboxsf_dir_buf, head); + vboxsf_dir_buf_free(b); + } + kfree(p); +} + +int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d, + u64 handle) +{ + struct vboxsf_dir_buf *b; + u32 entries, size; + int err = 0; + void *buf; + + /* vboxsf_dirinfo returns 1 on end of dir */ + while (err == 0) { + b = vboxsf_dir_buf_alloc(&sf_d->info_list); + if (!b) { + err = -ENOMEM; + break; + } + + buf = b->buf; + size = b->free; + + err = vboxsf_dirinfo(sbi->root, handle, NULL, 0, 0, + &size, buf, &entries); + if (err < 0) + break; + + b->entries += entries; + b->free -= size; + b->used += size; + } + + if (b && b->used == 0) + vboxsf_dir_buf_free(b); + + /* -EILSEQ means the host could not translate a filename, ignore */ + if (err > 0 || err == -EILSEQ) + err = 0; + + return err; +} diff --git a/fs/vboxsf/vboxsf_wrappers.c b/fs/vboxsf/vboxsf_wrappers.c new file mode 100644 index 000000000000..bfc78a097dae --- /dev/null +++ b/fs/vboxsf/vboxsf_wrappers.c @@ -0,0 +1,371 @@ +// SPDX-License-Identifier: MIT +/* + * Wrapper functions for the shfl host calls. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include +#include +#include +#include +#include "vfsmod.h" + +#define SHFL_REQUEST \ + (VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV_OTHER | \ + VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN) + +static u32 vboxsf_client_id; + +int vboxsf_connect(void) +{ + struct vbg_dev *gdev; + struct vmmdev_hgcm_service_location loc; + int err, vbox_status; + + loc.type = VMMDEV_HGCM_LOC_LOCALHOST_EXISTING; + strcpy(loc.u.localhost.service_name, "VBoxSharedFolders"); + + gdev = vbg_get_gdev(); + if (IS_ERR(gdev)) + return -ENODEV; /* No guest-device */ + + err = vbg_hgcm_connect(gdev, SHFL_REQUEST, &loc, + &vboxsf_client_id, &vbox_status); + vbg_put_gdev(gdev); + + return err ? err : vbg_status_code_to_errno(vbox_status); +} + +void vboxsf_disconnect(void) +{ + struct vbg_dev *gdev; + int vbox_status; + + gdev = vbg_get_gdev(); + if (IS_ERR(gdev)) + return; /* guest-device is gone, already disconnected */ + + vbg_hgcm_disconnect(gdev, SHFL_REQUEST, vboxsf_client_id, &vbox_status); + vbg_put_gdev(gdev); +} + +static int vboxsf_call(u32 function, void *parms, u32 parm_count, int *status) +{ + struct vbg_dev *gdev; + int err, vbox_status; + + gdev = vbg_get_gdev(); + if (IS_ERR(gdev)) + return -ESHUTDOWN; /* guest-dev removed underneath us */ + + err = vbg_hgcm_call(gdev, SHFL_REQUEST, vboxsf_client_id, function, + U32_MAX, parms, parm_count, &vbox_status); + vbg_put_gdev(gdev); + + if (err < 0) + return err; + + if (status) + *status = vbox_status; + + return vbg_status_code_to_errno(vbox_status); +} + +int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root) +{ + struct shfl_map_folder parms; + int err, status; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.path.u.pointer.size = shfl_string_buf_size(folder_name); + parms.path.u.pointer.u.linear_addr = (uintptr_t)folder_name; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = 0; + + parms.delimiter.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.delimiter.u.value32 = '/'; + + parms.case_sensitive.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.case_sensitive.u.value32 = 1; + + err = vboxsf_call(SHFL_FN_MAP_FOLDER, &parms, SHFL_CPARMS_MAP_FOLDER, + &status); + if (err == -ENOSYS && status == VERR_NOT_IMPLEMENTED) + vbg_err("%s: Error host is too old\n", __func__); + + *root = parms.root.u.value32; + return err; +} + +int vboxsf_unmap_folder(u32 root) +{ + struct shfl_unmap_folder parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + return vboxsf_call(SHFL_FN_UNMAP_FOLDER, &parms, + SHFL_CPARMS_UNMAP_FOLDER, NULL); +} + +/** + * vboxsf_create - Create a new file or folder + * @root: Root of the shared folder in which to create the file + * @parsed_path: The path of the file or folder relative to the shared folder + * @param: create_parms Parameters for file/folder creation. + * + * Create a new file or folder or open an existing one in a shared folder. + * Note this function always returns 0 / success unless an exceptional condition + * occurs - out of memory, invalid arguments, etc. If the file or folder could + * not be opened or created, create_parms->handle will be set to + * SHFL_HANDLE_NIL on return. In this case the value in create_parms->result + * provides information as to why (e.g. SHFL_FILE_EXISTS), create_parms->result + * is also set on success as additional information. + * + * Returns: + * 0 or negative errno value. + */ +int vboxsf_create(u32 root, struct shfl_string *parsed_path, + struct shfl_createparms *create_parms) +{ + struct shfl_create parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + + parms.parms.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.parms.u.pointer.size = sizeof(struct shfl_createparms); + parms.parms.u.pointer.u.linear_addr = (uintptr_t)create_parms; + + return vboxsf_call(SHFL_FN_CREATE, &parms, SHFL_CPARMS_CREATE, NULL); +} + +int vboxsf_close(u32 root, u64 handle) +{ + struct shfl_close parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + + return vboxsf_call(SHFL_FN_CLOSE, &parms, SHFL_CPARMS_CLOSE, NULL); +} + +int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags) +{ + struct shfl_remove parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + + return vboxsf_call(SHFL_FN_REMOVE, &parms, SHFL_CPARMS_REMOVE, NULL); +} + +int vboxsf_rename(u32 root, struct shfl_string *src_path, + struct shfl_string *dest_path, u32 flags) +{ + struct shfl_rename parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.src.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.src.u.pointer.size = shfl_string_buf_size(src_path); + parms.src.u.pointer.u.linear_addr = (uintptr_t)src_path; + + parms.dest.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.dest.u.pointer.size = shfl_string_buf_size(dest_path); + parms.dest.u.pointer.u.linear_addr = (uintptr_t)dest_path; + + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + + return vboxsf_call(SHFL_FN_RENAME, &parms, SHFL_CPARMS_RENAME, NULL); +} + +int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf) +{ + struct shfl_read parms; + int err; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.offset.u.value64 = offset; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.buffer.u.pointer.size = *buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + err = vboxsf_call(SHFL_FN_READ, &parms, SHFL_CPARMS_READ, NULL); + + *buf_len = parms.cb.u.value32; + return err; +} + +int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf) +{ + struct shfl_write parms; + int err; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.offset.u.value64 = offset; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.buffer.u.pointer.size = *buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + err = vboxsf_call(SHFL_FN_WRITE, &parms, SHFL_CPARMS_WRITE, NULL); + + *buf_len = parms.cb.u.value32; + return err; +} + +/* Returns 0 on success, 1 on end-of-dir, negative errno otherwise */ +int vboxsf_dirinfo(u32 root, u64 handle, + struct shfl_string *parsed_path, u32 flags, u32 index, + u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count) +{ + struct shfl_list parms; + int err, status; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + if (parsed_path) { + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + } else { + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_IN; + parms.path.u.pointer.size = 0; + parms.path.u.pointer.u.linear_addr = 0; + } + + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.buffer.u.pointer.size = *buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + parms.resume_point.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.resume_point.u.value32 = index; + parms.file_count.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.file_count.u.value32 = 0; /* out parameter only */ + + err = vboxsf_call(SHFL_FN_LIST, &parms, SHFL_CPARMS_LIST, &status); + if (err == -ENODATA && status == VERR_NO_MORE_FILES) + err = 1; + + *buf_len = parms.cb.u.value32; + *file_count = parms.file_count.u.value32; + return err; +} + +int vboxsf_fsinfo(u32 root, u64 handle, u32 flags, + u32 *buf_len, void *buf) +{ + struct shfl_information parms; + int err; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.info.u.pointer.size = *buf_len; + parms.info.u.pointer.u.linear_addr = (uintptr_t)buf; + + err = vboxsf_call(SHFL_FN_INFORMATION, &parms, SHFL_CPARMS_INFORMATION, + NULL); + + *buf_len = parms.cb.u.value32; + return err; +} + +int vboxsf_readlink(u32 root, struct shfl_string *parsed_path, + u32 buf_len, u8 *buf) +{ + struct shfl_readLink parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.buffer.u.pointer.size = buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + return vboxsf_call(SHFL_FN_READLINK, &parms, SHFL_CPARMS_READLINK, + NULL); +} + +int vboxsf_symlink(u32 root, struct shfl_string *new_path, + struct shfl_string *old_path, struct shfl_fsobjinfo *buf) +{ + struct shfl_symlink parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.new_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.new_path.u.pointer.size = shfl_string_buf_size(new_path); + parms.new_path.u.pointer.u.linear_addr = (uintptr_t)new_path; + + parms.old_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.old_path.u.pointer.size = shfl_string_buf_size(old_path); + parms.old_path.u.pointer.u.linear_addr = (uintptr_t)old_path; + + parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.info.u.pointer.size = sizeof(struct shfl_fsobjinfo); + parms.info.u.pointer.u.linear_addr = (uintptr_t)buf; + + return vboxsf_call(SHFL_FN_SYMLINK, &parms, SHFL_CPARMS_SYMLINK, NULL); +} + +int vboxsf_set_utf8(void) +{ + return vboxsf_call(SHFL_FN_SET_UTF8, NULL, 0, NULL); +} + +int vboxsf_set_symlinks(void) +{ + return vboxsf_call(SHFL_FN_SET_SYMLINKS, NULL, 0, NULL); +} diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h new file mode 100644 index 000000000000..18f95b00fc33 --- /dev/null +++ b/fs/vboxsf/vfsmod.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: MIT */ +/* + * VirtualBox Guest Shared Folders support: module header. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#ifndef VFSMOD_H +#define VFSMOD_H + +#include +#include +#include "shfl_hostintf.h" + +#define DIR_BUFFER_SIZE SZ_16K + +/* The cast is to prevent assignment of void * to pointers of arbitrary type */ +#define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info) +#define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode) + +struct vboxsf_options { + unsigned long ttl; + kuid_t uid; + kgid_t gid; + bool dmode_set; + bool fmode_set; + umode_t dmode; + umode_t fmode; + umode_t dmask; + umode_t fmask; +}; + +struct vboxsf_fs_context { + struct vboxsf_options o; + char *nls_name; +}; + +/* per-shared folder information */ +struct vboxsf_sbi { + struct vboxsf_options o; + struct shfl_fsobjinfo root_info; + struct idr ino_idr; + spinlock_t ino_idr_lock; /* This protects ino_idr */ + struct nls_table *nls; + u32 next_generation; + u32 root; + int bdi_id; +}; + +/* per-inode information */ +struct vboxsf_inode { + /* some information was changed, update data on next revalidate */ + int force_restat; + /* list of open handles for this inode + lock protecting it */ + struct list_head handle_list; + /* This mutex protects handle_list accesses */ + struct mutex handle_list_mutex; + /* The VFS inode struct */ + struct inode vfs_inode; +}; + +struct vboxsf_dir_info { + struct list_head info_list; +}; + +struct vboxsf_dir_buf { + size_t entries; + size_t free; + size_t used; + void *buf; + struct list_head head; +}; + +/* globals */ +extern const struct inode_operations vboxsf_dir_iops; +extern const struct inode_operations vboxsf_lnk_iops; +extern const struct inode_operations vboxsf_reg_iops; +extern const struct file_operations vboxsf_dir_fops; +extern const struct file_operations vboxsf_reg_fops; +extern const struct address_space_operations vboxsf_reg_aops; +extern const struct dentry_operations vboxsf_dentry_ops; + +/* from utils.c */ +struct inode *vboxsf_new_inode(struct super_block *sb); +void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, + const struct shfl_fsobjinfo *info); +int vboxsf_create_at_dentry(struct dentry *dentry, + struct shfl_createparms *params); +int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path, + struct shfl_fsobjinfo *info); +int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info); +int vboxsf_inode_revalidate(struct dentry *dentry); +int vboxsf_getattr(const struct path *path, struct kstat *kstat, + u32 request_mask, unsigned int query_flags); +int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr); +struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi, + struct dentry *dentry); +int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, + const unsigned char *utf8_name, size_t utf8_len); +struct vboxsf_dir_info *vboxsf_dir_info_alloc(void); +void vboxsf_dir_info_free(struct vboxsf_dir_info *p); +int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d, + u64 handle); + +/* from vboxsf_wrappers.c */ +int vboxsf_connect(void); +void vboxsf_disconnect(void); + +int vboxsf_create(u32 root, struct shfl_string *parsed_path, + struct shfl_createparms *create_parms); + +int vboxsf_close(u32 root, u64 handle); +int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags); +int vboxsf_rename(u32 root, struct shfl_string *src_path, + struct shfl_string *dest_path, u32 flags); + +int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf); +int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf); + +int vboxsf_dirinfo(u32 root, u64 handle, + struct shfl_string *parsed_path, u32 flags, u32 index, + u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count); +int vboxsf_fsinfo(u32 root, u64 handle, u32 flags, + u32 *buf_len, void *buf); + +int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root); +int vboxsf_unmap_folder(u32 root); + +int vboxsf_readlink(u32 root, struct shfl_string *parsed_path, + u32 buf_len, u8 *buf); +int vboxsf_symlink(u32 root, struct shfl_string *new_path, + struct shfl_string *old_path, struct shfl_fsobjinfo *buf); + +int vboxsf_set_utf8(void); +int vboxsf_set_symlinks(void); + +#endif diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig new file mode 100644 index 000000000000..fb87ad372e29 --- /dev/null +++ b/fs/zonefs/Kconfig @@ -0,0 +1,9 @@ +config ZONEFS_FS + tristate "zonefs filesystem support" + depends on BLOCK + depends on BLK_DEV_ZONED + help + zonefs is a simple file system which exposes zones of a zoned block + device (e.g. host-managed or host-aware SMR disk drives) as files. + + If unsure, say N. diff --git a/fs/zonefs/Makefile b/fs/zonefs/Makefile new file mode 100644 index 000000000000..75a380aa1ae1 --- /dev/null +++ b/fs/zonefs/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_ZONEFS_FS) += zonefs.o + +zonefs-y := super.o diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c new file mode 100644 index 000000000000..8bc6ef82d693 --- /dev/null +++ b/fs/zonefs/super.c @@ -0,0 +1,1439 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Simple file system for zoned block devices exposing zones as files. + * + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "zonefs.h" + +static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, + unsigned int flags, struct iomap *iomap, + struct iomap *srcmap) +{ + struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + loff_t isize; + + /* All I/Os should always be within the file maximum size */ + if (WARN_ON_ONCE(offset + length > zi->i_max_size)) + return -EIO; + + /* + * Sequential zones can only accept direct writes. This is already + * checked when writes are issued, so warn if we see a page writeback + * operation. + */ + if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ && + (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT))) + return -EIO; + + /* + * For conventional zones, all blocks are always mapped. For sequential + * zones, all blocks after always mapped below the inode size (zone + * write pointer) and unwriten beyond. + */ + mutex_lock(&zi->i_truncate_mutex); + isize = i_size_read(inode); + if (offset >= isize) + iomap->type = IOMAP_UNWRITTEN; + else + iomap->type = IOMAP_MAPPED; + if (flags & IOMAP_WRITE) + length = zi->i_max_size - offset; + else + length = min(length, isize - offset); + mutex_unlock(&zi->i_truncate_mutex); + + iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize); + iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset; + iomap->bdev = inode->i_sb->s_bdev; + iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset; + + return 0; +} + +static const struct iomap_ops zonefs_iomap_ops = { + .iomap_begin = zonefs_iomap_begin, +}; + +static int zonefs_readpage(struct file *unused, struct page *page) +{ + return iomap_readpage(page, &zonefs_iomap_ops); +} + +static int zonefs_readpages(struct file *unused, struct address_space *mapping, + struct list_head *pages, unsigned int nr_pages) +{ + return iomap_readpages(mapping, pages, nr_pages, &zonefs_iomap_ops); +} + +/* + * Map blocks for page writeback. This is used only on conventional zone files, + * which implies that the page range can only be within the fixed inode size. + */ +static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc, + struct inode *inode, loff_t offset) +{ + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV)) + return -EIO; + if (WARN_ON_ONCE(offset >= i_size_read(inode))) + return -EIO; + + /* If the mapping is already OK, nothing needs to be done */ + if (offset >= wpc->iomap.offset && + offset < wpc->iomap.offset + wpc->iomap.length) + return 0; + + return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset, + IOMAP_WRITE, &wpc->iomap, NULL); +} + +static const struct iomap_writeback_ops zonefs_writeback_ops = { + .map_blocks = zonefs_map_blocks, +}; + +static int zonefs_writepage(struct page *page, struct writeback_control *wbc) +{ + struct iomap_writepage_ctx wpc = { }; + + return iomap_writepage(page, wbc, &wpc, &zonefs_writeback_ops); +} + +static int zonefs_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct iomap_writepage_ctx wpc = { }; + + return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops); +} + +static const struct address_space_operations zonefs_file_aops = { + .readpage = zonefs_readpage, + .readpages = zonefs_readpages, + .writepage = zonefs_writepage, + .writepages = zonefs_writepages, + .set_page_dirty = iomap_set_page_dirty, + .releasepage = iomap_releasepage, + .invalidatepage = iomap_invalidatepage, + .migratepage = iomap_migrate_page, + .is_partially_uptodate = iomap_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, + .direct_IO = noop_direct_IO, +}; + +static void zonefs_update_stats(struct inode *inode, loff_t new_isize) +{ + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + loff_t old_isize = i_size_read(inode); + loff_t nr_blocks; + + if (new_isize == old_isize) + return; + + spin_lock(&sbi->s_lock); + + /* + * This may be called for an update after an IO error. + * So beware of the values seen. + */ + if (new_isize < old_isize) { + nr_blocks = (old_isize - new_isize) >> sb->s_blocksize_bits; + if (sbi->s_used_blocks > nr_blocks) + sbi->s_used_blocks -= nr_blocks; + else + sbi->s_used_blocks = 0; + } else { + sbi->s_used_blocks += + (new_isize - old_isize) >> sb->s_blocksize_bits; + if (sbi->s_used_blocks > sbi->s_blocks) + sbi->s_used_blocks = sbi->s_blocks; + } + + spin_unlock(&sbi->s_lock); +} + +/* + * Check a zone condition and adjust its file inode access permissions for + * offline and readonly zones. Return the inode size corresponding to the + * amount of readable data in the zone. + */ +static loff_t zonefs_check_zone_condition(struct inode *inode, + struct blk_zone *zone, bool warn) +{ + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + switch (zone->cond) { + case BLK_ZONE_COND_OFFLINE: + /* + * Dead zone: make the inode immutable, disable all accesses + * and set the file size to 0 (zone wp set to zone start). + */ + if (warn) + zonefs_warn(inode->i_sb, "inode %lu: offline zone\n", + inode->i_ino); + inode->i_flags |= S_IMMUTABLE; + inode->i_mode &= ~0777; + zone->wp = zone->start; + return 0; + case BLK_ZONE_COND_READONLY: + /* Do not allow writes in read-only zones */ + if (warn) + zonefs_warn(inode->i_sb, "inode %lu: read-only zone\n", + inode->i_ino); + inode->i_flags |= S_IMMUTABLE; + inode->i_mode &= ~0222; + /* fallthrough */ + default: + if (zi->i_ztype == ZONEFS_ZTYPE_CNV) + return zi->i_max_size; + return (zone->wp - zone->start) << SECTOR_SHIFT; + } +} + +struct zonefs_ioerr_data { + struct inode *inode; + bool write; +}; + +static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct zonefs_ioerr_data *err = data; + struct inode *inode = err->inode; + struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + loff_t isize, data_size; + + /* + * Check the zone condition: if the zone is not "bad" (offline or + * read-only), read errors are simply signaled to the IO issuer as long + * as there is no inconsistency between the inode size and the amount of + * data writen in the zone (data_size). + */ + data_size = zonefs_check_zone_condition(inode, zone, true); + isize = i_size_read(inode); + if (zone->cond != BLK_ZONE_COND_OFFLINE && + zone->cond != BLK_ZONE_COND_READONLY && + !err->write && isize == data_size) + return 0; + + /* + * At this point, we detected either a bad zone or an inconsistency + * between the inode size and the amount of data written in the zone. + * For the latter case, the cause may be a write IO error or an external + * action on the device. Two error patterns exist: + * 1) The inode size is lower than the amount of data in the zone: + * a write operation partially failed and data was writen at the end + * of the file. This can happen in the case of a large direct IO + * needing several BIOs and/or write requests to be processed. + * 2) The inode size is larger than the amount of data in the zone: + * this can happen with a deferred write error with the use of the + * device side write cache after getting successful write IO + * completions. Other possibilities are (a) an external corruption, + * e.g. an application reset the zone directly, or (b) the device + * has a serious problem (e.g. firmware bug). + * + * In all cases, warn about inode size inconsistency and handle the + * IO error according to the zone condition and to the mount options. + */ + if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && isize != data_size) + zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", + inode->i_ino, isize, data_size); + + /* + * First handle bad zones signaled by hardware. The mount options + * errors=zone-ro and errors=zone-offline result in changing the + * zone condition to read-only and offline respectively, as if the + * condition was signaled by the hardware. + */ + if (zone->cond == BLK_ZONE_COND_OFFLINE || + sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL) { + zonefs_warn(sb, "inode %lu: read/write access disabled\n", + inode->i_ino); + if (zone->cond != BLK_ZONE_COND_OFFLINE) { + zone->cond = BLK_ZONE_COND_OFFLINE; + data_size = zonefs_check_zone_condition(inode, zone, + false); + } + } else if (zone->cond == BLK_ZONE_COND_READONLY || + sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) { + zonefs_warn(sb, "inode %lu: write access disabled\n", + inode->i_ino); + if (zone->cond != BLK_ZONE_COND_READONLY) { + zone->cond = BLK_ZONE_COND_READONLY; + data_size = zonefs_check_zone_condition(inode, zone, + false); + } + } + + /* + * If error=remount-ro was specified, any error result in remounting + * the volume as read-only. + */ + if ((sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) && !sb_rdonly(sb)) { + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + } + + /* + * Update block usage stats and the inode size to prevent access to + * invalid data. + */ + zonefs_update_stats(inode, data_size); + i_size_write(inode, data_size); + zi->i_wpoffset = data_size; + + return 0; +} + +/* + * When an file IO error occurs, check the file zone to see if there is a change + * in the zone condition (e.g. offline or read-only). For a failed write to a + * sequential zone, the zone write pointer position must also be checked to + * eventually correct the file size and zonefs inode write pointer offset + * (which can be out of sync with the drive due to partial write failures). + */ +static void zonefs_io_error(struct inode *inode, bool write) +{ + struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + unsigned int noio_flag; + unsigned int nr_zones = + zi->i_max_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + struct zonefs_ioerr_data err = { + .inode = inode, + .write = write, + }; + int ret; + + mutex_lock(&zi->i_truncate_mutex); + + /* + * Memory allocations in blkdev_report_zones() can trigger a memory + * reclaim which may in turn cause a recursion into zonefs as well as + * struct request allocations for the same device. The former case may + * end up in a deadlock on the inode truncate mutex, while the latter + * may prevent IO forward progress. Executing the report zones under + * the GFP_NOIO context avoids both problems. + */ + noio_flag = memalloc_noio_save(); + ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, nr_zones, + zonefs_io_error_cb, &err); + if (ret != nr_zones) + zonefs_err(sb, "Get inode %lu zone information failed %d\n", + inode->i_ino, ret); + memalloc_noio_restore(noio_flag); + + mutex_unlock(&zi->i_truncate_mutex); +} + +static int zonefs_file_truncate(struct inode *inode, loff_t isize) +{ + struct zonefs_inode_info *zi = ZONEFS_I(inode); + loff_t old_isize; + enum req_opf op; + int ret = 0; + + /* + * Only sequential zone files can be truncated and truncation is allowed + * only down to a 0 size, which is equivalent to a zone reset, and to + * the maximum file size, which is equivalent to a zone finish. + */ + if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) + return -EPERM; + + if (!isize) + op = REQ_OP_ZONE_RESET; + else if (isize == zi->i_max_size) + op = REQ_OP_ZONE_FINISH; + else + return -EPERM; + + inode_dio_wait(inode); + + /* Serialize against page faults */ + down_write(&zi->i_mmap_sem); + + /* Serialize against zonefs_iomap_begin() */ + mutex_lock(&zi->i_truncate_mutex); + + old_isize = i_size_read(inode); + if (isize == old_isize) + goto unlock; + + ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector, + zi->i_max_size >> SECTOR_SHIFT, GFP_NOFS); + if (ret) { + zonefs_err(inode->i_sb, + "Zone management operation at %llu failed %d", + zi->i_zsector, ret); + goto unlock; + } + + zonefs_update_stats(inode, isize); + truncate_setsize(inode, isize); + zi->i_wpoffset = isize; + +unlock: + mutex_unlock(&zi->i_truncate_mutex); + up_write(&zi->i_mmap_sem); + + return ret; +} + +static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + int ret; + + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + ret = setattr_prepare(dentry, iattr); + if (ret) + return ret; + + /* + * Since files and directories cannot be created nor deleted, do not + * allow setting any write attributes on the sub-directories grouping + * files by zone type. + */ + if ((iattr->ia_valid & ATTR_MODE) && S_ISDIR(inode->i_mode) && + (iattr->ia_mode & 0222)) + return -EPERM; + + if (((iattr->ia_valid & ATTR_UID) && + !uid_eq(iattr->ia_uid, inode->i_uid)) || + ((iattr->ia_valid & ATTR_GID) && + !gid_eq(iattr->ia_gid, inode->i_gid))) { + ret = dquot_transfer(inode, iattr); + if (ret) + return ret; + } + + if (iattr->ia_valid & ATTR_SIZE) { + ret = zonefs_file_truncate(inode, iattr->ia_size); + if (ret) + return ret; + } + + setattr_copy(inode, iattr); + + return 0; +} + +static const struct inode_operations zonefs_file_inode_operations = { + .setattr = zonefs_inode_setattr, +}; + +static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct inode *inode = file_inode(file); + int ret = 0; + + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + /* + * Since only direct writes are allowed in sequential files, page cache + * flush is needed only for conventional zone files. + */ + if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV) + ret = file_write_and_wait_range(file, start, end); + if (!ret) + ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + + if (ret) + zonefs_io_error(inode, true); + + return ret; +} + +static vm_fault_t zonefs_filemap_fault(struct vm_fault *vmf) +{ + struct zonefs_inode_info *zi = ZONEFS_I(file_inode(vmf->vma->vm_file)); + vm_fault_t ret; + + down_read(&zi->i_mmap_sem); + ret = filemap_fault(vmf); + up_read(&zi->i_mmap_sem); + + return ret; +} + +static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vmf->vma->vm_file); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + vm_fault_t ret; + + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; + + /* + * Sanity check: only conventional zone files can have shared + * writeable mappings. + */ + if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV)) + return VM_FAULT_NOPAGE; + + sb_start_pagefault(inode->i_sb); + file_update_time(vmf->vma->vm_file); + + /* Serialize against truncates */ + down_read(&zi->i_mmap_sem); + ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops); + up_read(&zi->i_mmap_sem); + + sb_end_pagefault(inode->i_sb); + return ret; +} + +static const struct vm_operations_struct zonefs_file_vm_ops = { + .fault = zonefs_filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = zonefs_filemap_page_mkwrite, +}; + +static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* + * Conventional zones accept random writes, so their files can support + * shared writable mappings. For sequential zone files, only read + * mappings are possible since there are no guarantees for write + * ordering between msync() and page cache writeback. + */ + if (ZONEFS_I(file_inode(file))->i_ztype == ZONEFS_ZTYPE_SEQ && + (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) + return -EINVAL; + + file_accessed(file); + vma->vm_ops = &zonefs_file_vm_ops; + + return 0; +} + +static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence) +{ + loff_t isize = i_size_read(file_inode(file)); + + /* + * Seeks are limited to below the zone size for conventional zones + * and below the zone write pointer for sequential zones. In both + * cases, this limit is the inode size. + */ + return generic_file_llseek_size(file, offset, whence, isize, isize); +} + +static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, + int error, unsigned int flags) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + if (error) { + zonefs_io_error(inode, true); + return error; + } + + if (size && zi->i_ztype != ZONEFS_ZTYPE_CNV) { + /* + * Note that we may be seeing completions out of order, + * but that is not a problem since a write completed + * successfully necessarily means that all preceding writes + * were also successful. So we can safely increase the inode + * size to the write end location. + */ + mutex_lock(&zi->i_truncate_mutex); + if (i_size_read(inode) < iocb->ki_pos + size) { + zonefs_update_stats(inode, iocb->ki_pos + size); + i_size_write(inode, iocb->ki_pos + size); + } + mutex_unlock(&zi->i_truncate_mutex); + } + + return 0; +} + +static const struct iomap_dio_ops zonefs_write_dio_ops = { + .end_io = zonefs_file_write_dio_end_io, +}; + +/* + * Handle direct writes. For sequential zone files, this is the only possible + * write path. For these files, check that the user is issuing writes + * sequentially from the end of the file. This code assumes that the block layer + * delivers write requests to the device in sequential order. This is always the + * case if a block IO scheduler implementing the ELEVATOR_F_ZBD_SEQ_WRITE + * elevator feature is being used (e.g. mq-deadline). The block layer always + * automatically select such an elevator for zoned block devices during the + * device initialization. + */ +static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + size_t count; + ssize_t ret; + + /* + * For async direct IOs to sequential zone files, ignore IOCB_NOWAIT + * as this can cause write reordering (e.g. the first aio gets EAGAIN + * on the inode lock but the second goes through but is now unaligned). + */ + if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) + && (iocb->ki_flags & IOCB_NOWAIT)) + iocb->ki_flags &= ~IOCB_NOWAIT; + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) + return -EAGAIN; + } else { + inode_lock(inode); + } + + ret = generic_write_checks(iocb, from); + if (ret <= 0) + goto inode_unlock; + + iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos); + count = iov_iter_count(from); + + if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) { + ret = -EINVAL; + goto inode_unlock; + } + + /* Enforce sequential writes (append only) in sequential zones */ + mutex_lock(&zi->i_truncate_mutex); + if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && iocb->ki_pos != zi->i_wpoffset) { + mutex_unlock(&zi->i_truncate_mutex); + ret = -EINVAL; + goto inode_unlock; + } + mutex_unlock(&zi->i_truncate_mutex); + + ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops, + &zonefs_write_dio_ops, is_sync_kiocb(iocb)); + if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && + (ret > 0 || ret == -EIOCBQUEUED)) { + if (ret > 0) + count = ret; + mutex_lock(&zi->i_truncate_mutex); + zi->i_wpoffset += count; + mutex_unlock(&zi->i_truncate_mutex); + } + +inode_unlock: + inode_unlock(inode); + + return ret; +} + +static ssize_t zonefs_file_buffered_write(struct kiocb *iocb, + struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + ssize_t ret; + + /* + * Direct IO writes are mandatory for sequential zone files so that the + * write IO issuing order is preserved. + */ + if (zi->i_ztype != ZONEFS_ZTYPE_CNV) + return -EIO; + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) + return -EAGAIN; + } else { + inode_lock(inode); + } + + ret = generic_write_checks(iocb, from); + if (ret <= 0) + goto inode_unlock; + + iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos); + + ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops); + if (ret > 0) + iocb->ki_pos += ret; + else if (ret == -EIO) + zonefs_io_error(inode, true); + +inode_unlock: + inode_unlock(inode); + if (ret > 0) + ret = generic_write_sync(iocb, ret); + + return ret; +} + +static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (sb_rdonly(inode->i_sb)) + return -EROFS; + + /* Write operations beyond the zone size are not allowed */ + if (iocb->ki_pos >= ZONEFS_I(inode)->i_max_size) + return -EFBIG; + + if (iocb->ki_flags & IOCB_DIRECT) + return zonefs_file_dio_write(iocb, from); + + return zonefs_file_buffered_write(iocb, from); +} + +static int zonefs_file_read_dio_end_io(struct kiocb *iocb, ssize_t size, + int error, unsigned int flags) +{ + if (error) { + zonefs_io_error(file_inode(iocb->ki_filp), false); + return error; + } + + return 0; +} + +static const struct iomap_dio_ops zonefs_read_dio_ops = { + .end_io = zonefs_file_read_dio_end_io, +}; + +static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + loff_t isize; + ssize_t ret; + + /* Offline zones cannot be read */ + if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777))) + return -EPERM; + + if (iocb->ki_pos >= zi->i_max_size) + return 0; + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock_shared(inode)) + return -EAGAIN; + } else { + inode_lock_shared(inode); + } + + /* Limit read operations to written data */ + mutex_lock(&zi->i_truncate_mutex); + isize = i_size_read(inode); + if (iocb->ki_pos >= isize) { + mutex_unlock(&zi->i_truncate_mutex); + ret = 0; + goto inode_unlock; + } + iov_iter_truncate(to, isize - iocb->ki_pos); + mutex_unlock(&zi->i_truncate_mutex); + + if (iocb->ki_flags & IOCB_DIRECT) { + size_t count = iov_iter_count(to); + + if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) { + ret = -EINVAL; + goto inode_unlock; + } + file_accessed(iocb->ki_filp); + ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops, + &zonefs_read_dio_ops, is_sync_kiocb(iocb)); + } else { + ret = generic_file_read_iter(iocb, to); + if (ret == -EIO) + zonefs_io_error(inode, false); + } + +inode_unlock: + inode_unlock_shared(inode); + + return ret; +} + +static const struct file_operations zonefs_file_operations = { + .open = generic_file_open, + .fsync = zonefs_file_fsync, + .mmap = zonefs_file_mmap, + .llseek = zonefs_file_llseek, + .read_iter = zonefs_file_read_iter, + .write_iter = zonefs_file_write_iter, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .iopoll = iomap_dio_iopoll, +}; + +static struct kmem_cache *zonefs_inode_cachep; + +static struct inode *zonefs_alloc_inode(struct super_block *sb) +{ + struct zonefs_inode_info *zi; + + zi = kmem_cache_alloc(zonefs_inode_cachep, GFP_KERNEL); + if (!zi) + return NULL; + + inode_init_once(&zi->i_vnode); + mutex_init(&zi->i_truncate_mutex); + init_rwsem(&zi->i_mmap_sem); + + return &zi->i_vnode; +} + +static void zonefs_free_inode(struct inode *inode) +{ + kmem_cache_free(zonefs_inode_cachep, ZONEFS_I(inode)); +} + +/* + * File system stat. + */ +static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct super_block *sb = dentry->d_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + enum zonefs_ztype t; + u64 fsid; + + buf->f_type = ZONEFS_MAGIC; + buf->f_bsize = sb->s_blocksize; + buf->f_namelen = ZONEFS_NAME_MAX; + + spin_lock(&sbi->s_lock); + + buf->f_blocks = sbi->s_blocks; + if (WARN_ON(sbi->s_used_blocks > sbi->s_blocks)) + buf->f_bfree = 0; + else + buf->f_bfree = buf->f_blocks - sbi->s_used_blocks; + buf->f_bavail = buf->f_bfree; + + for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) { + if (sbi->s_nr_files[t]) + buf->f_files += sbi->s_nr_files[t] + 1; + } + buf->f_ffree = 0; + + spin_unlock(&sbi->s_lock); + + fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^ + le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64)); + buf->f_fsid.val[0] = (u32)fsid; + buf->f_fsid.val[1] = (u32)(fsid >> 32); + + return 0; +} + +enum { + Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair, + Opt_err, +}; + +static const match_table_t tokens = { + { Opt_errors_ro, "errors=remount-ro"}, + { Opt_errors_zro, "errors=zone-ro"}, + { Opt_errors_zol, "errors=zone-offline"}, + { Opt_errors_repair, "errors=repair"}, + { Opt_err, NULL} +}; + +static int zonefs_parse_options(struct super_block *sb, char *options) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + substring_t args[MAX_OPT_ARGS]; + char *p; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + + if (!*p) + continue; + + token = match_token(p, tokens, args); + switch (token) { + case Opt_errors_ro: + sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK; + sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_RO; + break; + case Opt_errors_zro: + sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK; + sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZRO; + break; + case Opt_errors_zol: + sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK; + sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZOL; + break; + case Opt_errors_repair: + sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK; + sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR; + break; + default: + return -EINVAL; + } + } + + return 0; +} + +static int zonefs_show_options(struct seq_file *seq, struct dentry *root) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(root->d_sb); + + if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) + seq_puts(seq, ",errors=remount-ro"); + if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) + seq_puts(seq, ",errors=zone-ro"); + if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL) + seq_puts(seq, ",errors=zone-offline"); + if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_REPAIR) + seq_puts(seq, ",errors=repair"); + + return 0; +} + +static int zonefs_remount(struct super_block *sb, int *flags, char *data) +{ + sync_filesystem(sb); + + return zonefs_parse_options(sb, data); +} + +static const struct super_operations zonefs_sops = { + .alloc_inode = zonefs_alloc_inode, + .free_inode = zonefs_free_inode, + .statfs = zonefs_statfs, + .remount_fs = zonefs_remount, + .show_options = zonefs_show_options, +}; + +static const struct inode_operations zonefs_dir_inode_operations = { + .lookup = simple_lookup, + .setattr = zonefs_inode_setattr, +}; + +static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode, + enum zonefs_ztype type) +{ + struct super_block *sb = parent->i_sb; + + inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1; + inode_init_owner(inode, parent, S_IFDIR | 0555); + inode->i_op = &zonefs_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + set_nlink(inode, 2); + inc_nlink(parent); +} + +static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, + enum zonefs_ztype type) +{ + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + inode->i_ino = zone->start >> sbi->s_zone_sectors_shift; + inode->i_mode = S_IFREG | sbi->s_perm; + + zi->i_ztype = type; + zi->i_zsector = zone->start; + zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE, + zone->len << SECTOR_SHIFT); + zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true); + + inode->i_uid = sbi->s_uid; + inode->i_gid = sbi->s_gid; + inode->i_size = zi->i_wpoffset; + inode->i_blocks = zone->len; + + inode->i_op = &zonefs_file_inode_operations; + inode->i_fop = &zonefs_file_operations; + inode->i_mapping->a_ops = &zonefs_file_aops; + + sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes); + sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits; + sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits; +} + +static struct dentry *zonefs_create_inode(struct dentry *parent, + const char *name, struct blk_zone *zone, + enum zonefs_ztype type) +{ + struct inode *dir = d_inode(parent); + struct dentry *dentry; + struct inode *inode; + + dentry = d_alloc_name(parent, name); + if (!dentry) + return NULL; + + inode = new_inode(parent->d_sb); + if (!inode) + goto dput; + + inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime; + if (zone) + zonefs_init_file_inode(inode, zone, type); + else + zonefs_init_dir_inode(dir, inode, type); + d_add(dentry, inode); + dir->i_size++; + + return dentry; + +dput: + dput(dentry); + + return NULL; +} + +struct zonefs_zone_data { + struct super_block *sb; + unsigned int nr_zones[ZONEFS_ZTYPE_MAX]; + struct blk_zone *zones; +}; + +/* + * Create a zone group and populate it with zone files. + */ +static int zonefs_create_zgroup(struct zonefs_zone_data *zd, + enum zonefs_ztype type) +{ + struct super_block *sb = zd->sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + struct blk_zone *zone, *next, *end; + const char *zgroup_name; + char *file_name; + struct dentry *dir; + unsigned int n = 0; + int ret = -ENOMEM; + + /* If the group is empty, there is nothing to do */ + if (!zd->nr_zones[type]) + return 0; + + file_name = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL); + if (!file_name) + return -ENOMEM; + + if (type == ZONEFS_ZTYPE_CNV) + zgroup_name = "cnv"; + else + zgroup_name = "seq"; + + dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type); + if (!dir) + goto free; + + /* + * The first zone contains the super block: skip it. + */ + end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk); + for (zone = &zd->zones[1]; zone < end; zone = next) { + + next = zone + 1; + if (zonefs_zone_type(zone) != type) + continue; + + /* + * For conventional zones, contiguous zones can be aggregated + * together to form larger files. Note that this overwrites the + * length of the first zone of the set of contiguous zones + * aggregated together. If one offline or read-only zone is + * found, assume that all zones aggregated have the same + * condition. + */ + if (type == ZONEFS_ZTYPE_CNV && + (sbi->s_features & ZONEFS_F_AGGRCNV)) { + for (; next < end; next++) { + if (zonefs_zone_type(next) != type) + break; + zone->len += next->len; + if (next->cond == BLK_ZONE_COND_READONLY && + zone->cond != BLK_ZONE_COND_OFFLINE) + zone->cond = BLK_ZONE_COND_READONLY; + else if (next->cond == BLK_ZONE_COND_OFFLINE) + zone->cond = BLK_ZONE_COND_OFFLINE; + } + } + + /* + * Use the file number within its group as file name. + */ + snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n); + if (!zonefs_create_inode(dir, file_name, zone, type)) + goto free; + + n++; + } + + zonefs_info(sb, "Zone group \"%s\" has %u file%s\n", + zgroup_name, n, n > 1 ? "s" : ""); + + sbi->s_nr_files[type] = n; + ret = 0; + +free: + kfree(file_name); + + return ret; +} + +static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct zonefs_zone_data *zd = data; + + /* + * Count the number of usable zones: the first zone at index 0 contains + * the super block and is ignored. + */ + switch (zone->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: + zone->wp = zone->start + zone->len; + if (idx) + zd->nr_zones[ZONEFS_ZTYPE_CNV]++; + break; + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: + if (idx) + zd->nr_zones[ZONEFS_ZTYPE_SEQ]++; + break; + default: + zonefs_err(zd->sb, "Unsupported zone type 0x%x\n", + zone->type); + return -EIO; + } + + memcpy(&zd->zones[idx], zone, sizeof(struct blk_zone)); + + return 0; +} + +static int zonefs_get_zone_info(struct zonefs_zone_data *zd) +{ + struct block_device *bdev = zd->sb->s_bdev; + int ret; + + zd->zones = kvcalloc(blkdev_nr_zones(bdev->bd_disk), + sizeof(struct blk_zone), GFP_KERNEL); + if (!zd->zones) + return -ENOMEM; + + /* Get zones information from the device */ + ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, + zonefs_get_zone_info_cb, zd); + if (ret < 0) { + zonefs_err(zd->sb, "Zone report failed %d\n", ret); + return ret; + } + + if (ret != blkdev_nr_zones(bdev->bd_disk)) { + zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n", + ret, blkdev_nr_zones(bdev->bd_disk)); + return -EIO; + } + + return 0; +} + +static inline void zonefs_cleanup_zone_info(struct zonefs_zone_data *zd) +{ + kvfree(zd->zones); +} + +/* + * Read super block information from the device. + */ +static int zonefs_read_super(struct super_block *sb) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + struct zonefs_super *super; + u32 crc, stored_crc; + struct page *page; + struct bio_vec bio_vec; + struct bio bio; + int ret; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + bio_init(&bio, &bio_vec, 1); + bio.bi_iter.bi_sector = 0; + bio.bi_opf = REQ_OP_READ; + bio_set_dev(&bio, sb->s_bdev); + bio_add_page(&bio, page, PAGE_SIZE, 0); + + ret = submit_bio_wait(&bio); + if (ret) + goto free_page; + + super = kmap(page); + + ret = -EINVAL; + if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC) + goto unmap; + + stored_crc = le32_to_cpu(super->s_crc); + super->s_crc = 0; + crc = crc32(~0U, (unsigned char *)super, sizeof(struct zonefs_super)); + if (crc != stored_crc) { + zonefs_err(sb, "Invalid checksum (Expected 0x%08x, got 0x%08x)", + crc, stored_crc); + goto unmap; + } + + sbi->s_features = le64_to_cpu(super->s_features); + if (sbi->s_features & ~ZONEFS_F_DEFINED_FEATURES) { + zonefs_err(sb, "Unknown features set 0x%llx\n", + sbi->s_features); + goto unmap; + } + + if (sbi->s_features & ZONEFS_F_UID) { + sbi->s_uid = make_kuid(current_user_ns(), + le32_to_cpu(super->s_uid)); + if (!uid_valid(sbi->s_uid)) { + zonefs_err(sb, "Invalid UID feature\n"); + goto unmap; + } + } + + if (sbi->s_features & ZONEFS_F_GID) { + sbi->s_gid = make_kgid(current_user_ns(), + le32_to_cpu(super->s_gid)); + if (!gid_valid(sbi->s_gid)) { + zonefs_err(sb, "Invalid GID feature\n"); + goto unmap; + } + } + + if (sbi->s_features & ZONEFS_F_PERM) + sbi->s_perm = le32_to_cpu(super->s_perm); + + if (memchr_inv(super->s_reserved, 0, sizeof(super->s_reserved))) { + zonefs_err(sb, "Reserved area is being used\n"); + goto unmap; + } + + uuid_copy(&sbi->s_uuid, (uuid_t *)super->s_uuid); + ret = 0; + +unmap: + kunmap(page); +free_page: + __free_page(page); + + return ret; +} + +/* + * Check that the device is zoned. If it is, get the list of zones and create + * sub-directories and files according to the device zone configuration and + * format options. + */ +static int zonefs_fill_super(struct super_block *sb, void *data, int silent) +{ + struct zonefs_zone_data zd; + struct zonefs_sb_info *sbi; + struct inode *inode; + enum zonefs_ztype t; + int ret; + + if (!bdev_is_zoned(sb->s_bdev)) { + zonefs_err(sb, "Not a zoned block device\n"); + return -EINVAL; + } + + /* + * Initialize super block information: the maximum file size is updated + * when the zone files are created so that the format option + * ZONEFS_F_AGGRCNV which increases the maximum file size of a file + * beyond the zone size is taken into account. + */ + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + + spin_lock_init(&sbi->s_lock); + sb->s_fs_info = sbi; + sb->s_magic = ZONEFS_MAGIC; + sb->s_maxbytes = 0; + sb->s_op = &zonefs_sops; + sb->s_time_gran = 1; + + /* + * The block size is set to the device physical sector size to ensure + * that write operations on 512e devices (512B logical block and 4KB + * physical block) are always aligned to the device physical blocks, + * as mandated by the ZBC/ZAC specifications. + */ + sb_set_blocksize(sb, bdev_physical_block_size(sb->s_bdev)); + sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev)); + sbi->s_uid = GLOBAL_ROOT_UID; + sbi->s_gid = GLOBAL_ROOT_GID; + sbi->s_perm = 0640; + sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO; + + ret = zonefs_read_super(sb); + if (ret) + return ret; + + ret = zonefs_parse_options(sb, data); + if (ret) + return ret; + + memset(&zd, 0, sizeof(struct zonefs_zone_data)); + zd.sb = sb; + ret = zonefs_get_zone_info(&zd); + if (ret) + goto cleanup; + + zonefs_info(sb, "Mounting %u zones", + blkdev_nr_zones(sb->s_bdev->bd_disk)); + + /* Create root directory inode */ + ret = -ENOMEM; + inode = new_inode(sb); + if (!inode) + goto cleanup; + + inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk); + inode->i_mode = S_IFDIR | 0555; + inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode); + inode->i_op = &zonefs_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + set_nlink(inode, 2); + + sb->s_root = d_make_root(inode); + if (!sb->s_root) + goto cleanup; + + /* Create and populate files in zone groups directories */ + for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) { + ret = zonefs_create_zgroup(&zd, t); + if (ret) + break; + } + +cleanup: + zonefs_cleanup_zone_info(&zd); + + return ret; +} + +static struct dentry *zonefs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, zonefs_fill_super); +} + +static void zonefs_kill_super(struct super_block *sb) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + + if (sb->s_root) + d_genocide(sb->s_root); + kill_block_super(sb); + kfree(sbi); +} + +/* + * File system definition and registration. + */ +static struct file_system_type zonefs_type = { + .owner = THIS_MODULE, + .name = "zonefs", + .mount = zonefs_mount, + .kill_sb = zonefs_kill_super, + .fs_flags = FS_REQUIRES_DEV, +}; + +static int __init zonefs_init_inodecache(void) +{ + zonefs_inode_cachep = kmem_cache_create("zonefs_inode_cache", + sizeof(struct zonefs_inode_info), 0, + (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT), + NULL); + if (zonefs_inode_cachep == NULL) + return -ENOMEM; + return 0; +} + +static void zonefs_destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy the inode cache. + */ + rcu_barrier(); + kmem_cache_destroy(zonefs_inode_cachep); +} + +static int __init zonefs_init(void) +{ + int ret; + + BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE); + + ret = zonefs_init_inodecache(); + if (ret) + return ret; + + ret = register_filesystem(&zonefs_type); + if (ret) { + zonefs_destroy_inodecache(); + return ret; + } + + return 0; +} + +static void __exit zonefs_exit(void) +{ + zonefs_destroy_inodecache(); + unregister_filesystem(&zonefs_type); +} + +MODULE_AUTHOR("Damien Le Moal"); +MODULE_DESCRIPTION("Zone file system for zoned block devices"); +MODULE_LICENSE("GPL"); +module_init(zonefs_init); +module_exit(zonefs_exit); diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h new file mode 100644 index 000000000000..ad17fef7ce91 --- /dev/null +++ b/fs/zonefs/zonefs.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Simple zone file system for zoned block devices. + * + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + */ +#ifndef __ZONEFS_H__ +#define __ZONEFS_H__ + +#include +#include +#include +#include +#include + +/* + * Maximum length of file names: this only needs to be large enough to fit + * the zone group directory names and a decimal zone number for file names. + * 16 characters is plenty. + */ +#define ZONEFS_NAME_MAX 16 + +/* + * Zone types: ZONEFS_ZTYPE_SEQ is used for all sequential zone types + * defined in linux/blkzoned.h, that is, BLK_ZONE_TYPE_SEQWRITE_REQ and + * BLK_ZONE_TYPE_SEQWRITE_PREF. + */ +enum zonefs_ztype { + ZONEFS_ZTYPE_CNV, + ZONEFS_ZTYPE_SEQ, + ZONEFS_ZTYPE_MAX, +}; + +static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone) +{ + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return ZONEFS_ZTYPE_CNV; + return ZONEFS_ZTYPE_SEQ; +} + +/* + * In-memory inode data. + */ +struct zonefs_inode_info { + struct inode i_vnode; + + /* File zone type */ + enum zonefs_ztype i_ztype; + + /* File zone start sector (512B unit) */ + sector_t i_zsector; + + /* File zone write pointer position (sequential zones only) */ + loff_t i_wpoffset; + + /* File maximum size */ + loff_t i_max_size; + + /* + * To serialise fully against both syscall and mmap based IO and + * sequential file truncation, two locks are used. For serializing + * zonefs_seq_file_truncate() against zonefs_iomap_begin(), that is, + * file truncate operations against block mapping, i_truncate_mutex is + * used. i_truncate_mutex also protects against concurrent accesses + * and changes to the inode private data, and in particular changes to + * a sequential file size on completion of direct IO writes. + * Serialization of mmap read IOs with truncate and syscall IO + * operations is done with i_mmap_sem in addition to i_truncate_mutex. + * Only zonefs_seq_file_truncate() takes both lock (i_mmap_sem first, + * i_truncate_mutex second). + */ + struct mutex i_truncate_mutex; + struct rw_semaphore i_mmap_sem; +}; + +static inline struct zonefs_inode_info *ZONEFS_I(struct inode *inode) +{ + return container_of(inode, struct zonefs_inode_info, i_vnode); +} + +/* + * On-disk super block (block 0). + */ +#define ZONEFS_LABEL_LEN 64 +#define ZONEFS_UUID_SIZE 16 +#define ZONEFS_SUPER_SIZE 4096 + +struct zonefs_super { + + /* Magic number */ + __le32 s_magic; + + /* Checksum */ + __le32 s_crc; + + /* Volume label */ + char s_label[ZONEFS_LABEL_LEN]; + + /* 128-bit uuid */ + __u8 s_uuid[ZONEFS_UUID_SIZE]; + + /* Features */ + __le64 s_features; + + /* UID/GID to use for files */ + __le32 s_uid; + __le32 s_gid; + + /* File permissions */ + __le32 s_perm; + + /* Padding to ZONEFS_SUPER_SIZE bytes */ + __u8 s_reserved[3988]; + +} __packed; + +/* + * Feature flags: specified in the s_features field of the on-disk super + * block struct zonefs_super and in-memory in the s_feartures field of + * struct zonefs_sb_info. + */ +enum zonefs_features { + /* + * Aggregate contiguous conventional zones into a single file. + */ + ZONEFS_F_AGGRCNV = 1ULL << 0, + /* + * Use super block specified UID for files instead of default 0. + */ + ZONEFS_F_UID = 1ULL << 1, + /* + * Use super block specified GID for files instead of default 0. + */ + ZONEFS_F_GID = 1ULL << 2, + /* + * Use super block specified file permissions instead of default 640. + */ + ZONEFS_F_PERM = 1ULL << 3, +}; + +#define ZONEFS_F_DEFINED_FEATURES \ + (ZONEFS_F_AGGRCNV | ZONEFS_F_UID | ZONEFS_F_GID | ZONEFS_F_PERM) + +/* + * Mount options for zone write pointer error handling. + */ +#define ZONEFS_MNTOPT_ERRORS_RO (1 << 0) /* Make zone file readonly */ +#define ZONEFS_MNTOPT_ERRORS_ZRO (1 << 1) /* Make zone file offline */ +#define ZONEFS_MNTOPT_ERRORS_ZOL (1 << 2) /* Make zone file offline */ +#define ZONEFS_MNTOPT_ERRORS_REPAIR (1 << 3) /* Remount read-only */ +#define ZONEFS_MNTOPT_ERRORS_MASK \ + (ZONEFS_MNTOPT_ERRORS_RO | ZONEFS_MNTOPT_ERRORS_ZRO | \ + ZONEFS_MNTOPT_ERRORS_ZOL | ZONEFS_MNTOPT_ERRORS_REPAIR) + +/* + * In-memory Super block information. + */ +struct zonefs_sb_info { + + unsigned long s_mount_opts; + + spinlock_t s_lock; + + unsigned long long s_features; + kuid_t s_uid; + kgid_t s_gid; + umode_t s_perm; + uuid_t s_uuid; + unsigned int s_zone_sectors_shift; + + unsigned int s_nr_files[ZONEFS_ZTYPE_MAX]; + + loff_t s_blocks; + loff_t s_used_blocks; +}; + +static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +#define zonefs_info(sb, format, args...) \ + pr_info("zonefs (%s): " format, sb->s_id, ## args) +#define zonefs_err(sb, format, args...) \ + pr_err("zonefs (%s) ERROR: " format, sb->s_id, ## args) +#define zonefs_warn(sb, format, args...) \ + pr_warn("zonefs (%s) WARNING: " format, sb->s_id, ## args) + +#endif diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e9ad3943cd9..49b1a70e12c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -728,7 +728,7 @@ struct bpf_struct_ops { #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); -void bpf_struct_ops_init(struct btf *btf); +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -752,7 +752,10 @@ static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } -static inline void bpf_struct_ops_init(struct btf *btf) { } +static inline void bpf_struct_ops_init(struct btf *btf, + struct bpf_verifier_log *log) +{ +} static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); diff --git a/include/linux/irq.h b/include/linux/irq.h index 7853eb9301f2..3ed5a055b5f4 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -209,6 +209,8 @@ struct irq_data { * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target * IRQD_DEFAULT_TRIGGER_SET - Expected trigger already been set * IRQD_CAN_RESERVE - Can use reservation mode + * IRQD_MSI_NOMASK_QUIRK - Non-maskable MSI quirk for affinity change + * required */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -231,6 +233,7 @@ enum { IRQD_SINGLE_TARGET = (1 << 24), IRQD_DEFAULT_TRIGGER_SET = (1 << 25), IRQD_CAN_RESERVE = (1 << 26), + IRQD_MSI_NOMASK_QUIRK = (1 << 27), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -390,6 +393,21 @@ static inline bool irqd_can_reserve(struct irq_data *d) return __irqd_to_state(d) & IRQD_CAN_RESERVE; } +static inline void irqd_set_msi_nomask_quirk(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK; +} + +static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK; +} + +static inline bool irqd_msi_nomask_quirk(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index f0b8ca766e7d..83439bfb6c5b 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -652,10 +652,10 @@ struct rdists { struct { void __iomem *rd_base; struct page *pend_page; - struct page *vpe_l1_page; phys_addr_t phys_base; bool lpi_enabled; cpumask_t *vpe_table_mask; + void *vpe_l1_base; } __percpu *rdist; phys_addr_t prop_table_pa; void *prop_table_va; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 698749f42ced..b2d47571ab67 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -206,6 +206,13 @@ enum { /* Irq domain implements MSI remapping */ IRQ_DOMAIN_FLAG_MSI_REMAP = (1 << 5), + /* + * Quirk to handle MSI implementations which do not provide + * masking. Currently known to affect x86, but partially + * handled in core code. + */ + IRQ_DOMAIN_MSI_NOMASK_QUIRK = (1 << 6), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 032cd6630720..ff8c9d527bb4 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1448,14 +1448,15 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_440[0x20]; - u8 tls[0x1]; - u8 reserved_at_461[0x2]; + u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x3]; u8 log_max_umem[0x5]; u8 max_num_eqs[0x10]; - u8 reserved_at_480[0x3]; + u8 reserved_at_480[0x1]; + u8 tls_tx[0x1]; + u8 reserved_at_482[0x1]; u8 log_max_l2_table[0x5]; u8 reserved_at_488[0x8]; u8 log_uar_page_sz[0x10]; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cf65763af0cb..547773f5894e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1544,4 +1544,8 @@ int perf_event_exit_cpu(unsigned int cpu); #define perf_event_exit_cpu NULL #endif +extern void __weak arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, + u64 now); + #endif /* _LINUX_PERF_EVENT_H */ diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h index c3b61ead41f2..6f6fed2b171d 100644 --- a/include/linux/platform_data/b53.h +++ b/include/linux/platform_data/b53.h @@ -19,7 +19,7 @@ #ifndef __B53_H #define __B53_H -#include +#include #include struct b53_platform_data { diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index 84789ca634aa..ea1cc6d829e9 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -19,7 +19,7 @@ #ifndef __MICROCHIP_KSZ_H #define __MICROCHIP_KSZ_H -#include +#include struct ksz_platform_data { u32 chip_id; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3d13a4b717e9..ca8806b69388 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1821,6 +1821,18 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) return list_->qlen; } +/** + * skb_queue_len_lockless - get queue length + * @list_: list to measure + * + * Return the length of an &sk_buff queue. + * This variant can be used in lockless contexts. + */ +static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) +{ + return READ_ONCE(list_->qlen); +} + /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize @@ -2026,7 +2038,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; - list->qlen--; + WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; diff --git a/include/net/ipx.h b/include/net/ipx.h index baf090390998..9d1342807b59 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -47,11 +47,6 @@ struct ipxhdr { /* From af_ipx.c */ extern int sysctl_ipx_pprop_broadcasting; -static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb) -{ - return (struct ipxhdr *)skb_transport_header(skb); -} - struct ipx_interface { /* IPX address */ __be32 if_netnum; diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 3ac436376d79..d78064007b17 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -87,6 +87,7 @@ #define NSFS_MAGIC 0x6e736673 #define BPF_FS_MAGIC 0xcafe4a11 #define AAFS_MAGIC 0x5a3c69f0 +#define ZONEFS_MAGIC 0x5a4f4653 /* Since UDF 2.01 is ISO 13346 based... */ #define UDF_SUPER_MAGIC 0x15013346 diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 8ad1c9ea26b2..042f95534f86 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -96,12 +96,11 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { static const struct btf_type *module_type; -void bpf_struct_ops_init(struct btf *btf) +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { s32 type_id, value_id, module_id; const struct btf_member *member; struct bpf_struct_ops *st_ops; - struct bpf_verifier_log log = {}; const struct btf_type *t; char value_name[128]; const char *mname; @@ -172,7 +171,7 @@ void bpf_struct_ops_init(struct btf *btf) member->type, NULL); if (func_proto && - btf_distill_func_proto(&log, btf, + btf_distill_func_proto(log, btf, func_proto, mname, &st_ops->func_models[j])) { pr_warn("Error in parsing func ptr %s in struct %s\n", diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b7c1660fb594..805c43b083e9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3643,7 +3643,7 @@ struct btf *btf_parse_vmlinux(void) goto errout; } - bpf_struct_ops_init(btf); + bpf_struct_ops_init(btf, log); btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); @@ -3931,6 +3931,7 @@ int btf_struct_access(struct bpf_verifier_log *log, if (btf_type_is_ptr(mtype)) { const struct btf_type *stype; + u32 id; if (msize != size || off != moff) { bpf_log(log, @@ -3939,12 +3940,9 @@ int btf_struct_access(struct bpf_verifier_log *log, return -EACCES; } - stype = btf_type_by_id(btf_vmlinux, mtype->type); - /* skip modifiers */ - while (btf_type_is_modifier(stype)) - stype = btf_type_by_id(btf_vmlinux, stype->type); + stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); if (btf_type_is_struct(stype)) { - *next_btf_id = mtype->type; + *next_btf_id = id; return PTR_TO_BTF_ID; } } diff --git a/kernel/events/core.c b/kernel/events/core.c index 17f9a4a909eb..e453589da97c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -951,9 +951,9 @@ list_update_cgroup_event(struct perf_event *event, /* * Because cgroup events are always per-cpu events, - * this will always be called from the right CPU. + * @ctx == &cpuctx->ctx. */ - cpuctx = __get_cpu_context(ctx); + cpuctx = container_of(ctx, struct perf_cpu_context, ctx); /* * Since setting cpuctx->cgrp is conditional on the current @cgrp @@ -979,7 +979,8 @@ list_update_cgroup_event(struct perf_event *event, cpuctx_entry = &cpuctx->cgrp_cpuctx_entry; if (add) - list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list)); + list_add(cpuctx_entry, + per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); else list_del(cpuctx_entry); } @@ -5916,7 +5917,15 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) */ user_lock_limit *= num_online_cpus(); - user_locked = atomic_long_read(&user->locked_vm) + user_extra; + user_locked = atomic_long_read(&user->locked_vm); + + /* + * sysctl_perf_event_mlock may have changed, so that + * user->locked_vm > user_lock_limit + */ + if (user_locked > user_lock_limit) + user_locked = user_lock_limit; + user_locked += user_extra; if (user_locked > user_lock_limit) { /* diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index c1eccd4f6520..a949bd39e343 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -114,6 +114,7 