diff options
602 files changed, 8436 insertions, 7172 deletions
@@ -25,6 +25,8 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com> Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru> Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com> Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru> +Alexander Mikhalitsyn <alexander@mihalicyn.com> <alexander.mikhalitsyn@virtuozzo.com> +Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@canonical.com> Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com> Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com> Alexei Starovoitov <ast@kernel.org> <ast@fb.com> diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index bb4681a01811..284224d1b56f 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -4,7 +4,8 @@ Contact: "Huang Jianan" <huangjianan@oppo.com> Description: Shows all enabled kernel features. Supported features: zero_padding, compr_cfgs, big_pcluster, chunked_file, - device_table, compr_head2, sb_chksum. + device_table, compr_head2, sb_chksum, ztailpacking, + dedupe, fragments. What: /sys/fs/erofs/<disk>/sync_decompress Date: November 2021 diff --git a/Documentation/admin-guide/hw-vuln/cross-thread-rsb.rst b/Documentation/admin-guide/hw-vuln/cross-thread-rsb.rst new file mode 100644 index 000000000000..875616d675fe --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/cross-thread-rsb.rst @@ -0,0 +1,91 @@ + +.. SPDX-License-Identifier: GPL-2.0 + +Cross-Thread Return Address Predictions +======================================= + +Certain AMD and Hygon processors are subject to a cross-thread return address +predictions vulnerability. When running in SMT mode and one sibling thread +transitions out of C0 state, the other sibling thread could use return target +predictions from the sibling thread that transitioned out of C0. + +The Spectre v2 mitigations protect the Linux kernel, as it fills the return +address prediction entries with safe targets when context switching to the idle +thread. However, KVM does allow a VMM to prevent exiting guest mode when +transitioning out of C0. This could result in a guest-controlled return target +being consumed by the sibling thread. + +Affected processors +------------------- + +The following CPUs are vulnerable: + + - AMD Family 17h processors + - Hygon Family 18h processors + +Related CVEs +------------ + +The following CVE entry is related to this issue: + + ============== ======================================= + CVE-2022-27672 Cross-Thread Return Address Predictions + ============== ======================================= + +Problem +------- + +Affected SMT-capable processors support 1T and 2T modes of execution when SMT +is enabled. In 2T mode, both threads in a core are executing code. For the +processor core to enter 1T mode, it is required that one of the threads +requests to transition out of the C0 state. This can be communicated with the +HLT instruction or with an MWAIT instruction that requests non-C0. +When the thread re-enters the C0 state, the processor transitions back +to 2T mode, assuming the other thread is also still in C0 state. + +In affected processors, the return address predictor (RAP) is partitioned +depending on the SMT mode. For instance, in 2T mode each thread uses a private +16-entry RAP, but in 1T mode, the active thread uses a 32-entry RAP. Upon +transition between 1T/2T mode, the RAP contents are not modified but the RAP +pointers (which control the next return target to use for predictions) may +change. This behavior may result in return targets from one SMT thread being +used by RET predictions in the sibling thread following a 1T/2T switch. In +particular, a RET instruction executed immediately after a transition to 1T may +use a return target from the thread that just became idle. In theory, this +could lead to information disclosure if the return targets used do not come +from trustworthy code. + +Attack scenarios +---------------- + +An attack can be mounted on affected processors by performing a series of CALL +instructions with targeted return locations and then transitioning out of C0 +state. + +Mitigation mechanism +-------------------- + +Before entering idle state, the kernel context switches to the idle thread. The +context switch fills the RAP entries (referred to as the RSB in Linux) with safe +targets by performing a sequence of CALL instructions. + +Prevent a guest VM from directly putting the processor into an idle state by +intercepting HLT and MWAIT instructions. + +Both mitigations are required to fully address this issue. + +Mitigation control on the kernel command line +--------------------------------------------- + +Use existing Spectre v2 mitigations that will fill the RSB on context switch. + +Mitigation control for KVM - module parameter +--------------------------------------------- + +By default, the KVM hypervisor mitigates this issue by intercepting guest +attempts to transition out of C0. A VMM can use the KVM_CAP_X86_DISABLE_EXITS +capability to override those interceptions, but since this is not common, the +mitigation that covers this path is not enabled by default. + +The mitigation for the KVM_CAP_X86_DISABLE_EXITS capability can be turned on +using the boolean module parameter mitigate_smt_rsb, e.g. ``kvm.mitigate_smt_rsb=1``. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 4df436e7c417..e0614760a99e 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -18,3 +18,4 @@ are configurable at compile, boot or run time. core-scheduling.rst l1d_flush.rst processor_mmio_stale_data.rst + cross-thread-rsb.rst diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index ef183387da20..eccd327e6df5 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -1277,8 +1277,8 @@ the file contents themselves, as described below: For the read path (->read_folio()) of regular files, filesystems can read the ciphertext into the page cache and decrypt it in-place. The -page lock must be held until decryption has finished, to prevent the -page from becoming visible to userspace prematurely. +folio lock must be held until decryption has finished, to prevent the +folio from becoming visible to userspace prematurely. For the write path (->writepage()) of regular files, filesystems cannot encrypt data in-place in the page cache, since the cached diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index cb8e7573882a..ede672dedf11 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -118,10 +118,11 @@ as follows: - ``hash_algorithm`` must be the identifier for the hash algorithm to use for the Merkle tree, such as FS_VERITY_HASH_ALG_SHA256. See ``include/uapi/linux/fsverity.h`` for the list of possible values. -- ``block_size`` must be the Merkle tree block size. Currently, this - must be equal to the system page size, which is usually 4096 bytes. - Other sizes may be supported in the future. This value is not - necessarily the same as the filesystem block size. +- ``block_size`` is the Merkle tree block size, in bytes. In Linux + v6.3 and later, this can be any power of 2 between (inclusively) + 1024 and the minimum of the system page size and the filesystem + block size. In earlier versions, the page size was the only allowed + value. - ``salt_size`` is the size of the salt in bytes, or 0 if no salt is provided. The salt is a value that is prepended to every hashed block; it can be used to personalize the hashing for a particular @@ -161,6 +162,7 @@ FS_IOC_ENABLE_VERITY can fail with the following errors: - ``EBUSY``: this ioctl is already running on the file - ``EEXIST``: the file already has verity enabled - ``EFAULT``: the caller provided inaccessible memory +- ``EFBIG``: the file is too large to enable verity on - ``EINTR``: the operation was interrupted by a fatal signal - ``EINVAL``: unsupported version, hash algorithm, or block size; or reserved bits are set; or the file descriptor refers to neither a @@ -495,9 +497,11 @@ To create verity files on an ext4 filesystem, the filesystem must have been formatted with ``-O verity`` or had ``tune2fs -O verity`` run on it. "verity" is an RO_COMPAT filesystem feature, so once set, old kernels will only be able to mount the filesystem readonly, and old -versions of e2fsck will be unable to check the filesystem. Moreover, -currently ext4 only supports mounting a filesystem with the "verity" -feature when its block size is equal to PAGE_SIZE (often 4096 bytes). +versions of e2fsck will be unable to check the filesystem. + +Originally, an ext4 filesystem with the "verity" feature could only be +mounted when its block size was equal to the system page size +(typically 4096 bytes). In Linux v6.3, this limitation was removed. ext4 sets the EXT4_VERITY_FL on-disk inode flag on verity files. It can only be set by `FS_IOC_ENABLE_VERITY`_, and it cannot be cleared. @@ -518,9 +522,7 @@ support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. -Currently, ext4 verity only supports the case where the Merkle tree -block size, filesystem block size, and page size are all the same. It -also only supports extent-based files. +ext4 only allows verity on extent-based files. f2fs ---- @@ -538,11 +540,10 @@ Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. See explanation for ext4 above. Moreover, f2fs supports at most 4096 bytes of xattr entries per inode -which wouldn't be enough for even a single Merkle tree block. +which usually wouldn't be enough for even a single Merkle tree block. -Currently, f2fs verity only supports a Merkle tree block size of 4096. -Also, f2fs doesn't support enabling verity on files that currently -have atomic or volatile writes pending. +f2fs doesn't support enabling verity on files that currently have +atomic or volatile writes pending. btrfs ----- @@ -567,51 +568,48 @@ Pagecache ~~~~~~~~~ For filesystems using Linux's pagecache, the ``->read_folio()`` and -``->readahead()`` methods must be modified to verify pages before they -are marked Uptodate. Merely hooking ``->read_iter()`` would be +``->readahead()`` methods must be modified to verify folios before +they are marked Uptodate. Merely hooking ``->read_iter()`` would be insufficient, since ``->read_iter()`` is not used for memory maps. -Therefore, fs/verity/ provides a function fsverity_verify_page() which -verifies a page that has been read into the pagecache of a verity -inode, but is still locked and not Uptodate, so it's not yet readable -by userspace. As needed to do the verification, -fsverity_verify_page() will call back into the filesystem to read -Merkle tree pages via fsverity_operations::read_merkle_tree_page(). +Therefore, fs/verity/ provides the function fsverity_verify_blocks() +which verifies data that has been read into the pagecache of a verity +inode. The containing folio must still be locked and not Uptodate, so +it's not yet readable by userspace. As needed to do the verification, +fsverity_verify_blocks() will call back into the filesystem to read +hash blocks via fsverity_operations::read_merkle_tree_page(). -fsverity_verify_page() returns false if verification failed; in this -case, the filesystem must not set the page Uptodate. Following this, +fsverity_verify_blocks() returns false if verification failed; in this +case, the filesystem must not set the folio Uptodate. Following this, as per the usual Linux pagecache behavior, attempts by userspace to -read() from the part of the file containing the page will fail with -EIO, and accesses to the page within a memory map will raise SIGBUS. - -fsverity_verify_page() currently only supports the case where the -Merkle tree block size is equal to PAGE_SIZE (often 4096 bytes). +read() from the part of the file containing the folio will fail with +EIO, and accesses to the folio within a memory map will raise SIGBUS. -In principle, fsverity_verify_page() verifies the entire path in the -Merkle tree from the data page to the root hash. However, for -efficiency the filesystem may cache the hash pages. Therefore, -fsverity_verify_page() only ascends the tree reading hash pages until -an already-verified hash page is seen, as indicated by the PageChecked -bit being set. It then verifies the path to that page. +In principle, verifying a data block requires verifying the entire +path in the Merkle tree from the data block to the root hash. +However, for efficiency the filesystem may cache the hash blocks. +Therefore, fsverity_verify_blocks() only ascends the tree reading hash +blocks until an already-verified hash block is seen. It then verifies +the path to that block. This optimization, which is also used by dm-verity, results in excellent sequential read performance. This is because usually (e.g. -127 in 128 times for 4K blocks and SHA-256) the hash page from the +127 in 128 times for 4K blocks and SHA-256) the hash block from the bottom level of the tree will already be cached and checked from -reading a previous data page. However, random reads perform worse. +reading a previous data block. However, random reads perform worse. Block device based filesystems ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Block device based filesystems (e.g. ext4 and f2fs) in Linux also use the pagecache, so the above subsection applies too. However, they -also usually read many pages from a file at once, grouped into a +also usually read many data blocks from a file at once, grouped into a structure called a "bio". To make it easier for these types of filesystems to support fs-verity, fs/verity/ also provides a function -fsverity_verify_bio() which verifies all pages in a bio. +fsverity_verify_bio() which verifies all data blocks in a bio. ext4 and f2fs also support encryption. If a verity file is also -encrypted, the pages must be decrypted before being verified. To +encrypted, the data must be decrypted before being verified. To support this, these filesystems allocate a "post-read context" for each bio and store it in ``->bi_private``:: @@ -626,14 +624,14 @@ each bio and store it in ``->bi_private``:: verity, or both is enabled. After the bio completes, for each needed postprocessing step the filesystem enqueues the bio_post_read_ctx on a workqueue, and then the workqueue work does the decryption or -verification. Finally, pages where no decryption or verity error -occurred are marked Uptodate, and the pages are unlocked. +verification. Finally, folios where no decryption or verity error +occurred are marked Uptodate, and the folios are unlocked. On many filesystems, files can contain holes. Normally, -``->readahead()`` simply zeroes holes and sets the corresponding pages -Uptodate; no bios are issued. To prevent this case from bypassing -fs-verity, these filesystems use fsverity_verify_page() to verify hole -pages. +``->readahead()`` simply zeroes hole blocks and considers the +corresponding data to be up-to-date; no bios are issued. To prevent +this case from bypassing fs-verity, filesystems use +fsverity_verify_blocks() to verify hole blocks. Filesystems also disable direct I/O on verity files, since otherwise direct I/O would bypass fs-verity. @@ -644,7 +642,7 @@ Userspace utility This document focuses on the kernel, but a userspace utility for fs-verity can be found at: - https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/fsverity-utils.git + https://git.kernel.org/pub/scm/fs/fsverity/fsverity-utils.git See the README.md file in the fsverity-utils source tree for details, including examples of setting up fs-verity protected files. @@ -793,9 +791,9 @@ weren't already directly answered in other parts of this document. :A: There are many reasons why this is not possible or would be very difficult, including the following: - - To prevent bypassing verification, pages must not be marked + - To prevent bypassing verification, folios must not be marked Uptodate until they've been verified. Currently, each - filesystem is responsible for marking pages Uptodate via + filesystem is responsible for marking folios Uptodate via ``->readahead()``. Therefore, currently it's not possible for the VFS to do the verification on its own. Changing this would require significant changes to the VFS and all filesystems. diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 36fa2a83d714..7de7a7272a5e 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -56,35 +56,35 @@ inode_operations prototypes:: - int (*create) (struct inode *,struct dentry *,umode_t, bool); + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t, bool); struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,umode_t); + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *); + int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t); + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, unsigned int); + int (*permission) (struct mnt_idmap *, struct inode *, int, unsigned int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); + int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); void (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct user_namespace *, struct inode *, + int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); - int (*fileattr_set)(struct user_namespace *mnt_userns, + int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); - struct posix_acl * (*get_acl)(struct user_namespace *, struct dentry *, int); + struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int); locking rules: all may block @@ -135,7 +135,7 @@ prototypes:: struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 2c15e7053113..c53f30251a66 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -421,31 +421,31 @@ As of kernel 2.6.22, the following members are defined: .. code-block:: c struct inode_operations { - int (*create) (struct user_namespace *, struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct user_namespace *, struct inode *,struct dentry *,const char *); - int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *,umode_t); + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *); + int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct user_namespace *, struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct user_namespace *, struct inode *, struct dentry *, + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t); + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct user_namespace *, struct inode *, int); + int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); - int (*setattr) (struct user_namespace *, struct dentry *, struct iattr *); - int (*getattr) (struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); + int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); + int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); void (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct user_namespace *, struct inode *, struct file *, umode_t); - struct posix_acl * (*get_acl)(struct user_namespace *, struct dentry *, int); - int (*set_acl)(struct user_namespace *, struct dentry *, struct posix_acl *, int); - int (*fileattr_set)(struct user_namespace *mnt_userns, + int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); + struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int); + int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); + int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); }; diff --git a/MAINTAINERS b/MAINTAINERS index 39ff1a717625..82938ca70466 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7747,6 +7747,7 @@ R: Jeffle Xu <jefflexu@linux.alibaba.com> L: linux-erofs@lists.ozlabs.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git +F: Documentation/ABI/testing/sysfs-fs-erofs F: Documentation/filesystems/erofs.rst F: fs/erofs/ F: include/trace/events/erofs.h @@ -8202,7 +8203,7 @@ F: drivers/fpga/microchip-spi.c FPU EMULATOR M: Bill Metzenthen <billm@melbpc.org.au> S: Maintained -W: http://floatingpoint.sourceforge.net/emulator/index.html +W: https://floatingpoint.billm.au/ F: arch/x86/math-emu/ FRAMEBUFFER CORE @@ -9996,7 +9997,7 @@ S: Maintained T: git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git F: Documentation/filesystems/idmappings.rst F: tools/testing/selftests/mount_setattr/ -F: include/linux/mnt_idmapping.h +F: include/linux/mnt_idmapping.* IDT VersaClock 5 CLOCK DRIVER M: Luca Ceresoli <luca@lucaceresoli.net> @@ -18234,6 +18235,7 @@ L: rust-for-linux@vger.kernel.org S: Supported W: https://github.com/Rust-for-Linux/linux B: https://github.com/Rust-for-Linux/linux/issues +C: zulip://rust-for-linux.zulipchat.com T: git https://github.com/Rust-for-Linux/linux.git rust-next F: Documentation/rust/ F: rust/ @@ -20323,8 +20325,7 @@ S: Maintained F: drivers/platform/x86/system76_acpi.c SYSV FILESYSTEM -M: Christoph Hellwig <hch@infradead.org> -S: Maintained +S: Orphan F: Documentation/filesystems/sysv-fs.rst F: fs/sysv/ F: include/linux/sysv_fs.h @@ -21819,11 +21820,9 @@ W: http://en.wikipedia.org/wiki/Util-linux T: git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git UUID HELPERS -M: Christoph Hellwig <hch@lst.de> R: Andy Shevchenko <andriy.shevchenko@linux.intel.com> L: linux-kernel@vger.kernel.org S: Maintained -T: git git://git.infradead.org/users/hch/uuid.git F: include/linux/uuid.h F: include/uapi/linux/uuid.h F: lib/test_uuid.c @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -1602,7 +1602,7 @@ endif # CONFIG_MODULES CLEAN_FILES += include/ksym vmlinux.symvers modules-only.symvers \ modules.builtin modules.builtin.modinfo modules.nsdeps \ compile_commands.json .thinlto-cache rust/test rust/doc \ - .vmlinux.objs .vmlinux.export.c + rust-project.json .vmlinux.objs .vmlinux.export.c # Directories & files removed with 'make mrproper' MRPROPER_FILES += include/config include/generated \ diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 68112c172025..006163195d67 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -73,6 +73,7 @@ #include <linux/syscalls.h> #include <linux/errno.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/cred.h> #include <linux/fcntl.h> #include <linux/eventpoll.h> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index a5193f2146a6..dde06c0f97f3 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1023,12 +1023,6 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, return 0; } -static bool armv8pmu_filter(struct pmu *pmu, int cpu) -{ - struct arm_pmu *armpmu = to_arm_pmu(pmu); - return !cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus); -} - static void armv8pmu_reset(void *info) { struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; @@ -1069,6 +1063,14 @@ static int __armv8_pmuv3_map_event(struct perf_event *event, &armv8_pmuv3_perf_cache_map, ARMV8_PMU_EVTYPE_EVENT); + /* + * CHAIN events only work when paired with an adjacent counter, and it + * never makes sense for a user to open one in isolation, as they'll be + * rotated arbitrarily. + */ + if (hw_event_id == ARMV8_PMUV3_PERFCTR_CHAIN) + return -EINVAL; + if (armv8pmu_event_is_64bit(event)) event->hw.flags |= ARMPMU_EVT_64BIT; @@ -1258,7 +1260,6 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, cpu_pmu->stop = armv8pmu_stop; cpu_pmu->reset = armv8pmu_reset; cpu_pmu->set_event_filter = armv8pmu_set_event_filter; - cpu_pmu->filter = armv8pmu_filter; cpu_pmu->pmu.event_idx = armv8pmu_user_event_idx; diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index d5cd16270c5d..2bbc0fcce04a 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -97,8 +97,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) radix__tlb_flush(tlb); - - return hash__tlb_flush(tlb); + else + hash__tlb_flush(tlb); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index dbcfe361831a..ea807aa0c31a 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -92,7 +92,7 @@ out: } static int -spufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +spufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -100,7 +100,7 @@ spufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if ((attr->ia_valid & ATTR_SIZE) && (attr->ia_size != inode->i_size)) return -EINVAL; - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -237,7 +237,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags, if (!inode) return -ENOSPC; - inode_init_owner(&init_user_ns, inode, dir, mode | S_IFDIR); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode | S_IFDIR); ctx = alloc_spu_context(SPUFS_I(dir)->i_gang); /* XXX gang */ SPUFS_I(inode)->i_ctx = ctx; if (!ctx) { @@ -468,7 +468,7 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode) goto out; ret = 0; - inode_init_owner(&init_user_ns, inode, dir, mode | S_IFDIR); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode | S_IFDIR); gang = alloc_spu_gang(); SPUFS_I(inode)->i_ctx = NULL; SPUFS_I(inode)->i_gang = gang; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 85a63a41c471..d096b04bf80e 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2974,17 +2974,19 @@ unsigned long perf_misc_flags(struct pt_regs *regs) void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) { - if (!x86_pmu_initialized()) { + /* This API doesn't currently support enumerating hybrid PMUs. */ + if (WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) || + !x86_pmu_initialized()) { memset(cap, 0, sizeof(*cap)); return; } - cap->version = x86_pmu.version; /* - * KVM doesn't support the hybrid PMU yet. - * Return the common value in global x86_pmu, - * which available for all cores. + * Note, hybrid CPU models get tracked as having hybrid PMUs even when + * all E-cores are disabled via BIOS. When E-cores are disabled, the + * base PMU holds the correct number of counters for P-cores. */ + cap->version = x86_pmu.version; cap->num_counters_gp = x86_pmu.num_counters; cap->num_counters_fixed = x86_pmu.num_counters_fixed; cap->bit_width_gp = x86_pmu.cntval_bits; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 61012476d66e..8f39c46197b8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -466,5 +466,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9cfca3d7d0e2..f3cc7699e1e1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1256,6 +1256,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define MMIO_SBDS BIT(2) /* CPU is affected by RETbleed, speculating where you would not expect it */ #define RETBLEED BIT(3) +/* CPU is affected by SMT (cross-thread) return predictions */ +#define SMT_RSB BIT(4) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1287,8 +1289,8 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED), - VULNBL_HYGON(0x18, RETBLEED), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), {} }; @@ -1406,6 +1408,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !(ia32_cap & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) + setup_force_cpu_bug(X86_BUG_SMT_RSB); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index cdb91009701d..ee67ba625094 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -165,15 +165,27 @@ static inline void kvm_init_pmu_capability(void) { bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL; - perf_get_x86_pmu_capability(&kvm_pmu_cap); - - /* - * For Intel, only support guest architectural pmu - * on a host with architectural pmu. - */ - if ((is_intel && !kvm_pmu_cap.version) || !kvm_pmu_cap.num_counters_gp) + /* + * Hybrid PMUs don't play nice with virtualization without careful + * configuration by userspace, and KVM's APIs for reporting supported + * vPMU features do not account for hybrid PMUs. Disable vPMU support + * for hybrid PMUs until KVM gains a way to let userspace opt-in. + */ + if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) enable_pmu = false; + if (enable_pmu) { + perf_get_x86_pmu_capability(&kvm_pmu_cap); + + /* + * For Intel, only support guest architectural pmu + * on a host with architectural pmu. + */ + if ((is_intel && !kvm_pmu_cap.version) || + !kvm_pmu_cap.num_counters_gp) + enable_pmu = false; + } + if (!enable_pmu) { memset(&kvm_pmu_cap, 0, sizeof(kvm_pmu_cap)); return; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index da4bbd043a7b..a2c299d47e69 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -191,6 +191,10 @@ module_param(enable_pmu, bool, 0444); bool __read_mostly eager_page_split = true; module_param(eager_page_split, bool, 0644); +/* Enable/disable SMT_RSB bug mitigation */ +bool __read_mostly mitigate_smt_rsb; +module_param(mitigate_smt_rsb, bool, 0444); + /* * Restoring the host value for MSRs that are only consumed when running in * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU @@ -4448,10 +4452,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: - r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE | - KVM_X86_DISABLE_EXITS_CSTATE; - if(kvm_can_mwait_in_guest()) - r |= KVM_X86_DISABLE_EXITS_MWAIT; + r = KVM_X86_DISABLE_EXITS_PAUSE; + + if (!mitigate_smt_rsb) { + r |= KVM_X86_DISABLE_EXITS_HLT | + KVM_X86_DISABLE_EXITS_CSTATE; + + if (kvm_can_mwait_in_guest()) + r |= KVM_X86_DISABLE_EXITS_MWAIT; + } break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) @@ -5254,12 +5263,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, @@ -6227,15 +6235,26 @@ split_irqchip_unlock: if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) break; - if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && - kvm_can_mwait_in_guest()) - kvm->arch.mwait_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) - kvm->arch.hlt_in_guest = true; if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) kvm->arch.pause_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) - kvm->arch.cstate_in_guest = true; + +#define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ + "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." + + if (!mitigate_smt_rsb) { + if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && + (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) + pr_warn_once(SMT_RSB_MSG); + + if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && + kvm_can_mwait_in_guest()) + kvm->arch.mwait_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) + kvm->arch.hlt_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) + kvm->arch.cstate_in_guest = true; + } + r = 0; break; case KVM_CAP_MSR_PLATFORM_INFO: @@ -13456,6 +13475,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); static int __init kvm_x86_init(void) { kvm_mmu_x86_module_init(); + mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; } module_init(kvm_x86_init); diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index fb4b1b5e0dea..46de9cf5c91d 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -387,8 +387,7 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, u8 mtrr_type, uniform; mtrr_type = mtrr_type_lookup(start, end, &uniform); - if (mtrr_type != MTRR_TYPE_WRBACK && - mtrr_type != MTRR_TYPE_INVALID) + if (mtrr_type != MTRR_TYPE_WRBACK) return _PAGE_CACHE_MODE_UC_MINUS; return _PAGE_CACHE_MODE_WB; diff --git a/certs/blacklist.c b/certs/blacklist.c index 41f10601cc72..675dd7a8f07a 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -183,16 +183,19 @@ static int mark_raw_hash_blacklisted(const char *hash) { key_ref_t key; - key = key_create_or_update(make_key_ref(blacklist_keyring, true), - "blacklist", - hash, - NULL, - 0, - BLACKLIST_KEY_PERM, - KEY_ALLOC_NOT_IN_QUOTA | - KEY_ALLOC_BUILT_IN); + key = key_create(make_key_ref(blacklist_keyring, true), + "blacklist", + hash, + NULL, + 0, + BLACKLIST_KEY_PERM, + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_BUILT_IN); if (IS_ERR(key)) { - pr_err("Problem blacklisting hash (%ld)\n", PTR_ERR(key)); + if (PTR_ERR(key) == -EEXIST) + pr_warn("Duplicate blacklisted hash %s\n", hash); + else + pr_err("Problem blacklisting hash %s: %pe\n", hash, key); return PTR_ERR(key); } return 0; diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index 3df3fe4ed95f..1ef3b46d6f6e 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -83,6 +83,6 @@ config FIPS_SIGNATURE_SELFTEST for FIPS. depends on KEYS depends on ASYMMETRIC_KEY_TYPE - depends on PKCS7_MESSAGE_PARSER + depends on PKCS7_MESSAGE_PARSER=X509_CERTIFICATE_PARSER endif # ASYMMETRIC_KEY_TYPE diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index f6321c785714..4fa769c4bcdb 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -485,3 +485,4 @@ int pkcs7_supply_detached_data(struct pkcs7_message *pkcs7, pkcs7->data_len = datalen; return 0; } +EXPORT_SYMBOL_GPL(pkcs7_supply_detached_data); diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index 2f8352e88860..eca5671ad3f2 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -186,8 +186,28 @@ static int software_key_query(const struct kernel_pkey_params *params, len = crypto_akcipher_maxsize(tfm); info->key_size = len * 8; - info->max_data_size = len; - info->max_sig_size = len; + + if (strncmp(pkey->pkey_algo, "ecdsa", 5) == 0) { + /* + * ECDSA key sizes are much smaller than RSA, and thus could + * operate on (hashed) inputs that are larger than key size. + * For example SHA384-hashed input used with secp256r1 + * based keys. Set max_data_size to be at least as large as + * the largest supported hash size (SHA512) + */ + info->max_data_size = 64; + + /* + * Verify takes ECDSA-Sig (described in RFC 5480) as input, + * which is actually 2 'key_size'-bit integers encoded in + * ASN.1. Account for the ASN.1 encoding overhead here. + */ + info->max_sig_size = 2 * (len + 3) + 2; + } else { + info->max_data_size = len; + info->max_sig_size = len; + } + info->max_enc_size = len; info->max_dec_size = len; info->supported_ops = (KEYCTL_SUPPORTS_ENCRYPT | diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 09b2ce7e4c34..348d63d1e3d3 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -352,7 +352,7 @@ static inline bool is_binderfs_control_device(const struct dentry *dentry) return info->control_dentry == dentry; } -static int binderfs_rename(struct user_namespace *mnt_userns, +static int binderfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -361,7 +361,7 @@ static int binderfs_rename(struct user_namespace *mnt_userns, is_binderfs_control_device(new_dentry)) return -EPERM; - return simple_rename(&init_user_ns, old_dir, old_dentry, new_dir, + return simple_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags); } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 14a1c0d14916..3bb9bb483fe3 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -421,6 +421,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_low_power }, /* Ice Lake LP AHCI */ { PCI_VDEVICE(INTEL, 0x02d3), board_ahci_low_power }, /* Comet Lake PCH-U AHCI */ { PCI_VDEVICE(INTEL, 0x02d7), board_ahci_low_power }, /* Comet Lake PCH RAID */ + { PCI_VDEVICE(INTEL, 0xa0d3), board_ahci_low_power }, /* Tiger Lake UP{3,4} AHCI */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 2ea572628b1c..c4c89d24f84c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4045,6 +4045,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NO_NCQ_ON_ATI }, + { "SAMSUNG*MZ7LH*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM }, diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c index 35608a0cf552..4cbcdc5da038 100644 --- a/drivers/ata/pata_octeon_cf.c +++ b/drivers/ata/pata_octeon_cf.c @@ -67,7 +67,7 @@ module_param(enable_dma, int, 0444); MODULE_PARM_DESC(enable_dma, "Enable use of DMA on interfaces that support it (0=no dma [default], 1=use dma)"); -/** +/* * Convert nanosecond based time to setting used in the * boot bus timing register, based on timing multiple */ @@ -114,7 +114,7 @@ static void octeon_cf_set_boot_reg_cfg(int cs, unsigned int multiplier) cvmx_write_csr(CVMX_MIO_BOOT_REG_CFGX(cs), reg_cfg.u64); } -/** +/* * Called after libata determines the needed PIO mode. This * function programs the Octeon bootbus regions to support the * timing requirements of the PIO mode. @@ -278,7 +278,7 @@ static void octeon_cf_set_dmamode(struct ata_port *ap, struct ata_device *dev) cvmx_write_csr(cf_port->dma_base + DMA_TIM, dma_tim.u64); } -/** +/* * Handle an 8 bit I/O request. * * @qc: Queued command @@ -317,7 +317,7 @@ static unsigned int octeon_cf_data_xfer8(struct ata_queued_cmd *qc, return buflen; } -/** +/* * Handle a 16 bit I/O request. * * @qc: Queued command @@ -372,7 +372,7 @@ static unsigned int octeon_cf_data_xfer16(struct ata_queued_cmd *qc, return buflen; } -/** +/* * Read the taskfile for 16bit non-True IDE only. */ static void octeon_cf_tf_read16(struct ata_port *ap, struct ata_taskfile *tf) @@ -453,7 +453,7 @@ static int octeon_cf_softreset16(struct ata_link *link, unsigned int *classes, return 0; } -/** +/* * Load the taskfile for 16bit non-True IDE only. The device_addr is * not loaded, we do this as part of octeon_cf_exec_command16. */ @@ -525,7 +525,7 @@ static void octeon_cf_dma_setup(struct ata_queued_cmd *qc) ap->ops->sff_exec_command(ap, &qc->tf); } -/** +/* * Start a DMA transfer that was already setup * * @qc: Information about the DMA @@ -580,7 +580,7 @@ static void octeon_cf_dma_start(struct ata_queued_cmd *qc) cvmx_write_csr(cf_port->dma_base + DMA_CFG, mio_boot_dma_cfg.u64); } -/** +/* * * LOCKING: * spin_lock_irqsave(host lock) diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index e4bffeabf344..03e8a95f1f35 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -173,7 +173,7 @@ static int dev_mkdir(const char *name, umode_t mode) if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mkdir(&init_user_ns, d_inode(path.dentry), dentry, mode); + err = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode); if (!err) /* mark as kernel-created inode */ d_inode(dentry)->i_private = &thread; @@ -223,7 +223,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid, if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mknod(&init_user_ns, d_inode(path.dentry), dentry, mode, + err = vfs_mknod(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode, dev->devt); if (!err) { struct iattr newattrs; @@ -233,7 +233,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid, newattrs.ia_gid = gid; newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID; inode_lock(d_inode(dentry)); - notify_change(&init_user_ns, dentry, &newattrs, NULL); + notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); /* mark as kernel-created inode */ @@ -254,7 +254,7 @@ static int dev_rmdir(const char *name) return PTR_ERR(dentry); if (d_really_is_positive(dentry)) { if (d_inode(dentry)->i_private == &thread) - err = vfs_rmdir(&init_user_ns, d_inode(parent.dentry), + err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry), dentry); else err = -EPERM; @@ -341,9 +341,9 @@ static int handle_remove(const char *nodename, struct device *dev) newattrs.ia_valid = ATTR_UID|ATTR_GID|ATTR_MODE; inode_lock(d_inode(dentry)); - notify_change(&init_user_ns, dentry, &newattrs, NULL); + notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); - err = vfs_unlink(&init_user_ns, d_inode(parent.dentry), + err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry), dentry, NULL); if (!err || err == -ENOENT) deleted = 1; diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 0913d3eb8d51..40360e599bc3 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -14,6 +14,7 @@ * Access to the event log extended by the TCG BIOS of PC platform */ +#include <linux/device.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/security.h> @@ -135,7 +136,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip) } /* malloc EventLog space */ - log->bios_event_log = kmalloc(len, GFP_KERNEL); + log->bios_event_log = devm_kmalloc(&chip->dev, len, GFP_KERNEL); if (!log->bios_event_log) return -ENOMEM; @@ -160,7 +161,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip) return format; err: - kfree(log->bios_event_log); + devm_kfree(&chip->dev, log->bios_event_log); log->bios_event_log = NULL; return ret; } diff --git a/drivers/char/tpm/eventlog/efi.c b/drivers/char/tpm/eventlog/efi.c index e6cb9d525e30..4e9d7c2bf32e 100644 --- a/drivers/char/tpm/eventlog/efi.c +++ b/drivers/char/tpm/eventlog/efi.c @@ -6,6 +6,7 @@ * Thiebaud Weksteen <tweek@google.com> */ +#include <linux/device.h> #include <linux/efi.h> #include <linux/tpm_eventlog.h> @@ -55,7 +56,7 @@ int tpm_read_log_efi(struct tpm_chip *chip) } /* malloc EventLog space */ - log->bios_event_log = kmemdup(log_tbl->log, log_size, GFP_KERNEL); + log->bios_event_log = devm_kmemdup(&chip->dev, log_tbl->log, log_size, GFP_KERNEL); if (!log->bios_event_log) { ret = -ENOMEM; goto out; @@ -76,7 +77,7 @@ int tpm_read_log_efi(struct tpm_chip *chip) MEMREMAP_WB); if (!final_tbl) { pr_err("Could not map UEFI TPM final log\n"); - kfree(log->bios_event_log); + devm_kfree(&chip->dev, log->bios_event_log); ret = -ENOMEM; goto out; } @@ -91,11 +92,11 @@ int tpm_read_log_efi(struct tpm_chip *chip) * Allocate memory for the 'combined log' where we will append the * 'final events log' to. */ - tmp = krealloc(log->bios_event_log, - log_size + final_events_log_size, - GFP_KERNEL); + tmp = devm_krealloc(&chip->dev, log->bios_event_log, + log_size + final_events_log_size, + GFP_KERNEL); if (!tmp) { - kfree(log->bios_event_log); + devm_kfree(&chip->dev, log->bios_event_log); ret = -ENOMEM; goto out; } diff --git a/drivers/char/tpm/eventlog/of.c b/drivers/char/tpm/eventlog/of.c index a9ce66d09a75..930fe43d5daf 100644 --- a/drivers/char/tpm/eventlog/of.c +++ b/drivers/char/tpm/eventlog/of.c @@ -10,13 +10,44 @@ * Read the event log created by the firmware on PPC64 */ +#include <linux/device.h> #include <linux/slab.h> +#include <linux/io.h> +#include <linux/ioport.h> #include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_reserved_mem.h> #include <linux/tpm_eventlog.h> #include "../tpm.h" #include "common.h" +static int tpm_read_log_memory_region(struct tpm_chip *chip) +{ + struct device_node *node; + struct resource res; + int rc; + + node = of_parse_phandle(chip->dev.parent->of_node, "memory-region", 0); + if (!node) + return -ENODEV; + + rc = of_address_to_resource(node, 0, &res); + of_node_put(node); + if (rc) + return rc; + + chip->log.bios_event_log = devm_memremap(&chip->dev, res.start, resource_size(&res), + MEMREMAP_WB); + if (IS_ERR(chip->log.bios_event_log)) + return -ENOMEM; + + chip->log.bios_event_log_end = chip->log.bios_event_log + resource_size(&res); + + return chip->flags & TPM_CHIP_FLAG_TPM2 ? EFI_TCG2_EVENT_LOG_FORMAT_TCG_2 : + EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; +} + int tpm_read_log_of(struct tpm_chip *chip) { struct device_node *np; @@ -38,7 +69,7 @@ int tpm_read_log_of(struct tpm_chip *chip) sizep = of_get_property(np, "linux,sml-size", NULL); basep = of_get_property(np, "linux,sml-base", NULL); if (sizep == NULL && basep == NULL) - return -ENODEV; + return tpm_read_log_memory_region(chip); if (sizep == NULL || basep == NULL) return -EIO; @@ -65,7 +96,7 @@ int tpm_read_log_of(struct tpm_chip *chip) return -EIO; } - log->bios_event_log = kmemdup(__va(base), size, GFP_KERNEL); + log->bios_event_log = devm_kmemdup(&chip->dev, __va(base), size, GFP_KERNEL); if (!log->bios_event_log) return -ENOMEM; diff --git a/drivers/char/tpm/st33zp24/i2c.c b/drivers/char/tpm/st33zp24/i2c.c index 8156bb2af78c..c4d0b744e3cc 100644 --- a/drivers/char/tpm/st33zp24/i2c.c +++ b/drivers/char/tpm/st33zp24/i2c.c @@ -101,8 +101,7 @@ static const struct st33zp24_phy_ops i2c_phy_ops = { * @return: 0 in case of success. * -1 in other case. */ -static int st33zp24_i2c_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int st33zp24_i2c_probe(struct i2c_client *client) { struct st33zp24_i2c_phy *phy; @@ -161,7 +160,7 @@ static struct i2c_driver st33zp24_i2c_driver = { .of_match_table = of_match_ptr(of_st33zp24_i2c_match), .acpi_match_table = ACPI_PTR(st33zp24_i2c_acpi_match), }, - .probe = st33zp24_i2c_probe, + .probe_new = st33zp24_i2c_probe, .remove = st33zp24_i2c_remove, .id_table = st33zp24_i2c_id }; diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 741d8f3e8fb3..b99f55f2d4fd 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -267,7 +267,6 @@ static void tpm_dev_release(struct device *dev) idr_remove(&dev_nums_idr, chip->dev_num); mutex_unlock(&idr_lock); - kfree(chip->log.bios_event_log); kfree(chip->work_space.context_buf); kfree(chip->work_space.session_buf); kfree(chip->allocated_banks); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 65d03867e114..93545be190a5 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -777,10 +777,12 @@ out: int tpm2_find_cc(struct tpm_chip *chip, u32 cc) { + u32 cc_mask; int i; + cc_mask = 1 << TPM2_CC_ATTR_VENDOR | GENMASK(15, 0); for (i = 0; i < chip->nr_commands; i++) - if (cc == (chip->cc_attrs_tbl[i] & GENMASK(15, 0))) + if (cc == (chip->cc_attrs_tbl[i] & cc_mask)) return i; return -1; diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 7e9da671a0e8..d43a0d7b97a8 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -98,6 +98,8 @@ struct crb_priv { u8 __iomem *rsp; u32 cmd_size; u32 smc_func_id; + u32 __iomem *pluton_start_addr; + u32 __iomem *pluton_reply_addr; }; struct tpm2_crb_smc { @@ -108,6 +110,11 @@ struct tpm2_crb_smc { u32 smc_func_id; }; +struct tpm2_crb_pluton { + u64 start_addr; + u64 reply_addr; +}; + static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, unsigned long timeout) { @@ -127,6 +134,25 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, return ((ioread32(reg) & mask) == value); } +static int crb_try_pluton_doorbell(struct crb_priv *priv, bool wait_for_complete) +{ + if (priv->sm != ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON) + return 0; + + if (!crb_wait_for_reg_32(priv->pluton_reply_addr, ~0, 1, TPM2_TIMEOUT_C)) + return -ETIME; + + iowrite32(1, priv->pluton_start_addr); + if (wait_for_complete == false) + return 0; + + if (!crb_wait_for_reg_32(priv->pluton_start_addr, + 0xffffffff, 0, 200)) + return -ETIME; + + return 0; +} + /** * __crb_go_idle - request tpm crb device to go the idle state * @@ -145,6 +171,8 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, */ static int __crb_go_idle(struct device *dev, struct crb_priv *priv) { + int rc; + if ((priv->sm == ACPI_TPM2_START_METHOD) || (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) || (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC)) @@ -152,6 +180,10 @@ static int __crb_go_idle(struct device *dev, struct crb_priv *priv) iowrite32(CRB_CTRL_REQ_GO_IDLE, &priv->regs_t->ctrl_req); + rc = crb_try_pluton_doorbell(priv, true); + if (rc) + return rc; + if (!crb_wait_for_reg_32(&priv->regs_t->ctrl_req, CRB_CTRL_REQ_GO_IDLE/* mask */, 0, /* value */ @@ -188,12 +220,19 @@ static int crb_go_idle(struct tpm_chip *chip) */ static int __crb_cmd_ready(struct device *dev, struct crb_priv *priv) { + int rc; + if ((priv->sm == ACPI_TPM2_START_METHOD) || (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) || (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC)) return 0; iowrite32(CRB_CTRL_REQ_CMD_READY, &priv->regs_t->ctrl_req); + + rc = crb_try_pluton_doorbell(priv, true); + if (rc) + return rc; + if (!crb_wait_for_reg_32(&priv->regs_t->ctrl_req, CRB_CTRL_REQ_CMD_READY /* mask */, 0, /* value */ @@ -371,6 +410,10 @@ static int crb_send(struct tpm_chip *chip, u8 *buf, size_t len) return -E2BIG; } + /* Seems to be necessary for every command */ + if (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON) + __crb_cmd_ready(&chip->dev, priv); + memcpy_toio(priv->cmd, buf, len); /* Make sure that cmd is populated before issuing start. */ @@ -394,7 +437,10 @@ static int crb_send(struct tpm_chip *chip, u8 *buf, size_t len) rc = tpm_crb_smc_start(&chip->dev, priv->smc_func_id); } - return rc; + if (rc) + return rc; + + return crb_try_pluton_doorbell(priv, false); } static void crb_cancel(struct tpm_chip *chip) @@ -524,15 +570,18 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, return ret; acpi_dev_free_resource_list(&acpi_resource_list); - if (resource_type(iores_array) != IORESOURCE_MEM) { - dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); - return -EINVAL; - } else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) == - IORESOURCE_MEM) { - dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n"); - memset(iores_array + TPM_CRB_MAX_RESOURCES, - 0, sizeof(*iores_array)); - iores_array[TPM_CRB_MAX_RESOURCES].flags = 0; + /* Pluton doesn't appear to define ACPI memory regions */ + if (priv->sm != ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON) { + if (resource_type(iores_array) != IORESOURCE_MEM) { + dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); + return -EINVAL; + } else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) == + IORESOURCE_MEM) { + dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n"); + memset(iores_array + TPM_CRB_MAX_RESOURCES, + 0, sizeof(*iores_array)); + iores_array[TPM_CRB_MAX_RESOURCES].flags = 0; + } } iores = NULL; @@ -656,6 +705,22 @@ out_relinquish_locality: return ret; } +static int crb_map_pluton(struct device *dev, struct crb_priv *priv, + struct acpi_table_tpm2 *buf, struct tpm2_crb_pluton *crb_pluton) +{ + priv->pluton_start_addr = crb_map_res(dev, NULL, NULL, + crb_pluton->start_addr, 4); + if (IS_ERR(priv->pluton_start_addr)) + return PTR_ERR(priv->pluton_start_addr); + + priv->pluton_reply_addr = crb_map_res(dev, NULL, NULL, + crb_pluton->reply_addr, 4); + if (IS_ERR(priv->pluton_reply_addr)) + return PTR_ERR(priv->pluton_reply_addr); + + return 0; +} + static int crb_acpi_add(struct acpi_device *device) { struct acpi_table_tpm2 *buf; @@ -663,6 +728,7 @@ static int crb_acpi_add(struct acpi_device *device) struct tpm_chip *chip; struct device *dev = &device->dev; struct tpm2_crb_smc *crb_smc; + struct tpm2_crb_pluton *crb_pluton; acpi_status status; u32 sm; int rc; @@ -700,6 +766,20 @@ static int crb_acpi_add(struct acpi_device *device) priv->smc_func_id = crb_smc->smc_func_id; } + if (sm == ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON) { + if (buf->header.length < (sizeof(*buf) + sizeof(*crb_pluton))) { + dev_err(dev, + FW_BUG "TPM2 ACPI table has wrong size %u for start method type %d\n", + buf->header.length, + ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON); + return -EINVAL; + } + crb_pluton = ACPI_ADD_PTR(struct tpm2_crb_pluton, buf, sizeof(*buf)); + rc = crb_map_pluton(dev, priv, buf, crb_pluton); + if (rc) + return rc; + } + priv->sm = sm; priv->hid = acpi_device_hid(device); diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c index 4be3677c1463..8f77154e0550 100644 --- a/drivers/char/tpm/tpm_i2c_atmel.c +++ b/drivers/char/tpm/tpm_i2c_atmel.c @@ -146,8 +146,7 @@ static const struct tpm_class_ops i2c_atmel = { .req_canceled = i2c_atmel_req_canceled, }; -static int i2c_atmel_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int i2c_atmel_probe(struct i2c_client *client) { struct tpm_chip *chip; struct device *dev = &client->dev; @@ -204,7 +203,7 @@ static SIMPLE_DEV_PM_OPS(i2c_atmel_pm_ops, tpm_pm_suspend, tpm_pm_resume); static struct i2c_driver i2c_atmel_driver = { .id_table = i2c_atmel_id, - .probe = i2c_atmel_probe, + .probe_new = i2c_atmel_probe, .remove = i2c_atmel_remove, .driver = { .name = I2C_DRIVER_NAME, diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c index fd3c3661e646..7cdaff52a96d 100644 --- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -681,8 +681,7 @@ MODULE_DEVICE_TABLE(of, tpm_tis_i2c_of_match); static SIMPLE_DEV_PM_OPS(tpm_tis_i2c_ops, tpm_pm_suspend, tpm_pm_resume); -static int tpm_tis_i2c_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int tpm_tis_i2c_probe(struct i2c_client *client) { int rc; struct device *dev = &(client->dev); @@ -717,7 +716,7 @@ static void tpm_tis_i2c_remove(struct i2c_client *client) static struct i2c_driver tpm_tis_i2c_driver = { .id_table = tpm_tis_i2c_table, - .probe = tpm_tis_i2c_probe, + .probe_new = tpm_tis_i2c_probe, .remove = tpm_tis_i2c_remove, .driver = { .name = "tpm_i2c_infineon", diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index 95c37350cc8e..a026e98add50 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -522,9 +522,9 @@ static int get_vid(struct i2c_client *client, u32 *res) return 0; } -static int i2c_nuvoton_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int i2c_nuvoton_probe(struct i2c_client *client) { + const struct i2c_device_id *id = i2c_client_get_device_id(client); int rc; struct tpm_chip *chip; struct device *dev = &client->dev; @@ -650,7 +650,7 @@ static SIMPLE_DEV_PM_OPS(i2c_nuvoton_pm_ops, tpm_pm_suspend, tpm_pm_resume); static struct i2c_driver i2c_nuvoton_driver = { .id_table = i2c_nuvoton_id, - .probe = i2c_nuvoton_probe, + .probe_new = i2c_nuvoton_probe, .remove = i2c_nuvoton_remove, .driver = { .name = "tpm_i2c_nuvoton", diff --git a/drivers/char/tpm/tpm_tis_i2c.c b/drivers/char/tpm/tpm_tis_i2c.c index f3a7251c8e38..c8c34adc14c0 100644 --- a/drivers/char/tpm/tpm_tis_i2c.c +++ b/drivers/char/tpm/tpm_tis_i2c.c @@ -312,8 +312,7 @@ static const struct tpm_tis_phy_ops tpm_i2c_phy_ops = { .verify_crc = tpm_tis_i2c_verify_crc, }; -static int tpm_tis_i2c_probe(struct i2c_client *dev, - const struct i2c_device_id *id) +static int tpm_tis_i2c_probe(struct i2c_client *dev) { struct tpm_tis_i2c_phy *phy; const u8 crc_enable = 1; @@ -380,7 +379,7 @@ static struct i2c_driver tpm_tis_i2c_driver = { .pm = &tpm_tis_pm, .of_match_table = of_match_ptr(of_tis_i2c_match), }, - .probe = tpm_tis_i2c_probe, + .probe_new = tpm_tis_i2c_probe, .remove = tpm_tis_i2c_remove, .id_table = tpm_tis_i2c_id, }; diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 957cf6bb8c05..d3f55ca06ed3 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -706,6 +706,8 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) return -ENOMEM; qcom_cpufreq.soc_data = of_device_get_match_data(dev); + if (!qcom_cpufreq.soc_data) + return -ENODEV; clk_data = devm_kzalloc(dev, struct_size(clk_data, hws, num_domains), GFP_KERNEL); if (!clk_data) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index ec7cfd4f52b1..e9917a45b005 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1531,6 +1531,7 @@ config GPIO_MLXBF2 tristate "Mellanox BlueField 2 SoC GPIO" depends on (MELLANOX_PLATFORM && ARM64 && ACPI) || (64BIT && COMPILE_TEST) select GPIO_GENERIC + select GPIOLIB_IRQCHIP help Say Y here if you want GPIO support on Mellanox BlueField 2 SoC. diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 60514bc5454f..9e3893b19e4f 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -736,7 +736,7 @@ static void gpio_sim_remove_hogs(struct gpio_sim_device *dev) gpiod_remove_hogs(dev->hogs); - for (hog = dev->hogs; !hog->chip_label; hog++) { + for (hog = dev->hogs; hog->chip_label; hog++) { kfree(hog->chip_label); kfree(hog->line_name); } diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 9db42f6a2043..9033db00c360 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -30,7 +30,6 @@ struct fsl_gpio_soc_data { struct vf610_gpio_port { struct gpio_chip gc; - struct irq_chip ic; void __iomem *base; void __iomem *gpio_base; const struct fsl_gpio_soc_data *sdata; @@ -207,20 +206,24 @@ static int vf610_gpio_irq_set_type(struct irq_data *d, u32 type) static void vf610_gpio_irq_mask(struct irq_data *d) { - struct vf610_gpio_port *port = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - void __iomem *pcr_base = port->base + PORT_PCR(d->hwirq); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct vf610_gpio_port *port = gpiochip_get_data(gc); + irq_hw_number_t gpio_num = irqd_to_hwirq(d); + void __iomem *pcr_base = port->base + PORT_PCR(gpio_num); vf610_gpio_writel(0, pcr_base); + gpiochip_disable_irq(gc, gpio_num); } static void vf610_gpio_irq_unmask(struct irq_data *d) { - struct vf610_gpio_port *port = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - void __iomem *pcr_base = port->base + PORT_PCR(d->hwirq); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct vf610_gpio_port *port = gpiochip_get_data(gc); + irq_hw_number_t gpio_num = irqd_to_hwirq(d); + void __iomem *pcr_base = port->base + PORT_PCR(gpio_num); - vf610_gpio_writel(port->irqc[d->hwirq] << PORT_PCR_IRQC_OFFSET, + gpiochip_enable_irq(gc, gpio_num); + vf610_gpio_writel(port->irqc[gpio_num] << PORT_PCR_IRQC_OFFSET, pcr_base); } @@ -237,6 +240,17 @@ static int vf610_gpio_irq_set_wake(struct irq_data *d, u32 enable) return 0; } +static const struct irq_chip vf610_irqchip = { + .name = "gpio-vf610", + .irq_ack = vf610_gpio_irq_ack, + .irq_mask = vf610_gpio_irq_mask, + .irq_unmask = vf610_gpio_irq_unmask, + .irq_set_type = vf610_gpio_irq_set_type, + .irq_set_wake = vf610_gpio_irq_set_wake, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static void vf610_gpio_disable_clk(void *data) { clk_disable_unprepare(data); @@ -249,7 +263,6 @@ static int vf610_gpio_probe(struct platform_device *pdev) struct vf610_gpio_port *port; struct gpio_chip *gc; struct gpio_irq_chip *girq; - struct irq_chip *ic; int i; int ret; @@ -315,14 +328,6 @@ static int vf610_gpio_probe(struct platform_device *pdev) gc->direction_output = vf610_gpio_direction_output; gc->set = vf610_gpio_set; - ic = &port->ic; - ic->name = "gpio-vf610"; - ic->irq_ack = vf610_gpio_irq_ack; - ic->irq_mask = vf610_gpio_irq_mask; - ic->irq_unmask = vf610_gpio_irq_unmask; - ic->irq_set_type = vf610_gpio_irq_set_type; - ic->irq_set_wake = vf610_gpio_irq_set_wake; - /* Mask all GPIO interrupts */ for (i = 0; i < gc->ngpio; i++) vf610_gpio_writel(0, port->base + PORT_PCR(i)); @@ -331,7 +336,7 @@ static int vf610_gpio_probe(struct platform_device *pdev) vf610_gpio_writel(~0, port->base + PORT_ISFR); girq = &gc->irq; - girq->chip = ic; + gpio_irq_chip_set_chip(girq, &vf610_irqchip); girq->parent_handler = vf610_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(&pdev->dev, 1, diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 17c53f484280..34ff048e70d0 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1637,6 +1637,18 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "ELAN0415:00@9", }, }, + { + /* + * Spurious wakeups from TP_ATTN# pin + * Found in BIOS 1.7.7 + */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "SYNA1202:00@16", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-acpi.h b/drivers/gpio/gpiolib-acpi.h index 9475f99a9694..5a08693b8fb1 100644 --- a/drivers/gpio/gpiolib-acpi.h +++ b/drivers/gpio/gpiolib-acpi.h @@ -14,7 +14,6 @@ #include <linux/gpio/consumer.h> -struct acpi_device; struct device; struct fwnode_handle; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 315cbdf61979..9abfb482b615 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -53,7 +53,8 @@ config DRM_DEBUG_MM config DRM_USE_DYNAMIC_DEBUG bool "use dynamic debug to implement drm.debug" - default y + default n + depends on BROKEN depends on DRM depends on DYNAMIC_DEBUG || DYNAMIC_DEBUG_CORE depends on JUMP_LABEL diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 2f28a8c02f64..fbf2f24169eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4268,6 +4268,9 @@ exit: } adev->in_suspend = false; + if (adev->enable_mes) + amdgpu_mes_self_test(adev); + if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) DRM_WARN("smart shift update failed\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 5dff79e8f301..1c4787000a5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -1344,7 +1344,7 @@ static int mes_v11_0_late_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* it's only intended for use in mes_self_test case, not for s0ix and reset */ - if (!amdgpu_in_reset(adev) && !adev->in_s0ix && + if (!amdgpu_in_reset(adev) && !adev->in_s0ix && !adev->in_suspend && (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))) amdgpu_mes_self_test(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 93dee3d1a483..9c7b69d377bd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9658,7 +9658,11 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * `dcn10_can_pipe_disable_cursor`). By now, all modified planes are in * atomic state, so call drm helper to normalize zpos. */ - drm_atomic_normalize_zpos(dev, state); + ret = drm_atomic_normalize_zpos(dev, state); + if (ret) { + drm_dbg(dev, "drm_atomic_normalize_zpos() failed\n"); + goto fail; + } /* Remove exiting planes if they are modified */ for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index c7443317c747..66a4a41c3fe9 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -714,7 +714,7 @@ static int ast_primary_plane_init(struct ast_private *ast) struct ast_plane *ast_primary_plane = &ast->primary_plane; struct drm_plane *primary_plane = &ast_primary_plane->base; void __iomem *vaddr = ast->vram; - u64 offset = ast->vram_base; + u64 offset = 0; /* with shmem, the primary plane is always at offset 0 */ unsigned long cursor_size = roundup(AST_HWC_SIZE + AST_HWC_SIGNATURE_SIZE, PAGE_SIZE); unsigned long size = ast->vram_fb_available - cursor_size; int ret; @@ -972,7 +972,7 @@ static int ast_cursor_plane_init(struct ast_private *ast) return -ENOMEM; vaddr = ast->vram + ast->vram_fb_available - size; - offset = ast->vram_base + ast->vram_fb_available - size; + offset = ast->vram_fb_available - size; ret = ast_plane_init(dev, ast_cursor_plane, vaddr, offset, size, 0x01, &ast_cursor_plane_funcs, diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 949c19339015..a0740308555d 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1355,6 +1355,13 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_L3_COH_PIPE); + /* + * Wa_1408615072:icl,ehl (vsunit) + * Wa_1407596294:icl,ehl (hsunit) + */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, + VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); + /* Wa_1407352427:icl,ehl */ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, PSDUNIT_CLKGATE_DIS); @@ -2540,13 +2547,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN11_ENABLE_32_PLANE_MODE); /* - * Wa_1408615072:icl,ehl (vsunit) - * Wa_1407596294:icl,ehl (hsunit) - */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, - VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); - - /* * Wa_1408767742:icl[a2..forever],ehl[all] * Wa_1605460711:icl[a0..c0] */ diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 0108613e79d5..7258975331ca 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -711,7 +711,7 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc, struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder); if (vc4_encoder->type == VC4_ENCODER_TYPE_HDMI0) { - vc4_state->hvs_load = max(mode->clock * mode->hdisplay / mode->htotal + 1000, + vc4_state->hvs_load = max(mode->clock * mode->hdisplay / mode->htotal + 8000, mode->clock * 9 / 10) * 1000; } else { vc4_state->hvs_load = mode->clock * 1000; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 55744216392b..7546103f1499 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -97,6 +97,10 @@ #define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1_SHIFT 8 #define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1_MASK VC4_MASK(15, 8) +#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_MASK VC4_MASK(7, 0) +#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_SET_AVMUTE BIT(0) +#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_CLEAR_AVMUTE BIT(4) + # define VC4_HD_M_SW_RST BIT(2) # define VC4_HD_M_ENABLE BIT(0) @@ -1306,7 +1310,6 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, VC4_HDMI_VERTB_VBP)); unsigned long flags; unsigned char gcp; - bool gcp_en; u32 reg; int idx; @@ -1341,16 +1344,13 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, switch (vc4_state->output_bpc) { case 12: gcp = 6; - gcp_en = true; break; case 10: gcp = 5; - gcp_en = true; break; case 8: default: - gcp = 4; - gcp_en = false; + gcp = 0; break; } @@ -1359,8 +1359,7 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, * doesn't signal in GCP. */ if (vc4_state->output_format == VC4_HDMI_OUTPUT_YUV422) { - gcp = 4; - gcp_en = false; + gcp = 0; } reg = HDMI_READ(HDMI_DEEP_COLOR_CONFIG_1); @@ -1373,11 +1372,12 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, reg = HDMI_READ(HDMI_GCP_WORD_1); reg &= ~VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1_MASK; reg |= VC4_SET_FIELD(gcp, VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1); + reg &= ~VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_MASK; + reg |= VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_CLEAR_AVMUTE; HDMI_WRITE(HDMI_GCP_WORD_1, reg); reg = HDMI_READ(HDMI_GCP_CONFIG); - reg &= ~VC5_HDMI_GCP_CONFIG_GCP_ENABLE; - reg |= gcp_en ? VC5_HDMI_GCP_CONFIG_GCP_ENABLE : 0; + reg |= VC5_HDMI_GCP_CONFIG_GCP_ENABLE; HDMI_WRITE(HDMI_GCP_CONFIG, reg); reg = HDMI_READ(HDMI_MISC_CONTROL); diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 8b92a45a3c89..bd5acc4a8687 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -340,7 +340,7 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) { struct vc4_plane_state *vc4_state = to_vc4_plane_state(state); struct drm_framebuffer *fb = state->fb; - struct drm_gem_dma_object *bo = drm_fb_dma_get_gem_obj(fb, 0); + struct drm_gem_dma_object *bo; int num_planes = fb->format->num_planes; struct drm_crtc_state *crtc_state; u32 h_subsample = fb->format->hsub; @@ -359,8 +359,10 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) if (ret) return ret; - for (i = 0; i < num_planes; i++) + for (i = 0; i < num_planes; i++) { + bo = drm_fb_dma_get_gem_obj(fb, i); vc4_state->offsets[i] = bo->dma_addr + fb->offsets[i]; + } /* * We don't support subpixel source positioning for scaling, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index aa1cd5126a32..4dcf2eb7aa80 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -462,6 +462,9 @@ int vmw_bo_create(struct vmw_private *vmw, return -ENOMEM; } + /* + * vmw_bo_init will delete the *p_bo object if it fails + */ ret = vmw_bo_init(vmw, *p_bo, size, placement, interruptible, pin, bo_free); @@ -470,7 +473,6 @@ int vmw_bo_create(struct vmw_private *vmw, return ret; out_error: - kfree(*p_bo); *p_bo = NULL; return ret; } @@ -596,6 +598,7 @@ static int vmw_user_bo_synccpu_release(struct drm_file *filp, ttm_bo_put(&vmw_bo->base); } + drm_gem_object_put(&vmw_bo->base.base); return ret; } @@ -636,6 +639,7 @@ int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, ret = vmw_user_bo_synccpu_grab(vbo, arg->flags); vmw_bo_unreference(&vbo); + drm_gem_object_put(&vbo->base.base); if (unlikely(ret != 0)) { if (ret == -ERESTARTSYS || ret == -EBUSY) return -EBUSY; @@ -693,7 +697,7 @@ int vmw_bo_unref_ioctl(struct drm_device *dev, void *data, * struct vmw_buffer_object should be placed. * Return: Zero on success, Negative error code on error. * - * The vmw buffer object pointer will be refcounted. + * The vmw buffer object pointer will be refcounted (both ttm and gem) */ int vmw_user_bo_lookup(struct drm_file *filp, uint32_t handle, @@ -710,7 +714,6 @@ int vmw_user_bo_lookup(struct drm_file *filp, *out = gem_to_vmw_bo(gobj); ttm_bo_get(&(*out)->base); - drm_gem_object_put(gobj); return 0; } @@ -791,7 +794,8 @@ int vmw_dumb_create(struct drm_file *file_priv, ret = vmw_gem_object_create_with_handle(dev_priv, file_priv, args->size, &args->handle, &vbo); - + /* drop reference from allocate - handle holds it now */ + drm_gem_object_put(&vbo->base.base); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index a44d53e33cdb..c0686283ffd1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1160,6 +1160,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, } ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, true, false); ttm_bo_put(&vmw_bo->base); + drm_gem_object_put(&vmw_bo->base.base); if (unlikely(ret != 0)) return ret; @@ -1214,6 +1215,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, } ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, false, false); ttm_bo_put(&vmw_bo->base); + drm_gem_object_put(&vmw_bo->base.base); if (unlikely(ret != 0)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index ce609e7d758f..4d2c28e39f4e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -146,14 +146,12 @@ int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, &vmw_sys_placement : &vmw_vram_sys_placement, true, false, &vmw_gem_destroy, p_vbo); - - (*p_vbo)->base.base.funcs = &vmw_gem_object_funcs; if (ret != 0) goto out_no_bo; + (*p_vbo)->base.base.funcs = &vmw_gem_object_funcs; + ret = drm_gem_handle_create(filp, &(*p_vbo)->base.base, handle); - /* drop reference from allocate - handle holds it now */ - drm_gem_object_put(&(*p_vbo)->base.base); out_no_bo: return ret; } @@ -180,6 +178,8 @@ int vmw_gem_object_create_ioctl(struct drm_device *dev, void *data, rep->map_handle = drm_vma_node_offset_addr(&vbo->base.base.vma_node); rep->cur_gmr_id = handle; rep->cur_gmr_offset = 0; + /* drop reference from allocate - handle holds it now */ + drm_gem_object_put(&vbo->base.base); out_no_bo: return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 257f090071f1..445d619e1fdc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1815,8 +1815,10 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, err_out: /* vmw_user_lookup_handle takes one ref so does new_fb */ - if (bo) + if (bo) { vmw_bo_unreference(&bo); + drm_gem_object_put(&bo->base.base); + } if (surface) vmw_surface_unreference(&surface); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c index e9f5c89b4ca6..b5b311f2a91a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c @@ -458,6 +458,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data, ret = vmw_overlay_update_stream(dev_priv, buf, arg, true); vmw_bo_unreference(&buf); + drm_gem_object_put(&buf->base.base); out_unlock: mutex_unlock(&overlay->mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 108a496b5d18..51e83dfa1cac 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -807,6 +807,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, num_output_sig, tfile, shader_handle); out_bad_arg: vmw_bo_unreference(&buffer); + drm_gem_object_put(&buffer->base.base); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 3bc63ae768f3..dcfb003841b3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -683,7 +683,7 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) container_of(base, struct vmw_user_surface, prime.base); struct vmw_resource *res = &user_srf->srf.res; - if (base->shareable && res && res->backup) + if (res && res->backup) drm_gem_object_put(&res->backup->base.base); *p_base = NULL; @@ -864,7 +864,11 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, goto out_unlock; } vmw_bo_reference(res->backup); - drm_gem_object_get(&res->backup->base.base); + /* + * We don't expose the handle to the userspace and surface + * already holds a gem reference + */ + drm_gem_handle_delete(file_priv, backup_handle); } tmp = vmw_resource_reference(&srf->res); @@ -1568,8 +1572,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev, drm_vma_node_offset_addr(&res->backup->base.base.vma_node); rep->buffer_size = res->backup->base.base.size; rep->buffer_handle = backup_handle; - if (user_srf->prime.base.shareable) - drm_gem_object_get(&res->backup->base.base); } else { rep->buffer_map_handle = 0; rep->buffer_size = 0; diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index babf21a0adeb..f191a2a76f3b 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -294,6 +294,12 @@ static void sdio_release_func(struct device *dev) if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO)) sdio_free_func_cis(func); + /* + * We have now removed the link to the tuples in the + * card structure, so remove the reference. + */ + put_device(&func->card->dev); + kfree(func->info); kfree(func->tmpbuf); kfree(func); @@ -324,6 +330,12 @@ struct sdio_func *sdio_alloc_func(struct mmc_card *card) device_initialize(&func->dev); + /* + * We may link to tuples in the card structure, + * we need make sure we have a reference to it. + */ + get_device(&func->card->dev); + func->dev.parent = &card->dev; func->dev.bus = &sdio_bus_type; func->dev.release = sdio_release_func; @@ -377,10 +389,9 @@ int sdio_add_func(struct sdio_func *func) */ void sdio_remove_func(struct sdio_func *func) { - if (!sdio_func_present(func)) - return; + if (sdio_func_present(func)) + device_del(&func->dev); - device_del(&func->dev); of_node_put(func->dev.of_node); put_device(&func->dev); } diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index a705ba6eff5b..afaa6cab1adc 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -404,12 +404,6 @@ int sdio_read_func_cis(struct sdio_func *func) return ret; /* - * Since we've linked to tuples in the card structure, - * we must make sure we have a reference to it. - */ - get_device(&func->card->dev); - - /* * Vendor/device id is optional for function CIS, so * copy it from the card structure as needed. */ @@ -434,11 +428,5 @@ void sdio_free_func_cis(struct sdio_func *func) } func->tuples = NULL; - - /* - * We have now removed the link to the tuples in the - * card structure, so remove the reference. - */ - put_device(&func->card->dev); } diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index dc2db9c185ea..eda1e2ddcaca 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -1053,6 +1053,16 @@ static int jz4740_mmc_probe(struct platform_device* pdev) mmc->ops = &jz4740_mmc_ops; if (!mmc->f_max) mmc->f_max = JZ_MMC_CLK_RATE; + + /* + * There seems to be a problem with this driver on the JZ4760 and + * JZ4760B SoCs. There, when using the maximum rate supported (50 MHz), + * the communication fails with many SD cards. + * Until this bug is sorted out, limit the maximum rate to 24 MHz. + */ + if (host->version == JZ_MMC_JZ4760 && mmc->f_max > JZ_MMC_CLK_RATE) + mmc->f_max = JZ_MMC_CLK_RATE; + mmc->f_min = mmc->f_max / 128; mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34; diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 6e5ea0213b47..5c94ad4661ce 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -435,7 +435,8 @@ static int meson_mmc_clk_init(struct meson_host *host) clk_reg |= FIELD_PREP(CLK_CORE_PHASE_MASK, CLK_PHASE_180); clk_reg |= FIELD_PREP(CLK_TX_PHASE_MASK, CLK_PHASE_0); clk_reg |= FIELD_PREP(CLK_RX_PHASE_MASK, CLK_PHASE_0); - clk_reg |= CLK_IRQ_SDIO_SLEEP(host); + if (host->mmc->caps & MMC_CAP_SDIO_IRQ) + clk_reg |= CLK_IRQ_SDIO_SLEEP(host); writel(clk_reg, host->regs + SD_EMMC_CLOCK); /* get the mux parents */ @@ -948,16 +949,18 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id) { struct meson_host *host = dev_id; struct mmc_command *cmd; - u32 status, raw_status; + u32 status, raw_status, irq_mask = IRQ_EN_MASK; irqreturn_t ret = IRQ_NONE; + if (host->mmc->caps & MMC_CAP_SDIO_IRQ) + irq_mask |= IRQ_SDIO; raw_status = readl(host->regs + SD_EMMC_STATUS); - status = raw_status & (IRQ_EN_MASK | IRQ_SDIO); + status = raw_status & irq_mask; if (!status) { dev_dbg(host->dev, - "Unexpected IRQ! irq_en 0x%08lx - status 0x%08x\n", - IRQ_EN_MASK | IRQ_SDIO, raw_status); + "Unexpected IRQ! irq_en 0x%08x - status 0x%08x\n", + irq_mask, raw_status); return IRQ_NONE; } @@ -1204,6 +1207,11 @@ static int meson_mmc_probe(struct platform_device *pdev) goto free_host; } + mmc->caps |= MMC_CAP_CMD23; + + if (mmc->caps & MMC_CAP_SDIO_IRQ) + mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD; + host->data = (struct meson_mmc_data *) of_device_get_match_data(&pdev->dev); if (!host->data) { @@ -1277,11 +1285,6 @@ static int meson_mmc_probe(struct platform_device *pdev) spin_lock_init(&host->lock); - mmc->caps |= MMC_CAP_CMD23; - - if (mmc->caps & MMC_CAP_SDIO_IRQ) - mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD; - if (host->dram_access_quirk) { /* Limit segments to 1 due to low available sram memory */ mmc->max_segs = 1; diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 106dd204b1a7..cc333ad67cac 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1437,7 +1437,7 @@ static int mmc_spi_probe(struct spi_device *spi) status = mmc_add_host(mmc); if (status != 0) - goto fail_add_host; + goto fail_glue_init; /* * Index 0 is card detect @@ -1445,7 +1445,7 @@ static int mmc_spi_probe(struct spi_device *spi) */ status = mmc_gpiod_request_cd(mmc, NULL, 0, false, 1000); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) { /* * The platform has a CD GPIO signal that may support @@ -1460,7 +1460,7 @@ static int mmc_spi_probe(struct spi_device *spi) /* Index 1 is write protect/read only */ status = mmc_gpiod_request_ro(mmc, NULL, 1, 0); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) has_ro = true; @@ -1474,7 +1474,7 @@ static int mmc_spi_probe(struct spi_device *spi) ? ", cd polling" : ""); return 0; -fail_add_host: +fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: mmc_spi_dma_free(host); diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 02bd3cf9a260..6e4f36aaf5db 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -240,12 +240,12 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (ci->pkg == BCMA_PKG_ID_BCM47188 || - ci->pkg == BCMA_PKG_ID_BCM47186) { + if ((ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM47186) || + (ci->id == BCMA_CHIP_ID_BCM53572 && ci->pkg == BCMA_PKG_ID_BCM47188)) { bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; } - if (ci->pkg == BCMA_PKG_ID_BCM5358) + if (ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM5358) bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII; break; case BCMA_CHIP_ID_BCM53573: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 240a7e8a7652..6c32f5c427b5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -9274,10 +9274,14 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; } - if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) { + if (tcs && (bp->tx_nr_rings_per_tc * tcs != + bp->tx_nr_rings - bp->tx_nr_rings_xdp)) { netdev_err(bp->dev, "tx ring reservation failure\n"); netdev_reset_tc(bp->dev); - bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + if (bp->tx_nr_rings_xdp) + bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp; + else + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; return -ENOMEM; } return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 53d0083e35da..52eec0a50492 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2921,7 +2921,7 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) struct i40e_pf *pf = vsi->back; if (i40e_enabled_xdp_vsi(vsi)) { - int frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int frame_size = new_mtu + I40E_PACKET_HDR_PAD; if (frame_size > i40e_max_xdp_frame_size(vsi)) return -EINVAL; @@ -13167,6 +13167,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, } br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 8286e47b4bae..0fae0186bd85 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -899,7 +899,7 @@ static int ice_set_object_tx_priority(struct ice_port_info *pi, struct ice_sched { int status; - if (node->tx_priority >= 8) { + if (priority >= 8) { NL_SET_ERR_MSG_MOD(extack, "Priority should be less than 8"); return -EINVAL; } @@ -929,7 +929,7 @@ static int ice_set_object_tx_weight(struct ice_port_info *pi, struct ice_sched_n { int status; - if (node->tx_weight > 200 || node->tx_weight < 1) { + if (weight > 200 || weight < 1) { NL_SET_ERR_MSG_MOD(extack, "Weight must be between 1 and 200"); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b288a01a321a..8ec24f6cf6be 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -275,6 +275,8 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (status && status != -EEXIST) return status; + netdev_dbg(vsi->netdev, "set promisc filter bits for VSI %i: 0x%x\n", + vsi->vsi_num, promisc_m); return 0; } @@ -300,6 +302,8 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) promisc_m, 0); } + netdev_dbg(vsi->netdev, "clear promisc filter bits for VSI %i: 0x%x\n", + vsi->vsi_num, promisc_m); return status; } @@ -414,6 +418,16 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } err = 0; vlan_ops->dis_rx_filtering(vsi); + + /* promiscuous mode implies allmulticast so + * that VSIs that are in promiscuous mode are + * subscribed to multicast packets coming to + * the port + */ + err = ice_set_promisc(vsi, + ICE_MCAST_PROMISC_BITS); + if (err) + goto out_promisc; } } else { /* Clear Rx filter to remove traffic from wire */ @@ -430,6 +444,18 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) NETIF_F_HW_VLAN_CTAG_FILTER) vlan_ops->ena_rx_filtering(vsi); } + + /* disable allmulti here, but only if allmulti is not + * still enabled for the netdev + */ + if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) { + err = ice_clear_promisc(vsi, + ICE_MCAST_PROMISC_BITS); + if (err) { + netdev_err(netdev, "Error %d clearing multicast promiscuous on VSI %i\n", + err, vsi->vsi_num); + } + } } } goto exit; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 7105de6fb344..374b7f10b549 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -800,6 +800,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) struct ice_tx_desc *tx_desc; u16 cnt = xdp_ring->count; struct ice_tx_buf *tx_buf; + u16 completed_frames = 0; u16 xsk_frames = 0; u16 last_rs; int i; @@ -809,19 +810,21 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) if ((tx_desc->cmd_type_offset_bsz & cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) { if (last_rs >= ntc) - xsk_frames = last_rs - ntc + 1; + completed_frames = last_rs - ntc + 1; else - xsk_frames = last_rs + cnt - ntc + 1; + completed_frames = last_rs + cnt - ntc + 1; } - if (!xsk_frames) + if (!completed_frames) return; - if (likely(!xdp_ring->xdp_tx_active)) + if (likely(!xdp_ring->xdp_tx_active)) { + xsk_frames = completed_frames; goto skip; + } ntc = xdp_ring->next_to_clean; - for (i = 0; i < xsk_frames; i++) { + for (i = 0; i < completed_frames; i++) { tx_buf = &xdp_ring->tx_buf[ntc]; if (tx_buf->raw_buf) { @@ -837,7 +840,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) } skip: tx_desc->cmd_type_offset_bsz = 0; - xdp_ring->next_to_clean += xsk_frames; + xdp_ring->next_to_clean += completed_frames; if (xdp_ring->next_to_clean >= cnt) xdp_ring->next_to_clean -= cnt; if (xsk_frames) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 3c0c35ecea10..b5b443883da9 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2256,6 +2256,30 @@ static void igb_enable_mas(struct igb_adapter *adapter) } } +#ifdef CONFIG_IGB_HWMON +/** + * igb_set_i2c_bb - Init I2C interface + * @hw: pointer to hardware structure + **/ +static void igb_set_i2c_bb(struct e1000_hw *hw) +{ + u32 ctrl_ext; + s32 i2cctl; + + ctrl_ext = rd32(E1000_CTRL_EXT); + ctrl_ext |= E1000_CTRL_I2C_ENA; + wr32(E1000_CTRL_EXT, ctrl_ext); + wrfl(); + + i2cctl = rd32(E1000_I2CPARAMS); + i2cctl |= E1000_I2CBB_EN + | E1000_I2C_CLK_OE_N + | E1000_I2C_DATA_OE_N; + wr32(E1000_I2CPARAMS, i2cctl); + wrfl(); +} +#endif + void igb_reset(struct igb_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; @@ -2400,7 +2424,8 @@ void igb_reset(struct igb_adapter *adapter) * interface. */ if (adapter->ets) - mac->ops.init_thermal_sensor_thresh(hw); + igb_set_i2c_bb(hw); + mac->ops.init_thermal_sensor_thresh(hw); } } #endif @@ -3117,21 +3142,12 @@ static void igb_init_mas(struct igb_adapter *adapter) **/ static s32 igb_init_i2c(struct igb_adapter *adapter) { - struct e1000_hw *hw = &adapter->hw; s32 status = 0; - s32 i2cctl; /* I2C interface supported on i350 devices */ if (adapter->hw.mac.type != e1000_i350) return 0; - i2cctl = rd32(E1000_I2CPARAMS); - i2cctl |= E1000_I2CBB_EN - | E1000_I2C_CLK_OUT | E1000_I2C_CLK_OE_N - | E1000_I2C_DATA_OUT | E1000_I2C_DATA_OE_N; - wr32(E1000_I2CPARAMS, i2cctl); - wrfl(); - /* Initialize the i2c bus which is controlled by the registers. * This bus will use the i2c_algo_bit structure that implements * the protocol through toggling of the 4 bits in the register. @@ -3521,6 +3537,12 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->ets = true; else adapter->ets = false; + /* Only enable I2C bit banging if an external thermal + * sensor is supported. + */ + if (adapter->ets) + igb_set_i2c_bb(hw); + hw->mac.ops.init_thermal_sensor_thresh(hw); if (igb_sysfs_init(adapter)) dev_err(&pdev->dev, "failed to allocate sysfs resources\n"); @@ -6794,7 +6816,7 @@ static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) struct timespec64 ts; u32 tsauxc; - if (pin < 0 || pin >= IGB_N_PEROUT) + if (pin < 0 || pin >= IGB_N_SDP) return; spin_lock(&adapter->tmreg_lock); @@ -6802,7 +6824,7 @@ static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) if (hw->mac.type == e1000_82580 || hw->mac.type == e1000_i354 || hw->mac.type == e1000_i350) { - s64 ns = timespec64_to_ns(&adapter->perout[pin].period); + s64 ns = timespec64_to_ns(&adapter->perout[tsintr_tt].period); u32 systiml, systimh, level_mask, level, rem; u64 systim, now; @@ -6850,8 +6872,8 @@ static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) ts.tv_nsec = (u32)systim; ts.tv_sec = ((u32)(systim >> 32)) & 0xFF; } else { - ts = timespec64_add(adapter->perout[pin].start, - adapter->perout[pin].period); + ts = timespec64_add(adapter->perout[tsintr_tt].start, + adapter->perout[tsintr_tt].period); } /* u32 conversion of tv_sec is safe until y2106 */ @@ -6860,7 +6882,7 @@ static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) tsauxc = rd32(E1000_TSAUXC); tsauxc |= TSAUXC_EN_TT0; wr32(E1000_TSAUXC, tsauxc); - adapter->perout[pin].start = ts; + adapter->perout[tsintr_tt].start = ts; spin_unlock(&adapter->tmreg_lock); } @@ -6874,7 +6896,7 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) struct ptp_clock_event event; struct timespec64 ts; - if (pin < 0 || pin >= IGB_N_EXTTS) + if (pin < 0 || pin >= IGB_N_SDP) return; if (hw->mac.type == e1000_82580 || diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index bc68b8f2176d..8736ca4b2628 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -73,6 +73,8 @@ #define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ +#define IXGBE_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + /* Attempt to maximize the headroom available for incoming frames. We * use a 2K buffer for receives and need 1536/1534 to store the data for * the frame. This leaves us with 512 bytes of room. From that we need diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ab8370c413f3..4507fba8747a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6778,6 +6778,18 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) } /** + * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @adapter: device handle, pointer to adapter + */ +static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter) +{ + if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + return IXGBE_RXBUFFER_2K; + else + return IXGBE_RXBUFFER_3K; +} + +/** * ixgbe_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size @@ -6788,18 +6800,12 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - if (adapter->xdp_prog) { - int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; - int i; - - for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *ring = adapter->rx_ring[i]; + if (ixgbe_enabled_xdp_adapter(adapter)) { + int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD; - if (new_frame_size > ixgbe_rx_bufsz(ring)) { - e_warn(probe, "Requested MTU size is not supported with XDP\n"); - return -EINVAL; - } + if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) { + e_warn(probe, "Requested MTU size is not supported with XDP\n"); + return -EINVAL; } } diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c index 4632268695cb..063cd371033a 100644 --- a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c +++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c @@ -129,26 +129,31 @@ struct nfp_ipsec_cfg_mssg { }; }; -static int nfp_ipsec_cfg_cmd_issue(struct nfp_net *nn, int type, int saidx, - struct nfp_ipsec_cfg_mssg *msg) +static int nfp_net_ipsec_cfg(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry) { + unsigned int offset = nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL; + struct nfp_ipsec_cfg_mssg *msg = (struct nfp_ipsec_cfg_mssg *)entry->msg; int i, msg_size, ret; - msg->cmd = type; - msg->sa_idx = saidx; - msg->rsp = 0; - msg_size = ARRAY_SIZE(msg->raw); + ret = nfp_net_mbox_lock(nn, sizeof(*msg)); + if (ret) + return ret; + msg_size = ARRAY_SIZE(msg->raw); for (i = 0; i < msg_size; i++) - nn_writel(nn, NFP_NET_CFG_MBOX_VAL + 4 * i, msg->raw[i]); + nn_writel(nn, offset + 4 * i, msg->raw[i]); - ret = nfp_net_mbox_reconfig(nn, NFP_NET_CFG_MBOX_CMD_IPSEC); - if (ret < 0) + ret = nfp_net_mbox_reconfig(nn, entry->cmd); + if (ret < 0) { + nn_ctrl_bar_unlock(nn); return ret; + } /* For now we always read the whole message response back */ for (i = 0; i < msg_size; i++) - msg->raw[i] = nn_readl(nn, NFP_NET_CFG_MBOX_VAL + 4 * i); + msg->raw[i] = nn_readl(nn, offset + 4 * i); + + nn_ctrl_bar_unlock(nn); switch (msg->rsp) { case NFP_IPSEC_CFG_MSSG_OK: @@ -477,7 +482,10 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x) } /* Allocate saidx and commit the SA */ - err = nfp_ipsec_cfg_cmd_issue(nn, NFP_IPSEC_CFG_MSSG_ADD_SA, saidx, &msg); + msg.cmd = NFP_IPSEC_CFG_MSSG_ADD_SA; + msg.sa_idx = saidx; + err = nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_IPSEC, &msg, + sizeof(msg), nfp_net_ipsec_cfg); if (err) { xa_erase(&nn->xa_ipsec, saidx); nn_err(nn, "Failed to issue IPsec command err ret=%d\n", err); @@ -491,14 +499,17 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x) static void nfp_net_xfrm_del_state(struct xfrm_state *x) { + struct nfp_ipsec_cfg_mssg msg = { + .cmd = NFP_IPSEC_CFG_MSSG_INV_SA, + .sa_idx = x->xso.offload_handle - 1, + }; struct net_device *netdev = x->xso.dev; - struct nfp_ipsec_cfg_mssg msg; struct nfp_net *nn; int err; nn = netdev_priv(netdev); - err = nfp_ipsec_cfg_cmd_issue(nn, NFP_IPSEC_CFG_MSSG_INV_SA, - x->xso.offload_handle - 1, &msg); + err = nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_IPSEC, &msg, + sizeof(msg), nfp_net_ipsec_cfg); if (err) nn_warn(nn, "Failed to invalidate SA in hardware\n"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 432d79d691c2..939cfce15830 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -617,9 +617,10 @@ struct nfp_net_dp { * @vnic_no_name: For non-port PF vNIC make ndo_get_phys_port_name return * -EOPNOTSUPP to keep backwards compatibility (set by app) * @port: Pointer to nfp_port structure if vNIC is a port - * @mc_lock: Protect mc_addrs list - * @mc_addrs: List of mc addrs to add/del to HW - * @mc_work: Work to update mc addrs + * @mbox_amsg: Asynchronously processed message via mailbox + * @mbox_amsg.lock: Protect message list + * @mbox_amsg.list: List of message to process + * @mbox_amsg.work: Work to process message asynchronously * @app_priv: APP private data for this vNIC */ struct nfp_net { @@ -721,13 +722,25 @@ struct nfp_net { struct nfp_port *port; - spinlock_t mc_lock; - struct list_head mc_addrs; - struct work_struct mc_work; + struct { + spinlock_t lock; + struct list_head list; + struct work_struct work; + } mbox_amsg; void *app_priv; }; +struct nfp_mbox_amsg_entry { + struct list_head list; + int (*cfg)(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry); + u32 cmd; + char msg[]; +}; + +int nfp_net_sched_mbox_amsg_work(struct nfp_net *nn, u32 cmd, const void *data, size_t len, + int (*cb)(struct nfp_net *, struct nfp_mbox_amsg_entry *)); + /* Functions to read/write from/to a BAR * Performs any endian conversion necessary. */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 18fc9971f1c8..70d7484c82af 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1334,14 +1334,54 @@ err_unlock: return err; } -struct nfp_mc_addr_entry { - u8 addr[ETH_ALEN]; - u32 cmd; - struct list_head list; -}; +int nfp_net_sched_mbox_amsg_work(struct nfp_net *nn, u32 cmd, const void *data, size_t len, + int (*cb)(struct nfp_net *, struct nfp_mbox_amsg_entry *)) +{ + struct nfp_mbox_amsg_entry *entry; + + entry = kmalloc(sizeof(*entry) + len, GFP_ATOMIC); + if (!entry) + return -ENOMEM; + + memcpy(entry->msg, data, len); + entry->cmd = cmd; + entry->cfg = cb; + + spin_lock_bh(&nn->mbox_amsg.lock); + list_add_tail(&entry->list, &nn->mbox_amsg.list); + spin_unlock_bh(&nn->mbox_amsg.lock); + + schedule_work(&nn->mbox_amsg.work); + + return 0; +} + +static void nfp_net_mbox_amsg_work(struct work_struct *work) +{ + struct nfp_net *nn = container_of(work, struct nfp_net, mbox_amsg.work); + struct nfp_mbox_amsg_entry *entry, *tmp; + struct list_head tmp_list; + + INIT_LIST_HEAD(&tmp_list); + + spin_lock_bh(&nn->mbox_amsg.lock); + list_splice_init(&nn->mbox_amsg.list, &tmp_list); + spin_unlock_bh(&nn->mbox_amsg.lock); + + list_for_each_entry_safe(entry, tmp, &tmp_list, list) { + int err = entry->cfg(nn, entry); + + if (err) + nn_err(nn, "Config cmd %d to HW failed %d.\n", entry->cmd, err); + + list_del(&entry->list); + kfree(entry); + } +} -static int nfp_net_mc_cfg(struct nfp_net *nn, const unsigned char *addr, const u32 cmd) +static int nfp_net_mc_cfg(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry) { + unsigned char *addr = entry->msg; int ret; ret = nfp_net_mbox_lock(nn, NFP_NET_CFG_MULTICAST_SZ); @@ -1353,26 +1393,7 @@ static int nfp_net_mc_cfg(struct nfp_net *nn, const unsigned char *addr, const u nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MULTICAST_MAC_LO, get_unaligned_be16(addr + 4)); - return nfp_net_mbox_reconfig_and_unlock(nn, cmd); -} - -static int nfp_net_mc_prep(struct nfp_net *nn, const unsigned char *addr, const u32 cmd) -{ - struct nfp_mc_addr_entry *entry; - - entry = kmalloc(sizeof(*entry), GFP_ATOMIC); - if (!entry) - return -ENOMEM; - - ether_addr_copy(entry->addr, addr); - entry->cmd = cmd; - spin_lock_bh(&nn->mc_lock); - list_add_tail(&entry->list, &nn->mc_addrs); - spin_unlock_bh(&nn->mc_lock); - - schedule_work(&nn->mc_work); - - return 0; + return nfp_net_mbox_reconfig_and_unlock(nn, entry->cmd); } static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr) @@ -1385,35 +1406,16 @@ static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr) return -EINVAL; } - return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD); + return nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD, addr, + NFP_NET_CFG_MULTICAST_SZ, nfp_net_mc_cfg); } static int nfp_net_mc_unsync(struct net_device *netdev, const unsigned char *addr) { struct nfp_net *nn = netdev_priv(netdev); - return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL); -} - -static void nfp_net_mc_addr_config(struct work_struct *work) -{ - struct nfp_net *nn = container_of(work, struct nfp_net, mc_work); - struct nfp_mc_addr_entry *entry, *tmp; - struct list_head tmp_list; - - INIT_LIST_HEAD(&tmp_list); - - spin_lock_bh(&nn->mc_lock); - list_splice_init(&nn->mc_addrs, &tmp_list); - spin_unlock_bh(&nn->mc_lock); - - list_for_each_entry_safe(entry, tmp, &tmp_list, list) { - if (nfp_net_mc_cfg(nn, entry->addr, entry->cmd)) - nn_err(nn, "Config mc address to HW failed.\n"); - - list_del(&entry->list); - kfree(entry); - } + return nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL, addr, + NFP_NET_CFG_MULTICAST_SZ, nfp_net_mc_cfg); } static void nfp_net_set_rx_mode(struct net_device *netdev) @@ -2681,9 +2683,9 @@ int nfp_net_init(struct nfp_net *nn) if (!nn->dp.netdev) return 0; - spin_lock_init(&nn->mc_lock); - INIT_LIST_HEAD(&nn->mc_addrs); - INIT_WORK(&nn->mc_work, nfp_net_mc_addr_config); + spin_lock_init(&nn->mbox_amsg.lock); + INIT_LIST_HEAD(&nn->mbox_amsg.list); + INIT_WORK(&nn->mbox_amsg.work, nfp_net_mbox_amsg_work); return register_netdev(nn->dp.netdev); @@ -2704,6 +2706,6 @@ void nfp_net_clean(struct nfp_net *nn) unregister_netdev(nn->dp.netdev); nfp_net_ipsec_clean(nn); nfp_ccm_mbox_clean(nn); - flush_work(&nn->mc_work); + flush_work(&nn->mbox_amsg.work); nfp_net_reconfig_wait_posted(nn); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 51124309ae1f..f03dcadff738 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -403,7 +403,6 @@ */ #define NFP_NET_CFG_MBOX_BASE 0x1800 #define NFP_NET_CFG_MBOX_VAL_MAX_SZ 0x1F8 -#define NFP_NET_CFG_MBOX_VAL 0x1808 #define NFP_NET_CFG_MBOX_SIMPLE_CMD 0x0 #define NFP_NET_CFG_MBOX_SIMPLE_RET 0x4 #define NFP_NET_CFG_MBOX_SIMPLE_VAL 0x8 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 413f66017219..e95d35f1e5a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -541,9 +541,9 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, return 0; } - val |= PPSCMDx(index, 0x2); val |= TRGTMODSELx(index, 0x2); val |= PPSEN0; + writel(val, ioaddr + MAC_PPS_CONTROL); writel(cfg->start.tv_sec, ioaddr + MAC_PPSx_TARGET_TIME_SEC(index)); @@ -568,6 +568,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, writel(period - 1, ioaddr + MAC_PPSx_WIDTH(index)); /* Finally, activate it */ + val |= PPSCMDx(index, 0x2); writel(val, ioaddr + MAC_PPS_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index eb6d9cd8e93f..0046a4ee6e64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -559,7 +559,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst"); plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode"); - if (plat->force_thresh_dma_mode) { + if (plat->force_thresh_dma_mode && plat->force_sf_dma_mode) { plat->force_sf_dma_mode = 0; dev_warn(&pdev->dev, "force_sf_dma_mode is ignored if force_thresh_dma_mode is set.\n"); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index ecbde83b5243..6cda4b7c10cb 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -501,7 +501,15 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) k3_udma_glue_disable_tx_chn(common->tx_chns[i].tx_chn); } + reinit_completion(&common->tdown_complete); k3_udma_glue_tdown_rx_chn(common->rx_chns.rx_chn, true); + + if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) { + i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000)); + if (!i) + dev_err(common->dev, "rx teardown timeout\n"); + } + napi_disable(&common->napi_rx); for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) @@ -721,6 +729,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, if (cppi5_desc_is_tdcm(desc_dma)) { dev_dbg(dev, "%s RX tdown flow: %u\n", __func__, flow_idx); + if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) + complete(&common->tdown_complete); return 0; } @@ -2672,7 +2682,7 @@ static const struct am65_cpsw_pdata j721e_pdata = { }; static const struct am65_cpsw_pdata am64x_cpswxg_pdata = { - .quirks = 0, + .quirks = AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ, .ale_dev_id = "am64-cpswxg", .fdqring_mode = K3_RINGACC_RING_MODE_RING, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 4b75620f8d28..e5f1c44788c1 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -90,6 +90,7 @@ struct am65_cpsw_rx_chn { }; #define AM65_CPSW_QUIRK_I2027_NO_TX_CSUM BIT(0) +#define AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ BIT(1) struct am65_cpsw_pdata { u32 quirks; diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c index 9f2b70ef39aa..613fc6910f14 100644 --- a/drivers/net/usb/kalmia.c +++ b/drivers/net/usb/kalmia.c @@ -65,8 +65,8 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT); if (status != 0) { netdev_err(dev->net, - "Error sending init packet. Status %i, length %i\n", - status, act_len); + "Error sending init packet. Status %i\n", + status); return status; } else if (act_len != init_msg_len) { @@ -83,8 +83,8 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, if (status != 0) netdev_err(dev->net, - "Error receiving init result. Status %i, length %i\n", - status, act_len); + "Error receiving init result. Status %i\n", + status); else if (act_len != expected_len) netdev_err(dev->net, "Unexpected init result length: %i\n", act_len); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 56267c327f0b..682987040ea8 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1546,31 +1546,6 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, rxd->len = rbi->len; } -#ifdef VMXNET3_RSS - if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE && - (adapter->netdev->features & NETIF_F_RXHASH)) { - enum pkt_hash_types hash_type; - - switch (rcd->rssType) { - case VMXNET3_RCD_RSS_TYPE_IPV4: - case VMXNET3_RCD_RSS_TYPE_IPV6: - hash_type = PKT_HASH_TYPE_L3; - break; - case VMXNET3_RCD_RSS_TYPE_TCPIPV4: - case VMXNET3_RCD_RSS_TYPE_TCPIPV6: - case VMXNET3_RCD_RSS_TYPE_UDPIPV4: - case VMXNET3_RCD_RSS_TYPE_UDPIPV6: - hash_type = PKT_HASH_TYPE_L4; - break; - default: - hash_type = PKT_HASH_TYPE_L3; - break; - } - skb_set_hash(ctx->skb, - le32_to_cpu(rcd->rssHash), - hash_type); - } -#endif skb_record_rx_queue(ctx->skb, rq->qid); skb_put(ctx->skb, rcd->len); @@ -1653,6 +1628,31 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, u32 mtu = adapter->netdev->mtu; skb->len += skb->data_len; +#ifdef VMXNET3_RSS + if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE && + (adapter->netdev->features & NETIF_F_RXHASH)) { + enum pkt_hash_types hash_type; + + switch (rcd->rssType) { + case VMXNET3_RCD_RSS_TYPE_IPV4: + case VMXNET3_RCD_RSS_TYPE_IPV6: + hash_type = PKT_HASH_TYPE_L3; + break; + case VMXNET3_RCD_RSS_TYPE_TCPIPV4: + case VMXNET3_RCD_RSS_TYPE_TCPIPV6: + case VMXNET3_RCD_RSS_TYPE_UDPIPV4: + case VMXNET3_RCD_RSS_TYPE_UDPIPV6: + hash_type = PKT_HASH_TYPE_L4; + break; + default: + hash_type = PKT_HASH_TYPE_L3; + break; + } + skb_set_hash(skb, + le32_to_cpu(rcd->rssHash), + hash_type); + } +#endif vmxnet3_rx_csum(adapter, skb, (union Vmxnet3_GenericDesc *)rcd); skb->protocol = eth_type_trans(skb, adapter->netdev); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c734934c407c..c11e0cfeef0f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -110,6 +110,7 @@ struct nvme_queue; static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); static void nvme_delete_io_queues(struct nvme_dev *dev); +static void nvme_update_attrs(struct nvme_dev *dev); /* * Represents an NVM Express device. Each nvme_dev is a PCI function. @@ -1923,6 +1924,8 @@ static void nvme_map_cmb(struct nvme_dev *dev) if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) == (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) pci_p2pmem_publish(pdev, true); + + nvme_update_attrs(dev); } static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) @@ -2209,6 +2212,11 @@ static const struct attribute_group *nvme_pci_dev_attr_groups[] = { NULL, }; +static void nvme_update_attrs(struct nvme_dev *dev) +{ + sysfs_update_group(&dev->ctrl.device->kobj, &nvme_pci_dev_attrs_group); +} + /* * nirqs is the number of interrupts available for write and read * queues. The core already reserved an interrupt for the admin queue. @@ -2509,18 +2517,12 @@ static int nvme_pci_enable(struct nvme_dev *dev) { int result = -ENOMEM; struct pci_dev *pdev = to_pci_dev(dev->dev); - int dma_address_bits = 64; if (pci_enable_device_mem(pdev)) return result; pci_set_master(pdev); - if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48) - dma_address_bits = 48; - if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(dma_address_bits))) - goto disable; - if (readl(dev->bar + NVME_REG_CSTS) == -1) { result = -ENODEV; goto disable; @@ -2970,7 +2972,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node); if (!dev) - return NULL; + return ERR_PTR(-ENOMEM); INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); mutex_init(&dev->shutdown_lock); @@ -2998,7 +3000,11 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, quirks); if (ret) goto out_put_device; - + + if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48) + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48)); + else + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); dma_set_min_align_mask(&pdev->dev, NVME_CTRL_PAGE_SIZE - 1); dma_set_max_seg_size(&pdev->dev, 0xffffffff); @@ -3031,8 +3037,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) int result = -ENOMEM; dev = nvme_pci_alloc_dev(pdev, id); - if (!dev) - return -ENOMEM; + if (IS_ERR(dev)) + return PTR_ERR(dev); result = nvme_dev_map(dev); if (result) @@ -3423,6 +3429,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN | NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x10ec, 0x5763), /* ADATA SX6000PNP */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 65f3b02a0e4e..f90975e00446 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -48,9 +48,10 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, err = memblock_mark_nomap(base, size); if (err) memblock_phys_free(base, size); - kmemleak_ignore_phys(base); } + kmemleak_ignore_phys(base); + return err; } diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 9b593f985805..40f70f83daba 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -550,13 +550,7 @@ static void armpmu_disable(struct pmu *pmu) static bool armpmu_filter(struct pmu *pmu, int cpu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); - bool ret; - - ret = cpumask_test_cpu(cpu, &armpmu->supported_cpus); - if (ret && armpmu->filter) - return armpmu->filter(pmu, cpu); - - return ret; + return !cpumask_test_cpu(cpu, &armpmu->supported_cpus); } static ssize_t cpus_show(struct device *dev, diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index bb81b8b1f7e9..89c5374e33b3 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -408,14 +408,23 @@ static const struct intel_vsec_platform_info dg1_info = { .quirks = VSEC_QUIRK_NO_DVSEC | VSEC_QUIRK_EARLY_HW, }; +/* MTL info */ +static const struct intel_vsec_platform_info mtl_info = { + .quirks = VSEC_QUIRK_NO_WATCHER | VSEC_QUIRK_NO_CRASHLOG, +}; + #define PCI_DEVICE_ID_INTEL_VSEC_ADL 0x467d #define PCI_DEVICE_ID_INTEL_VSEC_DG1 0x490e +#define PCI_DEVICE_ID_INTEL_VSEC_MTL_M 0x7d0d +#define PCI_DEVICE_ID_INTEL_VSEC_MTL_S 0xad0d #define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM 0x09a7 #define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d #define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_MTL_M, &mtl_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_MTL_S, &mtl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM, &(struct intel_vsec_platform_info) {}) }, { PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) }, diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 15f174f4e056..3f33934f5429 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2220,11 +2220,26 @@ void spi_flush_queue(struct spi_controller *ctlr) /*-------------------------------------------------------------------------*/ #if defined(CONFIG_OF) +static void of_spi_parse_dt_cs_delay(struct device_node *nc, + struct spi_delay *delay, const char *prop) +{ + u32 value; + + if (!of_property_read_u32(nc, prop, &value)) { + if (value > U16_MAX) { + delay->value = DIV_ROUND_UP(value, 1000); + delay->unit = SPI_DELAY_UNIT_USECS; + } else { + delay->value = value; + delay->unit = SPI_DELAY_UNIT_NSECS; + } + } +} + static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, struct device_node *nc) { u32 value; - u16 cs_setup; int rc; /* Mode (clock phase/polarity/etc.) */ @@ -2310,10 +2325,8 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, if (!of_property_read_u32(nc, "spi-max-frequency", &value)) spi->max_speed_hz = value; - if (!of_property_read_u16(nc, "spi-cs-setup-delay-ns", &cs_setup)) { - spi->cs_setup.value = cs_setup; - spi->cs_setup.unit = SPI_DELAY_UNIT_NSECS; - } + /* Device CS delays */ + of_spi_parse_dt_cs_delay(nc, &spi->cs_setup, "spi-cs-setup-delay-ns"); return 0; } diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 27295bda3e0b..b1c6231defad 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -11,6 +11,7 @@ #include <linux/tee_drv.h> #include <linux/uaccess.h> #include <linux/uio.h> +#include <linux/highmem.h> #include "tee_private.h" static void shm_put_kernel_pages(struct page **pages, size_t page_count) @@ -24,38 +25,20 @@ static void shm_put_kernel_pages(struct page **pages, size_t page_count) static int shm_get_kernel_pages(unsigned long start, size_t page_count, struct page **pages) { + struct page *page; size_t n; - int rc; - - if (is_vmalloc_addr((void *)start)) { - struct page *page; - - for (n = 0; n < page_count; n++) { - page = vmalloc_to_page((void *)(start + PAGE_SIZE * n)); - if (!page) - return -ENOMEM; - get_page(page); - pages[n] = page; - } - rc = page_count; - } else { - struct kvec *kiov; - - kiov = kcalloc(page_count, sizeof(*kiov), GFP_KERNEL); - if (!kiov) - return -ENOMEM; - - for (n = 0; n < page_count; n++) { - kiov[n].iov_base = (void *)(start + n * PAGE_SIZE); - kiov[n].iov_len = PAGE_SIZE; - } + if (WARN_ON_ONCE(is_vmalloc_addr((void *)start) || + is_kmap_addr((void *)start))) + return -EINVAL; - rc = get_kernel_pages(kiov, page_count, 0, pages); - kfree(kiov); + page = virt_to_page(start); + for (n = 0; n < page_count; n++) { + pages[n] = page + n; + get_page(pages[n]); } - return rc; + return page_count; } static void release_registered_pages(struct tee_shm *shm) diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index c730253ab85c..583cbcf09446 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -313,7 +313,7 @@ void fb_deferred_io_open(struct fb_info *info, } EXPORT_SYMBOL_GPL(fb_deferred_io_open); -void fb_deferred_io_cleanup(struct fb_info *info) +void fb_deferred_io_release(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; struct page *page; @@ -327,6 +327,14 @@ void fb_deferred_io_cleanup(struct fb_info *info) page = fb_deferred_io_page(info, i); page->mapping = NULL; } +} +EXPORT_SYMBOL_GPL(fb_deferred_io_release); + +void fb_deferred_io_cleanup(struct fb_info *info) +{ + struct fb_deferred_io *fbdefio = info->fbdefio; + + fb_deferred_io_release(info); kvfree(info->pagerefs); mutex_destroy(&fbdefio->lock); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 3a6c8458eb8d..ab3545a00abc 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1454,6 +1454,10 @@ __releases(&info->lock) struct fb_info * const info = file->private_data; lock_fb_info(info); +#if IS_ENABLED(CONFIG_FB_DEFERRED_IO) + if (info->fbdefio) + fb_deferred_io_release(info); +#endif if (info->fbops->fb_release) info->fbops->fb_release(info,1); module_put(info->fbops->owner); diff --git a/fs/9p/acl.c b/fs/9p/acl.c index c397c51f80d9..eed551d8555f 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -139,7 +139,7 @@ struct posix_acl *v9fs_iop_get_inode_acl(struct inode *inode, int type, bool rcu } -struct posix_acl *v9fs_iop_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *v9fs_iop_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type) { struct v9fs_session_info *v9ses; @@ -151,7 +151,7 @@ struct posix_acl *v9fs_iop_get_acl(struct user_namespace *mnt_userns, return v9fs_get_cached_acl(d_inode(dentry), type); } -int v9fs_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int v9fs_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int retval; @@ -195,7 +195,7 @@ int v9fs_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, goto err_out; } - if (!inode_owner_or_capable(&init_user_ns, inode)) { + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) { retval = -EPERM; goto err_out; } @@ -206,7 +206,7 @@ int v9fs_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr iattr = {}; struct posix_acl *acl_mode = acl; - retval = posix_acl_update_mode(&init_user_ns, inode, + retval = posix_acl_update_mode(&nop_mnt_idmap, inode, &iattr.ia_mode, &acl_mode); if (retval) @@ -225,7 +225,7 @@ int v9fs_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, * FIXME should we update ctime ? * What is the following setxattr update the mode ? */ - v9fs_vfs_setattr_dotl(&init_user_ns, dentry, &iattr); + v9fs_vfs_setattr_dotl(&nop_mnt_idmap, dentry, &iattr); } break; case ACL_TYPE_DEFAULT: diff --git a/fs/9p/acl.h b/fs/9p/acl.h index 4c60a2bce5de..333cfcc281da 100644 --- a/fs/9p/acl.h +++ b/fs/9p/acl.h @@ -10,9 +10,9 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid); struct posix_acl *v9fs_iop_get_inode_acl(struct inode *inode, int type, bool rcu); -struct posix_acl *v9fs_iop_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *v9fs_iop_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type); -int v9fs_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int v9fs_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid); int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid, diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 6acabc2e7dc9..f3f74d197b5d 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -151,7 +151,7 @@ extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d); extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d); -extern int v9fs_vfs_rename(struct user_namespace *mnt_userns, +extern int v9fs_vfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index bc417da7e9c1..75106b9f293d 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -60,7 +60,7 @@ void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat); int v9fs_uflags2omode(int uflags, int extended); void v9fs_blank_wstat(struct p9_wstat *wstat); -int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, +int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end, int datasync); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b740017634ef..b6ba22975781 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/sched.h> #include <linux/file.h> #include <linux/stat.h> diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 27a04a226d97..4344e7a7865f 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -260,7 +260,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, { int err = 0; - inode_init_owner(&init_user_ns, inode, NULL, mode); + inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_blocks = 0; inode->i_rdev = rdev; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); @@ -672,7 +672,7 @@ error: /** * v9fs_vfs_create - VFS hook to create a regular file - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @dir: The parent directory * @dentry: The name of file to be created * @mode: The UNIX file mode to set @@ -684,7 +684,7 @@ error: */ static int -v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); @@ -704,14 +704,14 @@ v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir, /** * v9fs_vfs_mkdir - VFS mkdir hook to create a directory - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @dir: inode that is being unlinked * @dentry: dentry that is being unlinked * @mode: mode for new directory * */ -static int v9fs_vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int v9fs_vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int err; @@ -908,7 +908,7 @@ int v9fs_vfs_rmdir(struct inode *i, struct dentry *d) /** * v9fs_vfs_rename - VFS hook to rename an inode - * @mnt_userns: The user namespace of the mount + * @idmap: The idmap of the mount * @old_dir: old dir inode * @old_dentry: old dentry * @new_dir: new dir inode @@ -918,7 +918,7 @@ int v9fs_vfs_rmdir(struct inode *i, struct dentry *d) */ int -v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +v9fs_vfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -1018,7 +1018,7 @@ error: /** * v9fs_vfs_getattr - retrieve file metadata - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @path: Object to query * @stat: metadata structure to populate * @request_mask: Mask of STATX_xxx flags indicating the caller's interests @@ -1027,7 +1027,7 @@ error: */ static int -v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, +v9fs_vfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; @@ -1038,7 +1038,7 @@ v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { - generic_fillattr(&init_user_ns, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); return 0; } fid = v9fs_fid_lookup(dentry); @@ -1051,7 +1051,7 @@ v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, return PTR_ERR(st); v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0); - generic_fillattr(&init_user_ns, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); p9stat_free(st); kfree(st); @@ -1060,13 +1060,13 @@ v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, /** * v9fs_vfs_setattr - set file metadata - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @dentry: file whose metadata to set * @iattr: metadata assignment structure * */ -static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, +static int v9fs_vfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; @@ -1077,7 +1077,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, struct p9_wstat wstat; p9_debug(P9_DEBUG_VFS, "\n"); - retval = setattr_prepare(&init_user_ns, dentry, iattr); + retval = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (retval) return retval; @@ -1135,7 +1135,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, v9fs_invalidate_inode_attr(inode); - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); mark_inode_dirty(inode); return 0; } @@ -1300,7 +1300,7 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, /** * v9fs_vfs_symlink - helper function to create symlinks - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @dir: directory inode containing symlink * @dentry: dentry for symlink * @symname: symlink data @@ -1310,7 +1310,7 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, */ static int -v9fs_vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n", @@ -1356,7 +1356,7 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, /** * v9fs_vfs_mknod - create a special file - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @dir: inode destination for new link * @dentry: dentry for file * @mode: mode for creation @@ -1365,7 +1365,7 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, */ static int -v9fs_vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index f806b3f11649..3bed3eb3a0e2 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -30,7 +30,7 @@ #include "acl.h" static int -v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t omode, dev_t rdev); /** @@ -211,7 +211,7 @@ int v9fs_open_to_dotl_flags(int flags) /** * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol. - * @mnt_userns: The user namespace of the mount + * @idmap: The user namespace of the mount * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @omode: create permissions @@ -219,10 +219,10 @@ int v9fs_open_to_dotl_flags(int flags) * */ static int -v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_create_dotl(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t omode, bool excl) { - return v9fs_vfs_mknod_dotl(mnt_userns, dir, dentry, omode, 0); + return v9fs_vfs_mknod_dotl(idmap, dir, dentry, omode, 0); } static int @@ -356,14 +356,14 @@ out: /** * v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory - * @mnt_userns: The user namespace of the mount + * @idmap: The idmap of the mount * @dir: inode that is being unlinked * @dentry: dentry that is being unlinked * @omode: mode for new directory * */ -static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns, +static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t omode) { @@ -450,7 +450,7 @@ error: } static int -v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns, +v9fs_vfs_getattr_dotl(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -462,7 +462,7 @@ v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { - generic_fillattr(&init_user_ns, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); return 0; } fid = v9fs_fid_lookup(dentry); @@ -479,7 +479,7 @@ v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns, return PTR_ERR(st); v9fs_stat2inode_dotl(st, d_inode(dentry), 0); - generic_fillattr(&init_user_ns, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); /* Change block size to what the server returned */ stat->blksize = st->st_blksize; @@ -529,13 +529,13 @@ static int v9fs_mapped_iattr_valid(int iattr_valid) /** * v9fs_vfs_setattr_dotl - set file metadata - * @mnt_userns: The user namespace of the mount + * @idmap: idmap of the mount * @dentry: file whose metadata to set * @iattr: metadata assignment structure * */ -int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, +int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; @@ -548,7 +548,7 @@ int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, p9_debug(P9_DEBUG_VFS, "\n"); - retval = setattr_prepare(&init_user_ns, dentry, iattr); + retval = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (retval) return retval; @@ -597,7 +597,7 @@ int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, truncate_setsize(inode, iattr->ia_size); v9fs_invalidate_inode_attr(inode); - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) { /* We also want to update ACL when we update mode bits */ @@ -687,7 +687,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, } static int -v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_symlink_dotl(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int err; @@ -817,7 +817,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, /** * v9fs_vfs_mknod_dotl - create a special file - * @mnt_userns: The user namespace of the mount + * @idmap: The idmap of the mount * @dir: inode destination for new link * @dentry: dentry for file * @omode: mode for creation @@ -825,7 +825,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, * */ static int -v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, +v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t omode, dev_t rdev) { int err; diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index b6984311e00a..50f7f3f6b55e 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -150,7 +150,7 @@ static int v9fs_xattr_handler_get(const struct xattr_handler *handler, } static int v9fs_xattr_handler_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/Makefile b/fs/Makefile index 4dea17840761..76abc9e055bd 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -16,7 +16,7 @@ obj-y := open.o read_write.o file_table.o super.o \ pnode.o splice.o sync.o utimes.o d_path.o \ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ fs_types.o fs_context.o fs_parser.o fsopen.o init.o \ - kernel_read_file.o remap_range.o + kernel_read_file.o mnt_idmapping.o remap_range.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o direct-io.o mpage.o diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h index 06b7c92343ad..223f0283d20f 100644 --- a/fs/adfs/adfs.h +++ b/fs/adfs/adfs.h @@ -144,7 +144,7 @@ struct adfs_discmap { /* Inode stuff */ struct inode *adfs_iget(struct super_block *sb, struct object_info *obj); int adfs_write_inode(struct inode *inode, struct writeback_control *wbc); -int adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, +int adfs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); /* map.c */ diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index ee22278b0cfc..c3ac613d0975 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -294,7 +294,7 @@ out: * later. */ int -adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, +adfs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -302,7 +302,7 @@ adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, unsigned int ia_valid = attr->ia_valid; int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); /* * we can't change the UID or GID of any file - diff --git a/fs/affs/affs.h b/fs/affs/affs.h index bfa89e131ead..60685ec76d98 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -167,17 +167,17 @@ extern const struct export_operations affs_export_ops; extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); -extern int affs_create(struct user_namespace *mnt_userns, struct inode *dir, +extern int affs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool); -extern int affs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +extern int affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, struct dentry *dentry); -extern int affs_symlink(struct user_namespace *mnt_userns, +extern int affs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname); -extern int affs_rename2(struct user_namespace *mnt_userns, +extern int affs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); @@ -185,7 +185,7 @@ extern int affs_rename2(struct user_namespace *mnt_userns, /* inode.c */ extern struct inode *affs_new_inode(struct inode *dir); -extern int affs_notify_change(struct user_namespace *mnt_userns, +extern int affs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void affs_evict_inode(struct inode *inode); extern struct inode *affs_iget(struct super_block *sb, diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 2352a75bd9d6..27f77a52c5c8 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -216,7 +216,7 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc) } int -affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, +affs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -224,7 +224,7 @@ affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid); - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) goto out; @@ -250,7 +250,7 @@ affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, affs_truncate(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); if (attr->ia_valid & ATTR_MODE) diff --git a/fs/affs/namei.c b/fs/affs/namei.c index bcab18956b4f..d12ccfd2a83d 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -242,7 +242,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry) } int -affs_create(struct user_namespace *mnt_userns, struct inode *dir, +affs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; @@ -274,7 +274,7 @@ affs_create(struct user_namespace *mnt_userns, struct inode *dir, } int -affs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -313,7 +313,7 @@ affs_rmdir(struct inode *dir, struct dentry *dentry) } int -affs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +affs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct super_block *sb = dir->i_sb; @@ -503,7 +503,7 @@ done: return retval; } -int affs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, +int affs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/afs/dir.c b/fs/afs/dir.c index b7c1f8c84b38..82690d1dd49a 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -28,17 +28,17 @@ static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, in loff_t fpos, u64 ino, unsigned dtype); static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); -static int afs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int afs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl); -static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); static int afs_rmdir(struct inode *dir, struct dentry *dentry); static int afs_unlink(struct inode *dir, struct dentry *dentry); static int afs_link(struct dentry *from, struct inode *dir, struct dentry *dentry); -static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *content); -static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags); @@ -1332,7 +1332,7 @@ static const struct afs_operation_ops afs_mkdir_operation = { /* * create a directory on an AFS filesystem */ -static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct afs_operation *op; @@ -1630,7 +1630,7 @@ static const struct afs_operation_ops afs_create_operation = { /* * create a regular file on an AFS filesystem */ -static int afs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int afs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct afs_operation *op; @@ -1760,7 +1760,7 @@ static const struct afs_operation_ops afs_symlink_operation = { /* * create a symlink in an AFS filesystem */ -static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *content) { struct afs_operation *op; @@ -1897,7 +1897,7 @@ static const struct afs_operation_ops afs_rename_operation = { /* * rename a file in an AFS filesystem and/or move it between directories */ -static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/afs/flock.c b/fs/afs/flock.c index bbcc5afd1576..9c6dea3139f5 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -451,7 +451,7 @@ static int afs_do_setlk_check(struct afs_vnode *vnode, struct key *key, */ static int afs_do_setlk(struct file *file, struct file_lock *fl) { - struct inode *inode = locks_inode(file); + struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); enum afs_flock_mode mode = AFS_FS_S(inode->i_sb)->flock_mode; afs_lock_type_t type; @@ -701,7 +701,7 @@ error: */ static int afs_do_unlk(struct file *file, struct file_lock *fl) { - struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); int ret; _enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); @@ -721,7 +721,7 @@ static int afs_do_unlk(struct file *file, struct file_lock *fl) */ static int afs_do_getlk(struct file *file, struct file_lock *fl) { - struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); struct key *key = afs_file_key(file); int ret, lock_count; @@ -763,7 +763,7 @@ error: */ int afs_lock(struct file *file, int cmd, struct file_lock *fl) { - struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); enum afs_flock_operation op; int ret; @@ -798,7 +798,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl) */ int afs_flock(struct file *file, int cmd, struct file_lock *fl) { - struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); enum afs_flock_operation op; int ret; @@ -843,7 +843,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl) */ static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl) { - struct afs_vnode *vnode = AFS_FS_I(locks_inode(fl->fl_file)); + struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->fl_file)); _enter(""); @@ -861,7 +861,7 @@ static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl) */ static void afs_fl_release_private(struct file_lock *fl) { - struct afs_vnode *vnode = AFS_FS_I(locks_inode(fl->fl_file)); + struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->fl_file)); _enter(""); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 6d3a3dbe4928..0167e96e5198 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -737,7 +737,7 @@ error_unlock: /* * read the attributes of an inode */ -int afs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int afs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -761,7 +761,7 @@ int afs_getattr(struct user_namespace *mnt_userns, const struct path *path, do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) && stat->nlink > 0) stat->nlink -= 1; @@ -870,7 +870,7 @@ static const struct afs_operation_ops afs_setattr_operation = { /* * set the attributes of an inode */ -int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { const unsigned int supported = diff --git a/fs/afs/internal.h b/fs/afs/internal.h index fd8567b98e2b..ad8523d0d038 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/pagemap.h> #include <linux/rxrpc.h> #include <linux/key.h> @@ -1170,9 +1171,9 @@ extern struct inode *afs_iget(struct afs_operation *, struct afs_vnode_param *); extern struct inode *afs_root_iget(struct super_block *, struct key *); extern bool afs_check_validity(struct afs_vnode *); extern int afs_validate(struct afs_vnode *, struct key *); -extern int afs_getattr(struct user_namespace *mnt_userns, const struct path *, +extern int afs_getattr(struct mnt_idmap *idmap, const struct path *, struct kstat *, u32, unsigned int); -extern int afs_setattr(struct user_namespace *mnt_userns, struct dentry *, struct iattr *); +extern int afs_setattr(struct mnt_idmap *idmap, struct dentry *, struct iattr *); extern void afs_evict_inode(struct inode *); extern int afs_drop_inode(struct inode *); @@ -1387,7 +1388,7 @@ extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int, extern struct key *afs_request_key(struct afs_cell *); extern struct key *afs_request_key_rcu(struct afs_cell *); extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *); -extern int afs_permission(struct user_namespace *, struct inode *, int); +extern int afs_permission(struct mnt_idmap *, struct inode *, int); extern void __exit afs_clean_up_permit_cache(void); /* diff --git a/fs/afs/security.c b/fs/afs/security.c index 7c6a63a30394..6a7744c9e2a2 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -395,7 +395,7 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, * - AFS ACLs are attached to directories only, and a file is controlled by its * parent directory's ACL */ -int afs_permission(struct user_namespace *mnt_userns, struct inode *inode, +int afs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct afs_vnode *vnode = AFS_FS_I(inode); diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index 7751b0b3f81d..9048d8ccc715 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -97,7 +97,7 @@ static const struct afs_operation_ops afs_store_acl_operation = { * Set a file's AFS3 ACL. */ static int afs_xattr_set_acl(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) @@ -228,7 +228,7 @@ static const struct afs_operation_ops yfs_store_opaque_acl2_operation = { * Set a file's YFS ACL. */ static int afs_xattr_set_yfs(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) @@ -361,6 +361,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma) spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); + if (!table) + goto out_unlock; + for (i = 0; i < table->nr; i++) { struct kioctx *ctx; @@ -374,6 +377,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) } } +out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; diff --git a/fs/attr.c b/fs/attr.c index b45f30e516fa..aca9ff7aed33 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -14,6 +14,7 @@ #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> +#include <linux/filelock.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/ima.h> @@ -23,7 +24,7 @@ /** * setattr_should_drop_sgid - determine whether the setgid bit needs to be * removed - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the setgid bit needs to be removed. @@ -33,7 +34,7 @@ * * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. */ -int setattr_should_drop_sgid(struct user_namespace *mnt_userns, +int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode) { umode_t mode = inode->i_mode; @@ -42,8 +43,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, return 0; if (mode & S_IXGRP) return ATTR_KILL_SGID; - if (!in_group_or_capable(mnt_userns, inode, - i_gid_into_vfsgid(mnt_userns, inode))) + if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) return ATTR_KILL_SGID; return 0; } @@ -51,7 +51,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to * be dropped - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the set{g,u}id bits need to be removed. @@ -63,7 +63,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits * to remove, 0 otherwise. */ -int setattr_should_drop_suidgid(struct user_namespace *mnt_userns, +int setattr_should_drop_suidgid(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; @@ -73,7 +73,7 @@ int setattr_should_drop_suidgid(struct user_namespace *mnt_userns, if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; - kill |= setattr_should_drop_sgid(mnt_userns, inode); + kill |= setattr_should_drop_sgid(idmap, inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; @@ -84,24 +84,24 @@ EXPORT_SYMBOL(setattr_should_drop_suidgid); /** * chown_ok - verify permissions to chown inode - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsuid: uid to chown @inode to * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply pass @nop_mnt_idmap. */ -static bool chown_ok(struct user_namespace *mnt_userns, +static bool chown_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsuid_t ia_vfsuid) { - vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid()) && vfsuid_eq(ia_vfsuid, vfsuid)) return true; - if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) + if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsuid_valid(vfsuid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) @@ -111,28 +111,28 @@ static bool chown_ok(struct user_namespace *mnt_userns, /** * chgrp_ok - verify permissions to chgrp inode - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsgid: gid to chown @inode to * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply pass @nop_mnt_idmap. */ -static bool chgrp_ok(struct user_namespace *mnt_userns, +static bool chgrp_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t ia_vfsgid) { - vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); - vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) { if (vfsgid_eq(ia_vfsgid, vfsgid)) return true; if (vfsgid_in_group_p(ia_vfsgid)) return true; } - if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) + if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsgid_valid(vfsgid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) @@ -142,7 +142,7 @@ static bool chgrp_ok(struct user_namespace *mnt_userns, /** * setattr_prepare - check if attribute changes to a dentry are allowed - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: dentry to check * @attr: attributes to change * @@ -152,16 +152,16 @@ static bool chgrp_ok(struct user_namespace *mnt_userns, * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ -int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry, +int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -183,34 +183,34 @@ int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry, /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && - !chown_ok(mnt_userns, inode, attr->ia_vfsuid)) + !chown_ok(idmap, inode, attr->ia_vfsuid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && - !chgrp_ok(mnt_userns, inode, attr->ia_vfsgid)) + !chgrp_ok(idmap, inode, attr->ia_vfsgid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { vfsgid_t vfsgid; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ia_valid & ATTR_GID) vfsgid = attr->ia_vfsgid; else - vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsgid = i_gid_into_vfsgid(idmap, inode); /* Also check the setgid bit! */ - if (!in_group_or_capable(mnt_userns, inode, vfsgid)) + if (!in_group_or_capable(idmap, inode, vfsgid)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; } @@ -219,7 +219,7 @@ kill_priv: if (ia_valid & ATTR_KILL_PRIV) { int error; - error = security_inode_killpriv(mnt_userns, dentry); + error = security_inode_killpriv(idmap, dentry); if (error) return error; } @@ -276,7 +276,7 @@ EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy - copy simple metadata updates into the generic inode - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: the inode to be updated * @attr: the new attributes * @@ -289,23 +289,23 @@ EXPORT_SYMBOL(inode_newsize_ok); * Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply pass @nop_mnt_idmap. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ -void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, +void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; - i_uid_update(mnt_userns, attr, inode); - i_gid_update(mnt_userns, attr, inode); + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_ATIME) inode->i_atime = attr->ia_atime; if (ia_valid & ATTR_MTIME) @@ -314,15 +314,15 @@ void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - if (!in_group_or_capable(mnt_userns, inode, - i_gid_into_vfsgid(mnt_userns, inode))) + if (!in_group_or_capable(idmap, inode, + i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; inode->i_mode = mode; } } EXPORT_SYMBOL(setattr_copy); -int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, +int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid) { int error; @@ -340,8 +340,8 @@ int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, if (IS_IMMUTABLE(inode)) return -EPERM; - if (!inode_owner_or_capable(mnt_userns, inode)) { - error = inode_permission(mnt_userns, inode, MAY_WRITE); + if (!inode_owner_or_capable(idmap, inode)) { + error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; } @@ -352,7 +352,7 @@ EXPORT_SYMBOL(may_setattr); /** * notify_change - modify attributes of a filesytem object - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated @@ -371,13 +371,13 @@ EXPORT_SYMBOL(may_setattr); * the file open for write, as there can be no conflicting delegation in * that case. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply pass @nop_mnt_idmap. */ -int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, +int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; @@ -388,7 +388,7 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, WARN_ON_ONCE(!inode_is_locked(inode)); - error = may_setattr(mnt_userns, inode, ia_valid); + error = may_setattr(idmap, inode, ia_valid); if (error) return error; @@ -453,11 +453,11 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, * namespace of the superblock. */ if (ia_valid & ATTR_UID && - !vfsuid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns, + !vfsuid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsuid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && - !vfsgid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns, + !vfsgid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsgid)) return -EOVERFLOW; @@ -465,13 +465,13 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && - !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode))) + !vfsuid_valid(i_uid_into_vfsuid(idmap, inode))) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && - !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode))) + !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; - error = security_inode_setattr(mnt_userns, dentry, attr); + error = security_inode_setattr(idmap, dentry, attr); if (error) return error; error = try_break_deleg(inode, delegated_inode); @@ -479,13 +479,13 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, return error; if (inode->i_op->setattr) - error = inode->i_op->setattr(mnt_userns, dentry, attr); + error = inode->i_op->setattr(idmap, dentry, attr); else - error = simple_setattr(mnt_userns, dentry, attr); + error = simple_setattr(idmap, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); - ima_inode_post_setattr(mnt_userns, dentry); + ima_inode_post_setattr(idmap, dentry); evm_inode_post_setattr(dentry, ia_valid); } diff --git a/fs/autofs/root.c b/fs/autofs/root.c index ca03c1cae2be..6baf90b08e0e 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -10,12 +10,12 @@ #include "autofs_i.h" -static int autofs_dir_permission(struct user_namespace *, struct inode *, int); -static int autofs_dir_symlink(struct user_namespace *, struct inode *, +static int autofs_dir_permission(struct mnt_idmap *, struct inode *, int); +static int autofs_dir_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); static int autofs_dir_unlink(struct inode *, struct dentry *); static int autofs_dir_rmdir(struct inode *, struct dentry *); -static int autofs_dir_mkdir(struct user_namespace *, struct inode *, +static int autofs_dir_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); static long autofs_root_ioctl(struct file *, unsigned int, unsigned long); #ifdef CONFIG_COMPAT @@ -543,7 +543,7 @@ static struct dentry *autofs_lookup(struct inode *dir, return NULL; } -static int autofs_dir_permission(struct user_namespace *mnt_userns, +static int autofs_dir_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (mask & MAY_WRITE) { @@ -560,10 +560,10 @@ static int autofs_dir_permission(struct user_namespace *mnt_userns, return -EACCES; } - return generic_permission(mnt_userns, inode, mask); + return generic_permission(idmap, inode, mask); } -static int autofs_dir_symlink(struct user_namespace *mnt_userns, +static int autofs_dir_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { @@ -720,7 +720,7 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) return 0; } -static int autofs_dir_mkdir(struct user_namespace *mnt_userns, +static int autofs_dir_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 92737166203f..db649487d58c 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -27,7 +27,7 @@ static const struct file_operations bad_file_ops = .open = bad_file_open, }; -static int bad_inode_create(struct user_namespace *mnt_userns, +static int bad_inode_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { @@ -51,14 +51,14 @@ static int bad_inode_unlink(struct inode *dir, struct dentry *dentry) return -EIO; } -static int bad_inode_symlink(struct user_namespace *mnt_userns, +static int bad_inode_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { return -EIO; } -static int bad_inode_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int bad_inode_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { return -EIO; @@ -69,13 +69,13 @@ static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry) return -EIO; } -static int bad_inode_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int bad_inode_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { return -EIO; } -static int bad_inode_rename2(struct user_namespace *mnt_userns, +static int bad_inode_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -89,20 +89,20 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, return -EIO; } -static int bad_inode_permission(struct user_namespace *mnt_userns, +static int bad_inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { return -EIO; } -static int bad_inode_getattr(struct user_namespace *mnt_userns, +static int bad_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { return -EIO; } -static int bad_inode_setattr(struct user_namespace *mnt_userns, +static int bad_inode_setattr(struct mnt_idmap *idmap, struct dentry *direntry, struct iattr *attrs) { return -EIO; @@ -146,14 +146,14 @@ static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry, return -EIO; } -static int bad_inode_tmpfile(struct user_namespace *mnt_userns, +static int bad_inode_tmpfile(struct mnt_idmap *idmap, struct inode *inode, struct file *file, umode_t mode) { return -EIO; } -static int bad_inode_set_acl(struct user_namespace *mnt_userns, +static int bad_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 34d4f68f786b..040d5140e426 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -75,7 +75,7 @@ const struct file_operations bfs_dir_operations = { .llseek = generic_file_llseek, }; -static int bfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int bfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { int err; @@ -96,7 +96,7 @@ static int bfs_create(struct user_namespace *mnt_userns, struct inode *dir, } set_bit(ino, info->si_imap); info->si_freei--; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_blocks = 0; inode->i_op = &bfs_file_inops; @@ -199,7 +199,7 @@ out_brelse: return error; } -static int bfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int bfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 3da1779e8b79..7427449a04a3 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -110,7 +110,7 @@ out: return ret; } -int btrfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int btrfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int ret; @@ -118,7 +118,7 @@ int btrfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, umode_t old_mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - ret = posix_acl_update_mode(mnt_userns, inode, + ret = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (ret) return ret; diff --git a/fs/btrfs/acl.h b/fs/btrfs/acl.h index 39bd36e6eeb7..a270e71ec05f 100644 --- a/fs/btrfs/acl.h +++ b/fs/btrfs/acl.h @@ -6,7 +6,7 @@ #ifdef CONFIG_BTRFS_FS_POSIX_ACL struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu); -int btrfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int btrfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode, struct posix_acl *acl, int type); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 49a92aa65de1..9dc21622806e 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -453,7 +453,7 @@ int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, int btrfs_create_new_inode(struct btrfs_trans_handle *trans, struct btrfs_new_inode_args *args); void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args); -struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns, +struct inode *btrfs_new_subvol_inode(struct mnt_idmap *idmap, struct inode *dir); void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *state, u32 bits); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 44e9acc77a74..6c18dc9a1831 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5128,7 +5128,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) return ret; } -static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +static int btrfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -5138,7 +5138,7 @@ static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentr if (btrfs_root_readonly(root)) return -EROFS; - err = setattr_prepare(mnt_userns, dentry, attr); + err = setattr_prepare(idmap, dentry, attr); if (err) return err; @@ -5149,12 +5149,12 @@ static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentr } if (attr->ia_valid) { - setattr_copy(mnt_userns, inode, attr); + setattr_copy(idmap, inode, attr); inode_inc_iversion(inode); err = btrfs_dirty_inode(BTRFS_I(inode)); if (!err && attr->ia_valid & ATTR_MODE) - err = posix_acl_chmod(mnt_userns, dentry, inode->i_mode); + err = posix_acl_chmod(idmap, dentry, inode->i_mode); } return err; @@ -6569,7 +6569,7 @@ out_inode: return err; } -static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int btrfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; @@ -6577,13 +6577,13 @@ static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, inode = new_inode(dir->i_sb); if (!inode) return -ENOMEM; - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); inode->i_op = &btrfs_special_inode_operations; init_special_inode(inode, inode->i_mode, rdev); return btrfs_create_common(dir, dentry, inode); } -static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int btrfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; @@ -6591,7 +6591,7 @@ static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir, inode = new_inode(dir->i_sb); if (!inode) return -ENOMEM; - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; inode->i_mapping->a_ops = &btrfs_aops; @@ -6682,7 +6682,7 @@ fail: return err; } -static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -6690,7 +6690,7 @@ static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, inode = new_inode(dir->i_sb); if (!inode) return -ENOMEM; - inode_init_owner(mnt_userns, inode, dir, S_IFDIR | mode); + inode_init_owner(idmap, inode, dir, S_IFDIR | mode); inode->i_op = &btrfs_dir_inode_operations; inode->i_fop = &btrfs_dir_file_operations; return btrfs_create_common(dir, dentry, inode); @@ -8423,7 +8423,7 @@ out: return ret; } -struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns, +struct inode *btrfs_new_subvol_inode(struct mnt_idmap *idmap, struct inode *dir) { struct inode *inode; @@ -8434,7 +8434,7 @@ struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns, * Subvolumes don't inherit the sgid bit or the parent's gid if * the parent's sgid bit is set. This is probably a bug. */ - inode_init_owner(mnt_userns, inode, NULL, + inode_init_owner(idmap, inode, NULL, S_IFDIR | (~current_umask() & S_IRWXUGO)); inode->i_op = &btrfs_dir_inode_operations; inode->i_fop = &btrfs_dir_file_operations; @@ -8623,7 +8623,7 @@ fail: return -ENOMEM; } -static int btrfs_getattr(struct user_namespace *mnt_userns, +static int btrfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -8653,7 +8653,7 @@ static int btrfs_getattr(struct user_namespace *mnt_userns, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; spin_lock(&BTRFS_I(inode)->lock); @@ -8908,14 +8908,14 @@ out_notrans: return ret; } -static struct inode *new_whiteout_inode(struct user_namespace *mnt_userns, +static struct inode *new_whiteout_inode(struct mnt_idmap *idmap, struct inode *dir) { struct inode *inode; inode = new_inode(dir->i_sb); if (inode) { - inode_init_owner(mnt_userns, inode, dir, + inode_init_owner(idmap, inode, dir, S_IFCHR | WHITEOUT_MODE); inode->i_op = &btrfs_special_inode_operations; init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); @@ -8923,7 +8923,7 @@ static struct inode *new_whiteout_inode(struct user_namespace *mnt_userns, return inode; } -static int btrfs_rename(struct user_namespace *mnt_userns, +static int btrfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -8995,7 +8995,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, filemap_flush(old_inode->i_mapping); if (flags & RENAME_WHITEOUT) { - whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir); + whiteout_args.inode = new_whiteout_inode(idmap, old_dir); if (!whiteout_args.inode) { ret = -ENOMEM; goto out_fscrypt_names; @@ -9164,7 +9164,7 @@ out_fscrypt_names: return ret; } -static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, +static int btrfs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -9177,7 +9177,7 @@ static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_di ret = btrfs_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); else - ret = btrfs_rename(mnt_userns, old_dir, old_dentry, new_dir, + ret = btrfs_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags); btrfs_btree_balance_dirty(BTRFS_I(new_dir)->root->fs_info); @@ -9377,7 +9377,7 @@ out: return ret; } -static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); @@ -9405,7 +9405,7 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, inode = new_inode(dir->i_sb); if (!inode) return -ENOMEM; - inode_init_owner(mnt_userns, inode, dir, S_IFLNK | S_IRWXUGO); + inode_init_owner(idmap, inode, dir, S_IFLNK | S_IRWXUGO); inode->i_op = &btrfs_symlink_inode_operations; inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_aops; @@ -9694,7 +9694,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, min_size, actual_len, alloc_hint, trans); } -static int btrfs_permission(struct user_namespace *mnt_userns, +static int btrfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -9707,10 +9707,10 @@ static int btrfs_permission(struct user_namespace *mnt_userns, if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) return -EACCES; } - return generic_permission(mnt_userns, inode, mask); + return generic_permission(idmap, inode, mask); } -static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); @@ -9728,7 +9728,7 @@ static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, inode = new_inode(dir->i_sb); if (!inode) return -ENOMEM; - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; inode->i_mapping->a_ops = &btrfs_aops; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8ea557e22252..84626c8ad5bf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -243,7 +243,7 @@ int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int btrfs_fileattr_set(struct user_namespace *mnt_userns, +int btrfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -578,7 +578,7 @@ static unsigned int create_subvol_num_items(struct btrfs_qgroup_inherit *inherit return num_items; } -static noinline int create_subvol(struct user_namespace *mnt_userns, +static noinline int create_subvol(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct btrfs_qgroup_inherit *inherit) { @@ -623,7 +623,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, if (ret < 0) goto out_root_item; - new_inode_args.inode = btrfs_new_subvol_inode(mnt_userns, dir); + new_inode_args.inode = btrfs_new_subvol_inode(idmap, dir); if (!new_inode_args.inode) { ret = -ENOMEM; goto out_anon_dev; @@ -898,7 +898,7 @@ free_pending: * nfs_async_unlink(). */ -static int btrfs_may_delete(struct user_namespace *mnt_userns, +static int btrfs_may_delete(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, int isdir) { int error; @@ -909,12 +909,12 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns, BUG_ON(d_inode(victim->d_parent) != dir); audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(mnt_userns, dir, d_inode(victim)) || + if (check_sticky(idmap, dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) || IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim))) return -EPERM; @@ -933,16 +933,16 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns, } /* copy of may_create in fs/namei.c() */ -static inline int btrfs_may_create(struct user_namespace *mnt_userns, +static inline int btrfs_may_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child) { if (d_really_is_positive(child)) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns)) + if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; - return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); + return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } /* @@ -951,7 +951,7 @@ static inline int btrfs_may_create(struct user_namespace *mnt_userns, * inside this filesystem so it's quite a bit simpler. */ static noinline int btrfs_mksubvol(const struct path *parent, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const char *name, int namelen, struct btrfs_root *snap_src, bool readonly, @@ -967,12 +967,12 @@ static noinline int btrfs_mksubvol(const struct path *parent, if (error == -EINTR) return error; - dentry = lookup_one(mnt_userns, name, parent->dentry, namelen); + dentry = lookup_one(idmap, name, parent->dentry, namelen); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_unlock; - error = btrfs_may_create(mnt_userns, dir, dentry); + error = btrfs_may_create(idmap, dir, dentry); if (error) goto out_dput; @@ -993,7 +993,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, if (snap_src) error = create_snapshot(snap_src, dir, dentry, readonly, inherit); else - error = create_subvol(mnt_userns, dir, dentry, inherit); + error = create_subvol(idmap, dir, dentry, inherit); if (!error) fsnotify_mkdir(dir, dentry); @@ -1007,7 +1007,7 @@ out_unlock: } static noinline int btrfs_mksnapshot(const struct path *parent, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const char *name, int namelen, struct btrfs_root *root, bool readonly, @@ -1037,7 +1037,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent, btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); - ret = btrfs_mksubvol(parent, mnt_userns, name, namelen, + ret = btrfs_mksubvol(parent, idmap, name, namelen, root, readonly, inherit); out: if (snapshot_force_cow) @@ -1240,7 +1240,7 @@ out_drop: } static noinline int __btrfs_ioctl_snap_create(struct file *file, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const char *name, unsigned long fd, int subvol, bool readonly, struct btrfs_qgroup_inherit *inherit) @@ -1268,7 +1268,7 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, } if (subvol) { - ret = btrfs_mksubvol(&file->f_path, mnt_userns, name, + ret = btrfs_mksubvol(&file->f_path, idmap, name, namelen, NULL, readonly, inherit); } else { struct fd src = fdget(fd); @@ -1283,14 +1283,14 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); ret = -EXDEV; - } else if (!inode_owner_or_capable(mnt_userns, src_inode)) { + } else if (!inode_owner_or_capable(idmap, src_inode)) { /* * Subvolume creation is not restricted, but snapshots * are limited to own subvolumes only */ ret = -EPERM; } else { - ret = btrfs_mksnapshot(&file->f_path, mnt_userns, + ret = btrfs_mksnapshot(&file->f_path, idmap, name, namelen, BTRFS_I(src_inode)->root, readonly, inherit); @@ -1317,7 +1317,7 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, return PTR_ERR(vol_args); vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file), + ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), vol_args->name, vol_args->fd, subvol, false, NULL); @@ -1377,7 +1377,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, } } - ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file), + ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), vol_args->name, vol_args->fd, subvol, readonly, inherit); if (ret) @@ -1422,7 +1422,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, u64 flags; int ret = 0; - if (!inode_owner_or_capable(file_mnt_user_ns(file), inode)) + if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -1870,7 +1870,7 @@ out: return ret; } -static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, +static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, struct inode *inode, struct btrfs_ioctl_ino_lookup_user_args *args) { @@ -1962,7 +1962,7 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, ret = PTR_ERR(temp_inode); goto out_put; } - ret = inode_permission(mnt_userns, temp_inode, + ret = inode_permission(idmap, temp_inode, MAY_READ | MAY_EXEC); iput(temp_inode); if (ret) { @@ -2101,7 +2101,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp) return -EACCES; } - ret = btrfs_search_path_in_tree_user(file_mnt_user_ns(file), inode, args); + ret = btrfs_search_path_in_tree_user(file_mnt_idmap(file), inode, args); if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) ret = -EFAULT; @@ -2335,7 +2335,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, struct btrfs_root *dest = NULL; struct btrfs_ioctl_vol_args *vol_args = NULL; struct btrfs_ioctl_vol_args_v2 *vol_args2 = NULL; - struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct mnt_idmap *idmap = file_mnt_idmap(file); char *subvol_name, *subvol_name_ptr = NULL; int subvol_namelen; int err = 0; @@ -2428,7 +2428,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, * anywhere in the filesystem the user wouldn't be able * to delete without an idmapped mount. */ - if (old_dir != dir && mnt_userns != &init_user_ns) { + if (old_dir != dir && idmap != &nop_mnt_idmap) { err = -EOPNOTSUPP; goto free_parent; } @@ -2471,7 +2471,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); if (err == -EINTR) goto free_subvol_name; - dentry = lookup_one(mnt_userns, subvol_name, parent, subvol_namelen); + dentry = lookup_one(idmap, subvol_name, parent, subvol_namelen); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_unlock_dir; @@ -2513,13 +2513,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, if (root == dest) goto out_dput; - err = inode_permission(mnt_userns, inode, MAY_WRITE | MAY_EXEC); + err = inode_permission(idmap, inode, MAY_WRITE | MAY_EXEC); if (err) goto out_dput; } /* check if subvolume may be deleted by a user */ - err = btrfs_may_delete(mnt_userns, dir, dentry, 1); + err = btrfs_may_delete(idmap, dir, dentry, 1); if (err) goto out_dput; @@ -2582,7 +2582,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) * running and allows defrag on files open in read-only mode. */ if (!capable(CAP_SYS_ADMIN) && - inode_permission(&init_user_ns, inode, MAY_WRITE)) { + inode_permission(&nop_mnt_idmap, inode, MAY_WRITE)) { ret = -EPERM; goto out; } @@ -3907,7 +3907,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info, } static long _btrfs_ioctl_set_received_subvol(struct file *file, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct btrfs_ioctl_received_subvol_args *sa) { struct inode *inode = file_inode(file); @@ -3919,7 +3919,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, int ret = 0; int received_uuid_changed; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -4024,7 +4024,7 @@ static long btrfs_ioctl_set_received_subvol_32(struct file *file, args64->rtime.nsec = args32->rtime.nsec; args64->flags = args32->flags; - ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_user_ns(file), args64); + ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_idmap(file), args64); if (ret) goto out; @@ -4058,7 +4058,7 @@ static long btrfs_ioctl_set_received_subvol(struct file *file, if (IS_ERR(sa)) return PTR_ERR(sa); - ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_user_ns(file), sa); + ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_idmap(file), sa); if (ret) goto out; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 8a855d5ac2fa..d51b9a2f2f6e 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -6,7 +6,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int btrfs_fileattr_set(struct user_namespace *mnt_userns, +int btrfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int btrfs_ioctl_get_supported_features(void __user *arg); void btrfs_sync_inode_flags_to_i_flags(struct inode *inode); diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 181469fc0bb3..ca09cf9afce8 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -64,7 +64,7 @@ struct inode *btrfs_new_test_inode(void) BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; BTRFS_I(inode)->location.offset = 0; - inode_init_owner(&init_user_ns, inode, NULL, S_IFREG); + inode_init_owner(&nop_mnt_idmap, inode, NULL, S_IFREG); return inode; } diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c index bf9eb693a6a7..c5ff16f9e9fa 100644 --- a/fs/btrfs/verity.c +++ b/fs/btrfs/verity.c @@ -783,30 +783,25 @@ again: /* * fsverity op that writes a Merkle tree block into the btree. * - * @inode: inode to write a Merkle tree block for - * @buf: Merkle tree data block to write - * @index: index of the block in the Merkle tree - * @log_blocksize: log base 2 of the Merkle tree block size - * - * Note that the block size could be different from the page size, so it is not - * safe to assume that index is a page index. + * @inode: inode to write a Merkle tree block for + * @buf: Merkle tree block to write + * @pos: the position of the block in the Merkle tree (in bytes) + * @size: the Merkle tree block size (in bytes) * * Returns 0 on success or negative error code on failure */ static int btrfs_write_merkle_tree_block(struct inode *inode, const void *buf, - u64 index, int log_blocksize) + u64 pos, unsigned int size) { - u64 off = index << log_blocksize; - u64 len = 1ULL << log_blocksize; loff_t merkle_pos = merkle_file_pos(inode); if (merkle_pos < 0) return merkle_pos; - if (merkle_pos > inode->i_sb->s_maxbytes - off - len) + if (merkle_pos > inode->i_sb->s_maxbytes - pos - size) return -EFBIG; return write_key_bytes(BTRFS_I(inode), BTRFS_VERITY_MERKLE_ITEM_KEY, - off, buf, len); + pos, buf, size); } const struct fsverity_operations btrfs_verityops = { diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 0ed4b119a7ca..0ebeaf4e81f9 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -370,7 +370,7 @@ static int btrfs_xattr_handler_get(const struct xattr_handler *handler, } static int btrfs_xattr_handler_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) @@ -383,7 +383,7 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, } static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/buffer.c b/fs/buffer.c index d9c6d1fbb6dd..623e77d6ef77 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -48,6 +48,7 @@ #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> +#include <linux/fsverity.h> #include "internal.h" @@ -295,20 +296,53 @@ still_busy: return; } -struct decrypt_bh_ctx { +struct postprocess_bh_ctx { struct work_struct work; struct buffer_head *bh; }; +static void verify_bh(struct work_struct *work) +{ + struct postprocess_bh_ctx *ctx = + container_of(work, struct postprocess_bh_ctx, work); + struct buffer_head *bh = ctx->bh; + bool valid; + + valid = fsverity_verify_blocks(page_folio(bh->b_page), bh->b_size, + bh_offset(bh)); + end_buffer_async_read(bh, valid); + kfree(ctx); +} + +static bool need_fsverity(struct buffer_head *bh) +{ + struct page *page = bh->b_page; + struct inode *inode = page->mapping->host; + + return fsverity_active(inode) && + /* needed by ext4 */ + page->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); +} + static void decrypt_bh(struct work_struct *work) { - struct decrypt_bh_ctx *ctx = - container_of(work, struct decrypt_bh_ctx, work); + struct postprocess_bh_ctx *ctx = + container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; - err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size, - bh_offset(bh)); + err = fscrypt_decrypt_pagecache_blocks(page_folio(bh->b_page), + bh->b_size, bh_offset(bh)); + if (err == 0 && need_fsverity(bh)) { + /* + * We use different work queues for decryption and for verity + * because verity may require reading metadata pages that need + * decryption, and we shouldn't recurse to the same workqueue. + */ + INIT_WORK(&ctx->work, verify_bh); + fsverity_enqueue_verify_work(&ctx->work); + return; + } end_buffer_async_read(bh, err == 0); kfree(ctx); } @@ -319,15 +353,24 @@ static void decrypt_bh(struct work_struct *work) */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { - /* Decrypt if needed */ - if (uptodate && - fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { - struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); + struct inode *inode = bh->b_page->mapping->host; + bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode); + bool verify = need_fsverity(bh); + + /* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */ + if (uptodate && (decrypt || verify)) { + struct postprocess_bh_ctx *ctx = + kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { - INIT_WORK(&ctx->work, decrypt_bh); ctx->bh = bh; - fscrypt_enqueue_decrypt_work(&ctx->work); + if (decrypt) { + INIT_WORK(&ctx->work, decrypt_bh); + fscrypt_enqueue_decrypt_work(&ctx->work); + } else { + INIT_WORK(&ctx->work, verify_bh); + fsverity_enqueue_verify_work(&ctx->work); + } return; } uptodate = 0; @@ -2245,6 +2288,11 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block) int nr, i; int fully_mapped = 1; bool page_error = false; + loff_t limit = i_size_read(inode); + + /* This is needed for ext4. */ + if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) + limit = inode->i_sb->s_maxbytes; VM_BUG_ON_FOLIO(folio_test_large(folio), folio); @@ -2253,7 +2301,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block) bbits = block_size_bits(blocksize); iblock = (sector_t)folio->index << (PAGE_SHIFT - bbits); - lblock = (i_size_read(inode)+blocksize-1) >> bbits; + lblock = (limit+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index a69073a1d3f0..40052bdb3365 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -138,7 +138,7 @@ static int cachefiles_adjust_size(struct cachefiles_object *object) newattrs.ia_size = oi_size & PAGE_MASK; ret = cachefiles_inject_remove_error(); if (ret == 0) - ret = notify_change(&init_user_ns, file->f_path.dentry, + ret = notify_change(&nop_mnt_idmap, file->f_path.dentry, &newattrs, NULL); if (ret < 0) goto truncate_failed; @@ -148,7 +148,7 @@ static int cachefiles_adjust_size(struct cachefiles_object *object) newattrs.ia_size = ni_size; ret = cachefiles_inject_write_error(); if (ret == 0) - ret = notify_change(&init_user_ns, file->f_path.dentry, + ret = notify_change(&nop_mnt_idmap, file->f_path.dentry, &newattrs, NULL); truncate_failed: diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 03ca8f2f657a..82219a8f6084 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -130,7 +130,7 @@ retry: goto mkdir_error; ret = cachefiles_inject_write_error(); if (ret == 0) - ret = vfs_mkdir(&init_user_ns, d_inode(dir), subdir, 0700); + ret = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); if (ret < 0) { trace_cachefiles_vfs_error(NULL, d_inode(dir), ret, cachefiles_trace_mkdir_error); @@ -245,7 +245,7 @@ static int cachefiles_unlink(struct cachefiles_cache *cache, ret = cachefiles_inject_remove_error(); if (ret == 0) { - ret = vfs_unlink(&init_user_ns, d_backing_inode(dir), dentry, NULL); + ret = vfs_unlink(&nop_mnt_idmap, d_backing_inode(dir), dentry, NULL); if (ret == -EIO) cachefiles_io_error(cache, "Unlink failed"); } @@ -382,10 +382,10 @@ try_again: cachefiles_io_error(cache, "Rename security error %d", ret); } else { struct renamedata rd = { - .old_mnt_userns = &init_user_ns, + .old_mnt_idmap = &nop_mnt_idmap, .old_dir = d_inode(dir), .old_dentry = rep, - .new_mnt_userns = &init_user_ns, + .new_mnt_idmap = &nop_mnt_idmap, .new_dir = d_inode(cache->graveyard), .new_dentry = grave, }; @@ -451,7 +451,7 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) ret = cachefiles_inject_write_error(); if (ret == 0) { - file = vfs_tmpfile_open(&init_user_ns, &parentpath, S_IFREG, + file = vfs_tmpfile_open(&nop_mnt_idmap, &parentpath, S_IFREG, O_RDWR | O_LARGEFILE | O_DIRECT, cache->cache_cred); ret = PTR_ERR_OR_ZERO(file); @@ -714,7 +714,7 @@ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, ret = cachefiles_inject_read_error(); if (ret == 0) - ret = vfs_link(object->file->f_path.dentry, &init_user_ns, + ret = vfs_link(object->file->f_path.dentry, &nop_mnt_idmap, d_inode(fan), dentry, NULL); if (ret < 0) { trace_cachefiles_vfs_error(object, d_inode(fan), ret, diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 00b087c14995..bcb6173943ee 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -65,7 +65,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) ret = cachefiles_inject_write_error(); if (ret == 0) - ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, buf, sizeof(struct cachefiles_xattr) + len, 0); if (ret < 0) { trace_cachefiles_vfs_error(object, file_inode(file), ret, @@ -108,7 +108,7 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file xlen = cachefiles_inject_read_error(); if (xlen == 0) - xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, buf, tlen); + xlen = vfs_getxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, buf, tlen); if (xlen != tlen) { if (xlen < 0) trace_cachefiles_vfs_error(object, file_inode(file), xlen, @@ -150,7 +150,7 @@ int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, ret = cachefiles_inject_remove_error(); if (ret == 0) - ret = vfs_removexattr(&init_user_ns, dentry, cachefiles_xattr_cache); + ret = vfs_removexattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache); if (ret < 0) { trace_cachefiles_vfs_error(object, d_inode(dentry), ret, cachefiles_trace_remxattr_error); @@ -207,7 +207,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) ret = cachefiles_inject_write_error(); if (ret == 0) - ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, buf, len, 0); if (ret < 0) { trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, @@ -249,7 +249,7 @@ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) xlen = cachefiles_inject_read_error(); if (xlen == 0) - xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, buf, len); + xlen = vfs_getxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, buf, len); if (xlen != len) { if (xlen < 0) { trace_cachefiles_vfs_error(NULL, d_inode(dentry), xlen, diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index c7e8dd5b58d4..6945a938d396 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -85,7 +85,7 @@ retry: return acl; } -int ceph_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int ret = 0, size = 0; @@ -105,7 +105,7 @@ int ceph_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { - ret = posix_acl_update_mode(&init_user_ns, inode, + ret = posix_acl_update_mode(&nop_mnt_idmap, inode, &new_mode, &acl); if (ret) goto out; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 210e40037881..7cc20772eac9 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -9,6 +9,7 @@ #include <linux/wait.h> #include <linux/writeback.h> #include <linux/iversion.h> +#include <linux/filelock.h> #include "super.h" #include "mds_client.h" diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 6c7026cc8988..0ced8b570e42 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -845,7 +845,7 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry) return PTR_ERR(result); } -static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); @@ -905,13 +905,13 @@ out: return err; } -static int ceph_create(struct user_namespace *mnt_userns, struct inode *dir, +static int ceph_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return ceph_mknod(mnt_userns, dir, dentry, mode, 0); + return ceph_mknod(idmap, dir, dentry, mode, 0); } -static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *dest) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); @@ -970,7 +970,7 @@ out: return err; } -static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); @@ -1269,7 +1269,7 @@ out: return err; } -static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 23d05ec87fcc..8e5f41d45283 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2227,7 +2227,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) /* * setattr */ -int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -2240,7 +2240,7 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (ceph_inode_is_shutdown(inode)) return -ESTALE; - err = setattr_prepare(&init_user_ns, dentry, attr); + err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err != 0) return err; @@ -2255,7 +2255,7 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, err = __ceph_setattr(inode, attr); if (err >= 0 && (attr->ia_valid & ATTR_MODE)) - err = posix_acl_chmod(&init_user_ns, dentry, attr->ia_mode); + err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode); return err; } @@ -2397,7 +2397,7 @@ out: * Check inode permissions. We verify we have a valid value for * the AUTH cap, then call the generic handler. */ -int ceph_permission(struct user_namespace *mnt_userns, struct inode *inode, +int ceph_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int err; @@ -2408,7 +2408,7 @@ int ceph_permission(struct user_namespace *mnt_userns, struct inode *inode, err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false); if (!err) - err = generic_permission(&init_user_ns, inode, mask); + err = generic_permission(&nop_mnt_idmap, inode, mask); return err; } @@ -2417,10 +2417,10 @@ static int statx_to_caps(u32 want, umode_t mode) { int mask = 0; - if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME|STATX_BTIME)) + if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME|STATX_BTIME|STATX_CHANGE_COOKIE)) mask |= CEPH_CAP_AUTH_SHARED; - if (want & (STATX_NLINK|STATX_CTIME)) { + if (want & (STATX_NLINK|STATX_CTIME|STATX_CHANGE_COOKIE)) { /* * The link count for directories depends on inode->i_subdirs, * and that is only updated when Fs caps are held. @@ -2431,11 +2431,10 @@ static int statx_to_caps(u32 want, umode_t mode) mask |= CEPH_CAP_LINK_SHARED; } - if (want & (STATX_ATIME|STATX_MTIME|STATX_CTIME|STATX_SIZE| - STATX_BLOCKS)) + if (want & (STATX_ATIME|STATX_MTIME|STATX_CTIME|STATX_SIZE|STATX_BLOCKS|STATX_CHANGE_COOKIE)) mask |= CEPH_CAP_FILE_SHARED; - if (want & (STATX_CTIME)) + if (want & (STATX_CTIME|STATX_CHANGE_COOKIE)) mask |= CEPH_CAP_XATTR_SHARED; return mask; @@ -2445,7 +2444,7 @@ static int statx_to_caps(u32 want, umode_t mode) * Get all the attributes. If we have sufficient caps for the requested attrs, * then we can avoid talking to the MDS at all. */ -int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ceph_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); @@ -2466,7 +2465,7 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, return err; } - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->ino = ceph_present_inode(inode); /* @@ -2478,6 +2477,11 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, valid_mask |= STATX_BTIME; } + if (request_mask & STATX_CHANGE_COOKIE) { + stat->change_cookie = inode_peek_iversion_raw(inode); + valid_mask |= STATX_CHANGE_COOKIE; + } + if (ceph_snap(inode) == CEPH_NOSNAP) stat->dev = sb->s_dev; else @@ -2519,6 +2523,8 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->nlink = 1 + 1 + ci->i_subdirs; } + stat->attributes_mask |= STATX_ATTR_CHANGE_MONOTONIC; + stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC; stat->result_mask = request_mask & valid_mask; return err; } diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 9c8dc8a55e7e..cb51c7e9c8e2 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -7,6 +7,7 @@ #include "super.h" #include "mds_client.h" +#include <linux/filelock.h> #include <linux/ceph/pagelist.h> static u64 lock_secret; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 07c6906cda70..6ecca2c6d137 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1050,12 +1050,12 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force) { return __ceph_do_getattr(inode, NULL, mask, force); } -extern int ceph_permission(struct user_namespace *mnt_userns, +extern int ceph_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); extern int __ceph_setattr(struct inode *inode, struct iattr *attr); -extern int ceph_setattr(struct user_namespace *mnt_userns, +extern int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -extern int ceph_getattr(struct user_namespace *mnt_userns, +extern int ceph_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); void ceph_inode_shutdown(struct inode *inode); @@ -1128,7 +1128,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx); #ifdef CONFIG_CEPH_FS_POSIX_ACL struct posix_acl *ceph_get_acl(struct inode *, int, bool); -int ceph_set_acl(struct user_namespace *mnt_userns, +int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int ceph_pre_init_acls(struct inode *dir, umode_t *mode, struct ceph_acl_sec_ctx *as_ctx); diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index f31350cda960..f65b07cc33a2 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1285,7 +1285,7 @@ static int ceph_get_xattr_handler(const struct xattr_handler *handler, } static int ceph_set_xattr_handler(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index bbf58c2439da..9a2d390bd06f 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1674,7 +1674,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, return rc; } -struct posix_acl *cifs_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *cifs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type) { #if defined(CONFIG_CIFS_ALLOW_INSECURE_LEGACY) && defined(CONFIG_CIFS_POSIX) @@ -1738,7 +1738,7 @@ out: #endif } -int cifs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int cifs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { #if defined(CONFIG_CIFS_ALLOW_INSECURE_LEGACY) && defined(CONFIG_CIFS_POSIX) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 10e00c624922..cb7c5460a80b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/mount.h> #include <linux/slab.h> #include <linux/init.h> @@ -345,7 +346,7 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) return -EOPNOTSUPP; } -static int cifs_permission(struct user_namespace *mnt_userns, +static int cifs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct cifs_sb_info *cifs_sb; @@ -361,7 +362,7 @@ static int cifs_permission(struct user_namespace *mnt_userns, on the client (above and beyond ACL on servers) for servers which do not support setting and viewing mode bits, so allowing client to check permissions is useful */ - return generic_permission(&init_user_ns, inode, mask); + return generic_permission(&nop_mnt_idmap, inode, mask); } static struct kmem_cache *cifs_inode_cachep; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 