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), BIT_MASK_DESCR(IRQD_CAN_RESERVE), + BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK), BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU), diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 818b2802d3e7..3089a60ea8f9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -731,6 +731,13 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on) * * Wakeup mode lets this IRQ wake the system from sleep * states like "suspend to RAM". + * + * Note: irq enable/disable state is completely orthogonal + * to the enable/disable state of irq wake. An irq can be + * disabled with disable_irq() and still wake the system as + * long as the irq has wake enabled. If this does not hold, + * then the underlying irq chip and the related driver need + * to be investigated. */ int irq_set_irq_wake(unsigned int irq, unsigned int on) { diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index ad26fbcfbfc8..eb95f6106a1e 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -453,8 +453,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, continue; irq_data = irq_domain_get_irq_data(domain, desc->irq); - if (!can_reserve) + if (!can_reserve) { irqd_clr_can_reserve(irq_data); + if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) + irqd_set_msi_nomask_quirk(irq_data); + } ret = irq_domain_activate_irq(irq_data, can_reserve); if (ret) goto cleanup; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index d812b90f4c86..a9b3f660dee7 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -44,7 +44,7 @@ __attribute__((weak, section(".rodata"))); extern const unsigned long kallsyms_relative_base __attribute__((weak, section(".rodata"))); -extern const u8 kallsyms_token_table[] __weak; +extern const char kallsyms_token_table[] __weak; extern const u16 kallsyms_token_index[] __weak; extern const unsigned int kallsyms_markers[] __weak; @@ -58,7 +58,8 @@ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result, size_t maxlen) { int len, skipped_first = 0; - const u8 *tptr, *data; + const char *tptr; + const u8 *data; /* Get the compressed symbol length from the first symbol byte. */ data = &kallsyms_names[off]; diff --git a/kernel/smp.c b/kernel/smp.c index 3b7bedc97af3..d0ada39eb4d4 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -435,7 +435,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, /* Fastpath: do that cpu by itself. */ if (next_cpu >= nr_cpu_ids) { - if (!cond_func || (cond_func && cond_func(cpu, info))) + if (!cond_func || cond_func(cpu, info)) smp_call_function_single(cpu, func, info, wait); return; } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index fff5f64981c6..428beb69426a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -293,8 +293,15 @@ static void clocksource_watchdog(struct timer_list *unused) next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = cpumask_first(cpu_online_mask); - watchdog_timer.expires += WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, next_cpu); + + /* + * Arm timer if not already pending: could race with concurrent + * pair clocksource_stop_watchdog() clocksource_start_watchdog(). + */ + if (!timer_pending(&watchdog_timer)) { + watchdog_timer.expires += WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, next_cpu); + } out: spin_unlock(&watchdog_lock); } diff --git a/kernel/up.c b/kernel/up.c index 53144d056252..c6f323dcd45b 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -14,7 +14,8 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, { unsigned long flags; - WARN_ON(cpu != 0); + if (cpu != 0) + return -ENXIO; local_irq_save(flags); func(info); diff --git a/lib/Makefile b/lib/Makefile index 8bb91176c2a1..5d64890d6b6a 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -241,8 +241,8 @@ obj-$(CONFIG_ASN1) += asn1_decoder.o obj-$(CONFIG_FONT_SUPPORT) += fonts/ -hostprogs-y := gen_crc32table -hostprogs-y += gen_crc64table +hostprogs := gen_crc32table +hostprogs += gen_crc64table clean-files := crc32table.h clean-files += crc64table.h diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 0083b5cc646c..b4c0df6d706d 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -10,7 +10,7 @@ raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \ raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o -hostprogs-y += mktables +hostprogs += mktables ifeq ($(CONFIG_ALTIVEC),y) altivec_flags := -maltivec $(call cc-option,-mabi=altivec) diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index aa945ab5b655..36580301da70 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -3,7 +3,7 @@ # Makefile for the Linux BPFILTER layer. # -hostprogs-y := bpfilter_umh +hostprogs := bpfilter_umh bpfilter_umh-objs := main.o KBUILD_HOSTCFLAGS += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi HOSTCC := $(CC) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 458be6b3eda9..3ab23f698221 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -643,9 +643,10 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); + nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - smap->bucket_log = max_t(u32, 1, ilog2(roundup_pow_of_two(num_possible_cpus()))); - nbuckets = 1U << smap->bucket_log; + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); ret = bpf_map_charge_init(&smap->map.memory, cost); diff --git a/net/core/devlink.c b/net/core/devlink.c index ca1df0ec3c97..549ee56b7a21 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3986,6 +3986,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } + /* return 0 if there is no further data to read */ + if (start_offset >= region->size) { + err = 0; + goto out_unlock; + } + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index ea46fc6aa883..31700e0c3928 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1000,8 +1000,10 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { int cpu; - if (!monitor_hw) + if (!monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled"); + return; + } monitor_hw = false; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 8998e356f423..085cef5857bb 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -234,7 +234,6 @@ static void sock_map_free(struct bpf_map *map) int i; synchronize_rcu(); - rcu_read_lock(); raw_spin_lock_bh(&stab->lock); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; @@ -243,13 +242,15 @@ static void sock_map_free(struct bpf_map *map) sk = xchg(psk, NULL); if (sk) { lock_sock(sk); + rcu_read_lock(); sock_map_unref(sk, psk); + rcu_read_unlock(); release_sock(sk); } } raw_spin_unlock_bh(&stab->lock); - rcu_read_unlock(); + /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(stab->sks); @@ -416,14 +417,16 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, ret = -EINVAL; goto out; } - if (!sock_map_sk_is_suitable(sk) || - sk->sk_state != TCP_ESTABLISHED) { + if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); - ret = sock_map_update_common(map, idx, sk, flags); + if (sk->sk_state != TCP_ESTABLISHED) + ret = -EOPNOTSUPP; + else + ret = sock_map_update_common(map, idx, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); @@ -739,14 +742,16 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key, ret = -EINVAL; goto out; } - if (!sock_map_sk_is_suitable(sk) || - sk->sk_state != TCP_ESTABLISHED) { + if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); - ret = sock_hash_update_common(map, key, sk, flags); + if (sk->sk_state != TCP_ESTABLISHED) + ret = -EOPNOTSUPP; + else + ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); @@ -859,19 +864,22 @@ static void sock_hash_free(struct bpf_map *map) int i; synchronize_rcu(); - rcu_read_lock(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); raw_spin_lock_bh(&bucket->lock); hlist_for_each_entry_safe(elem, node, &bucket->head, node) { hlist_del_rcu(&elem->node); lock_sock(elem->sk); + rcu_read_lock(); sock_map_unref(elem->sk, elem); + rcu_read_unlock(); release_sock(elem->sk); } raw_spin_unlock_bh(&bucket->lock); } - rcu_read_unlock(); + + /* wait for psock readers accessing its map link */ + synchronize_rcu(); bpf_map_area_free(htab->buckets); kfree(htab); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 39d861d00377..cb493e15959c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5718,6 +5718,9 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) struct nlattr *tb[IFLA_INET6_MAX + 1]; int err; + if (!idev) + return -EAFNOSUPPORT; + if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) BUG(); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3bccee455688..73780b4cb108 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -24,57 +24,12 @@ #define MPTCP_SAME_STATE TCP_MAX_STATES -static void __mptcp_close(struct sock *sk, long timeout); - -static const struct proto_ops *tcp_proto_ops(struct sock *sk) -{ #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (sk->sk_family == AF_INET6) - return &inet6_stream_ops; +struct mptcp6_sock { + struct mptcp_sock msk; + struct ipv6_pinfo np; +}; #endif - return &inet_stream_ops; -} - -/* MP_CAPABLE handshake failed, convert msk to plain tcp, replacing - * socket->sk and stream ops and destroying msk - * return the msk socket, as we can't access msk anymore after this function - * completes - * Called with msk lock held, releases such lock before returning - */ -static struct socket *__mptcp_fallback_to_tcp(struct mptcp_sock *msk, - struct sock *ssk) -{ - struct mptcp_subflow_context *subflow; - struct socket *sock; - struct sock *sk; - - sk = (struct sock *)msk; - sock = sk->sk_socket; - subflow = mptcp_subflow_ctx(ssk); - - /* detach the msk socket */ - list_del_init(&subflow->node); - sock_orphan(sk); - sock->sk = NULL; - - /* socket is now TCP */ - lock_sock(ssk); - sock_graft(ssk, sock); - if (subflow->conn) { - /* We can't release the ULP data on a live socket, - * restore the tcp callback - */ - mptcp_subflow_tcp_fallback(ssk, subflow); - sock_put(subflow->conn); - subflow->conn = NULL; - } - release_sock(ssk); - sock->ops = tcp_proto_ops(ssk); - - /* destroy the left-over msk sock */ - __mptcp_close(sk, 0); - return sock; -} /* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not * completed yet or has failed, return the subflow socket. @@ -93,10 +48,6 @@ static bool __mptcp_needs_tcp_fallback(const struct mptcp_sock *msk) return msk->first && !sk_is_mptcp(msk->first); } -/* if the mp_capable handshake has failed, it fallbacks msk to plain TCP, - * releases the socket lock and returns a reference to the now TCP socket. - * Otherwise returns NULL - */ static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk) { sock_owned_by_me((const struct sock *)msk); @@ -105,15 +56,11 @@ static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk) return NULL; if (msk->subflow) { - /* the first subflow is an active connection, discart the - * paired socket - */ - msk->subflow->sk = NULL; - sock_release(msk->subflow); - msk->subflow = NULL; + release_sock((struct sock *)msk); + return msk->subflow; } - return __mptcp_fallback_to_tcp(msk, msk->first); + return NULL; } static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk) @@ -640,12 +587,14 @@ static void mptcp_subflow_shutdown(struct sock *ssk, int how) } /* Called with msk lock held, releases such lock before returning */ -static void __mptcp_close(struct sock *sk, long timeout) +static void mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); LIST_HEAD(conn_list); + lock_sock(sk); + mptcp_token_destroy(msk->token); inet_sk_state_store(sk, TCP_CLOSE); @@ -662,12 +611,6 @@ static void __mptcp_close(struct sock *sk, long timeout) sk_common_release(sk); } -static void mptcp_close(struct sock *sk, long timeout) -{ - lock_sock(sk); - __mptcp_close(sk, timeout); -} - static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -691,6 +634,30 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr; } +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) +{ + unsigned int offset = sizeof(struct mptcp6_sock) - sizeof(struct ipv6_pinfo); + + return (struct ipv6_pinfo *)(((u8 *)sk) + offset); +} +#endif + +struct sock *mptcp_sk_clone_lock(const struct sock *sk) +{ + struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); + + if (!nsk) + return NULL; + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (nsk->sk_family == AF_INET6) + inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); +#endif + + return nsk; +} + static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, bool kern) { @@ -721,7 +688,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, lock_sock(sk); local_bh_disable(); - new_mptcp_sock = sk_clone_lock(sk, GFP_ATOMIC); + new_mptcp_sock = mptcp_sk_clone_lock(sk); if (!new_mptcp_sock) { *err = -ENOBUFS; local_bh_enable(); @@ -1270,8 +1237,7 @@ int mptcp_proto_v6_init(void) strcpy(mptcp_v6_prot.name, "MPTCPv6"); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.destroy = mptcp_v6_destroy; - mptcp_v6_prot.obj_size = sizeof(struct mptcp_sock) + - sizeof(struct ipv6_pinfo); + mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); err = proto_register(&mptcp_v6_prot, 1); if (err) diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index dbdbc4f18b5e..c9f34b0a11df 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -562,11 +562,11 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* - * Final call destruction under RCU. + * Final call destruction - but must be done in process context. */ -static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +static void rxrpc_destroy_call(struct work_struct *work) { - struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); struct rxrpc_net *rxnet = call->rxnet; rxrpc_put_connection(call->conn); @@ -578,6 +578,22 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) wake_up_var(&rxnet->nr_calls); } +/* + * Final call destruction under RCU. + */ +static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +{ + struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + + if (in_softirq()) { + INIT_WORK(&call->processor, rxrpc_destroy_call); + if (!rxrpc_queue_work(&call->processor)) + BUG(); + } else { + rxrpc_destroy_call(&call->processor); + } +} + /* * clean up a call */ diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index c0b3154f7a7e..19e141eeed17 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -171,8 +171,6 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, _enter("%d,%x", conn->debug_id, call->cid); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - if (rcu_access_pointer(chan->call) == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. @@ -225,6 +223,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) __rxrpc_disconnect_call(conn, call); spin_unlock(&conn->channel_lock); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 0323aee03de7..09b7dc5fe7e0 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -365,7 +365,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result, net); if (err < 0) - goto errout1; + goto errout_alloc; if (old_r) cr = r->res; @@ -484,7 +484,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, tcindex_free_perfect_hash(cp); else if (balloc == 2) kfree(cp->h); -errout1: tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index bbd0dea6b6b9..214657eb3dfd 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -349,9 +349,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); - kfree_skb(skb); len_dropped += qdisc_pkt_len(skb); num_dropped += 1; + rtnl_kfree_skbs(skb, skb); } qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c609373c8661..660fc45ee40f 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(taprio_list_lock); #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) +#define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { struct list_head list; @@ -766,6 +767,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, }; static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, @@ -1367,6 +1369,33 @@ static int taprio_mqprio_cmp(const struct net_device *dev, return 0; } +/* The semantics of the 'flags' argument in relation to 'change()' + * requests, are interpreted following two rules (which are applied in + * this order): (1) an omitted 'flags' argument is interpreted as + * zero; (2) the 'flags' of a "running" taprio instance cannot be + * changed. + */ +static int taprio_new_flags(const struct nlattr *attr, u32 old, + struct netlink_ext_ack *extack) +{ + u32 new = 0; + + if (attr) + new = nla_get_u32(attr); + + if (old != TAPRIO_FLAGS_INVALID && old != new) { + NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); + return -EOPNOTSUPP; + } + + if (!taprio_flags_valid(new)) { + NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid"); + return -EINVAL; + } + + return new; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1375,7 +1404,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; - u32 taprio_flags = 0; unsigned long flags; ktime_t start; int i, err; @@ -1388,21 +1416,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); - if (tb[TCA_TAPRIO_ATTR_FLAGS]) { - taprio_flags = nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]); + err = taprio_new_flags(tb[TCA_TAPRIO_ATTR_FLAGS], + q->flags, extack); + if (err < 0) + return err; - if (q->flags != 0 && q->flags != taprio_flags) { - NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); - return -EOPNOTSUPP; - } else if (!taprio_flags_valid(taprio_flags)) { - NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid"); - return -EINVAL; - } + q->flags = err; - q->flags = taprio_flags; - } - - err = taprio_parse_mqprio_opt(dev, mqprio, extack, taprio_flags); + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; @@ -1444,7 +1465,20 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, taprio_set_picos_per_byte(dev, q); - if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + if (mqprio) { + netdev_set_num_tc(dev, mqprio->num_tc); + for (i = 0; i < mqprio->num_tc; i++) + netdev_set_tc_queue(dev, i, + mqprio->count[i], + mqprio->offset[i]); + + /* Always use supplied priority mappings */ + for (i = 0; i <= TC_BITMASK; i++) + netdev_set_prio_tc_map(dev, i, + mqprio->prio_tc_map[i]); + } + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); @@ -1464,27 +1498,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); } - if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) && - !FULL_OFFLOAD_IS_ENABLED(taprio_flags) && + if (!TXTIME_ASSIST_IS_ENABLED(q->flags) && + !FULL_OFFLOAD_IS_ENABLED(q->flags) && !hrtimer_active(&q->advance_timer)) { hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; } - if (mqprio) { - netdev_set_num_tc(dev, mqprio->num_tc); - for (i = 0; i < mqprio->num_tc; i++) - netdev_set_tc_queue(dev, i, - mqprio->count[i], - mqprio->offset[i]); - - /* Always use supplied priority mappings */ - for (i = 0; i <= TC_BITMASK; i++) - netdev_set_prio_tc_map(dev, i, - mqprio->prio_tc_map[i]); - } - - if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) { + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { q->dequeue = taprio_dequeue_offload; q->peek = taprio_peek_offload; } else { @@ -1501,9 +1522,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto unlock; } - if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) { - setup_txtime(q, new_admin, start); + setup_txtime(q, new_admin, start); + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { if (!oper) { rcu_assign_pointer(q->oper_sched, new_admin); err = 0; @@ -1528,7 +1549,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, spin_unlock_irqrestore(&q->current_entry_lock, flags); - if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) taprio_offload_config_changed(q); } @@ -1567,7 +1588,7 @@ static void taprio_destroy(struct Qdisc *sch) } q->qdiscs = NULL; - netdev_set_num_tc(dev, 0); + netdev_reset_tc(dev); if (q->oper_sched) call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb); @@ -1597,6 +1618,7 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, * and get the valid one on taprio_change(). */ q->clockid = -1; + q->flags = TAPRIO_FLAGS_INVALID; spin_lock(&taprio_list_lock); list_add(&q->taprio_list, &taprio_list); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 321af97c7bbe..62c12cb5763e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -189,11 +189,17 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return unix_peer(osk) == NULL || unix_our_peer(sk, osk); } -static inline int unix_recvq_full(struct sock const *sk) +static inline int unix_recvq_full(const struct sock *sk) { return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } +static inline int unix_recvq_full_lockless(const struct sock *sk) +{ + return skb_queue_len_lockless(&sk->sk_receive_queue) > + READ_ONCE(sk->sk_max_ack_backlog); +} + struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -1758,7 +1764,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, * - unix_peer(sk) == sk by time of get but disconnected before lock */ if (other != sk && - unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + unlikely(unix_peer(other) != sk && + unix_recvq_full_lockless(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index b0e8adf7eb01..79b0fee6943b 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -111,65 +111,65 @@ ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS) hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS) # Tell kbuild to always build the programs -always := $(tprogs-y) -always += sockex1_kern.o -always += sockex2_kern.o -always += sockex3_kern.o -always += tracex1_kern.o -always += tracex2_kern.o -always += tracex3_kern.o -always += tracex4_kern.o -always += tracex5_kern.o -always += tracex6_kern.o -always += tracex7_kern.o -always += sock_flags_kern.o -always += test_probe_write_user_kern.o -always += trace_output_kern.o -always += tcbpf1_kern.o -always += tc_l2_redirect_kern.o -always += lathist_kern.o -always += offwaketime_kern.o -always += spintest_kern.o -always += map_perf_test_kern.o -always += test_overhead_tp_kern.o -always += test_overhead_raw_tp_kern.o -always += test_overhead_kprobe_kern.o -always += parse_varlen.o parse_simple.o parse_ldabs.o -always += test_cgrp2_tc_kern.o -always += xdp1_kern.o -always += xdp2_kern.o -always += xdp_router_ipv4_kern.o -always += test_current_task_under_cgroup_kern.o -always += trace_event_kern.o -always += sampleip_kern.o -always += lwt_len_hist_kern.o -always += xdp_tx_iptunnel_kern.o -always += test_map_in_map_kern.o -always += tcp_synrto_kern.o -always += tcp_rwnd_kern.o -always += tcp_bufs_kern.o -always += tcp_cong_kern.o -always += tcp_iw_kern.o -always += tcp_clamp_kern.o -always += tcp_basertt_kern.o -always += tcp_tos_reflect_kern.o -always += tcp_dumpstats_kern.o -always += xdp_redirect_kern.o -always += xdp_redirect_map_kern.o -always += xdp_redirect_cpu_kern.o -always += xdp_monitor_kern.o -always += xdp_rxq_info_kern.o -always += xdp2skb_meta_kern.o -always += syscall_tp_kern.o -always += cpustat_kern.o -always += xdp_adjust_tail_kern.o -always += xdp_fwd_kern.o -always += task_fd_query_kern.o -always += xdp_sample_pkts_kern.o -always += ibumad_kern.o -always += hbm_out_kern.o -always += hbm_edt_kern.o -always += xdpsock_kern.o +always-y := $(tprogs-y) +always-y += sockex1_kern.o +always-y += sockex2_kern.o +always-y += sockex3_kern.o +always-y += tracex1_kern.o +always-y += tracex2_kern.o +always-y += tracex3_kern.o +always-y += tracex4_kern.o +always-y += tracex5_kern.o +always-y += tracex6_kern.o +always-y += tracex7_kern.o +always-y += sock_flags_kern.o +always-y += test_probe_write_user_kern.o +always-y += trace_output_kern.o +always-y += tcbpf1_kern.o +always-y += tc_l2_redirect_kern.o +always-y += lathist_kern.o +always-y += offwaketime_kern.o +always-y += spintest_kern.o +always-y += map_perf_test_kern.o +always-y += test_overhead_tp_kern.o +always-y += test_overhead_raw_tp_kern.o +always-y += test_overhead_kprobe_kern.o +always-y += parse_varlen.o parse_simple.o parse_ldabs.o +always-y += test_cgrp2_tc_kern.o +always-y += xdp1_kern.o +always-y += xdp2_kern.o +always-y += xdp_router_ipv4_kern.o +always-y += test_current_task_under_cgroup_kern.o +always-y += trace_event_kern.o +always-y += sampleip_kern.o +always-y += lwt_len_hist_kern.o +always-y += xdp_tx_iptunnel_kern.o +always-y += test_map_in_map_kern.o +always-y += tcp_synrto_kern.o +always-y += tcp_rwnd_kern.o +always-y += tcp_bufs_kern.o +always-y += tcp_cong_kern.o +always-y += tcp_iw_kern.o +always-y += tcp_clamp_kern.o +always-y += tcp_basertt_kern.o +always-y += tcp_tos_reflect_kern.o +always-y += tcp_dumpstats_kern.o +always-y += xdp_redirect_kern.o +always-y += xdp_redirect_map_kern.o +always-y += xdp_redirect_cpu_kern.o +always-y += xdp_monitor_kern.o +always-y += xdp_rxq_info_kern.o +always-y += xdp2skb_meta_kern.o +always-y += syscall_tp_kern.o +always-y += cpustat_kern.o +always-y += xdp_adjust_tail_kern.o +always-y += xdp_fwd_kern.o +always-y += task_fd_query_kern.o +always-y += xdp_sample_pkts_kern.o +always-y += ibumad_kern.o +always-y += hbm_out_kern.o +always-y += hbm_edt_kern.o +always-y += xdpsock_kern.o ifeq ($(ARCH), arm) # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 0b5acd722306..c91e91362a0c 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -83,7 +83,6 @@ static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; static u32 opt_umem_flags; static int opt_unaligned_chunks; static int opt_mmap_flags; -static u32 opt_xdp_bind_flags; static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static int opt_timeout = 1000; static bool opt_need_wakeup = true; @@ -789,7 +788,8 @@ static void kick_tx(struct xsk_socket_info *xsk) int ret; ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); - if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY) + if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || + errno == EBUSY || errno == ENETDOWN) return; exit_with_error(errno); } diff --git a/samples/connector/Makefile b/samples/connector/Makefile index 6ad71620e503..b785cbde5ffa 100644 --- a/samples/connector/Makefile +++ b/samples/connector/Makefile @@ -2,12 +2,8 @@ obj-$(CONFIG_SAMPLE_CONNECTOR) += cn_test.o # List of programs to build -ifdef CONFIG_SAMPLE_CONNECTOR -hostprogs-y := ucon -endif - -# Tell kbuild to always build the programs -always := $(hostprogs-y) +hostprogs := ucon +always-y := $(hostprogs) HOSTCFLAGS_ucon.o += -I$(objtree)/usr/include diff --git a/samples/hidraw/Makefile b/samples/hidraw/Makefile index dec1b22adf54..8bd25f77671f 100644 --- a/samples/hidraw/Makefile +++ b/samples/hidraw/Makefile @@ -1,9 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # List of programs to build -hostprogs-y := hid-example - -# Tell kbuild to always build the programs -always := $(hostprogs-y) +hostprogs := hid-example +always-y := $(hostprogs) HOSTCFLAGS_hid-example.o += -I$(objtree)/usr/include diff --git a/samples/mei/Makefile b/samples/mei/Makefile index 27f37efdadb4..f5b9d02be2cd 100644 --- a/samples/mei/Makefile +++ b/samples/mei/Makefile @@ -1,10 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (c) 2012-2019, Intel Corporation. All rights reserved. -hostprogs-y := mei-amt-version +hostprogs := mei-amt-version HOSTCFLAGS_mei-amt-version.o += -I$(objtree)/usr/include -always := $(hostprogs-y) +always-y := $(hostprogs) all: mei-amt-version diff --git a/samples/pidfd/Makefile b/samples/pidfd/Makefile index 0ff97784177a..ee2979849d92 100644 --- a/samples/pidfd/Makefile +++ b/samples/pidfd/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -hostprogs-y := pidfd-metadata -always := $(hostprogs-y) +hostprogs := pidfd-metadata +always-y := $(hostprogs) HOSTCFLAGS_pidfd-metadata.o += -I$(objtree)/usr/include all: pidfd-metadata diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile index 009775b52538..89279e8b87df 100644 --- a/samples/seccomp/Makefile +++ b/samples/seccomp/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 ifndef CROSS_COMPILE -hostprogs-y := bpf-fancy dropper bpf-direct user-trap +hostprogs := bpf-fancy dropper bpf-direct user-trap HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include HOSTCFLAGS_bpf-fancy.o += -idirafter $(objtree)/include @@ -40,5 +40,5 @@ HOSTLDLIBS_bpf-fancy += $(MFLAG) HOSTLDLIBS_dropper += $(MFLAG) HOSTLDLIBS_user-trap += $(MFLAG) endif -always := $(hostprogs-y) +always-y := $(hostprogs) endif diff --git a/samples/uhid/Makefile b/samples/uhid/Makefile index 8c9bc9f98d37..5f44ea40d6d5 100644 --- a/samples/uhid/Makefile +++ b/samples/uhid/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only # List of programs to build -hostprogs-y := uhid-example +hostprogs := uhid-example # Tell kbuild to always build the programs -always := $(hostprogs-y) +always-y := $(hostprogs) HOSTCFLAGS_uhid-example.o += -I$(objtree)/usr/include diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile index e21c9f6fe9be..65acdde5c117 100644 --- a/samples/vfs/Makefile +++ b/samples/vfs/Makefile @@ -1,11 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only # List of programs to build -hostprogs-y := \ +hostprogs := \ test-fsmount \ test-statx -# Tell kbuild to always build the programs -always := $(hostprogs-y) +always-y := $(hostprogs) HOSTCFLAGS_test-fsmount.o += -I$(objtree)/usr/include HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include diff --git a/scripts/Makefile b/scripts/Makefile index 4d41f48e7376..5e75802b1a44 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -7,14 +7,14 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -hostprogs-$(CONFIG_BUILD_BIN2C) += bin2c -hostprogs-$(CONFIG_KALLSYMS) += kallsyms -hostprogs-$(BUILD_C_RECORDMCOUNT) += recordmcount -hostprogs-$(CONFIG_BUILDTIME_TABLE_SORT) += sorttable -hostprogs-$(CONFIG_ASN1) += asn1_compiler -hostprogs-$(CONFIG_MODULE_SIG_FORMAT) += sign-file -hostprogs-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert -hostprogs-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert +always-$(CONFIG_BUILD_BIN2C) += bin2c +always-$(CONFIG_KALLSYMS) += kallsyms +always-$(BUILD_C_RECORDMCOUNT) += recordmcount +always-$(CONFIG_BUILDTIME_TABLE_SORT) += sorttable +always-$(CONFIG_ASN1) += asn1_compiler +always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file +always-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert +always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include @@ -30,10 +30,10 @@ HOSTCFLAGS_sorttable.o += -DUNWINDER_ORC_ENABLED HOSTLDLIBS_sorttable = -lpthread endif -always := $(hostprogs-y) $(hostprogs-m) +hostprogs := $(always-y) $(always-m) -# The following hostprogs-y programs are only build on demand -hostprogs-y += unifdef +# The following programs are only built on demand +hostprogs += unifdef subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins subdir-$(CONFIG_MODVERSIONS) += genksyms diff --git a/scripts/Makefile.build b/scripts/Makefile.build index a562d695f0fa..a1730d42e5f3 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -16,6 +16,8 @@ obj-m := lib-y := lib-m := always := +always-y := +always-m := targets := subdir-y := subdir-m := @@ -44,7 +46,7 @@ include $(kbuild-file) include scripts/Makefile.lib # Do not include host rules unless needed -ifneq ($(hostprogs-y)$(hostprogs-m)$(hostlibs-y)$(hostlibs-m)$(hostcxxlibs-y)$(hostcxxlibs-m),) +ifneq ($(hostprogs)$(hostlibs-y)$(hostlibs-m)$(hostcxxlibs-y)$(hostcxxlibs-m),) include scripts/Makefile.host endif @@ -348,7 +350,7 @@ $(obj)/%.o: $(src)/%.S $(objtool_dep) FORCE $(call if_changed_rule,as_o_S) targets += $(filter-out $(subdir-obj-y), $(real-obj-y)) $(real-obj-m) $(lib-y) -targets += $(extra-y) $(MAKECMDGOALS) $(always) +targets += $(extra-y) $(always-y) $(MAKECMDGOALS) # Linker scripts preprocessor (.lds.S -> .lds) # --------------------------------------------------------------------------- @@ -490,7 +492,7 @@ else __build: $(if $(KBUILD_BUILTIN),$(builtin-target) $(lib-target) $(extra-y)) \ $(if $(KBUILD_MODULES),$(obj-m) $(mod-targets) $(modorder-target)) \ - $(subdir-ym) $(always) + $(subdir-ym) $(always-y) @: endif diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index e367eb95c5c0..1e4206566a82 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -28,8 +28,8 @@ subdir-ymn := $(addprefix $(obj)/,$(subdir-ymn)) # directory __clean-files := $(extra-y) $(extra-m) $(extra-) \ - $(always) $(targets) $(clean-files) \ - $(hostprogs-y) $(hostprogs-m) $(hostprogs-) \ + $(always) $(always-y) $(always-m) $(always-) $(targets) $(clean-files) \ + $(hostprogs) $(hostprogs-y) $(hostprogs-m) $(hostprogs-) \ $(hostlibs-y) $(hostlibs-m) $(hostlibs-) \ $(hostcxxlibs-y) $(hostcxxlibs-m) diff --git a/scripts/Makefile.host b/scripts/Makefile.host index 4c51c95d40f4..3b7121d43324 100644 --- a/scripts/Makefile.host +++ b/scripts/Makefile.host @@ -24,21 +24,21 @@ $(obj)/%.tab.c $(obj)/%.tab.h: $(src)/%.y FORCE # Both C and C++ are supported, but preferred language is C for such utilities. # # Sample syntax (see Documentation/kbuild/makefiles.rst for reference) -# hostprogs-y := bin2hex +# hostprogs := bin2hex # Will compile bin2hex.c and create an executable named bin2hex # -# hostprogs-y := lxdialog +# hostprogs := lxdialog # lxdialog-objs := checklist.o lxdialog.o # Will compile lxdialog.c and checklist.c, and then link the executable # lxdialog, based on checklist.o and lxdialog.o # -# hostprogs-y := qconf +# hostprogs := qconf # qconf-cxxobjs := qconf.o # qconf-objs := menu.o # Will compile qconf as a C++ program, and menu as a C program. # They are linked as C++ code to the executable qconf -__hostprogs := $(sort $(hostprogs-y) $(hostprogs-m)) +__hostprogs := $(sort $(hostprogs)) host-cshlib := $(sort $(hostlibs-y) $(hostlibs-m)) host-cxxshlib := $(sort $(hostcxxlibs-y) $(hostcxxlibs-m)) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index d10f7a03e0ee..bae62549e3d2 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -4,6 +4,8 @@ asflags-y += $(EXTRA_AFLAGS) ccflags-y += $(EXTRA_CFLAGS) cppflags-y += $(EXTRA_CPPFLAGS) ldflags-y += $(EXTRA_LDFLAGS) +always-y += $(always) +hostprogs += $(hostprogs-y) $(hostprogs-m) # flags that take effect in current and sub directories KBUILD_AFLAGS += $(subdir-asflags-y) @@ -59,6 +61,8 @@ subdir-obj-y := $(filter %/built-in.a, $(obj-y)) real-obj-y := $(foreach m, $(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-))),$($(m:.o=-objs)) $($(m:.o=-y)),$(m))) real-obj-m := $(foreach m, $(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m)) $($(m:.o=-))),$($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m)),$(m))) +always-y += $(always-m) + # DTB # If CONFIG_OF_ALL_DTBS is enabled, all DT blobs are built extra-y += $(dtb-y) @@ -72,7 +76,7 @@ endif # Add subdir path extra-y := $(addprefix $(obj)/,$(extra-y)) -always := $(addprefix $(obj)/,$(always)) +always-y := $(addprefix $(obj)/,$(always-y)) targets := $(addprefix $(obj)/,$(targets)) modorder := $(addprefix $(obj)/,$(modorder)) obj-m := $(addprefix $(obj)/,$(obj-m)) diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile index 7c9cb80d097b..290dd27d2809 100644 --- a/scripts/basic/Makefile +++ b/scripts/basic/Makefile @@ -2,5 +2,5 @@ # # fixdep: used to generate dependency information during build process -hostprogs-y := fixdep -always := $(hostprogs-y) +hostprogs := fixdep +always-y := $(hostprogs) diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile index b5a5b1c548c9..3acbb410904c 100644 --- a/scripts/dtc/Makefile +++ b/scripts/dtc/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # scripts/dtc makefile -hostprogs-$(CONFIG_DTC) := dtc -always := $(hostprogs-y) +hostprogs := dtc +always-$(CONFIG_DTC) := $(hostprogs) dtc-objs := dtc.o flattree.o fstree.o data.o livetree.o treesource.o \ srcpos.o checks.o util.o diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index aa0d0ec6936d..f2ee8bd7abc6 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -23,7 +23,7 @@ $(objtree)/$(obj)/randomize_layout_seed.h: FORCE targets = randomize_layout_seed.h randomize_layout_hash.h $(HOSTLIBS)-y := $(foreach p,$(GCC_PLUGIN),$(if $(findstring /,$(p)),,$(p))) -always := $($(HOSTLIBS)-y) +always-y := $($(HOSTLIBS)-y) $(foreach p,$($(HOSTLIBS)-y:%.so=%),$(eval $(p)-objs := $(p).o)) diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile index 78629f515e78..d328de1e10ee 100644 --- a/scripts/genksyms/Makefile +++ b/scripts/genksyms/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -hostprogs-y := genksyms -always := $(hostprogs-y) +hostprogs := genksyms +always-y := $(hostprogs) genksyms-objs := genksyms.o parse.tab.o lex.lex.o diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 94153732ec00..a566d8201b56 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -33,8 +33,8 @@ struct sym_entry { unsigned long long addr; unsigned int len; unsigned int start_pos; - unsigned char *sym; unsigned int percpu_absolute; + unsigned char sym[0]; }; struct addr_range { @@ -55,7 +55,7 @@ static struct addr_range percpu_range = { "__per_cpu_start", "__per_cpu_end", -1ULL, 0 }; -static struct sym_entry *table; +static struct sym_entry **table; static unsigned int table_size, table_cnt; static int all_symbols; static int absolute_percpu; @@ -174,49 +174,55 @@ static void check_symbol_range(const char *sym, unsigned long long addr, } } -static int read_symbol(FILE *in, struct sym_entry *s) +static struct sym_entry *read_symbol(FILE *in) { - char sym[500], stype; + char name[500], type; + unsigned long long addr; + unsigned int len; + struct sym_entry *sym; int rc; - rc = fscanf(in, "%llx %c %499s\n", &s->addr, &stype, sym); + rc = fscanf(in, "%llx %c %499s\n", &addr, &type, name); if (rc != 3) { - if (rc != EOF && fgets(sym, 500, in) == NULL) + if (rc != EOF && fgets(name, 500, in) == NULL) fprintf(stderr, "Read error or end of file.\n"); - return -1; + return NULL; } - if (strlen(sym) >= KSYM_NAME_LEN) { + if (strlen(name) >= KSYM_NAME_LEN) { fprintf(stderr, "Symbol %s too long for kallsyms (%zu >= %d).\n" "Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n", - sym, strlen(sym), KSYM_NAME_LEN); - return -1; + name, strlen(name), KSYM_NAME_LEN); + return NULL; } - if (is_ignored_symbol(sym, stype)) - return -1; + if (is_ignored_symbol(name, type)) + return NULL; /* Ignore most absolute/undefined (?) symbols. */ - if (strcmp(sym, "_text") == 0) - _text = s->addr; + if (strcmp(name, "_text") == 0) + _text = addr; - check_symbol_range(sym, s->addr, text_ranges, ARRAY_SIZE(text_ranges)); - check_symbol_range(sym, s->addr, &percpu_range, 1); + check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges)); + check_symbol_range(name, addr, &percpu_range, 1); /* include the type field in the symbol name, so that it gets * compressed together */ - s->len = strlen(sym) + 1; - s->sym = malloc(s->len + 1); - if (!s->sym) { + + len = strlen(name) + 1; + + sym = malloc(sizeof(*sym) + len); + if (!sym) { fprintf(stderr, "kallsyms failure: " "unable to allocate required amount of memory\n"); exit(EXIT_FAILURE); } - strcpy(sym_name(s), sym); - s->sym[0] = stype; + sym->addr = addr; + sym->len = len; + sym->sym[0] = type; + memcpy(sym_name(sym), name, len); + sym->percpu_absolute = 0; - s->percpu_absolute = 0; - - return 0; + return sym; } static int symbol_in_range(const struct sym_entry *s, @@ -268,12 +274,12 @@ static void shrink_table(void) pos = 0; for (i = 0; i < table_cnt; i++) { - if (symbol_valid(&table[i])) { + if (symbol_valid(table[i])) { if (pos != i) table[pos] = table[i]; pos++; } else { - free(table[i].sym); + free(table[i]); } } table_cnt = pos; @@ -287,7 +293,15 @@ static void shrink_table(void) static void read_map(FILE *in) { + struct sym_entry *sym; + while (!feof(in)) { + sym = read_symbol(in); + if (!sym) + continue; + + sym->start_pos = table_cnt; + if (table_cnt >= table_size) { table_size += 10000; table = realloc(table, sizeof(*table) * table_size); @@ -296,10 +310,8 @@ static void read_map(FILE *in) exit (1); } } - if (read_symbol(in, &table[table_cnt]) == 0) { - table[table_cnt].start_pos = table_cnt; - table_cnt++; - } + + table[table_cnt++] = sym; } } @@ -387,27 +399,27 @@ static void write_src(void) int overflow; if (!absolute_percpu) { - offset = table[i].addr - relative_base; + offset = table[i]->addr - relative_base; overflow = (offset < 0 || offset > UINT_MAX); - } else if (symbol_absolute(&table[i])) { - offset = table[i].addr; + } else if (symbol_absolute(table[i])) { + offset = table[i]->addr; overflow = (offset < 0 || offset > INT_MAX); } else { - offset = relative_base - table[i].addr - 1; + offset = relative_base - table[i]->addr - 1; overflow = (offset < INT_MIN || offset >= 0); } if (overflow) { fprintf(stderr, "kallsyms failure: " "%s symbol value %#llx out of range in relative mode\n", - symbol_absolute(&table[i]) ? "absolute" : "relative", - table[i].addr); + symbol_absolute(table[i]) ? "absolute" : "relative", + table[i]->addr); exit(EXIT_FAILURE); } printf("\t.long\t%#x\n", (int)offset); - } else if (!symbol_absolute(&table[i])) { - output_address(table[i].addr); + } else if (!symbol_absolute(table[i])) { + output_address(table[i]->addr); } else { - printf("\tPTR\t%#llx\n", table[i].addr); + printf("\tPTR\t%#llx\n", table[i]->addr); } } printf("\n"); @@ -437,12 +449,12 @@ static void write_src(void) if ((i & 0xFF) == 0) markers[i >> 8] = off; - printf("\t.byte 0x%02x", table[i].len); - for (k = 0; k < table[i].len; k++) - printf(", 0x%02x", table[i].sym[k]); + printf("\t.byte 0x%02x", table[i]->len); + for (k = 0; k < table[i]->len; k++) + printf(", 0x%02x", table[i]->sym[k]); printf("\n"); - off += table[i].len + 1; + off += table[i]->len + 1; } printf("\n"); @@ -496,7 +508,7 @@ static void build_initial_tok_table(void) unsigned int i; for (i = 0; i < table_cnt; i++) - learn_symbol(table[i].sym, table[i].len); + learn_symbol(table[i]->sym, table[i]->len); } static unsigned char *find_token(unsigned char *str, int len, @@ -520,15 +532,15 @@ static void compress_symbols(const unsigned char *str, int idx) for (i = 0; i < table_cnt; i++) { - len = table[i].len; - p1 = table[i].sym; + len = table[i]->len; + p1 = table[i]->sym; /* find the token on the symbol */ p2 = find_token(p1, len, str); if (!p2) continue; /* decrease the counts for this symbol's tokens */ - forget_symbol(table[i].sym, len); + forget_symbol(table[i]->sym, len); size = len; @@ -547,10 +559,10 @@ static void compress_symbols(const unsigned char *str, int idx) } while (p2); - table[i].len = len; + table[i]->len = len; /* increase the counts for this symbol's new tokens */ - learn_symbol(table[i].sym, len); + learn_symbol(table[i]->sym, len); } } @@ -606,8 +618,8 @@ static void insert_real_symbols_in_table(void) unsigned int i, j, c; for (i = 0; i < table_cnt; i++) { - for (j = 0; j < table[i].len; j++) { - c = table[i].sym[j]; + for (j = 0; j < table[i]->len; j++) { + c = table[i]->sym[j]; best_table[c][0]=c; best_table_len[c]=1; } @@ -660,13 +672,10 @@ static int may_be_linker_script_provide_symbol(const struct sym_entry *se) static int compare_symbols(const void *a, const void *b) { - const struct sym_entry *sa; - const struct sym_entry *sb; + const struct sym_entry *sa = *(const struct sym_entry **)a; + const struct sym_entry *sb = *(const struct sym_entry **)b; int wa, wb; - sa = a; - sb = b; - /* sort by address first */ if (sa->addr > sb->addr) return 1; @@ -697,7 +706,7 @@ static int compare_symbols(const void *a, const void *b) static void sort_symbols(void) { - qsort(table, table_cnt, sizeof(struct sym_entry), compare_symbols); + qsort(table, table_cnt, sizeof(table[0]), compare_symbols); } static void make_percpus_absolute(void) @@ -705,14 +714,14 @@ static void make_percpus_absolute(void) unsigned int i; for (i = 0; i < table_cnt; i++) - if (symbol_in_range(&table[i], &percpu_range, 1)) { + if (symbol_in_range(table[i], &percpu_range, 1)) { /* * Keep the 'A' override for percpu symbols to * ensure consistent behavior compared to older * versions of this tool. */ - table[i].sym[0] = 'A'; - table[i].percpu_absolute = 1; + table[i]->sym[0] = 'A'; + table[i]->percpu_absolute = 1; } } @@ -722,12 +731,12 @@ static void record_relative_base(void) unsigned int i; for (i = 0; i < table_cnt; i++) - if (!symbol_absolute(&table[i])) { + if (!symbol_absolute(table[i])) { /* * The table is sorted by address. * Take the first non-absolute symbol value. */ - relative_base = table[i].addr; + relative_base = table[i]->addr; return; } } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index fbeb62ae3401..5887ceb6229e 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -157,11 +157,11 @@ HOSTCFLAGS_lexer.lex.o := -I $(srctree)/$(src) HOSTCFLAGS_parser.tab.o := -I $(srctree)/$(src) # conf: Used for defconfig, oldconfig and related targets -hostprogs-y += conf +hostprogs += conf conf-objs := conf.o $(common-objs) # nconf: Used for the nconfig target based on ncurses -hostprogs-y += nconf +hostprogs += nconf nconf-objs := nconf.o nconf.gui.o $(common-objs) HOSTLDLIBS_nconf = $(shell . $(obj)/nconf-cfg && echo $$libs) @@ -171,7 +171,7 @@ HOSTCFLAGS_nconf.gui.o = $(shell . $(obj)/nconf-cfg && echo $$cflags) $(obj)/nconf.o $(obj)/nconf.gui.o: $(obj)/nconf-cfg # mconf: Used for the menuconfig target based on lxdialog -hostprogs-y += mconf +hostprogs += mconf lxdialog := $(addprefix lxdialog/, \ checklist.o inputbox.o menubox.o textbox.o util.o yesno.o) mconf-objs := mconf.o $(lxdialog) $(common-objs) @@ -183,7 +183,7 @@ $(foreach f, mconf.o $(lxdialog), \ $(addprefix $(obj)/, mconf.o $(lxdialog)): $(obj)/mconf-cfg # qconf: Used for the xconfig target based on Qt -hostprogs-y += qconf +hostprogs += qconf qconf-cxxobjs := qconf.o qconf-objs := images.o $(common-objs) @@ -199,7 +199,7 @@ $(obj)/%.moc: $(src)/%.h $(obj)/qconf-cfg $(call cmd,moc) # gconf: Used for the gconfig target based on GTK+ -hostprogs-y += gconf +hostprogs += gconf gconf-objs := gconf.o images.o $(common-objs) HOSTLDLIBS_gconf = $(shell . $(obj)/gconf-cfg && echo $$libs) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 11f6c72c2eee..a39d93e3c6ae 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -1312,7 +1312,7 @@ bool conf_set_all_new_symbols(enum conf_def_mode mode) sym_calc_value(csym); if (mode == def_random) - has_changed = randomize_choice_values(csym); + has_changed |= randomize_choice_values(csym); else { set_all_choice_values(csym); has_changed = true; @@ -1331,9 +1331,8 @@ void conf_rewrite_mod_or_yes(enum conf_def_mode mode) for_all_symbols(i, sym) { if (sym_get_type(sym) == S_TRISTATE && - sym->def[S_DEF_USER].tri == old_val) { + sym->def[S_DEF_USER].tri == old_val) sym->def[S_DEF_USER].tri = new_val; - sym_add_change_count(1); - } } + sym_clear_all_valid(); } diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile index 42c5d50f2bcc..296b6a3878b2 100644 --- a/scripts/mod/Makefile +++ b/scripts/mod/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD := y -hostprogs-y := modpost mk_elfconfig -always := $(hostprogs-y) empty.o +hostprogs := modpost mk_elfconfig +always-y := $(hostprogs) empty.o modpost-objs := modpost.o file2alias.o sumversion.o diff --git a/scripts/selinux/genheaders/Makefile b/scripts/selinux/genheaders/Makefile index e8c533140981..70cf8d95d07c 100644 --- a/scripts/selinux/genheaders/Makefile +++ b/scripts/selinux/genheaders/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -hostprogs-y := genheaders +hostprogs := genheaders HOST_EXTRACFLAGS += \ -I$(srctree)/include/uapi -I$(srctree)/include \ -I$(srctree)/security/selinux/include -always := $(hostprogs-y) +always-y := $(hostprogs) diff --git a/scripts/selinux/mdp/Makefile b/scripts/selinux/mdp/Makefile index 8a1269a9d0ba..3026f3c2aa2b 100644 --- a/scripts/selinux/mdp/Makefile +++ b/scripts/selinux/mdp/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -hostprogs-y := mdp +hostprogs := mdp HOST_EXTRACFLAGS += \ -I$(srctree)/include/uapi -I$(srctree)/include \ -I$(srctree)/security/selinux/include -I$(objtree)/include -always := $(hostprogs-y) +always-y := $(hostprogs) clean-files := policy.