63a0ac2b9355..b58cd737b21e 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -49,7 +49,7 @@ extern void cifs_sb_deactive(struct super_block *sb); /* Functions related to inodes */ extern const struct inode_operations cifs_dir_inode_ops; extern struct inode *cifs_root_iget(struct super_block *); -extern int cifs_create(struct user_namespace *, struct inode *, +extern int cifs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool excl); extern int cifs_atomic_open(struct inode *, struct dentry *, struct file *, unsigned, umode_t); @@ -57,12 +57,12 @@ extern struct dentry *cifs_lookup(struct inode *, struct dentry *, unsigned int); extern int cifs_unlink(struct inode *dir, struct dentry *dentry); extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *); -extern int cifs_mknod(struct user_namespace *, struct inode *, struct dentry *, +extern int cifs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); -extern int cifs_mkdir(struct user_namespace *, struct inode *, struct dentry *, +extern int cifs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); extern int cifs_rmdir(struct inode *, struct dentry *); -extern int cifs_rename2(struct user_namespace *, struct inode *, +extern int cifs_rename2(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern int cifs_revalidate_file_attr(struct file *filp); @@ -72,9 +72,9 @@ extern int cifs_revalidate_dentry(struct dentry *); extern int cifs_invalidate_mapping(struct inode *inode); extern int cifs_revalidate_mapping(struct inode *inode); extern int cifs_zap_mapping(struct inode *inode); -extern int cifs_getattr(struct user_namespace *, const struct path *, +extern int cifs_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); -extern int cifs_setattr(struct user_namespace *, struct dentry *, +extern int cifs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int cifs_fiemap(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); @@ -124,7 +124,7 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path); /* Functions related to symlinks */ extern const char *cifs_get_link(struct dentry *, struct inode *, struct delayed_call *); -extern int cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, +extern int cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, const char *symname); #ifdef CONFIG_CIFS_XATTR diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index cfdd5bf701a1..cd8171a1c9a0 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -26,6 +26,7 @@ #include <uapi/linux/cifs/cifs_mount.h> #include "../smbfs_common/smb2pdu.h" #include "smb2pdu.h" +#include <linux/filelock.h> #define SMB_PATH_MAX 260 #define CIFS_PORT 445 diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 1207b39686fb..b8a47704a6ef 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -225,9 +225,9 @@ extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *, const char *, u32 *, u32); extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *, const struct cifs_fid *, u32 *, u32); -extern struct posix_acl *cifs_get_acl(struct user_namespace *mnt_userns, +extern struct posix_acl *cifs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type); -extern int cifs_set_acl(struct user_namespace *mnt_userns, +extern int cifs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *, const char *, int); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 23f10e0d6e7e..60dd4e37030a 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -15,6 +15,7 @@ /* want to reuse a stale file handle and only the caller knows the file info */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/kernel.h> #include <linux/vfs.h> #include <linux/slab.h> diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index ad4208bf1e32..2b6076324ffc 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -529,7 +529,7 @@ out_free_xid: return rc; } -int cifs_create(struct user_namespace *mnt_userns, struct inode *inode, +int cifs_create(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, umode_t mode, bool excl) { int rc; @@ -579,7 +579,7 @@ out_free_xid: return rc; } -int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode, +int cifs_mknod(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, umode_t mode, dev_t device_number) { int rc = -EPERM; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index b8d1cbadb689..2870e3b6ffe8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -9,6 +9,7 @@ * */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/backing-dev.h> #include <linux/stat.h> #include <linux/fcntl.h> diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index f145a59af89b..11cdc7cfe0ba 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1910,7 +1910,7 @@ posix_mkdir_get_info: } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode, +int cifs_mkdir(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, umode_t mode) { int rc = 0; @@ -2138,7 +2138,7 @@ do_rename_exit: } int -cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, +cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, struct dentry *source_dentry, struct inode *target_dir, struct dentry *target_dentry, unsigned int flags) { @@ -2496,7 +2496,7 @@ int cifs_revalidate_dentry(struct dentry *dentry) return cifs_revalidate_mapping(inode); } -int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int cifs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; @@ -2537,7 +2537,7 @@ int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path, return rc; } - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->blksize = cifs_sb->ctx->bsize; stat->ino = CIFS_I(inode)->uniqueid; @@ -2752,7 +2752,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = setattr_prepare(&init_user_ns, direntry, attrs); + rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs); if (rc < 0) goto out; @@ -2859,7 +2859,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size); } - setattr_copy(&init_user_ns, inode, attrs); + setattr_copy(&nop_mnt_idmap, inode, attrs); mark_inode_dirty(inode); /* force revalidate when any of these times are set since some @@ -2903,7 +2903,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = setattr_prepare(&init_user_ns, direntry, attrs); + rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs); if (rc < 0) goto cifs_setattr_exit; @@ -3058,7 +3058,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size); } - setattr_copy(&init_user_ns, inode, attrs); + setattr_copy(&nop_mnt_idmap, inode, attrs); mark_inode_dirty(inode); cifs_setattr_exit: @@ -3068,7 +3068,7 @@ cifs_setattr_exit: } int -cifs_setattr(struct user_namespace *mnt_userns, struct dentry *direntry, +cifs_setattr(struct mnt_idmap *idmap, struct dentry *direntry, struct iattr *attrs) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index a5a097a69983..4510dea77be3 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -569,7 +569,7 @@ cifs_hl_exit: } int -cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, +cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, const char *symname) { int rc = -EOPNOTSUPP; diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index ba6cc50af390..9f1dd04b555a 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -7,6 +7,7 @@ * */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/pagemap.h> diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 5f2fb2fd2e37..50e762fa1a14 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -89,7 +89,7 @@ static int cifs_creation_time_set(unsigned int xid, struct cifs_tcon *pTcon, } static int cifs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h index 9be281bbcc06..dd6277d87afb 100644 --- a/fs/coda/coda_linux.h +++ b/fs/coda/coda_linux.h @@ -46,12 +46,12 @@ extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); int coda_release(struct inode *i, struct file *f); -int coda_permission(struct user_namespace *mnt_userns, struct inode *inode, +int coda_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); int coda_revalidate_inode(struct inode *); -int coda_getattr(struct user_namespace *, const struct path *, struct kstat *, +int coda_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); -int coda_setattr(struct user_namespace *, struct dentry *, struct iattr *); +int coda_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); /* this file: helpers */ char *coda_f2s(struct CodaFid *f); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 328d7a684b63..8450b1bd354b 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -73,7 +73,7 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig } -int coda_permission(struct user_namespace *mnt_userns, struct inode *inode, +int coda_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int error; @@ -133,7 +133,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir) } /* creation routines: create, mknod, mkdir, link, symlink */ -static int coda_create(struct user_namespace *mnt_userns, struct inode *dir, +static int coda_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *de, umode_t mode, bool excl) { int error; @@ -166,7 +166,7 @@ err_out: return error; } -static int coda_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int coda_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *de, umode_t mode) { struct inode *inode; @@ -228,7 +228,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, } -static int coda_symlink(struct user_namespace *mnt_userns, +static int coda_symlink(struct mnt_idmap *idmap, struct inode *dir_inode, struct dentry *de, const char *symname) { @@ -295,7 +295,7 @@ static int coda_rmdir(struct inode *dir, struct dentry *de) } /* rename */ -static int coda_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int coda_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 2185328b65c7..d661e6cf17ac 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -251,16 +251,16 @@ static void coda_evict_inode(struct inode *inode) coda_cache_clear_inode(inode); } -int coda_getattr(struct user_namespace *mnt_userns, const struct path *path, +int coda_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { int err = coda_revalidate_inode(d_inode(path->dentry)); if (!err) - generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(path->dentry), stat); return err; } -int coda_setattr(struct user_namespace *mnt_userns, struct dentry *de, +int coda_setattr(struct mnt_idmap *idmap, struct dentry *de, struct iattr *iattr) { struct inode *inode = d_inode(de); diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index cb9fd59a688c..36e35c15561a 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -24,7 +24,7 @@ #include "coda_linux.h" /* pioctl ops */ -static int coda_ioctl_permission(struct user_namespace *mnt_userns, +static int coda_ioctl_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); static long coda_pioctl(struct file *filp, unsigned int cmd, unsigned long user_data); @@ -41,7 +41,7 @@ const struct file_operations coda_ioctl_operations = { }; /* the coda pioctl inode ops */ -static int coda_ioctl_permission(struct user_namespace *mnt_userns, +static int coda_ioctl_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { return (mask & MAY_EXEC) ? -EACCES : 0; diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index c0395363eab9..e710a1782382 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -77,7 +77,7 @@ extern void configfs_hash_and_remove(struct dentry * dir, const char * name); extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); -extern int configfs_setattr(struct user_namespace *mnt_userns, +extern int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); extern struct dentry *configfs_pin_fs(void); @@ -91,7 +91,7 @@ extern const struct inode_operations configfs_root_inode_operations; extern const struct inode_operations configfs_symlink_inode_operations; extern const struct dentry_operations configfs_dentry_ops; -extern int configfs_symlink(struct user_namespace *mnt_userns, +extern int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname); extern int configfs_unlink(struct inode *dir, struct dentry *dentry); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index ec6519e1ca3b..4afcbbe63e68 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1251,7 +1251,7 @@ out_root_unlock: } EXPORT_SYMBOL(configfs_depend_item_unlocked); -static int configfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int configfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int ret = 0; diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index b601610e9907..1c15edbe70ff 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -32,7 +32,7 @@ static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; -int configfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode * inode = d_inode(dentry); @@ -60,7 +60,7 @@ int configfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } /* attributes were changed atleast once in past */ - error = simple_setattr(mnt_userns, dentry, iattr); + error = simple_setattr(idmap, dentry, iattr); if (error) return error; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 0623c3edcfb9..69133ec1fac2 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -137,7 +137,7 @@ static int get_target(const char *symname, struct path *path, } -int configfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int ret; @@ -196,7 +196,7 @@ int configfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (dentry->d_inode || d_unhashed(dentry)) ret = -EEXIST; else - ret = inode_permission(&init_user_ns, dir, + ret = inode_permission(&nop_mnt_idmap, dir, MAY_WRITE | MAY_EXEC); if (!ret) ret = type->ct_item_ops->allow_link(parent_item, target_item); diff --git a/fs/coredump.c b/fs/coredump.c index a25ecec9ca7c..68619329ec65 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -644,7 +644,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto close_fail; } } else { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct inode *inode; int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | O_LARGEFILE | O_EXCL; @@ -722,8 +722,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) * a process dumps core while its cwd is e.g. on a vfat * filesystem. */ - mnt_userns = file_mnt_user_ns(cprm.file); - if (!vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode), + idmap = file_mnt_idmap(cprm.file); + if (!vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) { pr_info_ratelimited("Core dump to %s aborted: cannot preserve file owner\n", cn.corename); @@ -736,7 +736,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) } if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) goto close_fail; - if (do_truncate(mnt_userns, cprm.file->f_path.dentry, + if (do_truncate(idmap, cprm.file->f_path.dentry, 0, 0, cprm.file)) goto close_fail; } diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 1b4403136d05..d57d0a020f71 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -30,13 +30,11 @@ */ bool fscrypt_decrypt_bio(struct bio *bio) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; - int err = fscrypt_decrypt_pagecache_blocks(page, bv->bv_len, - bv->bv_offset); + bio_for_each_folio_all(fi, bio) { + int err = fscrypt_decrypt_pagecache_blocks(fi.folio, fi.length, + fi.offset); if (err) { bio->bi_status = errno_to_blk_status(err); diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index e78be66bbf01..bf642479269a 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -237,41 +237,43 @@ EXPORT_SYMBOL(fscrypt_encrypt_block_inplace); /** * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a - * pagecache page - * @page: The locked pagecache page containing the block(s) to decrypt + * pagecache folio + * @folio: The locked pagecache folio containing the block(s) to decrypt * @len: Total size of the block(s) to decrypt. Must be a nonzero * multiple of the filesystem's block size. - * @offs: Byte offset within @page of the first block to decrypt. Must be + * @offs: Byte offset within @folio of the first block to decrypt. Must be * a multiple of the filesystem's block size. * - * The specified block(s) are decrypted in-place within the pagecache page, - * which must still be locked and not uptodate. Normally, blocksize == - * PAGE_SIZE and the whole page is decrypted at once. + * The specified block(s) are decrypted in-place within the pagecache folio, + * which must still be locked and not uptodate. * * This is for use by the filesystem's ->readahead() method. * * Return: 0 on success; -errno on failure */ -int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, - unsigned int offs) +int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, + size_t offs) { - const struct inode *inode = page->mapping->host; + const struct inode *inode = folio->mapping->host; const unsigned int blockbits = inode->i_blkbits; const unsigned int blocksize = 1 << blockbits; - u64 lblk_num = ((u64)page->index << (PAGE_SHIFT - blockbits)) + + u64 lblk_num = ((u64)folio->index << (PAGE_SHIFT - blockbits)) + (offs >> blockbits); - unsigned int i; + size_t i; int err; - if (WARN_ON_ONCE(!PageLocked(page))) + if (WARN_ON_ONCE(!folio_test_locked(folio))) return -EINVAL; if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, blocksize))) return -EINVAL; for (i = offs; i < offs + len; i += blocksize, lblk_num++) { + struct page *page = folio_page(folio, i >> PAGE_SHIFT); + err = fscrypt_crypt_block(inode, FS_DECRYPT, lblk_num, page, - page, blocksize, i, GFP_NOFS); + page, blocksize, i & ~PAGE_MASK, + GFP_NOFS); if (err) return err; } diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 316a778cec0f..0fec2dfc36eb 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -573,6 +573,9 @@ fscrypt_find_master_key(struct super_block *sb, int fscrypt_get_test_dummy_key_identifier( u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); +int fscrypt_add_test_dummy_key(struct super_block *sb, + struct fscrypt_key_specifier *key_spec); + int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); @@ -651,6 +654,7 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1, const union fscrypt_policy *policy2); int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy, struct fscrypt_key_specifier *key_spec); +const union fscrypt_policy *fscrypt_get_dummy_policy(struct super_block *sb); bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, const struct inode *inode); int fscrypt_policy_from_context(union fscrypt_policy *policy_u, diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 78dd2ff306bd..78086f8dbda5 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -211,10 +211,6 @@ static int allocate_filesystem_keyring(struct super_block *sb) * are still available at this time; this is important because after user file * accesses have been allowed, this function may need to evict keys from the * keyslots of an inline crypto engine, which requires the block device(s). - * - * This is also called when the super_block is being freed. This is needed to - * avoid a memory leak if mounting fails after the "test_dummy_encryption" - * option was processed, as in that case the unmount-time call isn't made. */ void fscrypt_destroy_keyring(struct super_block *sb) { @@ -778,34 +774,26 @@ out: /** * fscrypt_add_test_dummy_key() - add the test dummy encryption key * @sb: the filesystem instance to add the key to - * @dummy_policy: the encryption policy for test_dummy_encryption + * @key_spec: the key specifier of the test dummy encryption key * - * If needed, add the key for the test_dummy_encryption mount option to the - * filesystem. To prevent misuse of this mount option, a per-boot random key is - * used instead of a hardcoded one. This makes it so that any encrypted files - * created using this option won't be accessible after a reboot. + * Add the key for the test_dummy_encryption mount option to the filesystem. To + * prevent misuse of this mount option, a per-boot random key is used instead of + * a hardcoded one. This makes it so that any encrypted files created using + * this option won't be accessible after a reboot. * * Return: 0 on success, -errno on failure */ int fscrypt_add_test_dummy_key(struct super_block *sb, - const struct fscrypt_dummy_policy *dummy_policy) + struct fscrypt_key_specifier *key_spec) { - const union fscrypt_policy *policy = dummy_policy->policy; - struct fscrypt_key_specifier key_spec; struct fscrypt_master_key_secret secret; int err; - if (!policy) - return 0; - err = fscrypt_policy_to_key_spec(policy, &key_spec); - if (err) - return err; fscrypt_get_test_dummy_secret(&secret); - err = add_master_key(sb, &secret, &key_spec); + err = add_master_key(sb, &secret, key_spec); wipe_master_key_secret(&secret); return err; } -EXPORT_SYMBOL_GPL(fscrypt_add_test_dummy_key); /* * Verify that the current user has added a master key with the given identifier diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 94757ccd3056..aa94fba9d17e 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -438,6 +438,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, bool need_dirhash_key, struct fscrypt_master_key **mk_ret) { + struct super_block *sb = ci->ci_inode->i_sb; struct fscrypt_key_specifier mk_spec; struct fscrypt_master_key *mk; int err; @@ -450,8 +451,26 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, if (err) return err; - mk = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); - if (!mk) { + mk = fscrypt_find_master_key(sb, &mk_spec); + if (unlikely(!mk)) { + const union fscrypt_policy *dummy_policy = + fscrypt_get_dummy_policy(sb); + + /* + * Add the test_dummy_encryption key on-demand. In principle, + * it should be added at mount time. Do it here instead so that + * the individual filesystems don't need to worry about adding + * this key at mount time and cleaning up on mount failure. + */ + if (dummy_policy && + fscrypt_policies_equal(dummy_policy, &ci->ci_policy)) { + err = fscrypt_add_test_dummy_key(sb, &mk_spec); + if (err) + return err; + mk = fscrypt_find_master_key(sb, &mk_spec); + } + } + if (unlikely(!mk)) { if (ci->ci_policy.version != FSCRYPT_POLICY_V1) return -ENOKEY; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 893661b52376..3b5fcb6402ea 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -53,8 +53,7 @@ int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy, } } -static const union fscrypt_policy * -fscrypt_get_dummy_policy(struct super_block *sb) +const union fscrypt_policy *fscrypt_get_dummy_policy(struct super_block *sb) { if (!sb->s_cop->get_dummy_policy) return NULL; @@ -506,7 +505,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) return -EFAULT; policy.version = version; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -1271,8 +1271,9 @@ static s64 dax_unshare_iter(struct iomap_iter *iter) if (ret < 0) goto out_unlock; - ret = copy_mc_to_kernel(daddr, saddr, length); - if (ret) + if (copy_mc_to_kernel(daddr, saddr, length) == 0) + ret = length; + else ret = -EIO; out_unlock: diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 2e8e112b1993..bf397f6a6a33 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -42,7 +42,7 @@ static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ -static int debugfs_setattr(struct user_namespace *mnt_userns, +static int debugfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int ret; @@ -52,7 +52,7 @@ static int debugfs_setattr(struct user_namespace *mnt_userns, if (ret) return ret; } - return simple_setattr(&init_user_ns, dentry, ia); + return simple_setattr(&nop_mnt_idmap, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { @@ -837,7 +837,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, take_dentry_name_snapshot(&old_name, old_dentry); - error = simple_rename(&init_user_ns, d_inode(old_dir), old_dentry, + error = simple_rename(&nop_mnt_idmap, d_inode(old_dir), old_dentry, d_inode(new_dir), dentry, 0); if (error) { release_dentry_name_snapshot(&old_name); diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 737f185aad8d..ed4357e62f35 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -4,6 +4,7 @@ */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/miscdevice.h> #include <linux/poll.h> #include <linux/dlm.h> diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index e3f5d7f3c8a0..bd3f3c755b24 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1105,7 +1105,7 @@ ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, } inode_lock(lower_inode); - rc = __vfs_setxattr(&init_user_ns, lower_dentry, lower_inode, + rc = __vfs_setxattr(&nop_mnt_idmap, lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME, page_virt, size, 0); if (!rc && ecryptfs_inode) fsstack_copy_attr_all(ecryptfs_inode, lower_inode); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index f3cd00fac9c3..144ace9e0dd9 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -139,7 +139,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, if (d_unhashed(lower_dentry)) rc = -EINVAL; else - rc = vfs_unlink(&init_user_ns, lower_dir, lower_dentry, + rc = vfs_unlink(&nop_mnt_idmap, lower_dir, lower_dentry, NULL); } if (rc) { @@ -180,7 +180,7 @@ ecryptfs_do_create(struct inode *directory_inode, rc = lock_parent(ecryptfs_dentry, &lower_dentry, &lower_dir); if (!rc) - rc = vfs_create(&init_user_ns, lower_dir, + rc = vfs_create(&nop_mnt_idmap, lower_dir, lower_dentry, mode, true); if (rc) { printk(KERN_ERR "%s: Failure to create dentry in lower fs; " @@ -191,7 +191,7 @@ ecryptfs_do_create(struct inode *directory_inode, inode = __ecryptfs_get_inode(d_inode(lower_dentry), directory_inode->i_sb); if (IS_ERR(inode)) { - vfs_unlink(&init_user_ns, lower_dir, lower_dentry, NULL); + vfs_unlink(&nop_mnt_idmap, lower_dir, lower_dentry, NULL); goto out_lock; } fsstack_copy_attr_times(directory_inode, lower_dir); @@ -253,7 +253,7 @@ out: * Returns zero on success; non-zero on error condition */ static int -ecryptfs_create(struct user_namespace *mnt_userns, +ecryptfs_create(struct mnt_idmap *idmap, struct inode *directory_inode, struct dentry *ecryptfs_dentry, umode_t mode, bool excl) { @@ -434,7 +434,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir, lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry); rc = lock_parent(new_dentry, &lower_new_dentry, &lower_dir); if (!rc) - rc = vfs_link(lower_old_dentry, &init_user_ns, lower_dir, + rc = vfs_link(lower_old_dentry, &nop_mnt_idmap, lower_dir, lower_new_dentry, NULL); if (rc || d_really_is_negative(lower_new_dentry)) goto out_lock; @@ -456,7 +456,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) return ecryptfs_do_unlink(dir, dentry, d_inode(dentry)); } -static int ecryptfs_symlink(struct user_namespace *mnt_userns, +static int ecryptfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { @@ -478,7 +478,7 @@ static int ecryptfs_symlink(struct user_namespace *mnt_userns, strlen(symname)); if (rc) goto out_lock; - rc = vfs_symlink(&init_user_ns, lower_dir, lower_dentry, + rc = vfs_symlink(&nop_mnt_idmap, lower_dir, lower_dentry, encoded_symname); kfree(encoded_symname); if (rc || d_really_is_negative(lower_dentry)) @@ -495,7 +495,7 @@ out_lock: return rc; } -static int ecryptfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int rc; @@ -504,7 +504,7 @@ static int ecryptfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, rc = lock_parent(dentry, &lower_dentry, &lower_dir); if (!rc) - rc = vfs_mkdir(&init_user_ns, lower_dir, + rc = vfs_mkdir(&nop_mnt_idmap, lower_dir, lower_dentry, mode); if (rc || d_really_is_negative(lower_dentry)) goto out; @@ -533,7 +533,7 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) if (d_unhashed(lower_dentry)) rc = -EINVAL; else - rc = vfs_rmdir(&init_user_ns, lower_dir, lower_dentry); + rc = vfs_rmdir(&nop_mnt_idmap, lower_dir, lower_dentry); } if (!rc) { clear_nlink(d_inode(dentry)); @@ -548,7 +548,7 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) } static int -ecryptfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +ecryptfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { int rc; @@ -557,7 +557,7 @@ ecryptfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, rc = lock_parent(dentry, &lower_dentry, &lower_dir); if (!rc) - rc = vfs_mknod(&init_user_ns, lower_dir, + rc = vfs_mknod(&nop_mnt_idmap, lower_dir, lower_dentry, mode, dev); if (rc || d_really_is_negative(lower_dentry)) goto out; @@ -574,7 +574,7 @@ out: } static int -ecryptfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +ecryptfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -616,10 +616,10 @@ ecryptfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, goto out_lock; } - rd.old_mnt_userns = &init_user_ns; + rd.old_mnt_idmap = &nop_mnt_idmap; rd.old_dir = d_inode(lower_old_dir_dentry); rd.old_dentry = lower_old_dentry; - rd.new_mnt_userns = &init_user_ns; + rd.new_mnt_idmap = &nop_mnt_idmap; rd.new_dir = d_inode(lower_new_dir_dentry); rd.new_dentry = lower_new_dentry; rc = vfs_rename(&rd); @@ -856,7 +856,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length) struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); inode_lock(d_inode(lower_dentry)); - rc = notify_change(&init_user_ns, lower_dentry, + rc = notify_change(&nop_mnt_idmap, lower_dentry, &lower_ia, NULL); inode_unlock(d_inode(lower_dentry)); } @@ -864,16 +864,16 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length) } static int -ecryptfs_permission(struct user_namespace *mnt_userns, struct inode *inode, +ecryptfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { - return inode_permission(&init_user_ns, + return inode_permission(&nop_mnt_idmap, ecryptfs_inode_to_lower(inode), mask); } /** * ecryptfs_setattr - * @mnt_userns: user namespace of the target mount + * @idmap: idmap of the target mount * @dentry: dentry handle to the inode to modify * @ia: Structure with flags of what to change and values * @@ -884,7 +884,7 @@ ecryptfs_permission(struct user_namespace *mnt_userns, struct inode *inode, * All other metadata changes will be passed right to the lower filesystem, * and we will just update our inode to look like the lower. */ -static int ecryptfs_setattr(struct user_namespace *mnt_userns, +static int ecryptfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int rc = 0; @@ -939,7 +939,7 @@ static int ecryptfs_setattr(struct user_namespace *mnt_userns, } mutex_unlock(&crypt_stat->cs_mutex); - rc = setattr_prepare(&init_user_ns, dentry, ia); + rc = setattr_prepare(&nop_mnt_idmap, dentry, ia); if (rc) goto out; if (ia->ia_valid & ATTR_SIZE) { @@ -965,14 +965,14 @@ static int ecryptfs_setattr(struct user_namespace *mnt_userns, lower_ia.ia_valid &= ~ATTR_MODE; inode_lock(d_inode(lower_dentry)); - rc = notify_change(&init_user_ns, lower_dentry, &lower_ia, NULL); + rc = notify_change(&nop_mnt_idmap, lower_dentry, &lower_ia, NULL); inode_unlock(d_inode(lower_dentry)); out: fsstack_copy_attr_all(inode, lower_inode); return rc; } -static int ecryptfs_getattr_link(struct user_namespace *mnt_userns, +static int ecryptfs_getattr_link(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -982,7 +982,7 @@ static int ecryptfs_getattr_link(struct user_namespace *mnt_userns, mount_crypt_stat = &ecryptfs_superblock_to_private( dentry->d_sb)->mount_crypt_stat; - generic_fillattr(&init_user_ns, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) { char *target; size_t targetsiz; @@ -998,7 +998,7 @@ static int ecryptfs_getattr_link(struct user_namespace *mnt_userns, return rc; } -static int ecryptfs_getattr(struct user_namespace *mnt_userns, +static int ecryptfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -1011,7 +1011,7 @@ static int ecryptfs_getattr(struct user_namespace *mnt_userns, if (!rc) { fsstack_copy_attr_all(d_inode(dentry), ecryptfs_inode_to_lower(d_inode(dentry))); - generic_fillattr(&init_user_ns, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); stat->blocks = lower_stat.blocks; } return rc; @@ -1033,7 +1033,7 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, goto out; } inode_lock(lower_inode); - rc = __vfs_setxattr_locked(&init_user_ns, lower_dentry, name, value, size, flags, NULL); + rc = __vfs_setxattr_locked(&nop_mnt_idmap, lower_dentry, name, value, size, flags, NULL); inode_unlock(lower_inode); if (!rc && inode) fsstack_copy_attr_all(inode, lower_inode); @@ -1099,7 +1099,7 @@ static int ecryptfs_removexattr(struct dentry *dentry, struct inode *inode, goto out; } inode_lock(lower_inode); - rc = __vfs_removexattr(&init_user_ns, lower_dentry, name); + rc = __vfs_removexattr(&nop_mnt_idmap, lower_dentry, name); inode_unlock(lower_inode); out: return rc; @@ -1110,26 +1110,26 @@ static int ecryptfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return vfs_fileattr_get(ecryptfs_dentry_to_lower(dentry), fa); } -static int ecryptfs_fileattr_set(struct user_namespace *mnt_userns, +static int ecryptfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); int rc; - rc = vfs_fileattr_set(&init_user_ns, lower_dentry, fa); + rc = vfs_fileattr_set(&nop_mnt_idmap, lower_dentry, fa); fsstack_copy_attr_all(d_inode(dentry), d_inode(lower_dentry)); return rc; } -static struct posix_acl *ecryptfs_get_acl(struct user_namespace *mnt_userns, +static struct posix_acl *ecryptfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type) { - return vfs_get_acl(mnt_userns, ecryptfs_dentry_to_lower(dentry), + return vfs_get_acl(idmap, ecryptfs_dentry_to_lower(dentry), posix_acl_xattr_name(type)); } -static int ecryptfs_set_acl(struct user_namespace *mnt_userns, +static int ecryptfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { @@ -1137,7 +1137,7 @@ static int ecryptfs_set_acl(struct user_namespace *mnt_userns, struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); struct inode *lower_inode = d_inode(lower_dentry); - rc = vfs_set_acl(&init_user_ns, lower_dentry, + rc = vfs_set_acl(&nop_mnt_idmap, lower_dentry, posix_acl_xattr_name(type), acl); if (!rc) fsstack_copy_attr_all(d_inode(dentry), lower_inode); @@ -1190,7 +1190,7 @@ static int ecryptfs_xattr_get(const struct xattr_handler *handler, } static int ecryptfs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 19af229eb7ca..373c3e5747e6 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -428,7 +428,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode) if (size < 0) size = 8; put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt); - rc = __vfs_setxattr(&init_user_ns, lower_dentry, lower_inode, + rc = __vfs_setxattr(&nop_mnt_idmap, lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME, xattr_virt, size, 0); inode_unlock(lower_inode); if (rc) diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 617f3ad2485e..b973a2c03dde 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -70,7 +70,7 @@ bool efivarfs_valid_name(const char *str, int len) return uuid_is_valid(s); } -static int efivarfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode = NULL; @@ -163,7 +163,7 @@ efivarfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) } static int -efivarfs_fileattr_set(struct user_namespace *mnt_userns, +efivarfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { unsigned int i_flags = 0; diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 85490370e0ca..704fb59577e0 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -108,3 +108,21 @@ config EROFS_FS_ONDEMAND read support. If unsure, say N. + +config EROFS_FS_PCPU_KTHREAD + bool "EROFS per-cpu decompression kthread workers" + depends on EROFS_FS_ZIP + help + Saying Y here enables per-CPU kthread workers pool to carry out + async decompression for low latencies on some architectures. + + If unsure, say N. + +config EROFS_FS_PCPU_KTHREAD_HIPRI + bool "EROFS high priority per-CPU kthread workers" + depends on EROFS_FS_ZIP && EROFS_FS_PCPU_KTHREAD + help + This permits EROFS to configure per-CPU kthread workers to run + at higher priority. + + If unsure, say N. diff --git a/fs/erofs/data.c b/fs/erofs/data.c index f57f921683d7..032e12dccb84 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -74,8 +74,7 @@ void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, } static int erofs_map_blocks_flatmode(struct inode *inode, - struct erofs_map_blocks *map, - int flags) + struct erofs_map_blocks *map) { erofs_blk_t nblocks, lastblk; u64 offset = map->m_la; @@ -91,11 +90,8 @@ static int erofs_map_blocks_flatmode(struct inode *inode, map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la; map->m_plen = blknr_to_addr(lastblk) - offset; } else if (tailendpacking) { - /* 2 - inode inline B: inode, [xattrs], inline last blk... */ - struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); - - map->m_pa = iloc(sbi, vi->nid) + vi->inode_isize + - vi->xattr_isize + erofs_blkoff(map->m_la); + map->m_pa = erofs_iloc(inode) + vi->inode_isize + + vi->xattr_isize + erofs_blkoff(offset); map->m_plen = inode->i_size - offset; /* inline data should be located in the same meta block */ @@ -117,8 +113,7 @@ static int erofs_map_blocks_flatmode(struct inode *inode, return 0; } -int erofs_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, int flags) +int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) { struct super_block *sb = inode->i_sb; struct erofs_inode *vi = EROFS_I(inode); @@ -130,7 +125,7 @@ int erofs_map_blocks(struct inode *inode, void *kaddr; int err = 0; - trace_erofs_map_blocks_enter(inode, map, flags); + trace_erofs_map_blocks_enter(inode, map, 0); map->m_deviceid = 0; if (map->m_la >= inode->i_size) { /* leave out-of-bound access unmapped */ @@ -140,7 +135,7 @@ int erofs_map_blocks(struct inode *inode, } if (vi->datalayout != EROFS_INODE_CHUNK_BASED) { - err = erofs_map_blocks_flatmode(inode, map, flags); + err = erofs_map_blocks_flatmode(inode, map); goto out; } @@ -150,7 +145,7 @@ int erofs_map_blocks(struct inode *inode, unit = EROFS_BLOCK_MAP_ENTRY_SIZE; /* block map */ chunknr = map->m_la >> vi->chunkbits; - pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize + + pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, unit) + unit * chunknr; kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); @@ -192,7 +187,7 @@ out_unlock: out: if (!err) map->m_llen = map->m_plen; - trace_erofs_map_blocks_exit(inode, map, flags, 0); + trace_erofs_map_blocks_exit(inode, map, 0, err); return err; } @@ -255,7 +250,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, map.m_la = offset; map.m_llen = length; - ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + ret = erofs_map_blocks(inode, &map); if (ret < 0) return ret; diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index ecf28f66b97d..6970b09b8307 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -6,21 +6,6 @@ */ #include "internal.h" -static void debug_one_dentry(unsigned char d_type, const char *de_name, - unsigned int de_namelen) -{ -#ifdef CONFIG_EROFS_FS_DEBUG - /* since the on-disk name could not have the trailing '\0' */ - unsigned char dbg_namebuf[EROFS_NAME_LEN + 1]; - - memcpy(dbg_namebuf, de_name, de_namelen); - dbg_namebuf[de_namelen] = '\0'; - - erofs_dbg("found dirent %s de_len %u d_type %d", dbg_namebuf, - de_namelen, d_type); -#endif -} - static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, void *dentry_blk, struct erofs_dirent *de, unsigned int nameoff, unsigned int maxsize) @@ -52,10 +37,8 @@ static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, return -EFSCORRUPTED; } - debug_one_dentry(d_type, de_name, de_namelen); if (!dir_emit(ctx, de_name, de_namelen, le64_to_cpu(de->nid), d_type)) - /* stopped by some reason */ return 1; ++de; ctx->pos += sizeof(struct erofs_dirent); diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 014e20962376..96a87c023128 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -9,6 +9,7 @@ static DEFINE_MUTEX(erofs_domain_list_lock); static DEFINE_MUTEX(erofs_domain_cookies_lock); static LIST_HEAD(erofs_domain_list); +static LIST_HEAD(erofs_domain_cookies_list); static struct vfsmount *erofs_pseudo_mnt; struct erofs_fscache_request { @@ -164,18 +165,8 @@ static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie, static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) { int ret; - struct super_block *sb = folio_mapping(folio)->host->i_sb; + struct erofs_fscache *ctx = folio_mapping(folio)->host->i_private; struct erofs_fscache_request *req; - struct erofs_map_dev mdev = { - .m_deviceid = 0, - .m_pa = folio_pos(folio), - }; - - ret = erofs_map_dev(sb, &mdev); - if (ret) { - folio_unlock(folio); - return ret; - } req = erofs_fscache_req_alloc(folio_mapping(folio), folio_pos(folio), folio_size(folio)); @@ -184,8 +175,8 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) return PTR_ERR(req); } - ret = erofs_fscache_read_folios_async(mdev.m_fscache->cookie, - req, mdev.m_pa, folio_size(folio)); + ret = erofs_fscache_read_folios_async(ctx->cookie, req, + folio_pos(folio), folio_size(folio)); if (ret) req->error = ret; @@ -207,7 +198,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary) int ret; map.m_la = pos; - ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + ret = erofs_map_blocks(inode, &map); if (ret) return ret; @@ -328,8 +319,6 @@ const struct address_space_operations erofs_fscache_access_aops = { static void erofs_fscache_domain_put(struct erofs_domain *domain) { - if (!domain) - return; mutex_lock(&erofs_domain_list_lock); if (refcount_dec_and_test(&domain->ref)) { list_del(&domain->list); @@ -337,8 +326,8 @@ static void erofs_fscache_domain_put(struct erofs_domain *domain) kern_unmount(erofs_pseudo_mnt); erofs_pseudo_mnt = NULL; } - mutex_unlock(&erofs_domain_list_lock); fscache_relinquish_volume(domain->volume, NULL, false); + mutex_unlock(&erofs_domain_list_lock); kfree(domain->domain_id); kfree(domain); return; @@ -431,19 +420,21 @@ static int erofs_fscache_register_domain(struct super_block *sb) return err; } -static -struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb, - char *name, - unsigned int flags) +static struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb, + char *name, unsigned int flags) { struct fscache_volume *volume = EROFS_SB(sb)->volume; struct erofs_fscache *ctx; struct fscache_cookie *cookie; + struct super_block *isb; + struct inode *inode; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&ctx->node); + refcount_set(&ctx->ref, 1); cookie = fscache_acquire_cookie(volume, FSCACHE_ADV_WANT_CACHE_SIZE, name, strlen(name), NULL, 0, 0); @@ -452,32 +443,32 @@ struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb, ret = -EINVAL; goto err; } - fscache_use_cookie(cookie, false); - ctx->cookie = cookie; - - if (flags & EROFS_REG_COOKIE_NEED_INODE) { - struct inode *const inode = new_inode(sb); - - if (!inode) { - erofs_err(sb, "failed to get anon inode for %s", name); - ret = -ENOMEM; - goto err_cookie; - } - set_nlink(inode, 1); - inode->i_size = OFFSET_MAX; - inode->i_mapping->a_ops = &erofs_fscache_meta_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - - ctx->inode = inode; + /* + * Allocate anonymous inode in global pseudo mount for shareable blobs, + * so that they are accessible among erofs fs instances. + */ + isb = flags & EROFS_REG_COOKIE_SHARE ? erofs_pseudo_mnt->mnt_sb : sb; + inode = new_inode(isb); + if (!inode) { + erofs_err(sb, "failed to get anon inode for %s", name); + ret = -ENOMEM; + goto err_cookie; } + inode->i_size = OFFSET_MAX; + inode->i_mapping->a_ops = &erofs_fscache_meta_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + inode->i_private = ctx; + + ctx->cookie = cookie; + ctx->inode = inode; return ctx; err_cookie: - fscache_unuse_cookie(ctx->cookie, NULL, NULL); - fscache_relinquish_cookie(ctx->cookie, false); + fscache_unuse_cookie(cookie, NULL, NULL); + fscache_relinquish_cookie(cookie, false); err: kfree(ctx); return ERR_PTR(ret); @@ -492,13 +483,9 @@ static void erofs_fscache_relinquish_cookie(struct erofs_fscache *ctx) kfree(ctx); } -static -struct erofs_fscache *erofs_fscache_domain_init_cookie(struct super_block *sb, - char *name, - unsigned int flags) +static struct erofs_fscache *erofs_domain_init_cookie(struct super_block *sb, + char *name, unsigned int flags) { - int err; - struct inode *inode; struct erofs_fscache *ctx; struct erofs_domain *domain = EROFS_SB(sb)->domain; @@ -508,55 +495,38 @@ struct erofs_fscache *erofs_fscache_domain_init_cookie(struct super_block *sb, ctx->name = kstrdup(name, GFP_KERNEL); if (!ctx->name) { - err = -ENOMEM; - goto out; - } - - inode = new_inode(erofs_pseudo_mnt->mnt_sb); - if (!inode) { - err = -ENOMEM; - goto out; + erofs_fscache_relinquish_cookie(ctx); + return ERR_PTR(-ENOMEM); } - ctx->domain = domain; - ctx->anon_inode = inode; - inode->i_private = ctx; refcount_inc(&domain->ref); + ctx->domain = domain; + list_add(&ctx->node, &erofs_domain_cookies_list); return ctx; -out: - erofs_fscache_relinquish_cookie(ctx); - return ERR_PTR(err); } -static -struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb, - char *name, - unsigned int flags) +static struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb, + char *name, unsigned int flags) { - struct inode *inode; struct erofs_fscache *ctx; struct erofs_domain *domain = EROFS_SB(sb)->domain; - struct super_block *psb = erofs_pseudo_mnt->mnt_sb; + flags |= EROFS_REG_COOKIE_SHARE; mutex_lock(&erofs_domain_cookies_lock); - spin_lock(&psb->s_inode_list_lock); - list_for_each_entry(inode, &psb->s_inodes, i_sb_list) { - ctx = inode->i_private; - if (!ctx || ctx->domain != domain || strcmp(ctx->name, name)) + list_for_each_entry(ctx, &erofs_domain_cookies_list, node) { + if (ctx->domain != domain || strcmp(ctx->name, name)) continue; if (!(flags & EROFS_REG_COOKIE_NEED_NOEXIST)) { - igrab(inode); + refcount_inc(&ctx->ref); } else { erofs_err(sb, "%s already exists in domain %s", name, domain->domain_id); ctx = ERR_PTR(-EEXIST); } - spin_unlock(&psb->s_inode_list_lock); mutex_unlock(&erofs_domain_cookies_lock); return ctx; } - spin_unlock(&psb->s_inode_list_lock); - ctx = erofs_fscache_domain_init_cookie(sb, name, flags); + ctx = erofs_domain_init_cookie(sb, name, flags); mutex_unlock(&erofs_domain_cookies_lock); return ctx; } @@ -572,23 +542,22 @@ struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb, void erofs_fscache_unregister_cookie(struct erofs_fscache *ctx) { - bool drop; - struct erofs_domain *domain; + struct erofs_domain *domain = NULL; if (!ctx) return; - domain = ctx->domain; - if (domain) { - mutex_lock(&erofs_domain_cookies_lock); - drop = atomic_read(&ctx->anon_inode->i_count) == 1; - iput(ctx->anon_inode); - mutex_unlock(&erofs_domain_cookies_lock); - if (!drop) - return; - } + if (!ctx->domain) + return erofs_fscache_relinquish_cookie(ctx); - erofs_fscache_relinquish_cookie(ctx); - erofs_fscache_domain_put(domain); + mutex_lock(&erofs_domain_cookies_lock); + if (refcount_dec_and_test(&ctx->ref)) { + domain = ctx->domain; + list_del(&ctx->node); + erofs_fscache_relinquish_cookie(ctx); + } + mutex_unlock(&erofs_domain_cookies_lock); + if (domain) + erofs_fscache_domain_put(domain); } int erofs_fscache_register_fs(struct super_block *sb) @@ -596,7 +565,7 @@ int erofs_fscache_register_fs(struct super_block *sb) int ret; struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_fscache *fscache; - unsigned int flags; + unsigned int flags = 0; if (sbi->domain_id) ret = erofs_fscache_register_domain(sb); @@ -615,7 +584,6 @@ int erofs_fscache_register_fs(struct super_block *sb) * * Acquired domain/volume will be relinquished in kill_sb() on error. */ - flags = EROFS_REG_COOKIE_NEED_INODE; if (sbi->domain_id) flags |= EROFS_REG_COOKIE_NEED_NOEXIST; fscache = erofs_fscache_register_cookie(sb, sbi->fsid, flags); diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index d3b8736fa124..4be7dda3cd24 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -14,7 +14,7 @@ static void *erofs_read_inode(struct erofs_buf *buf, struct super_block *sb = inode->i_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_inode *vi = EROFS_I(inode); - const erofs_off_t inode_loc = iloc(sbi, vi->nid); + const erofs_off_t inode_loc = erofs_iloc(inode); erofs_blk_t blkaddr, nblks = 0; void *kaddr; @@ -308,52 +308,54 @@ out_unlock: } /* - * erofs nid is 64bits, but i_ino is 'unsigned long', therefore - * we should do more for 32-bit platform to find the right inode. + * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down + * so that it will fit. */ -static int erofs_ilookup_test_actor(struct inode *inode, void *opaque) +static ino_t erofs_squash_ino(erofs_nid_t nid) { - const erofs_nid_t nid = *(erofs_nid_t *)opaque; + ino_t ino = (ino_t)nid; + + if (sizeof(ino_t) < sizeof(erofs_nid_t)) + ino ^= nid >> (sizeof(erofs_nid_t) - sizeof(ino_t)) * 8; + return ino; +} - return EROFS_I(inode)->nid == nid; +static int erofs_iget5_eq(struct inode *inode, void *opaque) +{ + return EROFS_I(inode)->nid == *(erofs_nid_t *)opaque; } -static int erofs_iget_set_actor(struct inode *inode, void *opaque) +static int erofs_iget5_set(struct inode *inode, void *opaque) { const erofs_nid_t nid = *(erofs_nid_t *)opaque; - inode->i_ino = erofs_inode_hash(nid); + inode->i_ino = erofs_squash_ino(nid); + EROFS_I(inode)->nid = nid; return 0; } struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid) { - const unsigned long hashval = erofs_inode_hash(nid); struct inode *inode; - inode = iget5_locked(sb, hashval, erofs_ilookup_test_actor, - erofs_iget_set_actor, &nid); + inode = iget5_locked(sb, erofs_squash_ino(nid), erofs_iget5_eq, + erofs_iget5_set, &nid); if (!inode) return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { - int err; - struct erofs_inode *vi = EROFS_I(inode); - - vi->nid = nid; + int err = erofs_fill_inode(inode); - err = erofs_fill_inode(inode); - if (!err) { - unlock_new_inode(inode); - } else { + if (err) { iget_failed(inode); - inode = ERR_PTR(err); + return ERR_PTR(err); } + unlock_new_inode(inode); } return inode; } -int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int erofs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -366,7 +368,7 @@ int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_IMMUTABLE); - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); return 0; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index bb8501c0ff5b..3f3561d37d1b 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -12,7 +12,6 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/bio.h> -#include <linux/buffer_head.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -108,9 +107,12 @@ struct erofs_domain { struct erofs_fscache { struct fscache_cookie *cookie; - struct inode *inode; - struct inode *anon_inode; + struct inode *inode; /* anonymous inode for the blob */ + + /* used for share domain mode */ struct erofs_domain *domain; + struct list_head node; + refcount_t ref; char *name; }; @@ -271,11 +273,6 @@ struct erofs_buf { #define erofs_blkoff(addr) ((addr) % EROFS_BLKSIZ) #define blknr_to_addr(nr) ((erofs_off_t)(nr) * EROFS_BLKSIZ) -static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid) -{ - return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits); -} - #define EROFS_FEATURE_FUNCS(name, compat, feature) \ static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \ { \ @@ -340,13 +337,14 @@ struct erofs_inode { struct inode vfs_inode; }; -#define EROFS_I(ptr) \ - container_of(ptr, struct erofs_inode, vfs_inode) +#define EROFS_I(ptr) container_of(ptr, struct erofs_inode, vfs_inode) -static inline unsigned long erofs_inode_datablocks(struct inode *inode) +static inline erofs_off_t erofs_iloc(struct inode *inode) { - /* since i_size cannot be changed */ - return DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ); + struct erofs_sb_info *sbi = EROFS_I_SB(inode); + + return blknr_to_addr(sbi->meta_blkaddr) + + (EROFS_I(inode)->nid << sbi->islotbits); } static inline unsigned int erofs_bitrange(unsigned int value, unsigned int bit, @@ -382,31 +380,18 @@ struct page *erofs_grab_cache_page_nowait(struct address_space *mapping, readahead_gfp_mask(mapping) & ~__GFP_RECLAIM); } -extern const struct super_operations erofs_sops; -extern struct file_system_type erofs_fs_type; - -extern const struct address_space_operations erofs_raw_access_aops; -extern const struct address_space_operations z_erofs_aops; - -enum { - BH_Encoded = BH_PrivateStart, - BH_FullMapped, - BH_Fragment, - BH_Partialref, -}; - /* Has a disk mapping */ -#define EROFS_MAP_MAPPED (1 << BH_Mapped) +#define EROFS_MAP_MAPPED 0x0001 /* Located in metadata (could be copied from bd_inode) */ -#define EROFS_MAP_META (1 << BH_Meta) +#define EROFS_MAP_META 0x0002 /* The extent is encoded */ -#define EROFS_MAP_ENCODED (1 << BH_Encoded) +#define EROFS_MAP_ENCODED 0x0004 /* The length of extent is full */ -#define EROFS_MAP_FULL_MAPPED (1 << BH_FullMapped) +#define EROFS_MAP_FULL_MAPPED 0x0008 /* Located in the special packed inode */ -#define EROFS_MAP_FRAGMENT (1 << BH_Fragment) +#define EROFS_MAP_FRAGMENT 0x0010 /* The extent refers to partial decompressed data */ -#define EROFS_MAP_PARTIAL_REF (1 << BH_Partialref) +#define EROFS_MAP_PARTIAL_REF 0x0020 struct erofs_map_blocks { struct erofs_buf buf; @@ -419,17 +404,15 @@ struct erofs_map_blocks { unsigned int m_flags; }; -/* Flags used by erofs_map_blocks_flatmode() */ -#define EROFS_GET_BLOCKS_RAW 0x0001 /* * Used to get the exact decompressed length, e.g. fiemap (consider lookback * approach instead if possible since it's more metadata lightweight.) */ -#define EROFS_GET_BLOCKS_FIEMAP 0x0002 +#define EROFS_GET_BLOCKS_FIEMAP 0x0001 /* Used to map the whole extent if non-negligible data is requested for LZMA */ -#define EROFS_GET_BLOCKS_READMORE 0x0004 +#define EROFS_GET_BLOCKS_READMORE 0x0002 /* Used to map tail extent for tailpacking inline or fragment pcluster */ -#define EROFS_GET_BLOCKS_FINDTAIL 0x0008 +#define EROFS_GET_BLOCKS_FINDTAIL 0x0004 enum { Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX, @@ -437,24 +420,6 @@ enum { Z_EROFS_COMPRESSION_RUNTIME_MAX }; -/* zmap.c */ -extern const struct iomap_ops z_erofs_iomap_report_ops; - -#ifdef CONFIG_EROFS_FS_ZIP -int z_erofs_fill_inode(struct inode *inode); -int z_erofs_map_blocks_iter(struct inode *inode, - struct erofs_map_blocks *map, - int flags); -#else -static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; } -static inline int z_erofs_map_blocks_iter(struct inode *inode, - struct erofs_map_blocks *map, - int flags) -{ - return -EOPNOTSUPP; -} -#endif /* !CONFIG_EROFS_FS_ZIP */ - struct erofs_map_dev { struct erofs_fscache *m_fscache; struct block_device *m_bdev; @@ -465,8 +430,27 @@ struct erofs_map_dev { unsigned int m_deviceid; }; -/* data.c */ +extern struct file_system_type erofs_fs_type; +extern const struct super_operations erofs_sops; + +extern const struct address_space_operations erofs_raw_access_aops; +extern const struct address_space_operations z_erofs_aops; +extern const struct address_space_operations erofs_fscache_access_aops; + +extern const struct inode_operations erofs_generic_iops; +extern const struct inode_operations erofs_symlink_iops; +extern const struct inode_operations erofs_fast_symlink_iops; +extern const struct inode_operations erofs_dir_iops; + extern const struct file_operations erofs_file_fops; +extern const struct file_operations erofs_dir_fops; + +extern const struct iomap_ops z_erofs_iomap_report_ops; + +/* flags for erofs_fscache_register_cookie() */ +#define EROFS_REG_COOKIE_SHARE 0x0001 +#define EROFS_REG_COOKIE_NEED_NOEXIST 0x0002 + void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); void *erofs_bread(struct erofs_buf *buf, struct inode *inode, @@ -476,37 +460,14 @@ void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev); int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); -int erofs_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, int flags); - -/* inode.c */ -static inline unsigned long erofs_inode_hash(erofs_nid_t nid) -{ -#if BITS_PER_LONG == 32 - return (nid >> 32) ^ (nid & 0xffffffff); -#else - return nid; -#endif -} - -extern const struct inode_operations erofs_generic_iops; -extern const struct inode_operations erofs_symlink_iops; -extern const struct inode_operations erofs_fast_symlink_iops; - +int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map); struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid); -int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int erofs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); - -/* namei.c */ -extern const struct inode_operations erofs_dir_iops; - int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, unsigned int *d_type); -/* dir.c */ -extern const struct file_operations erofs_dir_fops; - static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) { int retried = 0; @@ -522,23 +483,19 @@ static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) return NULL; } -/* pcpubuf.c */ void *erofs_get_pcpubuf(unsigned int requiredpages); void erofs_put_pcpubuf(void *ptr); int erofs_pcpubuf_growsize(unsigned int nrpages); void erofs_pcpubuf_init(void); void erofs_pcpubuf_exit(void); -/* sysfs.c */ int erofs_register_sysfs(struct super_block *sb); void erofs_unregister_sysfs(struct super_block *sb); int __init erofs_init_sysfs(void); void erofs_exit_sysfs(void); -/* utils.c / zdata.c */ struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp); -static inline void erofs_pagepool_add(struct page **pagepool, - struct page *page) +static inline void erofs_pagepool_add(struct page **pagepool, struct page *page) { set_page_private(page, (unsigned long)*pagepool); *pagepool = page; @@ -564,6 +521,9 @@ int erofs_try_to_free_cached_page(struct page *page); int z_erofs_load_lz4_config(struct super_block *sb, struct erofs_super_block *dsb, struct z_erofs_lz4_cfgs *lz4, int len); +int z_erofs_fill_inode(struct inode *inode); +int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, + int flags); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -581,6 +541,7 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb, } return 0; } +static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; } #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA @@ -601,23 +562,15 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb, } return 0; } -#endif /* !CONFIG_EROFS_FS_ZIP */ +#endif /* !CONFIG_EROFS_FS_ZIP_LZMA */ -/* flags for erofs_fscache_register_cookie() */ -#define EROFS_REG_COOKIE_NEED_INODE 1 -#define EROFS_REG_COOKIE_NEED_NOEXIST 2 - -/* fscache.c */ #ifdef CONFIG_EROFS_FS_ONDEMAND int erofs_fscache_register_fs(struct super_block *sb); void erofs_fscache_unregister_fs(struct super_block *sb); struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb, - char *name, - unsigned int flags); + char *name, unsigned int flags); void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache); - -extern const struct address_space_operations erofs_fscache_access_aops; #else static inline int erofs_fscache_register_fs(struct super_block *sb) { @@ -627,8 +580,7 @@ static inline void erofs_fscache_unregister_fs(struct super_block *sb) {} static inline struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb, - char *name, - unsigned int flags) + char *name, unsigned int flags) { return ERR_PTR(-EOPNOTSUPP); } diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index b64a108fac92..966eabc61c13 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -5,7 +5,6 @@ * Copyright (C) 2022, Alibaba Cloud */ #include "xattr.h" - #include <trace/events/erofs.h> struct erofs_qstr { @@ -87,19 +86,13 @@ static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name, return ERR_PTR(-ENOENT); } -static void *find_target_block_classic(struct erofs_buf *target, - struct inode *dir, - struct erofs_qstr *name, - int *_ndirents) +static void *erofs_find_target_block(struct erofs_buf *target, + struct inode *dir, struct erofs_qstr *name, int *_ndirents) { - unsigned int startprfx, endprfx; - int head, back; + int head = 0, back = DIV_ROUND_UP(dir->i_size, EROFS_BLKSIZ) - 1; + unsigned int startprfx = 0, endprfx = 0; void *candidate = ERR_PTR(-ENOENT); - startprfx = endprfx = 0; - head = 0; - back = erofs_inode_datablocks(dir) - 1; - while (head <= back) { const int mid = head + (back - head) / 2; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; @@ -180,8 +173,7 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, qn.end = name->name + name->len; ndirents = 0; - - de = find_target_block_classic(&buf, dir, &qn, &ndirents); + de = erofs_find_target_block(&buf, dir, &qn, &ndirents); if (IS_ERR(de)) return PTR_ERR(de); diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 626a615dafc2..19b1ae79cec4 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -5,7 +5,6 @@ * Copyright (C) 2021, Alibaba Cloud */ #include <linux/module.h> -#include <linux/buffer_head.h> #include <linux/statfs.h> #include <linux/parser.h> #include <linux/seq_file.h> @@ -969,6 +968,8 @@ static void erofs_put_super(struct super_block *sb) iput(sbi->packed_inode); sbi->packed_inode = NULL; #endif + erofs_free_dev_context(sbi->devs); + sbi->devs = NULL; erofs_fscache_unregister_fs(sb); } diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c index fd476961f742..435e515c0792 100644 --- a/fs/erofs/sysfs.c +++ b/fs/erofs/sysfs.c @@ -179,13 +179,13 @@ static const struct sysfs_ops erofs_attr_ops = { .store = erofs_attr_store, }; -static struct kobj_type erofs_sb_ktype = { +static const struct kobj_type erofs_sb_ktype = { .default_groups = erofs_groups, .sysfs_ops = &erofs_attr_ops, .release = erofs_sb_release, }; -static struct kobj_type erofs_ktype = { +static const struct kobj_type erofs_ktype = { .sysfs_ops = &erofs_attr_ops, }; @@ -193,7 +193,7 @@ static struct kset erofs_root = { .kobj = {.ktype = &erofs_ktype}, }; -static struct kobj_type erofs_feat_ktype = { +static const struct kobj_type erofs_feat_ktype = { .default_groups = erofs_feat_groups, .sysfs_ops = &erofs_attr_ops, }; diff --git a/fs/erofs/tagptr.h b/fs/erofs/tagptr.h deleted file mode 100644 index 64ceb7270b5c..000000000000 --- a/fs/erofs/tagptr.h +++ /dev/null @@ -1,107 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * A tagged pointer implementation - */ -#ifndef __EROFS_FS_TAGPTR_H -#define __EROFS_FS_TAGPTR_H - -#include <linux/types.h> -#include <linux/build_bug.h> - -/* - * the name of tagged pointer types are tagptr{1, 2, 3...}_t - * avoid directly using the internal structs __tagptr{1, 2, 3...} - */ -#define __MAKE_TAGPTR(n) \ -typedef struct __tagptr##n { \ - uintptr_t v; \ -} tagptr##n##_t; - -__MAKE_TAGPTR(1) -__MAKE_TAGPTR(2) -__MAKE_TAGPTR(3) -__MAKE_TAGPTR(4) - -#undef __MAKE_TAGPTR - -extern void __compiletime_error("bad tagptr tags") - __bad_tagptr_tags(void); - -extern void __compiletime_error("bad tagptr type") - __bad_tagptr_type(void); - -/* fix the broken usage of "#define tagptr2_t tagptr3_t" by users */ -#define __tagptr_mask_1(ptr, n) \ - __builtin_types_compatible_p(typeof(ptr), struct __tagptr##n) ? \ - (1UL << (n)) - 1 : - -#define __tagptr_mask(ptr) (\ - __tagptr_mask_1(ptr, 1) ( \ - __tagptr_mask_1(ptr, 2) ( \ - __tagptr_mask_1(ptr, 3) ( \ - __tagptr_mask_1(ptr, 4) ( \ - __bad_tagptr_type(), 0))))) - -/* generate a tagged pointer from a raw value */ -#define tagptr_init(type, val) \ - ((typeof(type)){ .v = (uintptr_t)(val) }) - -/* - * directly cast a tagged pointer to the native pointer type, which - * could be used for backward compatibility of existing code. - */ -#define tagptr_cast_ptr(tptr) ((void *)(tptr).v) - -/* encode tagged pointers */ -#define tagptr_fold(type, ptr, _tags) ({ \ - const typeof(_tags) tags = (_tags); \ - if (__builtin_constant_p(tags) && (tags & ~__tagptr_mask(type))) \ - __bad_tagptr_tags(); \ -tagptr_init(type, (uintptr_t)(ptr) | tags); }) - -/* decode tagged pointers */ -#define tagptr_unfold_ptr(tptr) \ - ((void *)((tptr).v & ~__tagptr_mask(tptr))) - -#define tagptr_unfold_tags(tptr) \ - ((tptr).v & __tagptr_mask(tptr)) - -/* operations for the tagger pointer */ -#define tagptr_eq(_tptr1, _tptr2) ({ \ - typeof(_tptr1) tptr1 = (_tptr1); \ - typeof(_tptr2) tptr2 = (_tptr2); \ - (void)(&tptr1 == &tptr2); \ -(tptr1).v == (tptr2).v; }) - -/* lock-free CAS operation */ -#define tagptr_cmpxchg(_ptptr, _o, _n) ({ \ - typeof(_ptptr) ptptr = (_ptptr); \ - typeof(_o) o = (_o); \ - typeof(_n) n = (_n); \ - (void)(&o == &n); \ - (void)(&o == ptptr); \ -tagptr_init(o, cmpxchg(&ptptr->v, o.v, n.v)); }) - -/* wrap WRITE_ONCE if atomic update is needed */ -#define tagptr_replace_tags(_ptptr, tags) ({ \ - typeof(_ptptr) ptptr = (_ptptr); \ - *ptptr = tagptr_fold(*ptptr, tagptr_unfold_ptr(*ptptr), tags); \ -*ptptr; }) - -#define tagptr_set_tags(_ptptr, _tags) ({ \ - typeof(_ptptr) ptptr = (_ptptr); \ - const typeof(_tags) tags = (_tags); \ - if (__builtin_constant_p(tags) && (tags & ~__tagptr_mask(*ptptr))) \ - __bad_tagptr_tags(); \ - ptptr->v |= tags; \ -*ptptr; }) - -#define tagptr_clear_tags(_ptptr, _tags) ({ \ - typeof(_ptptr) ptptr = (_ptptr); \ - const typeof(_tags) tags = (_tags); \ - if (__builtin_constant_p(tags) && (tags & ~__tagptr_mask(*ptptr))) \ - __bad_tagptr_tags(); \ - ptptr->v &= ~tags; \ -*ptptr; }) - -#endif /* __EROFS_FS_TAGPTR_H */ diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index a62fb8a3318a..60729b1220b6 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -22,8 +22,7 @@ static int init_inode_xattrs(struct inode *inode) struct xattr_iter it; unsigned int i; struct erofs_xattr_ibody_header *ih; - struct super_block *sb; - struct erofs_sb_info *sbi; + struct super_block *sb = inode->i_sb; int ret = 0; /* the most case is that xattrs of this inode are initialized. */ @@ -52,15 +51,14 @@ static int init_inode_xattrs(struct inode *inode) * undefined right now (maybe use later with some new sb feature). */ if (vi->xattr_isize == sizeof(struct erofs_xattr_ibody_header)) { - erofs_err(inode->i_sb, + erofs_err(sb, "xattr_isize %d of nid %llu is not supported yet", vi->xattr_isize, vi->nid); ret = -EOPNOTSUPP; goto out_unlock; } else if (vi->xattr_isize < sizeof(struct erofs_xattr_ibody_header)) { if (vi->xattr_isize) { - erofs_err(inode->i_sb, - "bogus xattr ibody @ nid %llu", vi->nid); + erofs_err(sb, "bogus xattr ibody @ nid %llu", vi->nid); DBG_BUGON(1); ret = -EFSCORRUPTED; goto out_unlock; /* xattr ondisk layout error */ @@ -69,11 +67,9 @@ static int init_inode_xattrs(struct inode *inode) goto out_unlock; } - sb = inode->i_sb; - sbi = EROFS_SB(sb); it.buf = __EROFS_BUF_INITIALIZER; - it.blkaddr = erofs_blknr(iloc(sbi, vi->nid) + vi->inode_isize); - it.ofs = erofs_blkoff(iloc(sbi, vi->nid) + vi->inode_isize); + it.blkaddr = erofs_blknr(erofs_iloc(inode) + vi->inode_isize); + it.ofs = erofs_blkoff(erofs_iloc(inode) + vi->inode_isize); /* read in shared xattr array (non-atomic, see kmalloc below) */ it.kaddr = erofs_read_metabuf(&it.buf, sb, it.blkaddr, EROFS_KMAP); @@ -159,7 +155,6 @@ static int inline_xattr_iter_begin(struct xattr_iter *it, struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); - struct erofs_sb_info *const sbi = EROFS_SB(inode->i_sb); unsigned int xattr_header_sz, inline_xattr_ofs; xattr_header_sz = inlinexattr_header_size(inode); @@ -170,9 +165,8 @@ static int inline_xattr_iter_begin(struct xattr_iter *it, inline_xattr_ofs = vi->inode_isize + xattr_header_sz; - it->blkaddr = erofs_blknr(iloc(sbi, vi->nid) + inline_xattr_ofs); - it->ofs = erofs_blkoff(iloc(sbi, vi->nid) + inline_xattr_ofs); - + it->blkaddr = erofs_blknr(erofs_iloc(inode) + inline_xattr_ofs); + it->ofs = erofs_blkoff(erofs_iloc(inode) + inline_xattr_ofs); it->kaddr = erofs_read_metabuf(&it->buf, inode->i_sb, it->blkaddr, EROFS_KMAP); if (IS_ERR(it->kaddr)) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 5200bb86e264..3247d2422bea 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -4,13 +4,178 @@ * https://www.huawei.com/ * Copyright (C) 2022 Alibaba Cloud */ -#include "zdata.h" #include "compress.h" #include <linux/prefetch.h> #include <linux/psi.h> - +#include <linux/cpuhotplug.h> #include <trace/events/erofs.h> +#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE) +#define Z_EROFS_INLINE_BVECS 2 + +/* + * let's leave a type here in case of introducing + * another tagged pointer later. + */ +typedef void *z_erofs_next_pcluster_t; + +struct z_erofs_bvec { + struct page *page; + int offset; + unsigned int end; +}; + +#define __Z_EROFS_BVSET(name, total) \ +struct name { \ + /* point to the next page which contains the following bvecs */ \ + struct page *nextpage; \ + struct z_erofs_bvec bvec[total]; \ +} +__Z_EROFS_BVSET(z_erofs_bvset,); +__Z_EROFS_BVSET(z_erofs_bvset_inline, Z_EROFS_INLINE_BVECS); + +/* + * Structure fields follow one of the following exclusion rules. + * + * I: Modifiable by initialization/destruction paths and read-only + * for everyone else; + * + * L: Field should be protected by the pcluster lock; + * + * A: Field should be accessed / updated in atomic for parallelized code. + */ +struct z_erofs_pcluster { + struct erofs_workgroup obj; + struct mutex lock; + + /* A: point to next chained pcluster or TAILs */ + z_erofs_next_pcluster_t next; + + /* L: the maximum decompression size of this round */ + unsigned int length; + + /* L: total number of bvecs */ + unsigned int vcnt; + + /* I: page offset of start position of decompression */ + unsigned short pageofs_out; + + /* I: page offset of inline compressed data */ + unsigned short pageofs_in; + + union { + /* L: inline a certain number of bvec for bootstrap */ + struct z_erofs_bvset_inline bvset; + + /* I: can be used to free the pcluster by RCU. */ + struct rcu_head rcu; + }; + + union { + /* I: physical cluster size in pages */ + unsigned short pclusterpages; + + /* I: tailpacking inline compressed size */ + unsigned short tailpacking_size; + }; + + /* I: compression algorithm format */ + unsigned char algorithmformat; + + /* L: whether partial decompression or not */ + bool partial; + + /* L: indicate several pageofs_outs or not */ + bool multibases; + + /* A: compressed bvecs (can be cached or inplaced pages) */ + struct z_erofs_bvec compressed_bvecs[]; +}; + +/* let's avoid the valid 32-bit kernel addresses */ + +/* the chained workgroup has't submitted io (still open) */ +#define Z_EROFS_PCLUSTER_TAIL ((void *)0x5F0ECAFE) +/* the chained workgroup has already submitted io */ +#define Z_EROFS_PCLUSTER_TAIL_CLOSED ((void *)0x5F0EDEAD) + +#define Z_EROFS_PCLUSTER_NIL (NULL) + +struct z_erofs_decompressqueue { + struct super_block *sb; + atomic_t pending_bios; + z_erofs_next_pcluster_t head; + + union { + struct completion done; + struct work_struct work; + struct kthread_work kthread_work; + } u; + bool eio, sync; +}; + +static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl) +{ + return !pcl->obj.index; +} + +static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl) +{ + if (z_erofs_is_inline_pcluster(pcl)) + return 1; + return pcl->pclusterpages; +} + +/* + * bit 30: I/O error occurred on this page + * bit 0 - 29: remaining parts to complete this page + */ +#define Z_EROFS_PAGE_EIO (1 << 30) + +static inline void z_erofs_onlinepage_init(struct page *page) +{ + union { + atomic_t o; + unsigned long v; + } u = { .o = ATOMIC_INIT(1) }; + + set_page_private(page, u.v); + smp_wmb(); + SetPagePrivate(page); +} + +static inline void z_erofs_onlinepage_split(struct page *page) +{ + atomic_inc((atomic_t *)&page->private); +} + +static inline void z_erofs_page_mark_eio(struct page *page) +{ + int orig; + + do { + orig = atomic_read((atomic_t *)&page->private); + } while (atomic_cmpxchg((atomic_t *)&page->private, orig, + orig | Z_EROFS_PAGE_EIO) != orig); +} + +static inline void z_erofs_onlinepage_endio(struct page *page) +{ + unsigned int v; + + DBG_BUGON(!PagePrivate(page)); + v = atomic_dec_return((atomic_t *)&page->private); + if (!(v & ~Z_EROFS_PAGE_EIO)) { + set_page_private(page, 0); + ClearPagePrivate(page); + if (!(v & Z_EROFS_PAGE_EIO)) + SetPageUptodate(page); + unlock_page(page); + } +} + +#define Z_EROFS_ONSTACK_PAGES 32 + /* * since pclustersize is variable for big pcluster feature, introduce slab * pools implementation for different pcluster sizes. @@ -175,35 +340,130 @@ static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl) DBG_BUGON(1); } -/* - * tagged pointer with 1-bit tag for all compressed pages - * tag 0 - the page is just found with an extra page reference - */ -typedef tagptr1_t compressed_page_t; +static struct workqueue_struct *z_erofs_workqueue __read_mostly; -#define tag_compressed_page_justfound(page) \ - tagptr_fold(compressed_page_t, page, 1) +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD +static struct kthread_worker __rcu **z_erofs_pcpu_workers; -static struct workqueue_struct *z_erofs_workqueue __read_mostly; +static void erofs_destroy_percpu_workers(void) +{ + struct kthread_worker *worker; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + worker = rcu_dereference_protected( + z_erofs_pcpu_workers[cpu], 1); + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL); + if (worker) + kthread_destroy_worker(worker); + } + kfree(z_erofs_pcpu_workers); +} -void z_erofs_exit_zip_subsystem(void) +static struct kthread_worker *erofs_init_percpu_worker(int cpu) { - destroy_workqueue(z_erofs_workqueue); - z_erofs_destroy_pcluster_pool(); + struct kthread_worker *worker = + kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu); + + if (IS_ERR(worker)) + return worker; + if (IS_ENABLED(CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI)) + sched_set_fifo_low(worker->task); + else + sched_set_normal(worker->task, 0); + return worker; } -static inline int z_erofs_init_workqueue(void) +static int erofs_init_percpu_workers(void) { - const unsigned int onlinecpus = num_possible_cpus(); + struct kthread_worker *worker; + unsigned int cpu; - /* - * no need to spawn too many threads, limiting threads could minimum - * scheduling overhead, perhaps per-CPU threads should be better? - */ - z_erofs_workqueue = alloc_workqueue("erofs_unzipd", - WQ_UNBOUND | WQ_HIGHPRI, - onlinecpus + onlinecpus / 4); - return z_erofs_workqueue ? 0 : -ENOMEM; + z_erofs_pcpu_workers = kcalloc(num_possible_cpus(), + sizeof(struct kthread_worker *), GFP_ATOMIC); + if (!z_erofs_pcpu_workers) + return -ENOMEM; + + for_each_online_cpu(cpu) { /* could miss cpu{off,on}line? */ + worker = erofs_init_percpu_worker(cpu); + if (!IS_ERR(worker)) + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker); + } + return 0; +} +#else +static inline void erofs_destroy_percpu_workers(void) {} +static inline int erofs_init_percpu_workers(void) { return 0; } +#endif + +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_EROFS_FS_PCPU_KTHREAD) +static DEFINE_SPINLOCK(z_erofs_pcpu_worker_lock); +static enum cpuhp_state erofs_cpuhp_state; + +static int erofs_cpu_online(unsigned int cpu) +{ + struct kthread_worker *worker, *old; + + worker = erofs_init_percpu_worker(cpu); + if (IS_ERR(worker)) + return PTR_ERR(worker); + + spin_lock(&z_erofs_pcpu_worker_lock); + old = rcu_dereference_protected(z_erofs_pcpu_workers[cpu], + lockdep_is_held(&z_erofs_pcpu_worker_lock)); + if (!old) + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker); + spin_unlock(&z_erofs_pcpu_worker_lock); + if (old) + kthread_destroy_worker(worker); + return 0; +} + +static int erofs_cpu_offline(unsigned int cpu) +{ + struct kthread_worker *worker; + + spin_lock(&z_erofs_pcpu_worker_lock); + worker = rcu_dereference_protected(z_erofs_pcpu_workers[cpu], + lockdep_is_held(&z_erofs_pcpu_worker_lock)); + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL); + spin_unlock(&z_erofs_pcpu_worker_lock); + + synchronize_rcu(); + if (worker) + kthread_destroy_worker(worker); + return 0; +} + +static int erofs_cpu_hotplug_init(void) +{ + int state; + + state = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "fs/erofs:online", erofs_cpu_online, erofs_cpu_offline); + if (state < 0) + return state; + + erofs_cpuhp_state = state; + return 0; +} + +static void erofs_cpu_hotplug_destroy(void) +{ + if (erofs_cpuhp_state) + cpuhp_remove_state_nocalls(erofs_cpuhp_state); +} +#else /* !CONFIG_HOTPLUG_CPU || !CONFIG_EROFS_FS_PCPU_KTHREAD */ +static inline int erofs_cpu_hotplug_init(void) { return 0; } +static inline void erofs_cpu_hotplug_destroy(void) {} +#endif + +void z_erofs_exit_zip_subsystem(void) +{ + erofs_cpu_hotplug_destroy(); + erofs_destroy_percpu_workers(); + destroy_workqueue(z_erofs_workqueue); + z_erofs_destroy_pcluster_pool(); } int __init z_erofs_init_zip_subsystem(void) @@ -211,10 +471,31 @@ int __init z_erofs_init_zip_subsystem(void) int err = z_erofs_create_pcluster_pool(); if (err) - return err; - err = z_erofs_init_workqueue(); + goto out_error_pcluster_pool; + + z_erofs_workqueue = alloc_workqueue("erofs_worker", + WQ_UNBOUND | WQ_HIGHPRI, num_possible_cpus()); + if (!z_erofs_workqueue) { + err = -ENOMEM; + goto out_error_workqueue_init; + } + + err = erofs_init_percpu_workers(); if (err) - z_erofs_destroy_pcluster_pool(); + goto out_error_pcpu_worker; + + err = erofs_cpu_hotplug_init(); + if (err < 0) + goto out_error_cpuhp_init; + return err; + +out_error_cpuhp_init: + erofs_destroy_percpu_workers(); +out_error_pcpu_worker: + destroy_workqueue(z_erofs_workqueue); +out_error_workqueue_init: + z_erofs_destroy_pcluster_pool(); +out_error_pcluster_pool: return err; } @@ -319,7 +600,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, for (i = 0; i < pcl->pclusterpages; ++i) { struct page *page; - compressed_page_t t; + void *t; /* mark pages just found for debugging */ struct page *newpage = NULL; /* the compressed page was loaded before */ @@ -329,7 +610,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, page = find_get_page(mc, pcl->obj.index + i); if (page) { - t = tag_compressed_page_justfound(page); + t = (void *)((unsigned long)page | 1); } else { /* I/O is needed, no possible to decompress directly */ standalone = false; @@ -345,11 +626,10 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, if (!newpage) continue; set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE); - t = tag_compressed_page_justfound(newpage); + t = (void *)((unsigned long)newpage | 1); } - if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, - tagptr_cast_ptr(t))) + if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, t)) continue; if (page) @@ -1151,18 +1431,24 @@ static void z_erofs_decompressqueue_work(struct work_struct *work) DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED); z_erofs_decompress_queue(bgq, &pagepool); - erofs_release_pages(&pagepool); kvfree(bgq); } +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD +static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) +{ + z_erofs_decompressqueue_work((struct work_struct *)work); +} +#endif + static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, - bool sync, int bios) + int bios) { struct erofs_sb_info *const sbi = EROFS_SB(io->sb); /* wake up the caller thread for sync decompression */ - if (sync) { + if (io->sync) { if (!atomic_add_return(bios, &io->pending_bios)) complete(&io->u.done); return; @@ -1170,9 +1456,24 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, if (atomic_add_return(bios, &io->pending_bios)) return; - /* Use workqueue and sync decompression for atomic contexts only */ + /* Use (kthread_)work and sync decompression for atomic contexts only */ if (in_atomic() || irqs_disabled()) { +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD + struct kthread_worker *worker; + + rcu_read_lock(); + worker = rcu_dereference( + z_erofs_pcpu_workers[raw_smp_processor_id()]); + if (!worker) { + INIT_WORK(&io->u.work, z_erofs_decompressqueue_work); + queue_work(z_erofs_workqueue, &io->u.work); + } else { + kthread_queue_work(worker, &io->u.kthread_work); + } + rcu_read_unlock(); +#else queue_work(z_erofs_workqueue, &io->u.work); +#endif /* enable sync decompression for readahead */ if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON; @@ -1192,8 +1493,6 @@ static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl, struct address_space *mapping; struct page *oldpage, *page; - - compressed_page_t t; int justfound; repeat: @@ -1203,10 +1502,8 @@ repeat: if (!page) goto out_allocpage; - /* process the target tagged pointer */ - t = tagptr_init(compressed_page_t, page); - justfound = tagptr_unfold_tags(t); - page = tagptr_unfold_ptr(t); + justfound = (unsigned long)page & 1UL; + page = (struct page *)((unsigned long)page & ~1UL); /* * preallocated cached pages, which is used to avoid direct reclaim @@ -1294,9 +1591,8 @@ out: /* the only exit (for tracing and debugging) */ return page; } -static struct z_erofs_decompressqueue * -jobqueue_init(struct super_block *sb, - struct z_erofs_decompressqueue *fgq, bool *fg) +static struct z_erofs_decompressqueue *jobqueue_init(struct super_block *sb, + struct z_erofs_decompressqueue *fgq, bool *fg) { struct z_erofs_decompressqueue *q; @@ -1306,13 +1602,19 @@ jobqueue_init(struct super_block *sb, *fg = true; goto fg_out; } +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD + kthread_init_work(&q->u.kthread_work, + z_erofs_decompressqueue_kthread_work); +#else INIT_WORK(&q->u.work, z_erofs_decompressqueue_work); +#endif } else { fg_out: q = fgq; init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); q->eio = false; + q->sync = true; } q->sb = sb; q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED; @@ -1326,20 +1628,6 @@ enum { NR_JOBQUEUES, }; -static void *jobqueueset_init(struct super_block *sb, - struct z_erofs_decompressqueue *q[], - struct z_erofs_decompressqueue *fgq, bool *fg) -{ - /* - * if managed cache is enabled, bypass jobqueue is needed, - * no need to read from device for all pclusters in this queue. - */ - q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL); - q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, fg); - - return tagptr_cast_ptr(tagptr_fold(tagptr1_t, q[JQ_SUBMIT], *fg)); -} - static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, z_erofs_next_pcluster_t qtail[], z_erofs_next_pcluster_t owned_head) @@ -1361,8 +1649,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, static void z_erofs_decompressqueue_endio(struct bio *bio) { - tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private); - struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t); + struct z_erofs_decompressqueue *q = bio->bi_private; blk_status_t err = bio->bi_status; struct bio_vec *bvec; struct bvec_iter_all iter_all; @@ -1381,7 +1668,7 @@ static void z_erofs_decompressqueue_endio(struct bio *bio) } if (err) q->eio = true; - z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1); + z_erofs_decompress_kickoff(q, -1); bio_put(bio); } @@ -1394,7 +1681,6 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb)); z_erofs_next_pcluster_t qtail[NR_JOBQUEUES]; struct z_erofs_decompressqueue *q[NR_JOBQUEUES]; - void *bi_private; z_erofs_next_pcluster_t owned_head = f->owned_head; /* bio is NULL initially, so no need to initialize last_{index,bdev} */ pgoff_t last_index; @@ -1404,7 +1690,13 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, unsigned long pflags; int memstall = 0; - bi_private = jobqueueset_init(sb, q, fgq, force_fg); + /* + * if managed cache is enabled, bypass jobqueue is needed, + * no need to read from device for all pclusters in this queue. + */ + q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL); + q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, force_fg); + qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head; qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head; @@ -1473,7 +1765,7 @@ submit_bio_retry: last_bdev = mdev.m_bdev; bio->bi_iter.bi_sector = (sector_t)cur << LOG_SECTORS_PER_BLOCK; - bio->bi_private = bi_private; + bio->bi_private = q[JQ_SUBMIT]; if (f->readahead) bio->bi_opf |= REQ_RAHEAD; ++nr_bios; @@ -1500,13 +1792,13 @@ submit_bio_retry: /* * although background is preferred, no one is pending for submission. - * don't issue workqueue for decompression but drop it directly instead. + * don't issue decompression but drop it directly instead. */ if (!*force_fg && !nr_bios) { kvfree(q[JQ_SUBMIT]); return; } - z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios); + z_erofs_decompress_kickoff(q[JQ_SUBMIT], nr_bios); } static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h deleted file mode 100644 index d98c95212985..000000000000 --- a/fs/erofs/zdata.h +++ /dev/null @@ -1,178 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2018 HUAWEI, Inc. - * https://www.huawei.com/ - */ -#ifndef __EROFS_FS_ZDATA_H -#define __EROFS_FS_ZDATA_H - -#include "internal.h" -#include "tagptr.h" - -#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE) -#define Z_EROFS_INLINE_BVECS 2 - -/* - * let's leave a type here in case of introducing - * another tagged pointer later. - */ -typedef void *z_erofs_next_pcluster_t; - -struct z_erofs_bvec { - struct page *page; - int offset; - unsigned int end; -}; - -#define __Z_EROFS_BVSET(name, total) \ -struct name { \ - /* point to the next page which contains the following bvecs */ \ - struct page *nextpage; \ - struct z_erofs_bvec bvec[total]; \ -} -__Z_EROFS_BVSET(z_erofs_bvset,); -__Z_EROFS_BVSET(z_erofs_bvset_inline, Z_EROFS_INLINE_BVECS); - -/* - * Structure fields follow one of the following exclusion rules. - * - * I: Modifiable by initialization/destruction paths and read-only - * for everyone else; - * - * L: Field should be protected by the pcluster lock; - * - * A: Field should be accessed / updated in atomic for parallelized code. - */ -struct z_erofs_pcluster { - struct erofs_workgroup obj; - struct mutex lock; - - /* A: point to next chained pcluster or TAILs */ - z_erofs_next_pcluster_t next; - - /* L: the maximum decompression size of this round */ - unsigned int length; - - /* L: total number of bvecs */ - unsigned int vcnt; - - /* I: page offset of start position of decompression */ - unsigned short pageofs_out; - - /* I: page offset of inline compressed data */ - unsigned short pageofs_in; - - union { - /* L: inline a certain number of bvec for bootstrap */ - struct z_erofs_bvset_inline bvset; - - /* I: can be used to free the pcluster by RCU. */ - struct rcu_head rcu; - }; - - union { - /* I: physical cluster size in pages */ - unsigned short pclusterpages; - - /* I: tailpacking inline compressed size */ - unsigned short tailpacking_size; - }; - - /* I: compression algorithm format */ - unsigned char algorithmformat; - - /* L: whether partial decompression or not */ - bool partial; - - /* L: indicate several pageofs_outs or not */ - bool multibases; - - /* A: compressed bvecs (can be cached or inplaced pages) */ - struct z_erofs_bvec compressed_bvecs[]; -}; - -/* let's avoid the valid 32-bit kernel addresses */ - -/* the chained workgroup has't submitted io (still open) */ -#define Z_EROFS_PCLUSTER_TAIL ((void *)0x5F0ECAFE) -/* the chained workgroup has already submitted io */ -#define Z_EROFS_PCLUSTER_TAIL_CLOSED ((void *)0x5F0EDEAD) - -#define Z_EROFS_PCLUSTER_NIL (NULL) - -struct z_erofs_decompressqueue { - struct super_block *sb; - atomic_t pending_bios; - z_erofs_next_pcluster_t head; - - union { - struct completion done; - struct work_struct work; - } u; - - bool eio; -}; - -static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl) -{ - return !pcl->obj.index; -} - -static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl) -{ - if (z_erofs_is_inline_pcluster(pcl)) - return 1; - return pcl->pclusterpages; -} - -/* - * bit 30: I/O error occurred on this page - * bit 0 - 29: remaining parts to complete this page - */ -#define Z_EROFS_PAGE_EIO (1 << 30) - -static inline void z_erofs_onlinepage_init(struct page *page) -{ - union { - atomic_t o; - unsigned long v; - } u = { .o = ATOMIC_INIT(1) }; - - set_page_private(page, u.v); - smp_wmb(); - SetPagePrivate(page); -} - -static inline void z_erofs_onlinepage_split(struct page *page) -{ - atomic_inc((atomic_t *)&page->private); -} - -static inline void z_erofs_page_mark_eio(struct page *page) -{ - int orig; - - do { - orig = atomic_read((atomic_t *)&page->private); - } while (atomic_cmpxchg((atomic_t *)&page->private, orig, - orig | Z_EROFS_PAGE_EIO) != orig); -} - -static inline void z_erofs_onlinepage_endio(struct page *page) -{ - unsigned int v; - - DBG_BUGON(!PagePrivate(page)); - v = atomic_dec_return((atomic_t *)&page->private); - if (!(v & ~Z_EROFS_PAGE_EIO)) { - set_page_private(page, 0); - ClearPagePrivate(page); - if (!(v & Z_EROFS_PAGE_EIO)) - SetPageUptodate(page); - unlock_page(page); - } -} - -#define Z_EROFS_ONSTACK_PAGES 32 - -#endif diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 98fb90b9af71..8bf6d30518b6 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -7,10 +7,6 @@ #include <asm/unaligned.h> #include <trace/events/erofs.h> -static int z_erofs_do_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, - int flags); - int z_erofs_fill_inode(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); @@ -29,126 +25,6 @@ int z_erofs_fill_inode(struct inode *inode) return 0; } -static int z_erofs_fill_inode_lazy(struct inode *inode) -{ - struct erofs_inode *const vi = EROFS_I(inode); - struct super_block *const sb = inode->i_sb; - int err, headnr; - erofs_off_t pos; - struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - void *kaddr; - struct z_erofs_map_header *h; - - if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { - /* - * paired with smp_mb() at the end of the function to ensure - * fields will only be observed after the bit is set. - */ - smp_mb(); - return 0; - } - - if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) - return -ERESTARTSYS; - - err = 0; - if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) - goto out_unlock; - - pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize + - vi->xattr_isize, 8); - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); - if (IS_ERR(kaddr)) { - err = PTR_ERR(kaddr); - goto out_unlock; - } - - h = kaddr + erofs_blkoff(pos); - /* - * if the highest bit of the 8-byte map header is set, the whole file - * is stored in the packed inode. The rest bits keeps z_fragmentoff. - */ - if (h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT) { - vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; - vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63); - vi->z_tailextent_headlcn = 0; - goto done; - } - vi->z_advise = le16_to_cpu(h->h_advise); - vi->z_algorithmtype[0] = h->h_algorithmtype & 15; - vi->z_algorithmtype[1] = h->h_algorithmtype >> 4; - - headnr = 0; - if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || - vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { - erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", - headnr + 1, vi->z_algorithmtype[headnr], vi->nid); - err = -EOPNOTSUPP; - goto out_put_metabuf; - } - - vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7); - if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && - vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | - Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { - erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu", - vi->nid); - err = -EFSCORRUPTED; - goto out_put_metabuf; - } - if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && - !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ - !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { - erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", - vi->nid); - err = -EFSCORRUPTED; - goto out_put_metabuf; - } - - if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) { - struct erofs_map_blocks map = { - .buf = __EROFS_BUF_INITIALIZER - }; - - vi->z_idata_size = le16_to_cpu(h->h_idata_size); - err = z_erofs_do_map_blocks(inode, &map, - EROFS_GET_BLOCKS_FINDTAIL); - erofs_put_metabuf(&map.buf); - - if (!map.m_plen || - erofs_blkoff(map.m_pa) + map.m_plen > EROFS_BLKSIZ) { - erofs_err(sb, "invalid tail-packing pclustersize %llu", - map.m_plen); - err = -EFSCORRUPTED; - } - if (err < 0) - goto out_put_metabuf; - } - - if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER && - !(h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT)) { - struct erofs_map_blocks map = { - .buf = __EROFS_BUF_INITIALIZER - }; - - vi->z_fragmentoff = le32_to_cpu(h->h_fragmentoff); - err = z_erofs_do_map_blocks(inode, &map, - EROFS_GET_BLOCKS_FINDTAIL); - erofs_put_metabuf(&map.buf); - if (err < 0) - goto out_put_metabuf; - } -done: - /* paired with smp_mb() at the beginning of the function */ - smp_mb(); - set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); -out_put_metabuf: - erofs_put_metabuf(&buf); -out_unlock: - clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags); - return err; -} - struct z_erofs_maprecorder { struct inode *inode; struct erofs_map_blocks *map; @@ -169,10 +45,9 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); - const erofs_off_t ibase = iloc(EROFS_I_SB(inode), vi->nid); const erofs_off_t pos = - Z_EROFS_VLE_LEGACY_INDEX_ALIGN(ibase + vi->inode_isize + - vi->xattr_isize) + + Z_EROFS_VLE_LEGACY_INDEX_ALIGN(erofs_iloc(inode) + + vi->inode_isize + vi->xattr_isize) + lcn * sizeof(struct z_erofs_vle_decompressed_index); struct z_erofs_vle_decompressed_index *di; unsigned int advise, type; @@ -372,9 +247,8 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); const unsigned int lclusterbits = vi->z_logical_clusterbits; - const erofs_off_t ebase = ALIGN(iloc(EROFS_I_SB(inode), vi->nid) + - vi->inode_isize + vi->xattr_isize, 8) + - sizeof(struct z_erofs_map_header); + const erofs_off_t ebase = sizeof(struct z_erofs_map_header) + + ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); const unsigned int totalidx = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ); unsigned int compacted_4b_initial, compacted_2b; unsigned int amortizedshift; @@ -732,6 +606,125 @@ unmap_out: return err; } +static int z_erofs_fill_inode_lazy(struct inode *inode) +{ + struct erofs_inode *const vi = EROFS_I(inode); + struct super_block *const sb = inode->i_sb; + int err, headnr; + erofs_off_t pos; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + void *kaddr; + struct z_erofs_map_header *h; + + if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { + /* + * paired with smp_mb() at the end of the function to ensure + * fields will only be observed after the bit is set. + */ + smp_mb(); + return 0; + } + + if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) + return -ERESTARTSYS; + + err = 0; + if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) + goto out_unlock; + + pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); + if (IS_ERR(kaddr)) { + err = PTR_ERR(kaddr); + goto out_unlock; + } + + h = kaddr + erofs_blkoff(pos); + /* + * if the highest bit of the 8-byte map header is set, the whole file + * is stored in the packed inode. The rest bits keeps z_fragmentoff. + */ + if (h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT) { + vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; + vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63); + vi->z_tailextent_headlcn = 0; + goto done; + } + vi->z_advise = le16_to_cpu(h->h_advise); + vi->z_algorithmtype[0] = h->h_algorithmtype & 15; + vi->z_algorithmtype[1] = h->h_algorithmtype >> 4; + + headnr = 0; + if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || + vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { + erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", + headnr + 1, vi->z_algorithmtype[headnr], vi->nid); + err = -EOPNOTSUPP; + goto out_put_metabuf; + } + + vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7); + if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && + vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | + Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { + erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu", + vi->nid); + err = -EFSCORRUPTED; + goto out_put_metabuf; + } + if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && + !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ + !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { + erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", + vi->nid); + err = -EFSCORRUPTED; + goto out_put_metabuf; + } + + if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) { + struct erofs_map_blocks map = { + .buf = __EROFS_BUF_INITIALIZER + }; + + vi->z_idata_size = le16_to_cpu(h->h_idata_size); + err = z_erofs_do_map_blocks(inode, &map, + EROFS_GET_BLOCKS_FINDTAIL); + erofs_put_metabuf(&map.buf); + + if (!map.m_plen || + erofs_blkoff(map.m_pa) + map.m_plen > EROFS_BLKSIZ) { + erofs_err(sb, "invalid tail-packing pclustersize %llu", + map.m_plen); + err = -EFSCORRUPTED; + } + if (err < 0) + goto out_put_metabuf; + } + + if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER && + !(h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT)) { + struct erofs_map_blocks map = { + .buf = __EROFS_BUF_INITIALIZER + }; + + vi->z_fragmentoff = le32_to_cpu(h->h_fragmentoff); + err = z_erofs_do_map_blocks(inode, &map, + EROFS_GET_BLOCKS_FINDTAIL); + erofs_put_metabuf(&map.buf); + if (err < 0) + goto out_put_metabuf; + } +done: + /* paired with smp_mb() at the beginning of the function */ + smp_mb(); + set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); +out_put_metabuf: + erofs_put_metabuf(&buf); +out_unlock: + clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags); + return err; +} + int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags) { diff --git a/fs/exec.c b/fs/exec.c index ab913243a367..3d2b80d8d58e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1414,15 +1414,15 @@ EXPORT_SYMBOL(begin_new_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); - struct user_namespace *mnt_userns = file_mnt_user_ns(file); - if (inode_permission(mnt_userns, inode, MAY_READ) < 0) { + struct mnt_idmap *idmap = file_mnt_idmap(file); + if (inode_permission(idmap, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; /* Ensure mm->user_ns contains the executable */ user_ns = old = bprm->mm->user_ns; while ((user_ns != &init_user_ns) && - !privileged_wrt_inode_uidgid(user_ns, mnt_userns, inode)) + !privileged_wrt_inode_uidgid(user_ns, idmap, inode)) user_ns = user_ns->parent; if (old != user_ns) { @@ -1596,7 +1596,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm) static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) { /* Handle suid and sgid on files */ - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct inode *inode = file_inode(file); unsigned int mode; vfsuid_t vfsuid; @@ -1612,15 +1612,15 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) if (!(mode & (S_ISUID|S_ISGID))) return; - mnt_userns = file_mnt_user_ns(file); + idmap = file_mnt_idmap(file); /* Be careful if suid/sgid is set */ inode_lock(inode); /* reload atomically mode/uid/gid now that lock held */ mode = inode->i_mode; - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); - vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid = i_gid_into_vfsgid(idmap, inode); inode_unlock(inode); /* We ignore suid/sgid if there are no mappings for them in the ns */ diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index bc6d21d7c5ad..1bf16abe3c84 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -450,9 +450,9 @@ int exfat_trim_fs(struct inode *inode, struct fstrim_range *range); extern const struct file_operations exfat_file_operations; int __exfat_truncate(struct inode *inode); void exfat_truncate(struct inode *inode); -int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int exfat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -int exfat_getattr(struct user_namespace *mnt_userns, const struct path *path, +int exfat_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, unsigned int request_mask, unsigned int query_flags); int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/fs/exfat/file.c b/fs/exfat/file.c index f5b29072775d..1fdb0a64b91d 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -226,14 +226,14 @@ write_size: mutex_unlock(&sbi->s_lock); } -int exfat_getattr(struct user_namespace *mnt_uerns, const struct path *path, +int exfat_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, unsigned int request_mask, unsigned int query_flags) { struct inode *inode = d_backing_inode(path->dentry); struct exfat_inode_info *ei = EXFAT_I(inode); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); exfat_truncate_atime(&stat->atime); stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = ei->i_crtime.tv_sec; @@ -242,7 +242,7 @@ int exfat_getattr(struct user_namespace *mnt_uerns, const struct path *path, return 0; } -int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int exfat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct exfat_sb_info *sbi = EXFAT_SB(dentry->d_sb); @@ -266,7 +266,7 @@ int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, ATTR_TIMES_SET); } - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); attr->ia_valid = ia_valid; if (error) goto out; @@ -293,7 +293,7 @@ int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (attr->ia_valid & ATTR_SIZE) inode->i_mtime = inode->i_ctime = current_time(inode); - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); exfat_truncate_atime(&inode->i_atime); if (attr->ia_valid & ATTR_SIZE) { diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 5f995eba5dbb..02aab4c3a5f7 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -551,7 +551,7 @@ out: return ret; } -static int exfat_create(struct user_namespace *mnt_userns, struct inode *dir, +static int exfat_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; @@ -834,7 +834,7 @@ unlock: return err; } -static int exfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; @@ -1285,7 +1285,7 @@ out: return ret; } -static int exfat_rename(struct user_namespace *mnt_userns, +static int exfat_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 3204bd33e4e8..ab88d33d106c 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -145,7 +145,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, if (err) goto out_err; dprintk("%s: found name: %s\n", __func__, nbuf); - tmp = lookup_one_unlocked(mnt_user_ns(mnt), nbuf, parent, strlen(nbuf)); + tmp = lookup_one_unlocked(mnt_idmap(mnt), nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); @@ -524,7 +524,7 @@ exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, } inode_lock(target_dir->d_inode); - nresult = lookup_one(mnt_user_ns(mnt), nbuf, + nresult = lookup_one(mnt_idmap(mnt), nbuf, target_dir, strlen(nbuf)); if (!IS_ERR(nresult)) { if (unlikely(nresult->d_inode != result->d_inode)) { diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 440d5f1e9d47..82b17d7fc93f 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -219,7 +219,7 @@ __ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) * inode->i_mutex: down */ int -ext2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +ext2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; @@ -228,7 +228,7 @@ ext2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, umode_t mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - error = posix_acl_update_mode(&init_user_ns, inode, &mode, + error = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (error) return error; diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h index 3841becb94ff..4a8443a2b8ec 100644 --- a/fs/ext2/acl.h +++ b/fs/ext2/acl.h @@ -56,7 +56,7 @@ static inline int ext2_acl_count(size_t size) /* acl.c */ extern struct posix_acl *ext2_get_acl(struct inode *inode, int type, bool rcu); -extern int ext2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int ext2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int ext2_init_acl (struct inode *, struct inode *); diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index e5cbc27ba459..4a6955a0a116 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -461,9 +461,9 @@ static int ext2_handle_dirsync(struct inode *dir) return err; } -void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, - struct page *page, void *page_addr, struct inode *inode, - int update_times) +int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, + struct page *page, void *page_addr, struct inode *inode, + bool update_times) { loff_t pos = page_offset(page) + (char *) de - (char *) page_addr; @@ -472,7 +472,10 @@ void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, lock_page(page); err = ext2_prepare_chunk(page, pos, len); - BUG_ON(err); + if (err) { + unlock_page(page); + return err; + } de->inode = cpu_to_le32(inode->i_ino); ext2_set_de_type(de, inode); ext2_commit_chunk(page, pos, len); @@ -480,7 +483,7 @@ void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, dir->i_mtime = dir->i_ctime = current_time(dir); EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; mark_inode_dirty(dir); - ext2_handle_dirsync(dir); + return ext2_handle_dirsync(dir); } /* @@ -646,7 +649,7 @@ int ext2_make_empty(struct inode *inode, struct inode *parent) unlock_page(page); goto fail; } - kaddr = kmap_atomic(page); + kaddr = kmap_local_page(page); memset(kaddr, 0, chunk_size); de = (struct ext2_dir_entry_2 *)kaddr; de->name_len = 1; @@ -661,7 +664,7 @@ int ext2_make_empty(struct inode *inode, struct inode *parent) de->inode = cpu_to_le32(parent->i_ino); memcpy (de->name, "..\0", 4); ext2_set_de_type (de, inode); - kunmap_atomic(kaddr); + kunmap_local(kaddr); ext2_commit_chunk(page, 0, chunk_size); err = ext2_handle_dirsync(inode); fail: diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 28de11a22e5f..cb78d7dcfb95 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -734,8 +734,9 @@ extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page, char *kaddr); extern int ext2_empty_dir (struct inode *); extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa); -extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *, - struct inode *, int); +int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, + struct page *page, void *page_addr, struct inode *inode, + bool update_times); static inline void ext2_put_page(struct page *page, void *page_addr) { kunmap_local(page_addr); @@ -753,8 +754,8 @@ extern struct inode *ext2_iget (struct super_block *, unsigned long); extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_evict_inode(struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern int ext2_setattr (struct user_namespace *, struct dentry *, struct iattr *); -extern int ext2_getattr (struct user_namespace *, const struct path *, +extern int ext2_setattr (struct mnt_idmap *, struct dentry *, struct iattr *); +extern int ext2_getattr (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void ext2_set_inode_flags(struct inode *inode); extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, @@ -762,7 +763,7 @@ extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* ioctl.c */ extern int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa); -extern int ext2_fileattr_set(struct user_namespace *mnt_userns, +extern int ext2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); extern long ext2_ioctl(struct file *, unsigned int, unsigned long); extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long); diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 78b8686d9a4a..a4e1d7a9c544 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -545,7 +545,7 @@ got: inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; } else - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = ino; inode->i_blocks = 0; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 69aed9e2359e..26f135e7ffce 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1592,7 +1592,7 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } -int ext2_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ext2_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -1614,28 +1614,28 @@ int ext2_getattr(struct user_namespace *mnt_userns, const struct path *path, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; } -int ext2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ext2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(&init_user_ns, dentry, iattr); + error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) return error; - if (is_quota_modification(mnt_userns, inode, iattr)) { + if (is_quota_modification(&nop_mnt_idmap, inode, iattr)) { error = dquot_initialize(inode); if (error) return error; } - if (i_uid_needs_update(mnt_userns, iattr, inode) || - i_gid_needs_update(mnt_userns, iattr, inode)) { - error = dquot_transfer(mnt_userns, inode, iattr); + if (i_uid_needs_update(&nop_mnt_idmap, iattr, inode) || + i_gid_needs_update(&nop_mnt_idmap, iattr, inode)) { + error = dquot_transfer(&nop_mnt_idmap, inode, iattr); if (error) return error; } @@ -1644,9 +1644,9 @@ int ext2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (error) return error; } - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); if (iattr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode); + error = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); mark_inode_dirty(inode); return error; diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index e8340bf09b10..cc87d413eb43 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -27,7 +27,7 @@ int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int ext2_fileattr_set(struct user_namespace *mnt_userns, +int ext2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -66,7 +66,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case EXT2_IOC_SETVERSION: { __u32 generation; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) return -EPERM; ret = mnt_want_write_file(filp); if (ret) @@ -99,7 +99,7 @@ setversion_out: if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) return -ENOTTY; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) return -EACCES; if (get_user(rsv_window_size, (int __user *)arg)) diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index c056957221a2..7f5dfa87cc95 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -99,7 +99,7 @@ struct dentry *ext2_get_parent(struct dentry *child) * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ext2_create (struct user_namespace * mnt_userns, +static int ext2_create (struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { @@ -119,7 +119,7 @@ static int ext2_create (struct user_namespace * mnt_userns, return ext2_add_nondir(dentry, inode); } -static int ext2_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int ext2_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode = ext2_new_inode(dir, mode, NULL); @@ -133,7 +133,7 @@ static int ext2_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return finish_open_simple(file, 0); } -static int ext2_mknod (struct user_namespace * mnt_userns, struct inode * dir, +static int ext2_mknod (struct mnt_idmap * idmap, struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode * inode; @@ -154,7 +154,7 @@ static int ext2_mknod (struct user_namespace * mnt_userns, struct inode * dir, return err; } -static int ext2_symlink (struct user_namespace * mnt_userns, struct inode * dir, +static int ext2_symlink (struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, const char * symname) { struct super_block * sb = dir->i_sb; @@ -225,7 +225,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir, return err; } -static int ext2_mkdir(struct user_namespace * mnt_userns, +static int ext2_mkdir(struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, umode_t mode) { struct inode * inode; @@ -315,7 +315,7 @@ static int ext2_rmdir (struct inode * dir, struct dentry *dentry) return err; } -static int ext2_rename (struct user_namespace * mnt_userns, +static int ext2_rename (struct mnt_idmap * idmap, struct inode * old_dir, struct dentry * old_dentry, struct inode * new_dir, struct dentry * new_dentry, unsigned int flags) @@ -370,8 +370,11 @@ static int ext2_rename (struct user_namespace * mnt_userns, err = PTR_ERR(new_de); goto out_dir; } - ext2_set_link(new_dir, new_de, new_page, page_addr, old_inode, 1); + err = ext2_set_link(new_dir, new_de, new_page, page_addr, + old_inode, true); ext2_put_page(new_page, page_addr); + if (err) + goto out_dir; new_inode->i_ctime = current_time(new_inode); if (dir_de) drop_nlink(new_inode); @@ -394,24 +397,24 @@ static int ext2_rename (struct user_namespace * mnt_userns, ext2_delete_entry(old_de, old_page, old_page_addr); if (dir_de) { - if (old_dir != new_dir) - ext2_set_link(old_inode, dir_de, dir_page, - dir_page_addr, new_dir, 0); + if (old_dir != new_dir) { + err = ext2_set_link(old_inode, dir_de, dir_page, + dir_page_addr, new_dir, false); + } ext2_put_page(dir_page, dir_page_addr); inode_dec_link_count(old_dir); } +out_old: ext2_put_page(old_page, old_page_addr); - return 0; +out: + return err; out_dir: if (dir_de) ext2_put_page(dir_page, dir_page_addr); -out_old: - ext2_put_page(old_page, old_page_addr); -out: - return err; + goto out_old; } const struct inode_operations ext2_dir_inode_operations = { diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index ebade1f52451..db47b8ab153e 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -19,7 +19,7 @@ ext2_xattr_security_get(const struct xattr_handler *handler, static int ext2_xattr_security_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 18a87d5dd1ab..995f931228ce 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -26,7 +26,7 @@ ext2_xattr_trusted_get(const struct xattr_handler *handler, static int ext2_xattr_trusted_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c index 58092449f8ff..dd1507231081 100644 --- a/fs/ext2/xattr_user.c +++ b/fs/ext2/xattr_user.c @@ -30,7 +30,7 @@ ext2_xattr_user_get(const struct xattr_handler *handler, static int ext2_xattr_user_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index a9f89539aeee..27fcbddfb148 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -225,7 +225,7 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, } int -ext4_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { handle_t *handle; @@ -249,7 +249,7 @@ retry: return PTR_ERR(handle); if ((type == ACL_TYPE_ACCESS) && acl) { - error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl); + error = posix_acl_update_mode(idmap, inode, &mode, &acl); if (error) goto out_stop; if (mode != inode->i_mode) diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 09c4a8a3b716..0c5a79c3b5d4 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -56,7 +56,7 @@ static inline int ext4_acl_count(size_t size) /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu); -int ext4_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 140e1eb300d1..43e26e6f6e42 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2845,7 +2845,7 @@ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len, /* ialloc.c */ extern int ext4_mark_inode_used(struct super_block *sb, int ino); -extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *, +extern struct inode *__ext4_new_inode(struct mnt_idmap *, handle_t *, struct inode *, umode_t, const struct qstr *qstr, __u32 goal, uid_t *owner, __u32 i_flags, @@ -2853,11 +2853,11 @@ extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *, int nblocks); #define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \ - __ext4_new_inode(&init_user_ns, (handle), (dir), (mode), (qstr), \ + __ext4_new_inode(&nop_mnt_idmap, (handle), (dir), (mode), (qstr), \ (goal), (owner), i_flags, 0, 0, 0) -#define ext4_new_inode_start_handle(mnt_userns, dir, mode, qstr, goal, owner, \ +#define ext4_new_inode_start_handle(idmap, dir, mode, qstr, goal, owner, \ type, nblocks) \ - __ext4_new_inode((mnt_userns), NULL, (dir), (mode), (qstr), (goal), (owner), \ + __ext4_new_inode((idmap), NULL, (dir), (mode), (qstr), (goal), (owner), \ 0, (type), __LINE__, (nblocks)) @@ -2976,14 +2976,14 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, __ext4_iget((sb), (ino), (flags), __func__, __LINE__) extern int ext4_write_inode(struct inode *, struct writeback_control *); -extern int ext4_setattr(struct user_namespace *, struct dentry *, +extern int ext4_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern u32 ext4_dio_alignment(struct inode *inode); -extern int ext4_getattr(struct user_namespace *, const struct path *, +extern int ext4_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); -extern int ext4_file_getattr(struct user_namespace *, const struct path *, +extern int ext4_file_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int ext4_sync_inode(handle_t *, struct inode *); extern void ext4_dirty_inode(struct inode *, int); @@ -3024,7 +3024,7 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode, /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); -int ext4_fileattr_set(struct user_namespace *mnt_userns, +int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 63f9bb6e8851..157663031f8c 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -921,7 +921,7 @@ static int ext4_xattr_credits_for_new_inode(struct inode *dir, mode_t mode, * For other inodes, search forward from the parent directory's block * group to find a free inode. */ -struct inode *__ext4_new_inode(struct user_namespace *mnt_userns, +struct inode *__ext4_new_inode(struct mnt_idmap *idmap, handle_t *handle, struct inode *dir, umode_t mode, const struct qstr *qstr, __u32 goal, uid_t *owner, __u32 i_flags, @@ -972,10 +972,10 @@ struct inode *__ext4_new_inode(struct user_namespace *mnt_userns, i_gid_write(inode, owner[1]); } else if (test_opt(sb, GRPID)) { inode->i_mode = mode; - inode_fsuid_set(inode, mnt_userns); + inode_fsuid_set(inode, idmap); inode->i_gid = dir->i_gid; } else - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); if (ext4_has_feature_project(sb) && ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9d9f414f99fe..b936ee3af51e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1136,7 +1136,8 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, for (i = 0; i < nr_wait; i++) { int err2; - err2 = fscrypt_decrypt_pagecache_blocks(page, blocksize, + err2 = fscrypt_decrypt_pagecache_blocks(page_folio(page), + blocksize, bh_offset(wait[i])); if (err2) { clear_buffer_uptodate(wait[i]); @@ -3858,7 +3859,8 @@ static int __ext4_block_zero_page_range(handle_t *handle, if (fscrypt_inode_uses_fs_layer_crypto(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); - err = fscrypt_decrypt_pagecache_blocks(page, blocksize, + err = fscrypt_decrypt_pagecache_blocks(page_folio(page), + blocksize, bh_offset(bh)); if (err) { clear_buffer_uptodate(bh); @@ -5434,7 +5436,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) * * Called with inode->i_rwsem down. */ -int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -5454,7 +5456,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, ATTR_GID | ATTR_TIMES_SET)))) return -EPERM; - error = setattr_prepare(mnt_userns, dentry, attr); + error = setattr_prepare(idmap, dentry, attr); if (error) return error; @@ -5466,14 +5468,14 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (error) return error; - if (is_quota_modification(mnt_userns, inode, attr)) { + if (is_quota_modification(idmap, inode, attr)) { error = dquot_initialize(inode); if (error) return error; } - if (i_uid_needs_update(mnt_userns, attr, inode) || - i_gid_needs_update(mnt_userns, attr, inode)) { + if (i_uid_needs_update(idmap, attr, inode) || + i_gid_needs_update(idmap, attr, inode)) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, @@ -5490,7 +5492,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, * counts xattr inode references. */ down_read(&EXT4_I(inode)->xattr_sem); - error = dquot_transfer(mnt_userns, inode, attr); + error = dquot_transfer(idmap, inode, attr); up_read(&EXT4_I(inode)->xattr_sem); if (error) { @@ -5499,8 +5501,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } /* Update corresponding info in inode so that everything is in * one transaction */ - i_uid_update(mnt_userns, attr, inode); - i_gid_update(mnt_userns, attr, inode); + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); if (unlikely(error)) { @@ -5630,7 +5632,7 @@ out_mmap_sem: if (!error) { if (inc_ivers) inode_inc_iversion(inode); - setattr_copy(mnt_userns, inode, attr); + setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); } @@ -5642,7 +5644,7 @@ out_mmap_sem: ext4_orphan_del(NULL, inode); if (!error && (ia_valid & ATTR_MODE)) - rc = posix_acl_chmod(mnt_userns, dentry, inode->i_mode); + rc = posix_acl_chmod(idmap, dentry, inode->i_mode); err_out: if (error) @@ -5668,7 +5670,7 @@ u32 ext4_dio_alignment(struct inode *inode) return 1; /* use the iomap defaults */ } -int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ext4_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -5725,18 +5727,18 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, STATX_ATTR_NODUMP | STATX_ATTR_VERITY); - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); return 0; } -int ext4_file_getattr(struct user_namespace *mnt_userns, +int ext4_file_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); u64 delalloc_blocks; - ext4_getattr(mnt_userns, path, stat, request_mask, query_flags); + ext4_getattr(idmap, path, stat, request_mask, query_flags); /* * If there is inline data in the inode, the inode will normally not diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 8067ccda34e4..b0dc7212694e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -358,12 +358,12 @@ void ext4_reset_inode_seed(struct inode *inode) * important fields of the inodes. * * @sb: the super block of the filesystem - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: the inode to swap with EXT4_BOOT_LOADER_INO * */ static long swap_inode_boot_loader(struct super_block *sb, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *inode) { handle_t *handle; @@ -393,7 +393,7 @@ static long swap_inode_boot_loader(struct super_block *sb, } if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || - !inode_owner_or_capable(mnt_userns, inode) || + !inode_owner_or_capable(idmap, inode) || !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto journal_err_out; @@ -979,7 +979,7 @@ int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int ext4_fileattr_set(struct user_namespace *mnt_userns, +int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -1217,7 +1217,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; - struct user_namespace *mnt_userns = file_mnt_user_ns(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); ext4_debug("cmd = %u, arg = %lu\n", cmd, arg); @@ -1234,7 +1234,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) __u32 generation; int err; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ext4_has_metadata_csum(inode->i_sb)) { @@ -1376,7 +1376,7 @@ mext_out: case EXT4_IOC_MIGRATE: { int err; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); @@ -1398,7 +1398,7 @@ mext_out: case EXT4_IOC_ALLOC_DA_BLKS: { int err; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); @@ -1417,7 +1417,7 @@ mext_out: err = mnt_want_write_file(filp); if (err) return err; - err = swap_inode_boot_loader(sb, mnt_userns, inode); + err = swap_inode_boot_loader(sb, idmap, inode); mnt_drop_write_file(filp); return err; } @@ -1542,7 +1542,7 @@ resizefs_out: case EXT4_IOC_CLEAR_ES_CACHE: { - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ext4_clear_inode_es(inode); return 0; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index dd28453d6ea3..d10a508d95cd 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2792,7 +2792,7 @@ static int ext4_add_nondir(handle_t *handle, * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir, +static int ext4_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { handle_t *handle; @@ -2806,7 +2806,7 @@ static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir, credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: - inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name, + inode = ext4_new_inode_start_handle(idmap, dir, mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); handle = ext4_journal_current_handle(); err = PTR_ERR(inode); @@ -2827,7 +2827,7 @@ retry: return err; } -static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int ext4_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { handle_t *handle; @@ -2841,7 +2841,7 @@ static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir, credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: - inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name, + inode = ext4_new_inode_start_handle(idmap, dir, mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); handle = ext4_journal_current_handle(); err = PTR_ERR(inode); @@ -2861,7 +2861,7 @@ retry: return err; } -static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int ext4_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { handle_t *handle; @@ -2873,7 +2873,7 @@ static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return err; retry: - inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, + inode = ext4_new_inode_start_handle(idmap, dir, mode, NULL, 0, NULL, EXT4_HT_DIR, EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) + @@ -2972,7 +2972,7 @@ out: return err; } -static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { handle_t *handle; @@ -2989,7 +2989,7 @@ static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir, credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: - inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFDIR | mode, + inode = ext4_new_inode_start_handle(idmap, dir, S_IFDIR | mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); handle = ext4_journal_current_handle(); @@ -3339,7 +3339,7 @@ out: return err; } -static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int ext4_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { handle_t *handle; @@ -3370,7 +3370,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; retry: - inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO, + inode = ext4_new_inode_start_handle(idmap, dir, S_IFLNK|S_IRWXUGO, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); handle = ext4_journal_current_handle(); @@ -3720,7 +3720,7 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent) } } -static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns, +static struct inode *ext4_whiteout_for_rename(struct mnt_idmap *idmap, struct ext4_renament *ent, int credits, handle_t **h) { @@ -3735,7 +3735,7 @@ static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns, credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) + EXT4_XATTR_TRANS_BLOCKS + 4); retry: - wh = ext4_new_inode_start_handle(mnt_userns, ent->dir, + wh = ext4_new_inode_start_handle(idmap, ent->dir, S_IFCHR | WHITEOUT_MODE, &ent->dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -3763,7 +3763,7 @@ retry: * while new_{dentry,inode) refers to the destination dentry/inode * This comes from rename(const char *oldpath, const char *newpath) */ -static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -3851,7 +3851,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, goto release_bh; } } else { - whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle); + whiteout = ext4_whiteout_for_rename(idmap, &old, credits, &handle); if (IS_ERR(whiteout)) { retval = PTR_ERR(whiteout); goto release_bh; @@ -4158,7 +4158,7 @@ end_rename: return retval; } -static int ext4_rename2(struct user_namespace *mnt_userns, +static int ext4_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -4181,7 +4181,7 @@ static int ext4_rename2(struct user_namespace *mnt_userns, new_dir, new_dentry); } - return ext4_rename(mnt_userns, old_dir, old_dentry, new_dir, new_dentry, flags); + return ext4_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags); } /* diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index d5266932ce6c..c61dc8a7c014 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -211,8 +211,7 @@ static void ext4_set_bio_post_read_ctx(struct bio *bio, static inline loff_t ext4_readpage_limit(struct inode *inode) { - if (IS_ENABLED(CONFIG_FS_VERITY) && - (IS_VERITY(inode) || ext4_verity_in_progress(inode))) + if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) return inode->i_sb->s_maxbytes; return i_size_read(inode); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 260c1b3e3ef2..2ae46d11aa30 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2635,7 +2635,6 @@ static int ext4_check_test_dummy_encryption(const struct fs_context *fc, { const struct ext4_fs_context *ctx = fc->fs_private; const struct ext4_sb_info *sbi = EXT4_SB(sb); - int err; if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy)) return 0; @@ -2668,17 +2667,7 @@ static int ext4_check_test_dummy_encryption(const struct fs_context *fc, "Conflicting test_dummy_encryption options"); return -EINVAL; } - /* - * fscrypt_add_test_dummy_key() technically changes the super_block, so - * technically it should be delayed until ext4_apply_options() like the - * other changes. But since we never get here for remounts (see above), - * and this is the last chance to report errors, we do it here. - */ - err = fscrypt_add_test_dummy_key(sb, &ctx->dummy_enc_policy); - if (err) - ext4_msg(NULL, KERN_WARNING, - "Error adding test dummy encryption key [%d]", err); - return err; + return 0; } static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx, @@ -5336,11 +5325,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) } } - if (ext4_has_feature_verity(sb) && sb->s_blocksize != PAGE_SIZE) { - ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs-verity"); - goto failed_mount_wq; - } - /* * Get the # of file system overhead blocks from the * superblock if present. diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index 3d3ed3c38f56..75bf1f88843c 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -55,12 +55,12 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, return paddr; } -static int ext4_encrypted_symlink_getattr(struct user_namespace *mnt_userns, +static int ext4_encrypted_symlink_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - ext4_getattr(mnt_userns, path, stat, request_mask, query_flags); + ext4_getattr(idmap, path, stat, request_mask, query_flags); return fscrypt_symlink_getattr(path, stat); } diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 30e3b65798b5..e4da1704438e 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -381,11 +381,11 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode, } static int ext4_write_merkle_tree_block(struct inode *inode, const void *buf, - u64 index, int log_blocksize) + u64 pos, unsigned int size) { - loff_t pos = ext4_verity_metadata_pos(inode) + (index << log_blocksize); + pos += ext4_verity_metadata_pos(inode); - return pagecache_write(inode, buf, 1 << log_blocksize, pos); + return pagecache_write(inode, buf, size, pos); } const struct fsverity_operations ext4_verityops = { diff --git a/fs/ext4/xattr_hurd.c b/fs/ext4/xattr_hurd.c index c78df5790377..8a5842e4cd95 100644 --- a/fs/ext4/xattr_hurd.c +++ b/fs/ext4/xattr_hurd.c @@ -32,7 +32,7 @@ ext4_xattr_hurd_get(const struct xattr_handler *handler, static int ext4_xattr_hurd_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 8213f66f7b2d..776cf11d24ca 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -23,7 +23,7 @@ ext4_xattr_security_get(const struct xattr_handler *handler, static int ext4_xattr_security_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c index 7c21ffb26d25..9811eb0ab276 100644 --- a/fs/ext4/xattr_trusted.c +++ b/fs/ext4/xattr_trusted.c @@ -30,7 +30,7 @@ ext4_xattr_trusted_get(const struct xattr_handler *handler, static int ext4_xattr_trusted_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c index 2fe7ff0a479c..4b70bf4e7626 100644 --- a/fs/ext4/xattr_user.c +++ b/fs/ext4/xattr_user.c @@ -31,7 +31,7 @@ ext4_xattr_user_get(const struct xattr_handler *handler, static int ext4_xattr_user_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index c1c74aa658ae..ec2aeccb69a3 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -204,7 +204,7 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type, bool rcu) return __f2fs_get_acl(inode, type, NULL); } -static int f2fs_acl_update_mode(struct user_namespace *mnt_userns, +static int f2fs_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { @@ -219,14 +219,14 @@ static int f2fs_acl_update_mode(struct user_namespace *mnt_userns, return error; if (error == 0) *acl = NULL; - if (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) && - !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) + if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) && + !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) mode &= ~S_ISGID; *mode_p = mode; return 0; } -static int __f2fs_set_acl(struct user_namespace *mnt_userns, +static int __f2fs_set_acl(struct mnt_idmap *idmap, struct inode *inode, int type, struct posix_acl *acl, struct page *ipage) { @@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct user_namespace *mnt_userns, case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl && !ipage) { - error = f2fs_acl_update_mode(mnt_userns, inode, + error = f2fs_acl_update_mode(idmap, inode, &mode, &acl); if (error) return error; @@ -276,7 +276,7 @@ static int __f2fs_set_acl(struct user_namespace *mnt_userns, return error; } -int f2fs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int f2fs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct inode *inode = d_inode(dentry); @@ -284,7 +284,7 @@ int f2fs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; - return __f2fs_set_acl(mnt_userns, inode, type, acl, NULL); + return __f2fs_set_acl(idmap, inode, type, acl, NULL); } /* diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index ea2bbb3f264b..94ebfbfbdc6f 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -34,7 +34,7 @@ struct f2fs_acl_header { #ifdef CONFIG_F2FS_FS_POSIX_ACL extern struct posix_acl *f2fs_get_acl(struct inode *, int, bool); -extern int f2fs_set_acl(struct user_namespace *, struct dentry *, +extern int f2fs_set_acl(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); extern int f2fs_init_acl(struct inode *, struct inode *, struct page *, struct page *); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 97e816590cd9..8630df80fedb 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2053,8 +2053,7 @@ out: static inline loff_t f2fs_readpage_limit(struct inode *inode) { - if (IS_ENABLED(CONFIG_FS_VERITY) && - (IS_VERITY(inode) || f2fs_verity_in_progress(inode))) + if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) return inode->i_sb->s_maxbytes; return i_size_read(inode); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e8953c3dc81a..9a3ffa39ad30 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3469,15 +3469,15 @@ void f2fs_truncate_data_blocks(struct dnode_of_data *dn); int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); -int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); -int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); int f2fs_precache_extents(struct inode *inode); int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int f2fs_fileattr_set(struct user_namespace *mnt_userns, +int f2fs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -3505,7 +3505,7 @@ void f2fs_handle_failed_inode(struct inode *inode); int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); -int f2fs_get_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct inode **new_inode); /* diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ecbc8c135b49..b90617639743 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -837,7 +837,7 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw) return false; } -int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -892,7 +892,7 @@ int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, STATX_ATTR_NODUMP | STATX_ATTR_VERITY); - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); /* we need to show initial sectors used for inline_data/dentries */ if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) || @@ -903,13 +903,13 @@ int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, } #ifdef CONFIG_F2FS_FS_POSIX_ACL -static void __setattr_copy(struct user_namespace *mnt_userns, +static void __setattr_copy(struct mnt_idmap *idmap, struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; - i_uid_update(mnt_userns, attr, inode); - i_gid_update(mnt_userns, attr, inode); + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_ATIME) inode->i_atime = attr->ia_atime; if (ia_valid & ATTR_MTIME) @@ -918,10 +918,10 @@ static void __setattr_copy(struct user_namespace *mnt_userns, inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); if (!vfsgid_in_group_p(vfsgid) && - !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) mode &= ~S_ISGID; set_acl_inode(inode, mode); } @@ -930,7 +930,7 @@ static void __setattr_copy(struct user_namespace *mnt_userns, #define __setattr_copy setattr_copy #endif -int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -951,7 +951,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, !f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; - err = setattr_prepare(mnt_userns, dentry, attr); + err = setattr_prepare(idmap, dentry, attr); if (err) return err; @@ -963,15 +963,15 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (err) return err; - if (is_quota_modification(mnt_userns, inode, attr)) { + if (is_quota_modification(idmap, inode, attr)) { err = f2fs_dquot_initialize(inode); if (err) return err; } - if (i_uid_needs_update(mnt_userns, attr, inode) || - i_gid_needs_update(mnt_userns, attr, inode)) { + if (i_uid_needs_update(idmap, attr, inode) || + i_gid_needs_update(idmap, attr, inode)) { f2fs_lock_op(F2FS_I_SB(inode)); - err = dquot_transfer(mnt_userns, inode, attr); + err = dquot_transfer(idmap, inode, attr); if (err) { set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); @@ -982,8 +982,8 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, * update uid/gid under lock_op(), so that dquot and inode can * be updated atomically. */ - i_uid_update(mnt_userns, attr, inode); - i_gid_update(mnt_userns, attr, inode); + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); f2fs_mark_inode_dirty_sync(inode, true); f2fs_unlock_op(F2FS_I_SB(inode)); } @@ -1023,10 +1023,10 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, spin_unlock(&F2FS_I(inode)->i_size_lock); } - __setattr_copy(mnt_userns, inode, attr); + __setattr_copy(idmap, inode, attr); if (attr->ia_valid & ATTR_MODE) { - err = posix_acl_chmod(mnt_userns, dentry, f2fs_get_inode_mode(inode)); + err = posix_acl_chmod(idmap, dentry, f2fs_get_inode_mode(inode)); if (is_inode_flag_set(inode, FI_ACL_MODE)) { if (!err) @@ -2038,14 +2038,14 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate) { struct inode *inode = file_inode(filp); - struct user_namespace *mnt_userns = file_mnt_user_ns(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inode *pinode; loff_t isize; int ret; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) @@ -2095,7 +2095,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate) goto out; } - ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode); + ret = f2fs_get_tmpfile(idmap, pinode, &fi->cow_inode); iput(pinode); if (ret) { f2fs_up_write(&fi->i_gc_rwsem[WRITE]); @@ -2135,10 +2135,10 @@ out: static int f2fs_ioc_commit_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); - struct user_namespace *mnt_userns = file_mnt_user_ns(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); int ret; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -2167,10 +2167,10 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) static int f2fs_ioc_abort_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); - struct user_namespace *mnt_userns = file_mnt_user_ns(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); int ret; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -3090,7 +3090,7 @@ int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int f2fs_fileattr_set(struct user_namespace *mnt_userns, +int f2fs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 6032589099ce..d8e01bbbf27f 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -202,7 +202,7 @@ static void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode, file_set_hot(inode); } -static struct inode *f2fs_new_inode(struct user_namespace *mnt_userns, +static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, struct inode *dir, umode_t mode, const char *name) { @@ -225,7 +225,7 @@ static struct inode *f2fs_new_inode(struct user_namespace *mnt_userns, nid_free = true; - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); inode->i_ino = ino; inode->i_blocks = 0; @@ -246,7 +246,7 @@ static struct inode *f2fs_new_inode(struct user_namespace *mnt_userns, (F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL)) F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid; else - F2FS_I(inode)->i_projid = make_kprojid(mnt_userns, + F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns, F2FS_DEF_PROJID); err = fscrypt_prepare_new_inode(dir, inode, &encrypt); @@ -333,7 +333,7 @@ fail_drop: return ERR_PTR(err); } -static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int f2fs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); @@ -350,7 +350,7 @@ static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - inode = f2fs_new_inode(mnt_userns, dir, mode, dentry->d_name.name); + inode = f2fs_new_inode(idmap, dir, mode, dentry->d_name.name); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -659,7 +659,7 @@ static const char *f2fs_get_link(struct dentry *dentry, return link; } -static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int f2fs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); @@ -682,7 +682,7 @@ static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - inode = f2fs_new_inode(mnt_userns, dir, S_IFLNK | S_IRWXUGO, NULL); + inode = f2fs_new_inode(idmap, dir, S_IFLNK | S_IRWXUGO, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -739,7 +739,7 @@ out_free_encrypted_link: return err; } -static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); @@ -753,7 +753,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - inode = f2fs_new_inode(mnt_userns, dir, S_IFDIR | mode, NULL); + inode = f2fs_new_inode(idmap, dir, S_IFDIR | mode, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -794,7 +794,7 @@ static int f2fs_rmdir(struct inode *dir, struct dentry *dentry) return -ENOTEMPTY; } -static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int f2fs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); @@ -810,7 +810,7 @@ static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - inode = f2fs_new_inode(mnt_userns, dir, mode, NULL); + inode = f2fs_new_inode(idmap, dir, mode, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -837,7 +837,7 @@ out: return err; } -static int __f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode, bool is_whiteout, struct inode **new_inode) { @@ -849,7 +849,7 @@ static int __f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - inode = f2fs_new_inode(mnt_userns, dir, mode, NULL); + inode = f2fs_new_inode(idmap, dir, mode, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -907,7 +907,7 @@ out: return err; } -static int f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); @@ -918,28 +918,28 @@ static int f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = __f2fs_tmpfile(mnt_userns, dir, file, mode, false, NULL); + err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL); return finish_open_simple(file, err); } -static int f2fs_create_whiteout(struct user_namespace *mnt_userns, +static int f2fs_create_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct inode **whiteout) { if (unlikely(f2fs_cp_error(F2FS_I_SB(dir)))) return -EIO; - return __f2fs_tmpfile(mnt_userns, dir, NULL, + return __f2fs_tmpfile(idmap, dir, NULL, S_IFCHR | WHITEOUT_MODE, true, whiteout); } -int f2fs_get_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct inode **new_inode) { - return __f2fs_tmpfile(mnt_userns, dir, NULL, S_IFREG, false, new_inode); + return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, false, new_inode); } -static int f2fs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -979,7 +979,7 @@ static int f2fs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, } if (flags & RENAME_WHITEOUT) { - err = f2fs_create_whiteout(mnt_userns, old_dir, &whiteout); + err = f2fs_create_whiteout(idmap, old_dir, &whiteout); if (err) return err; } @@ -1295,7 +1295,7 @@ out: return err; } -static int f2fs_rename2(struct user_namespace *mnt_userns, +static int f2fs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -1318,7 +1318,7 @@ static int f2fs_rename2(struct user_namespace *mnt_userns, * VFS has already handled the new dentry existence case, * here, we just deal with "RENAME_NOREPLACE" as regular rename. */ - return f2fs_rename(mnt_userns, old_dir, old_dentry, + return f2fs_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags); } @@ -1342,12 +1342,12 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry, return target; } -static int f2fs_encrypted_symlink_getattr(struct user_namespace *mnt_userns, +static int f2fs_encrypted_symlink_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - f2fs_getattr(mnt_userns, path, stat, request_mask, query_flags); + f2fs_getattr(idmap, path, stat, request_mask, query_flags); return fscrypt_symlink_getattr(path, stat); } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 77fd453949b1..dfd41908b12d 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -258,15 +258,15 @@ static int recover_quota_data(struct inode *inode, struct page *page) attr.ia_vfsuid = VFSUIDT_INIT(make_kuid(inode->i_sb->s_user_ns, i_uid)); attr.ia_vfsgid = VFSGIDT_INIT(make_kgid(inode->i_sb->s_user_ns, i_gid)); - if (!vfsuid_eq(attr.ia_vfsuid, i_uid_into_vfsuid(&init_user_ns, inode))) + if (!vfsuid_eq(attr.ia_vfsuid, i_uid_into_vfsuid(&nop_mnt_idmap, inode))) attr.ia_valid |= ATTR_UID; - if (!vfsgid_eq(attr.ia_vfsgid, i_gid_into_vfsgid(&init_user_ns, inode))) + if (!vfsgid_eq(attr.ia_vfsgid, i_gid_into_vfsgid(&nop_mnt_idmap, inode))) attr.ia_valid |= ATTR_GID; if (!attr.ia_valid) return 0; - err = dquot_transfer(&init_user_ns, inode, &attr); + err = dquot_transfer(&nop_mnt_idmap, inode, &attr); if (err) set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); return err; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1f812b9ce985..64d3556d61a5 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -540,12 +540,6 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb, opt, err); return -EINVAL; } - err = fscrypt_add_test_dummy_key(sb, policy); - if (err) { - f2fs_warn(sbi, "Error adding test dummy encryption key [%d]", - err); - return err; - } f2fs_warn(sbi, "Test dummy encryption mode enabled"); return 0; } diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index c352fff88a5e..f320ed8172ec 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -276,11 +276,11 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode, } static int f2fs_write_merkle_tree_block(struct inode *inode, const void *buf, - u64 index, int log_blocksize) + u64 pos, unsigned int size) { - loff_t pos = f2fs_verity_metadata_pos(inode) + (index << log_blocksize); + pos += f2fs_verity_metadata_pos(inode); - return pagecache_write(inode, buf, 1 << log_blocksize, pos); + return pagecache_write(inode, buf, size, pos); } const struct fsverity_operations f2fs_verityops = { diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index dc2e8637189e..d92edbbdc30e 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -65,7 +65,7 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler, } static int f2fs_xattr_generic_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -109,7 +109,7 @@ static int f2fs_xattr_advise_get(const struct xattr_handler *handler, } static int f2fs_xattr_advise_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -117,7 +117,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, unsigned char old_advise = F2FS_I(inode)->i_advise; unsigned char new_advise; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) return -EPERM; if (value == NULL) return -EINVAL; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index a415c02ede39..e3b690b48e3e 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -398,10 +398,10 @@ extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); extern const struct file_operations fat_file_operations; extern const struct inode_operations fat_file_inode_operations; -extern int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void fat_truncate_blocks(struct inode *inode, loff_t offset); -extern int fat_getattr(struct user_namespace *mnt_userns, +extern int fat_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); extern int fat_file_fsync(struct file *file, loff_t start, loff_t end, diff --git a/fs/fat/file.c b/fs/fat/file.c index 8a6b493b5b5f..795a4fad5c40 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -90,13 +90,13 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) * out the RO attribute for checking by the security * module, just because it maps to a file mode. */ - err = security_inode_setattr(file_mnt_user_ns(file), + err = security_inode_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); if (err) goto out_unlock_inode; /* This MUST be done before doing anything irreversible... */ - err = fat_setattr(file_mnt_user_ns(file), file->f_path.dentry, &ia); + err = fat_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); if (err) goto out_unlock_inode; @@ -395,13 +395,13 @@ void fat_truncate_blocks(struct inode *inode, loff_t offset) fat_flush_inodes(inode->i_sb, inode, NULL); } -int fat_getattr(struct user_namespace *mnt_userns, const struct path *path, +int fat_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); stat->blksize = sbi->cluster_size; if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) { @@ -456,14 +456,14 @@ static int fat_sanitize_mode(const struct msdos_sb_info *sbi, return 0; } -static int fat_allow_set_time(struct user_namespace *mnt_userns, +static int fat_allow_set_time(struct mnt_idmap *idmap, struct msdos_sb_info *sbi, struct inode *inode) { umode_t allow_utime = sbi->options.allow_utime; - if (!vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode), + if (!vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) { - if (vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode))) + if (vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode))) allow_utime >>= 3; if (allow_utime & MAY_WRITE) return 1; @@ -477,7 +477,7 @@ static int fat_allow_set_time(struct user_namespace *mnt_userns, /* valid file mode bits */ #define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO) -int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); @@ -488,11 +488,11 @@ int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, /* Check for setting the inode time. */ ia_valid = attr->ia_valid; if (ia_valid & TIMES_SET_FLAGS) { - if (fat_allow_set_time(mnt_userns, sbi, inode)) + if (fat_allow_set_time(idmap, sbi, inode)) attr->ia_valid &= ~TIMES_SET_FLAGS; } - error = setattr_prepare(mnt_userns, dentry, attr); + error = setattr_prepare(idmap, dentry, attr); attr->ia_valid = ia_valid; if (error) { if (sbi->options.quiet) @@ -518,10 +518,10 @@ int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } if (((attr->ia_valid & ATTR_UID) && - (!uid_eq(from_vfsuid(mnt_userns, i_user_ns(inode), attr->ia_vfsuid), + (!uid_eq(from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid), sbi->options.fs_uid))) || ((attr->ia_valid & ATTR_GID) && - (!gid_eq(from_vfsgid(mnt_userns, i_user_ns(inode), attr->ia_vfsgid), + (!gid_eq(from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid), sbi->options.fs_gid))) || ((attr->ia_valid & ATTR_MODE) && (attr->ia_mode & ~FAT_VALID_MODE))) @@ -564,7 +564,7 @@ int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, fat_truncate_time(inode, &attr->ia_mtime, S_MTIME); attr->ia_valid &= ~(ATTR_ATIME|ATTR_CTIME|ATTR_MTIME); - setattr_copy(mnt_userns, inode, attr); + setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); out: return error; diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index efba301d68ae..2116c486843b 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -261,7 +261,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, } /***** Create a file */ -static int msdos_create(struct user_namespace *mnt_userns, struct inode *dir, +static int msdos_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; @@ -339,7 +339,7 @@ out: } /***** Make a directory */ -static int msdos_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int msdos_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; @@ -594,7 +594,7 @@ error_inode: } /***** Rename, a wrapper for rename_same_dir & rename_diff_dir */ -static int msdos_rename(struct user_namespace *mnt_userns, +static int msdos_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 21620054e1c4..fceda1de4805 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -756,7 +756,7 @@ error: return ERR_PTR(err); } -static int vfat_create(struct user_namespace *mnt_userns, struct inode *dir, +static int vfat_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; @@ -844,7 +844,7 @@ out: return err; } -static int vfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int vfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; @@ -1158,7 +1158,7 @@ error_exchange: goto out; } -static int vfat_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, +static int vfat_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/fcntl.c b/fs/fcntl.c index 146c9ab0cd4b..b622be119706 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> @@ -47,7 +48,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) - if (!inode_owner_or_capable(file_mnt_user_ns(filp), inode)) + if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ diff --git a/fs/file_table.c b/fs/file_table.c index dd88701e54a9..372653b92617 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c index ad670369955f..3d192b80a561 100644 --- a/fs/fuse/acl.c +++ b/fs/fuse/acl.c @@ -12,7 +12,7 @@ #include <linux/posix_acl_xattr.h> static struct posix_acl *__fuse_get_acl(struct fuse_conn *fc, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *inode, int type, bool rcu) { int size; @@ -65,7 +65,7 @@ static inline bool fuse_no_acl(const struct fuse_conn *fc, return !fc->posix_acl && (i_user_ns(inode) != &init_user_ns); } -struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *fuse_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type) { struct inode *inode = d_inode(dentry); @@ -74,7 +74,7 @@ struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns, if (fuse_no_acl(fc, inode)) return ERR_PTR(-EOPNOTSUPP); - return __fuse_get_acl(fc, mnt_userns, inode, type, false); + return __fuse_get_acl(fc, idmap, inode, type, false); } struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu) @@ -91,10 +91,10 @@ struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu) if (!fc->posix_acl) return NULL; - return __fuse_get_acl(fc, &init_user_ns, inode, type, rcu); + return __fuse_get_acl(fc, &nop_mnt_idmap, inode, type, rcu); } -int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int fuse_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct inode *inode = d_inode(dentry); @@ -146,8 +146,8 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, * be stripped. */ if (fc->posix_acl && - !vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) && - !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) + !vfsgid_in_group_p(i_gid_into_vfsgid(&nop_mnt_idmap, inode)) && + !capable_wrt_inode_uidgid(&nop_mnt_idmap, inode, CAP_FSETID)) extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID; ret = fuse_setxattr(inode, name, value, size, 0, extra_flags); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 2725fb54328e..cd1eae61e84c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -645,7 +645,7 @@ out_err: return err; } -static int fuse_mknod(struct user_namespace *, struct inode *, struct dentry *, +static int fuse_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct file *file, unsigned flags, @@ -686,7 +686,7 @@ out_dput: return err; mknod: - err = fuse_mknod(&init_user_ns, dir, entry, mode, 0); + err = fuse_mknod(&nop_mnt_idmap, dir, entry, mode, 0); if (err) goto out_dput; no_open: @@ -773,7 +773,7 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, return err; } -static int fuse_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int fuse_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *entry, umode_t mode, dev_t rdev) { struct fuse_mknod_in inarg; @@ -796,13 +796,13 @@ static int fuse_mknod(struct user_namespace *mnt_userns, struct inode *dir, return create_new_entry(fm, &args, dir, entry, mode); } -static int fuse_create(struct user_namespace *mnt_userns, struct inode *dir, +static int fuse_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *entry, umode_t mode, bool excl) { - return fuse_mknod(&init_user_ns, dir, entry, mode, 0); + return fuse_mknod(&nop_mnt_idmap, dir, entry, mode, 0); } -static int fuse_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int fuse_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct fuse_conn *fc = get_fuse_conn(dir); @@ -819,7 +819,7 @@ static int fuse_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return err; } -static int fuse_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int fuse_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *entry, umode_t mode) { struct fuse_mkdir_in inarg; @@ -841,7 +841,7 @@ static int fuse_mkdir(struct user_namespace *mnt_userns, struct inode *dir, return create_new_entry(fm, &args, dir, entry, S_IFDIR); } -static int fuse_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *entry, const char *link) { struct fuse_mount *fm = get_fuse_mount(dir); @@ -998,7 +998,7 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent, return err; } -static int fuse_rename2(struct user_namespace *mnt_userns, struct inode *olddir, +static int fuse_rename2(struct mnt_idmap *idmap, struct inode *olddir, struct dentry *oldent, struct inode *newdir, struct dentry *newent, unsigned int flags) { @@ -1156,7 +1156,7 @@ static int fuse_update_get_attr(struct inode *inode, struct file *file, forget_all_cached_acls(inode); err = fuse_do_getattr(inode, stat, file); } else if (stat) { - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->mode = fi->orig_i_mode; stat->ino = fi->orig_ino; } @@ -1326,7 +1326,7 @@ static int fuse_perm_getattr(struct inode *inode, int mask) * access request is sent. Execute permission is still checked * locally based on file mode. */ -static int fuse_permission(struct user_namespace *mnt_userns, +static int fuse_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct fuse_conn *fc = get_fuse_conn(inode); @@ -1358,7 +1358,7 @@ static int fuse_permission(struct user_namespace *mnt_userns, } if (fc->default_permissions) { - err = generic_permission(&init_user_ns, inode, mask); + err = generic_permission(&nop_mnt_idmap, inode, mask); /* If permission is denied, try to refresh file attributes. This is also needed, because the root @@ -1366,7 +1366,7 @@ static int fuse_permission(struct user_namespace *mnt_userns, if (err == -EACCES && !refreshed) { err = fuse_perm_getattr(inode, mask); if (!err) - err = generic_permission(&init_user_ns, + err = generic_permission(&nop_mnt_idmap, inode, mask); } @@ -1690,7 +1690,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, if (!fc->default_permissions) attr->ia_valid |= ATTR_FORCE; - err = setattr_prepare(&init_user_ns, dentry, attr); + err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err) return err; @@ -1837,7 +1837,7 @@ error: return err; } -static int fuse_setattr(struct user_namespace *mnt_userns, struct dentry *entry, +static int fuse_setattr(struct mnt_idmap *idmap, struct dentry *entry, struct iattr *attr) { struct inode *inode = d_inode(entry); @@ -1900,7 +1900,7 @@ static int fuse_setattr(struct user_namespace *mnt_userns, struct dentry *entry, return ret; } -static int fuse_getattr(struct user_namespace *mnt_userns, +static int fuse_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 875314ee6f59..82710d103556 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -18,6 +18,7 @@ #include <linux/falloc.h> #include <linux/uio.h> #include <linux/fs.h> +#include <linux/filelock.h> static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, unsigned int open_flags, int opcode, @@ -1313,7 +1314,8 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) return err; if (fc->handle_killpriv_v2 && - setattr_should_drop_suidgid(&init_user_ns, file_inode(file))) { + setattr_should_drop_suidgid(&nop_mnt_idmap, + file_inode(file))) { goto writethrough; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 46797a171a84..9b5058cf5bc3 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1267,9 +1267,9 @@ extern const struct xattr_handler *fuse_xattr_handlers[]; struct posix_acl; struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu); -struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *fuse_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type); -int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int fuse_set_acl(struct mnt_idmap *, struct dentry *dentry, struct posix_acl *acl, int type); /* readdir.c */ @@ -1309,7 +1309,7 @@ long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long fuse_file_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int fuse_fileattr_set(struct user_namespace *mnt_userns, +int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); /* file.c */ diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c index fcce94ace2c2..e50a18ee6cc6 100644 --- a/fs/fuse/ioctl.c +++ b/fs/fuse/ioctl.c @@ -467,7 +467,7 @@ cleanup: return err; } -int fuse_fileattr_set(struct user_namespace *mnt_userns, +int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 9fe571ab569e..49c01559580f 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -189,7 +189,7 @@ static int fuse_xattr_get(const struct xattr_handler *handler, } static int fuse_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 3dcde4912413..a392aa0f041d 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -109,7 +109,7 @@ out: return error; } -int gfs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int gfs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct inode *inode = d_inode(dentry); @@ -135,7 +135,7 @@ int gfs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - ret = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl); + ret = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (ret) goto unlock; } diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index b8de8c148f5c..d4deb2b19959 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -13,7 +13,7 @@ extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu); extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int gfs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int gfs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); #endif /* __ACL_DOT_H__ */ diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index eea5be4fbf0e..300844f50dcd 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/mount.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/gfs2_ondisk.h> #include <linux/falloc.h> #include <linux/swap.h> @@ -235,7 +236,7 @@ static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask) goto out; if (!IS_IMMUTABLE(inode)) { - error = gfs2_permission(&init_user_ns, inode, MAY_WRITE); + error = gfs2_permission(&nop_mnt_idmap, inode, MAY_WRITE); if (error) goto out; } @@ -273,7 +274,7 @@ out: return error; } -int gfs2_fileattr_set(struct user_namespace *mnt_userns, +int gfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 614db3055c02..713efa3bb732 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -320,7 +320,7 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, } if (!is_root) { - error = gfs2_permission(&init_user_ns, dir, MAY_EXEC); + error = gfs2_permission(&nop_mnt_idmap, dir, MAY_EXEC); if (error) goto out; } @@ -350,7 +350,7 @@ static int create_ok(struct gfs2_inode *dip, const struct qstr *name, { int error; - error = gfs2_permission(&init_user_ns, &dip->i_inode, + error = gfs2_permission(&nop_mnt_idmap, &dip->i_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -843,7 +843,7 @@ fail: /** * gfs2_create - Create a file - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The directory in which to create the file * @dentry: The dentry of the new file * @mode: The mode of the new file @@ -852,7 +852,7 @@ fail: * Returns: errno */ -static int gfs2_create(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl); @@ -960,7 +960,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (inode->i_nlink == 0) goto out_gunlock; - error = gfs2_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); + error = gfs2_permission(&nop_mnt_idmap, dir, MAY_WRITE | MAY_EXEC); if (error) goto out_gunlock; @@ -1078,7 +1078,7 @@ static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, if (IS_APPEND(&dip->i_inode)) return -EPERM; - error = gfs2_permission(&init_user_ns, &dip->i_inode, + error = gfs2_permission(&nop_mnt_idmap, &dip->i_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -1207,7 +1207,7 @@ out_inodes: /** * gfs2_symlink - Create a symlink - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The directory to create the symlink in * @dentry: The dentry to put the symlink in * @symname: The thing which the link points to @@ -1215,7 +1215,7 @@ out_inodes: * Returns: errno */ -static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { unsigned int size; @@ -1229,7 +1229,7 @@ static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, /** * gfs2_mkdir - Make a directory - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The parent directory of the new one * @dentry: The dentry of the new directory * @mode: The mode of the new directory @@ -1237,7 +1237,7 @@ static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, * Returns: errno */ -static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir)); @@ -1246,7 +1246,7 @@ static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, /** * gfs2_mknod - Make a special file - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The directory in which the special file will reside * @dentry: The dentry of the special file * @mode: The mode of the special file @@ -1254,7 +1254,7 @@ static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, * */ -static int gfs2_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0); @@ -1504,7 +1504,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, } } } else { - error = gfs2_permission(&init_user_ns, ndir, + error = gfs2_permission(&nop_mnt_idmap, ndir, MAY_WRITE | MAY_EXEC); if (error) goto out_gunlock; @@ -1541,7 +1541,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, /* Check out the dir to be renamed */ if (dir_rename) { - error = gfs2_permission(&init_user_ns, d_inode(odentry), + error = gfs2_permission(&nop_mnt_idmap, d_inode(odentry), MAY_WRITE); if (error) goto out_gunlock; @@ -1705,13 +1705,13 @@ static int gfs2_exchange(struct inode *odir, struct dentry *odentry, goto out_gunlock; if (S_ISDIR(old_mode)) { - error = gfs2_permission(&init_user_ns, odentry->d_inode, + error = gfs2_permission(&nop_mnt_idmap, odentry->d_inode, MAY_WRITE); if (error) goto out_gunlock; } if (S_ISDIR(new_mode)) { - error = gfs2_permission(&init_user_ns, ndentry->d_inode, + error = gfs2_permission(&nop_mnt_idmap, ndentry->d_inode, MAY_WRITE); if (error) goto out_gunlock; @@ -1766,7 +1766,7 @@ out: return error; } -static int gfs2_rename2(struct user_namespace *mnt_userns, struct inode *odir, +static int gfs2_rename2(struct mnt_idmap *idmap, struct inode *odir, struct dentry *odentry, struct inode *ndir, struct dentry *ndentry, unsigned int flags) { @@ -1841,7 +1841,7 @@ out: /** * gfs2_permission - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: The inode * @mask: The mask to be tested * @@ -1852,7 +1852,7 @@ out: * Returns: errno */ -int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, +int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct gfs2_inode *ip; @@ -1872,7 +1872,7 @@ int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) error = -EPERM; else - error = generic_permission(&init_user_ns, inode, mask); + error = generic_permission(&nop_mnt_idmap, inode, mask); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); @@ -1881,7 +1881,7 @@ int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr) { - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -1966,7 +1966,7 @@ out: /** * gfs2_setattr - Change attributes on an inode - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: The dentry which is changing * @attr: The structure describing the change * @@ -1976,7 +1976,7 @@ out: * Returns: errno */ -static int gfs2_setattr(struct user_namespace *mnt_userns, +static int gfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -1992,11 +1992,11 @@ static int gfs2_setattr(struct user_namespace *mnt_userns, if (error) goto out; - error = may_setattr(&init_user_ns, inode, attr->ia_valid); + error = may_setattr(&nop_mnt_idmap, inode, attr->ia_valid); if (error) goto error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) goto error; @@ -2007,7 +2007,7 @@ static int gfs2_setattr(struct user_namespace *mnt_userns, else { error = gfs2_setattr_simple(inode, attr); if (!error && attr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(&init_user_ns, dentry, + error = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); } @@ -2022,7 +2022,7 @@ out: /** * gfs2_getattr - Read out an inode's attributes - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @path: Object to query * @stat: The inode's stats * @request_mask: Mask of STATX_xxx flags indicating the caller's interests @@ -2037,7 +2037,7 @@ out: * Returns: errno */ -static int gfs2_getattr(struct user_namespace *mnt_userns, +static int gfs2_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -2066,7 +2066,7 @@ static int gfs2_getattr(struct user_namespace *mnt_userns, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (gfs2_holder_initialized(&gh)) gfs2_glock_dq_uninit(&gh); diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 0264d514dda7..c8c5814e7295 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -99,7 +99,7 @@ extern int gfs2_inode_refresh(struct gfs2_inode *ip); extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, int is_root); -extern int gfs2_permission(struct user_namespace *mnt_userns, +extern int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); @@ -111,7 +111,7 @@ extern const struct file_operations gfs2_file_fops_nolock; extern const struct file_operations gfs2_dir_fops_nolock; extern int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa); -extern int gfs2_fileattr_set(struct user_namespace *mnt_userns, +extern int gfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); extern void gfs2_set_inode_flags(struct inode *inode); diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 518c0677e12a..adf6d17cf033 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1225,7 +1225,7 @@ int __gfs2_xattr_set(struct inode *inode, const char *name, } static int gfs2_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c index 2bd54efaf416..6341bb248247 100644 --- a/fs/hfs/attr.c +++ b/fs/hfs/attr.c @@ -121,7 +121,7 @@ static int hfs_xattr_get(const struct xattr_handler *handler, } static int hfs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 527f6e46cbe8..3e1e3dcf0b48 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -189,7 +189,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file) * a directory and return a corresponding inode, given the inode for * the directory and the name (and its length) of the new file. */ -static int hfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int hfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; @@ -219,7 +219,7 @@ static int hfs_create(struct user_namespace *mnt_userns, struct inode *dir, * in a directory, given the inode for the parent directory and the * name (and its length) of the new directory. */ -static int hfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int hfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -280,7 +280,7 @@ static int hfs_remove(struct inode *dir, struct dentry *dentry) * new file/directory. * XXX: how do you handle must_be dir? */ -static int hfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int hfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 68d0305880f7..49d02524e667 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -206,7 +206,7 @@ int hfs_write_begin(struct file *file, struct address_space *mapping, extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t); extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *); extern int hfs_write_inode(struct inode *, struct writeback_control *); -extern int hfs_inode_setattr(struct user_namespace *, struct dentry *, +extern int hfs_inode_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, __be32 log_size, __be32 phys_size, u32 clump_size); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 3a155c1d810e..1f7bd068acf0 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -611,14 +611,14 @@ static int hfs_file_release(struct inode *inode, struct file *file) * correspond to the same HFS file. */ -int hfs_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int hfs_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hfs_sb_info *hsb = HFS_SB(inode->i_sb); int error; - error = setattr_prepare(&init_user_ns, dentry, + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); /* basic permission checks */ if (error) return error; @@ -658,7 +658,7 @@ int hfs_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, current_time(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 84714bbccc12..56fb5f1312e7 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -434,7 +434,7 @@ out: return res; } -static int hfsplus_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int hfsplus_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); @@ -476,7 +476,7 @@ out: return res; } -static int hfsplus_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int hfsplus_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); @@ -517,19 +517,19 @@ out: return res; } -static int hfsplus_create(struct user_namespace *mnt_userns, struct inode *dir, +static int hfsplus_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return hfsplus_mknod(&init_user_ns, dir, dentry, mode, 0); + return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); } -static int hfsplus_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int hfsplus_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - return hfsplus_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0); + return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); } -static int hfsplus_rename(struct user_namespace *mnt_userns, +static int hfsplus_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 6aa919e59483..7ededcb720c1 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -481,13 +481,13 @@ void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork); int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd); int hfsplus_cat_write_inode(struct inode *inode); -int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path, +int hfsplus_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int hfsplus_fileattr_set(struct user_namespace *mnt_userns, +int hfsplus_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); /* ioctl.c */ diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 840577a0c1e7..abb91f5fae92 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -246,13 +246,13 @@ static int hfsplus_file_release(struct inode *inode, struct file *file) return 0; } -static int hfsplus_setattr(struct user_namespace *mnt_userns, +static int hfsplus_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -270,13 +270,13 @@ static int hfsplus_setattr(struct user_namespace *mnt_userns, inode->i_mtime = inode->i_ctime = current_time(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } -int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path, +int hfsplus_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -298,7 +298,7 @@ int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->attributes_mask |= STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP; - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; } @@ -390,7 +390,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, return NULL; inode->i_ino = sbi->next_cnid++; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); set_nlink(inode, 1); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); @@ -655,7 +655,7 @@ int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int hfsplus_fileattr_set(struct user_namespace *mnt_userns, +int hfsplus_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 49891b12c415..5b476f57eb17 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -857,7 +857,7 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler, } static int hfsplus_osx_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c index c1c7a16cbf21..90f68ec119cd 100644 --- a/fs/hfsplus/xattr_security.c +++ b/fs/hfsplus/xattr_security.c @@ -23,7 +23,7 @@ static int hfsplus_security_getxattr(const struct xattr_handler *handler, } static int hfsplus_security_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c index e150372ec564..fdbaebc1c49a 100644 --- a/fs/hfsplus/xattr_trusted.c +++ b/fs/hfsplus/xattr_trusted.c @@ -22,7 +22,7 @@ static int hfsplus_trusted_getxattr(const struct xattr_handler *handler, } static int hfsplus_trusted_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c index a6b60b153916..6464b6c3d58d 100644 --- a/fs/hfsplus/xattr_user.c +++ b/fs/hfsplus/xattr_user.c @@ -22,7 +22,7 @@ static int hfsplus_user_getxattr(const struct xattr_handler *handler, } static int hfsplus_user_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 277468783fee..c18bb50c31b6 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -559,7 +559,7 @@ static int read_name(struct inode *ino, char *name) return 0; } -static int hostfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; @@ -658,7 +658,7 @@ static int hostfs_unlink(struct inode *ino, struct dentry *dentry) return err; } -static int hostfs_symlink(struct user_namespace *mnt_userns, struct inode *ino, +static int hostfs_symlink(struct mnt_idmap *idmap, struct inode *ino, struct dentry *dentry, const char *to) { char *file; @@ -671,7 +671,7 @@ static int hostfs_symlink(struct user_namespace *mnt_userns, struct inode *ino, return err; } -static int hostfs_mkdir(struct user_namespace *mnt_userns, struct inode *ino, +static int hostfs_mkdir(struct mnt_idmap *idmap, struct inode *ino, struct dentry *dentry, umode_t mode) { char *file; @@ -696,7 +696,7 @@ static int hostfs_rmdir(struct inode *ino, struct dentry *dentry) return err; } -static int hostfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int hostfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; @@ -734,7 +734,7 @@ static int hostfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, return err; } -static int hostfs_rename2(struct user_namespace *mnt_userns, +static int hostfs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -763,7 +763,7 @@ static int hostfs_rename2(struct user_namespace *mnt_userns, return err; } -static int hostfs_permission(struct user_namespace *mnt_userns, +static int hostfs_permission(struct mnt_idmap *idmap, struct inode *ino, int desired) { char *name; @@ -786,11 +786,11 @@ static int hostfs_permission(struct user_namespace *mnt_userns, err = access_file(name, r, w, x); __putname(name); if (!err) - err = generic_permission(&init_user_ns, ino, desired); + err = generic_permission(&nop_mnt_idmap, ino, desired); return err; } -static int hostfs_setattr(struct user_namespace *mnt_userns, +static int hostfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -800,7 +800,7 @@ static int hostfs_setattr(struct user_namespace *mnt_userns, int fd = HOSTFS_I(inode)->fd; - err = setattr_prepare(&init_user_ns, dentry, attr); + err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err) return err; @@ -857,7 +857,7 @@ static int hostfs_setattr(struct user_namespace *mnt_userns, attr->ia_size != i_size_read(inode)) truncate_setsize(inode, attr->ia_size); - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 167ec6884642..f5a2476c47bf 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -280,7 +280,7 @@ void hpfs_init_inode(struct inode *); void hpfs_read_inode(struct inode *); void hpfs_write_inode(struct inode *); void hpfs_write_inode_nolock(struct inode *); -int hpfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); +int hpfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); void hpfs_write_if_changed(struct inode *); void hpfs_evict_inode(struct inode *); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 82208cc28ebd..e50e92a42432 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -257,7 +257,7 @@ void hpfs_write_inode_nolock(struct inode *i) brelse(bh); } -int hpfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int hpfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -275,7 +275,7 @@ int hpfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) goto out_unlock; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) goto out_unlock; @@ -289,7 +289,7 @@ int hpfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, hpfs_truncate(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); hpfs_write_inode(inode); diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 15fc63276caa..69fb40b2c99a 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -20,7 +20,7 @@ static void hpfs_update_directory_times(struct inode *dir) hpfs_write_inode_nolock(dir); } -static int hpfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; @@ -129,7 +129,7 @@ bail: return err; } -static int hpfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { const unsigned char *name = dentry->d_name.name; @@ -217,7 +217,7 @@ bail: return err; } -static int hpfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int hpfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { const unsigned char *name = dentry->d_name.name; @@ -292,7 +292,7 @@ bail: return err; } -static int hpfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int hpfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symlink) { const unsigned char *name = dentry->d_name.name; @@ -512,7 +512,7 @@ const struct address_space_operations hpfs_symlink_aops = { .read_folio = hpfs_symlink_read_folio }; -static int hpfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int hpfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 790d2727141a..0ce1cc4c2add 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -898,7 +898,7 @@ out: return error; } -static int hugetlbfs_setattr(struct user_namespace *mnt_userns, +static int hugetlbfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -907,7 +907,7 @@ static int hugetlbfs_setattr(struct user_namespace *mnt_userns, unsigned int ia_valid = attr->ia_valid; struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -924,7 +924,7 @@ static int hugetlbfs_setattr(struct user_namespace *mnt_userns, hugetlb_vmtruncate(inode, newsize); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -980,7 +980,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); inode->i_ino = get_next_ino(); - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; @@ -1019,7 +1019,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, /* * File creation. Allocate an inode, and we're done.. */ -static int hugetlbfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; @@ -1033,24 +1033,24 @@ static int hugetlbfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, return 0; } -static int hugetlbfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - int retval = hugetlbfs_mknod(&init_user_ns, dir, dentry, + int retval = hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } -static int hugetlbfs_create(struct user_namespace *mnt_userns, +static int hugetlbfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return hugetlbfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); + return hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); } -static int hugetlbfs_tmpfile(struct user_namespace *mnt_userns, +static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { @@ -1064,7 +1064,7 @@ static int hugetlbfs_tmpfile(struct user_namespace *mnt_userns, return finish_open_simple(file, 0); } -static int hugetlbfs_symlink(struct user_namespace *mnt_userns, +static int hugetlbfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { diff --git a/fs/init.c b/fs/init.c index 5c36adaa9b44..9684406a8416 100644 --- a/fs/init.c +++ b/fs/init.c @@ -157,7 +157,7 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev) mode &= ~current_umask(); error = security_path_mknod(&path, dentry, mode, dev); if (!error) - error = vfs_mknod(mnt_user_ns(path.mnt), path.dentry->d_inode, + error = vfs_mknod(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode, new_decode_dev(dev)); done_path_create(&path, dentry); return error; @@ -167,7 +167,7 @@ int __init init_link(const char *oldname, const char *newname) { struct dentry *new_dentry; struct path old_path, new_path; - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; int error; error = kern_path(oldname, 0, &old_path); @@ -182,14 +182,14 @@ int __init init_link(const char *oldname, const char *newname) error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - mnt_userns = mnt_user_ns(new_path.mnt); - error = may_linkat(mnt_userns, &old_path); + idmap = mnt_idmap(new_path.mnt); + error = may_linkat(idmap, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode, + error = vfs_link(old_path.dentry, idmap, new_path.dentry->d_inode, new_dentry, NULL); out_dput: done_path_create(&new_path, new_dentry); @@ -209,7 +209,7 @@ int __init init_symlink(const char *oldname, const char *newname) return PTR_ERR(dentry); error = security_path_symlink(&path, dentry, oldname); if (!error) - error = vfs_symlink(mnt_user_ns(path.mnt), path.dentry->d_inode, + error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, oldname); done_path_create(&path, dentry); return error; @@ -233,7 +233,7 @@ int __init init_mkdir(const char *pathname, umode_t mode) mode &= ~current_umask(); error = security_path_mkdir(&path, dentry, mode); if (!error) - error = vfs_mkdir(mnt_user_ns(path.mnt), path.dentry->d_inode, + error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); return error; diff --git a/fs/inode.c b/fs/inode.c index f453eb58fd03..4558dc2f1355 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -5,6 +5,7 @@ */ #include <linux/export.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> @@ -1893,7 +1894,7 @@ bool atime_needs_update(const struct path *path, struct inode *inode) /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ - if (HAS_UNMAPPED_ID(mnt_user_ns(mnt), inode)) + if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode)) return false; if (IS_NOATIME(inode)) @@ -1953,7 +1954,7 @@ EXPORT_SYMBOL(touch_atime); * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ -int dentry_needs_remove_privs(struct user_namespace *mnt_userns, +int dentry_needs_remove_privs(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_inode(dentry); @@ -1963,7 +1964,7 @@ int dentry_needs_remove_privs(struct user_namespace *mnt_userns, if (IS_NOSEC(inode)) return 0; - mask = setattr_should_drop_suidgid(mnt_userns, inode); + mask = setattr_should_drop_suidgid(idmap, inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; @@ -1972,7 +1973,7 @@ int dentry_needs_remove_privs(struct user_namespace *mnt_userns, return mask; } -static int __remove_privs(struct user_namespace *mnt_userns, +static int __remove_privs(struct mnt_idmap *idmap, struct dentry *dentry, int kill) { struct iattr newattrs; @@ -1982,7 +1983,7 @@ static int __remove_privs(struct user_namespace *mnt_userns, * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ - return notify_change(mnt_userns, dentry, &newattrs, NULL); + return notify_change(idmap, dentry, &newattrs, NULL); } static int __file_remove_privs(struct file *file, unsigned int flags) @@ -1995,7 +1996,7 @@ static int __file_remove_privs(struct file *file, unsigned int flags) if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; - kill = dentry_needs_remove_privs(file_mnt_user_ns(file), dentry); + kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry); if (kill < 0) return kill; @@ -2003,7 +2004,7 @@ static int __file_remove_privs(struct file *file, unsigned int flags) if (flags & IOCB_NOWAIT) return -EAGAIN; - error = __remove_privs(file_mnt_user_ns(file), dentry, kill); + error = __remove_privs(file_mnt_idmap(file), dentry, kill); } if (!error) @@ -2279,21 +2280,21 @@ EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards - * @mnt_userns: User namespace of the mount the inode was created from + * @idmap: idmap of the mount the inode was created from * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode * - * If the inode has been created through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions + * If the inode has been created through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions * and initializing i_uid and i_gid. On non-idmapped mounts or if permission - * checking is to be performed on the raw inode simply passs init_user_ns. + * checking is to be performed on the raw inode simply pass @nop_mnt_idmap. */ -void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, +void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode) { - inode_fsuid_set(inode, mnt_userns); + inode_fsuid_set(inode, idmap); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; @@ -2301,32 +2302,32 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode_fsgid_set(inode, mnt_userns); + inode_fsgid_set(inode, idmap); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -bool inode_owner_or_capable(struct user_namespace *mnt_userns, +bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) { vfsuid_t vfsuid; struct user_namespace *ns; - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return true; @@ -2458,7 +2459,7 @@ EXPORT_SYMBOL(current_time); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @inode: inode to check * @vfsgid: the new/current vfsgid of @inode * @@ -2468,19 +2469,19 @@ EXPORT_SYMBOL(current_time); * * Return: true if the caller is sufficiently privileged, false if not. */ -bool in_group_or_capable(struct user_namespace *mnt_userns, +bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid) { if (vfsgid_in_group_p(vfsgid)) return true; - if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) + if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) return true; return false; } /** * mode_strip_sgid - handle the sgid bit for non-directories - * @mnt_userns: User namespace of the mount the inode was created from + * @idmap: idmap of the mount the inode was created from * @dir: parent directory inode * @mode: mode of the file to be created in @dir * @@ -2492,15 +2493,14 @@ bool in_group_or_capable(struct user_namespace *mnt_userns, * * Return: the new mode to use for the file */ -umode_t mode_strip_sgid(struct user_namespace *mnt_userns, +umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; - if (in_group_or_capable(mnt_userns, dir, - i_gid_into_vfsgid(mnt_userns, dir))) + if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir))) return mode; return mode & ~S_ISGID; } diff --git a/fs/internal.h b/fs/internal.h index a803cc3cf716..766e8a554b2c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -14,9 +14,9 @@ struct path; struct mount; struct shrink_control; struct fs_context; -struct user_namespace; struct pipe_inode_info; struct iov_iter; +struct mnt_idmap; /* * block/bdev.c @@ -63,7 +63,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); int do_rmdir(int dfd, struct filename *name); int do_unlinkat(int dfd, struct filename *name); -int may_linkat(struct user_namespace *mnt_userns, const struct path *link); +int may_linkat(struct mnt_idmap *idmap, const struct path *link); int do_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); int do_mkdirat(int dfd, struct filename *name, umode_t mode); @@ -150,8 +150,8 @@ extern int vfs_open(const struct path *, struct file *); * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); -int dentry_needs_remove_privs(struct user_namespace *, struct dentry *dentry); -bool in_group_or_capable(struct user_namespace *mnt_userns, +int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); +bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* @@ -234,7 +234,7 @@ ssize_t do_getxattr(struct mnt_idmap *idmap, int setxattr_copy(const char __user *name, struct xattr_ctx *ctx); int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_ctx *ctx); -int may_write_xattr(struct user_namespace *mnt_userns, struct inode *inode); +int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode); #ifdef CONFIG_FS_POSIX_ACL int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, @@ -261,5 +261,8 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po /* * fs/attr.c */ -int setattr_should_drop_sgid(struct user_namespace *mnt_userns, +int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); +struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); +struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); +void mnt_idmap_put(struct mnt_idmap *idmap); diff --git a/fs/ioctl.c b/fs/ioctl.c index 80ac36aea913..5b2481cd4750 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -651,7 +651,7 @@ static int fileattr_set_prepare(struct inode *inode, /** * vfs_fileattr_set - change miscellaneous file attributes - * @mnt_userns: user namespace of the mount + * @idmap: idmap of the mount * @dentry: the object to change * @fa: fileattr pointer * @@ -665,7 +665,7 @@ static int fileattr_set_prepare(struct inode *inode, * * Return: 0 on success, or a negative error on failure. */ -int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -675,7 +675,7 @@ int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; inode_lock(inode); @@ -693,7 +693,7 @@ int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, } err = fileattr_set_prepare(inode, &old_ma, fa); if (!err) - err = inode->i_op->fileattr_set(mnt_userns, dentry, fa); + err = inode->i_op->fileattr_set(idmap, dentry, fa); } inode_unlock(inode); @@ -714,7 +714,7 @@ static int ioctl_getflags(struct file *file, unsigned int __user *argp) static int ioctl_setflags(struct file *file, unsigned int __user *argp) { - struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; unsigned int flags; @@ -725,7 +725,7 @@ static int ioctl_setflags(struct file *file, unsigned int __user *argp) err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); - err = vfs_fileattr_set(mnt_userns, dentry, &fa); + err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } @@ -746,7 +746,7 @@ static int ioctl_fsgetxattr(struct file *file, void __user *argp) static int ioctl_fssetxattr(struct file *file, void __user *argp) { - struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; int err; @@ -755,7 +755,7 @@ static int ioctl_fssetxattr(struct file *file, void __user *argp) if (!err) { err = mnt_want_write_file(file); if (!err) { - err = vfs_fileattr_set(mnt_userns, dentry, &fa); + err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 8bb58ce5c06c..888a7ceb6479 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -229,7 +229,7 @@ static int __jffs2_set_acl(struct inode *inode, int xprefix, struct posix_acl *a return rc; } -int jffs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int jffs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int rc, xprefix; @@ -241,7 +241,7 @@ int jffs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, if (acl) { umode_t mode; - rc = posix_acl_update_mode(&init_user_ns, inode, &mode, + rc = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (rc) return rc; diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index ca36a6eca594..e976b8cb82cf 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -28,7 +28,7 @@ struct jffs2_acl_header { #ifdef CONFIG_JFFS2_FS_POSIX_ACL struct posix_acl *jffs2_get_acl(struct inode *inode, int type, bool rcu); -int jffs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int jffs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *); extern int jffs2_init_acl_post(struct inode *); diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index f399b390b5f6..5075a0a6d594 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -24,20 +24,20 @@ static int jffs2_readdir (struct file *, struct dir_context *); -static int jffs2_create (struct user_namespace *, struct inode *, +static int jffs2_create (struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); static struct dentry *jffs2_lookup (struct inode *,struct dentry *, unsigned int); static int jffs2_link (struct dentry *,struct inode *,struct dentry *); static int jffs2_unlink (struct inode *,struct dentry *); -static int jffs2_symlink (struct user_namespace *, struct inode *, +static int jffs2_symlink (struct mnt_idmap *, struct inode *, struct dentry *, const char *); -static int jffs2_mkdir (struct user_namespace *, struct inode *,struct dentry *, +static int jffs2_mkdir (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); static int jffs2_rmdir (struct inode *,struct dentry *); -static int jffs2_mknod (struct user_namespace *, struct inode *,struct dentry *, +static int jffs2_mknod (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); -static int jffs2_rename (struct user_namespace *, struct inode *, +static int jffs2_rename (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); @@ -160,7 +160,7 @@ static int jffs2_readdir(struct file *file, struct dir_context *ctx) /***********************************************************************/ -static int jffs2_create(struct user_namespace *mnt_userns, struct inode *dir_i, +static int jffs2_create(struct mnt_idmap *idmap, struct inode *dir_i, struct dentry *dentry, umode_t mode, bool excl) { struct jffs2_raw_inode *ri; @@ -279,7 +279,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de /***********************************************************************/ -static int jffs2_symlink (struct user_namespace *mnt_userns, struct inode *dir_i, +static int jffs2_symlink (struct mnt_idmap *idmap, struct inode *dir_i, struct dentry *dentry, const char *target) { struct jffs2_inode_info *f, *dir_f; @@ -442,7 +442,7 @@ static int jffs2_symlink (struct user_namespace *mnt_userns, struct inode *dir_i } -static int jffs2_mkdir (struct user_namespace *mnt_userns, struct inode *dir_i, +static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, struct dentry *dentry, umode_t mode) { struct jffs2_inode_info *f, *dir_f; @@ -614,7 +614,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) return ret; } -static int jffs2_mknod (struct user_namespace *mnt_userns, struct inode *dir_i, +static int jffs2_mknod (struct mnt_idmap *idmap, struct inode *dir_i, struct dentry *dentry, umode_t mode, dev_t rdev) { struct jffs2_inode_info *f, *dir_f; @@ -762,7 +762,7 @@ static int jffs2_mknod (struct user_namespace *mnt_userns, struct inode *dir_i, return ret; } -static int jffs2_rename (struct user_namespace *mnt_userns, +static int jffs2_rename (struct mnt_idmap *idmap, struct inode *old_dir_i, struct dentry *old_dentry, struct inode *new_dir_i, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 66af51c41619..09174898efd0 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -190,19 +190,19 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) return 0; } -int jffs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int jffs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int rc; - rc = setattr_prepare(&init_user_ns, dentry, iattr); + rc = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (rc) return rc; rc = jffs2_do_setattr(inode, iattr); if (!rc && (iattr->ia_valid & ATTR_MODE)) - rc = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode); + rc = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); return rc; } diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 921d782583d6..8da19766c101 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -164,7 +164,7 @@ long jffs2_ioctl(struct file *, unsigned int, unsigned long); extern const struct inode_operations jffs2_symlink_inode_operations; /* fs.c */ -int jffs2_setattr (struct user_namespace *, struct dentry *, struct iattr *); +int jffs2_setattr (struct mnt_idmap *, struct dentry *, struct iattr *); int jffs2_do_setattr (struct inode *, struct iattr *); struct inode *jffs2_iget(struct super_block *, unsigned long); void jffs2_evict_inode (struct inode *); diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index aef5522551db..437f3a2c1b54 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -57,7 +57,7 @@ static int jffs2_security_getxattr(const struct xattr_handler *handler, } static int jffs2_security_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c index cc3f24883e7d..b7c5da2d89bd 100644 --- a/fs/jffs2/xattr_trusted.c +++ b/fs/jffs2/xattr_trusted.c @@ -25,7 +25,7 @@ static int jffs2_trusted_getxattr(const struct xattr_handler *handler, } static int jffs2_trusted_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c index fb945977c013..f64edce4927b 100644 --- a/fs/jffs2/xattr_user.c +++ b/fs/jffs2/xattr_user.c @@ -25,7 +25,7 @@ static int jffs2_user_getxattr(const struct xattr_handler *handler, } static int jffs2_user_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 3b667eccc73b..fb96f872d207 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -94,7 +94,7 @@ out: return rc; } -int jfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int jfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int rc; @@ -106,7 +106,7 @@ int jfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, tid = txBegin(inode->i_sb, 0); mutex_lock(&JFS_IP(inode)->commit_mutex); if (type == ACL_TYPE_ACCESS && acl) { - rc = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl); + rc = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (rc) goto end_tx; if (mode != inode->i_mode) diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 88663465aecd..2ee35be49de1 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -85,24 +85,24 @@ static int jfs_release(struct inode *inode, struct file *file) return 0; } -int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int jfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int rc; - rc = setattr_prepare(&init_user_ns, dentry, iattr); + rc = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (rc) return rc; - if (is_quota_modification(mnt_userns, inode, iattr)) { + if (is_quota_modification(&nop_mnt_idmap, inode, iattr)) { rc = dquot_initialize(inode); if (rc) return rc; } 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))) { - rc = dquot_transfer(mnt_userns, inode, iattr); + rc = dquot_transfer(&nop_mnt_idmap, inode, iattr); if (rc) return rc; } @@ -119,11 +119,11 @@ int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, jfs_truncate(inode); } - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) - rc = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode); + rc = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); return rc; } diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 1e7b177ece60..ed7989bc2db1 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -70,7 +70,7 @@ int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int jfs_fileattr_set(struct user_namespace *mnt_userns, +int jfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index f0704a25835f..f892e54d0fcd 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -8,7 +8,7 @@ #ifdef CONFIG_JFS_POSIX_ACL struct posix_acl *jfs_get_acl(struct inode *inode, int type, bool rcu); -int jfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int jfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int jfs_init_acl(tid_t, struct inode *, struct inode *); diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index 59379089e939..9e1f02767201 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -64,7 +64,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode) goto fail_put; } - inode_init_owner(&init_user_ns, inode, parent, mode); + inode_init_owner(&nop_mnt_idmap, inode, parent, mode); /* * New inodes need to save sane values on disk when * uid & gid mount options are used diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 7de961a81862..ea80661597ac 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -10,7 +10,7 @@ struct fid; extern struct inode *ialloc(struct inode *, umode_t); extern int jfs_fsync(struct file *, loff_t, loff_t, int); extern int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -extern int jfs_fileattr_set(struct user_namespace *mnt_userns, +extern int jfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); extern long jfs_ioctl(struct file *, unsigned int, unsigned long); extern struct inode *jfs_iget(struct super_block *, unsigned long); @@ -28,7 +28,7 @@ extern struct dentry *jfs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); extern void jfs_set_inode_flags(struct inode *); extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern int jfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); +extern int jfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern const struct address_space_operations jfs_aops; extern const struct inode_operations jfs_dir_inode_operations; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index a38d14eed047..b29d68b5eec5 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -59,7 +59,7 @@ static inline void free_ea_wmap(struct inode *inode) * RETURN: Errors from subroutines * */ -static int jfs_create(struct user_namespace *mnt_userns, struct inode *dip, +static int jfs_create(struct mnt_idmap *idmap, struct inode *dip, struct dentry *dentry, umode_t mode, bool excl) { int rc = 0; @@ -192,7 +192,7 @@ static int jfs_create(struct user_namespace *mnt_userns, struct inode *dip, * note: * EACCES: user needs search+write permission on the parent directory */ -static int jfs_mkdir(struct user_namespace *mnt_userns, struct inode *dip, +static int jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, struct dentry *dentry, umode_t mode) { int rc = 0; @@ -869,7 +869,7 @@ static int jfs_link(struct dentry *old_dentry, * an intermediate result whose length exceeds PATH_MAX [XPG4.2] */ -static int jfs_symlink(struct user_namespace *mnt_userns, struct inode *dip, +static int jfs_symlink(struct mnt_idmap *idmap, struct inode *dip, struct dentry *dentry, const char *name) { int rc; @@ -1059,7 +1059,7 @@ static int jfs_symlink(struct user_namespace *mnt_userns, struct inode *dip, * * FUNCTION: rename a file or directory */ -static int jfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int jfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -1345,7 +1345,7 @@ static int jfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, * * FUNCTION: Create a special file (device) */ -static int jfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int jfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct jfs_inode_info *jfs_ip; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index f9273f6901c8..f817798fa1eb 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -932,7 +932,7 @@ static int jfs_xattr_get(const struct xattr_handler *handler, } static int jfs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -951,7 +951,7 @@ static int jfs_xattr_get_os2(const struct xattr_handler *handler, } static int jfs_xattr_set_os2(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 935ef8cb02b2..e3181c3e1988 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1200,7 +1200,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, return d_splice_alias(inode, dentry); } -static int kernfs_iop_mkdir(struct user_namespace *mnt_userns, +static int kernfs_iop_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { @@ -1238,7 +1238,7 @@ static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) return ret; } -static int kernfs_iop_rename(struct user_namespace *mnt_userns, +static int kernfs_iop_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index eac0f210299a..30494dcb0df3 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -107,7 +107,7 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) return ret; } -int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); @@ -120,7 +120,7 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, root = kernfs_root(kn); down_write(&root->kernfs_rwsem); - error = setattr_prepare(&init_user_ns, dentry, iattr); + error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) goto out; @@ -129,7 +129,7 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, goto out; /* this ignores size changes */ - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); out: up_write(&root->kernfs_rwsem); @@ -181,7 +181,7 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) set_nlink(inode, kn->dir.subdirs + 2); } -int kernfs_iop_getattr(struct user_namespace *mnt_userns, +int kernfs_iop_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -191,7 +191,7 @@ int kernfs_iop_getattr(struct user_namespace *mnt_userns, down_read(&root->kernfs_rwsem); kernfs_refresh_inode(kn, inode); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); up_read(&root->kernfs_rwsem); return 0; @@ -272,7 +272,7 @@ void kernfs_evict_inode(struct inode *inode) kernfs_put(kn); } -int kernfs_iop_permission(struct user_namespace *mnt_userns, +int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct kernfs_node *kn; @@ -287,7 +287,7 @@ int kernfs_iop_permission(struct user_namespace *mnt_userns, down_read(&root->kernfs_rwsem); kernfs_refresh_inode(kn, inode); - ret = generic_permission(&init_user_ns, inode, mask); + ret = generic_permission(&nop_mnt_idmap, inode, mask); up_read(&root->kernfs_rwsem); return ret; @@ -324,7 +324,7 @@ static int kernfs_vfs_xattr_get(const struct xattr_handler *handler, } static int kernfs_vfs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -391,7 +391,7 @@ static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn, } static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 9046d9f39e63..236c3a6113f1 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -127,11 +127,11 @@ extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; */ extern const struct xattr_handler *kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); -int kernfs_iop_permission(struct user_namespace *mnt_userns, +int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); -int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); -int kernfs_iop_getattr(struct user_namespace *mnt_userns, +int kernfs_iop_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); diff --git a/fs/ksmbd/ndr.c b/fs/ksmbd/ndr.c index 4d9e0b54e3db..3507d8f89074 100644 --- a/fs/ksmbd/ndr.c +++ b/fs/ksmbd/ndr.c @@ -338,7 +338,7 @@ static int ndr_encode_posix_acl_entry(struct ndr *n, struct xattr_smb_acl *acl) } int ndr_encode_posix_acl(struct ndr *n, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct inode *inode, struct xattr_smb_acl *acl, struct xattr_smb_acl *def_acl) @@ -374,11 +374,11 @@ int ndr_encode_posix_acl(struct ndr *n, if (ret) return ret; - vfsuid = i_uid_into_vfsuid(user_ns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); ret = ndr_write_int64(n, from_kuid(&init_user_ns, vfsuid_into_kuid(vfsuid))); if (ret) return ret; - vfsgid = i_gid_into_vfsgid(user_ns, inode); + vfsgid = i_gid_into_vfsgid(idmap, inode); ret = ndr_write_int64(n, from_kgid(&init_user_ns, vfsgid_into_kgid(vfsgid))); if (ret) return ret; diff --git a/fs/ksmbd/ndr.h b/fs/ksmbd/ndr.h index 60ca265d1bb0..f3c108c8cf4d 100644 --- a/fs/ksmbd/ndr.h +++ b/fs/ksmbd/ndr.h @@ -14,7 +14,7 @@ struct ndr { int ndr_encode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da); int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da); -int ndr_encode_posix_acl(struct ndr *n, struct user_namespace *user_ns, +int ndr_encode_posix_acl(struct ndr *n, struct mnt_idmap *idmap, struct inode *inode, struct xattr_smb_acl *acl, struct xattr_smb_acl *def_acl); int ndr_encode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index d7d47b82451d..2e54ded4d92c 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1608,9 +1608,9 @@ void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp) { struct create_posix_rsp *buf; struct inode *inode = file_inode(fp->filp); - struct user_namespace *user_ns = file_mnt_user_ns(fp->filp); - vfsuid_t vfsuid = i_uid_into_vfsuid(user_ns, inode); - vfsgid_t vfsgid = i_gid_into_vfsgid(user_ns, inode); + struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); buf = (struct create_posix_rsp *)cc; memset(buf, 0, sizeof(struct create_posix_rsp)); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index d681f91947d9..4ef6e1e59a40 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -12,6 +12,7 @@ #include <linux/ethtool.h> #include <linux/falloc.h> #include <linux/mount.h> +#include <linux/filelock.h> #include "glob.h" #include "smbfsctl.h" @@ -2192,7 +2193,7 @@ out: static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, const struct path *path) { - struct user_namespace *user_ns = mnt_user_ns(path->mnt); + struct mnt_idmap *idmap = mnt_idmap(path->mnt); char *attr_name = NULL, *value; int rc = 0; unsigned int next = 0; @@ -2228,7 +2229,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, value = (char *)&eabuf->name + eabuf->EaNameLength + 1; if (!eabuf->EaValueLength) { - rc = ksmbd_vfs_casexattr_len(user_ns, + rc = ksmbd_vfs_casexattr_len(idmap, path->dentry, attr_name, XATTR_USER_PREFIX_LEN + @@ -2236,7 +2237,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* delete the EA only when it exits */ if (rc > 0) { - rc = ksmbd_vfs_remove_xattr(user_ns, + rc = ksmbd_vfs_remove_xattr(idmap, path->dentry, attr_name); @@ -2251,7 +2252,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* if the EA doesn't exist, just do nothing. */ rc = 0; } else { - rc = ksmbd_vfs_setxattr(user_ns, + rc = ksmbd_vfs_setxattr(idmap, path->dentry, attr_name, value, le16_to_cpu(eabuf->EaValueLength), 0); if (rc < 0) { @@ -2281,7 +2282,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, struct ksmbd_file *fp, char *stream_name, int s_type) { - struct user_namespace *user_ns = mnt_user_ns(path->mnt); + struct mnt_idmap *idmap = mnt_idmap(path->mnt); size_t xattr_stream_size; char *xattr_stream_name; int rc; @@ -2297,7 +2298,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, fp->stream.size = xattr_stream_size; /* Check if there is stream prefix in xattr space */ - rc = ksmbd_vfs_casexattr_len(user_ns, + rc = ksmbd_vfs_casexattr_len(idmap, path->dentry, xattr_stream_name, xattr_stream_size); @@ -2309,7 +2310,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, return -EBADF; } - rc = ksmbd_vfs_setxattr(user_ns, path->dentry, + rc = ksmbd_vfs_setxattr(idmap, path->dentry, xattr_stream_name, NULL, 0, 0); if (rc < 0) pr_err("Failed to store XATTR stream name :%d\n", rc); @@ -2318,7 +2319,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, static int smb2_remove_smb_xattrs(const struct path *path) { - struct user_namespace *user_ns = mnt_user_ns(path->mnt); + struct mnt_idmap *idmap = mnt_idmap(path->mnt); char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; @@ -2338,7 +2339,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { - err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, + err = ksmbd_vfs_remove_xattr(idmap, path->dentry, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", @@ -2385,7 +2386,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_user_ns(path->mnt), + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path->dentry, &da); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); @@ -2404,7 +2405,7 @@ static void smb2_update_xattrs(struct ksmbd_tree_connect *tcon, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS)) return; - rc = ksmbd_vfs_get_dos_attrib_xattr(mnt_user_ns(path->mnt), + rc = ksmbd_vfs_get_dos_attrib_xattr(mnt_idmap(path->mnt), path->dentry, &da); if (rc > 0) { fp->f_ci->m_fattr = cpu_to_le32(da.attr); @@ -2479,11 +2480,11 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, } static void ksmbd_acls_fattr(struct smb_fattr *fattr, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *inode) { - vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); - vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); fattr->cf_uid = vfsuid_into_kuid(vfsuid); fattr->cf_gid = vfsgid_into_kgid(vfsgid); @@ -2515,7 +2516,7 @@ int smb2_open(struct ksmbd_work *work) struct ksmbd_share_config *share = tcon->share_conf; struct ksmbd_file *fp = NULL; struct file *filp = NULL; - struct user_namespace *user_ns = NULL; + struct mnt_idmap *idmap = NULL; struct kstat stat; struct create_context *context; struct lease_ctx_info *lc = NULL; @@ -2768,7 +2769,7 @@ int smb2_open(struct ksmbd_work *work) rc = 0; } else { file_present = true; - user_ns = mnt_user_ns(path.mnt); + idmap = mnt_idmap(path.mnt); } if (stream_name) { if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) { @@ -2831,7 +2832,7 @@ int smb2_open(struct ksmbd_work *work) if (!file_present) { daccess = cpu_to_le32(GENERIC_ALL_FLAGS); } else { - rc = ksmbd_vfs_query_maximal_access(user_ns, + rc = ksmbd_vfs_query_maximal_access(idmap, path.dentry, &daccess); if (rc) @@ -2867,7 +2868,7 @@ int smb2_open(struct ksmbd_work *work) } created = true; - user_ns = mnt_user_ns(path.mnt); + idmap = mnt_idmap(path.mnt); if (ea_buf) { if (le32_to_cpu(ea_buf->ccontext.DataLength) < sizeof(struct smb2_ea_info)) { @@ -2889,7 +2890,7 @@ int smb2_open(struct ksmbd_work *work) * is already granted. */ if (daccess & ~(FILE_READ_ATTRIBUTES_LE | FILE_READ_CONTROL_LE)) { - rc = inode_permission(user_ns, + rc = inode_permission(idmap, d_inode(path.dentry), may_flags); if (rc) @@ -2897,7 +2898,7 @@ int smb2_open(struct ksmbd_work *work) if ((daccess & FILE_DELETE_LE) || (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE)) { - rc = ksmbd_vfs_may_delete(user_ns, + rc = ksmbd_vfs_may_delete(idmap, path.dentry); if (rc) goto err_out; @@ -2960,7 +2961,7 @@ int smb2_open(struct ksmbd_work *work) int posix_acl_rc; struct inode *inode = d_inode(path.dentry); - posix_acl_rc = ksmbd_vfs_inherit_posix_acl(user_ns, + posix_acl_rc = ksmbd_vfs_inherit_posix_acl(idmap, path.dentry, d_inode(path.dentry->d_parent)); if (posix_acl_rc) @@ -2976,7 +2977,7 @@ int smb2_open(struct ksmbd_work *work) rc = smb2_create_sd_buffer(work, req, &path); if (rc) { if (posix_acl_rc) - ksmbd_vfs_set_init_posix_acl(user_ns, + ksmbd_vfs_set_init_posix_acl(idmap, path.dentry); if (test_share_config_flag(work->tcon->share_conf, @@ -2985,7 +2986,7 @@ int smb2_open(struct ksmbd_work *work) struct smb_ntsd *pntsd; int pntsd_size, ace_num = 0; - ksmbd_acls_fattr(&fattr, user_ns, inode); + ksmbd_acls_fattr(&fattr, idmap, inode); if (fattr.cf_acls) ace_num = fattr.cf_acls->a_count; if (fattr.cf_dacls) @@ -2999,7 +3000,7 @@ int smb2_open(struct ksmbd_work *work) if (!pntsd) goto err_out; - rc = build_sec_desc(user_ns, + rc = build_sec_desc(idmap, pntsd, NULL, 0, OWNER_SECINFO | GROUP_SECINFO | @@ -3013,7 +3014,7 @@ int smb2_open(struct ksmbd_work *work) } rc = ksmbd_vfs_set_sd_xattr(conn, - user_ns, + idmap, path.dentry, pntsd, pntsd_size); @@ -3209,7 +3210,7 @@ int smb2_open(struct ksmbd_work *work) struct create_context *mxac_ccontext; if (maximal_access == 0) - ksmbd_vfs_query_maximal_access(user_ns, + ksmbd_vfs_query_maximal_access(idmap, path.dentry, &maximal_access); mxac_ccontext = (struct create_context *)(rsp->Buffer + @@ -3634,7 +3635,7 @@ static void unlock_dir(struct ksmbd_file *dir_fp) static int process_query_dir_entries(struct smb2_query_dir_private *priv) { - struct user_namespace *user_ns = file_mnt_user_ns(priv->dir_fp->filp); + struct mnt_idmap *idmap = file_mnt_idmap(priv->dir_fp->filp); struct kstat kstat; struct ksmbd_kstat ksmbd_kstat; int rc; @@ -3647,7 +3648,7 @@ static int process_query_dir_entries(struct smb2_query_dir_private *priv) return -EINVAL; lock_dir(priv->dir_fp); - dent = lookup_one(user_ns, priv->d_info->name, + dent = lookup_one(idmap, priv->d_info->name, priv->dir_fp->filp->f_path.dentry, priv->d_info->name_len); unlock_dir(priv->dir_fp); @@ -3668,7 +3669,7 @@ static int process_query_dir_entries(struct smb2_query_dir_private *priv) ksmbd_kstat.kstat = &kstat; if (priv->info_level != FILE_NAMES_INFORMATION) ksmbd_vfs_fill_dentry_attrs(priv->work, - user_ns, + idmap, dent, &ksmbd_kstat); @@ -3898,7 +3899,7 @@ int smb2_query_dir(struct ksmbd_work *work) } if (!(dir_fp->daccess & FILE_LIST_DIRECTORY_LE) || - inode_permission(file_mnt_user_ns(dir_fp->filp), + inode_permission(file_mnt_idmap(dir_fp->filp), file_inode(dir_fp->filp), MAY_READ | MAY_EXEC)) { pr_err("no right to enumerate directory (%pD)\n", dir_fp->filp); @@ -4164,7 +4165,7 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, ssize_t buf_free_len, alignment_bytes, next_offset, rsp_data_cnt = 0; struct smb2_ea_info_req *ea_req = NULL; const struct path *path; - struct user_namespace *user_ns = file_mnt_user_ns(fp->filp); + struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); if (!(fp->daccess & FILE_READ_EA_LE)) { pr_err("Not permitted to read ext attr : 0x%x\n", @@ -4244,7 +4245,7 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, buf_free_len -= (offsetof(struct smb2_ea_info, name) + name_len + 1); /* bailout if xattr can't fit in buf_free_len */ - value_len = ksmbd_vfs_getxattr(user_ns, path->dentry, + value_len = ksmbd_vfs_getxattr(idmap, path->dentry, name, &buf); if (value_len <= 0) { rc = -ENOENT; @@ -4334,7 +4335,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, } basic_info = (struct smb2_file_basic_info *)rsp->Buffer; - generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), + generic_fillattr(file_mnt_idmap(fp->filp), file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -4375,7 +4376,7 @@ static void get_file_standard_info(struct smb2_query_info_rsp *rsp, struct kstat stat; inode = file_inode(fp->filp); - generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); + generic_fillattr(file_mnt_idmap(fp->filp), inode, &stat); sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); @@ -4429,7 +4430,7 @@ static int get_file_all_info(struct ksmbd_work *work, return PTR_ERR(filename); inode = file_inode(fp->filp); - generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); + generic_fillattr(file_mnt_idmap(fp->filp), inode, &stat); ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); @@ -4506,7 +4507,7 @@ static void get_file_stream_info(struct ksmbd_work *work, int buf_free_len; struct smb2_query_info_req *req = ksmbd_req_buf_next(work); - generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), + generic_fillattr(file_mnt_idmap(fp->filp), file_inode(fp->filp), &stat); file_info = (struct smb2_file_stream_info *)rsp->Buffer; @@ -4597,7 +4598,7 @@ static void get_file_internal_info(struct smb2_query_info_rsp *rsp, struct smb2_file_internal_info *file_info; struct kstat stat; - generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), + generic_fillattr(file_mnt_idmap(fp->filp), file_inode(fp->filp), &stat); file_info = (struct smb2_file_internal_info *)rsp->Buffer; file_info->IndexNumber = cpu_to_le64(stat.ino); @@ -4623,7 +4624,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; inode = file_inode(fp->filp); - generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); + generic_fillattr(file_mnt_idmap(fp->filp), inode, &stat); file_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -4684,7 +4685,7 @@ static void get_file_compression_info(struct smb2_query_info_rsp *rsp, struct smb2_file_comp_info *file_info; struct kstat stat; - generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), + generic_fillattr(file_mnt_idmap(fp->filp), file_inode(fp->filp), &stat); file_info = (struct smb2_file_comp_info *)rsp->Buffer; @@ -4725,9 +4726,9 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, { struct smb311_posix_qinfo *file_info; struct inode *inode = file_inode(fp->filp); - struct user_namespace *user_ns = file_mnt_user_ns(fp->filp); - vfsuid_t vfsuid = i_uid_into_vfsuid(user_ns, inode); - vfsgid_t vfsgid = i_gid_into_vfsgid(user_ns, inode); + struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); u64 time; int out_buf_len = sizeof(struct smb311_posix_qinfo) + 32; @@ -5127,7 +5128,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, struct smb2_query_info_rsp *rsp) { struct ksmbd_file *fp; - struct user_namespace *user_ns; + struct mnt_idmap *idmap; struct smb_ntsd *pntsd = (struct smb_ntsd *)rsp->Buffer, *ppntsd = NULL; struct smb_fattr fattr = {{0}}; struct inode *inode; @@ -5174,19 +5175,19 @@ static int smb2_get_info_sec(struct ksmbd_work *work, if (!fp) return -ENOENT; - user_ns = file_mnt_user_ns(fp->filp); + idmap = file_mnt_idmap(fp->filp); inode = file_inode(fp->filp); - ksmbd_acls_fattr(&fattr, user_ns, inode); + ksmbd_acls_fattr(&fattr, idmap, inode); if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) - ppntsd_size = ksmbd_vfs_get_sd_xattr(work->conn, user_ns, + ppntsd_size = ksmbd_vfs_get_sd_xattr(work->conn, idmap, fp->filp->f_path.dentry, &ppntsd); /* Check if sd buffer size exceeds response buffer size */ if (smb2_resp_buf_len(work, 8) > ppntsd_size) - rc = build_sec_desc(user_ns, pntsd, ppntsd, ppntsd_size, + rc = build_sec_desc(idmap, pntsd, ppntsd, ppntsd_size, addition_info, &secdesclen, &fattr); posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); @@ -5416,7 +5417,7 @@ int smb2_echo(struct ksmbd_work *work) static int smb2_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct smb2_file_rename_info *file_info, struct nls_table *local_nls) { @@ -5479,7 +5480,7 @@ static int smb2_rename(struct ksmbd_work *work, if (rc) goto out; - rc = ksmbd_vfs_setxattr(user_ns, + rc = ksmbd_vfs_setxattr(idmap, fp->filp->f_path.dentry, xattr_stream_name, NULL, 0, 0); @@ -5618,7 +5619,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, struct iattr attrs; struct file *filp; struct inode *inode; - struct user_namespace *user_ns; + struct mnt_idmap *idmap; int rc = 0; if (!(fp->daccess & FILE_WRITE_ATTRIBUTES_LE)) @@ -5627,7 +5628,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, attrs.ia_valid = 0; filp = fp->filp; inode = file_inode(filp); - user_ns = file_mnt_user_ns(filp); + idmap = file_mnt_idmap(filp); if (file_info->CreationTime) fp->create_time = le64_to_cpu(file_info->CreationTime); @@ -5671,7 +5672,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(user_ns, + rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, filp->f_path.dentry, &da); if (rc) ksmbd_debug(SMB, @@ -5689,7 +5690,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, inode_lock(inode); inode->i_ctime = attrs.ia_ctime; attrs.ia_valid &= ~ATTR_CTIME; - rc = notify_change(user_ns, dentry, &attrs, NULL); + rc = notify_change(idmap, dentry, &attrs, NULL); inode_unlock(inode); } return rc; @@ -5782,7 +5783,7 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, struct smb2_file_rename_info *rename_info, unsigned int buf_len) { - struct user_namespace *user_ns; + struct mnt_idmap *idmap; struct ksmbd_file *parent_fp; struct dentry *parent; struct dentry *dentry = fp->filp->f_path.dentry; @@ -5797,12 +5798,12 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, le32_to_cpu(rename_info->FileNameLength)) return -EINVAL; - user_ns = file_mnt_user_ns(fp->filp); + idmap = file_mnt_idmap(fp->filp); if (ksmbd_stream_fd(fp)) goto next; parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(user_ns, parent, dentry); + ret = ksmbd_vfs_lock_parent(idmap, parent, dentry); if (ret) { dput(parent); return ret; @@ -5821,7 +5822,7 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, ksmbd_fd_put(work, parent_fp); } next: - return smb2_rename(work, fp, user_ns, rename_info, + return smb2_rename(work, fp, idmap, rename_info, work->conn->local_nls); } @@ -7530,14 +7531,14 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, struct file_sparse *sparse) { struct ksmbd_file *fp; - struct user_namespace *user_ns; + struct mnt_idmap *idmap; int ret = 0; __le32 old_fattr; fp = ksmbd_lookup_fd_fast(work, id); if (!fp) return -ENOENT; - user_ns = file_mnt_user_ns(fp->filp); + idmap = file_mnt_idmap(fp->filp); old_fattr = fp->f_ci->m_fattr; if (sparse->SetSparse) @@ -7550,13 +7551,13 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS)) { struct xattr_dos_attrib da; - ret = ksmbd_vfs_get_dos_attrib_xattr(user_ns, + ret = ksmbd_vfs_get_dos_attrib_xattr(idmap, fp->filp->f_path.dentry, &da); if (ret <= 0) goto out; da.attr = le32_to_cpu(fp->f_ci->m_fattr); - ret = ksmbd_vfs_set_dos_attrib_xattr(user_ns, + ret = ksmbd_vfs_set_dos_attrib_xattr(idmap, fp->filp->f_path.dentry, &da); if (ret) fp->f_ci->m_fattr = old_fattr; diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 2a4fbbd55b91..fa2b54df6ee6 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -307,7 +307,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, { int i, rc = 0; struct ksmbd_conn *conn = work->conn; - struct user_namespace *user_ns = file_mnt_user_ns(dir->filp); + struct mnt_idmap *idmap = file_mnt_idmap(dir->filp); for (i = 0; i < 2; i++) { struct kstat kstat; @@ -333,7 +333,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, ksmbd_kstat.kstat = &kstat; ksmbd_vfs_fill_dentry_attrs(work, - user_ns, + idmap, dentry, &ksmbd_kstat); rc = fn(conn, info_level, d_info, &ksmbd_kstat); diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index ab5c68cc0e13..6d6cfb6957a9 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -254,7 +254,7 @@ void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid) ssid->num_subauth++; } -static int sid_to_id(struct user_namespace *user_ns, +static int sid_to_id(struct mnt_idmap *idmap, struct smb_sid *psid, uint sidtype, struct smb_fattr *fattr) { @@ -276,7 +276,7 @@ static int sid_to_id(struct user_namespace *user_ns, id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); uid = KUIDT_INIT(id); - uid = from_vfsuid(user_ns, &init_user_ns, VFSUIDT_INIT(uid)); + uid = from_vfsuid(idmap, &init_user_ns, VFSUIDT_INIT(uid)); if (uid_valid(uid)) { fattr->cf_uid = uid; rc = 0; @@ -287,7 +287,7 @@ static int sid_to_id(struct user_namespace *user_ns, id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); gid = KGIDT_INIT(id); - gid = from_vfsgid(user_ns, &init_user_ns, VFSGIDT_INIT(gid)); + gid = from_vfsgid(idmap, &init_user_ns, VFSGIDT_INIT(gid)); if (gid_valid(gid)) { fattr->cf_gid = gid; rc = 0; @@ -362,7 +362,7 @@ void free_acl_state(struct posix_acl_state *state) kfree(state->groups); } -static void parse_dacl(struct user_namespace *user_ns, +static void parse_dacl(struct mnt_idmap *idmap, struct smb_acl *pdacl, char *end_of_acl, struct smb_sid *pownersid, struct smb_sid *pgrpsid, struct smb_fattr *fattr) @@ -489,7 +489,7 @@ static void parse_dacl(struct user_namespace *user_ns, acl_mode = access_flags_to_mode(fattr, ppace[i]->access_req, ppace[i]->type); temp_fattr.cf_uid = INVALID_UID; - ret = sid_to_id(user_ns, &ppace[i]->sid, SIDOWNER, &temp_fattr); + ret = sid_to_id(idmap, &ppace[i]->sid, SIDOWNER, &temp_fattr); if (ret || uid_eq(temp_fattr.cf_uid, INVALID_UID)) { pr_err("%s: Error %d mapping Owner SID to uid\n", __func__, ret); @@ -575,7 +575,7 @@ static void parse_dacl(struct user_namespace *user_ns, free_acl_state(&default_acl_state); } -static void set_posix_acl_entries_dacl(struct user_namespace *user_ns, +static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, struct smb_ace *pndace, struct smb_fattr *fattr, u32 *num_aces, u16 *size, u32 nt_aces_num) @@ -600,14 +600,14 @@ static void set_posix_acl_entries_dacl(struct user_namespace *user_ns, uid_t uid; unsigned int sid_type = SIDOWNER; - uid = posix_acl_uid_translate(user_ns, pace); + uid = posix_acl_uid_translate(idmap, pace); if (!uid) sid_type = SIDUNIX_USER; id_to_sid(uid, sid_type, sid); } else if (pace->e_tag == ACL_GROUP) { gid_t gid; - gid = posix_acl_gid_translate(user_ns, pace); + gid = posix_acl_gid_translate(idmap, pace); id_to_sid(gid, SIDUNIX_GROUP, sid); } else if (pace->e_tag == ACL_OTHER && !nt_aces_num) { smb_copy_sid(sid, &sid_everyone); @@ -666,12 +666,12 @@ posix_default_acl: if (pace->e_tag == ACL_USER) { uid_t uid; - uid = posix_acl_uid_translate(user_ns, pace); + uid = posix_acl_uid_translate(idmap, pace); id_to_sid(uid, SIDCREATOR_OWNER, sid); } else if (pace->e_tag == ACL_GROUP) { gid_t gid; - gid = posix_acl_gid_translate(user_ns, pace); + gid = posix_acl_gid_translate(idmap, pace); id_to_sid(gid, SIDCREATOR_GROUP, sid); } else { kfree(sid); @@ -689,7 +689,7 @@ posix_default_acl: } } -static void set_ntacl_dacl(struct user_namespace *user_ns, +static void set_ntacl_dacl(struct mnt_idmap *idmap, struct smb_acl *pndacl, struct smb_acl *nt_dacl, unsigned int aces_size, @@ -723,13 +723,13 @@ static void set_ntacl_dacl(struct user_namespace *user_ns, } } - set_posix_acl_entries_dacl(user_ns, pndace, fattr, + set_posix_acl_entries_dacl(idmap, pndace, fattr, &num_aces, &size, nt_num_aces); pndacl->num_aces = cpu_to_le32(num_aces); pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size); } -static void set_mode_dacl(struct user_namespace *user_ns, +static void set_mode_dacl(struct mnt_idmap *idmap, struct smb_acl *pndacl, struct smb_fattr *fattr) { struct smb_ace *pace, *pndace; @@ -741,7 +741,7 @@ static void set_mode_dacl(struct user_namespace *user_ns, pace = pndace = (struct smb_ace *)((char *)pndacl + sizeof(struct smb_acl)); if (fattr->cf_acls) { - set_posix_acl_entries_dacl(user_ns, pndace, fattr, + set_posix_acl_entries_dacl(idmap, pndace, fattr, &num_aces, &size, num_aces); goto out; } @@ -808,7 +808,7 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl) } /* Convert CIFS ACL to POSIX form */ -int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, +int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, int acl_len, struct smb_fattr *fattr) { int rc = 0; @@ -851,7 +851,7 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, return rc; } - rc = sid_to_id(user_ns, owner_sid_ptr, SIDOWNER, fattr); + rc = sid_to_id(idmap, owner_sid_ptr, SIDOWNER, fattr); if (rc) { pr_err("%s: Error %d mapping Owner SID to uid\n", __func__, rc); @@ -866,7 +866,7 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, __func__, rc); return rc; } - rc = sid_to_id(user_ns, group_sid_ptr, SIDUNIX_GROUP, fattr); + rc = sid_to_id(idmap, group_sid_ptr, SIDUNIX_GROUP, fattr); if (rc) { pr_err("%s: Error %d mapping Group SID to gid\n", __func__, rc); @@ -881,7 +881,7 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, pntsd->type |= cpu_to_le16(DACL_PROTECTED); if (dacloffset) { - parse_dacl(user_ns, dacl_ptr, end_of_acl, + parse_dacl(idmap, dacl_ptr, end_of_acl, owner_sid_ptr, group_sid_ptr, fattr); } @@ -889,7 +889,7 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, } /* Convert permission bits from mode to equivalent CIFS ACL */ -int build_sec_desc(struct user_namespace *user_ns, +int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info, __u32 *secdesclen, struct smb_fattr *fattr) @@ -950,7 +950,7 @@ int build_sec_desc(struct user_namespace *user_ns, dacl_ptr->num_aces = 0; if (!ppntsd) { - set_mode_dacl(user_ns, dacl_ptr, fattr); + set_mode_dacl(idmap, dacl_ptr, fattr); } else { struct smb_acl *ppdacl_ptr; unsigned int dacl_offset = le32_to_cpu(ppntsd->dacloffset); @@ -966,7 +966,7 @@ int build_sec_desc(struct user_namespace *user_ns, ppdacl_size < sizeof(struct smb_acl)) goto out; - set_ntacl_dacl(user_ns, dacl_ptr, ppdacl_ptr, + set_ntacl_dacl(idmap, dacl_ptr, ppdacl_ptr, ntacl_size - sizeof(struct smb_acl), nowner_sid_ptr, ngroup_sid_ptr, fattr); @@ -1002,13 +1002,13 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, struct smb_ntsd *parent_pntsd = NULL; struct smb_sid owner_sid, group_sid; struct dentry *parent = path->dentry->d_parent; - struct user_namespace *user_ns = mnt_user_ns(path->mnt); + struct mnt_idmap *idmap = mnt_idmap(path->mnt); int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size; int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size; char *aces_base; bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode); - pntsd_size = ksmbd_vfs_get_sd_xattr(conn, user_ns, + pntsd_size = ksmbd_vfs_get_sd_xattr(conn, idmap, parent, &parent_pntsd); if (pntsd_size <= 0) return -ENOENT; @@ -1162,7 +1162,7 @@ pass: pntsd_size += sizeof(struct smb_acl) + nt_size; } - ksmbd_vfs_set_sd_xattr(conn, user_ns, + ksmbd_vfs_set_sd_xattr(conn, idmap, path->dentry, pntsd, pntsd_size); kfree(pntsd); } @@ -1190,7 +1190,7 @@ bool smb_inherit_flags(int flags, bool is_dir) int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, __le32 *pdaccess, int uid) { - struct user_namespace *user_ns = mnt_user_ns(path->mnt); + struct mnt_idmap *idmap = mnt_idmap(path->mnt); struct smb_ntsd *pntsd = NULL; struct smb_acl *pdacl; struct posix_acl *posix_acls; @@ -1206,7 +1206,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, unsigned short ace_size; ksmbd_debug(SMB, "check permission using windows acl\n"); - pntsd_size = ksmbd_vfs_get_sd_xattr(conn, user_ns, + pntsd_size = ksmbd_vfs_get_sd_xattr(conn, idmap, path->dentry, &pntsd); if (pntsd_size <= 0 || !pntsd) goto err_out; @@ -1296,9 +1296,9 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, pa_entry = posix_acls->a_entries; for (i = 0; i < posix_acls->a_count; i++, pa_entry++) { if (pa_entry->e_tag == ACL_USER) - id = posix_acl_uid_translate(user_ns, pa_entry); + id = posix_acl_uid_translate(idmap, pa_entry); else if (pa_entry->e_tag == ACL_GROUP) - id = posix_acl_gid_translate(user_ns, pa_entry); + id = posix_acl_gid_translate(idmap, pa_entry); else continue; @@ -1360,14 +1360,14 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, int rc; struct smb_fattr fattr = {{0}}; struct inode *inode = d_inode(path->dentry); - struct user_namespace *user_ns = mnt_user_ns(path->mnt); + struct mnt_idmap *idmap = mnt_idmap(path->mnt); struct iattr newattrs; fattr.cf_uid = INVALID_UID; fattr.cf_gid = INVALID_GID; fattr.cf_mode = inode->i_mode; - rc = parse_sec_desc(user_ns, pntsd, ntsd_len, &fattr); + rc = parse_sec_desc(idmap, pntsd, ntsd_len, &fattr); if (rc) goto out; @@ -1383,17 +1383,17 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, newattrs.ia_valid |= ATTR_MODE; newattrs.ia_mode = (inode->i_mode & ~0777) | (fattr.cf_mode & 0777); - ksmbd_vfs_remove_acl_xattrs(user_ns, path->dentry); + ksmbd_vfs_remove_acl_xattrs(idmap, path->dentry); /* Update posix acls */ if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && fattr.cf_dacls) { - rc = set_posix_acl(user_ns, path->dentry, + rc = set_posix_acl(idmap, path->dentry, ACL_TYPE_ACCESS, fattr.cf_acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", rc); if (S_ISDIR(inode->i_mode) && fattr.cf_dacls) { - rc = set_posix_acl(user_ns, path->dentry, + rc = set_posix_acl(idmap, path->dentry, ACL_TYPE_DEFAULT, fattr.cf_dacls); if (rc) ksmbd_debug(SMB, @@ -1403,7 +1403,7 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, } inode_lock(inode); - rc = notify_change(user_ns, path->dentry, &newattrs, NULL); + rc = notify_change(idmap, path->dentry, &newattrs, NULL); inode_unlock(inode); if (rc) goto out; @@ -1414,8 +1414,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { /* Update WinACL in xattr */ - ksmbd_vfs_remove_sd_xattrs(user_ns, path->dentry); - ksmbd_vfs_set_sd_xattr(conn, user_ns, + ksmbd_vfs_remove_sd_xattrs(idmap, path->dentry); + ksmbd_vfs_set_sd_xattr(conn, idmap, path->dentry, pntsd, ntsd_len); } diff --git a/fs/ksmbd/smbacl.h b/fs/ksmbd/smbacl.h index 618f2e0236b3..49a8c292bd2e 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -190,9 +190,9 @@ struct posix_acl_state { struct posix_ace_state_array *groups; }; -int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, +int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, int acl_len, struct smb_fattr *fattr); -int build_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, +int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info, __u32 *secdesclen, struct smb_fattr *fattr); int init_acl_state(struct posix_acl_state *state, int cnt); @@ -211,25 +211,25 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid); void ksmbd_init_domain(u32 *sub_auth); -static inline uid_t posix_acl_uid_translate(struct user_namespace *mnt_userns, +static inline uid_t posix_acl_uid_translate(struct mnt_idmap *idmap, struct posix_acl_entry *pace) { vfsuid_t vfsuid; /* If this is an idmapped mount, apply the idmapping. */ - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, pace->e_uid); + vfsuid = make_vfsuid(idmap, &init_user_ns, pace->e_uid); /* Translate the kuid into a userspace id ksmbd would see. */ return from_kuid(&init_user_ns, vfsuid_into_kuid(vfsuid)); } -static inline gid_t posix_acl_gid_translate(struct user_namespace *mnt_userns, +static inline gid_t posix_acl_gid_translate(struct mnt_idmap *idmap, struct posix_acl_entry *pace) { vfsgid_t vfsgid; /* If this is an idmapped mount, apply the idmapping. */ - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, pace->e_gid); + vfsgid = make_vfsgid(idmap, &init_user_ns, pace->e_gid); /* Translate the kgid into a userspace id ksmbd would see. */ return from_kgid(&init_user_ns, vfsgid_into_kgid(vfsgid)); diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index ff0e7a4fcd4d..aa1300b7bfc2 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/uaccess.h> #include <linux/backing-dev.h> #include <linux/writeback.h> @@ -69,14 +70,14 @@ static void ksmbd_vfs_inherit_owner(struct ksmbd_work *work, * * the reference count of @parent isn't incremented. */ -int ksmbd_vfs_lock_parent(struct user_namespace *user_ns, struct dentry *parent, +int ksmbd_vfs_lock_parent(struct mnt_idmap *idmap, struct dentry *parent, struct dentry *child) { struct dentry *dentry; int ret = 0; inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); - dentry = lookup_one(user_ns, child->d_name.name, parent, + dentry = lookup_one(idmap, child->d_name.name, parent, child->d_name.len); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); @@ -96,20 +97,20 @@ out_err: return ret; } -int ksmbd_vfs_may_delete(struct user_namespace *user_ns, +int ksmbd_vfs_may_delete(struct mnt_idmap *idmap, struct dentry *dentry) { struct dentry *parent; int ret; parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(user_ns, parent, dentry); + ret = ksmbd_vfs_lock_parent(idmap, parent, dentry); if (ret) { dput(parent); return ret; } - ret = inode_permission(user_ns, d_inode(parent), + ret = inode_permission(idmap, d_inode(parent), MAY_EXEC | MAY_WRITE); inode_unlock(d_inode(parent)); @@ -117,7 +118,7 @@ int ksmbd_vfs_may_delete(struct user_namespace *user_ns, return ret; } -int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, +int ksmbd_vfs_query_maximal_access(struct mnt_idmap *idmap, struct dentry *dentry, __le32 *daccess) { struct dentry *parent; @@ -125,26 +126,26 @@ int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, *daccess = cpu_to_le32(FILE_READ_ATTRIBUTES | READ_CONTROL); - if (!inode_permission(user_ns, d_inode(dentry), MAY_OPEN | MAY_WRITE)) + if (!inode_permission(idmap, d_inode(dentry), MAY_OPEN | MAY_WRITE)) *daccess |= cpu_to_le32(WRITE_DAC | WRITE_OWNER | SYNCHRONIZE | FILE_WRITE_DATA | FILE_APPEND_DATA | FILE_WRITE_EA | FILE_WRITE_ATTRIBUTES | FILE_DELETE_CHILD); - if (!inode_permission(user_ns, d_inode(dentry), MAY_OPEN | MAY_READ)) + if (!inode_permission(idmap, d_inode(dentry), MAY_OPEN | MAY_READ)) *daccess |= FILE_READ_DATA_LE | FILE_READ_EA_LE; - if (!inode_permission(user_ns, d_inode(dentry), MAY_OPEN | MAY_EXEC)) + if (!inode_permission(idmap, d_inode(dentry), MAY_OPEN | MAY_EXEC)) *daccess |= FILE_EXECUTE_LE; parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(user_ns, parent, dentry); + ret = ksmbd_vfs_lock_parent(idmap, parent, dentry); if (ret) { dput(parent); return ret; } - if (!inode_permission(user_ns, d_inode(parent), MAY_EXEC | MAY_WRITE)) + if (!inode_permission(idmap, d_inode(parent), MAY_EXEC | MAY_WRITE)) *daccess |= FILE_DELETE_LE; inode_unlock(d_inode(parent)); @@ -177,7 +178,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) } mode |= S_IFREG; - err = vfs_create(mnt_user_ns(path.mnt), d_inode(path.dentry), + err = vfs_create(mnt_idmap(path.mnt), d_inode(path.dentry), dentry, mode, true); if (!err) { ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), @@ -199,7 +200,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) */ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) { - struct user_namespace *user_ns; + struct mnt_idmap *idmap; struct path path; struct dentry *dentry; int err; @@ -215,15 +216,15 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) return err; } - user_ns = mnt_user_ns(path.mnt); + idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; - err = vfs_mkdir(user_ns, d_inode(path.dentry), dentry, mode); + err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); if (err) { goto out; } else if (d_unhashed(dentry)) { struct dentry *d; - d = lookup_one(user_ns, dentry->d_name.name, dentry->d_parent, + d = lookup_one(idmap, dentry->d_name.name, dentry->d_parent, dentry->d_name.len); if (IS_ERR(d)) { err = PTR_ERR(d); @@ -245,7 +246,7 @@ out: return err; } -static ssize_t ksmbd_vfs_getcasexattr(struct user_namespace *user_ns, +static ssize_t ksmbd_vfs_getcasexattr(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name, int attr_name_len, char **attr_value) { @@ -262,7 +263,7 @@ static ssize_t ksmbd_vfs_getcasexattr(struct user_namespace *user_ns, if (strncasecmp(attr_name, name, attr_name_len)) continue; - value_len = ksmbd_vfs_getxattr(user_ns, + value_len = ksmbd_vfs_getxattr(idmap, dentry, name, attr_value); @@ -285,7 +286,7 @@ static int ksmbd_vfs_stream_read(struct ksmbd_file *fp, char *buf, loff_t *pos, ksmbd_debug(VFS, "read stream data pos : %llu, count : %zd\n", *pos, count); - v_len = ksmbd_vfs_getcasexattr(file_mnt_user_ns(fp->filp), + v_len = ksmbd_vfs_getcasexattr(file_mnt_idmap(fp->filp), fp->filp->f_path.dentry, fp->stream.name, fp->stream.size, @@ -409,7 +410,7 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, size_t count) { char *stream_buf = NULL, *wbuf; - struct user_namespace *user_ns = file_mnt_user_ns(fp->filp); + struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); size_t size, v_len; int err = 0; @@ -422,7 +423,7 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, count = (*pos + count) - XATTR_SIZE_MAX; } - v_len = ksmbd_vfs_getcasexattr(user_ns, + v_len = ksmbd_vfs_getcasexattr(idmap, fp->filp->f_path.dentry, fp->stream.name, fp->stream.size, @@ -448,7 +449,7 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, memcpy(&stream_buf[*pos], buf, count); - err = ksmbd_vfs_setxattr(user_ns, + err = ksmbd_vfs_setxattr(idmap, fp->filp->f_path.dentry, fp->stream.name, (void *)stream_buf, @@ -583,7 +584,7 @@ int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id) */ int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) { - struct user_namespace *user_ns; + struct mnt_idmap *idmap; struct path path; struct dentry *parent; int err; @@ -598,9 +599,9 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) return err; } - user_ns = mnt_user_ns(path.mnt); + idmap = mnt_idmap(path.mnt); parent = dget_parent(path.dentry); - err = ksmbd_vfs_lock_parent(user_ns, parent, path.dentry); + err = ksmbd_vfs_lock_parent(idmap, parent, path.dentry); if (err) { dput(parent); path_put(&path); @@ -614,12 +615,12 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) } if (S_ISDIR(d_inode(path.dentry)->i_mode)) { - err = vfs_rmdir(user_ns, d_inode(parent), path.dentry); + err = vfs_rmdir(idmap, d_inode(parent), path.dentry); if (err && err != -ENOTEMPTY) ksmbd_debug(VFS, "%s: rmdir failed, err %d\n", name, err); } else { - err = vfs_unlink(user_ns, d_inode(parent), path.dentry, NULL); + err = vfs_unlink(idmap, d_inode(parent), path.dentry, NULL); if (err) ksmbd_debug(VFS, "%s: unlink failed, err %d\n", name, err); @@ -672,7 +673,7 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, goto out3; } - err = vfs_link(oldpath.dentry, mnt_user_ns(newpath.mnt), + err = vfs_link(oldpath.dentry, mnt_idmap(newpath.mnt), d_inode(newpath.dentry), dentry, NULL); if (err) @@ -711,10 +712,10 @@ static int ksmbd_validate_entry_in_use(struct dentry *src_dent) } static int __ksmbd_vfs_rename(struct ksmbd_work *work, - struct user_namespace *src_user_ns, + struct mnt_idmap *src_idmap, struct dentry *src_dent_parent, struct dentry *src_dent, - struct user_namespace *dst_user_ns, + struct mnt_idmap *dst_idmap, struct dentry *dst_dent_parent, struct dentry *trap_dent, char *dst_name) @@ -740,8 +741,8 @@ static int __ksmbd_vfs_rename(struct ksmbd_work *work, if (ksmbd_override_fsids(work)) return -ENOMEM; - dst_dent = lookup_one(dst_user_ns, dst_name, dst_dent_parent, - strlen(dst_name)); + dst_dent = lookup_one(dst_idmap, dst_name, + dst_dent_parent, strlen(dst_name)); err = PTR_ERR(dst_dent); if (IS_ERR(dst_dent)) { pr_err("lookup failed %s [%d]\n", dst_name, err); @@ -751,10 +752,10 @@ static int __ksmbd_vfs_rename(struct ksmbd_work *work, err = -ENOTEMPTY; if (dst_dent != trap_dent && !d_really_is_positive(dst_dent)) { struct renamedata rd = { - .old_mnt_userns = src_user_ns, + .old_mnt_idmap = src_idmap, .old_dir = d_inode(src_dent_parent), .old_dentry = src_dent, - .new_mnt_userns = dst_user_ns, + .new_mnt_idmap = dst_idmap, .new_dir = d_inode(dst_dent_parent), .new_dentry = dst_dent, }; @@ -772,7 +773,7 @@ out: int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, char *newname) { - struct user_namespace *user_ns; + struct mnt_idmap *idmap; struct path dst_path; struct dentry *src_dent_parent, *dst_dent_parent; struct dentry *src_dent, *trap_dent, *src_child; @@ -800,8 +801,8 @@ int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, trap_dent = lock_rename(src_dent_parent, dst_dent_parent); dget(src_dent); dget(dst_dent_parent); - user_ns = file_mnt_user_ns(fp->filp); - src_child = lookup_one(user_ns, src_dent->d_name.name, src_dent_parent, + idmap = file_mnt_idmap(fp->filp); + src_child = lookup_one(idmap, src_dent->d_name.name, src_dent_parent, src_dent->d_name.len); if (IS_ERR(src_child)) { err = PTR_ERR(src_child); @@ -816,10 +817,10 @@ int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, dput(src_child); err = __ksmbd_vfs_rename(work, - user_ns, + idmap, src_dent_parent, src_dent, - mnt_user_ns(dst_path.mnt), + mnt_idmap(dst_path.mnt), dst_dent_parent, trap_dent, dst_name); @@ -907,22 +908,22 @@ ssize_t ksmbd_vfs_listxattr(struct dentry *dentry, char **list) return size; } -static ssize_t ksmbd_vfs_xattr_len(struct user_namespace *user_ns, +static ssize_t ksmbd_vfs_xattr_len(struct mnt_idmap *idmap, struct dentry *dentry, char *xattr_name) { - return vfs_getxattr(user_ns, dentry, xattr_name, NULL, 0); + return vfs_getxattr(idmap, dentry, xattr_name, NULL, 0); } /** * ksmbd_vfs_getxattr() - vfs helper for smb get extended attributes value - * @user_ns: user namespace + * @idmap: idmap * @dentry: dentry of file for getting xattrs * @xattr_name: name of xattr name to query * @xattr_buf: destination buffer xattr value * * Return: read xattr value length on success, otherwise error */ -ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, +ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry, char *xattr_name, char **xattr_buf) { @@ -930,7 +931,7 @@ ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, char *buf; *xattr_buf = NULL; - xattr_len = ksmbd_vfs_xattr_len(user_ns, dentry, xattr_name); + xattr_len = ksmbd_vfs_xattr_len(idmap, dentry, xattr_name); if (xattr_len < 0) return xattr_len; @@ -938,7 +939,7 @@ ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, if (!buf) return -ENOMEM; - xattr_len = vfs_getxattr(user_ns, dentry, xattr_name, + xattr_len = vfs_getxattr(idmap, dentry, xattr_name, (void *)buf, xattr_len); if (xattr_len > 0) *xattr_buf = buf; @@ -949,7 +950,7 @@ ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, /** * ksmbd_vfs_setxattr() - vfs helper for smb set extended attributes value - * @user_ns: user namespace + * @idmap: idmap of the relevant mount * @dentry: dentry to set XATTR at * @name: xattr name for setxattr * @value: xattr value to set @@ -958,13 +959,13 @@ ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_setxattr(struct user_namespace *user_ns, +int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *attr_name, void *attr_value, size_t attr_size, int flags) { int err; - err = vfs_setxattr(user_ns, + err = vfs_setxattr(idmap, dentry, attr_name, attr_value, @@ -1074,26 +1075,26 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, return ret; } -int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns, +int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name) { - return vfs_removexattr(user_ns, dentry, attr_name); + return vfs_removexattr(idmap, dentry, attr_name); } -int ksmbd_vfs_unlink(struct user_namespace *user_ns, +int ksmbd_vfs_unlink(struct mnt_idmap *idmap, struct dentry *dir, struct dentry *dentry) { int err = 0; - err = ksmbd_vfs_lock_parent(user_ns, dir, dentry); + err = ksmbd_vfs_lock_parent(idmap, dir, dentry); if (err) return err; dget(dentry); if (S_ISDIR(d_inode(dentry)->i_mode)) - err = vfs_rmdir(user_ns, d_inode(dir), dentry); + err = vfs_rmdir(idmap, d_inode(dir), dentry); else - err = vfs_unlink(user_ns, d_inode(dir), dentry, NULL); + err = vfs_unlink(idmap, d_inode(dir), dentry, NULL); dput(dentry); inode_unlock(d_inode(dir)); @@ -1298,7 +1299,7 @@ struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, return dent; } -int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, +int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, struct dentry *dentry) { char *name, *xattr_list = NULL; @@ -1321,7 +1322,7 @@ int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1) || !strncmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1)) { - err = vfs_remove_acl(user_ns, dentry, name); + err = vfs_remove_acl(idmap, dentry, name); if (err) ksmbd_debug(SMB, "remove acl xattr failed : %s\n", name); @@ -1332,7 +1333,7 @@ out: return err; } -int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, +int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, struct dentry *dentry) { char *name, *xattr_list = NULL; @@ -1352,7 +1353,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(user_ns, dentry, name); + err = ksmbd_vfs_remove_xattr(idmap, dentry, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } @@ -1362,7 +1363,7 @@ out: return err; } -static struct xattr_smb_acl *ksmbd_vfs_make_xattr_posix_acl(struct user_namespace *user_ns, +static struct xattr_smb_acl *ksmbd_vfs_make_xattr_posix_acl(struct mnt_idmap *idmap, struct inode *inode, int acl_type) { @@ -1392,14 +1393,14 @@ static struct xattr_smb_acl *ksmbd_vfs_make_xattr_posix_acl(struct user_namespac switch (pa_entry->e_tag) { case ACL_USER: xa_entry->type = SMB_ACL_USER; - xa_entry->uid = posix_acl_uid_translate(user_ns, pa_entry); + xa_entry->uid = posix_acl_uid_translate(idmap, pa_entry); break; case ACL_USER_OBJ: xa_entry->type = SMB_ACL_USER_OBJ; break; case ACL_GROUP: xa_entry->type = SMB_ACL_GROUP; - xa_entry->gid = posix_acl_gid_translate(user_ns, pa_entry); + xa_entry->gid = posix_acl_gid_translate(idmap, pa_entry); break; case ACL_GROUP_OBJ: xa_entry->type = SMB_ACL_GROUP_OBJ; @@ -1428,7 +1429,7 @@ out: } int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd *pntsd, int len) { @@ -1461,13 +1462,13 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, return rc; } - smb_acl = ksmbd_vfs_make_xattr_posix_acl(user_ns, inode, + smb_acl = ksmbd_vfs_make_xattr_posix_acl(idmap, inode, ACL_TYPE_ACCESS); if (S_ISDIR(inode->i_mode)) - def_smb_acl = ksmbd_vfs_make_xattr_posix_acl(user_ns, inode, + def_smb_acl = ksmbd_vfs_make_xattr_posix_acl(idmap, inode, ACL_TYPE_DEFAULT); - rc = ndr_encode_posix_acl(&acl_ndr, user_ns, inode, + rc = ndr_encode_posix_acl(&acl_ndr, idmap, inode, smb_acl, def_smb_acl); if (rc) { pr_err("failed to encode ndr to posix acl\n"); @@ -1487,7 +1488,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, goto out; } - rc = ksmbd_vfs_setxattr(user_ns, dentry, + rc = ksmbd_vfs_setxattr(idmap, dentry, XATTR_NAME_SD, sd_ndr.data, sd_ndr.offset, 0); if (rc < 0) @@ -1502,7 +1503,7 @@ out: } int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd **pntsd) { @@ -1514,7 +1515,7 @@ int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, struct xattr_smb_acl *smb_acl = NULL, *def_smb_acl = NULL; __u8 cmp_hash[XATTR_SD_HASH_SIZE] = {0}; - rc = ksmbd_vfs_getxattr(user_ns, dentry, XATTR_NAME_SD, &n.data); + rc = ksmbd_vfs_getxattr(idmap, dentry, XATTR_NAME_SD, &n.data); if (rc <= 0) return rc; @@ -1523,13 +1524,13 @@ int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, if (rc) goto free_n_data; - smb_acl = ksmbd_vfs_make_xattr_posix_acl(user_ns, inode, + smb_acl = ksmbd_vfs_make_xattr_posix_acl(idmap, inode, ACL_TYPE_ACCESS); if (S_ISDIR(inode->i_mode)) - def_smb_acl = ksmbd_vfs_make_xattr_posix_acl(user_ns, inode, + def_smb_acl = ksmbd_vfs_make_xattr_posix_acl(idmap, inode, ACL_TYPE_DEFAULT); - rc = ndr_encode_posix_acl(&acl_ndr, user_ns, inode, smb_acl, + rc = ndr_encode_posix_acl(&acl_ndr, idmap, inode, smb_acl, def_smb_acl); if (rc) { pr_err("failed to encode ndr to posix acl\n"); @@ -1576,7 +1577,7 @@ free_n_data: return rc; } -int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, +int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da) { @@ -1587,7 +1588,7 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, if (err) return err; - err = ksmbd_vfs_setxattr(user_ns, dentry, XATTR_NAME_DOS_ATTRIBUTE, + err = ksmbd_vfs_setxattr(idmap, dentry, XATTR_NAME_DOS_ATTRIBUTE, (void *)n.data, n.offset, 0); if (err) ksmbd_debug(SMB, "failed to store dos attribute in xattr\n"); @@ -1596,14 +1597,14 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, return err; } -int ksmbd_vfs_get_dos_attrib_xattr(struct user_namespace *user_ns, +int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da) { struct ndr n; int err; - err = ksmbd_vfs_getxattr(user_ns, dentry, XATTR_NAME_DOS_ATTRIBUTE, + err = ksmbd_vfs_getxattr(idmap, dentry, XATTR_NAME_DOS_ATTRIBUTE, (char **)&n.data); if (err > 0) { n.length = err; @@ -1650,14 +1651,14 @@ void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat) } int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat) { u64 time; int rc; - generic_fillattr(user_ns, d_inode(dentry), ksmbd_kstat->kstat); + generic_fillattr(idmap, d_inode(dentry), ksmbd_kstat->kstat); time = ksmbd_UnixTimeToNT(ksmbd_kstat->kstat->ctime); ksmbd_kstat->create_time = time; @@ -1675,7 +1676,7 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS)) { struct xattr_dos_attrib da; - rc = ksmbd_vfs_get_dos_attrib_xattr(user_ns, dentry, &da); + rc = ksmbd_vfs_get_dos_attrib_xattr(idmap, dentry, &da); if (rc > 0) { ksmbd_kstat->file_attributes = cpu_to_le32(da.attr); ksmbd_kstat->create_time = da.create_time; @@ -1687,7 +1688,7 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, return 0; } -ssize_t ksmbd_vfs_casexattr_len(struct user_namespace *user_ns, +ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name, int attr_name_len) { @@ -1704,7 +1705,7 @@ ssize_t ksmbd_vfs_casexattr_len(struct user_namespace *user_ns, if (strncasecmp(attr_name, name, attr_name_len)) continue; - value_len = ksmbd_vfs_xattr_len(user_ns, dentry, name); + value_len = ksmbd_vfs_xattr_len(idmap, dentry, name); break; } @@ -1823,7 +1824,7 @@ void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock) locks_delete_block(flock); } -int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, +int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry) { struct posix_acl_state acl_state; @@ -1857,13 +1858,13 @@ int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, return -ENOMEM; } posix_state_to_acl(&acl_state, acls->a_entries); - rc = set_posix_acl(user_ns, dentry, ACL_TYPE_ACCESS, acls); + rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", rc); else if (S_ISDIR(inode->i_mode)) { posix_state_to_acl(&acl_state, acls->a_entries); - rc = set_posix_acl(user_ns, dentry, ACL_TYPE_DEFAULT, acls); + rc = set_posix_acl(idmap, dentry, ACL_TYPE_DEFAULT, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); @@ -1873,7 +1874,7 @@ int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, return rc; } -int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns, +int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *parent_inode) { struct posix_acl *acls; @@ -1896,12 +1897,12 @@ int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns, } } - rc = set_posix_acl(user_ns, dentry, ACL_TYPE_ACCESS, acls); + rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", rc); if (S_ISDIR(inode->i_mode)) { - rc = set_posix_acl(user_ns, dentry, ACL_TYPE_DEFAULT, + rc = set_posix_acl(idmap, dentry, ACL_TYPE_DEFAULT, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index 0d73d735cc39..9d676ab0cd25 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -71,10 +71,10 @@ struct ksmbd_kstat { __le32 file_attributes; }; -int ksmbd_vfs_lock_parent(struct user_namespace *user_ns, struct dentry *parent, +int ksmbd_vfs_lock_parent(struct mnt_idmap *idmap, struct dentry *parent, struct dentry *child); -int ksmbd_vfs_may_delete(struct user_namespace *user_ns, struct dentry *dentry); -int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, +int ksmbd_vfs_may_delete(struct mnt_idmap *idmap, struct dentry *dentry); +int ksmbd_vfs_query_maximal_access(struct mnt_idmap *idmap, struct dentry *dentry, __le32 *daccess); int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode); int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode); @@ -102,19 +102,19 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, unsigned int *chunk_size_written, loff_t *total_size_written); ssize_t ksmbd_vfs_listxattr(struct dentry *dentry, char **list); -ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, +ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry, char *xattr_name, char **xattr_buf); -ssize_t ksmbd_vfs_casexattr_len(struct user_namespace *user_ns, +ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name, int attr_name_len); -int ksmbd_vfs_setxattr(struct user_namespace *user_ns, +int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *attr_name, void *attr_value, size_t attr_size, int flags); int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); -int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns, +int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name); int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, unsigned int flags, struct path *path, @@ -131,37 +131,37 @@ struct file_allocated_range_buffer; int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, struct file_allocated_range_buffer *ranges, unsigned int in_count, unsigned int *out_count); -int ksmbd_vfs_unlink(struct user_namespace *user_ns, - struct dentry *dir, struct dentry *dentry); +int ksmbd_vfs_unlink(struct mnt_idmap *idmap, struct dentry *dir, + struct dentry *dentry); void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat); int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat); void ksmbd_vfs_posix_lock_wait(struct file_lock *flock); int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout); void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock); -int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, +int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, struct dentry *dentry); -int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, +int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, struct dentry *dentry); int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd *pntsd, int len); int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, - struct user_namespace *user_ns, + struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd **pntsd); -int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, +int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da); -int ksmbd_vfs_get_dos_attrib_xattr(struct user_namespace *user_ns, +int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da); -int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, +int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry); -int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns, +int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *parent_inode); #endif /* __KSMBD_VFS_H__ */ diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index da9163b00350..1d8126443a7f 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -5,6 +5,7 @@ */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -251,7 +252,7 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) filp = fp->filp; if (ksmbd_stream_fd(fp) && (ci->m_flags & S_DEL_ON_CLS_STREAM)) { ci->m_flags &= ~S_DEL_ON_CLS_STREAM; - err = ksmbd_vfs_remove_xattr(file_mnt_user_ns(filp), + err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), filp->f_path.dentry, fp->stream.name); if (err) @@ -266,7 +267,7 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) dir = dentry->d_parent; ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); write_unlock(&ci->m_lock); - ksmbd_vfs_unlink(file_mnt_user_ns(filp), dir, dentry); + ksmbd_vfs_unlink(file_mnt_idmap(filp), dir, dentry); write_lock(&ci->m_lock); } write_unlock(&ci->m_lock); diff --git a/fs/libfs.c b/fs/libfs.c index aada4e7c8713..4eda519c3002 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -28,12 +28,12 @@ #include "internal.h" -int simple_getattr(struct user_namespace *mnt_userns, const struct path *path, +int simple_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } @@ -473,7 +473,7 @@ int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, } EXPORT_SYMBOL_GPL(simple_rename_exchange); -int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +int simple_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -509,7 +509,7 @@ EXPORT_SYMBOL(simple_rename); /** * simple_setattr - setattr for simple filesystem - * @mnt_userns: user namespace of the target mount + * @idmap: idmap of the target mount * @dentry: dentry * @iattr: iattr structure * @@ -522,19 +522,19 @@ EXPORT_SYMBOL(simple_rename); * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ -int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int simple_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(mnt_userns, dentry, iattr); + error = setattr_prepare(idmap, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); - setattr_copy(mnt_userns, inode, iattr); + setattr_copy(idmap, inode, iattr); mark_inode_dirty(inode); return 0; } @@ -1315,16 +1315,16 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ENOENT); } -static int empty_dir_getattr(struct user_namespace *mnt_userns, +static int empty_dir_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; } -static int empty_dir_setattr(struct user_namespace *mnt_userns, +static int empty_dir_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EPERM; @@ -1582,3 +1582,39 @@ bool inode_maybe_inc_iversion(struct inode *inode, bool force) return true; } EXPORT_SYMBOL(inode_maybe_inc_iversion); + +/** + * inode_query_iversion - read i_version for later use + * @inode: inode from which i_version should be read + * + * Read the inode i_version counter. This should be used by callers that wish + * to store the returned i_version for later comparison. This will guarantee + * that a later query of the i_version will result in a different value if + * anything has changed. + * + * In this implementation, we fetch the current value, set the QUERIED flag and + * then try to swap it into place with a cmpxchg, if it wasn't already set. If + * that fails, we try again with the newly fetched value from the cmpxchg. + */ +u64 inode_query_iversion(struct inode *inode) +{ + u64 cur, new; + + cur = inode_peek_iversion_raw(inode); + do { + /* If flag is already set, then no need to swap */ + if (cur & I_VERSION_QUERIED) { + /* + * This barrier (and the implicit barrier in the + * cmpxchg below) pairs with the barrier in + * inode_maybe_inc_iversion(). + */ + smp_mb(); + break; + } + + new = cur | I_VERSION_QUERIED; + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); + return cur >> I_VERSION_QUERIED_SHIFT; +} +EXPORT_SYMBOL(inode_query_iversion); diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index a5bb3f721a9d..82b19a30e0f0 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -188,7 +188,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock) continue; if (!rpc_cmp_addr(nlm_addr(block->b_host), addr)) continue; - if (nfs_compare_fh(NFS_FH(locks_inode(fl_blocked->fl_file)), fh) != 0) + if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->fl_file)), fh) != 0) continue; /* Alright, we found a lock. Set the return status * and wake up the caller diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 99fffc9cb958..16b4de868cd2 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -12,6 +12,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/nfs_fs.h> #include <linux/utsname.h> #include <linux/freezer.h> @@ -130,7 +131,7 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl) char *nodename = req->a_host->h_rpcclnt->cl_nodename; nlmclnt_next_cookie(&argp->cookie); - memcpy(&lock->fh, NFS_FH(locks_inode(fl->fl_file)), sizeof(struct nfs_fh)); + memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh)); lock->caller = nodename; lock->oh.data = req->a_owner; lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s", diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h index 5bec78c8e431..17432c445fe6 100644 --- a/fs/lockd/netns.h +++ b/fs/lockd/netns.h @@ -3,6 +3,7 @@ #define __LOCKD_NETNS_H__ #include <linux/fs.h> +#include <linux/filelock.h> #include <net/netns/generic.h> struct lockd_net { diff --git a/fs/locks.c b/fs/locks.c index 8f01bee17715..624c6ac92ede 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -52,6 +52,7 @@ #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/filelock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> @@ -233,7 +234,7 @@ locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { struct file_lock *fl; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); list_for_each_entry(fl, list, fl_list) if (fl->fl_file == filp) @@ -887,7 +888,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); void *owner; void (*func)(void); @@ -1330,7 +1331,7 @@ retry: int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return posix_lock_inode(locks_inode(filp), fl, conflock); + return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); @@ -1629,7 +1630,7 @@ EXPORT_SYMBOL(lease_get_mtime); int fcntl_getlease(struct file *filp) { struct file_lock *fl; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); @@ -1667,7 +1668,7 @@ int fcntl_getlease(struct file *filp) static int check_conflicting_open(struct file *filp, const long arg, int flags) { - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) @@ -1703,7 +1704,7 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct file_lock *fl, *my_fl = NULL, *lease; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; @@ -1819,7 +1820,7 @@ static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); @@ -1861,7 +1862,7 @@ static int generic_delete_lease(struct file *filp, void *owner) int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); int error; if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) @@ -2350,7 +2351,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file *f; int error; @@ -2554,7 +2555,7 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock lock; struct file_lock_context *ctx; @@ -2591,7 +2592,7 @@ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); if (list_empty(&flctx->flc_flock)) return; @@ -2636,7 +2637,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; - ctx = locks_inode_context(locks_inode(filp)); + ctx = locks_inode_context(file_inode(filp)); if (!ctx) return; @@ -2720,7 +2721,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, */ if (fl->fl_file != NULL) - inode = locks_inode(fl->fl_file); + inode = file_inode(fl->fl_file); seq_printf(f, "%lld: ", id); @@ -2861,7 +2862,7 @@ static void __show_fd_locks(struct seq_file *f, void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int id = 0; diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index 9115948c624e..724d8191a310 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -252,7 +252,7 @@ struct inode *minix_new_inode(const struct inode *dir, umode_t mode, int *error) iput(inode); return NULL; } - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = j; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_blocks = 0; diff --git a/fs/minix/file.c b/fs/minix/file.c index 6a7bd2d9eec0..0dd05d47724a 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -22,13 +22,13 @@ const struct file_operations minix_file_operations = { .splice_read = generic_file_splice_read, }; -static int minix_setattr(struct user_namespace *mnt_userns, +static int minix_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -42,7 +42,7 @@ static int minix_setattr(struct user_namespace *mnt_userns, minix_truncate(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index da8bdd1712a7..e9fbb5303a22 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -654,13 +654,13 @@ static int minix_write_inode(struct inode *inode, struct writeback_control *wbc) return err; } -int minix_getattr(struct user_namespace *mnt_userns, const struct path *path, +int minix_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct super_block *sb = path->dentry->d_sb; struct inode *inode = d_inode(path->dentry); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (INODE_VERSION(inode) == MINIX_V1) stat->blocks = (BLOCK_SIZE / 512) * V1_minix_blocks(stat->size, sb); else diff --git a/fs/minix/minix.h b/fs/minix/minix.h index 202173368025..e0b76defa85c 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -51,7 +51,7 @@ extern unsigned long minix_count_free_inodes(struct super_block *sb); extern int minix_new_block(struct inode * inode); extern void minix_free_block(struct inode *inode, unsigned long block); extern unsigned long minix_count_free_blocks(struct super_block *sb); -extern int minix_getattr(struct user_namespace *, const struct path *, +extern int minix_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len); diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 8afdc408ca4f..39ebe10d6a8b 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -33,7 +33,7 @@ static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, un return d_splice_alias(inode, dentry); } -static int minix_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int minix_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { int error; @@ -52,7 +52,7 @@ static int minix_mknod(struct user_namespace *mnt_userns, struct inode *dir, return error; } -static int minix_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int minix_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { int error; @@ -65,13 +65,13 @@ static int minix_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return finish_open_simple(file, error); } -static int minix_create(struct user_namespace *mnt_userns, struct inode *dir, +static int minix_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return minix_mknod(mnt_userns, dir, dentry, mode, 0); + return minix_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); } -static int minix_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int minix_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int err = -ENAMETOOLONG; @@ -111,7 +111,7 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir, return add_nondir(dentry, inode); } -static int minix_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int minix_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode * inode; @@ -184,7 +184,7 @@ static int minix_rmdir(struct inode * dir, struct dentry *dentry) return err; } -static int minix_rename(struct user_namespace *mnt_userns, +static int minix_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c new file mode 100644 index 000000000000..4905665c47d0 --- /dev/null +++ b/fs/mnt_idmapping.