* file_contexts diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 446ba891f1e2..941873d778d8 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -580,7 +580,7 @@ probe_large_insn_limit(const char *define_prefix, __u32 ifindex) res = bpf_probe_large_insn_limit(ifindex); print_bool_feature("have_large_insn_limit", "Large program size limit", - "HAVE_LARGE_INSN_LIMIT", + "LARGE_INSN_LIMIT", res, define_prefix); } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index a3521deca869..b352ab041160 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -536,7 +536,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, buf = (unsigned char *)(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ - if (info->xlated_prog_len == 0) { + if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); return -1; } diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 0c021352beed..39edd68afa8e 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -41,7 +41,7 @@ clean: $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) $(call msg,BINARY,$@) - $(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@ + $(Q)$(CC) $(CFLAGS) $^ -lelf -lz -o $@ $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ $(OUTPUT)/runqslower.bpf.o @@ -75,7 +75,7 @@ $(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) fi $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ -$(BPFOBJ): | $(OUTPUT) +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ OUTPUT=$(abspath $(dir $@))/ $(abspath $@) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index ede040cf82ad..2898cfdf8fe1 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -226,7 +226,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG) continue; - sink = term->val.drv_cfg; + sink = term->val.str; snprintf(path, PATH_MAX, "sinks/%s", sink); ret = perf_pmu__scan_file(pmu, path, "%x", &hash); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 4ac56741ac5f..29c793ac7d10 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -131,7 +131,6 @@ int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_un TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5); cpu_map__snprint(c, buf, sizeof(buf)); TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7")); - perf_cpu_map__put(a); perf_cpu_map__put(b); perf_cpu_map__put(c); return 0; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a69e64236120..c8dc4450884c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -808,12 +808,12 @@ static void apply_config_terms(struct evsel *evsel, perf_evsel__reset_sample_bit(evsel, TIME); break; case PERF_EVSEL__CONFIG_TERM_CALLGRAPH: - callgraph_buf = term->val.callgraph; + callgraph_buf = term->val.str; break; case PERF_EVSEL__CONFIG_TERM_BRANCH: - if (term->val.branch && strcmp(term->val.branch, "no")) { + if (term->val.str && strcmp(term->val.str, "no")) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); - parse_branch_str(term->val.branch, + parse_branch_str(term->val.str, &attr->branch_sample_type); } else perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); @@ -1265,6 +1265,8 @@ static void perf_evsel__free_config_terms(struct evsel *evsel) list_for_each_entry_safe(term, h, &evsel->config_terms, list) { list_del_init(&term->list); + if (term->free_str) + zfree(&term->val.str); free(term); } } diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index 1f8d2fe0b66e..e026ab67b008 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -32,22 +32,21 @@ enum evsel_term_type { struct perf_evsel_config_term { struct list_head list; enum evsel_term_type type; + bool free_str; union { u64 period; u64 freq; bool time; - char *callgraph; - char *drv_cfg; u64 stack_user; int max_stack; bool inherit; bool overwrite; - char *branch; unsigned long max_events; bool percore; bool aux_output; u32 aux_sample_size; u64 cfg_chg; + char *str; } val; bool weak; }; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index fdd5bddb3075..f67960bedebb 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -549,6 +549,7 @@ void maps__insert(struct maps *maps, struct map *map) if (maps_by_name == NULL) { __maps__free_maps_by_name(maps); + up_write(&maps->lock); return; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index ed7c008b9c8b..c01ba6f8fdad 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1219,8 +1219,7 @@ static int config_attr(struct perf_event_attr *attr, static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused) { -#define ADD_CONFIG_TERM(__type, __name, __val) \ -do { \ +#define ADD_CONFIG_TERM(__type) \ struct perf_evsel_config_term *__t; \ \ __t = zalloc(sizeof(*__t)); \ @@ -1229,9 +1228,24 @@ do { \ \ INIT_LIST_HEAD(&__t->list); \ __t->type = PERF_EVSEL__CONFIG_TERM_ ## __type; \ - __t->val.__name = __val; \ __t->weak = term->weak; \ - list_add_tail(&__t->list, head_terms); \ + list_add_tail(&__t->list, head_terms) + +#define ADD_CONFIG_TERM_VAL(__type, __name, __val) \ +do { \ + ADD_CONFIG_TERM(__type); \ + __t->val.__name = __val; \ +} while (0) + +#define ADD_CONFIG_TERM_STR(__type, __val) \ +do { \ + ADD_CONFIG_TERM(__type); \ + __t->val.str = strdup(__val); \ + if (!__t->val.str) { \ + zfree(&__t); \ + return -ENOMEM; \ + } \ + __t->free_str = true; \ } while (0) struct parse_events_term *term; @@ -1239,53 +1253,62 @@ do { \ list_for_each_entry(term, head_config, list) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: - ADD_CONFIG_TERM(PERIOD, period, term->val.num); + ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: - ADD_CONFIG_TERM(FREQ, freq, term->val.num); + ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_TIME: - ADD_CONFIG_TERM(TIME, time, term->val.num); + ADD_CONFIG_TERM_VAL(TIME, time, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: - ADD_CONFIG_TERM(CALLGRAPH, callgraph, term->val.str); + ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: - ADD_CONFIG_TERM(BRANCH, branch, term->val.str); + ADD_CONFIG_TERM_STR(BRANCH, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_STACKSIZE: - ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num); + ADD_CONFIG_TERM_VAL(STACK_USER, stack_user, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_INHERIT: - ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(INHERIT, inherit, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_NOINHERIT: - ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1); + ADD_CONFIG_TERM_VAL(INHERIT, inherit, + term->val.num ? 0 : 1); break; case PARSE_EVENTS__TERM_TYPE_MAX_STACK: - ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num); + ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: - ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num); + ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_OVERWRITE: - ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: - ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1); + ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, + term->val.num ? 0 : 1); break; case PARSE_EVENTS__TERM_TYPE_DRV_CFG: - ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str); + ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_PERCORE: - ADD_CONFIG_TERM(PERCORE, percore, - term->val.num ? true : false); + ADD_CONFIG_TERM_VAL(PERCORE, percore, + term->val.num ? true : false); break; case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: - ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: - ADD_CONFIG_TERM(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num); + ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, + term->val.num); break; default: break; @@ -1322,7 +1345,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, } if (bits) - ADD_CONFIG_TERM(CFG_CHG, cfg_chg, bits); + ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits); #undef ADD_CONFIG_TERM return 0; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c470c49a804f..1c817add6ca4 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -303,7 +303,8 @@ static int convert_variable_type(Dwarf_Die *vr_die, char prefix; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "x") != 0 && + if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "ustring") && + strcmp(cast, "x") != 0 && strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ /* and respect signedness/hexadecimal cast */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 6ccf6f6d09df..5b7d6c16d33f 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -193,16 +193,30 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data) bfd_vma pc, vma; bfd_size_type size; struct a2l_data *a2l = data; + flagword flags; if (a2l->found) return; - if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0) +#ifdef bfd_get_section_flags + flags = bfd_get_section_flags(abfd, section); +#else + flags = bfd_section_flags(section); +#endif + if ((flags & SEC_ALLOC) == 0) return; pc = a2l->addr; +#ifdef bfd_get_section_vma vma = bfd_get_section_vma(abfd, section); +#else + vma = bfd_section_vma(section); +#endif +#ifdef bfd_get_section_size size = bfd_get_section_size(section); +#else + size = bfd_section_size(section); +#endif if (pc < vma || pc >= vma + size) return; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c new file mode 100644 index 000000000000..07f5b462c2ef --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare + +#include "test_progs.h" + +static int connected_socket_v4(void) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_port = htons(80), + .sin_addr = { inet_addr("127.0.0.1") }, + }; + socklen_t len = sizeof(addr); + int s, repair, err; + + s = socket(AF_INET, SOCK_STREAM, 0); + if (CHECK_FAIL(s == -1)) + goto error; + + repair = TCP_REPAIR_ON; + err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair)); + if (CHECK_FAIL(err)) + goto error; + + err = connect(s, (struct sockaddr *)&addr, len); + if (CHECK_FAIL(err)) + goto error; + + repair = TCP_REPAIR_OFF_NO_WP; + err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair)); + if (CHECK_FAIL(err)) + goto error; + + return s; +error: + perror(__func__); + close(s); + return -1; +} + +/* Create a map, populate it with one socket, and free the map. */ +static void test_sockmap_create_update_free(enum bpf_map_type map_type) +{ + const int zero = 0; + int s, map, err; + + s = connected_socket_v4(); + if (CHECK_FAIL(s == -1)) + return; + + map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + if (CHECK_FAIL(map == -1)) { + perror("bpf_create_map"); + goto out; + } + + err = bpf_map_update_elem(map, &zero, &s, BPF_NOEXIST); + if (CHECK_FAIL(err)) { + perror("bpf_map_update"); + goto out; + } + +out: + close(map); + close(s); +} + +void test_sockmap_basic(void) +{ + if (test__start_subtest("sockmap create_update_free")) + test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP); + if (test__start_subtest("sockhash create_update_free")) + test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH); +} diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index 1235f3d1cc50..1f6ccdaed1ac 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -46,7 +46,7 @@ void test_trampoline_count(void) const char *fentry_name = "fentry/__set_task_comm"; const char *fexit_name = "fexit/__set_task_comm"; const char *object = "test_trampoline_count.o"; - struct inst inst[MAX_TRAMP_PROGS] = { 0 }; + struct inst inst[MAX_TRAMP_PROGS] = {}; int err, i = 0, duration = 0; struct bpf_object *obj; struct bpf_link *link; diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh index 45115f81c2b1..eab79b9e58cd 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/fib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh @@ -14,6 +14,7 @@ ALL_TESTS=" ipv4_plen ipv4_replay ipv4_flush + ipv4_local_replace ipv6_add ipv6_metric ipv6_append_single @@ -26,6 +27,7 @@ ALL_TESTS=" ipv6_delete_multipath ipv6_replay_single ipv6_replay_multipath + ipv6_local_replace " NUM_NETIFS=0 source $lib_dir/lib.sh @@ -89,6 +91,43 @@ ipv4_flush() fib_ipv4_flush_test "testns1" } +ipv4_local_replace() +{ + local ns="testns1" + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add table local 192.0.2.1/32 dev dummy1 + fib4_trap_check $ns "table local 192.0.2.1/32 dev dummy1" false + check_err $? "Local table route not in hardware when should" + + ip -n $ns route add table main 192.0.2.1/32 dev dummy1 + fib4_trap_check $ns "table main 192.0.2.1/32 dev dummy1" true + check_err $? "Main table route in hardware when should not" + + fib4_trap_check $ns "table local 192.0.2.1/32 dev dummy1" false + check_err $? "Local table route was replaced when should not" + + # Test that local routes can replace routes in main table. + ip -n $ns route add table main 192.0.2.2/32 dev dummy1 + fib4_trap_check $ns "table main 192.0.2.2/32 dev dummy1" false + check_err $? "Main table route not in hardware when should" + + ip -n $ns route add table local 192.0.2.2/32 dev dummy1 + fib4_trap_check $ns "table local 192.0.2.2/32 dev dummy1" false + check_err $? "Local table route did not replace route in main table when should" + + fib4_trap_check $ns "table main 192.0.2.2/32 dev dummy1" true + check_err $? "Main table route was not replaced when should" + + log_test "IPv4 local table route replacement" + + ip -n $ns link del dev dummy1 +} + ipv6_add() { fib_ipv6_add_test "testns1" @@ -149,6 +188,43 @@ ipv6_replay_multipath() fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" } +ipv6_local_replace() +{ + local ns="testns1" + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add table local 2001:db8:1::1/128 dev dummy1 + fib6_trap_check $ns "table local 2001:db8:1::1/128 dev dummy1" false + check_err $? "Local table route not in hardware when should" + + ip -n $ns route add table main 2001:db8:1::1/128 dev dummy1 + fib6_trap_check $ns "table main 2001:db8:1::1/128 dev dummy1" true + check_err $? "Main table route in hardware when should not" + + fib6_trap_check $ns "table local 2001:db8:1::1/128 dev dummy1" false + check_err $? "Local table route was replaced when should not" + + # Test that local routes can replace routes in main table. + ip -n $ns route add table main 2001:db8:1::2/128 dev dummy1 + fib6_trap_check $ns "table main 2001:db8:1::2/128 dev dummy1" false + check_err $? "Main table route not in hardware when should" + + ip -n $ns route add table local 2001:db8:1::2/128 dev dummy1 + fib6_trap_check $ns "table local 2001:db8:1::2/128 dev dummy1" false + check_err $? "Local route route did not replace route in main table when should" + + fib6_trap_check $ns "table main 2001:db8:1::2/128 dev dummy1" true + check_err $? "Main table route was not replaced when should" + + log_test "IPv6 local table route replacement" + + ip -n $ns link del dev dummy1 +} + setup_prepare() { ip netns add testns1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index a3dccd816ae4..99579c0223c1 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -634,6 +634,14 @@ static void check_getpeername_connect(int fd) cfg_host, a, cfg_port, b); } +static void maybe_close(int fd) +{ + unsigned int r = rand(); + + if (r & 1) + close(fd); +} + int main_loop_s(int listensock) { struct sockaddr_storage ss; @@ -657,6 +665,7 @@ int main_loop_s(int listensock) salen = sizeof(ss); remotesock = accept(listensock, (struct sockaddr *)&ss, &salen); if (remotesock >= 0) { + maybe_close(listensock); check_sockaddr(pf, &ss, salen); check_getpeername(remotesock, &ss, salen); diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index d5c85c7494f2..f5ab1cda8bb5 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -38,9 +38,8 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } sleep() { read -t "$1" -N 1 || true; } -waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; } -waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } -waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } +waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } cleanup() { @@ -119,22 +118,22 @@ tests() { # TCP over IPv4 n2 iperf3 -s -1 -B 192.168.241.2 & - waitiperf $netns2 + waitiperf $netns2 $! n1 iperf3 -Z -t 3 -c 192.168.241.2 # TCP over IPv6 n1 iperf3 -s -1 -B fd00::1 & - waitiperf $netns1 + waitiperf $netns1 $! n2 iperf3 -Z -t 3 -c fd00::1 # UDP over IPv4 n1 iperf3 -s -1 -B 192.168.241.1 & - waitiperf $netns1 + waitiperf $netns1 $! n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1 # UDP over IPv6 n2 iperf3 -s -1 -B fd00::2 & - waitiperf $netns2 + waitiperf $netns2 $! n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 } @@ -207,7 +206,7 @@ n1 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24 exec 4< <(n1 ncat -l -u -p 1111) ncat_pid=$! -waitncatudp $netns1 +waitncatudp $netns1 $ncat_pid n2 ncat -u 192.168.241.1 1111 <<<"X" read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]] kill $ncat_pid @@ -216,7 +215,7 @@ n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32 n2 wg set wg0 listen-port 9997 exec 4< <(n1 ncat -l -u -p 1111) ncat_pid=$! -waitncatudp $netns1 +waitncatudp $netns1 $ncat_pid n2 ncat -u 192.168.241.1 1111 <<<"X" ! read -r -N 1 -t 1 out <&4 || false kill $ncat_pid @@ -516,6 +515,12 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16. n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0 n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 n0 wg set wg0 peer "$pub2" allowed-ips ::/0 +n0 wg set wg0 peer "$pub2" remove +low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= ) +n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer } +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer } +[[ -z $(n0 wg show wg0 peers) ]] ip0 link del wg0 declare -A objects diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index b9c72706fe4d..5909e7ef2a5c 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -1,5 +1,4 @@ CONFIG_LOCALVERSION="-debug" -CONFIG_ENABLE_WARN_DEPRECATED=y CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_POINTER=y CONFIG_STACK_VALIDATION=y diff --git a/usr/Makefile b/usr/Makefile index b6081bb2cc72..c12e6b15ce72 100644 --- a/usr/Makefile +++ b/usr/Makefile @@ -52,7 +52,7 @@ ifeq ($(cpio-data),) cpio-data := $(obj)/initramfs_data.cpio -hostprogs-y := gen_init_cpio +hostprogs := gen_init_cpio # .initramfs_data.cpio.d is used to identify all files included # in initramfs and to detect if any files are added/removed.