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */ + +#include <linux/cred.h> +#include <linux/fs.h> +#include <linux/mnt_idmapping.h> +#include <linux/slab.h> +#include <linux/user_namespace.h> + +#include "internal.h" + +struct mnt_idmap { + struct user_namespace *owner; + refcount_t count; +}; + +/* + * Carries the initial idmapping of 0:0:4294967295 which is an identity + * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is + * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. + */ +struct mnt_idmap nop_mnt_idmap = { + .owner = &init_user_ns, + .count = REFCOUNT_INIT(1), +}; +EXPORT_SYMBOL_GPL(nop_mnt_idmap); + +/** + * check_fsmapping - check whether an mount idmapping is allowed + * @idmap: idmap of the relevent mount + * @sb: super block of the filesystem + * + * Return: true if @idmap is allowed, false if not. + */ +bool check_fsmapping(const struct mnt_idmap *idmap, + const struct super_block *sb) +{ + return idmap->owner != sb->s_user_ns; +} + +/** + * initial_idmapping - check whether this is the initial mapping + * @ns: idmapping to check + * + * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, + * [...], 1000 to 1000 [...]. + * + * Return: true if this is the initial mapping, false if not. + */ +static inline bool initial_idmapping(const struct user_namespace *ns) +{ + return ns == &init_user_ns; +} + +/** + * no_idmapping - check whether we can skip remapping a kuid/gid + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * This function can be used to check whether a remapping between two + * idmappings is required. + * An idmapped mount is a mount that has an idmapping attached to it that + * is different from the filsystem's idmapping and the initial idmapping. + * If the initial mapping is used or the idmapping of the mount and the + * filesystem are identical no remapping is required. + * + * Return: true if remapping can be skipped, false if not. + */ +static inline bool no_idmapping(const struct user_namespace *mnt_userns, + const struct user_namespace *fs_userns) +{ + return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; +} + +/** + * make_vfsuid - map a filesystem kuid according to an idmapping + * @idmap: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Take a @kuid and remap it from @fs_userns into @idmap. Use this + * function when preparing a @kuid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * from_kuid() so we can simply retrieve the value via __kuid_val() + * directly. + * + * Return: @kuid mapped according to @idmap. + * If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is + * returned. + */ + +vfsuid_t make_vfsuid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + struct user_namespace *mnt_userns = idmap->owner; + + if (no_idmapping(mnt_userns, fs_userns)) + return VFSUIDT_INIT(kuid); + if (initial_idmapping(fs_userns)) + uid = __kuid_val(kuid); + else + uid = from_kuid(fs_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_VFSUID; + return VFSUIDT_INIT(make_kuid(mnt_userns, uid)); +} +EXPORT_SYMBOL_GPL(make_vfsuid); + +/** + * make_vfsgid - map a filesystem kgid according to an idmapping + * @idmap: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Take a @kgid and remap it from @fs_userns into @idmap. Use this + * function when preparing a @kgid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * from_kgid() so we can simply retrieve the value via __kgid_val() + * directly. + * + * Return: @kgid mapped according to @idmap. + * If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is + * returned. + */ +vfsgid_t make_vfsgid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, kgid_t kgid) +{ + gid_t gid; + struct user_namespace *mnt_userns = idmap->owner; + + if (no_idmapping(mnt_userns, fs_userns)) + return VFSGIDT_INIT(kgid); + if (initial_idmapping(fs_userns)) + gid = __kgid_val(kgid); + else + gid = from_kgid(fs_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_VFSGID; + return VFSGIDT_INIT(make_kgid(mnt_userns, gid)); +} +EXPORT_SYMBOL_GPL(make_vfsgid); + +/** + * from_vfsuid - map a vfsuid into the filesystem idmapping + * @idmap: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @vfsuid : vfsuid to be mapped + * + * Map @vfsuid into the filesystem idmapping. This function has to be used in + * order to e.g. write @vfsuid to inode->i_uid. + * + * Return: @vfsuid mapped into the filesystem idmapping + */ +kuid_t from_vfsuid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, vfsuid_t vfsuid) +{ + uid_t uid; + struct user_namespace *mnt_userns = idmap->owner; + + if (no_idmapping(mnt_userns, fs_userns)) + return AS_KUIDT(vfsuid); + uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid)); + if (uid == (uid_t)-1) + return INVALID_UID; + if (initial_idmapping(fs_userns)) + return KUIDT_INIT(uid); + return make_kuid(fs_userns, uid); +} +EXPORT_SYMBOL_GPL(from_vfsuid); + +/** + * from_vfsgid - map a vfsgid into the filesystem idmapping + * @idmap: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @vfsgid : vfsgid to be mapped + * + * Map @vfsgid into the filesystem idmapping. This function has to be used in + * order to e.g. write @vfsgid to inode->i_gid. + * + * Return: @vfsgid mapped into the filesystem idmapping + */ +kgid_t from_vfsgid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, vfsgid_t vfsgid) +{ + gid_t gid; + struct user_namespace *mnt_userns = idmap->owner; + + if (no_idmapping(mnt_userns, fs_userns)) + return AS_KGIDT(vfsgid); + gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid)); + if (gid == (gid_t)-1) + return INVALID_GID; + if (initial_idmapping(fs_userns)) + return KGIDT_INIT(gid); + return make_kgid(fs_userns, gid); +} +EXPORT_SYMBOL_GPL(from_vfsgid); + +#ifdef CONFIG_MULTIUSER +/** + * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups + * @vfsgid: the mnt gid to match + * + * This function can be used to determine whether @vfsuid matches any of the + * caller's groups. + * + * Return: 1 if vfsuid matches caller's groups, 0 if not. + */ +int vfsgid_in_group_p(vfsgid_t vfsgid) +{ + return in_group_p(AS_KGIDT(vfsgid)); +} +#else +int vfsgid_in_group_p(vfsgid_t vfsgid) +{ + return 1; +} +#endif +EXPORT_SYMBOL_GPL(vfsgid_in_group_p); + +struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) +{ + struct mnt_idmap *idmap; + + idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); + if (!idmap) + return ERR_PTR(-ENOMEM); + + idmap->owner = get_user_ns(mnt_userns); + refcount_set(&idmap->count, 1); + return idmap; +} + +/** + * mnt_idmap_get - get a reference to an idmapping + * @idmap: the idmap to bump the reference on + * + * If @idmap is not the @nop_mnt_idmap bump the reference count. + * + * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. + */ +struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) +{ + if (idmap != &nop_mnt_idmap) + refcount_inc(&idmap->count); + + return idmap; +} + +/** + * mnt_idmap_put - put a reference to an idmapping + * @idmap: the idmap to put the reference on + * + * If this is a non-initial idmapping, put the reference count when a mount is + * released and free it if we're the last user. + */ +void mnt_idmap_put(struct mnt_idmap *idmap) +{ + if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) { + put_user_ns(idmap->owner); + kfree(idmap); + } +} diff --git a/fs/mpage.c b/fs/mpage.c index 0f8ae954a579..ce53179428db 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -532,6 +532,8 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, map_bh.b_size = 1 << blkbits; if (mpd->get_block(inode, block_in_file, &map_bh, 1)) goto confused; + if (!buffer_mapped(&map_bh)) + goto confused; if (buffer_new(&map_bh)) clean_bdev_bh_alias(&map_bh); if (buffer_boundary(&map_bh)) { diff --git a/fs/namei.c b/fs/namei.c index 309ae6fc8c99..5855dc6edbd5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> @@ -273,7 +274,7 @@ void putname(struct filename *name) /** * check_acl - perform ACL permission checking - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * @@ -281,13 +282,13 @@ void putname(struct filename *name) * retrieve POSIX acls it needs to know whether it is called from a blocking or * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -static int check_acl(struct user_namespace *mnt_userns, +static int check_acl(struct mnt_idmap *idmap, struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL @@ -300,14 +301,14 @@ static int check_acl(struct user_namespace *mnt_userns, /* no ->get_inode_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; - return posix_acl_permission(mnt_userns, inode, acl, mask); + return posix_acl_permission(idmap, inode, acl, mask); } acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - int error = posix_acl_permission(mnt_userns, inode, acl, mask); + int error = posix_acl_permission(idmap, inode, acl, mask); posix_acl_release(acl); return error; } @@ -318,7 +319,7 @@ static int check_acl(struct user_namespace *mnt_userns, /** * acl_permission_check - perform basic UNIX permission checking - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * @@ -326,20 +327,20 @@ static int check_acl(struct user_namespace *mnt_userns, * function may retrieve POSIX acls it needs to know whether it is called from a * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -static int acl_permission_check(struct user_namespace *mnt_userns, +static int acl_permission_check(struct mnt_idmap *idmap, struct inode *inode, int mask) { unsigned int mode = inode->i_mode; vfsuid_t vfsuid; /* Are we the owner? If so, ACL's don't matter */ - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) { mask &= 7; mode >>= 6; @@ -348,7 +349,7 @@ static int acl_permission_check(struct user_namespace *mnt_userns, /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { - int error = check_acl(mnt_userns, inode, mask); + int error = check_acl(idmap, inode, mask); if (error != -EAGAIN) return error; } @@ -362,7 +363,7 @@ static int acl_permission_check(struct user_namespace *mnt_userns, * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { - vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) mode >>= 3; } @@ -373,7 +374,7 @@ static int acl_permission_check(struct user_namespace *mnt_userns, /** * generic_permission - check for access rights on a Posix-like filesystem - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) @@ -387,13 +388,13 @@ static int acl_permission_check(struct user_namespace *mnt_userns, * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int generic_permission(struct user_namespace *mnt_userns, struct inode *inode, +int generic_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret; @@ -401,17 +402,17 @@ int generic_permission(struct user_namespace *mnt_userns, struct inode *inode, /* * Do the basic permission checks. */ - ret = acl_permission_check(mnt_userns, inode, mask); + ret = acl_permission_check(idmap, inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) - if (capable_wrt_inode_uidgid(mnt_userns, inode, + if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; - if (capable_wrt_inode_uidgid(mnt_userns, inode, + if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; @@ -422,7 +423,7 @@ int generic_permission(struct user_namespace *mnt_userns, struct inode *inode, */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (capable_wrt_inode_uidgid(mnt_userns, inode, + if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; /* @@ -431,7 +432,7 @@ int generic_permission(struct user_namespace *mnt_userns, struct inode *inode, * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (capable_wrt_inode_uidgid(mnt_userns, inode, + if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; @@ -441,7 +442,7 @@ EXPORT_SYMBOL(generic_permission); /** * do_inode_permission - UNIX permission checking - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * @@ -450,19 +451,19 @@ EXPORT_SYMBOL(generic_permission); * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ -static inline int do_inode_permission(struct user_namespace *mnt_userns, +static inline int do_inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) - return inode->i_op->permission(mnt_userns, inode, mask); + return inode->i_op->permission(idmap, inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } - return generic_permission(mnt_userns, inode, mask); + return generic_permission(idmap, inode, mask); } /** @@ -487,7 +488,7 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) /** * inode_permission - Check for access rights to a given inode - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * @@ -497,7 +498,7 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ -int inode_permission(struct user_namespace *mnt_userns, +int inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int retval; @@ -518,11 +519,11 @@ int inode_permission(struct user_namespace *mnt_userns, * written back improperly if their true value is unknown * to the vfs. */ - if (HAS_UNMAPPED_ID(mnt_userns, inode)) + if (HAS_UNMAPPED_ID(idmap, inode)) return -EACCES; } - retval = do_inode_permission(mnt_userns, inode, mask); + retval = do_inode_permission(idmap, inode, mask); if (retval) return retval; @@ -1094,14 +1095,14 @@ fs_initcall(init_fs_namei_sysctls); */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; vfsuid_t vfsuid; if (!sysctl_protected_symlinks) return 0; - mnt_userns = mnt_user_ns(nd->path.mnt); - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + idmap = mnt_idmap(nd->path.mnt); + vfsuid = i_uid_into_vfsuid(idmap, inode); /* Allowed if owner and follower match. */ if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return 0; @@ -1124,7 +1125,7 @@ static inline int may_follow_link(struct nameidata *nd, const struct inode *inod /** * safe_hardlink_source - Check for safe hardlink conditions - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: @@ -1135,7 +1136,7 @@ static inline int may_follow_link(struct nameidata *nd, const struct inode *inod * * Otherwise returns true. */ -static bool safe_hardlink_source(struct user_namespace *mnt_userns, +static bool safe_hardlink_source(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; @@ -1153,7 +1154,7 @@ static bool safe_hardlink_source(struct user_namespace *mnt_userns, return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ - if (inode_permission(mnt_userns, inode, MAY_READ | MAY_WRITE)) + if (inode_permission(idmap, inode, MAY_READ | MAY_WRITE)) return false; return true; @@ -1161,8 +1162,8 @@ static bool safe_hardlink_source(struct user_namespace *mnt_userns, /** * may_linkat - Check permissions for creating a hardlink - * @mnt_userns: user namespace of the mount the inode was found from - * @link: the source to hardlink from + * @idmap: idmap of the mount the inode was found from + * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled @@ -1170,21 +1171,21 @@ static bool safe_hardlink_source(struct user_namespace *mnt_userns, * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if successful, -ve on error. */ -int may_linkat(struct user_namespace *mnt_userns, const struct path *link) +int may_linkat(struct mnt_idmap *idmap, const struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ - if (!vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || - !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode))) + if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; if (!sysctl_protected_hardlinks) @@ -1193,8 +1194,8 @@ int may_linkat(struct user_namespace *mnt_userns, const struct path *link) /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (safe_hardlink_source(mnt_userns, inode) || - inode_owner_or_capable(mnt_userns, inode)) + if (safe_hardlink_source(idmap, inode) || + inode_owner_or_capable(idmap, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); @@ -1205,7 +1206,7 @@ int may_linkat(struct user_namespace *mnt_userns, const struct path *link) * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @nd: nameidata pathwalk data * @inode: the inode of the file to open * @@ -1220,15 +1221,15 @@ int may_linkat(struct user_namespace *mnt_userns, const struct path *link) * the directory doesn't have to be world writable: being group writable will * be enough. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if the open is allowed, -ve on error. */ -static int may_create_in_sticky(struct user_namespace *mnt_userns, +static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd, struct inode *const inode) { umode_t dir_mode = nd->dir_mode; @@ -1237,8 +1238,8 @@ static int may_create_in_sticky(struct user_namespace *mnt_userns, if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || - vfsuid_eq(i_uid_into_vfsuid(mnt_userns, inode), dir_vfsuid) || - vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode), current_fsuid())) + vfsuid_eq(i_uid_into_vfsuid(idmap, inode), dir_vfsuid) || + vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) return 0; if (likely(dir_mode & 0002) || @@ -1704,15 +1705,15 @@ static struct dentry *lookup_slow(const struct qstr *name, return res; } -static inline int may_lookup(struct user_namespace *mnt_userns, +static inline int may_lookup(struct mnt_idmap *idmap, struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { - int err = inode_permission(mnt_userns, nd->inode, MAY_EXEC|MAY_NOT_BLOCK); + int err = inode_permission(idmap, nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD || !try_to_unlazy(nd)) return err; } - return inode_permission(mnt_userns, nd->inode, MAY_EXEC); + return inode_permission(idmap, nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link) @@ -2253,13 +2254,13 @@ static int link_path_walk(const char *name, struct nameidata *nd) /* At this point we know we have a real path component. */ for(;;) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; const char *link; u64 hash_len; int type; - mnt_userns = mnt_user_ns(nd->path.mnt); - err = may_lookup(mnt_userns, nd); + idmap = mnt_idmap(nd->path.mnt); + err = may_lookup(idmap, nd); if (err) return err; @@ -2307,7 +2308,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) OK: /* pathname or trailing symlink, done */ if (!depth) { - nd->dir_vfsuid = i_uid_into_vfsuid(mnt_userns, nd->inode); + nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; @@ -2622,7 +2623,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, } EXPORT_SYMBOL(vfs_path_lookup); -static int lookup_one_common(struct user_namespace *mnt_userns, +static int lookup_one_common(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len, struct qstr *this) { @@ -2652,7 +2653,7 @@ static int lookup_one_common(struct user_namespace *mnt_userns, return err; } - return inode_permission(mnt_userns, base->d_inode, MAY_EXEC); + return inode_permission(idmap, base->d_inode, MAY_EXEC); } /** @@ -2676,7 +2677,7 @@ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_common(&init_user_ns, name, base, len, &this); + err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2703,7 +2704,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_common(&init_user_ns, name, base, len, &this); + err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2714,7 +2715,7 @@ EXPORT_SYMBOL(lookup_one_len); /** * lookup_one - filesystem helper to lookup single pathname component - * @mnt_userns: user namespace of the mount the lookup is performed from + * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to @@ -2724,7 +2725,7 @@ EXPORT_SYMBOL(lookup_one_len); * * The caller must hold base->i_mutex. */ -struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name, +struct dentry *lookup_one(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { struct dentry *dentry; @@ -2733,7 +2734,7 @@ struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name, WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_common(mnt_userns, name, base, len, &this); + err = lookup_one_common(idmap, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2744,7 +2745,7 @@ EXPORT_SYMBOL(lookup_one); /** * lookup_one_unlocked - filesystem helper to lookup single pathname component - * @mnt_userns: idmapping of the mount the lookup is performed from + * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to @@ -2755,7 +2756,7 @@ EXPORT_SYMBOL(lookup_one); * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ -struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, +struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { @@ -2763,7 +2764,7 @@ struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, int err; struct dentry *ret; - err = lookup_one_common(mnt_userns, name, base, len, &this); + err = lookup_one_common(idmap, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2777,7 +2778,7 @@ EXPORT_SYMBOL(lookup_one_unlocked); /** * lookup_one_positive_unlocked - filesystem helper to lookup single * pathname component - * @mnt_userns: idmapping of the mount the lookup is performed from + * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to @@ -2794,11 +2795,11 @@ EXPORT_SYMBOL(lookup_one_unlocked); * * The helper should be called without i_mutex held. */ -struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, +struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { - struct dentry *ret = lookup_one_unlocked(mnt_userns, name, base, len); + struct dentry *ret = lookup_one_unlocked(idmap, name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); @@ -2823,7 +2824,7 @@ EXPORT_SYMBOL(lookup_one_positive_unlocked); struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { - return lookup_one_unlocked(&init_user_ns, name, base, len); + return lookup_one_unlocked(&nop_mnt_idmap, name, base, len); } EXPORT_SYMBOL(lookup_one_len_unlocked); @@ -2838,7 +2839,7 @@ EXPORT_SYMBOL(lookup_one_len_unlocked); struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { - return lookup_one_positive_unlocked(&init_user_ns, name, base, len); + return lookup_one_positive_unlocked(&nop_mnt_idmap, name, base, len); } EXPORT_SYMBOL(lookup_positive_unlocked); @@ -2880,16 +2881,16 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags, } EXPORT_SYMBOL(user_path_at_empty); -int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, +int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); - if (vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode), fsuid)) + if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), fsuid)) return 0; - if (vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, dir), fsuid)) + if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, dir), fsuid)) return 0; - return !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FOWNER); + return !capable_wrt_inode_uidgid(idmap, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); @@ -2913,7 +2914,7 @@ EXPORT_SYMBOL(__check_sticky); * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ -static int may_delete(struct user_namespace *mnt_userns, struct inode *dir, +static int may_delete(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); @@ -2926,21 +2927,21 @@ static int may_delete(struct user_namespace *mnt_userns, struct inode *dir, BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ - if (!vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || - !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode))) + if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(mnt_userns, dir, inode) || IS_APPEND(inode) || + if (check_sticky(idmap, dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || - HAS_UNMAPPED_ID(mnt_userns, inode)) + HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) @@ -2965,7 +2966,7 @@ static int may_delete(struct user_namespace *mnt_userns, struct inode *dir, * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ -static inline int may_create(struct user_namespace *mnt_userns, +static inline int may_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child) { audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); @@ -2973,10 +2974,10 @@ static inline int may_create(struct user_namespace *mnt_userns, return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns)) + if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; - return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); + return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } /* @@ -3044,7 +3045,7 @@ static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) /** * vfs_prepare_mode - prepare the mode to be used for a new inode - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs @@ -3065,11 +3066,11 @@ static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) * * Returns: mode to be passed to the filesystem */ -static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, +static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { - mode = mode_strip_sgid(mnt_userns, dir, mode); + mode = mode_strip_sgid(idmap, dir, mode); mode = mode_strip_umask(dir, mode); /* @@ -3084,7 +3085,7 @@ static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, /** * vfs_create - create new file - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: inode of @dentry * @dentry: pointer to dentry of the base directory * @mode: mode of the new file @@ -3092,27 +3093,29 @@ static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, * * Create a new file. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_create(struct user_namespace *mnt_userns, struct inode *dir, +int vfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { - int error = may_create(mnt_userns, dir, dentry); + int error; + + error = may_create(idmap, dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ - mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IALLUGO, S_IFREG); + mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; - error = dir->i_op->create(mnt_userns, dir, dentry, mode, want_excl); + error = dir->i_op->create(idmap, dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; @@ -3124,7 +3127,7 @@ int vfs_mkobj(struct dentry *dentry, umode_t mode, void *arg) { struct inode *dir = dentry->d_parent->d_inode; - int error = may_create(&init_user_ns, dir, dentry); + int error = may_create(&nop_mnt_idmap, dir, dentry); if (error) return error; @@ -3146,7 +3149,7 @@ bool may_open_dev(const struct path *path) !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } -static int may_open(struct user_namespace *mnt_userns, const struct path *path, +static int may_open(struct mnt_idmap *idmap, const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; @@ -3182,7 +3185,7 @@ static int may_open(struct user_namespace *mnt_userns, const struct path *path, break; } - error = inode_permission(mnt_userns, inode, MAY_OPEN | acc_mode); + error = inode_permission(idmap, inode, MAY_OPEN | acc_mode); if (error) return error; @@ -3197,13 +3200,13 @@ static int may_open(struct user_namespace *mnt_userns, const struct path *path, } /* O_NOATIME can only be set by the owner or superuser */ - if (flag & O_NOATIME && !inode_owner_or_capable(mnt_userns, inode)) + if (flag & O_NOATIME && !inode_owner_or_capable(idmap, inode)) return -EPERM; return 0; } -static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp) +static int handle_truncate(struct mnt_idmap *idmap, struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; @@ -3213,7 +3216,7 @@ static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp) error = security_file_truncate(filp); if (!error) { - error = do_truncate(mnt_userns, path->dentry, 0, + error = do_truncate(idmap, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } @@ -3228,7 +3231,7 @@ static inline int open_to_namei_flags(int flag) return flag; } -static int may_o_create(struct user_namespace *mnt_userns, +static int may_o_create(struct mnt_idmap *idmap, const struct path *dir, struct dentry *dentry, umode_t mode) { @@ -3236,10 +3239,10 @@ static int may_o_create(struct user_namespace *mnt_userns, if (error) return error; - if (!fsuidgid_has_mapping(dir->dentry->d_sb, mnt_userns)) + if (!fsuidgid_has_mapping(dir->dentry->d_sb, idmap)) return -EOVERFLOW; - error = inode_permission(mnt_userns, dir->dentry->d_inode, + error = inode_permission(idmap, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -3319,7 +3322,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; @@ -3367,13 +3370,13 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; - mnt_userns = mnt_user_ns(nd->path.mnt); + idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; - mode = vfs_prepare_mode(mnt_userns, dir->d_inode, mode, mode, mode); + mode = vfs_prepare_mode(idmap, dir->d_inode, mode, mode, mode); if (likely(got_write)) - create_error = may_o_create(mnt_userns, &nd->path, + create_error = may_o_create(idmap, &nd->path, dentry, mode); else create_error = -EROFS; @@ -3410,7 +3413,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, goto out_dput; } - error = dir_inode->i_op->create(mnt_userns, dir_inode, dentry, + error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; @@ -3513,7 +3516,7 @@ finish_lookup: static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; int open_flag = op->open_flag; bool do_truncate; int acc_mode; @@ -3526,13 +3529,13 @@ static int do_open(struct nameidata *nd, } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); - mnt_userns = mnt_user_ns(nd->path.mnt); + idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; - error = may_create_in_sticky(mnt_userns, nd, + error = may_create_in_sticky(idmap, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; @@ -3552,13 +3555,13 @@ static int do_open(struct nameidata *nd, return error; do_truncate = true; } - error = may_open(mnt_userns, &nd->path, acc_mode, open_flag); + error = may_open(idmap, &nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) - error = handle_truncate(mnt_userns, file); + error = handle_truncate(idmap, file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; @@ -3570,20 +3573,20 @@ static int do_open(struct nameidata *nd, /** * vfs_tmpfile - create tmpfile - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: pointer to dentry of the base directory * @mode: mode of the new tmpfile * @open_flag: flags * * Create a temporary file. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -static int vfs_tmpfile(struct user_namespace *mnt_userns, +static int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode) { @@ -3594,7 +3597,7 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, int open_flag = file->f_flags; /* we want directory to be writable */ - error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (!dir->i_op->tmpfile) @@ -3604,13 +3607,13 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, return -ENOMEM; file->f_path.mnt = parentpath->mnt; file->f_path.dentry = child; - mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); - error = dir->i_op->tmpfile(mnt_userns, dir, file, mode); + mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); + error = dir->i_op->tmpfile(idmap, dir, file, mode); dput(child); if (error) return error; /* Don't check for other permissions, the inode was just created */ - error = may_open(mnt_userns, &file->f_path, 0, file->f_flags); + error = may_open(idmap, &file->f_path, 0, file->f_flags); if (error) return error; inode = file_inode(file); @@ -3619,13 +3622,13 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } - ima_post_create_tmpfile(mnt_userns, inode); + ima_post_create_tmpfile(idmap, inode); return 0; } /** * vfs_tmpfile_open - open a tmpfile for kernel internal use - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @parentpath: path of the base directory * @mode: mode of the new tmpfile * @open_flag: flags @@ -3635,7 +3638,7 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, * hence this is only for kernel internal use, and must not be installed into * file tables or such. */ -struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, +struct file *vfs_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred) { @@ -3644,7 +3647,7 @@ struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, file = alloc_empty_file_noaccount(open_flag, cred); if (!IS_ERR(file)) { - error = vfs_tmpfile(mnt_userns, parentpath, file, mode); + error = vfs_tmpfile(idmap, parentpath, file, mode); if (error) { fput(file); file = ERR_PTR(error); @@ -3658,7 +3661,6 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { - struct user_namespace *mnt_userns; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); @@ -3667,8 +3669,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; - mnt_userns = mnt_user_ns(path.mnt); - error = vfs_tmpfile(mnt_userns, &path, file, op->mode); + error = vfs_tmpfile(mnt_idmap(path.mnt), &path, file, op->mode); if (error) goto out2; audit_inode(nd->name, file->f_path.dentry, 0); @@ -3873,7 +3874,7 @@ EXPORT_SYMBOL(user_path_create); /** * vfs_mknod - create device node or file - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: inode of @dentry * @dentry: pointer to dentry of the base directory * @mode: mode of the new device node or file @@ -3881,17 +3882,17 @@ EXPORT_SYMBOL(user_path_create); * * Create a device node or file. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; - int error = may_create(mnt_userns, dir, dentry); + int error = may_create(idmap, dir, dentry); if (error) return error; @@ -3903,7 +3904,7 @@ int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mknod) return -EPERM; - mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); + mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; @@ -3912,7 +3913,7 @@ int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (error) return error; - error = dir->i_op->mknod(mnt_userns, dir, dentry, mode, dev); + error = dir->i_op->mknod(idmap, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; @@ -3939,7 +3940,7 @@ static int may_mknod(umode_t mode) static int do_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct dentry *dentry; struct path path; int error; @@ -3959,20 +3960,20 @@ retry: if (error) goto out2; - mnt_userns = mnt_user_ns(path.mnt); + idmap = mnt_idmap(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(mnt_userns, path.dentry->d_inode, + error = vfs_create(idmap, path.dentry->d_inode, dentry, mode, true); if (!error) - ima_post_path_mknod(mnt_userns, dentry); + ima_post_path_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: - error = vfs_mknod(mnt_userns, path.dentry->d_inode, + error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: - error = vfs_mknod(mnt_userns, path.dentry->d_inode, + error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, 0); break; } @@ -4000,32 +4001,33 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d /** * vfs_mkdir - create directory - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: inode of @dentry * @dentry: pointer to dentry of the base directory * @mode: mode of the new directory * * Create a directory. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - int error = may_create(mnt_userns, dir, dentry); + int error; unsigned max_links = dir->i_sb->s_max_links; + error = may_create(idmap, dir, dentry); if (error) return error; if (!dir->i_op->mkdir) return -EPERM; - mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IRWXUGO | S_ISVTX, 0); + mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; @@ -4033,7 +4035,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (max_links && dir->i_nlink >= max_links) return -EMLINK; - error = dir->i_op->mkdir(mnt_userns, dir, dentry, mode); + error = dir->i_op->mkdir(idmap, dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; @@ -4056,10 +4058,8 @@ retry: error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { - struct user_namespace *mnt_userns; - mnt_userns = mnt_user_ns(path.mnt); - error = vfs_mkdir(mnt_userns, path.dentry->d_inode, dentry, - mode); + error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, + dentry, mode); } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { @@ -4083,22 +4083,22 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) /** * vfs_rmdir - remove directory - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: inode of @dentry * @dentry: pointer to dentry of the base directory * * Remove a directory. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, +int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { - int error = may_delete(mnt_userns, dir, dentry, 1); + int error = may_delete(idmap, dir, dentry, 1); if (error) return error; @@ -4138,7 +4138,6 @@ EXPORT_SYMBOL(vfs_rmdir); int do_rmdir(int dfd, struct filename *name) { - struct user_namespace *mnt_userns; int error; struct dentry *dentry; struct path path; @@ -4178,8 +4177,7 @@ retry: error = security_path_rmdir(&path, dentry); if (error) goto exit4; - mnt_userns = mnt_user_ns(path.mnt); - error = vfs_rmdir(mnt_userns, path.dentry->d_inode, dentry); + error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry); exit4: dput(dentry); exit3: @@ -4203,7 +4201,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) /** * vfs_unlink - unlink a filesystem object - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. @@ -4220,17 +4218,17 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir, +int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; - int error = may_delete(mnt_userns, dir, dentry, 0); + int error = may_delete(idmap, dir, dentry, 0); if (error) return error; @@ -4304,7 +4302,6 @@ retry_deleg: dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { - struct user_namespace *mnt_userns; /* Why not before? Because we want correct error value */ if (last.name[last.len]) @@ -4316,9 +4313,8 @@ retry_deleg: error = security_path_unlink(&path, dentry); if (error) goto exit3; - mnt_userns = mnt_user_ns(path.mnt); - error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry, - &delegated_inode); + error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode, + dentry, &delegated_inode); exit3: dput(dentry); } @@ -4370,24 +4366,25 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) /** * vfs_symlink - create symlink - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: inode of @dentry * @dentry: pointer to dentry of the base directory * @oldname: name of the file to link to * * Create a symlink. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *oldname) { - int error = may_create(mnt_userns, dir, dentry); + int error; + error = may_create(idmap, dir, dentry); if (error) return error; @@ -4398,7 +4395,7 @@ int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (error) return error; - error = dir->i_op->symlink(mnt_userns, dir, dentry, oldname); + error = dir->i_op->symlink(idmap, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; @@ -4423,13 +4420,9 @@ retry: goto out_putnames; error = security_path_symlink(&path, dentry, from->name); - if (!error) { - struct user_namespace *mnt_userns; - - mnt_userns = mnt_user_ns(path.mnt); - error = vfs_symlink(mnt_userns, path.dentry->d_inode, dentry, - from->name); - } + if (!error) + error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, + dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -4455,7 +4448,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn /** * vfs_link - create a new link * @old_dentry: object to be linked - * @mnt_userns: the user namespace of the mount + * @idmap: idmap of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break @@ -4472,13 +4465,13 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then take - * care to map the inode according to @mnt_userns before checking permissions. + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then take + * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs init_user_ns. + * raw inode simply passs @nop_mnt_idmap. */ -int vfs_link(struct dentry *old_dentry, struct user_namespace *mnt_userns, +int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { @@ -4489,7 +4482,7 @@ int vfs_link(struct dentry *old_dentry, struct user_namespace *mnt_userns, if (!inode) return -ENOENT; - error = may_create(mnt_userns, dir, new_dentry); + error = may_create(idmap, dir, new_dentry); if (error) return error; @@ -4506,7 +4499,7 @@ int vfs_link(struct dentry *old_dentry, struct user_namespace *mnt_userns, * be writen back improperly if their true value is unknown to * the vfs. */ - if (HAS_UNMAPPED_ID(mnt_userns, inode)) + if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; @@ -4553,7 +4546,7 @@ EXPORT_SYMBOL(vfs_link); int do_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; @@ -4590,14 +4583,14 @@ retry: error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - mnt_userns = mnt_user_ns(new_path.mnt); - error = may_linkat(mnt_userns, &old_path); + idmap = mnt_idmap(new_path.mnt); + error = may_linkat(idmap, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode, + error = vfs_link(old_path.dentry, idmap, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); @@ -4697,20 +4690,20 @@ int vfs_rename(struct renamedata *rd) if (source == target) return 0; - error = may_delete(rd->old_mnt_userns, old_dir, old_dentry, is_dir); + error = may_delete(rd->old_mnt_idmap, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { - error = may_create(rd->new_mnt_userns, new_dir, new_dentry); + error = may_create(rd->new_mnt_idmap, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) - error = may_delete(rd->new_mnt_userns, new_dir, + error = may_delete(rd->new_mnt_idmap, new_dir, new_dentry, is_dir); else - error = may_delete(rd->new_mnt_userns, new_dir, + error = may_delete(rd->new_mnt_idmap, new_dir, new_dentry, new_is_dir); } if (error) @@ -4725,13 +4718,13 @@ int vfs_rename(struct renamedata *rd) */ if (new_dir != old_dir) { if (is_dir) { - error = inode_permission(rd->old_mnt_userns, source, + error = inode_permission(rd->old_mnt_idmap, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { - error = inode_permission(rd->new_mnt_userns, target, + error = inode_permission(rd->new_mnt_idmap, target, MAY_WRITE); if (error) return error; @@ -4776,7 +4769,7 @@ int vfs_rename(struct renamedata *rd) if (error) goto out; } - error = old_dir->i_op->rename(rd->new_mnt_userns, old_dir, old_dentry, + error = old_dir->i_op->rename(rd->new_mnt_idmap, old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; @@ -4921,10 +4914,10 @@ retry_deleg: rd.old_dir = old_path.dentry->d_inode; rd.old_dentry = old_dentry; - rd.old_mnt_userns = mnt_user_ns(old_path.mnt); + rd.old_mnt_idmap = mnt_idmap(old_path.mnt); rd.new_dir = new_path.dentry->d_inode; rd.new_dentry = new_dentry; - rd.new_mnt_userns = mnt_user_ns(new_path.mnt); + rd.new_mnt_idmap = mnt_idmap(new_path.mnt); rd.delegated_inode = &delegated_inode; rd.flags = flags; error = vfs_rename(&rd); diff --git a/fs/namespace.c b/fs/namespace.c index ab467ee58341..5927d90e24a0 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -75,22 +75,6 @@ static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ -struct mnt_idmap { - struct user_namespace *owner; - refcount_t count; -}; - -/* - * Carries the initial idmapping of 0:0:4294967295 which is an identity - * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is - * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. - */ -struct mnt_idmap nop_mnt_idmap = { - .owner = &init_user_ns, - .count = REFCOUNT_INIT(1), -}; -EXPORT_SYMBOL_GPL(nop_mnt_idmap); - struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; @@ -210,104 +194,6 @@ int mnt_get_count(struct mount *mnt) #endif } -/** - * mnt_idmap_owner - retrieve owner of the mount's idmapping - * @idmap: mount idmapping - * - * This helper will go away once the conversion to use struct mnt_idmap - * everywhere has finished at which point the helper will be unexported. - * - * Only code that needs to perform permission checks based on the owner of the - * idmapping will get access to it. All other code will solely rely on - * idmappings. This will get us type safety so it's impossible to conflate - * filesystems idmappings with mount idmappings. - * - * Return: The owner of the idmapping. - */ -struct user_namespace *mnt_idmap_owner(const struct mnt_idmap *idmap) -{ - return idmap->owner; -} -EXPORT_SYMBOL_GPL(mnt_idmap_owner); - -/** - * mnt_user_ns - retrieve owner of an idmapped mount - * @mnt: the relevant vfsmount - * - * This helper will go away once the conversion to use struct mnt_idmap - * everywhere has finished at which point the helper will be unexported. - * - * Only code that needs to perform permission checks based on the owner of the - * idmapping will get access to it. All other code will solely rely on - * idmappings. This will get us type safety so it's impossible to conflate - * filesystems idmappings with mount idmappings. - * - * Return: The owner of the idmapped. - */ -struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) -{ - struct mnt_idmap *idmap = mnt_idmap(mnt); - - /* Return the actual owner of the filesystem instead of the nop. */ - if (idmap == &nop_mnt_idmap && - !initial_idmapping(mnt->mnt_sb->s_user_ns)) - return mnt->mnt_sb->s_user_ns; - return mnt_idmap_owner(idmap); -} -EXPORT_SYMBOL_GPL(mnt_user_ns); - -/** - * alloc_mnt_idmap - allocate a new idmapping for the mount - * @mnt_userns: owning userns of the idmapping - * - * Allocate a new struct mnt_idmap which carries the idmapping of the mount. - * - * Return: On success a new idmap, on error an error pointer is returned. - */ -static struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) -{ - struct mnt_idmap *idmap; - - idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); - if (!idmap) - return ERR_PTR(-ENOMEM); - - idmap->owner = get_user_ns(mnt_userns); - refcount_set(&idmap->count, 1); - return idmap; -} - -/** - * mnt_idmap_get - get a reference to an idmapping - * @idmap: the idmap to bump the reference on - * - * If @idmap is not the @nop_mnt_idmap bump the reference count. - * - * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. - */ -static inline struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) -{ - if (idmap != &nop_mnt_idmap) - refcount_inc(&idmap->count); - - return idmap; -} - -/** - * mnt_idmap_put - put a reference to an idmapping - * @idmap: the idmap to put the reference on - * - * If this is a non-initial idmapping, put the reference count when a mount is - * released and free it if we're the last user. - */ -static inline void mnt_idmap_put(struct mnt_idmap *idmap) -{ - if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) { - put_user_ns(idmap->owner); - kfree(idmap); - } -} - static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); @@ -4094,7 +3980,7 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ - if (mnt_idmap_owner(kattr->mnt_idmap) == fs_userns) + if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb)) return -EINVAL; /* @@ -4340,7 +4226,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); - if (initial_idmapping(mnt_userns)) { + if (mnt_userns == &init_user_ns) { err = -EPERM; goto out_fput; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 1ead5bd740c2..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -209,8 +209,8 @@ config NFS_DISABLE_UDP_SUPPORT config NFS_V4_2_READ_PLUS bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation" depends on NFS_V4_2 - default y + default n help - Choose Y here to enable the use of READ_PLUS over NFS v4.2. READ_PLUS - attempts to improve read performance by compressing out sparse holes - in the file contents. + This is intended for developers only. The READ_PLUS operation has + been shown to have issues under specific conditions and should not + be used in production. diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index f7e4a88d5d92..f8e420464b77 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2296,7 +2296,7 @@ EXPORT_SYMBOL_GPL(nfs_instantiate); * that the operation succeeded on the server, but an error in the * reply path made it appear to have failed. */ -int nfs_create(struct user_namespace *mnt_userns, struct inode *dir, +int nfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct iattr attr; @@ -2325,7 +2325,7 @@ EXPORT_SYMBOL_GPL(nfs_create); * See comments for nfs_proc_create regarding failed operations. */ int -nfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +nfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct iattr attr; @@ -2352,7 +2352,7 @@ EXPORT_SYMBOL_GPL(nfs_mknod); /* * See comments for nfs_proc_create regarding failed operations. */ -int nfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +int nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct iattr attr; @@ -2524,7 +2524,7 @@ EXPORT_SYMBOL_GPL(nfs_unlink); * now have a new file handle and can instantiate an in-core NFS inode * and move the raw page into its mapping. */ -int nfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +int nfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct page *page; @@ -2642,7 +2642,7 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) * If these conditions are met, we can drop the dentries before doing * the rename. */ -int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -3262,7 +3262,7 @@ static int nfs_execute_ok(struct inode *inode, int mask) return ret; } -int nfs_permission(struct user_namespace *mnt_userns, +int nfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { @@ -3313,7 +3313,7 @@ out_notsup: res = nfs_revalidate_inode(inode, NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER); if (res == 0) - res = generic_permission(&init_user_ns, inode, mask); + res = generic_permission(&nop_mnt_idmap, inode, mask); goto out; } EXPORT_SYMBOL_GPL(nfs_permission); diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 01596f2d0a1e..1a9d5aa51dfb 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -145,17 +145,10 @@ out: return parent; } -static u64 nfs_fetch_iversion(struct inode *inode) -{ - nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE); - return inode_peek_iversion_raw(inode); -} - const struct export_operations nfs_export_ops = { .encode_fh = nfs_encode_fh, .fh_to_dentry = nfs_fh_to_dentry, .get_parent = nfs_get_parent, - .fetch_iversion = nfs_fetch_iversion, .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| EXPORT_OP_NOATOMIC_ATTR, diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d8ec889a4b3f..b0f3c9339e70 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -31,6 +31,7 @@ #include <linux/swap.h> #include <linux/uaccess.h> +#include <linux/filelock.h> #include "delegation.h" #include "internal.h" diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e98ee7599eeb..222a28320e1c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -606,7 +606,7 @@ EXPORT_SYMBOL_GPL(nfs_fhget); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) int -nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -825,10 +825,12 @@ static u32 nfs_get_valid_attrmask(struct inode *inode) reply_mask |= STATX_UID | STATX_GID; if (!(cache_validity & NFS_INO_INVALID_BLOCKS)) reply_mask |= STATX_BLOCKS; + if (!(cache_validity & NFS_INO_INVALID_CHANGE)) + reply_mask |= STATX_CHANGE_COOKIE; return reply_mask; } -int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int nfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -843,7 +845,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID | STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME | - STATX_INO | STATX_SIZE | STATX_BLOCKS; + STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_BTIME | + STATX_CHANGE_COOKIE; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { if (readdirplus_enabled) @@ -851,8 +854,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, goto out_no_revalidate; } - /* Flush out writes to the server in order to update c/mtime. */ - if ((request_mask & (STATX_CTIME | STATX_MTIME)) && + /* Flush out writes to the server in order to update c/mtime/version. */ + if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_CHANGE_COOKIE)) && S_ISREG(inode->i_mode)) filemap_write_and_wait(inode->i_mapping); @@ -872,7 +875,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, /* Is the user requesting attributes that might need revalidation? */ if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME| STATX_MTIME|STATX_UID|STATX_GID| - STATX_SIZE|STATX_BLOCKS))) + STATX_SIZE|STATX_BLOCKS| + STATX_CHANGE_COOKIE))) goto out_no_revalidate; /* Check whether the cached attributes are stale */ @@ -908,8 +912,12 @@ out_no_revalidate: /* Only return attributes that were revalidated. */ stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask; - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); + stat->change_cookie = inode_peek_iversion_raw(inode); + stat->attributes_mask |= STATX_ATTR_CHANGE_MONOTONIC; + if (server->change_attr_type != NFS4_CHANGE_TYPE_IS_UNDEFINED) + stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC; if (S_ISDIR(inode->i_mode)) stat->blksize = NFS_SERVER(inode)->dtsize; out: diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ae7d4a8c728c..41468c21291d 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -384,18 +384,18 @@ extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); void nfs_d_prune_case_insensitive_aliases(struct inode *inode); -int nfs_create(struct user_namespace *, struct inode *, struct dentry *, +int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *, +int nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); -int nfs_symlink(struct user_namespace *, struct inode *, struct dentry *, +int nfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); -int nfs_mknod(struct user_namespace *, struct inode *, struct dentry *, umode_t, +int nfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); -int nfs_rename(struct user_namespace *, struct inode *, struct dentry *, +int nfs_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index b0ef7e7ddb30..19d51ebf842c 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -208,23 +208,23 @@ out_fc: } static int -nfs_namespace_getattr(struct user_namespace *mnt_userns, +nfs_namespace_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { if (NFS_FH(d_inode(path->dentry))->size != 0) - return nfs_getattr(mnt_userns, path, stat, request_mask, + return nfs_getattr(idmap, path, stat, request_mask, query_flags); - generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(path->dentry), stat); return 0; } static int -nfs_namespace_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +nfs_namespace_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { if (NFS_FH(d_inode(dentry))->size != 0) - return nfs_setattr(mnt_userns, dentry, attr); + return nfs_setattr(idmap, dentry, attr); return -EACCES; } diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index df9ca56db347..4fa37dc038b5 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -12,7 +12,7 @@ */ #ifdef CONFIG_NFS_V3_ACL extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu); -extern int nfs3_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int nfs3_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, struct posix_acl *dfacl); diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 74d11e3c4205..1247f544a440 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -255,7 +255,7 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, } -int nfs3_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int nfs3_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct posix_acl *orig = acl, *dfacl = NULL, *alloc; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 5edd1704f735..4c9f8bd866ab 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -23,6 +23,7 @@ #define NFS4_MAX_LOOP_ON_RECOVER (10) #include <linux/seqlock.h> +#include <linux/filelock.h> struct idmap; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 40d749f29ed3..d9c332019d06 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7692,7 +7692,7 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp) #define XATTR_NAME_NFSV4_ACL "system.nfs4_acl" static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) @@ -7716,7 +7716,7 @@ static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) #define XATTR_NAME_NFSV4_DACL "system.nfs4_dacl" static int nfs4_xattr_set_nfs4_dacl(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) @@ -7739,7 +7739,7 @@ static bool nfs4_xattr_list_nfs4_dacl(struct dentry *dentry) #define XATTR_NAME_NFSV4_SACL "system.nfs4_sacl" static int nfs4_xattr_set_nfs4_sacl(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) @@ -7764,7 +7764,7 @@ static bool nfs4_xattr_list_nfs4_sacl(struct dentry *dentry) #ifdef CONFIG_NFS_V4_SECURITY_LABEL static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) @@ -7815,7 +7815,7 @@ nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) #ifdef CONFIG_NFS_V4_2 static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 16be6dae524f..779bfc37233c 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -21,6 +21,7 @@ #include <linux/nfs_page.h> #include <linux/nfs_mount.h> #include <linux/export.h> +#include <linux/filelock.h> #include "internal.h" #include "pnfs.h" diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 80c240e50952..1a80d548253a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -25,6 +25,7 @@ #include <linux/freezer.h> #include <linux/wait.h> #include <linux/iversion.h> +#include <linux/filelock.h> #include <linux/uaccess.h> #include <linux/sched/mm.h> diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index 0a9b72685f98..1479583fbb62 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -9,6 +9,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/fs.h> +#include <linux/filelock.h> static unsigned int grace_net_id; static DEFINE_SPINLOCK(grace_lock); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 51a4b7885cae..ec49b200b797 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -10,6 +10,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <linux/filelock.h> #include <linux/percpu_counter.h> #include <linux/siphash.h> diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 1457f59f447a..995cb2c90b1a 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -113,11 +113,11 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, argp->acl_default); if (error) goto out_drop_lock; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 647108138e8a..887803735e2a 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -103,11 +103,11 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, argp->acl_default); out_drop_lock: diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index d01b29aba662..f41992ecd0d7 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -320,7 +320,7 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode &= ~current_umask(); fh_fill_pre_attrs(fhp); - host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, inode, child, iap->ia_mode, true); if (host_err < 0) { status = nfserrno(host_err); goto out; diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 78b8cd9651d5..3509e73abe1f 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -233,7 +233,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * as well be forgiving and just succeed silently. */ goto out_put; - status = vfs_mkdir(&init_user_ns, d_inode(dir), dentry, S_IRWXU); + status = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU); out_put: dput(dentry); out_unlock: @@ -353,7 +353,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn) status = -ENOENT; if (d_really_is_negative(dentry)) goto out; - status = vfs_rmdir(&init_user_ns, d_inode(dir), dentry); + status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry); out: dput(dentry); out_unlock: @@ -443,7 +443,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) if (nfs4_has_reclaimed_state(name, nn)) goto out_free; - status = vfs_rmdir(&init_user_ns, d_inode(parent), child); + status = vfs_rmdir(&nop_mnt_idmap, d_inode(parent), child); if (status) printk("failed to remove client recovery directory %pd\n", child); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4ef529379065..c1684da6c01f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5356,7 +5356,7 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, { struct nfs4_ol_stateid *st; struct file *f = fp->fi_deleg_file->nf_file; - struct inode *ino = locks_inode(f); + struct inode *ino = file_inode(f); int writes; writes = atomic_read(&ino->i_writecount); @@ -7809,7 +7809,7 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) return status; } - inode = locks_inode(nf->nf_file); + inode = file_inode(nf->nf_file); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { @@ -8182,7 +8182,6 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); - rhltable_destroy(&nfs4_file_rhltable); #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_shutdown_umount(nn); #endif @@ -8192,6 +8191,7 @@ void nfs4_state_shutdown(void) { nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 97edb32be77f..e12e5a4ad502 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2965,7 +2965,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; } - err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); + err = vfs_getattr(&path, &stat, + STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE, + AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; if (!(stat.result_mask & STATX_BTIME)) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 8c52b6c9d31a..ccd8485fee04 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -40,7 +40,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry) /* make sure parents give x permission to user */ int err; parent = dget_parent(tdentry); - err = inode_permission(&init_user_ns, + err = inode_permission(&nop_mnt_idmap, d_inode(parent), MAY_EXEC); if (err < 0) { dput(parent); @@ -628,6 +628,10 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) stat.mtime = inode->i_mtime; stat.ctime = inode->i_ctime; stat.size = inode->i_size; + if (v4 && IS_I_VERSION(inode)) { + stat.change_cookie = inode_query_iversion(inode); + stat.result_mask |= STATX_CHANGE_COOKIE; + } } if (v4) fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); @@ -659,6 +663,10 @@ void fh_fill_post_attrs(struct svc_fh *fhp) if (err) { fhp->fh_post_saved = false; fhp->fh_post_attr.ctime = inode->i_ctime; + if (v4 && IS_I_VERSION(inode)) { + fhp->fh_post_attr.change_cookie = inode_query_iversion(inode); + fhp->fh_post_attr.result_mask |= STATX_CHANGE_COOKIE; + } } else fhp->fh_post_saved = true; if (v4) @@ -748,3 +756,37 @@ enum fsid_source fsid_source(const struct svc_fh *fhp) return FSIDSOURCE_UUID; return FSIDSOURCE_DEV; } + +/* + * We could use i_version alone as the change attribute. However, i_version + * can go backwards on a regular file after an unclean shutdown. On its own + * that doesn't necessarily cause a problem, but if i_version goes backwards + * and then is incremented again it could reuse a value that was previously + * used before boot, and a client who queried the two values might incorrectly + * assume nothing changed. + * + * By using both ctime and the i_version counter we guarantee that as long as + * time doesn't go backwards we never reuse an old value. If the filesystem + * advertises STATX_ATTR_CHANGE_MONOTONIC, then this mitigation is not + * needed. + * + * We only need to do this for regular files as well. For directories, we + * assume that the new change attr is always logged to stable storage in some + * fashion before the results can be seen. + */ +u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode) +{ + u64 chattr; + + if (stat->result_mask & STATX_CHANGE_COOKIE) { + chattr = stat->change_cookie; + if (S_ISREG(inode->i_mode) && + !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) { + chattr += (u64)stat->ctime.tv_sec << 30; + chattr += stat->ctime.tv_nsec; + } + } else { + chattr = time_to_chattr(&stat->ctime); + } + return chattr; +} diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 513e028b0bbe..4e0ecf0ae2cf 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -293,34 +293,7 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) fhp->fh_pre_saved = false; } -/* - * We could use i_version alone as the change attribute. However, - * i_version can go backwards after a reboot. On its own that doesn't - * necessarily cause a problem, but if i_version goes backwards and then - * is incremented again it could reuse a value that was previously used - * before boot, and a client who queried the two values might - * incorrectly assume nothing changed. - * - * By using both ctime and the i_version counter we guarantee that as - * long as time doesn't go backwards we never reuse an old value. - */ -static inline u64 nfsd4_change_attribute(struct kstat *stat, - struct inode *inode) -{ - if (inode->i_sb->s_export_op->fetch_iversion) - return inode->i_sb->s_export_op->fetch_iversion(inode); - else if (IS_I_VERSION(inode)) { - u64 chattr; - - chattr = stat->ctime.tv_sec; - chattr <<= 30; - chattr += stat->ctime.tv_nsec; - chattr += inode_query_iversion(inode); - return chattr; - } else - return time_to_chattr(&stat->ctime); -} - +u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode); extern void fh_fill_pre_attrs(struct svc_fh *fhp); extern void fh_fill_post_attrs(struct svc_fh *fhp); extern void fh_fill_both_attrs(struct svc_fh *fhp); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 9744443c3965..a82d91afdc9c 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -93,7 +93,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) if (delta < 0) delta = -delta; if (delta < MAX_TOUCH_TIME_ERROR && - setattr_prepare(&init_user_ns, fhp->fh_dentry, iap) != 0) { + setattr_prepare(&nop_mnt_idmap, fhp->fh_dentry, iap) != 0) { /* * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. * This will cause notify_change to set these times diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 4c3a0d84043c..ab4ee3509ce3 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -426,7 +426,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (iap->ia_size < 0) return -EFBIG; - host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); + host_err = notify_change(&nop_mnt_idmap, dentry, &size_attr, NULL); if (host_err) return host_err; iap->ia_valid &= ~ATTR_SIZE; @@ -444,7 +444,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) return 0; iap->ia_valid |= ATTR_CTIME; - return notify_change(&init_user_ns, dentry, iap, NULL); + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } /** @@ -542,12 +542,12 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, attr->na_labelerr = security_inode_setsecctx(dentry, attr->na_seclabel->data, attr->na_seclabel->len); if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl) - attr->na_aclerr = set_posix_acl(&init_user_ns, + attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_ACCESS, attr->na_pacl); if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode)) - attr->na_aclerr = set_posix_acl(&init_user_ns, + attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_DEFAULT, attr->na_dpacl); inode_unlock(inode); @@ -583,7 +583,7 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; if (!(inode->i_mode & S_ISVTX)) return 0; - if (vfs_getxattr(&init_user_ns, dentry, NFSD_JUNCTION_XATTR_NAME, + if (vfs_getxattr(&nop_mnt_idmap, dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0) return 0; return 1; @@ -1363,12 +1363,13 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, dirp, dchild, + iap->ia_mode, true); if (!host_err) nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - host_err = vfs_mkdir(&init_user_ns, dirp, dchild, iap->ia_mode); + host_err = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode); if (!host_err && unlikely(d_unhashed(dchild))) { struct dentry *d; d = lookup_one_len(dchild->d_name.name, @@ -1396,7 +1397,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, case S_IFBLK: case S_IFIFO: case S_IFSOCK: - host_err = vfs_mknod(&init_user_ns, dirp, dchild, + host_err = vfs_mknod(&nop_mnt_idmap, dirp, dchild, iap->ia_mode, rdev); break; default: @@ -1557,7 +1558,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_drop_write; } fh_fill_pre_attrs(fhp); - host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path); + host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path); err = nfserrno(host_err); cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); if (!err) @@ -1625,7 +1626,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (d_really_is_negative(dold)) goto out_dput; fh_fill_pre_attrs(ffhp); - host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL); + host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL); fh_fill_post_attrs(ffhp); inode_unlock(dirp); if (!host_err) { @@ -1745,10 +1746,10 @@ retry: goto out_dput_old; } else { struct renamedata rd = { - .old_mnt_userns = &init_user_ns, + .old_mnt_idmap = &nop_mnt_idmap, .old_dir = fdir, .old_dentry = odentry, - .new_mnt_userns = &init_user_ns, + .new_mnt_idmap = &nop_mnt_idmap, .new_dir = tdir, .new_dentry = ndentry, }; @@ -1850,14 +1851,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, nfsd_close_cached_files(rdentry); for (retries = 1;;) { - host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); + host_err = vfs_unlink(&nop_mnt_idmap, dirp, rdentry, NULL); if (host_err != -EAGAIN || !retries--) break; if (!nfsd_wait_for_delegreturn(rqstp, rinode)) break; } } else { - host_err = vfs_rmdir(&init_user_ns, dirp, rdentry); + host_err = vfs_rmdir(&nop_mnt_idmap, dirp, rdentry); } fh_fill_post_attrs(fhp); @@ -2129,7 +2130,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, inode_lock_shared(inode); - len = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0); + len = vfs_getxattr(&nop_mnt_idmap, dentry, name, NULL, 0); /* * Zero-length attribute, just return. @@ -2156,7 +2157,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, goto out; } - len = vfs_getxattr(&init_user_ns, dentry, name, buf, len); + len = vfs_getxattr(&nop_mnt_idmap, dentry, name, buf, len); if (len <= 0) { kvfree(buf); buf = NULL; @@ -2267,7 +2268,7 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) inode_lock(fhp->fh_dentry->d_inode); fh_fill_pre_attrs(fhp); - ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, + ret = __vfs_removexattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, NULL); fh_fill_post_attrs(fhp); @@ -2294,7 +2295,7 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, inode_lock(fhp->fh_dentry->d_inode); fh_fill_pre_attrs(fhp); - ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf, + ret = __vfs_setxattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, buf, len, flags, NULL); fh_fill_post_attrs(fhp); inode_unlock(fhp->fh_dentry->d_inode); @@ -2378,14 +2379,14 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ - err = inode_permission(&init_user_ns, inode, + err = inode_permission(&nop_mnt_idmap, inode, acc & (MAY_READ | MAY_WRITE | MAY_EXEC)); /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) - err = inode_permission(&init_user_ns, inode, MAY_EXEC); + err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC); return err? nfserrno(err) : 0; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index dbdfef7ae85b..43fb57a301d3 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -170,9 +170,14 @@ static inline void fh_drop_write(struct svc_fh *fh) static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat) { + u32 request_mask = STATX_BASIC_STATS; struct path p = {.mnt = fh->fh_export->ex_path.mnt, .dentry = fh->fh_dentry}; - return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS, + + if (fh->fh_maxsize == NFS4_FHSIZE) + request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); + + return nfserrno(vfs_getattr(&p, stat, request_mask, AT_STATX_SYNC_AS_STAT)); } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 232dd7b6cca1..1310d2d5feb3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -364,7 +364,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) ii->i_bh = bh; atomic64_inc(&root->inodes_count); - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = ino; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); @@ -949,7 +949,7 @@ void nilfs_evict_inode(struct inode *inode) */ } -int nilfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int nilfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct nilfs_transaction_info ti; @@ -957,7 +957,7 @@ int nilfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct super_block *sb = inode->i_sb; int err; - err = setattr_prepare(&init_user_ns, dentry, iattr); + err = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (err) return err; @@ -972,7 +972,7 @@ int nilfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, nilfs_truncate(inode); } - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) { @@ -988,7 +988,7 @@ out_err: return err; } -int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode, +int nilfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct nilfs_root *root = NILFS_I(inode)->i_root; @@ -997,7 +997,7 @@ int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode, root->cno != NILFS_CPTREE_CURRENT_CNO) return -EROFS; /* snapshot is not writable */ - return generic_permission(&init_user_ns, inode, mask); + return generic_permission(&nop_mnt_idmap, inode, mask); } int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 87e1004b606d..5ccc638ae92f 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -128,7 +128,7 @@ int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) /** * nilfs_fileattr_set - ioctl to support chattr */ -int nilfs_fileattr_set(struct user_namespace *mnt_userns, +int nilfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -1114,7 +1114,14 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) minseg = range[0] + segbytes - 1; do_div(minseg, segbytes); + + if (range[1] < 4096) + goto out; + maxseg = NILFS_SB2_OFFSET_BYTES(range[1]); + if (maxseg < segbytes) + goto out; + do_div(maxseg, segbytes); maxseg--; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 23899e0ae850..c7024da8f1e2 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -72,7 +72,7 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int nilfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int nilfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; @@ -100,7 +100,7 @@ static int nilfs_create(struct user_namespace *mnt_userns, struct inode *dir, } static int -nilfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +nilfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; @@ -125,7 +125,7 @@ nilfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, return err; } -static int nilfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int nilfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct nilfs_transaction_info ti; @@ -202,7 +202,7 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, return err; } -static int nilfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -340,7 +340,7 @@ static int nilfs_rmdir(struct inode *dir, struct dentry *dentry) return err; } -static int nilfs_rename(struct user_namespace *mnt_userns, +static int nilfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index aecda4fc95f5..8046490cd7fe 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -242,7 +242,7 @@ extern int nilfs_sync_file(struct file *, loff_t, loff_t, int); /* ioctl.c */ int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *m); -int nilfs_fileattr_set(struct user_namespace *mnt_userns, +int nilfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); long nilfs_ioctl(struct file *, unsigned int, unsigned long); long nilfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -271,10 +271,10 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode); extern void nilfs_update_inode(struct inode *, struct buffer_head *, int); extern void nilfs_truncate(struct inode *); extern void nilfs_evict_inode(struct inode *); -extern int nilfs_setattr(struct user_namespace *, struct dentry *, +extern int nilfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void nilfs_write_failed(struct address_space *mapping, loff_t to); -int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode, +int nilfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh); extern int nilfs_inode_dirty(struct inode *); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 6edb6e0dd61f..1422b8ba24ed 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -409,6 +409,15 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) goto out; /* + * Prevent underflow in second superblock position calculation. + * The exact minimum size check is done in nilfs_sufile_resize(). + */ + if (newsize < 4096) { + ret = -ENOSPC; + goto out; + } + + /* * Write lock is required to protect some functions depending * on the number of segments, the number of reserved segments, * and so forth. diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 2064e6473d30..3a4c9c150cbf 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -544,9 +544,15 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; - u64 sb2off = NILFS_SB2_OFFSET_BYTES(bdev_nr_bytes(nilfs->ns_bdev)); + u64 sb2off, devsize = bdev_nr_bytes(nilfs->ns_bdev); int valid[2], swp = 0; + if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) { + nilfs_err(sb, "device size too small"); + return -EINVAL; + } + sb2off = NILFS_SB2_OFFSET_BYTES(devsize); + sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, &sbh[0]); sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]); diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index a2a15bc4df28..29bdd99b29fa 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -262,7 +262,7 @@ static int fanotify_get_response(struct fsnotify_group *group, } /* userspace responded, convert to something usable */ - switch (event->response & ~FAN_AUDIT) { + switch (event->response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: ret = 0; break; @@ -273,7 +273,8 @@ static int fanotify_get_response(struct fsnotify_group *group, /* Check if the response should be audited */ if (event->response & FAN_AUDIT) - audit_fanotify(event->response & ~FAN_AUDIT); + audit_fanotify(event->response & ~FAN_AUDIT, + &event->audit_rule); pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__, group, event, ret); @@ -563,6 +564,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH_PERM; pevent->response = 0; + pevent->hdr.type = FAN_RESPONSE_INFO_NONE; + pevent->hdr.pad = 0; + pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; path_get(path); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 57f51a9a3015..e8a3c28c5d12 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -425,9 +425,13 @@ FANOTIFY_PE(struct fanotify_event *event) struct fanotify_perm_event { struct fanotify_event fae; struct path path; - unsigned short response; /* userspace answer to the event */ + u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ + union { + struct fanotify_response_info_header hdr; + struct fanotify_response_info_audit_rule audit_rule; + }; }; static inline struct fanotify_perm_event * diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 4546da4a54f9..8f430bfad487 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -283,19 +283,42 @@ static int create_fd(struct fsnotify_group *group, const struct path *path, return client_fd; } +static int process_access_response_info(const char __user *info, + size_t info_len, + struct fanotify_response_info_audit_rule *friar) +{ + if (info_len != sizeof(*friar)) + return -EINVAL; + + if (copy_from_user(friar, info, sizeof(*friar))) + return -EFAULT; + + if (friar->hdr.type != FAN_RESPONSE_INFO_AUDIT_RULE) + return -EINVAL; + if (friar->hdr.pad != 0) + return -EINVAL; + if (friar->hdr.len != sizeof(*friar)) + return -EINVAL; + + return info_len; +} + /* * Finish processing of permission event by setting it to ANSWERED state and * drop group->notification_lock. */ static void finish_permission_event(struct fsnotify_group *group, - struct fanotify_perm_event *event, - unsigned int response) + struct fanotify_perm_event *event, u32 response, + struct fanotify_response_info_audit_rule *friar) __releases(&group->notification_lock) { bool destroy = false; assert_spin_locked(&group->notification_lock); - event->response = response; + event->response = response & ~FAN_INFO; + if (response & FAN_INFO) + memcpy(&event->audit_rule, friar, sizeof(*friar)); + if (event->state == FAN_EVENT_CANCELED) destroy = true; else @@ -306,20 +329,27 @@ static void finish_permission_event(struct fsnotify_group *group, } static int process_access_response(struct fsnotify_group *group, - struct fanotify_response *response_struct) + struct fanotify_response *response_struct, + const char __user *info, + size_t info_len) { struct fanotify_perm_event *event; int fd = response_struct->fd; - int response = response_struct->response; + u32 response = response_struct->response; + int ret = info_len; + struct fanotify_response_info_audit_rule friar; - pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group, - fd, response); + pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__, + group, fd, response, info, info_len); /* * make sure the response is valid, if invalid we do nothing and either * userspace can send a valid response or we will clean it up after the * timeout */ - switch (response & ~FAN_AUDIT) { + if (response & ~FANOTIFY_RESPONSE_VALID_MASK) + return -EINVAL; + + switch (response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: case FAN_DENY: break; @@ -327,10 +357,20 @@ static int process_access_response(struct fsnotify_group *group, return -EINVAL; } - if (fd < 0) + if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) return -EINVAL; - if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) + if (response & FAN_INFO) { + ret = process_access_response_info(info, info_len, &friar); + if (ret < 0) + return ret; + if (fd == FAN_NOFD) + return ret; + } else { + ret = 0; + } + + if (fd < 0) return -EINVAL; spin_lock(&group->notification_lock); @@ -340,9 +380,9 @@ static int process_access_response(struct fsnotify_group *group, continue; list_del_init(&event->fae.fse.list); - finish_permission_event(group, event, response); + finish_permission_event(group, event, response, &friar); wake_up(&group->fanotify_data.access_waitq); - return 0; + return ret; } spin_unlock(&group->notification_lock); @@ -804,7 +844,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, if (ret <= 0) { spin_lock(&group->notification_lock); finish_permission_event(group, - FANOTIFY_PERM(event), FAN_DENY); + FANOTIFY_PERM(event), FAN_DENY, NULL); wake_up(&group->fanotify_data.access_waitq); } else { spin_lock(&group->notification_lock); @@ -827,28 +867,32 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct fanotify_response response = { .fd = -1, .response = -1 }; + struct fanotify_response response; struct fsnotify_group *group; int ret; + const char __user *info_buf = buf + sizeof(struct fanotify_response); + size_t info_len; if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) return -EINVAL; group = file->private_data; + pr_debug("%s: group=%p count=%zu\n", __func__, group, count); + if (count < sizeof(response)) return -EINVAL; - count = sizeof(response); - - pr_debug("%s: group=%p count=%zu\n", __func__, group, count); - - if (copy_from_user(&response, buf, count)) + if (copy_from_user(&response, buf, sizeof(response))) return -EFAULT; - ret = process_access_response(group, &response); + info_len = count - sizeof(response); + + ret = process_access_response(group, &response, info_buf, info_len); if (ret < 0) count = ret; + else + count = sizeof(response) + ret; return count; } @@ -876,7 +920,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) event = list_first_entry(&group->fanotify_data.access_list, struct fanotify_perm_event, fae.fse.list); list_del_init(&event->fae.fse.list); - finish_permission_event(group, event, FAN_ALLOW); + finish_permission_event(group, event, FAN_ALLOW, NULL); spin_lock(&group->notification_lock); } @@ -893,7 +937,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) fsnotify_destroy_event(group, fsn_event); } else { finish_permission_event(group, FANOTIFY_PERM(event), - FAN_ALLOW); + FAN_ALLOW, NULL); } spin_lock(&group->notification_lock); } diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 08c659332e26..e6fc5f7cb1d7 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2865,7 +2865,7 @@ void ntfs_truncate_vfs(struct inode *vi) { /** * ntfs_setattr - called from notify_change() when an attribute is being changed - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: dentry whose attributes to change * @attr: structure describing the attributes and the changes * @@ -2878,14 +2878,14 @@ void ntfs_truncate_vfs(struct inode *vi) { * * Called with ->i_mutex held. */ -int ntfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ntfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *vi = d_inode(dentry); int err; unsigned int ia_valid = attr->ia_valid; - err = setattr_prepare(&init_user_ns, dentry, attr); + err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err) goto out; /* We do not support NTFS ACLs yet. */ diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h index 6f78ee00f57f..147ef4ddb691 100644 --- a/fs/ntfs/inode.h +++ b/fs/ntfs/inode.h @@ -289,7 +289,7 @@ extern int ntfs_show_options(struct seq_file *sf, struct dentry *root); extern int ntfs_truncate(struct inode *vi); extern void ntfs_truncate_vfs(struct inode *vi); -extern int ntfs_setattr(struct user_namespace *mnt_userns, +extern int ntfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern int __ntfs_write_inode(struct inode *vi, int sync); diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index d294cd975688..e9bdc1ff08c9 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -70,7 +70,7 @@ static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg) /* * ntfs_getattr - inode_operations::getattr */ -int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags) { struct inode *inode = d_inode(path->dentry); @@ -84,7 +84,7 @@ int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->attributes_mask |= STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED; - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); stat->result_mask |= STATX_BTIME; stat->btime = ni->i_crtime; @@ -657,7 +657,7 @@ out: /* * ntfs3_setattr - inode_operations::setattr */ -int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct super_block *sb = dentry->d_sb; @@ -676,7 +676,7 @@ int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, ia_valid = attr->ia_valid; } - err = setattr_prepare(mnt_userns, dentry, attr); + err = setattr_prepare(idmap, dentry, attr); if (err) goto out; @@ -704,10 +704,10 @@ int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, inode->i_size = newsize; } - setattr_copy(mnt_userns, inode, attr); + setattr_copy(idmap, inode, attr); if (mode != inode->i_mode) { - err = ntfs_acl_chmod(mnt_userns, dentry); + err = ntfs_acl_chmod(idmap, dentry); if (err) goto out; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 20b953871574..8ce2616b087f 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -1185,7 +1185,7 @@ out: * * NOTE: if fnd != NULL (ntfs_atomic_open) then @dir is locked */ -struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, +struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const struct cpu_str *uni, umode_t mode, dev_t dev, const char *symname, u32 size, @@ -1307,7 +1307,7 @@ struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, goto out3; } inode = &ni->vfs_inode; - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); mode = inode->i_mode; inode->i_atime = inode->i_mtime = inode->i_ctime = ni->i_crtime = @@ -1614,7 +1614,7 @@ struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, #ifdef CONFIG_NTFS3_FS_POSIX_ACL if (!S_ISLNK(mode) && (sb->s_flags & SB_POSIXACL)) { - err = ntfs_init_acl(mnt_userns, inode, dir); + err = ntfs_init_acl(idmap, inode, dir); if (err) goto out7; } else diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index c8db35e2ae17..407fe92394e2 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -94,12 +94,12 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry, /* * ntfs_create - inode_operations::create */ -static int ntfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; - inode = ntfs_create_inode(mnt_userns, dir, dentry, NULL, S_IFREG | mode, + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; @@ -110,12 +110,12 @@ static int ntfs_create(struct user_namespace *mnt_userns, struct inode *dir, * * inode_operations::mknod */ -static int ntfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int ntfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; - inode = ntfs_create_inode(mnt_userns, dir, dentry, NULL, mode, rdev, + inode = ntfs_create_inode(idmap, dir, dentry, NULL, mode, rdev, NULL, 0, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; @@ -183,13 +183,13 @@ static int ntfs_unlink(struct inode *dir, struct dentry *dentry) /* * ntfs_symlink - inode_operations::symlink */ -static int ntfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { u32 size = strlen(symname); struct inode *inode; - inode = ntfs_create_inode(mnt_userns, dir, dentry, NULL, S_IFLNK | 0777, + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0, symname, size, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; @@ -198,12 +198,12 @@ static int ntfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, /* * ntfs_mkdir- inode_operations::mkdir */ -static int ntfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; - inode = ntfs_create_inode(mnt_userns, dir, dentry, NULL, S_IFDIR | mode, + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, 0, NULL, 0, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; @@ -229,7 +229,7 @@ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry) /* * ntfs_rename - inode_operations::rename */ -static int ntfs_rename(struct user_namespace *mnt_userns, struct inode *dir, +static int ntfs_rename(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct inode *new_dir, struct dentry *new_dentry, u32 flags) { @@ -415,13 +415,13 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, /* * Unfortunately I don't know how to get here correct 'struct nameidata *nd' - * or 'struct user_namespace *mnt_userns'. + * or 'struct mnt_idmap *idmap'. * See atomic_open in fs/namei.c. * This is why xfstest/633 failed. - * Looks like ntfs_atomic_open must accept 'struct user_namespace *mnt_userns' as argument. + * Looks like ntfs_atomic_open must accept 'struct mnt_idmap *idmap' as argument. */ - inode = ntfs_create_inode(&init_user_ns, dir, dentry, uni, mode, 0, + inode = ntfs_create_inode(&nop_mnt_idmap, dir, dentry, uni, mode, 0, NULL, 0, fnd); err = IS_ERR(inode) ? PTR_ERR(inode) : finish_open(file, dentry, ntfs_file_open); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 0e051c5595a2..80072e5f96f7 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -492,10 +492,12 @@ bool dir_is_empty(struct inode *dir); extern const struct file_operations ntfs_dir_operations; /* Globals from file.c */ -int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); -int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); +void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, + CLST len); int ntfs_file_open(struct inode *inode, struct file *file); int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); @@ -706,7 +708,7 @@ int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); int inode_write_data(struct inode *inode, const void *data, size_t bytes); -struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, +struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const struct cpu_str *uni, umode_t mode, dev_t dev, const char *symname, u32 size, @@ -857,17 +859,17 @@ unsigned long ntfs_names_hash(const u16 *name, size_t len, const u16 *upcase, /* globals from xattr.c */ #ifdef CONFIG_NTFS3_FS_POSIX_ACL struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu); -int ntfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ntfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); -int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, +int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, struct inode *dir); #else #define ntfs_get_acl NULL #define ntfs_set_acl NULL #endif -int ntfs_acl_chmod(struct user_namespace *mnt_userns, struct dentry *dentry); -int ntfs_permission(struct user_namespace *mnt_userns, struct inode *inode, +int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); +int ntfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); extern const struct xattr_handler *ntfs_xattr_handlers[]; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 616df209feea..ff64302e87e5 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -578,7 +578,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu) return ntfs_get_acl_ex(inode, type, 0); } -static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, +static noinline int ntfs_set_acl_ex(struct mnt_idmap *idmap, struct inode *inode, struct posix_acl *acl, int type, bool init_acl) { @@ -597,7 +597,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, case ACL_TYPE_ACCESS: /* Do not change i_mode if we are in init_acl */ if (acl && !init_acl) { - err = posix_acl_update_mode(mnt_userns, inode, &mode, + err = posix_acl_update_mode(idmap, inode, &mode, &acl); if (err) return err; @@ -652,10 +652,10 @@ out: /* * ntfs_set_acl - inode_operations::set_acl */ -int ntfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ntfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { - return ntfs_set_acl_ex(mnt_userns, d_inode(dentry), acl, type, false); + return ntfs_set_acl_ex(idmap, d_inode(dentry), acl, type, false); } /* @@ -663,7 +663,7 @@ int ntfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, * * Called from ntfs_create_inode(). */ -int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, +int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, struct inode *dir) { struct posix_acl *default_acl, *acl; @@ -674,7 +674,7 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, return err; if (default_acl) { - err = ntfs_set_acl_ex(mnt_userns, inode, default_acl, + err = ntfs_set_acl_ex(idmap, inode, default_acl, ACL_TYPE_DEFAULT, true); posix_acl_release(default_acl); } else { @@ -683,7 +683,7 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, if (acl) { if (!err) - err = ntfs_set_acl_ex(mnt_userns, inode, acl, + err = ntfs_set_acl_ex(idmap, inode, acl, ACL_TYPE_ACCESS, true); posix_acl_release(acl); } else { @@ -697,7 +697,7 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, /* * ntfs_acl_chmod - Helper for ntfs3_setattr(). */ -int ntfs_acl_chmod(struct user_namespace *mnt_userns, struct dentry *dentry) +int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; @@ -708,13 +708,13 @@ int ntfs_acl_chmod(struct user_namespace *mnt_userns, struct dentry *dentry) if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - return posix_acl_chmod(mnt_userns, dentry, inode->i_mode); + return posix_acl_chmod(idmap, dentry, inode->i_mode); } /* * ntfs_permission - inode_operations::permission */ -int ntfs_permission(struct user_namespace *mnt_userns, struct inode *inode, +int ntfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (ntfs_sb(inode->i_sb)->options->noacsrules) { @@ -722,7 +722,7 @@ int ntfs_permission(struct user_namespace *mnt_userns, struct inode *inode, return 0; } - return generic_permission(mnt_userns, inode, mask); + return generic_permission(idmap, inode, mask); } /* @@ -835,7 +835,7 @@ out: * ntfs_setxattr - inode_operations::setxattr */ static noinline int ntfs_setxattr(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *de, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 9f19cf9a5a9f..9fd03eaf15f8 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -260,7 +260,7 @@ static int ocfs2_set_acl(handle_t *handle, return ret; } -int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ocfs2_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct buffer_head *bh = NULL; @@ -274,7 +274,7 @@ int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, if (type == ACL_TYPE_ACCESS && acl) { umode_t mode; - status = posix_acl_update_mode(&init_user_ns, inode, &mode, + status = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (status) goto unlock; diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index a897c4e41b26..667c6f03fa60 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -17,7 +17,7 @@ struct ocfs2_acl_entry { }; struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type, bool rcu); -int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ocfs2_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 8b2020f92b5f..ba26c5567cff 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -188,18 +188,18 @@ static int dlmfs_file_release(struct inode *inode, * We do ->setattr() just to override size changes. Our size is the size * of the LVB and nothing else. */ -static int dlmfs_file_setattr(struct user_namespace *mnt_userns, +static int dlmfs_file_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); attr->ia_valid &= ~ATTR_SIZE; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -336,7 +336,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { inode->i_ino = get_next_ino(); - inode_init_owner(&init_user_ns, inode, NULL, mode); + inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inc_nlink(inode); @@ -359,7 +359,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, return NULL; inode->i_ino = get_next_ino(); - inode_init_owner(&init_user_ns, inode, parent, mode); + inode_init_owner(&nop_mnt_idmap, inode, parent, mode); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); ip = DLMFS_I(inode); @@ -402,7 +402,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, * File creation. Allocate an inode, and we're done.. */ /* SMP-safe */ -static int dlmfs_mkdir(struct user_namespace * mnt_userns, +static int dlmfs_mkdir(struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, umode_t mode) @@ -451,7 +451,7 @@ bail: return status; } -static int dlmfs_create(struct user_namespace *mnt_userns, +static int dlmfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 5c60b6bc85bf..efb09de4343d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1111,7 +1111,7 @@ out: return ret; } -int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int status = 0, size_change; @@ -1142,11 +1142,11 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (!(attr->ia_valid & OCFS2_VALID_ATTRS)) return 0; - status = setattr_prepare(&init_user_ns, dentry, attr); + status = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (status) return status; - if (is_quota_modification(mnt_userns, inode, attr)) { + if (is_quota_modification(&nop_mnt_idmap, inode, attr)) { status = dquot_initialize(inode); if (status) return status; @@ -1265,7 +1265,7 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); status = ocfs2_mark_inode_dirty(handle, inode, bh); @@ -1302,7 +1302,7 @@ bail: return status; } -int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ocfs2_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); @@ -1317,7 +1317,7 @@ int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path, goto bail; } - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); /* * If there is inline data in the inode, the inode will normally not * have data blocks allocated (it may have an external xattr block). @@ -1334,7 +1334,7 @@ bail: return err; } -int ocfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, +int ocfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret, had_lock; @@ -1360,7 +1360,7 @@ int ocfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, dump_stack(); } - ret = generic_permission(&init_user_ns, inode, mask); + ret = generic_permission(&nop_mnt_idmap, inode, mask); ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); out: @@ -1991,7 +1991,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, } } - if (file && setattr_should_drop_suidgid(&init_user_ns, file_inode(file))) { + if (file && setattr_should_drop_suidgid(&nop_mnt_idmap, file_inode(file))) { ret = __ocfs2_write_remove_suid(inode, di_bh); if (ret) { mlog_errno(ret); @@ -2279,7 +2279,7 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * inode. There's also the dinode i_size state which * can be lost via setattr during extending writes (we * set inode->i_size at the end of a write. */ - if (setattr_should_drop_suidgid(&init_user_ns, inode)) { + if (setattr_should_drop_suidgid(&nop_mnt_idmap, inode)) { if (meta_level == 0) { ocfs2_inode_unlock_for_extent_tree(inode, &di_bh, diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 71db8f3aa027..8e53e4ac1120 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -49,11 +49,11 @@ int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size, u64 zero_to); int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, loff_t zero_to); -int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ocfs2_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); -int ocfs2_permission(struct user_namespace *mnt_userns, +int ocfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index afd54ec66103..811a6ea374bb 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -82,7 +82,7 @@ int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa) return status; } -int ocfs2_fileattr_set(struct user_namespace *mnt_userns, +int ocfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/ocfs2/ioctl.h b/fs/ocfs2/ioctl.h index 0297c8846945..48a5fdfe87a1 100644 --- a/fs/ocfs2/ioctl.h +++ b/fs/ocfs2/ioctl.h @@ -12,7 +12,7 @@ #define OCFS2_IOCTL_PROTO_H int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int ocfs2_fileattr_set(struct user_namespace *mnt_userns, +int ocfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg); diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index 73a3854b2afb..f37174e79fad 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -8,6 +8,7 @@ */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/fcntl.h> #include <cluster/masklog.h> diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index a8fd51afb794..9175dbc47201 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -197,8 +197,8 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); - mode = mode_strip_sgid(&init_user_ns, dir, mode); - inode_init_owner(&init_user_ns, inode, dir, mode); + mode = mode_strip_sgid(&nop_mnt_idmap, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); status = dquot_initialize(inode); if (status) return ERR_PTR(status); @@ -221,7 +221,7 @@ static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb, iput(inode); } -static int ocfs2_mknod(struct user_namespace *mnt_userns, +static int ocfs2_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, @@ -642,7 +642,7 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, fe_blkno, suballoc_loc, suballoc_bit); } -static int ocfs2_mkdir(struct user_namespace *mnt_userns, +static int ocfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) @@ -651,14 +651,14 @@ static int ocfs2_mkdir(struct user_namespace *mnt_userns, trace_ocfs2_mkdir(dir, dentry, dentry->d_name.len, dentry->d_name.name, OCFS2_I(dir)->ip_blkno, mode); - ret = ocfs2_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0); + ret = ocfs2_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); if (ret) mlog_errno(ret); return ret; } -static int ocfs2_create(struct user_namespace *mnt_userns, +static int ocfs2_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, @@ -668,7 +668,7 @@ static int ocfs2_create(struct user_namespace *mnt_userns, trace_ocfs2_create(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, mode); - ret = ocfs2_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); + ret = ocfs2_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); if (ret) mlog_errno(ret); @@ -1194,7 +1194,7 @@ static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2) ocfs2_inode_unlock(inode2, 1); } -static int ocfs2_rename(struct user_namespace *mnt_userns, +static int ocfs2_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -1784,7 +1784,7 @@ bail: return status; } -static int ocfs2_symlink(struct user_namespace *mnt_userns, +static int ocfs2_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 623db358b1ef..5a656dc683f1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4316,7 +4316,7 @@ static inline int ocfs2_may_create(struct inode *dir, struct dentry *child) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); + return inode_permission(&nop_mnt_idmap, dir, MAY_WRITE | MAY_EXEC); } /** @@ -4370,7 +4370,7 @@ static int ocfs2_vfs_reflink(struct dentry *old_dentry, struct inode *dir, * file. */ if (!preserve) { - error = inode_permission(&init_user_ns, inode, MAY_READ); + error = inode_permission(&nop_mnt_idmap, inode, MAY_READ); if (error) return error; } diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 64e6ddcfe329..05d4414d0c33 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/miscdevice.h> #include <linux/mutex.h> #include <linux/slab.h> diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 95d0611c5fc7..389308efe854 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7247,7 +7247,7 @@ static int ocfs2_xattr_security_get(const struct xattr_handler *handler, } static int ocfs2_xattr_security_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -7320,7 +7320,7 @@ static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler, } static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -7351,7 +7351,7 @@ static int ocfs2_xattr_user_get(const struct xattr_handler *handler, } static int ocfs2_xattr_user_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index c219f91f44e9..82cf7e9a665f 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -279,13 +279,13 @@ out_free_inode: return err; } -static int omfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int omfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { return omfs_add_node(dir, dentry, mode | S_IFDIR); } -static int omfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int omfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return omfs_add_node(dir, dentry, mode | S_IFREG); @@ -370,7 +370,7 @@ static bool omfs_fill_chain(struct inode *dir, struct dir_context *ctx, return true; } -static int omfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int omfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 3a5b4b88a583..0101f1f87b56 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -337,13 +337,13 @@ const struct file_operations omfs_file_operations = { .splice_read = generic_file_splice_read, }; -static int omfs_setattr(struct user_namespace *mnt_userns, +static int omfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -356,7 +356,7 @@ static int omfs_setattr(struct user_namespace *mnt_userns, omfs_truncate(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 2a0e83236c01..c4c79e07efc7 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -48,7 +48,7 @@ struct inode *omfs_new_inode(struct inode *dir, umode_t mode) goto fail; inode->i_ino = new_block; - inode_init_owner(&init_user_ns, inode, NULL, mode); + inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_mapping->a_ops = &omfs_aops; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); diff --git a/fs/open.c b/fs/open.c index 82c1a28b3308..8038cf652583 100644 --- a/fs/open.c +++ b/fs/open.c @@ -33,10 +33,11 @@ #include <linux/dnotify.h> #include <linux/compat.h> #include <linux/mnt_idmapping.h> +#include <linux/filelock.h> #include "internal.h" -int do_truncate(struct user_namespace *mnt_userns, struct dentry *dentry, +int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; @@ -54,7 +55,7 @@ int do_truncate(struct user_namespace *mnt_userns, struct dentry *dentry, } /* Remove suid, sgid, and file capabilities on truncate too */ - ret = dentry_needs_remove_privs(mnt_userns, dentry); + ret = dentry_needs_remove_privs(idmap, dentry); if (ret < 0) return ret; if (ret) @@ -62,14 +63,14 @@ int do_truncate(struct user_namespace *mnt_userns, struct dentry *dentry, inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ - ret = notify_change(mnt_userns, dentry, &newattrs, NULL); + ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct inode *inode; long error; @@ -85,8 +86,8 @@ long vfs_truncate(const struct path *path, loff_t length) if (error) goto out; - mnt_userns = mnt_user_ns(path->mnt); - error = inode_permission(mnt_userns, inode, MAY_WRITE); + idmap = mnt_idmap(path->mnt); + error = inode_permission(idmap, inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; @@ -108,7 +109,7 @@ long vfs_truncate(const struct path *path, loff_t length) error = security_path_truncate(path); if (!error) - error = do_truncate(mnt_userns, path->dentry, length, 0, NULL); + error = do_truncate(idmap, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); @@ -190,7 +191,7 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small) sb_start_write(inode->i_sb); error = security_file_truncate(f.file); if (!error) - error = do_truncate(file_mnt_user_ns(f.file), dentry, length, + error = do_truncate(file_mnt_idmap(f.file), dentry, length, ATTR_MTIME | ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: @@ -459,7 +460,7 @@ retry: goto out_path_release; } - res = inode_permission(mnt_user_ns(path.mnt), inode, mode | MAY_ACCESS); + res = inode_permission(mnt_idmap(path.mnt), inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; @@ -603,7 +604,7 @@ retry_deleg: goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; - error = notify_change(mnt_user_ns(path->mnt), path->dentry, + error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); @@ -701,7 +702,8 @@ static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid) int chown_common(const struct path *path, uid_t user, gid_t group) { - struct user_namespace *mnt_userns, *fs_userns; + struct mnt_idmap *idmap; + struct user_namespace *fs_userns; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; @@ -712,7 +714,7 @@ int chown_common(const struct path *path, uid_t user, gid_t group) uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); - mnt_userns = mnt_user_ns(path->mnt); + idmap = mnt_idmap(path->mnt); fs_userns = i_user_ns(inode); retry_deleg: @@ -726,14 +728,14 @@ retry_deleg: inode_lock(inode); if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | - setattr_should_drop_sgid(mnt_userns, inode); + setattr_should_drop_sgid(idmap, inode); /* Continue to send actual fs values, not the mount values. */ error = security_path_chown( path, - from_vfsuid(mnt_userns, fs_userns, newattrs.ia_vfsuid), - from_vfsgid(mnt_userns, fs_userns, newattrs.ia_vfsgid)); + from_vfsuid(idmap, fs_userns, newattrs.ia_vfsuid), + from_vfsgid(idmap, fs_userns, newattrs.ia_vfsgid)); if (!error) - error = notify_change(mnt_userns, path->dentry, &newattrs, + error = notify_change(idmap, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { @@ -870,7 +872,7 @@ static int do_dentry_open(struct file *f, if (error) goto cleanup_all; - error = break_lease(locks_inode(f), f->f_flags); + error = break_lease(file_inode(f), f->f_flags); if (error) goto cleanup_all; @@ -1064,7 +1066,7 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode, if (IS_ERR(f)) return f; - error = vfs_create(mnt_user_ns(path->mnt), + error = vfs_create(mnt_idmap(path->mnt), d_inode(path->dentry->d_parent), path->dentry, mode, true); if (!error) @@ -1411,8 +1413,9 @@ int filp_close(struct file *filp, fl_owner_t id) { int retval = 0; - if (!file_count(filp)) { - printk(KERN_ERR "VFS: Close: file count is 0\n"); + if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, + "VFS: Close: file count is 0 (f_op=%ps)", + filp->f_op)) { return 0; } diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index c5da2091cefb..5aefb705bcc8 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -118,7 +118,7 @@ out: return error; } -int orangefs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int orangefs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; @@ -136,7 +136,7 @@ int orangefs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, * and "mode" to the new desired value. It is up to * us to propagate the new mode back to the server... */ - error = posix_acl_update_mode(&init_user_ns, inode, + error = posix_acl_update_mode(&nop_mnt_idmap, inode, &iattr.ia_mode, &acl); if (error) { gossip_err("%s: posix_acl_update_mode err: %d\n", diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index 167fa43b24f9..4ecb91a9bbeb 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -14,6 +14,7 @@ #include "orangefs-kernel.h" #include "orangefs-bufmap.h" #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/pagemap.h> static int flush_racache(struct inode *inode) diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 4df560894386..11e21a0e65ce 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -822,7 +822,7 @@ again: ORANGEFS_I(inode)->attr_uid = current_fsuid(); ORANGEFS_I(inode)->attr_gid = current_fsgid(); } - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); spin_unlock(&inode->i_lock); mark_inode_dirty(inode); @@ -839,20 +839,20 @@ int __orangefs_setattr_mode(struct dentry *dentry, struct iattr *iattr) ret = __orangefs_setattr(inode, iattr); /* change mode on a file that has ACLs */ if (!ret && (iattr->ia_valid & ATTR_MODE)) - ret = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode); + ret = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); return ret; } /* * Change attributes of an object referenced by dentry. */ -int orangefs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int orangefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int ret; gossip_debug(GOSSIP_INODE_DEBUG, "__orangefs_setattr: called on %pd\n", dentry); - ret = setattr_prepare(&init_user_ns, dentry, iattr); + ret = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (ret) goto out; ret = __orangefs_setattr_mode(dentry, iattr); @@ -866,7 +866,7 @@ out: /* * Obtain attributes of an object given a dentry */ -int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int orangefs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { int ret; @@ -879,7 +879,7 @@ int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, ret = orangefs_inode_getattr(inode, request_mask & STATX_SIZE ? ORANGEFS_GETATTR_SIZE : 0); if (ret == 0) { - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); /* override block size reported to stat */ if (!(request_mask & STATX_SIZE)) @@ -890,7 +890,7 @@ int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, return ret; } -int orangefs_permission(struct user_namespace *mnt_userns, +int orangefs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret; @@ -905,7 +905,7 @@ int orangefs_permission(struct user_namespace *mnt_userns, if (ret < 0) return ret; - return generic_permission(&init_user_ns, inode, mask); + return generic_permission(&nop_mnt_idmap, inode, mask); } int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags) @@ -944,7 +944,7 @@ static int orangefs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -static int orangefs_fileattr_set(struct user_namespace *mnt_userns, +static int orangefs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { u64 val = 0; diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index 75c1a3dcf68c..77518e248cf7 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -15,7 +15,7 @@ /* * Get a newly allocated inode to go with a negative dentry. */ -static int orangefs_create(struct user_namespace *mnt_userns, +static int orangefs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, @@ -216,7 +216,7 @@ static int orangefs_unlink(struct inode *dir, struct dentry *dentry) return ret; } -static int orangefs_symlink(struct user_namespace *mnt_userns, +static int orangefs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) @@ -305,7 +305,7 @@ out: return ret; } -static int orangefs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct orangefs_inode_s *parent = ORANGEFS_I(dir); @@ -375,7 +375,7 @@ out: return ret; } -static int orangefs_rename(struct user_namespace *mnt_userns, +static int orangefs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 6e0cc01b3a14..ce20d3443869 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -106,7 +106,7 @@ enum orangefs_vfs_op_states { extern const struct xattr_handler *orangefs_xattr_handlers[]; extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu); -extern int orangefs_set_acl(struct user_namespace *mnt_userns, +extern int orangefs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int __orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type); @@ -362,12 +362,12 @@ struct inode *orangefs_new_inode(struct super_block *sb, int __orangefs_setattr(struct inode *, struct iattr *); int __orangefs_setattr_mode(struct dentry *dentry, struct iattr *iattr); -int orangefs_setattr(struct user_namespace *, struct dentry *, struct iattr *); +int orangefs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); -int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int orangefs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); -int orangefs_permission(struct user_namespace *mnt_userns, +int orangefs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); int orangefs_update_time(struct inode *, struct timespec64 *, int); diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 9a5b757fbd2f..6ecad4f94ae6 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -526,7 +526,7 @@ out_unlock: } static int orangefs_xattr_set_default(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index f61e37f4c8ff..fc25fb95d5fc 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -641,7 +641,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, inode->i_state |= I_CREATING; spin_unlock(&inode->i_lock); - inode_init_owner(&init_user_ns, inode, dentry->d_parent->d_inode, mode); + inode_init_owner(&nop_mnt_idmap, inode, dentry->d_parent->d_inode, mode); attr.mode = inode->i_mode; err = ovl_create_or_link(dentry, inode, &attr, false); @@ -655,19 +655,19 @@ out: return err; } -static int ovl_create(struct user_namespace *mnt_userns, struct inode *dir, +static int ovl_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); } -static int ovl_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ovl_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); } -static int ovl_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { /* Don't allow creation of "whiteout" on overlay */ @@ -677,7 +677,7 @@ static int ovl_mknod(struct user_namespace *mnt_userns, struct inode *dir, return ovl_create_object(dentry, mode, rdev, NULL); } -static int ovl_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int ovl_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *link) { return ovl_create_object(dentry, S_IFLNK, 0, link); @@ -1075,7 +1075,7 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) return err; } -static int ovl_rename(struct user_namespace *mnt_userns, struct inode *olddir, +static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, struct dentry *old, struct inode *newdir, struct dentry *new, unsigned int flags) { diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index a25bb3453dde..defd4e231ad2 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -392,8 +392,8 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected, */ take_dentry_name_snapshot(&name, real); /* - * No mnt_userns handling here: it's an internal lookup. Could skip - * permission checking altogether, but for now just use non-mnt_userns + * No idmap handling here: it's an internal lookup. Could skip + * permission checking altogether, but for now just use non-idmap * transformed ids. */ this = lookup_one_len(name.name.name, connected, name.name.len); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index c9d0c362c7ef..7c04f033aadd 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -42,7 +42,7 @@ static struct file *ovl_open_realfile(const struct file *file, { struct inode *realinode = d_inode(realpath->dentry); struct inode *inode = file_inode(file); - struct user_namespace *real_mnt_userns; + struct mnt_idmap *real_idmap; struct file *realfile; const struct cred *old_cred; int flags = file->f_flags | OVL_OPEN_FLAGS; @@ -53,12 +53,12 @@ static struct file *ovl_open_realfile(const struct file *file, acc_mode |= MAY_APPEND; old_cred = ovl_override_creds(inode->i_sb); - real_mnt_userns = mnt_user_ns(realpath->mnt); - err = inode_permission(real_mnt_userns, realinode, MAY_OPEN | acc_mode); + real_idmap = mnt_idmap(realpath->mnt); + err = inode_permission(real_idmap, realinode, MAY_OPEN | acc_mode); if (err) { realfile = ERR_PTR(err); } else { - if (!inode_owner_or_capable(real_mnt_userns, realinode)) + if (!inode_owner_or_capable(real_idmap, realinode)) flags &= ~O_NOATIME; realfile = open_with_fake_path(&file->f_path, flags, realinode, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index ee6dfa577c93..541cf3717fc2 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -19,7 +19,7 @@ #include "overlayfs.h" -int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int err; @@ -28,7 +28,7 @@ int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct dentry *upperdentry; const struct cred *old_cred; - err = setattr_prepare(&init_user_ns, dentry, attr); + err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err) return err; @@ -153,7 +153,7 @@ static void ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) } } -int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; @@ -278,7 +278,7 @@ out: return err; } -int ovl_permission(struct user_namespace *mnt_userns, +int ovl_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct inode *upperinode = ovl_inode_upper(inode); @@ -298,7 +298,7 @@ int ovl_permission(struct user_namespace *mnt_userns, * Check overlay inode with the creds of task and underlying inode * with creds of mounter */ - err = generic_permission(&init_user_ns, inode, mask); + err = generic_permission(&nop_mnt_idmap, inode, mask); if (err) return err; @@ -310,7 +310,7 @@ int ovl_permission(struct user_namespace *mnt_userns, /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; } - err = inode_permission(mnt_user_ns(realpath.mnt), realinode, mask); + err = inode_permission(mnt_idmap(realpath.mnt), realinode, mask); revert_creds(old_cred); return err; @@ -361,7 +361,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, if (!value && !upperdentry) { ovl_path_lower(dentry, &realpath); old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_getxattr(mnt_user_ns(realpath.mnt), realdentry, name, NULL, 0); + err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0); revert_creds(old_cred); if (err < 0) goto out_drop_write; @@ -403,7 +403,7 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, ovl_i_path_real(inode, &realpath); old_cred = ovl_override_creds(dentry->d_sb); - res = vfs_getxattr(mnt_user_ns(realpath.mnt), realpath.dentry, name, value, size); + res = vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size); revert_creds(old_cred); return res; } @@ -463,7 +463,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) * alter the POSIX ACLs for the underlying filesystem. */ static void ovl_idmap_posix_acl(const struct inode *realinode, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct posix_acl *acl) { struct user_namespace *fs_userns = i_user_ns(realinode); @@ -475,11 +475,11 @@ static void ovl_idmap_posix_acl(const struct inode *realinode, struct posix_acl_entry *e = &acl->a_entries[i]; switch (e->e_tag) { case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, fs_userns, e->e_uid); + vfsuid = make_vfsuid(idmap, fs_userns, e->e_uid); e->e_uid = vfsuid_into_kuid(vfsuid); break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, fs_userns, e->e_gid); + vfsgid = make_vfsgid(idmap, fs_userns, e->e_gid); e->e_gid = vfsgid_into_kgid(vfsgid); break; } @@ -514,15 +514,15 @@ struct posix_acl *ovl_get_acl_path(const struct path *path, const char *acl_name, bool noperm) { struct posix_acl *real_acl, *clone; - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct inode *realinode = d_inode(path->dentry); - mnt_userns = mnt_user_ns(path->mnt); + idmap = mnt_idmap(path->mnt); if (noperm) real_acl = get_inode_acl(realinode, posix_acl_type(acl_name)); else - real_acl = vfs_get_acl(mnt_userns, path->dentry, acl_name); + real_acl = vfs_get_acl(idmap, path->dentry, acl_name); if (IS_ERR_OR_NULL(real_acl)) return real_acl; @@ -540,7 +540,7 @@ struct posix_acl *ovl_get_acl_path(const struct path *path, if (!clone) return ERR_PTR(-ENOMEM); - ovl_idmap_posix_acl(realinode, mnt_userns, clone); + ovl_idmap_posix_acl(realinode, idmap, clone); return clone; } @@ -555,7 +555,7 @@ struct posix_acl *ovl_get_acl_path(const struct path *path, * * This is obviously only relevant when idmapped layers are used. */ -struct posix_acl *do_ovl_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap, struct inode *inode, int type, bool rcu, bool noperm) { @@ -618,7 +618,7 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, ovl_path_lower(dentry, &realpath); old_cred = ovl_override_creds(dentry->d_sb); - real_acl = vfs_get_acl(mnt_user_ns(realpath.mnt), realdentry, + real_acl = vfs_get_acl(mnt_idmap(realpath.mnt), realdentry, acl_name); revert_creds(old_cred); if (IS_ERR(real_acl)) { @@ -651,7 +651,7 @@ out_drop_write: return err; } -int ovl_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int err; @@ -665,7 +665,7 @@ int ovl_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) return -EPERM; /* @@ -674,10 +674,10 @@ int ovl_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, */ if (unlikely(inode->i_mode & S_ISGID) && type == ACL_TYPE_ACCESS && !in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) { + !capable_wrt_inode_uidgid(&nop_mnt_idmap, inode, CAP_FSETID)) { struct iattr iattr = { .ia_valid = ATTR_KILL_SGID }; - err = ovl_setattr(&init_user_ns, dentry, &iattr); + err = ovl_setattr(&nop_mnt_idmap, dentry, &iattr); if (err) return err; } @@ -755,10 +755,10 @@ int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa) if (err) return err; - return vfs_fileattr_set(mnt_user_ns(realpath->mnt), realpath->dentry, fa); + return vfs_fileattr_set(mnt_idmap(realpath->mnt), realpath->dentry, fa); } -int ovl_fileattr_set(struct user_namespace *mnt_userns, +int ovl_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 46753134533a..cfb3420b7df0 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -204,7 +204,7 @@ static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d, struct dentry *base, int len, bool drop_negative) { - struct dentry *ret = lookup_one_unlocked(mnt_user_ns(d->mnt), name, base, len); + struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { if (drop_negative && ret->d_lockref.count == 1) { @@ -711,7 +711,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, if (err) return ERR_PTR(err); - index = lookup_one_positive_unlocked(ovl_upper_mnt_userns(ofs), name.name, + index = lookup_one_positive_unlocked(ovl_upper_mnt_idmap(ofs), name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); @@ -1182,7 +1182,7 @@ bool ovl_lower_positive(struct dentry *dentry) struct dentry *this; struct dentry *lowerdir = poe->lowerstack[i].dentry; - this = lookup_one_positive_unlocked(mnt_user_ns(poe->lowerstack[i].layer->mnt), + this = lookup_one_positive_unlocked(mnt_idmap(poe->lowerstack[i].layer->mnt), name->name, lowerdir, name->len); if (IS_ERR(this)) { switch (PTR_ERR(this)) { diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 1df7f850ff3b..4d0b278f5630 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -141,13 +141,13 @@ static inline int ovl_do_notify_change(struct ovl_fs *ofs, struct dentry *upperdentry, struct iattr *attr) { - return notify_change(ovl_upper_mnt_userns(ofs), upperdentry, attr, NULL); + return notify_change(ovl_upper_mnt_idmap(ofs), upperdentry, attr, NULL); } static inline int ovl_do_rmdir(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { - int err = vfs_rmdir(ovl_upper_mnt_userns(ofs), dir, dentry); + int err = vfs_rmdir(ovl_upper_mnt_idmap(ofs), dir, dentry); pr_debug("rmdir(%pd2) = %i\n", dentry, err); return err; @@ -156,7 +156,7 @@ static inline int ovl_do_rmdir(struct ovl_fs *ofs, static inline int ovl_do_unlink(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { - int err = vfs_unlink(ovl_upper_mnt_userns(ofs), dir, dentry, NULL); + int err = vfs_unlink(ovl_upper_mnt_idmap(ofs), dir, dentry, NULL); pr_debug("unlink(%pd2) = %i\n", dentry, err); return err; @@ -165,7 +165,8 @@ static inline int ovl_do_unlink(struct ovl_fs *ofs, struct inode *dir, static inline int ovl_do_link(struct ovl_fs *ofs, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { - int err = vfs_link(old_dentry, ovl_upper_mnt_userns(ofs), dir, new_dentry, NULL); + int err = vfs_link(old_dentry, ovl_upper_mnt_idmap(ofs), dir, + new_dentry, NULL); pr_debug("link(%pd2, %pd2) = %i\n", old_dentry, new_dentry, err); return err; @@ -175,7 +176,7 @@ static inline int ovl_do_create(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode) { - int err = vfs_create(ovl_upper_mnt_userns(ofs), dir, dentry, mode, true); + int err = vfs_create(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, true); pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); return err; @@ -185,7 +186,7 @@ static inline int ovl_do_mkdir(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode) { - int err = vfs_mkdir(ovl_upper_mnt_userns(ofs), dir, dentry, mode); + int err = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode); pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err); return err; } @@ -194,7 +195,7 @@ static inline int ovl_do_mknod(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { - int err = vfs_mknod(ovl_upper_mnt_userns(ofs), dir, dentry, mode, dev); + int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev); pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err); return err; @@ -204,7 +205,7 @@ static inline int ovl_do_symlink(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, const char *oldname) { - int err = vfs_symlink(ovl_upper_mnt_userns(ofs), dir, dentry, oldname); + int err = vfs_symlink(ovl_upper_mnt_idmap(ofs), dir, dentry, oldname); pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); return err; @@ -217,7 +218,7 @@ static inline ssize_t ovl_do_getxattr(const struct path *path, const char *name, WARN_ON(path->dentry->d_sb != path->mnt->mnt_sb); - err = vfs_getxattr(mnt_user_ns(path->mnt), path->dentry, + err = vfs_getxattr(mnt_idmap(path->mnt), path->dentry, name, value, size); len = (value && err > 0) ? err : 0; @@ -251,7 +252,7 @@ static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - int err = vfs_setxattr(ovl_upper_mnt_userns(ofs), dentry, name, + int err = vfs_setxattr(ovl_upper_mnt_idmap(ofs), dentry, name, value, size, flags); pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, %d) = %i\n", @@ -269,7 +270,7 @@ static inline int ovl_setxattr(struct ovl_fs *ofs, struct dentry *dentry, static inline int ovl_do_removexattr(struct ovl_fs *ofs, struct dentry *dentry, const char *name) { - int err = vfs_removexattr(ovl_upper_mnt_userns(ofs), dentry, name); + int err = vfs_removexattr(ovl_upper_mnt_idmap(ofs), dentry, name); pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err); return err; } @@ -283,13 +284,13 @@ static inline int ovl_removexattr(struct ovl_fs *ofs, struct dentry *dentry, static inline int ovl_do_set_acl(struct ovl_fs *ofs, struct dentry *dentry, const char *acl_name, struct posix_acl *acl) { - return vfs_set_acl(ovl_upper_mnt_userns(ofs), dentry, acl_name, acl); + return vfs_set_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name, acl); } static inline int ovl_do_remove_acl(struct ovl_fs *ofs, struct dentry *dentry, const char *acl_name) { - return vfs_remove_acl(ovl_upper_mnt_userns(ofs), dentry, acl_name); + return vfs_remove_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name); } static inline int ovl_do_rename(struct ovl_fs *ofs, struct inode *olddir, @@ -298,10 +299,10 @@ static inline int ovl_do_rename(struct ovl_fs *ofs, struct inode *olddir, { int err; struct renamedata rd = { - .old_mnt_userns = ovl_upper_mnt_userns(ofs), + .old_mnt_idmap = ovl_upper_mnt_idmap(ofs), .old_dir = olddir, .old_dentry = olddentry, - .new_mnt_userns = ovl_upper_mnt_userns(ofs), + .new_mnt_idmap = ovl_upper_mnt_idmap(ofs), .new_dir = newdir, .new_dentry = newdentry, .flags = flags, @@ -319,7 +320,7 @@ static inline int ovl_do_rename(struct ovl_fs *ofs, struct inode *olddir, static inline int ovl_do_whiteout(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { - int err = vfs_whiteout(ovl_upper_mnt_userns(ofs), dir, dentry); + int err = vfs_whiteout(ovl_upper_mnt_idmap(ofs), dir, dentry); pr_debug("whiteout(%pd2) = %i\n", dentry, err); return err; } @@ -328,7 +329,7 @@ static inline struct file *ovl_do_tmpfile(struct ovl_fs *ofs, struct dentry *dentry, umode_t mode) { struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = dentry }; - struct file *file = vfs_tmpfile_open(ovl_upper_mnt_userns(ofs), &path, mode, + struct file *file = vfs_tmpfile_open(ovl_upper_mnt_idmap(ofs), &path, mode, O_LARGEFILE | O_WRONLY, current_cred()); int err = PTR_ERR_OR_ZERO(file); @@ -340,7 +341,7 @@ static inline struct dentry *ovl_lookup_upper(struct ovl_fs *ofs, const char *name, struct dentry *base, int len) { - return lookup_one(ovl_upper_mnt_userns(ofs), name, base, len); + return lookup_one(ovl_upper_mnt_idmap(ofs), name, base, len); } static inline bool ovl_open_flags_need_copy_up(int flags) @@ -596,11 +597,11 @@ int ovl_set_nlink_lower(struct dentry *dentry); unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry, struct dentry *upperdentry, unsigned int fallback); -int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); -int ovl_permission(struct user_namespace *mnt_userns, struct inode *inode, +int ovl_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags); @@ -609,20 +610,20 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); #ifdef CONFIG_FS_POSIX_ACL -struct posix_acl *do_ovl_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap, struct inode *inode, int type, bool rcu, bool noperm); static inline struct posix_acl *ovl_get_inode_acl(struct inode *inode, int type, bool rcu) { - return do_ovl_get_acl(&init_user_ns, inode, type, rcu, true); + return do_ovl_get_acl(&nop_mnt_idmap, inode, type, rcu, true); } -static inline struct posix_acl *ovl_get_acl(struct user_namespace *mnt_userns, +static inline struct posix_acl *ovl_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type) { - return do_ovl_get_acl(mnt_userns, d_inode(dentry), type, false, false); + return do_ovl_get_acl(idmap, d_inode(dentry), type, false, false); } -int ovl_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); struct posix_acl *ovl_get_acl_path(const struct path *path, const char *acl_name, bool noperm); @@ -717,7 +718,7 @@ void ovl_aio_request_cache_destroy(void); int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa); int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa); int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int ovl_fileattr_set(struct user_namespace *mnt_userns, +int ovl_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); /* copy_up.c */ diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index e1af8f660698..fd11fe6d6d45 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -90,9 +90,9 @@ static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs) return ofs->layers[0].mnt; } -static inline struct user_namespace *ovl_upper_mnt_userns(struct ovl_fs *ofs) +static inline struct mnt_idmap *ovl_upper_mnt_idmap(struct ovl_fs *ofs) { - return mnt_user_ns(ovl_upper_mnt(ofs)); + return mnt_idmap(ovl_upper_mnt(ofs)); } static inline struct ovl_fs *OVL_FS(struct super_block *sb) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 8cd2b9947de1..b6952b21a7ee 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -278,7 +278,7 @@ static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data while (rdd->first_maybe_whiteout) { p = rdd->first_maybe_whiteout; rdd->first_maybe_whiteout = p->next_maybe_whiteout; - dentry = lookup_one(mnt_user_ns(path->mnt), p->name, dir, p->len); + dentry = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); if (!IS_ERR(dentry)) { p->is_whiteout = ovl_is_whiteout(dentry); dput(dentry); @@ -480,7 +480,7 @@ static int ovl_cache_update_ino(const struct path *path, struct ovl_cache_entry goto get; } } - this = lookup_one(mnt_user_ns(path->mnt), p->name, dir, p->len); + this = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); if (IS_ERR_OR_NULL(this) || !this->d_inode) { /* Mark a stale entry */ p->is_whiteout = true; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 85b891152a2c..f1d9f75f8786 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1012,7 +1012,7 @@ static int ovl_own_xattr_get(const struct xattr_handler *handler, } static int ovl_own_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -1028,7 +1028,7 @@ static int ovl_other_xattr_get(const struct xattr_handler *handler, } static int ovl_other_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index bde291623c8c..923d66d131c1 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -491,7 +491,7 @@ bool ovl_is_whiteout(struct dentry *dentry) struct file *ovl_path_open(const struct path *path, int flags) { struct inode *inode = d_inode(path->dentry); - struct user_namespace *real_mnt_userns = mnt_user_ns(path->mnt); + struct mnt_idmap *real_idmap = mnt_idmap(path->mnt); int err, acc_mode; if (flags & ~(O_ACCMODE | O_LARGEFILE)) @@ -508,12 +508,12 @@ struct file *ovl_path_open(const struct path *path, int flags) BUG(); } - err = inode_permission(real_mnt_userns, inode, acc_mode | MAY_OPEN); + err = inode_permission(real_idmap, inode, acc_mode | MAY_OPEN); if (err) return ERR_PTR(err); /* O_NOATIME is an optimization, don't fail if not permitted */ - if (inode_owner_or_capable(real_mnt_userns, inode)) + if (inode_owner_or_capable(real_idmap, inode)) flags |= O_NOATIME; return dentry_open(path, flags, current_cred()); @@ -1101,16 +1101,16 @@ void ovl_copyattr(struct inode *inode) { struct path realpath; struct inode *realinode; - struct user_namespace *real_mnt_userns; + struct mnt_idmap *real_idmap; vfsuid_t vfsuid; vfsgid_t vfsgid; ovl_i_path_real(inode, &realpath); realinode = d_inode(realpath.dentry); - real_mnt_userns = mnt_user_ns(realpath.mnt); + real_idmap = mnt_idmap(realpath.mnt); - vfsuid = i_uid_into_vfsuid(real_mnt_userns, realinode); - vfsgid = i_gid_into_vfsgid(real_mnt_userns, realinode); + vfsuid = i_uid_into_vfsuid(real_idmap, realinode); + vfsgid = i_gid_into_vfsgid(real_idmap, realinode); inode->i_uid = vfsuid_into_kuid(vfsuid); inode->i_gid = vfsgid_into_kgid(vfsgid); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index d7bc81fc0840..5a76fb35923a 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -28,6 +28,7 @@ #include <linux/security.h> #include <linux/evm.h> #include <linux/fsnotify.h> +#include <linux/filelock.h> #include "internal.h" @@ -111,7 +112,7 @@ void forget_all_cached_acls(struct inode *inode) } EXPORT_SYMBOL(forget_all_cached_acls); -static struct posix_acl *__get_acl(struct user_namespace *mnt_userns, +static struct posix_acl *__get_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, int type) { @@ -154,7 +155,7 @@ static struct posix_acl *__get_acl(struct user_namespace *mnt_userns, * we'll just create the negative cache entry. */ if (dentry && inode->i_op->get_acl) { - acl = inode->i_op->get_acl(mnt_userns, dentry, type); + acl = inode->i_op->get_acl(idmap, dentry, type); } else if (inode->i_op->get_inode_acl) { acl = inode->i_op->get_inode_acl(inode, type, false); } else { @@ -174,14 +175,14 @@ static struct posix_acl *__get_acl(struct user_namespace *mnt_userns, * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); - if (unlikely(cmpxchg(p, sentinel, acl) != sentinel)) + if (unlikely(!try_cmpxchg(p, &sentinel, acl))) posix_acl_release(acl); return acl; } struct posix_acl *get_inode_acl(struct inode *inode, int type) { - return __get_acl(&init_user_ns, NULL, inode, type); + return __get_acl(&nop_mnt_idmap, NULL, inode, type); } EXPORT_SYMBOL(get_inode_acl); @@ -372,7 +373,7 @@ EXPORT_SYMBOL(posix_acl_from_mode); * by the acl. Returns -E... otherwise. */ int -posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, +posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; @@ -387,18 +388,18 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto check_perm; break; case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, fs_userns, + vfsuid = make_vfsuid(idmap, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: - vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) @@ -406,7 +407,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, } break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, fs_userns, + vfsgid = make_vfsgid(idmap, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; @@ -591,18 +592,18 @@ EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @dentry: dentry to check permissions on * @mode: the new mode of @inode * - * If the dentry has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the dentry has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. */ int - posix_acl_chmod(struct user_namespace *mnt_userns, struct dentry *dentry, + posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { struct inode *inode = d_inode(dentry); @@ -624,7 +625,7 @@ int ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; - ret = inode->i_op->set_acl(mnt_userns, dentry, acl, ACL_TYPE_ACCESS); + ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } @@ -683,7 +684,7 @@ EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl - * @mnt_userns: user namespace of the mount @inode was found from + * @idmap: idmap of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer @@ -695,15 +696,15 @@ EXPORT_SYMBOL_GPL(posix_acl_create); * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. * * Called from set_acl inode operations. */ -int posix_acl_update_mode(struct user_namespace *mnt_userns, +int posix_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { @@ -715,8 +716,8 @@ int posix_acl_update_mode(struct user_namespace *mnt_userns, return error; if (error == 0) *acl = NULL; - if (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) && - !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) + if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) && + !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) mode &= ~S_ISGID; *mode_p = mode; return 0; @@ -893,7 +894,6 @@ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; struct user_namespace *fs_userns, *caller_userns; - struct user_namespace *mnt_userns; ssize_t real_size, n; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -909,19 +909,18 @@ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, fs_userns = i_user_ns(inode); caller_userns = current_user_ns(); - mnt_userns = mnt_idmap_owner(idmap); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, fs_userns, acl_e->e_uid); + vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid); ext_entry->e_id = cpu_to_le32(from_kuid( caller_userns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, fs_userns, acl_e->e_gid); + vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid); ext_entry->e_id = cpu_to_le32(from_kgid( caller_userns, vfsgid_into_kgid(vfsgid))); break; @@ -934,7 +933,7 @@ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, } int -set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type, struct posix_acl *acl) { struct inode *inode = d_inode(dentry); @@ -946,7 +945,7 @@ set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry, if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (acl) { @@ -954,7 +953,7 @@ set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry, if (ret) return ret; } - return inode->i_op->set_acl(mnt_userns, dentry, acl, type); + return inode->i_op->set_acl(idmap, dentry, acl, type); } EXPORT_SYMBOL(set_posix_acl); @@ -978,14 +977,14 @@ const struct xattr_handler posix_acl_default_xattr_handler = { }; EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler); -int simple_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; struct inode *inode = d_inode(dentry); if (type == ACL_TYPE_ACCESS) { - error = posix_acl_update_mode(mnt_userns, inode, + error = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (error) return error; @@ -1017,7 +1016,7 @@ int simple_acl_create(struct inode *dir, struct inode *inode) return 0; } -static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns, +static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap, struct user_namespace *fs_userns, struct posix_acl *acl) { @@ -1026,11 +1025,11 @@ static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns, switch (acl_e->e_tag) { case ACL_USER: - acl_e->e_uid = from_vfsuid(mnt_userns, fs_userns, + acl_e->e_uid = from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(acl_e->e_uid)); break; case ACL_GROUP: - acl_e->e_gid = from_vfsgid(mnt_userns, fs_userns, + acl_e->e_gid = from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(acl_e->e_gid)); break; } @@ -1041,7 +1040,7 @@ static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns, /** * vfs_set_acl - set posix acls - * @mnt_userns: user namespace of the mount + * @idmap: idmap of the mount * @dentry: the dentry based on which to set the posix acls * @acl_name: the name of the posix acl * @kacl: the posix acls in the appropriate VFS format @@ -1051,7 +1050,7 @@ static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns, * * Return: On success 0, on error negative errno. */ -int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { int acl_type; @@ -1071,7 +1070,7 @@ int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, * if this is a filesystem with a backing store - ultimately * translate them to backing store values. */ - error = vfs_set_acl_idmapped_mnt(mnt_userns, i_user_ns(inode), kacl); + error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl); if (error) return error; } @@ -1083,11 +1082,11 @@ retry_deleg: * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ - error = may_write_xattr(mnt_userns, inode); + error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; - error = security_inode_set_acl(mnt_userns, dentry, acl_name, kacl); + error = security_inode_set_acl(idmap, dentry, acl_name, kacl); if (error) goto out_inode_unlock; @@ -1096,7 +1095,7 @@ retry_deleg: goto out_inode_unlock; if (inode->i_opflags & IOP_XATTR) - error = set_posix_acl(mnt_userns, dentry, acl_type, kacl); + error = set_posix_acl(idmap, dentry, acl_type, kacl); else if (unlikely(is_bad_inode(inode))) error = -EIO; else @@ -1121,7 +1120,7 @@ EXPORT_SYMBOL_GPL(vfs_set_acl); /** * vfs_get_acl - get posix acls - * @mnt_userns: user namespace of the mount + * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * @@ -1130,7 +1129,7 @@ EXPORT_SYMBOL_GPL(vfs_set_acl); * * Return: On success POSIX ACLs in VFS format, on error negative errno. */ -struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct inode *inode = d_inode(dentry); @@ -1145,7 +1144,7 @@ struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, * The VFS has no restrictions on reading POSIX ACLs so calling * something like xattr_permission() isn't needed. Only LSMs get a say. */ - error = security_inode_get_acl(mnt_userns, dentry, acl_name); + error = security_inode_get_acl(idmap, dentry, acl_name); if (error) return ERR_PTR(error); @@ -1154,7 +1153,7 @@ struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, if (S_ISLNK(inode->i_mode)) return ERR_PTR(-EOPNOTSUPP); - acl = __get_acl(mnt_userns, dentry, inode, acl_type); + acl = __get_acl(idmap, dentry, inode, acl_type); if (IS_ERR(acl)) return acl; if (!acl) @@ -1166,7 +1165,7 @@ EXPORT_SYMBOL_GPL(vfs_get_acl); /** * vfs_remove_acl - remove posix acls - * @mnt_userns: user namespace of the mount + * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * @@ -1174,7 +1173,7 @@ EXPORT_SYMBOL_GPL(vfs_get_acl); * * Return: On success 0, on error negative errno. */ -int vfs_remove_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int acl_type; @@ -1193,11 +1192,11 @@ retry_deleg: * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ - error = may_write_xattr(mnt_userns, inode); + error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; - error = security_inode_remove_acl(mnt_userns, dentry, acl_name); + error = security_inode_remove_acl(idmap, dentry, acl_name); if (error) goto out_inode_unlock; @@ -1206,14 +1205,14 @@ retry_deleg: goto out_inode_unlock; if (inode->i_opflags & IOP_XATTR) - error = set_posix_acl(mnt_userns, dentry, acl_type, NULL); + error = set_posix_acl(idmap, dentry, acl_type, NULL); else if (unlikely(is_bad_inode(inode))) error = -EIO; else error = -EOPNOTSUPP; if (!error) { fsnotify_xattr(dentry); - evm_inode_post_remove_acl(mnt_userns, dentry, acl_name); + evm_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: @@ -1245,7 +1244,7 @@ int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, return PTR_ERR(acl); } - error = vfs_set_acl(mnt_idmap_owner(idmap), dentry, acl_name, acl); + error = vfs_set_acl(idmap, dentry, acl_name, acl); posix_acl_release(acl); return error; } @@ -1256,7 +1255,7 @@ ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, ssize_t error; struct posix_acl *acl; - acl = vfs_get_acl(mnt_idmap_owner(idmap), dentry, acl_name); + acl = vfs_get_acl(idmap, dentry, acl_name); if (IS_ERR(acl)) return PTR_ERR(acl); diff --git a/fs/proc/base.c b/fs/proc/base.c index 9e479d7d202b..5e0e0ccd47aa 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -685,7 +685,7 @@ static bool proc_fd_access_allowed(struct inode *inode) return allowed; } -int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; @@ -694,11 +694,11 @@ int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (attr->ia_valid & ATTR_MODE) return -EPERM; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -727,7 +727,7 @@ static bool has_pid_permissions(struct proc_fs_info *fs_info, } -static int proc_pid_permission(struct user_namespace *mnt_userns, +static int proc_pid_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); @@ -753,7 +753,7 @@ static int proc_pid_permission(struct user_namespace *mnt_userns, return -EPERM; } - return generic_permission(&init_user_ns, inode, mask); + return generic_permission(&nop_mnt_idmap, inode, mask); } @@ -1959,14 +1959,14 @@ static struct inode *proc_pid_make_base_inode(struct super_block *sb, return inode; } -int pid_getattr(struct user_namespace *mnt_userns, const struct path *path, +int pid_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; @@ -3557,7 +3557,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) * This function makes sure that the node is always accessible for members of * same thread group. */ -static int proc_tid_comm_permission(struct user_namespace *mnt_userns, +static int proc_tid_comm_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { bool is_same_tgroup; @@ -3577,7 +3577,7 @@ static int proc_tid_comm_permission(struct user_namespace *mnt_userns, return 0; } - return generic_permission(&init_user_ns, inode, mask); + return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { @@ -3891,13 +3891,13 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) return 0; } -static int proc_task_getattr(struct user_namespace *mnt_userns, +static int proc_task_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct task_struct *p = get_proc_task(inode); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (p) { stat->nlink += get_nr_threads(p); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index fc46d6fe080c..b3140deebbbf 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -12,6 +12,7 @@ #include <linux/file.h> #include <linux/seq_file.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/proc_fs.h> @@ -325,13 +326,13 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, * /proc/pid/fd needs a special permission handler so that a process can still * access /proc/self/fd after it has executed a setuid(). */ -int proc_fd_permission(struct user_namespace *mnt_userns, +int proc_fd_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct task_struct *p; int rv; - rv = generic_permission(&init_user_ns, inode, mask); + rv = generic_permission(&nop_mnt_idmap, inode, mask); if (rv == 0) return rv; @@ -344,14 +345,14 @@ int proc_fd_permission(struct user_namespace *mnt_userns, return rv; } -static int proc_fd_getattr(struct user_namespace *mnt_userns, +static int proc_fd_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); int rv = 0; - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); /* If it's a directory, put the number of open fds there */ if (S_ISDIR(inode->i_mode)) { diff --git a/fs/proc/fd.h b/fs/proc/fd.h index c5a921a06a0b..7e7265f7e06f 100644 --- a/fs/proc/fd.h +++ b/fs/proc/fd.h @@ -10,7 +10,7 @@ extern const struct inode_operations proc_fd_inode_operations; extern const struct file_operations proc_fdinfo_operations; extern const struct inode_operations proc_fdinfo_inode_operations; -extern int proc_fd_permission(struct user_namespace *mnt_userns, +extern int proc_fd_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); static inline unsigned int proc_fd(struct inode *inode) diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 587b91d9d998..8379593fa4bb 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -115,18 +115,18 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, return true; } -static int proc_notify_change(struct user_namespace *mnt_userns, +static int proc_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct proc_dir_entry *de = PDE(inode); int error; - error = setattr_prepare(&init_user_ns, dentry, iattr); + error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) return error; - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); mark_inode_dirty(inode); proc_set_user(de, inode->i_uid, inode->i_gid); @@ -134,7 +134,7 @@ static int proc_notify_change(struct user_namespace *mnt_userns, return 0; } -static int proc_getattr(struct user_namespace *mnt_userns, +static int proc_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -147,7 +147,7 @@ static int proc_getattr(struct user_namespace *mnt_userns, } } - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index b701d0207edf..9dda7e54b2d0 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -162,9 +162,9 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, * base.c */ extern const struct dentry_operations pid_dentry_operations; -extern int pid_getattr(struct user_namespace *, const struct path *, +extern int pid_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); -extern int proc_setattr(struct user_namespace *, struct dentry *, +extern int proc_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void proc_pid_evict_inode(struct proc_inode *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 856839b8ae8b..a0c0419872e3 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -299,7 +299,7 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir, return de; } -static int proc_tgid_net_getattr(struct user_namespace *mnt_userns, +static int proc_tgid_net_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -308,7 +308,7 @@ static int proc_tgid_net_getattr(struct user_namespace *mnt_userns, net = get_proc_task_net(inode); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (net != NULL) { stat->nlink = net->proc_net->nlink; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 48f2d60bd78a..e89bd8f1368b 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -798,7 +798,7 @@ out: return 0; } -static int proc_sys_permission(struct user_namespace *mnt_userns, +static int proc_sys_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { /* @@ -827,7 +827,7 @@ static int proc_sys_permission(struct user_namespace *mnt_userns, return error; } -static int proc_sys_setattr(struct user_namespace *mnt_userns, +static int proc_sys_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -836,16 +836,16 @@ static int proc_sys_setattr(struct user_namespace *mnt_userns, if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } -static int proc_sys_getattr(struct user_namespace *mnt_userns, +static int proc_sys_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -856,7 +856,7 @@ static int proc_sys_getattr(struct user_namespace *mnt_userns, if (IS_ERR(head)) return PTR_ERR(head); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (table) stat->mode = (stat->mode & S_IFMT) | table->mode; diff --git a/fs/proc/root.c b/fs/proc/root.c index 3c2ee3eb1138..a86e65a608da 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -310,11 +310,11 @@ void __init proc_root_init(void) register_filesystem(&proc_fs_type); } -static int proc_root_getattr(struct user_namespace *mnt_userns, +static int proc_root_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(path->dentry), stat); stat->nlink = proc_root.nlink + nr_processes(); return 0; } diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f27faf5db554..a6357f728034 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2085,7 +2085,7 @@ EXPORT_SYMBOL(__dquot_transfer); /* Wrapper for transferring ownership of an inode for uid/gid only * Called from FSXXX_setattr() */ -int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, +int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr) { struct dquot *transfer_to[MAXQUOTAS] = {}; @@ -2096,8 +2096,8 @@ int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, if (!dquot_active(inode)) return 0; - if (i_uid_needs_update(mnt_userns, iattr, inode)) { - kuid_t kuid = from_vfsuid(mnt_userns, i_user_ns(inode), + if (i_uid_needs_update(idmap, iattr, inode)) { + kuid_t kuid = from_vfsuid(idmap, i_user_ns(inode), iattr->ia_vfsuid); dquot = dqget(sb, make_kqid_uid(kuid)); @@ -2110,8 +2110,8 @@ int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, } transfer_to[USRQUOTA] = dquot; } - if (i_gid_needs_update(mnt_userns, iattr, inode)) { - kgid_t kgid = from_vfsgid(mnt_userns, i_user_ns(inode), + if (i_gid_needs_update(idmap, iattr, inode)) { + kgid_t kgid = from_vfsgid(idmap, i_user_ns(inode), iattr->ia_vfsgid); dquot = dqget(sb, make_kqid_gid(kgid)); diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index cb240eac5036..5bf74c2f6042 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -22,7 +22,7 @@ #include <linux/uaccess.h> #include "internal.h" -static int ramfs_nommu_setattr(struct user_namespace *, struct dentry *, struct iattr *); +static int ramfs_nommu_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, @@ -158,7 +158,7 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size) * handle a change of attributes * - we're specifically interested in a change of size */ -static int ramfs_nommu_setattr(struct user_namespace *mnt_userns, +static int ramfs_nommu_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { struct inode *inode = d_inode(dentry); @@ -166,7 +166,7 @@ static int ramfs_nommu_setattr(struct user_namespace *mnt_userns, int ret = 0; /* POSIX UID/GID verification for setting inode attributes */ - ret = setattr_prepare(&init_user_ns, dentry, ia); + ret = setattr_prepare(&nop_mnt_idmap, dentry, ia); if (ret) return ret; @@ -186,7 +186,7 @@ static int ramfs_nommu_setattr(struct user_namespace *mnt_userns, } } - setattr_copy(&init_user_ns, inode, ia); + setattr_copy(&nop_mnt_idmap, inode, ia); out: ia->ia_valid = old_ia_valid; return ret; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index b3257e852820..5ba580c78835 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -61,7 +61,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, if (inode) { inode->i_ino = get_next_ino(); - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_mapping->a_ops = &ram_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); @@ -95,7 +95,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, */ /* SMP-safe */ static int -ramfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +ramfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev); @@ -110,22 +110,22 @@ ramfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, return error; } -static int ramfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - int retval = ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0); + int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } -static int ramfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); + return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); } -static int ramfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int ramfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode; @@ -145,7 +145,7 @@ static int ramfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, return error; } -static int ramfs_tmpfile(struct user_namespace *mnt_userns, +static int ramfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; diff --git a/fs/reiserfs/acl.h b/fs/reiserfs/acl.h index 29c503a06db4..2571b1a8be84 100644 --- a/fs/reiserfs/acl.h +++ b/fs/reiserfs/acl.h @@ -49,7 +49,7 @@ static inline int reiserfs_acl_count(size_t size) #ifdef CONFIG_REISERFS_FS_POSIX_ACL struct posix_acl *reiserfs_get_acl(struct inode *inode, int type, bool rcu); -int reiserfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int reiserfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int reiserfs_acl_chmod(struct dentry *dentry); int reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index c7d1fa526dea..d54cab854f60 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3262,21 +3262,21 @@ static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return ret; } -int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int reiserfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid; int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; /* must be turned off for recursive notify_change calls */ ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID); - if (is_quota_modification(mnt_userns, inode, attr)) { + if (is_quota_modification(&nop_mnt_idmap, inode, attr)) { error = dquot_initialize(inode); if (error) return error; @@ -3359,7 +3359,7 @@ int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, reiserfs_write_unlock(inode->i_sb); if (error) goto out; - error = dquot_transfer(mnt_userns, inode, attr); + error = dquot_transfer(&nop_mnt_idmap, inode, attr); reiserfs_write_lock(inode->i_sb); if (error) { journal_end(&th); @@ -3398,7 +3398,7 @@ int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } if (!error) { - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); } diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 4b86ecf5817e..6bf9b54e58ca 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -24,7 +24,7 @@ int reiserfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int reiserfs_fileattr_set(struct user_namespace *mnt_userns, +int reiserfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -96,7 +96,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) err = put_user(inode->i_generation, (int __user *)arg); break; case REISERFS_IOC_SETVERSION: - if (!inode_owner_or_capable(&init_user_ns, inode)) { + if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) { err = -EPERM; break; } diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 0b8aa99749f1..42d2c20e1345 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -616,11 +616,11 @@ static int new_inode_init(struct inode *inode, struct inode *dir, umode_t mode) * the quota init calls have to know who to charge the quota to, so * we have to set uid and gid here */ - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); return dquot_initialize(inode); } -static int reiserfs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int reiserfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { int retval; @@ -700,7 +700,7 @@ out_failed: return retval; } -static int reiserfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int reiserfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { int retval; @@ -784,7 +784,7 @@ out_failed: return retval; } -static int reiserfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int reiserfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int retval; @@ -1099,7 +1099,7 @@ out_unlink: return retval; } -static int reiserfs_symlink(struct user_namespace *mnt_userns, +static int reiserfs_symlink(struct mnt_idmap *idmap, struct inode *parent_dir, struct dentry *dentry, const char *symname) { @@ -1311,7 +1311,7 @@ static void set_ino_in_dir_entry(struct reiserfs_dir_entry *de, * one path. If it holds 2 or more, it can get into endless waiting in * get_empty_nodes or its clones */ -static int reiserfs_rename(struct user_namespace *mnt_userns, +static int reiserfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 3aa928ec527a..98e6f53c2fe0 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -3100,7 +3100,7 @@ static inline void reiserfs_update_sd(struct reiserfs_transaction_handle *th, } void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode); -int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int reiserfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len); @@ -3407,7 +3407,7 @@ __u32 r5_hash(const signed char *msg, int len); /* prototypes from ioctl.c */ int reiserfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int reiserfs_fileattr_set(struct user_namespace *mnt_userns, +int reiserfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long reiserfs_compat_ioctl(struct file *filp, diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 8b2d52443f41..06d810c72c52 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -66,14 +66,14 @@ static int xattr_create(struct inode *dir, struct dentry *dentry, int mode) { BUG_ON(!inode_is_locked(dir)); - return dir->i_op->create(&init_user_ns, dir, dentry, mode, true); + return dir->i_op->create(&nop_mnt_idmap, dir, dentry, mode, true); } #endif static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { BUG_ON(!inode_is_locked(dir)); - return dir->i_op->mkdir(&init_user_ns, dir, dentry, mode); + return dir->i_op->mkdir(&nop_mnt_idmap, dir, dentry, mode); } /* @@ -352,7 +352,7 @@ static int chown_one_xattr(struct dentry *dentry, void *data) * ATTR_MODE is set. */ attrs->ia_valid &= (ATTR_UID|ATTR_GID); - err = reiserfs_setattr(&init_user_ns, dentry, attrs); + err = reiserfs_setattr(&nop_mnt_idmap, dentry, attrs); attrs->ia_valid = ia_valid; return err; @@ -597,7 +597,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, inode_lock_nested(d_inode(dentry), I_MUTEX_XATTR); inode_dio_wait(d_inode(dentry)); - err = reiserfs_setattr(&init_user_ns, dentry, &newattrs); + err = reiserfs_setattr(&nop_mnt_idmap, dentry, &newattrs); inode_unlock(d_inode(dentry)); } else update_ctime(inode); @@ -941,7 +941,7 @@ static int xattr_mount_check(struct super_block *s) return 0; } -int reiserfs_permission(struct user_namespace *mnt_userns, struct inode *inode, +int reiserfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { /* @@ -951,7 +951,7 @@ int reiserfs_permission(struct user_namespace *mnt_userns, struct inode *inode, if (IS_PRIVATE(inode)) return 0; - return generic_permission(&init_user_ns, inode, mask); + return generic_permission(&nop_mnt_idmap, inode, mask); } static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags) diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index e47fde1182de..5868a4e990e3 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -16,7 +16,7 @@ int reiserfs_xattr_init(struct super_block *sb, int mount_flags); int reiserfs_lookup_privroot(struct super_block *sb); int reiserfs_delete_xattrs(struct inode *inode); int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); -int reiserfs_permission(struct user_namespace *mnt_userns, +int reiserfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); #ifdef CONFIG_REISERFS_FS_XATTR diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 93fe414fed18..138060452678 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -18,7 +18,7 @@ static int __reiserfs_set_acl(struct reiserfs_transaction_handle *th, int -reiserfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +reiserfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error, error2; @@ -42,7 +42,7 @@ reiserfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, reiserfs_write_unlock(inode->i_sb); if (error == 0) { if (type == ACL_TYPE_ACCESS && acl) { - error = posix_acl_update_mode(&init_user_ns, inode, + error = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (error) goto unlock; @@ -407,5 +407,5 @@ int reiserfs_acl_chmod(struct dentry *dentry) !reiserfs_posixacl(inode->i_sb)) return 0; - return posix_acl_chmod(&init_user_ns, dentry, inode->i_mode); + return posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); } diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 857a65b05726..41c0ea84fbff 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -22,7 +22,7 @@ security_get(const struct xattr_handler *handler, struct dentry *unused, static int security_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, struct dentry *unused, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index d853cea2afcd..0c0c74d8db0e 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -21,7 +21,7 @@ trusted_get(const struct xattr_handler *handler, struct dentry *unused, static int trusted_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, struct dentry *unused, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index 65d9cd10a5ea..88195181e1d7 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -18,7 +18,7 @@ user_get(const struct xattr_handler *handler, struct dentry *unused, } static int -user_set(const struct xattr_handler *handler, struct user_namespace *mnt_userns, +user_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/remap_range.c b/fs/remap_range.c index 41f60477bb41..1331a890f2f2 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -419,16 +419,16 @@ EXPORT_SYMBOL(vfs_clone_file_range); /* Check whether we are allowed to dedupe the destination file */ static bool allow_file_dedupe(struct file *file) { - struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); if (capable(CAP_SYS_ADMIN)) return true; if (file->f_mode & FMODE_WRITE) return true; - if (vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode), current_fsuid())) + if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) return true; - if (!inode_permission(mnt_userns, inode, MAY_WRITE)) + if (!inode_permission(idmap, inode, MAY_WRITE)) return true; return false; } diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index b88d19e9581e..c8469c656e0d 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, /* Sanity check values */ /* there is always at least one xattr id */ - if (*xattr_ids <= 0) + if (*xattr_ids == 0) return ERR_PTR(-EINVAL); len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); diff --git a/fs/stat.c b/fs/stat.c index d6cc74ca8486..7c238da22ef0 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -18,6 +18,7 @@ #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/compat.h> +#include <linux/iversion.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -27,7 +28,7 @@ /** * generic_fillattr - Fill in the basic attributes from the inode struct - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: Inode to use as the source * @stat: Where to fill in the attributes * @@ -35,17 +36,17 @@ * found on the VFS inode structure. This is the default if no getattr inode * operation is supplied. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before filling in the + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before filling in the * uid and gid filds. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. */ -void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode, +void generic_fillattr(struct mnt_idmap *idmap, struct inode *inode, struct kstat *stat) { - vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); - vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); stat->dev = inode->i_sb->s_dev; stat->ino = inode->i_ino; @@ -97,7 +98,7 @@ EXPORT_SYMBOL(generic_fill_statx_attr); int vfs_getattr_nosec(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; struct inode *inode = d_backing_inode(path->dentry); memset(stat, 0, sizeof(*stat)); @@ -122,12 +123,17 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | STATX_ATTR_DAX); - mnt_userns = mnt_user_ns(path->mnt); + if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { + stat->result_mask |= STATX_CHANGE_COOKIE; + stat->change_cookie = inode_query_iversion(inode); + } + + idmap = mnt_idmap(path->mnt); if (inode->i_op->getattr) - return inode->i_op->getattr(mnt_userns, path, stat, + return inode->i_op->getattr(idmap, path, stat, request_mask, query_flags); - generic_fillattr(mnt_userns, inode, stat); + generic_fillattr(idmap, inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); @@ -602,9 +608,11 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) memset(&tmp, 0, sizeof(tmp)); - tmp.stx_mask = stat->result_mask; + /* STATX_CHANGE_COOKIE is kernel-only for now */ + tmp.stx_mask = stat->result_mask & ~STATX_CHANGE_COOKIE; tmp.stx_blksize = stat->blksize; - tmp.stx_attributes = stat->attributes; + /* STATX_ATTR_CHANGE_MONOTONIC is kernel-only for now */ + tmp.stx_attributes = stat->attributes & ~STATX_ATTR_CHANGE_MONOTONIC; tmp.stx_nlink = stat->nlink; tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); @@ -643,6 +651,11 @@ int do_statx(int dfd, struct filename *filename, unsigned int flags, if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; + /* STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests + * from userland. + */ + mask &= ~STATX_CHANGE_COOKIE; + error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; diff --git a/fs/super.c b/fs/super.c index 12c08cb20405..8e531174e7c2 100644 --- a/fs/super.c +++ b/fs/super.c @@ -291,7 +291,6 @@ static void __put_super(struct super_block *s) WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); security_sb_free(s); - fscrypt_destroy_keyring(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); call_rcu(&s->rcu, destroy_super_rcu); @@ -491,10 +490,23 @@ void generic_shutdown_super(struct super_block *sb) if (sop->put_super) sop->put_super(sb); - if (!list_empty(&sb->s_inodes)) { - printk("VFS: Busy inodes after unmount of %s. " - "Self-destruct in 5 seconds. Have a nice day...\n", - sb->s_id); + if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), + "VFS: Busy inodes after unmount of %s (%s)", + sb->s_id, sb->s_type->name)) { + /* + * Adding a proper bailout path here would be hard, but + * we can at least make it more likely that a later + * iput_final() or such crashes cleanly. + */ + struct inode *inode; + + spin_lock(&sb->s_inode_list_lock); + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + inode->i_op = VFS_PTR_POISON; + inode->i_sb = VFS_PTR_POISON; + inode->i_mapping = VFS_PTR_POISON; + } + spin_unlock(&sb->s_inode_list_lock); } } spin_lock(&sb_lock); diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 90e00124ea07..50eb92557a0f 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -29,13 +29,13 @@ const struct file_operations sysv_file_operations = { .splice_read = generic_file_splice_read, }; -static int sysv_setattr(struct user_namespace *mnt_userns, +static int sysv_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -48,7 +48,7 @@ static int sysv_setattr(struct user_namespace *mnt_userns, sysv_truncate(inode); } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 50df794a3c1f..e732879036ab 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -163,7 +163,7 @@ struct inode * sysv_new_inode(const struct inode * dir, umode_t mode) *sbi->s_sb_fic_count = cpu_to_fs16(sbi, count); fs16_add(sbi, sbi->s_sb_total_free_inodes, -1); dirty_sb(sb); - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = fs16_to_cpu(sbi, ino); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_blocks = 0; diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 3b8567564e7e..b22764fe669c 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -441,11 +441,11 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size) return res; } -int sysv_getattr(struct user_namespace *mnt_userns, const struct path *path, +int sysv_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct super_block *s = path->dentry->d_sb; - generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); + generic_fillattr(&nop_mnt_idmap, d_inode(path->dentry), stat); stat->blocks = (s->s_blocksize / 512) * sysv_nblocks(s, stat->size); stat->blksize = s->s_blocksize; return 0; diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index b2e6abc06a2d..ecd424461511 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -41,7 +41,7 @@ static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, un return d_splice_alias(inode, dentry); } -static int sysv_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int sysv_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode * inode; @@ -61,13 +61,13 @@ static int sysv_mknod(struct user_namespace *mnt_userns, struct inode *dir, return err; } -static int sysv_create(struct user_namespace *mnt_userns, struct inode *dir, +static int sysv_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return sysv_mknod(&init_user_ns, dir, dentry, mode, 0); + return sysv_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); } -static int sysv_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int sysv_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int err = -ENAMETOOLONG; @@ -110,7 +110,7 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir, return add_nondir(dentry, inode); } -static int sysv_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int sysv_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode * inode; @@ -189,7 +189,7 @@ static int sysv_rmdir(struct inode * dir, struct dentry * dentry) * Anybody can rename anything with this: the permission checks are left to the * higher-level routines. */ -static int sysv_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index 99ddf033da4f..5e122a5673c1 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -141,7 +141,7 @@ extern struct inode *sysv_iget(struct super_block *, unsigned int); extern int sysv_write_inode(struct inode *, struct writeback_control *wbc); extern int sysv_sync_inode(struct inode *); extern void sysv_set_inode(struct inode *, dev_t); -extern int sysv_getattr(struct user_namespace *, const struct path *, +extern int sysv_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int sysv_init_icache(void); extern void sysv_destroy_icache(void); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index da85b3979195..57ac8aa4a724 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -67,7 +67,7 @@ static char *get_dname(struct dentry *dentry) return name; } -static int tracefs_syscall_mkdir(struct user_namespace *mnt_userns, +static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, struct inode *inode, struct dentry *dentry, umode_t mode) { diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 0f29cf201136..1e92c1730c16 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -95,7 +95,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, */ inode->i_flags |= S_NOCMTIME; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mapping->nrpages = 0; @@ -283,7 +283,7 @@ static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry, return fscrypt_setup_filename(dir, &dentry->d_name, 0, nm); } -static int ubifs_create(struct user_namespace *mnt_userns, struct inode *dir, +static int ubifs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; @@ -426,7 +426,7 @@ static void unlock_2_inodes(struct inode *inode1, struct inode *inode2) mutex_unlock(&ubifs_inode(inode1)->ui_mutex); } -static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int ubifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct dentry *dentry = file->f_path.dentry; @@ -979,7 +979,7 @@ out_fname: return err; } -static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -1052,7 +1052,7 @@ out_budg: return err; } -static int ubifs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; @@ -1141,7 +1141,7 @@ out_budg: return err; } -static int ubifs_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int ubifs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode; @@ -1606,7 +1606,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, return err; } -static int ubifs_rename(struct user_namespace *mnt_userns, +static int ubifs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -1631,7 +1631,7 @@ static int ubifs_rename(struct user_namespace *mnt_userns, return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } -int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, +int ubifs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { loff_t size; @@ -1654,7 +1654,7 @@ int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); stat->blksize = UBIFS_BLOCK_SIZE; stat->size = ui->ui_size; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index f2353dd676ef..8cb5d76b301c 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1258,7 +1258,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode, return err; } -int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ubifs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int err; @@ -1267,7 +1267,7 @@ int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, dbg_gen("ino %lu, mode %#x, ia_valid %#x", inode->i_ino, inode->i_mode, attr->ia_valid); - err = setattr_prepare(&init_user_ns, dentry, attr); + err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err) return err; @@ -1608,11 +1608,11 @@ static const char *ubifs_get_link(struct dentry *dentry, return fscrypt_get_symlink(inode, ui->data, ui->data_len, done); } -static int ubifs_symlink_getattr(struct user_namespace *mnt_userns, +static int ubifs_symlink_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - ubifs_getattr(mnt_userns, path, stat, request_mask, query_flags); + ubifs_getattr(idmap, path, stat, request_mask, query_flags); if (IS_ENCRYPTED(d_inode(path->dentry))) return fscrypt_symlink_getattr(path, stat); diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 71bcebe45f9c..67c5108abd89 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -144,7 +144,7 @@ int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -int ubifs_fileattr_set(struct user_namespace *mnt_userns, +int ubifs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 478bbbb5382f..9063b73536f8 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -2020,15 +2020,15 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc); /* file.c */ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync); -int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ubifs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags); /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, umode_t mode, bool is_xattr); -int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags); +int ubifs_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags); int ubifs_check_dir_empty(struct inode *dir); /* xattr.c */ @@ -2085,7 +2085,7 @@ void ubifs_destroy_size_tree(struct ubifs_info *c); /* ioctl.c */ int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int ubifs_fileattr_set(struct user_namespace *mnt_userns, +int ubifs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); void ubifs_set_inode_flags(struct inode *inode); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 3db8486e3725..349228dd1191 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -699,7 +699,7 @@ static int xattr_get(const struct xattr_handler *handler, } static int xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index 8e597db4d971..14b9db4c80f0 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -36,18 +36,41 @@ static int read_block_bitmap(struct super_block *sb, unsigned long bitmap_nr) { struct buffer_head *bh = NULL; - int retval = 0; + int i; + int max_bits, off, count; struct kernel_lb_addr loc; loc.logicalBlockNum = bitmap->s_extPosition; loc.partitionReferenceNum = UDF_SB(sb)->s_partition; - bh = udf_tread(sb, udf_get_lb_pblock(sb, &loc, block)); + bh = sb_bread(sb, udf_get_lb_pblock(sb, &loc, block)); + bitmap->s_block_bitmap[bitmap_nr] = bh; if (!bh) - retval = -EIO; + return -EIO; - bitmap->s_block_bitmap[bitmap_nr] = bh; - return retval; + /* Check consistency of Space Bitmap buffer. */ + max_bits = sb->s_blocksize * 8; + if (!bitmap_nr) { + off = sizeof(struct spaceBitmapDesc) << 3; + count = min(max_bits - off, bitmap->s_nr_groups); + } else { + /* + * Rough check if bitmap number is too big to have any bitmap + * blocks reserved. + */ + if (bitmap_nr > + (bitmap->s_nr_groups >> (sb->s_blocksize_bits + 3)) + 2) + return 0; + off = 0; + count = bitmap->s_nr_groups - bitmap_nr * max_bits + + (sizeof(struct spaceBitmapDesc) << 3); + count = min(count, max_bits); + } + + for (i = 0; i < count; i++) + if (udf_test_bit(i + off, bh->b_data)) + return -EFSCORRUPTED; + return 0; } static int __load_block_bitmap(struct super_block *sb, diff --git a/fs/udf/dir.c b/fs/udf/dir.c index be640f4b2f2c..212393b12c22 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -39,26 +39,13 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) { struct inode *dir = file_inode(file); - struct udf_inode_info *iinfo = UDF_I(dir); - struct udf_fileident_bh fibh = { .sbh = NULL, .ebh = NULL}; - struct fileIdentDesc *fi = NULL; - struct fileIdentDesc cfi; - udf_pblk_t block, iblock; loff_t nf_pos, emit_pos = 0; int flen; - unsigned char *fname = NULL, *copy_name = NULL; - unsigned char *nameptr; - uint16_t liu; - uint8_t lfi; - loff_t size = udf_ext0_offset(dir) + dir->i_size; - struct buffer_head *tmp, *bha[16]; - struct kernel_lb_addr eloc; - uint32_t elen; - sector_t offset; - int i, num, ret = 0; - struct extent_position epos = { NULL, 0, {0, 0} }; + unsigned char *fname = NULL; + int ret = 0; struct super_block *sb = dir->i_sb; bool pos_valid = false; + struct udf_fileident_iter iter; if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) @@ -66,7 +53,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) ctx->pos = 1; } nf_pos = (ctx->pos - 1) << 2; - if (nf_pos >= size) + if (nf_pos >= dir->i_size) goto out; /* @@ -90,138 +77,57 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) goto out; } - if (nf_pos == 0) - nf_pos = udf_ext0_offset(dir); - - fibh.soffset = fibh.eoffset = nf_pos & (sb->s_blocksize - 1); - if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - if (inode_bmap(dir, nf_pos >> sb->s_blocksize_bits, - &epos, &eloc, &elen, &offset) - != (EXT_RECORDED_ALLOCATED >> 30)) { - ret = -ENOENT; - goto out; - } - block = udf_get_lb_pblock(sb, &eloc, offset); - if ((++offset << sb->s_blocksize_bits) < elen) { - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - epos.offset -= sizeof(struct short_ad); - else if (iinfo->i_alloc_type == - ICBTAG_FLAG_AD_LONG) - epos.offset -= sizeof(struct long_ad); - } else { - offset = 0; - } - - if (!(fibh.sbh = fibh.ebh = udf_tread(sb, block))) { - ret = -EIO; - goto out; - } - - if (!(offset & ((16 >> (sb->s_blocksize_bits - 9)) - 1))) { - i = 16 >> (sb->s_blocksize_bits - 9); - if (i + offset > (elen >> sb->s_blocksize_bits)) - i = (elen >> sb->s_blocksize_bits) - offset; - for (num = 0; i > 0; i--) { - block = udf_get_lb_pblock(sb, &eloc, offset + i); - tmp = udf_tgetblk(sb, block); - if (tmp && !buffer_uptodate(tmp) && !buffer_locked(tmp)) - bha[num++] = tmp; - else - brelse(tmp); - } - if (num) { - bh_readahead_batch(num, bha, REQ_RAHEAD); - for (i = 0; i < num; i++) - brelse(bha[i]); - } - } - } - - while (nf_pos < size) { + for (ret = udf_fiiter_init(&iter, dir, nf_pos); + !ret && iter.pos < dir->i_size; + ret = udf_fiiter_advance(&iter)) { struct kernel_lb_addr tloc; - loff_t cur_pos = nf_pos; + udf_pblk_t iblock; - /* Update file position only if we got past the current one */ - if (nf_pos >= emit_pos) { - ctx->pos = (nf_pos >> 2) + 1; - pos_valid = true; - } - - fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc, - &elen, &offset); - if (!fi) - goto out; /* Still not at offset where user asked us to read from? */ - if (cur_pos < emit_pos) + if (iter.pos < emit_pos) continue; - liu = le16_to_cpu(cfi.lengthOfImpUse); - lfi = cfi.lengthFileIdent; - - if (fibh.sbh == fibh.ebh) { - nameptr = udf_get_fi_ident(fi); - } else { - int poffset; /* Unpaded ending offset */ - - poffset = fibh.soffset + sizeof(struct fileIdentDesc) + liu + lfi; - - if (poffset >= lfi) { - nameptr = (char *)(fibh.ebh->b_data + poffset - lfi); - } else { - if (!copy_name) { - copy_name = kmalloc(UDF_NAME_LEN, - GFP_NOFS); - if (!copy_name) { - ret = -ENOMEM; - goto out; - } - } - nameptr = copy_name; - memcpy(nameptr, udf_get_fi_ident(fi), - lfi - poffset); - memcpy(nameptr + lfi - poffset, - fibh.ebh->b_data, poffset); - } - } + /* Update file position only if we got past the current one */ + pos_valid = true; + ctx->pos = (iter.pos >> 2) + 1; - if ((cfi.fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) { + if (iter.fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) continue; } - if ((cfi.fileCharacteristics & FID_FILE_CHAR_HIDDEN) != 0) { + if (iter.fi.fileCharacteristics & FID_FILE_CHAR_HIDDEN) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) continue; } - if (cfi.fileCharacteristics & FID_FILE_CHAR_PARENT) { + if (iter.fi.fileCharacteristics & FID_FILE_CHAR_PARENT) { if (!dir_emit_dotdot(file, ctx)) - goto out; + goto out_iter; continue; } - flen = udf_get_filename(sb, nameptr, lfi, fname, UDF_NAME_LEN); + flen = udf_get_filename(sb, iter.name, + iter.fi.lengthFileIdent, fname, UDF_NAME_LEN); if (flen < 0) continue; - tloc = lelb_to_cpu(cfi.icb.extLocation); + tloc = lelb_to_cpu(iter.fi.icb.extLocation); iblock = udf_get_lb_pblock(sb, &tloc, 0); if (!dir_emit(ctx, fname, flen, iblock, DT_UNKNOWN)) - goto out; - } /* end while */ - - ctx->pos = (nf_pos >> 2) + 1; - pos_valid = true; + goto out_iter; + } + if (!ret) { + ctx->pos = (iter.pos >> 2) + 1; + pos_valid = true; + } +out_iter: + udf_fiiter_release(&iter); out: if (pos_valid) file->f_version = inode_query_iversion(dir); - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - brelse(epos.bh); kfree(fname); - kfree(copy_name); return ret; } diff --git a/fs/udf/directory.c b/fs/udf/directory.c index 16bcf2c6b8b3..654536d2b609 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -17,183 +17,478 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/bio.h> +#include <linux/crc-itu-t.h> +#include <linux/iversion.h> -struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos, - struct udf_fileident_bh *fibh, - struct fileIdentDesc *cfi, - struct extent_position *epos, - struct kernel_lb_addr *eloc, uint32_t *elen, - sector_t *offset) +static int udf_verify_fi(struct udf_fileident_iter *iter) { - struct fileIdentDesc *fi; - int i, num; - udf_pblk_t block; - struct buffer_head *tmp, *bha[16]; - struct udf_inode_info *iinfo = UDF_I(dir); - - fibh->soffset = fibh->eoffset; + unsigned int len; + + if (iter->fi.descTag.tagIdent != cpu_to_le16(TAG_IDENT_FID)) { + udf_err(iter->dir->i_sb, + "directory (ino %lu) has entry at pos %llu with incorrect tag %x\n", + iter->dir->i_ino, (unsigned long long)iter->pos, + le16_to_cpu(iter->fi.descTag.tagIdent)); + return -EFSCORRUPTED; + } + len = udf_dir_entry_len(&iter->fi); + if (le16_to_cpu(iter->fi.lengthOfImpUse) & 3) { + udf_err(iter->dir->i_sb, + "directory (ino %lu) has entry at pos %llu with unaligned length of impUse field\n", + iter->dir->i_ino, (unsigned long long)iter->pos); + return -EFSCORRUPTED; + } + /* + * This is in fact allowed by the spec due to long impUse field but + * we don't support it. If there is real media with this large impUse + * field, support can be added. + */ + if (len > 1 << iter->dir->i_blkbits) { + udf_err(iter->dir->i_sb, + "directory (ino %lu) has too big (%u) entry at pos %llu\n", + iter->dir->i_ino, len, (unsigned long long)iter->pos); + return -EFSCORRUPTED; + } + if (iter->pos + len > iter->dir->i_size) { + udf_err(iter->dir->i_sb, + "directory (ino %lu) has entry past directory size at pos %llu\n", + iter->dir->i_ino, (unsigned long long)iter->pos); + return -EFSCORRUPTED; + } + if (udf_dir_entry_len(&iter->fi) != + sizeof(struct tag) + le16_to_cpu(iter->fi.descTag.descCRCLength)) { + udf_err(iter->dir->i_sb, + "directory (ino %lu) has entry where CRC length (%u) does not match entry length (%u)\n", + iter->dir->i_ino, + (unsigned)le16_to_cpu(iter->fi.descTag.descCRCLength), + (unsigned)(udf_dir_entry_len(&iter->fi) - + sizeof(struct tag))); + return -EFSCORRUPTED; + } + return 0; +} +static int udf_copy_fi(struct udf_fileident_iter *iter) +{ + struct udf_inode_info *iinfo = UDF_I(iter->dir); + u32 blksize = 1 << iter->dir->i_blkbits; + u32 off, len, nameoff; + int err; + + /* Skip copying when we are at EOF */ + if (iter->pos >= iter->dir->i_size) { + iter->name = NULL; + return 0; + } + if (iter->dir->i_size < iter->pos + sizeof(struct fileIdentDesc)) { + udf_err(iter->dir->i_sb, + "directory (ino %lu) has entry straddling EOF\n", + iter->dir->i_ino); + return -EFSCORRUPTED; + } if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - fi = udf_get_fileident(iinfo->i_data - - (iinfo->i_efe ? - sizeof(struct extendedFileEntry) : - sizeof(struct fileEntry)), - dir->i_sb->s_blocksize, - &(fibh->eoffset)); - if (!fi) - return NULL; - - *nf_pos += fibh->eoffset - fibh->soffset; - - memcpy((uint8_t *)cfi, (uint8_t *)fi, + memcpy(&iter->fi, iinfo->i_data + iinfo->i_lenEAttr + iter->pos, sizeof(struct fileIdentDesc)); - - return fi; + err = udf_verify_fi(iter); + if (err < 0) + return err; + iter->name = iinfo->i_data + iinfo->i_lenEAttr + iter->pos + + sizeof(struct fileIdentDesc) + + le16_to_cpu(iter->fi.lengthOfImpUse); + return 0; } - if (fibh->eoffset == dir->i_sb->s_blocksize) { - uint32_t lextoffset = epos->offset; - unsigned char blocksize_bits = dir->i_sb->s_blocksize_bits; - - if (udf_next_aext(dir, epos, eloc, elen, 1) != - (EXT_RECORDED_ALLOCATED >> 30)) - return NULL; + off = iter->pos & (blksize - 1); + len = min_t(int, sizeof(struct fileIdentDesc), blksize - off); + memcpy(&iter->fi, iter->bh[0]->b_data + off, len); + if (len < sizeof(struct fileIdentDesc)) + memcpy((char *)(&iter->fi) + len, iter->bh[1]->b_data, + sizeof(struct fileIdentDesc) - len); + err = udf_verify_fi(iter); + if (err < 0) + return err; + + /* Handle directory entry name */ + nameoff = off + sizeof(struct fileIdentDesc) + + le16_to_cpu(iter->fi.lengthOfImpUse); + if (off + udf_dir_entry_len(&iter->fi) <= blksize) { + iter->name = iter->bh[0]->b_data + nameoff; + } else if (nameoff >= blksize) { + iter->name = iter->bh[1]->b_data + (nameoff - blksize); + } else { + iter->name = iter->namebuf; + len = blksize - nameoff; + memcpy(iter->name, iter->bh[0]->b_data + nameoff, len); + memcpy(iter->name + len, iter->bh[1]->b_data, + iter->fi.lengthFileIdent - len); + } + return 0; +} - block = udf_get_lb_pblock(dir->i_sb, eloc, *offset); +/* Readahead 8k once we are at 8k boundary */ +static void udf_readahead_dir(struct udf_fileident_iter *iter) +{ + unsigned int ralen = 16 >> (iter->dir->i_blkbits - 9); + struct buffer_head *tmp, *bha[16]; + int i, num; + udf_pblk_t blk; + + if (iter->loffset & (ralen - 1)) + return; + + if (iter->loffset + ralen > (iter->elen >> iter->dir->i_blkbits)) + ralen = (iter->elen >> iter->dir->i_blkbits) - iter->loffset; + num = 0; + for (i = 0; i < ralen; i++) { + blk = udf_get_lb_pblock(iter->dir->i_sb, &iter->eloc, + iter->loffset + i); + tmp = sb_getblk(iter->dir->i_sb, blk); + if (tmp && !buffer_uptodate(tmp) && !buffer_locked(tmp)) + bha[num++] = tmp; + else + brelse(tmp); + } + if (num) { + bh_readahead_batch(num, bha, REQ_RAHEAD); + for (i = 0; i < num; i++) + brelse(bha[i]); + } +} - (*offset)++; +static struct buffer_head *udf_fiiter_bread_blk(struct udf_fileident_iter *iter) +{ + udf_pblk_t blk; - if ((*offset << blocksize_bits) >= *elen) - *offset = 0; - else - epos->offset = lextoffset; + udf_readahead_dir(iter); + blk = udf_get_lb_pblock(iter->dir->i_sb, &iter->eloc, iter->loffset); + return sb_bread(iter->dir->i_sb, blk); +} - brelse(fibh->sbh); - fibh->sbh = fibh->ebh = udf_tread(dir->i_sb, block); - if (!fibh->sbh) - return NULL; - fibh->soffset = fibh->eoffset = 0; - - if (!(*offset & ((16 >> (blocksize_bits - 9)) - 1))) { - i = 16 >> (blocksize_bits - 9); - if (i + *offset > (*elen >> blocksize_bits)) - i = (*elen >> blocksize_bits)-*offset; - for (num = 0; i > 0; i--) { - block = udf_get_lb_pblock(dir->i_sb, eloc, - *offset + i); - tmp = udf_tgetblk(dir->i_sb, block); - if (tmp && !buffer_uptodate(tmp) && - !buffer_locked(tmp)) - bha[num++] = tmp; - else - brelse(tmp); - } - if (num) { - bh_readahead_batch(num, bha, REQ_RAHEAD); - for (i = 0; i < num; i++) - brelse(bha[i]); - } +/* + * Updates loffset to point to next directory block; eloc, elen & epos are + * updated if we need to traverse to the next extent as well. + */ +static int udf_fiiter_advance_blk(struct udf_fileident_iter *iter) +{ + iter->loffset++; + if (iter->loffset < DIV_ROUND_UP(iter->elen, 1<<iter->dir->i_blkbits)) + return 0; + + iter->loffset = 0; + if (udf_next_aext(iter->dir, &iter->epos, &iter->eloc, &iter->elen, 1) + != (EXT_RECORDED_ALLOCATED >> 30)) { + if (iter->pos == iter->dir->i_size) { + iter->elen = 0; + return 0; } - } else if (fibh->sbh != fibh->ebh) { - brelse(fibh->sbh); - fibh->sbh = fibh->ebh; + udf_err(iter->dir->i_sb, + "extent after position %llu not allocated in directory (ino %lu)\n", + (unsigned long long)iter->pos, iter->dir->i_ino); + return -EFSCORRUPTED; } + return 0; +} - fi = udf_get_fileident(fibh->sbh->b_data, dir->i_sb->s_blocksize, - &(fibh->eoffset)); - - if (!fi) - return NULL; +static int udf_fiiter_load_bhs(struct udf_fileident_iter *iter) +{ + int blksize = 1 << iter->dir->i_blkbits; + int off = iter->pos & (blksize - 1); + int err; + struct fileIdentDesc *fi; - *nf_pos += fibh->eoffset - fibh->soffset; + /* Is there any further extent we can map from? */ + if (!iter->bh[0] && iter->elen) { + iter->bh[0] = udf_fiiter_bread_blk(iter); + if (!iter->bh[0]) { + err = -ENOMEM; + goto out_brelse; + } + if (!buffer_uptodate(iter->bh[0])) { + err = -EIO; + goto out_brelse; + } + } + /* There's no next block so we are done */ + if (iter->pos >= iter->dir->i_size) + return 0; + /* Need to fetch next block as well? */ + if (off + sizeof(struct fileIdentDesc) > blksize) + goto fetch_next; + fi = (struct fileIdentDesc *)(iter->bh[0]->b_data + off); + /* Need to fetch next block to get name? */ + if (off + udf_dir_entry_len(fi) > blksize) { +fetch_next: + err = udf_fiiter_advance_blk(iter); + if (err) + goto out_brelse; + iter->bh[1] = udf_fiiter_bread_blk(iter); + if (!iter->bh[1]) { + err = -ENOMEM; + goto out_brelse; + } + if (!buffer_uptodate(iter->bh[1])) { + err = -EIO; + goto out_brelse; + } + } + return 0; +out_brelse: + brelse(iter->bh[0]); + brelse(iter->bh[1]); + iter->bh[0] = iter->bh[1] = NULL; + return err; +} - if (fibh->eoffset <= dir->i_sb->s_blocksize) { - memcpy((uint8_t *)cfi, (uint8_t *)fi, - sizeof(struct fileIdentDesc)); - } else if (fibh->eoffset > dir->i_sb->s_blocksize) { - uint32_t lextoffset = epos->offset; +int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, + loff_t pos) +{ + struct udf_inode_info *iinfo = UDF_I(dir); + int err = 0; + + iter->dir = dir; + iter->bh[0] = iter->bh[1] = NULL; + iter->pos = pos; + iter->elen = 0; + iter->epos.bh = NULL; + iter->name = NULL; + /* + * When directory is verified, we don't expect directory iteration to + * fail and it can be difficult to undo without corrupting filesystem. + * So just do not allow memory allocation failures here. + */ + iter->namebuf = kmalloc(UDF_NAME_LEN_CS0, GFP_KERNEL | __GFP_NOFAIL); - if (udf_next_aext(dir, epos, eloc, elen, 1) != - (EXT_RECORDED_ALLOCATED >> 30)) - return NULL; + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + err = udf_copy_fi(iter); + goto out; + } - block = udf_get_lb_pblock(dir->i_sb, eloc, *offset); + if (inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, + &iter->eloc, &iter->elen, &iter->loffset) != + (EXT_RECORDED_ALLOCATED >> 30)) { + if (pos == dir->i_size) + return 0; + udf_err(dir->i_sb, + "position %llu not allocated in directory (ino %lu)\n", + (unsigned long long)pos, dir->i_ino); + err = -EFSCORRUPTED; + goto out; + } + err = udf_fiiter_load_bhs(iter); + if (err < 0) + goto out; + err = udf_copy_fi(iter); +out: + if (err < 0) + udf_fiiter_release(iter); + return err; +} - (*offset)++; +int udf_fiiter_advance(struct udf_fileident_iter *iter) +{ + unsigned int oldoff, len; + int blksize = 1 << iter->dir->i_blkbits; + int err; + + oldoff = iter->pos & (blksize - 1); + len = udf_dir_entry_len(&iter->fi); + iter->pos += len; + if (UDF_I(iter->dir)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { + if (oldoff + len >= blksize) { + brelse(iter->bh[0]); + iter->bh[0] = NULL; + /* Next block already loaded? */ + if (iter->bh[1]) { + iter->bh[0] = iter->bh[1]; + iter->bh[1] = NULL; + } else { + err = udf_fiiter_advance_blk(iter); + if (err < 0) + return err; + } + } + err = udf_fiiter_load_bhs(iter); + if (err < 0) + return err; + } + return udf_copy_fi(iter); +} - if ((*offset << dir->i_sb->s_blocksize_bits) >= *elen) - *offset = 0; - else - epos->offset = lextoffset; +void udf_fiiter_release(struct udf_fileident_iter *iter) +{ + iter->dir = NULL; + brelse(iter->bh[0]); + brelse(iter->bh[1]); + iter->bh[0] = iter->bh[1] = NULL; + kfree(iter->namebuf); + iter->namebuf = NULL; +} - fibh->soffset -= dir->i_sb->s_blocksize; - fibh->eoffset -= dir->i_sb->s_blocksize; +static void udf_copy_to_bufs(void *buf1, int len1, void *buf2, int len2, + int off, void *src, int len) +{ + int copy; + + if (off >= len1) { + off -= len1; + } else { + copy = min(off + len, len1) - off; + memcpy(buf1 + off, src, copy); + src += copy; + len -= copy; + off = 0; + } + if (len > 0) { + if (WARN_ON_ONCE(off + len > len2 || !buf2)) + return; + memcpy(buf2 + off, src, len); + } +} - fibh->ebh = udf_tread(dir->i_sb, block); - if (!fibh->ebh) - return NULL; +static uint16_t udf_crc_fi_bufs(void *buf1, int len1, void *buf2, int len2, + int off, int len) +{ + int copy; + uint16_t crc = 0; + + if (off >= len1) { + off -= len1; + } else { + copy = min(off + len, len1) - off; + crc = crc_itu_t(crc, buf1 + off, copy); + len -= copy; + off = 0; + } + if (len > 0) { + if (WARN_ON_ONCE(off + len > len2 || !buf2)) + return 0; + crc = crc_itu_t(crc, buf2 + off, len); + } + return crc; +} - if (sizeof(struct fileIdentDesc) > -fibh->soffset) { - int fi_len; +static void udf_copy_fi_to_bufs(char *buf1, int len1, char *buf2, int len2, + int off, struct fileIdentDesc *fi, + uint8_t *impuse, uint8_t *name) +{ + uint16_t crc; + int fioff = off; + int crcoff = off + sizeof(struct tag); + unsigned int crclen = udf_dir_entry_len(fi) - sizeof(struct tag); + char zeros[UDF_NAME_PAD] = {}; + int endoff = off + udf_dir_entry_len(fi); + + udf_copy_to_bufs(buf1, len1, buf2, len2, off, fi, + sizeof(struct fileIdentDesc)); + off += sizeof(struct fileIdentDesc); + if (impuse) + udf_copy_to_bufs(buf1, len1, buf2, len2, off, impuse, + le16_to_cpu(fi->lengthOfImpUse)); + off += le16_to_cpu(fi->lengthOfImpUse); + if (name) { + udf_copy_to_bufs(buf1, len1, buf2, len2, off, name, + fi->lengthFileIdent); + off += fi->lengthFileIdent; + udf_copy_to_bufs(buf1, len1, buf2, len2, off, zeros, + endoff - off); + } - memcpy((uint8_t *)cfi, (uint8_t *)fi, -fibh->soffset); - memcpy((uint8_t *)cfi - fibh->soffset, - fibh->ebh->b_data, - sizeof(struct fileIdentDesc) + fibh->soffset); + crc = udf_crc_fi_bufs(buf1, len1, buf2, len2, crcoff, crclen); + fi->descTag.descCRC = cpu_to_le16(crc); + fi->descTag.descCRCLength = cpu_to_le16(crclen); + fi->descTag.tagChecksum = udf_tag_checksum(&fi->descTag); - fi_len = udf_dir_entry_len(cfi); - *nf_pos += fi_len - (fibh->eoffset - fibh->soffset); - fibh->eoffset = fibh->soffset + fi_len; - } else { - memcpy((uint8_t *)cfi, (uint8_t *)fi, - sizeof(struct fileIdentDesc)); - } - } - /* Got last entry outside of dir size - fs is corrupted! */ - if (*nf_pos > dir->i_size) - return NULL; - return fi; + udf_copy_to_bufs(buf1, len1, buf2, len2, fioff, fi, sizeof(struct tag)); } -struct fileIdentDesc *udf_get_fileident(void *buffer, int bufsize, int *offset) +void udf_fiiter_write_fi(struct udf_fileident_iter *iter, uint8_t *impuse) { - struct fileIdentDesc *fi; - int lengthThisIdent; - uint8_t *ptr; - int padlen; + struct udf_inode_info *iinfo = UDF_I(iter->dir); + void *buf1, *buf2 = NULL; + int len1, len2 = 0, off; + int blksize = 1 << iter->dir->i_blkbits; - if ((!buffer) || (!offset)) { - udf_debug("invalidparms, buffer=%p, offset=%p\n", - buffer, offset); - return NULL; + off = iter->pos & (blksize - 1); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + buf1 = iinfo->i_data + iinfo->i_lenEAttr; + len1 = iter->dir->i_size; + } else { + buf1 = iter->bh[0]->b_data; + len1 = blksize; + if (iter->bh[1]) { + buf2 = iter->bh[1]->b_data; + len2 = blksize; + } } - ptr = buffer; + udf_copy_fi_to_bufs(buf1, len1, buf2, len2, off, &iter->fi, impuse, + iter->name == iter->namebuf ? iter->name : NULL); - if ((*offset > 0) && (*offset < bufsize)) - ptr += *offset; - fi = (struct fileIdentDesc *)ptr; - if (fi->descTag.tagIdent != cpu_to_le16(TAG_IDENT_FID)) { - udf_debug("0x%x != TAG_IDENT_FID\n", - le16_to_cpu(fi->descTag.tagIdent)); - udf_debug("offset: %d sizeof: %lu bufsize: %d\n", - *offset, (unsigned long)sizeof(struct fileIdentDesc), - bufsize); - return NULL; + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + mark_inode_dirty(iter->dir); + } else { + mark_buffer_dirty_inode(iter->bh[0], iter->dir); + if (iter->bh[1]) + mark_buffer_dirty_inode(iter->bh[1], iter->dir); } - if ((*offset + sizeof(struct fileIdentDesc)) > bufsize) - lengthThisIdent = sizeof(struct fileIdentDesc); - else - lengthThisIdent = sizeof(struct fileIdentDesc) + - fi->lengthFileIdent + le16_to_cpu(fi->lengthOfImpUse); + inode_inc_iversion(iter->dir); +} - /* we need to figure padding, too! */ - padlen = lengthThisIdent % UDF_NAME_PAD; - if (padlen) - lengthThisIdent += (UDF_NAME_PAD - padlen); - *offset = *offset + lengthThisIdent; +void udf_fiiter_update_elen(struct udf_fileident_iter *iter, uint32_t new_elen) +{ + struct udf_inode_info *iinfo = UDF_I(iter->dir); + int diff = new_elen - iter->elen; + + /* Skip update when we already went past the last extent */ + if (!iter->elen) + return; + iter->elen = new_elen; + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) + iter->epos.offset -= sizeof(struct short_ad); + else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) + iter->epos.offset -= sizeof(struct long_ad); + udf_write_aext(iter->dir, &iter->epos, &iter->eloc, iter->elen, 1); + iinfo->i_lenExtents += diff; + mark_inode_dirty(iter->dir); +} - return fi; +/* Append new block to directory. @iter is expected to point at EOF */ +int udf_fiiter_append_blk(struct udf_fileident_iter *iter) +{ + struct udf_inode_info *iinfo = UDF_I(iter->dir); + int blksize = 1 << iter->dir->i_blkbits; + struct buffer_head *bh; + sector_t block; + uint32_t old_elen = iter->elen; + int err; + + if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) + return -EINVAL; + + /* Round up last extent in the file */ + udf_fiiter_update_elen(iter, ALIGN(iter->elen, blksize)); + + /* Allocate new block and refresh mapping information */ + block = iinfo->i_lenExtents >> iter->dir->i_blkbits; + bh = udf_bread(iter->dir, block, 1, &err); + if (!bh) { + udf_fiiter_update_elen(iter, old_elen); + return err; + } + if (inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, + &iter->loffset) != (EXT_RECORDED_ALLOCATED >> 30)) { + udf_err(iter->dir->i_sb, + "block %llu not allocated in directory (ino %lu)\n", + (unsigned long long)block, iter->dir->i_ino); + return -EFSCORRUPTED; + } + if (!(iter->pos & (blksize - 1))) { + brelse(iter->bh[0]); + iter->bh[0] = bh; + } else { + iter->bh[1] = bh; + } + return 0; } struct short_ad *udf_get_fileshortad(uint8_t *ptr, int maxoffset, uint32_t *offset, diff --git a/fs/udf/file.c b/fs/udf/file.c index 5c659e23e578..8238f742377b 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -38,100 +38,55 @@ #include "udf_i.h" #include "udf_sb.h" -static void __udf_adinicb_readpage(struct page *page) +static vm_fault_t udf_page_mkwrite(struct vm_fault *vmf) { - struct inode *inode = page->mapping->host; - char *kaddr; - struct udf_inode_info *iinfo = UDF_I(inode); - loff_t isize = i_size_read(inode); - - /* - * We have to be careful here as truncate can change i_size under us. - * So just sample it once and use the same value everywhere. - */ - kaddr = kmap_atomic(page); - memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, isize); - memset(kaddr + isize, 0, PAGE_SIZE - isize); - flush_dcache_page(page); - SetPageUptodate(page); - kunmap_atomic(kaddr); -} - -static int udf_adinicb_read_folio(struct file *file, struct folio *folio) -{ - BUG_ON(!folio_test_locked(folio)); - __udf_adinicb_readpage(&folio->page); - folio_unlock(folio); - - return 0; -} - -static int udf_adinicb_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - char *kaddr; - struct udf_inode_info *iinfo = UDF_I(inode); - - BUG_ON(!PageLocked(page)); - - kaddr = kmap_atomic(page); - memcpy(iinfo->i_data + iinfo->i_lenEAttr, kaddr, i_size_read(inode)); - SetPageUptodate(page); - kunmap_atomic(kaddr); - mark_inode_dirty(inode); - unlock_page(page); - - return 0; -} - -static int udf_adinicb_write_begin(struct file *file, - struct address_space *mapping, loff_t pos, - unsigned len, struct page **pagep, - void **fsdata) -{ - struct page *page; - - if (WARN_ON_ONCE(pos >= PAGE_SIZE)) - return -EIO; - page = grab_cache_page_write_begin(mapping, 0); - if (!page) - return -ENOMEM; - *pagep = page; - - if (!PageUptodate(page)) - __udf_adinicb_readpage(page); - return 0; -} - -static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - /* Fallback to buffered I/O. */ - return 0; -} + struct vm_area_struct *vma = vmf->vma; + struct inode *inode = file_inode(vma->vm_file); + struct address_space *mapping = inode->i_mapping; + struct page *page = vmf->page; + loff_t size; + unsigned int end; + vm_fault_t ret = VM_FAULT_LOCKED; + int err; -static int udf_adinicb_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - struct inode *inode = page->mapping->host; - loff_t last_pos = pos + copied; - if (last_pos > inode->i_size) - i_size_write(inode, last_pos); + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + filemap_invalidate_lock_shared(mapping); + lock_page(page); + size = i_size_read(inode); + if (page->mapping != inode->i_mapping || page_offset(page) >= size) { + unlock_page(page); + ret = VM_FAULT_NOPAGE; + goto out_unlock; + } + /* Space is already allocated for in-ICB file */ + if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) + goto out_dirty; + if (page->index == size >> PAGE_SHIFT) + end = size & ~PAGE_MASK; + else + end = PAGE_SIZE; + err = __block_write_begin(page, 0, end, udf_get_block); + if (!err) + err = block_commit_write(page, 0, end); + if (err < 0) { + unlock_page(page); + ret = block_page_mkwrite_return(err); + goto out_unlock; + } +out_dirty: set_page_dirty(page); - unlock_page(page); - put_page(page); - return copied; + wait_for_stable_page(page); +out_unlock: + filemap_invalidate_unlock_shared(mapping); + sb_end_pagefault(inode->i_sb); + return ret; } -const struct address_space_operations udf_adinicb_aops = { - .dirty_folio = block_dirty_folio, - .invalidate_folio = block_invalidate_folio, - .read_folio = udf_adinicb_read_folio, - .writepage = udf_adinicb_writepage, - .write_begin = udf_adinicb_write_begin, - .write_end = udf_adinicb_write_end, - .direct_IO = udf_adinicb_direct_IO, +static const struct vm_operations_struct udf_file_vm_ops = { + .fault = filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = udf_page_mkwrite, }; static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) @@ -140,7 +95,6 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct udf_inode_info *iinfo = UDF_I(inode); - int err; inode_lock(inode); @@ -148,27 +102,23 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (retval <= 0) goto out; - down_write(&iinfo->i_data_sem); - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - loff_t end = iocb->ki_pos + iov_iter_count(from); - - if (inode->i_sb->s_blocksize < - (udf_file_entry_alloc_offset(inode) + end)) { - err = udf_expand_file_adinicb(inode); - if (err) { - inode_unlock(inode); - udf_debug("udf_expand_adinicb: err=%d\n", err); - return err; - } - } else { - iinfo->i_lenAlloc = max(end, inode->i_size); - up_write(&iinfo->i_data_sem); - } - } else - up_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && + inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + + iocb->ki_pos + iov_iter_count(from))) { + filemap_invalidate_lock(inode->i_mapping); + retval = udf_expand_file_adinicb(inode); + filemap_invalidate_unlock(inode->i_mapping); + if (retval) + goto out; + } retval = __generic_file_write_iter(iocb, from); out: + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && retval > 0) { + down_write(&iinfo->i_data_sem); + iinfo->i_lenAlloc = inode->i_size; + up_write(&iinfo->i_data_sem); + } inode_unlock(inode); if (retval > 0) { @@ -243,11 +193,19 @@ static int udf_release_file(struct inode *inode, struct file *filp) return 0; } +static int udf_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + file_accessed(file); + vma->vm_ops = &udf_file_vm_ops; + + return 0; +} + const struct file_operations udf_file_operations = { .read_iter = generic_file_read_iter, .unlocked_ioctl = udf_ioctl, .open = generic_file_open, - .mmap = generic_file_mmap, + .mmap = udf_file_mmap, .write_iter = udf_file_write_iter, .release = udf_release_file, .fsync = generic_file_fsync, @@ -256,14 +214,14 @@ const struct file_operations udf_file_operations = { .llseek = generic_file_llseek, }; -static int udf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +static int udf_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -286,7 +244,7 @@ static int udf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (attr->ia_valid & ATTR_MODE) udf_update_extra_perms(inode, attr->ia_mode); - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index b5d611cee749..8d50121778a5 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -28,21 +28,7 @@ void udf_free_inode(struct inode *inode) { - struct super_block *sb = inode->i_sb; - struct udf_sb_info *sbi = UDF_SB(sb); - struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); - - if (lvidiu) { - mutex_lock(&sbi->s_alloc_mutex); - if (S_ISDIR(inode->i_mode)) - le32_add_cpu(&lvidiu->numDirs, -1); - else - le32_add_cpu(&lvidiu->numFiles, -1); - udf_updated_lvid(sb); - mutex_unlock(&sbi->s_alloc_mutex); - } - - udf_free_blocks(sb, NULL, &UDF_I(inode)->i_location, 0, 1); + udf_free_blocks(inode->i_sb, NULL, &UDF_I(inode)->i_location, 0, 1); } struct inode *udf_new_inode(struct inode *dir, umode_t mode) @@ -54,7 +40,6 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) uint32_t start = UDF_I(dir)->i_location.logicalBlockNum; struct udf_inode_info *iinfo; struct udf_inode_info *dinfo = UDF_I(dir); - struct logicalVolIntegrityDescImpUse *lvidiu; int err; inode = new_inode(sb); @@ -92,20 +77,10 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) return ERR_PTR(err); } - lvidiu = udf_sb_lvidiu(sb); - if (lvidiu) { - iinfo->i_unique = lvid_get_unique_id(sb); - inode->i_generation = iinfo->i_unique; - mutex_lock(&sbi->s_alloc_mutex); - if (S_ISDIR(mode)) - le32_add_cpu(&lvidiu->numDirs, 1); - else - le32_add_cpu(&lvidiu->numFiles, 1); - udf_updated_lvid(sb); - mutex_unlock(&sbi->s_alloc_mutex); - } + iinfo->i_unique = lvid_get_unique_id(sb); + inode->i_generation = iinfo->i_unique; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); if (UDF_QUERY_FLAG(sb, UDF_FLAG_UID_SET)) inode->i_uid = sbi->s_uid; if (UDF_QUERY_FLAG(sb, UDF_FLAG_GID_SET)) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 34e416327dd4..3b2adf4cbc57 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -52,21 +52,24 @@ #define FE_DELETE_PERMS (FE_PERM_U_DELETE | FE_PERM_G_DELETE | \ FE_PERM_O_DELETE) +struct udf_map_rq; + static umode_t udf_convert_permissions(struct fileEntry *); static int udf_update_inode(struct inode *, int); static int udf_sync_inode(struct inode *inode); static int udf_alloc_i_data(struct inode *inode, size_t size); -static sector_t inode_getblk(struct inode *, sector_t, int *, int *); -static int8_t udf_insert_aext(struct inode *, struct extent_position, - struct kernel_lb_addr, uint32_t); +static int inode_getblk(struct inode *inode, struct udf_map_rq *map); +static int udf_insert_aext(struct inode *, struct extent_position, + struct kernel_lb_addr, uint32_t); static void udf_split_extents(struct inode *, int *, int, udf_pblk_t, struct kernel_long_ad *, int *); static void udf_prealloc_extents(struct inode *, int, int, struct kernel_long_ad *, int *); static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *); -static void udf_update_extents(struct inode *, struct kernel_long_ad *, int, - int, struct extent_position *); -static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); +static int udf_update_extents(struct inode *, struct kernel_long_ad *, int, + int, struct extent_position *); +static int udf_get_block_wb(struct inode *inode, sector_t block, + struct buffer_head *bh_result, int create); static void __udf_clear_extent_cache(struct inode *inode) { @@ -182,14 +185,56 @@ static void udf_write_failed(struct address_space *mapping, loff_t to) } } +static int udf_adinicb_writepage(struct page *page, + struct writeback_control *wbc, void *data) +{ + struct inode *inode = page->mapping->host; + struct udf_inode_info *iinfo = UDF_I(inode); + + BUG_ON(!PageLocked(page)); + memcpy_to_page(page, 0, iinfo->i_data + iinfo->i_lenEAttr, + i_size_read(inode)); + unlock_page(page); + mark_inode_dirty(inode); + + return 0; +} + static int udf_writepages(struct address_space *mapping, - struct writeback_control *wbc) + struct writeback_control *wbc) { - return mpage_writepages(mapping, wbc, udf_get_block); + struct inode *inode = mapping->host; + struct udf_inode_info *iinfo = UDF_I(inode); + + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) + return mpage_writepages(mapping, wbc, udf_get_block_wb); + return write_cache_pages(mapping, wbc, udf_adinicb_writepage, NULL); +} + +static void udf_adinicb_readpage(struct page *page) +{ + struct inode *inode = page->mapping->host; + char *kaddr; + struct udf_inode_info *iinfo = UDF_I(inode); + loff_t isize = i_size_read(inode); + + kaddr = kmap_local_page(page); + memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, isize); + memset(kaddr + isize, 0, PAGE_SIZE - isize); + flush_dcache_page(page); + SetPageUptodate(page); + kunmap_local(kaddr); } static int udf_read_folio(struct file *file, struct folio *folio) { + struct udf_inode_info *iinfo = UDF_I(file_inode(file)); + + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + udf_adinicb_readpage(&folio->page); + folio_unlock(folio); + return 0; + } return mpage_read_folio(folio, udf_get_block); } @@ -199,15 +244,49 @@ static void udf_readahead(struct readahead_control *rac) } static int udf_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, + struct page **pagep, void **fsdata) { + struct udf_inode_info *iinfo = UDF_I(file_inode(file)); + struct page *page; int ret; - ret = block_write_begin(mapping, pos, len, pagep, udf_get_block); - if (unlikely(ret)) - udf_write_failed(mapping, pos + len); - return ret; + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { + ret = block_write_begin(mapping, pos, len, pagep, + udf_get_block); + if (unlikely(ret)) + udf_write_failed(mapping, pos + len); + return ret; + } + if (WARN_ON_ONCE(pos >= PAGE_SIZE)) + return -EIO; + page = grab_cache_page_write_begin(mapping, 0); + if (!page) + return -ENOMEM; + *pagep = page; + if (!PageUptodate(page)) + udf_adinicb_readpage(page); + return 0; +} + +static int udf_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + struct inode *inode = file_inode(file); + loff_t last_pos; + + if (UDF_I(inode)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) + return generic_write_end(file, mapping, pos, len, copied, page, + fsdata); + last_pos = pos + copied; + if (last_pos > inode->i_size) + i_size_write(inode, last_pos); + set_page_dirty(page); + unlock_page(page); + put_page(page); + + return copied; } static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter) @@ -218,6 +297,9 @@ static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter) size_t count = iov_iter_count(iter); ssize_t ret; + /* Fallback to buffered IO for in-ICB files */ + if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) + return 0; ret = blockdev_direct_IO(iocb, inode, iter, udf_get_block); if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE)) udf_write_failed(mapping, iocb->ki_pos + count); @@ -226,6 +308,10 @@ static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static sector_t udf_bmap(struct address_space *mapping, sector_t block) { + struct udf_inode_info *iinfo = UDF_I(mapping->host); + + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) + return -EINVAL; return generic_block_bmap(mapping, block, udf_get_block); } @@ -236,7 +322,7 @@ const struct address_space_operations udf_aops = { .readahead = udf_readahead, .writepages = udf_writepages, .write_begin = udf_write_begin, - .write_end = generic_write_end, + .write_end = udf_write_end, .direct_IO = udf_direct_IO, .bmap = udf_bmap, .migrate_folio = buffer_migrate_folio, @@ -245,18 +331,17 @@ const struct address_space_operations udf_aops = { /* * Expand file stored in ICB to a normal one-block-file * - * This function requires i_data_sem for writing and releases it. * This function requires i_mutex held */ int udf_expand_file_adinicb(struct inode *inode) { struct page *page; - char *kaddr; struct udf_inode_info *iinfo = UDF_I(inode); int err; WARN_ON_ONCE(!inode_is_locked(inode)); if (!iinfo->i_lenAlloc) { + down_write(&iinfo->i_data_sem); if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else @@ -267,26 +352,13 @@ int udf_expand_file_adinicb(struct inode *inode) mark_inode_dirty(inode); return 0; } - /* - * Release i_data_sem so that we can lock a page - page lock ranks - * above i_data_sem. i_mutex still protects us against file changes. - */ - up_write(&iinfo->i_data_sem); page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS); if (!page) return -ENOMEM; - if (!PageUptodate(page)) { - kaddr = kmap_atomic(page); - memset(kaddr + iinfo->i_lenAlloc, 0x00, - PAGE_SIZE - iinfo->i_lenAlloc); - memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, - iinfo->i_lenAlloc); - flush_dcache_page(page); - SetPageUptodate(page); - kunmap_atomic(kaddr); - } + if (!PageUptodate(page)) + udf_adinicb_readpage(page); down_write(&iinfo->i_data_sem); memset(iinfo->i_data + iinfo->i_lenEAttr, 0x00, iinfo->i_lenAlloc); @@ -295,8 +367,6 @@ int udf_expand_file_adinicb(struct inode *inode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; - /* from now on we have normal address_space methods */ - inode->i_data.a_ops = &udf_aops; set_page_dirty(page); unlock_page(page); up_write(&iinfo->i_data_sem); @@ -305,12 +375,10 @@ int udf_expand_file_adinicb(struct inode *inode) /* Restore everything back so that we don't lose data... */ lock_page(page); down_write(&iinfo->i_data_sem); - kaddr = kmap_atomic(page); - memcpy(iinfo->i_data + iinfo->i_lenEAttr, kaddr, inode->i_size); - kunmap_atomic(kaddr); + memcpy_to_page(page, 0, iinfo->i_data + iinfo->i_lenEAttr, + inode->i_size); unlock_page(page); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; - inode->i_data.a_ops = &udf_adinicb_aops; iinfo->i_lenAlloc = inode->i_size; up_write(&iinfo->i_data_sem); } @@ -320,162 +388,103 @@ int udf_expand_file_adinicb(struct inode *inode) return err; } -struct buffer_head *udf_expand_dir_adinicb(struct inode *inode, - udf_pblk_t *block, int *err) -{ - udf_pblk_t newblock; - struct buffer_head *dbh = NULL; - struct kernel_lb_addr eloc; - uint8_t alloctype; - struct extent_position epos; +#define UDF_MAP_CREATE 0x01 /* Mapping can allocate new blocks */ +#define UDF_MAP_NOPREALLOC 0x02 /* Do not preallocate blocks */ - struct udf_fileident_bh sfibh, dfibh; - loff_t f_pos = udf_ext0_offset(inode); - int size = udf_ext0_offset(inode) + inode->i_size; - struct fileIdentDesc cfi, *sfi, *dfi; - struct udf_inode_info *iinfo = UDF_I(inode); +#define UDF_BLK_MAPPED 0x01 /* Block was successfully mapped */ +#define UDF_BLK_NEW 0x02 /* Block was freshly allocated */ - if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) - alloctype = ICBTAG_FLAG_AD_SHORT; - else - alloctype = ICBTAG_FLAG_AD_LONG; +struct udf_map_rq { + sector_t lblk; + udf_pblk_t pblk; + int iflags; /* UDF_MAP_ flags determining behavior */ + int oflags; /* UDF_BLK_ flags reporting results */ +}; - if (!inode->i_size) { - iinfo->i_alloc_type = alloctype; - mark_inode_dirty(inode); - return NULL; - } +static int udf_map_block(struct inode *inode, struct udf_map_rq *map) +{ + int err; + struct udf_inode_info *iinfo = UDF_I(inode); - /* alloc block, and copy data to it */ - *block = udf_new_block(inode->i_sb, inode, - iinfo->i_location.partitionReferenceNum, - iinfo->i_location.logicalBlockNum, err); - if (!(*block)) - return NULL; - newblock = udf_get_pblock(inode->i_sb, *block, - iinfo->i_location.partitionReferenceNum, - 0); - if (!newblock) - return NULL; - dbh = udf_tgetblk(inode->i_sb, newblock); - if (!dbh) - return NULL; - lock_buffer(dbh); - memset(dbh->b_data, 0x00, inode->i_sb->s_blocksize); - set_buffer_uptodate(dbh); - unlock_buffer(dbh); - mark_buffer_dirty_inode(dbh, inode); - - sfibh.soffset = sfibh.eoffset = - f_pos & (inode->i_sb->s_blocksize - 1); - sfibh.sbh = sfibh.ebh = NULL; - dfibh.soffset = dfibh.eoffset = 0; - dfibh.sbh = dfibh.ebh = dbh; - while (f_pos < size) { - iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; - sfi = udf_fileident_read(inode, &f_pos, &sfibh, &cfi, NULL, - NULL, NULL, NULL); - if (!sfi) { - brelse(dbh); - return NULL; - } - iinfo->i_alloc_type = alloctype; - sfi->descTag.tagLocation = cpu_to_le32(*block); - dfibh.soffset = dfibh.eoffset; - dfibh.eoffset += (sfibh.eoffset - sfibh.soffset); - dfi = (struct fileIdentDesc *)(dbh->b_data + dfibh.soffset); - if (udf_write_fi(inode, sfi, dfi, &dfibh, sfi->impUse, - udf_get_fi_ident(sfi))) { - iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; - brelse(dbh); - return NULL; + map->oflags = 0; + if (!(map->iflags & UDF_MAP_CREATE)) { + struct kernel_lb_addr eloc; + uint32_t elen; + sector_t offset; + struct extent_position epos = {}; + + down_read(&iinfo->i_data_sem); + if (inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset) + == (EXT_RECORDED_ALLOCATED >> 30)) { + map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc, + offset); + map->oflags |= UDF_BLK_MAPPED; } - } - mark_buffer_dirty_inode(dbh, inode); + up_read(&iinfo->i_data_sem); + brelse(epos.bh); - memset(iinfo->i_data + iinfo->i_lenEAttr, 0, iinfo->i_lenAlloc); - iinfo->i_lenAlloc = 0; - eloc.logicalBlockNum = *block; - eloc.partitionReferenceNum = - iinfo->i_location.partitionReferenceNum; - iinfo->i_lenExtents = inode->i_size; - epos.bh = NULL; - epos.block = iinfo->i_location; - epos.offset = udf_file_entry_alloc_offset(inode); - udf_add_aext(inode, &epos, &eloc, inode->i_size, 0); - /* UniqueID stuff */ - - brelse(epos.bh); - mark_inode_dirty(inode); - return dbh; -} - -static int udf_get_block(struct inode *inode, sector_t block, - struct buffer_head *bh_result, int create) -{ - int err, new; - sector_t phys = 0; - struct udf_inode_info *iinfo; - - if (!create) { - phys = udf_block_map(inode, block); - if (phys) - map_bh(bh_result, inode->i_sb, phys); return 0; } - err = -EIO; - new = 0; - iinfo = UDF_I(inode); - down_write(&iinfo->i_data_sem); - if (block == iinfo->i_next_alloc_block + 1) { - iinfo->i_next_alloc_block++; - iinfo->i_next_alloc_goal++; - } - /* * Block beyond EOF and prealloc extents? Just discard preallocation * as it is not useful and complicates things. */ - if (((loff_t)block) << inode->i_blkbits > iinfo->i_lenExtents) + if (((loff_t)map->lblk) << inode->i_blkbits >= iinfo->i_lenExtents) udf_discard_prealloc(inode); udf_clear_extent_cache(inode); - phys = inode_getblk(inode, block, &err, &new); - if (!phys) - goto abort; - - if (new) - set_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, phys); - -abort: + err = inode_getblk(inode, map); up_write(&iinfo->i_data_sem); return err; } -static struct buffer_head *udf_getblk(struct inode *inode, udf_pblk_t block, - int create, int *err) +static int __udf_get_block(struct inode *inode, sector_t block, + struct buffer_head *bh_result, int flags) { - struct buffer_head *bh; - struct buffer_head dummy; - - dummy.b_state = 0; - dummy.b_blocknr = -1000; - *err = udf_get_block(inode, block, &dummy, create); - if (!*err && buffer_mapped(&dummy)) { - bh = sb_getblk(inode->i_sb, dummy.b_blocknr); - if (buffer_new(&dummy)) { - lock_buffer(bh); - memset(bh->b_data, 0x00, inode->i_sb->s_blocksize); - set_buffer_uptodate(bh); - unlock_buffer(bh); - mark_buffer_dirty_inode(bh, inode); - } - return bh; + int err; + struct udf_map_rq map = { + .lblk = block, + .iflags = flags, + }; + + err = udf_map_block(inode, &map); + if (err < 0) + return err; + if (map.oflags & UDF_BLK_MAPPED) { + map_bh(bh_result, inode->i_sb, map.pblk); + if (map.oflags & UDF_BLK_NEW) + set_buffer_new(bh_result); } + return 0; +} - return NULL; +int udf_get_block(struct inode *inode, sector_t block, + struct buffer_head *bh_result, int create) +{ + int flags = create ? UDF_MAP_CREATE : 0; + + /* + * We preallocate blocks only for regular files. It also makes sense + * for directories but there's a problem when to drop the + * preallocation. We might use some delayed work for that but I feel + * it's overengineering for a filesystem like UDF. + */ + if (!S_ISREG(inode->i_mode)) + flags |= UDF_MAP_NOPREALLOC; + return __udf_get_block(inode, block, bh_result, flags); +} + +/* + * We shouldn't be allocating blocks on page writeback since we allocate them + * on page fault. We can spot dirty buffers without allocated blocks though + * when truncate expands file. These however don't have valid data so we can + * safely ignore them. So never allocate blocks from page writeback. + */ +static int udf_get_block_wb(struct inode *inode, sector_t block, + struct buffer_head *bh_result, int create) +{ + return __udf_get_block(inode, block, bh_result, 0); } /* Extend the file with new blocks totaling 'new_block_bytes', @@ -509,6 +518,7 @@ static int udf_do_extend_file(struct inode *inode, ~(sb->s_blocksize - 1); } + add = 0; /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { @@ -521,8 +531,10 @@ static int udf_do_extend_file(struct inode *inode, } if (fake) { - udf_add_aext(inode, last_pos, &last_ext->extLocation, - last_ext->extLength, 1); + err = udf_add_aext(inode, last_pos, &last_ext->extLocation, + last_ext->extLength, 1); + if (err < 0) + goto out_err; count++; } else { struct kernel_lb_addr tmploc; @@ -539,6 +551,7 @@ static int udf_do_extend_file(struct inode *inode, if (new_block_bytes) udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); } + iinfo->i_lenExtents += add; /* Managed to do everything necessary? */ if (!new_block_bytes) @@ -556,7 +569,8 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; + iinfo->i_lenExtents += add; count++; } if (new_block_bytes) { @@ -565,7 +579,8 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; + iinfo->i_lenExtents += new_block_bytes; count++; } @@ -579,6 +594,11 @@ out: return -EIO; return count; +out_err: + /* Remove extents we've created so far */ + udf_clear_extent_cache(inode); + udf_truncate_extents(inode); + return err; } /* Extend the final block of the file to final_block_len bytes */ @@ -626,6 +646,7 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) else BUG(); + down_write(&iinfo->i_data_sem); /* * When creating hole in file, just don't bother with preserving * preallocation. It likely won't be very useful anyway. @@ -668,14 +689,13 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) if (err < 0) goto out; err = 0; - iinfo->i_lenExtents = newsize; out: brelse(epos.bh); + up_write(&iinfo->i_data_sem); return err; } -static sector_t inode_getblk(struct inode *inode, sector_t block, - int *err, int *new) +static int inode_getblk(struct inode *inode, struct udf_map_rq *map) { struct kernel_long_ad laarr[EXTENT_MERGE_SIZE]; struct extent_position prev_epos, cur_epos, next_epos; @@ -684,21 +704,20 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, struct kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; - udf_pblk_t newblocknum, newblock = 0; + udf_pblk_t newblocknum; sector_t offset = 0; int8_t etype; struct udf_inode_info *iinfo = UDF_I(inode); udf_pblk_t goal = 0, pgoal = iinfo->i_location.logicalBlockNum; int lastblock = 0; bool isBeyondEOF; + int ret = 0; - *err = 0; - *new = 0; prev_epos.offset = udf_file_entry_alloc_offset(inode); prev_epos.block = iinfo->i_location; prev_epos.bh = NULL; cur_epos = next_epos = prev_epos; - b_off = (loff_t)block << inode->i_sb->s_blocksize_bits; + b_off = (loff_t)map->lblk << inode->i_sb->s_blocksize_bits; /* find the extent which contains the block we are looking for. alternate between laarr[0] and laarr[1] for locations of the @@ -757,15 +776,18 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, elen = EXT_RECORDED_ALLOCATED | ((elen + inode->i_sb->s_blocksize - 1) & ~(inode->i_sb->s_blocksize - 1)); + iinfo->i_lenExtents = + ALIGN(iinfo->i_lenExtents, + inode->i_sb->s_blocksize); udf_write_aext(inode, &cur_epos, &eloc, elen, 1); } - newblock = udf_get_lb_pblock(inode->i_sb, &eloc, offset); + map->oflags = UDF_BLK_MAPPED; + map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc, offset); goto out_free; } /* Are we beyond EOF and preallocated extent? */ if (etype == -1) { - int ret; loff_t hole_len; isBeyondEOF = true; @@ -785,26 +807,22 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Create extents for the hole between EOF and offset */ hole_len = (loff_t)offset << inode->i_blkbits; ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); - if (ret < 0) { - *err = ret; + if (ret < 0) goto out_free; - } c = 0; offset = 0; count += ret; - /* We are not covered by a preallocated extent? */ - if ((laarr[0].extLength & UDF_EXTENT_FLAG_MASK) != - EXT_NOT_RECORDED_ALLOCATED) { - /* Is there any real extent? - otherwise we overwrite - * the fake one... */ - if (count) - c = !c; - laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - inode->i_sb->s_blocksize; - memset(&laarr[c].extLocation, 0x00, - sizeof(struct kernel_lb_addr)); - count++; - } + /* + * Is there any real extent? - otherwise we overwrite the fake + * one... + */ + if (count) + c = !c; + laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | + inode->i_sb->s_blocksize; + memset(&laarr[c].extLocation, 0x00, + sizeof(struct kernel_lb_addr)); + count++; endnum = c + 1; lastblock = 1; } else { @@ -838,7 +856,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, if ((laarr[c].extLength >> 30) == (EXT_NOT_RECORDED_ALLOCATED >> 30)) newblocknum = laarr[c].extLocation.logicalBlockNum + offset; else { /* otherwise, allocate a new block */ - if (iinfo->i_next_alloc_block == block) + if (iinfo->i_next_alloc_block == map->lblk) goal = iinfo->i_next_alloc_goal; if (!goal) { @@ -848,11 +866,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, newblocknum = udf_new_block(inode->i_sb, inode, iinfo->i_location.partitionReferenceNum, - goal, err); - if (!newblocknum) { - *err = -ENOSPC; + goal, &ret); + if (!newblocknum) goto out_free; - } if (isBeyondEOF) iinfo->i_lenExtents += inode->i_sb->s_blocksize; } @@ -863,11 +879,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, * block */ udf_split_extents(inode, &c, offset, newblocknum, laarr, &endnum); - /* We preallocate blocks only for regular files. It also makes sense - * for directories but there's a problem when to drop the - * preallocation. We might use some delayed work for that but I feel - * it's overengineering for a filesystem like UDF. */ - if (S_ISREG(inode->i_mode)) + if (!(map->iflags & UDF_MAP_NOPREALLOC)) udf_prealloc_extents(inode, c, lastblock, laarr, &endnum); /* merge any continuous blocks in laarr */ @@ -876,28 +888,31 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* write back the new extents, inserting new extents if the new number * of extents is greater than the old number, and deleting extents if * the new number of extents is less than the old number */ - udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + ret = udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + if (ret < 0) + goto out_free; - newblock = udf_get_pblock(inode->i_sb, newblocknum, + map->pblk = udf_get_pblock(inode->i_sb, newblocknum, iinfo->i_location.partitionReferenceNum, 0); - if (!newblock) { - *err = -EIO; + if (!map->pblk) { + ret = -EFSCORRUPTED; goto out_free; } - *new = 1; - iinfo->i_next_alloc_block = block; - iinfo->i_next_alloc_goal = newblocknum; + map->oflags = UDF_BLK_NEW | UDF_BLK_MAPPED; + iinfo->i_next_alloc_block = map->lblk + 1; + iinfo->i_next_alloc_goal = newblocknum + 1; inode->i_ctime = current_time(inode); if (IS_SYNC(inode)) udf_sync_inode(inode); else mark_inode_dirty(inode); + ret = 0; out_free: brelse(prev_epos.bh); brelse(cur_epos.bh); brelse(next_epos.bh); - return newblock; + return ret; } static void udf_split_extents(struct inode *inode, int *c, int offset, @@ -1080,23 +1095,8 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, blocksize - 1) >> blocksize_bits)))) { if (((li->extLength & UDF_EXTENT_LENGTH_MASK) + - (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + - blocksize - 1) & ~UDF_EXTENT_LENGTH_MASK) { - lip1->extLength = (lip1->extLength - - (li->extLength & - UDF_EXTENT_LENGTH_MASK) + - UDF_EXTENT_LENGTH_MASK) & - ~(blocksize - 1); - li->extLength = (li->extLength & - UDF_EXTENT_FLAG_MASK) + - (UDF_EXTENT_LENGTH_MASK + 1) - - blocksize; - lip1->extLocation.logicalBlockNum = - li->extLocation.logicalBlockNum + - ((li->extLength & - UDF_EXTENT_LENGTH_MASK) >> - blocksize_bits); - } else { + (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + + blocksize - 1) <= UDF_EXTENT_LENGTH_MASK) { li->extLength = lip1->extLength + (((li->extLength & UDF_EXTENT_LENGTH_MASK) + @@ -1159,21 +1159,30 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, } } -static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, - int startnum, int endnum, - struct extent_position *epos) +static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, + int startnum, int endnum, + struct extent_position *epos) { int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; + int err; if (startnum > endnum) { for (i = 0; i < (startnum - endnum); i++) udf_delete_aext(inode, *epos); } else if (startnum < endnum) { for (i = 0; i < (endnum - startnum); i++) { - udf_insert_aext(inode, *epos, laarr[i].extLocation, - laarr[i].extLength); + err = udf_insert_aext(inode, *epos, + laarr[i].extLocation, + laarr[i].extLength); + /* + * If we fail here, we are likely corrupting the extent + * list and leaking blocks. At least stop early to + * limit the damage. + */ + if (err < 0) + return err; udf_next_aext(inode, epos, &laarr[i].extLocation, &laarr[i].extLength, 1); start++; @@ -1185,17 +1194,36 @@ static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } + return 0; } struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, int create, int *err) { struct buffer_head *bh = NULL; + struct udf_map_rq map = { + .lblk = block, + .iflags = UDF_MAP_NOPREALLOC | (create ? UDF_MAP_CREATE : 0), + }; - bh = udf_getblk(inode, block, create, err); - if (!bh) + *err = udf_map_block(inode, &map); + if (*err || !(map.oflags & UDF_BLK_MAPPED)) return NULL; + bh = sb_getblk(inode->i_sb, map.pblk); + if (!bh) { + *err = -ENOMEM; + return NULL; + } + if (map.oflags & UDF_BLK_NEW) { + lock_buffer(bh); + memset(bh->b_data, 0x00, inode->i_sb->s_blocksize); + set_buffer_uptodate(bh); + unlock_buffer(bh); + mark_buffer_dirty_inode(bh, inode); + return bh; + } + if (bh_read(bh, 0) >= 0) return bh; @@ -1206,7 +1234,7 @@ struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, int udf_setsize(struct inode *inode, loff_t newsize) { - int err; + int err = 0; struct udf_inode_info *iinfo; unsigned int bsize = i_blocksize(inode); @@ -1216,28 +1244,25 @@ int udf_setsize(struct inode *inode, loff_t newsize) if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; + filemap_invalidate_lock(inode->i_mapping); iinfo = UDF_I(inode); if (newsize > inode->i_size) { - down_write(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - if (bsize < + if (bsize >= (udf_file_entry_alloc_offset(inode) + newsize)) { - err = udf_expand_file_adinicb(inode); - if (err) - return err; down_write(&iinfo->i_data_sem); - } else { iinfo->i_lenAlloc = newsize; + up_write(&iinfo->i_data_sem); goto set_size; } + err = udf_expand_file_adinicb(inode); + if (err) + goto out_unlock; } err = udf_extend_file(inode, newsize); - if (err) { - up_write(&iinfo->i_data_sem); - return err; - } + if (err) + goto out_unlock; set_size: - up_write(&iinfo->i_data_sem); truncate_setsize(inode, newsize); } else { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { @@ -1254,14 +1279,14 @@ set_size: err = block_truncate_page(inode->i_mapping, newsize, udf_get_block); if (err) - return err; + goto out_unlock; truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); err = udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); if (err) - return err; + goto out_unlock; } update_time: inode->i_mtime = inode->i_ctime = current_time(inode); @@ -1269,7 +1294,9 @@ update_time: udf_sync_inode(inode); else mark_inode_dirty(inode); - return 0; +out_unlock: + filemap_invalidate_unlock(inode->i_mapping); + return err; } /* @@ -1381,6 +1408,7 @@ reread: ret = -EIO; goto out; } + iinfo->i_hidden = hidden_inode; iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; @@ -1537,10 +1565,7 @@ reread: case ICBTAG_FILE_TYPE_REGULAR: case ICBTAG_FILE_TYPE_UNDEF: case ICBTAG_FILE_TYPE_VAT20: - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - inode->i_data.a_ops = &udf_adinicb_aops; - else - inode->i_data.a_ops = &udf_aops; + inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; inode->i_mode |= S_IFREG; @@ -1671,7 +1696,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; struct udf_inode_info *iinfo = UDF_I(inode); - bh = udf_tgetblk(inode->i_sb, + bh = sb_getblk(inode->i_sb, udf_get_lb_pblock(inode->i_sb, &iinfo->i_location, 0)); if (!bh) { udf_debug("getblk failure\n"); @@ -1716,8 +1741,12 @@ static int udf_update_inode(struct inode *inode, int do_sync) if (S_ISDIR(inode->i_mode) && inode->i_nlink > 0) fe->fileLinkCount = cpu_to_le16(inode->i_nlink - 1); - else - fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + else { + if (iinfo->i_hidden) + fe->fileLinkCount = cpu_to_le16(0); + else + fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + } fe->informationLength = cpu_to_le64(inode->i_size); @@ -1888,8 +1917,13 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if (UDF_I(inode)->i_hidden != hidden_inode) { + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr)); err = udf_read_inode(inode, hidden_inode); @@ -1922,7 +1956,7 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, neloc.logicalBlockNum = block; neloc.partitionReferenceNum = epos->block.partitionReferenceNum; - bh = udf_tgetblk(sb, udf_get_lb_pblock(sb, &neloc, 0)); + bh = sb_getblk(sb, udf_get_lb_pblock(sb, &neloc, 0)); if (!bh) return -EIO; lock_buffer(bh); @@ -2139,7 +2173,7 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); block = udf_get_lb_pblock(inode->i_sb, &epos->block, 0); - epos->bh = udf_tread(inode->i_sb, block); + epos->bh = sb_bread(inode->i_sb, block); if (!epos->bh) { udf_debug("reading block %u failed!\n", block); return -1; @@ -2203,12 +2237,13 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, return etype; } -static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, - struct kernel_lb_addr neloc, uint32_t nelen) +static int udf_insert_aext(struct inode *inode, struct extent_position epos, + struct kernel_lb_addr neloc, uint32_t nelen) { struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; + int err; if (epos.bh) get_bh(epos.bh); @@ -2218,10 +2253,10 @@ static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, neloc = oeloc; nelen = (etype << 30) | oelen; } - udf_add_aext(inode, &epos, &neloc, nelen, 1); + err = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); - return (nelen >> 30); + return err; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) @@ -2339,28 +2374,3 @@ int8_t inode_bmap(struct inode *inode, sector_t block, return etype; } - -udf_pblk_t udf_block_map(struct inode *inode, sector_t block) -{ - struct kernel_lb_addr eloc; - uint32_t elen; - sector_t offset; - struct extent_position epos = {}; - udf_pblk_t ret; - - down_read(&UDF_I(inode)->i_data_sem); - - if (inode_bmap(inode, block, &epos, &eloc, &elen, &offset) == - (EXT_RECORDED_ALLOCATED >> 30)) - ret = udf_get_lb_pblock(inode->i_sb, &eloc, offset); - else - ret = 0; - - up_read(&UDF_I(inode)->i_data_sem); - brelse(epos.bh); - - if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_VARCONV)) - return udf_fixed_to_variable(ret); - else - return ret; -} diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c index 46d697172197..c87ed942d076 100644 --- a/fs/udf/lowlevel.c +++ b/fs/udf/lowlevel.c @@ -45,7 +45,7 @@ unsigned int udf_get_last_session(struct super_block *sb) return 0; } -unsigned long udf_get_last_block(struct super_block *sb) +udf_pblk_t udf_get_last_block(struct super_block *sb) { struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); unsigned long lblock = 0; @@ -54,8 +54,11 @@ unsigned long udf_get_last_block(struct super_block *sb) * The cdrom layer call failed or returned obviously bogus value? * Try using the device size... */ - if (!cdi || cdrom_get_last_written(cdi, &lblock) || lblock == 0) + if (!cdi || cdrom_get_last_written(cdi, &lblock) || lblock == 0) { + if (sb_bdev_nr_blocks(sb) > ~(udf_pblk_t)0) + return 0; lblock = sb_bdev_nr_blocks(sb); + } if (lblock) return lblock - 1; diff --git a/fs/udf/misc.c b/fs/udf/misc.c index 1614d308d0f0..3777468d06ce 100644 --- a/fs/udf/misc.c +++ b/fs/udf/misc.c @@ -28,22 +28,6 @@ #include "udf_i.h" #include "udf_sb.h" -struct buffer_head *udf_tgetblk(struct super_block *sb, udf_pblk_t block) -{ - if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV)) - return sb_getblk(sb, udf_fixed_to_variable(block)); - else - return sb_getblk(sb, block); -} - -struct buffer_head *udf_tread(struct super_block *sb, udf_pblk_t block) -{ - if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV)) - return sb_bread(sb, udf_fixed_to_variable(block)); - else - return sb_bread(sb, block); -} - struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size, uint32_t type, uint8_t loc) { @@ -216,7 +200,7 @@ struct buffer_head *udf_read_tagged(struct super_block *sb, uint32_t block, if (block == 0xFFFFFFFF) return NULL; - bh = udf_tread(sb, block); + bh = sb_bread(sb, block); if (!bh) { udf_err(sb, "read failed, block=%u, location=%u\n", block, location); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 7c95c549dd64..fd20423d3ed2 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -41,283 +41,93 @@ static inline int udf_match(int len1, const unsigned char *name1, int len2, return !memcmp(name1, name2, len1); } -int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, - struct fileIdentDesc *sfi, struct udf_fileident_bh *fibh, - uint8_t *impuse, uint8_t *fileident) -{ - uint16_t crclen = fibh->eoffset - fibh->soffset - sizeof(struct tag); - uint16_t crc; - int offset; - uint16_t liu = le16_to_cpu(cfi->lengthOfImpUse); - uint8_t lfi = cfi->lengthFileIdent; - int padlen = fibh->eoffset - fibh->soffset - liu - lfi - - sizeof(struct fileIdentDesc); - int adinicb = 0; - - if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - adinicb = 1; - - offset = fibh->soffset + sizeof(struct fileIdentDesc); - - if (impuse) { - if (adinicb || (offset + liu < 0)) { - memcpy((uint8_t *)sfi->impUse, impuse, liu); - } else if (offset >= 0) { - memcpy(fibh->ebh->b_data + offset, impuse, liu); - } else { - memcpy((uint8_t *)sfi->impUse, impuse, -offset); - memcpy(fibh->ebh->b_data, impuse - offset, - liu + offset); - } - } - - offset += liu; - - if (fileident) { - if (adinicb || (offset + lfi < 0)) { - memcpy(sfi->impUse + liu, fileident, lfi); - } else if (offset >= 0) { - memcpy(fibh->ebh->b_data + offset, fileident, lfi); - } else { - memcpy(sfi->impUse + liu, fileident, -offset); - memcpy(fibh->ebh->b_data, fileident - offset, - lfi + offset); - } - } - - offset += lfi; - - if (adinicb || (offset + padlen < 0)) { - memset(sfi->impUse + liu + lfi, 0x00, padlen); - } else if (offset >= 0) { - memset(fibh->ebh->b_data + offset, 0x00, padlen); - } else { - memset(sfi->impUse + liu + lfi, 0x00, -offset); - memset(fibh->ebh->b_data, 0x00, padlen + offset); - } - - crc = crc_itu_t(0, (uint8_t *)cfi + sizeof(struct tag), - sizeof(struct fileIdentDesc) - sizeof(struct tag)); - - if (fibh->sbh == fibh->ebh) { - crc = crc_itu_t(crc, (uint8_t *)sfi->impUse, - crclen + sizeof(struct tag) - - sizeof(struct fileIdentDesc)); - } else if (sizeof(struct fileIdentDesc) >= -fibh->soffset) { - crc = crc_itu_t(crc, fibh->ebh->b_data + - sizeof(struct fileIdentDesc) + - fibh->soffset, - crclen + sizeof(struct tag) - - sizeof(struct fileIdentDesc)); - } else { - crc = crc_itu_t(crc, (uint8_t *)sfi->impUse, - -fibh->soffset - sizeof(struct fileIdentDesc)); - crc = crc_itu_t(crc, fibh->ebh->b_data, fibh->eoffset); - } - - cfi->descTag.descCRC = cpu_to_le16(crc); - cfi->descTag.descCRCLength = cpu_to_le16(crclen); - cfi->descTag.tagChecksum = udf_tag_checksum(&cfi->descTag); - - if (adinicb || (sizeof(struct fileIdentDesc) <= -fibh->soffset)) { - memcpy((uint8_t *)sfi, (uint8_t *)cfi, - sizeof(struct fileIdentDesc)); - } else { - memcpy((uint8_t *)sfi, (uint8_t *)cfi, -fibh->soffset); - memcpy(fibh->ebh->b_data, (uint8_t *)cfi - fibh->soffset, - sizeof(struct fileIdentDesc) + fibh->soffset); - } - - if (adinicb) { - mark_inode_dirty(inode); - } else { - if (fibh->sbh != fibh->ebh) - mark_buffer_dirty_inode(fibh->ebh, inode); - mark_buffer_dirty_inode(fibh->sbh, inode); - } - inode_inc_iversion(inode); - - return 0; -} - /** - * udf_find_entry - find entry in given directory. + * udf_fiiter_find_entry - find entry in given directory. * * @dir: directory inode to search in * @child: qstr of the name - * @fibh: buffer head / inode with file identifier descriptor we found - * @cfi: found file identifier descriptor with given name + * @iter: iter to use for searching * * This function searches in the directory @dir for a file name @child. When - * found, @fibh points to the buffer head(s) (bh is NULL for in ICB - * directories) containing the file identifier descriptor (FID). In that case - * the function returns pointer to the FID in the buffer or inode - but note - * that FID may be split among two buffers (blocks) so accessing it via that - * pointer isn't easily possible. This pointer can be used only as an iterator - * for other directory manipulation functions. For inspection of the FID @cfi - * can be used - the found FID is copied there. + * found, @iter points to the position in the directory with given entry. * - * Returns pointer to FID, NULL when nothing found, or error code. + * Returns 0 on success, < 0 on error (including -ENOENT). */ -static struct fileIdentDesc *udf_find_entry(struct inode *dir, - const struct qstr *child, - struct udf_fileident_bh *fibh, - struct fileIdentDesc *cfi) +static int udf_fiiter_find_entry(struct inode *dir, const struct qstr *child, + struct udf_fileident_iter *iter) { - struct fileIdentDesc *fi = NULL; - loff_t f_pos; - udf_pblk_t block; int flen; - unsigned char *fname = NULL, *copy_name = NULL; - unsigned char *nameptr; - uint8_t lfi; - uint16_t liu; - loff_t size; - struct kernel_lb_addr eloc; - uint32_t elen; - sector_t offset; - struct extent_position epos = {}; - struct udf_inode_info *dinfo = UDF_I(dir); + unsigned char *fname = NULL; + struct super_block *sb = dir->i_sb; int isdotdot = child->len == 2 && child->name[0] == '.' && child->name[1] == '.'; - struct super_block *sb = dir->i_sb; - - size = udf_ext0_offset(dir) + dir->i_size; - f_pos = udf_ext0_offset(dir); - - fibh->sbh = fibh->ebh = NULL; - fibh->soffset = fibh->eoffset = f_pos & (sb->s_blocksize - 1); - if (dinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - if (inode_bmap(dir, f_pos >> sb->s_blocksize_bits, &epos, - &eloc, &elen, &offset) != (EXT_RECORDED_ALLOCATED >> 30)) { - fi = ERR_PTR(-EIO); - goto out_err; - } - - block = udf_get_lb_pblock(sb, &eloc, offset); - if ((++offset << sb->s_blocksize_bits) < elen) { - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - epos.offset -= sizeof(struct short_ad); - else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - epos.offset -= sizeof(struct long_ad); - } else - offset = 0; - - fibh->sbh = fibh->ebh = udf_tread(sb, block); - if (!fibh->sbh) { - fi = ERR_PTR(-EIO); - goto out_err; - } - } + int ret; fname = kmalloc(UDF_NAME_LEN, GFP_NOFS); - if (!fname) { - fi = ERR_PTR(-ENOMEM); - goto out_err; - } - - while (f_pos < size) { - fi = udf_fileident_read(dir, &f_pos, fibh, cfi, &epos, &eloc, - &elen, &offset); - if (!fi) { - fi = ERR_PTR(-EIO); - goto out_err; - } - - liu = le16_to_cpu(cfi->lengthOfImpUse); - lfi = cfi->lengthFileIdent; - - if (fibh->sbh == fibh->ebh) { - nameptr = udf_get_fi_ident(fi); - } else { - int poffset; /* Unpaded ending offset */ - - poffset = fibh->soffset + sizeof(struct fileIdentDesc) + - liu + lfi; - - if (poffset >= lfi) - nameptr = (uint8_t *)(fibh->ebh->b_data + - poffset - lfi); - else { - if (!copy_name) { - copy_name = kmalloc(UDF_NAME_LEN_CS0, - GFP_NOFS); - if (!copy_name) { - fi = ERR_PTR(-ENOMEM); - goto out_err; - } - } - nameptr = copy_name; - memcpy(nameptr, udf_get_fi_ident(fi), - lfi - poffset); - memcpy(nameptr + lfi - poffset, - fibh->ebh->b_data, poffset); - } - } + if (!fname) + return -ENOMEM; - if ((cfi->fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) { + for (ret = udf_fiiter_init(iter, dir, 0); + !ret && iter->pos < dir->i_size; + ret = udf_fiiter_advance(iter)) { + if (iter->fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) continue; } - if ((cfi->fileCharacteristics & FID_FILE_CHAR_HIDDEN) != 0) { + if (iter->fi.fileCharacteristics & FID_FILE_CHAR_HIDDEN) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) continue; } - if ((cfi->fileCharacteristics & FID_FILE_CHAR_PARENT) && + if ((iter->fi.fileCharacteristics & FID_FILE_CHAR_PARENT) && isdotdot) goto out_ok; - if (!lfi) + if (!iter->fi.lengthFileIdent) continue; - flen = udf_get_filename(sb, nameptr, lfi, fname, UDF_NAME_LEN); + flen = udf_get_filename(sb, iter->name, + iter->fi.lengthFileIdent, fname, UDF_NAME_LEN); if (flen < 0) { - fi = ERR_PTR(flen); + ret = flen; goto out_err; } if (udf_match(flen, fname, child->len, child->name)) goto out_ok; } + if (!ret) + ret = -ENOENT; - fi = NULL; out_err: - if (fibh->sbh != fibh->ebh) - brelse(fibh->ebh); - brelse(fibh->sbh); + udf_fiiter_release(iter); out_ok: - brelse(epos.bh); kfree(fname); - kfree(copy_name); - return fi; + return ret; } static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; - struct fileIdentDesc cfi; - struct udf_fileident_bh fibh; - struct fileIdentDesc *fi; + struct udf_fileident_iter iter; + int err; if (dentry->d_name.len > UDF_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi); - if (IS_ERR(fi)) - return ERR_CAST(fi); + err = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); + if (err < 0 && err != -ENOENT) + return ERR_PTR(err); - if (fi) { + if (err == 0) { struct kernel_lb_addr loc; - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); + loc = lelb_to_cpu(iter.fi.icb.extLocation); + udf_fiiter_release(&iter); - loc = lelb_to_cpu(cfi.icb.extLocation); inode = udf_iget(dir->i_sb, &loc); if (IS_ERR(inode)) return ERR_CAST(inode); @@ -326,287 +136,249 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, return d_splice_alias(inode, dentry); } -static struct fileIdentDesc *udf_add_entry(struct inode *dir, - struct dentry *dentry, - struct udf_fileident_bh *fibh, - struct fileIdentDesc *cfi, int *err) +static int udf_expand_dir_adinicb(struct inode *inode, udf_pblk_t *block) { - struct super_block *sb = dir->i_sb; - struct fileIdentDesc *fi = NULL; - unsigned char *name = NULL; - int namelen; - loff_t f_pos; - loff_t size = udf_ext0_offset(dir) + dir->i_size; - int nfidlen; - udf_pblk_t block; + udf_pblk_t newblock; + struct buffer_head *dbh = NULL; struct kernel_lb_addr eloc; - uint32_t elen = 0; - sector_t offset; - struct extent_position epos = {}; - struct udf_inode_info *dinfo; + struct extent_position epos; + uint8_t alloctype; + struct udf_inode_info *iinfo = UDF_I(inode); + struct udf_fileident_iter iter; + uint8_t *impuse; + int ret; - fibh->sbh = fibh->ebh = NULL; - name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS); - if (!name) { - *err = -ENOMEM; - goto out_err; - } + if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) + alloctype = ICBTAG_FLAG_AD_SHORT; + else + alloctype = ICBTAG_FLAG_AD_LONG; - if (dentry) { - if (!dentry->d_name.len) { - *err = -EINVAL; - goto out_err; - } - namelen = udf_put_filename(sb, dentry->d_name.name, - dentry->d_name.len, - name, UDF_NAME_LEN_CS0); - if (!namelen) { - *err = -ENAMETOOLONG; - goto out_err; - } - } else { - namelen = 0; + if (!inode->i_size) { + iinfo->i_alloc_type = alloctype; + mark_inode_dirty(inode); + return 0; } - nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD); - - f_pos = udf_ext0_offset(dir); - - fibh->soffset = fibh->eoffset = f_pos & (dir->i_sb->s_blocksize - 1); - dinfo = UDF_I(dir); - if (dinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - if (inode_bmap(dir, f_pos >> dir->i_sb->s_blocksize_bits, &epos, - &eloc, &elen, &offset) != (EXT_RECORDED_ALLOCATED >> 30)) { - block = udf_get_lb_pblock(dir->i_sb, - &dinfo->i_location, 0); - fibh->soffset = fibh->eoffset = sb->s_blocksize; - goto add; - } - block = udf_get_lb_pblock(dir->i_sb, &eloc, offset); - if ((++offset << dir->i_sb->s_blocksize_bits) < elen) { - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - epos.offset -= sizeof(struct short_ad); - else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - epos.offset -= sizeof(struct long_ad); - } else - offset = 0; - - fibh->sbh = fibh->ebh = udf_tread(dir->i_sb, block); - if (!fibh->sbh) { - *err = -EIO; - goto out_err; - } + /* alloc block, and copy data to it */ + *block = udf_new_block(inode->i_sb, inode, + iinfo->i_location.partitionReferenceNum, + iinfo->i_location.logicalBlockNum, &ret); + if (!(*block)) + return ret; + newblock = udf_get_pblock(inode->i_sb, *block, + iinfo->i_location.partitionReferenceNum, + 0); + if (newblock == 0xffffffff) + return -EFSCORRUPTED; + dbh = sb_getblk(inode->i_sb, newblock); + if (!dbh) + return -ENOMEM; + lock_buffer(dbh); + memcpy(dbh->b_data, iinfo->i_data, inode->i_size); + memset(dbh->b_data + inode->i_size, 0, + inode->i_sb->s_blocksize - inode->i_size); + set_buffer_uptodate(dbh); + unlock_buffer(dbh); + + /* Drop inline data, add block instead */ + iinfo->i_alloc_type = alloctype; + memset(iinfo->i_data + iinfo->i_lenEAttr, 0, iinfo->i_lenAlloc); + iinfo->i_lenAlloc = 0; + eloc.logicalBlockNum = *block; + eloc.partitionReferenceNum = + iinfo->i_location.partitionReferenceNum; + iinfo->i_lenExtents = inode->i_size; + epos.bh = NULL; + epos.block = iinfo->i_location; + epos.offset = udf_file_entry_alloc_offset(inode); + ret = udf_add_aext(inode, &epos, &eloc, inode->i_size, 0); + brelse(epos.bh); + if (ret < 0) { + brelse(dbh); + udf_free_blocks(inode->i_sb, inode, &eloc, 0, 1); + return ret; + } + mark_inode_dirty(inode); - block = dinfo->i_location.logicalBlockNum; + /* Now fixup tags in moved directory entries */ + for (ret = udf_fiiter_init(&iter, inode, 0); + !ret && iter.pos < inode->i_size; + ret = udf_fiiter_advance(&iter)) { + iter.fi.descTag.tagLocation = cpu_to_le32(*block); + if (iter.fi.lengthOfImpUse != cpu_to_le16(0)) + impuse = dbh->b_data + iter.pos + + sizeof(struct fileIdentDesc); + else + impuse = NULL; + udf_fiiter_write_fi(&iter, impuse); } + brelse(dbh); + /* + * We don't expect the iteration to fail as the directory has been + * already verified to be correct + */ + WARN_ON_ONCE(ret); + udf_fiiter_release(&iter); - while (f_pos < size) { - fi = udf_fileident_read(dir, &f_pos, fibh, cfi, &epos, &eloc, - &elen, &offset); + return 0; +} - if (!fi) { - *err = -EIO; - goto out_err; - } +static int udf_fiiter_add_entry(struct inode *dir, struct dentry *dentry, + struct udf_fileident_iter *iter) +{ + struct udf_inode_info *dinfo = UDF_I(dir); + int nfidlen, namelen = 0; + int ret; + int off, blksize = 1 << dir->i_blkbits; + udf_pblk_t block; + char name[UDF_NAME_LEN_CS0]; + + if (dentry) { + if (!dentry->d_name.len) + return -EINVAL; + namelen = udf_put_filename(dir->i_sb, dentry->d_name.name, + dentry->d_name.len, + name, UDF_NAME_LEN_CS0); + if (!namelen) + return -ENAMETOOLONG; + } + nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD); - if ((cfi->fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) { - if (udf_dir_entry_len(cfi) == nfidlen) { - cfi->descTag.tagSerialNum = cpu_to_le16(1); - cfi->fileVersionNum = cpu_to_le16(1); - cfi->fileCharacteristics = 0; - cfi->lengthFileIdent = namelen; - cfi->lengthOfImpUse = cpu_to_le16(0); - if (!udf_write_fi(dir, cfi, fi, fibh, NULL, - name)) - goto out_ok; - else { - *err = -EIO; - goto out_err; - } + for (ret = udf_fiiter_init(iter, dir, 0); + !ret && iter->pos < dir->i_size; + ret = udf_fiiter_advance(iter)) { + if (iter->fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { + if (udf_dir_entry_len(&iter->fi) == nfidlen) { + iter->fi.descTag.tagSerialNum = cpu_to_le16(1); + iter->fi.fileVersionNum = cpu_to_le16(1); + iter->fi.fileCharacteristics = 0; + iter->fi.lengthFileIdent = namelen; + iter->fi.lengthOfImpUse = cpu_to_le16(0); + memcpy(iter->namebuf, name, namelen); + iter->name = iter->namebuf; + return 0; } } } - -add: - f_pos += nfidlen; - + if (ret) { + udf_fiiter_release(iter); + return ret; + } if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && - sb->s_blocksize - fibh->eoffset < nfidlen) { - brelse(epos.bh); - epos.bh = NULL; - fibh->soffset -= udf_ext0_offset(dir); - fibh->eoffset -= udf_ext0_offset(dir); - f_pos -= udf_ext0_offset(dir); - if (fibh->sbh != fibh->ebh) - brelse(fibh->ebh); - brelse(fibh->sbh); - fibh->sbh = fibh->ebh = - udf_expand_dir_adinicb(dir, &block, err); - if (!fibh->sbh) - goto out_err; - epos.block = dinfo->i_location; - epos.offset = udf_file_entry_alloc_offset(dir); - /* Load extent udf_expand_dir_adinicb() has created */ - udf_current_aext(dir, &epos, &eloc, &elen, 1); + blksize - udf_ext0_offset(dir) - iter->pos < nfidlen) { + udf_fiiter_release(iter); + ret = udf_expand_dir_adinicb(dir, &block); + if (ret) + return ret; + ret = udf_fiiter_init(iter, dir, dir->i_size); + if (ret < 0) + return ret; } - /* Entry fits into current block? */ - if (sb->s_blocksize - fibh->eoffset >= nfidlen) { - fibh->soffset = fibh->eoffset; - fibh->eoffset += nfidlen; - if (fibh->sbh != fibh->ebh) { - brelse(fibh->sbh); - fibh->sbh = fibh->ebh; - } - - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - block = dinfo->i_location.logicalBlockNum; - fi = (struct fileIdentDesc *) - (dinfo->i_data + fibh->soffset - - udf_ext0_offset(dir) + - dinfo->i_lenEAttr); - } else { - block = eloc.logicalBlockNum + - ((elen - 1) >> - dir->i_sb->s_blocksize_bits); - fi = (struct fileIdentDesc *) - (fibh->sbh->b_data + fibh->soffset); - } + /* Get blocknumber to use for entry tag */ + if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + block = dinfo->i_location.logicalBlockNum; } else { - /* Round up last extent in the file */ - elen = (elen + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1); - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - epos.offset -= sizeof(struct short_ad); - else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - epos.offset -= sizeof(struct long_ad); - udf_write_aext(dir, &epos, &eloc, elen, 1); - dinfo->i_lenExtents = (dinfo->i_lenExtents + sb->s_blocksize - - 1) & ~(sb->s_blocksize - 1); - - fibh->soffset = fibh->eoffset - sb->s_blocksize; - fibh->eoffset += nfidlen - sb->s_blocksize; - if (fibh->sbh != fibh->ebh) { - brelse(fibh->sbh); - fibh->sbh = fibh->ebh; - } + block = iter->eloc.logicalBlockNum + + ((iter->elen - 1) >> dir->i_blkbits); + } + off = iter->pos & (blksize - 1); + if (!off) + off = blksize; + /* Entry fits into current block? */ + if (blksize - udf_ext0_offset(dir) - off >= nfidlen) + goto store_fi; - block = eloc.logicalBlockNum + ((elen - 1) >> - dir->i_sb->s_blocksize_bits); - fibh->ebh = udf_bread(dir, - f_pos >> dir->i_sb->s_blocksize_bits, 1, err); - if (!fibh->ebh) - goto out_err; - /* Extents could have been merged, invalidate our position */ - brelse(epos.bh); - epos.bh = NULL; - epos.block = dinfo->i_location; - epos.offset = udf_file_entry_alloc_offset(dir); - - if (!fibh->soffset) { - /* Find the freshly allocated block */ - while (udf_next_aext(dir, &epos, &eloc, &elen, 1) == - (EXT_RECORDED_ALLOCATED >> 30)) - ; - block = eloc.logicalBlockNum + ((elen - 1) >> - dir->i_sb->s_blocksize_bits); - brelse(fibh->sbh); - fibh->sbh = fibh->ebh; - fi = (struct fileIdentDesc *)(fibh->sbh->b_data); - } else { - fi = (struct fileIdentDesc *) - (fibh->sbh->b_data + sb->s_blocksize + - fibh->soffset); - } + ret = udf_fiiter_append_blk(iter); + if (ret) { + udf_fiiter_release(iter); + return ret; } - memset(cfi, 0, sizeof(struct fileIdentDesc)); - if (UDF_SB(sb)->s_udfrev >= 0x0200) - udf_new_tag((char *)cfi, TAG_IDENT_FID, 3, 1, block, + /* Entry will be completely in the new block? Update tag location... */ + if (!(iter->pos & (blksize - 1))) + block = iter->eloc.logicalBlockNum + + ((iter->elen - 1) >> dir->i_blkbits); +store_fi: + memset(&iter->fi, 0, sizeof(struct fileIdentDesc)); + if (UDF_SB(dir->i_sb)->s_udfrev >= 0x0200) + udf_new_tag((char *)(&iter->fi), TAG_IDENT_FID, 3, 1, block, sizeof(struct tag)); else - udf_new_tag((char *)cfi, TAG_IDENT_FID, 2, 1, block, + udf_new_tag((char *)(&iter->fi), TAG_IDENT_FID, 2, 1, block, sizeof(struct tag)); - cfi->fileVersionNum = cpu_to_le16(1); - cfi->lengthFileIdent = namelen; - cfi->lengthOfImpUse = cpu_to_le16(0); - if (!udf_write_fi(dir, cfi, fi, fibh, NULL, name)) { - dir->i_size += nfidlen; - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - dinfo->i_lenAlloc += nfidlen; - else { - /* Find the last extent and truncate it to proper size */ - while (udf_next_aext(dir, &epos, &eloc, &elen, 1) == - (EXT_RECORDED_ALLOCATED >> 30)) - ; - elen -= dinfo->i_lenExtents - dir->i_size; - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - epos.offset -= sizeof(struct short_ad); - else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - epos.offset -= sizeof(struct long_ad); - udf_write_aext(dir, &epos, &eloc, elen, 1); - dinfo->i_lenExtents = dir->i_size; - } - - mark_inode_dirty(dir); - goto out_ok; + iter->fi.fileVersionNum = cpu_to_le16(1); + iter->fi.lengthFileIdent = namelen; + iter->fi.lengthOfImpUse = cpu_to_le16(0); + memcpy(iter->namebuf, name, namelen); + iter->name = iter->namebuf; + + dir->i_size += nfidlen; + if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + dinfo->i_lenAlloc += nfidlen; } else { - *err = -EIO; - goto out_err; + /* Truncate last extent to proper size */ + udf_fiiter_update_elen(iter, iter->elen - + (dinfo->i_lenExtents - dir->i_size)); } + mark_inode_dirty(dir); -out_err: - fi = NULL; - if (fibh->sbh != fibh->ebh) - brelse(fibh->ebh); - brelse(fibh->sbh); -out_ok: - brelse(epos.bh); - kfree(name); - return fi; + return 0; } -static int udf_delete_entry(struct inode *inode, struct fileIdentDesc *fi, - struct udf_fileident_bh *fibh, - struct fileIdentDesc *cfi) +static void udf_fiiter_delete_entry(struct udf_fileident_iter *iter) { - cfi->fileCharacteristics |= FID_FILE_CHAR_DELETED; + iter->fi.fileCharacteristics |= FID_FILE_CHAR_DELETED; + + if (UDF_QUERY_FLAG(iter->dir->i_sb, UDF_FLAG_STRICT)) + memset(&iter->fi.icb, 0x00, sizeof(struct long_ad)); + + udf_fiiter_write_fi(iter, NULL); +} - if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT)) - memset(&(cfi->icb), 0x00, sizeof(struct long_ad)); +static void udf_add_fid_counter(struct super_block *sb, bool dir, int val) +{ + struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); - return udf_write_fi(inode, cfi, fi, fibh, NULL, NULL); + if (!lvidiu) + return; + mutex_lock(&UDF_SB(sb)->s_alloc_mutex); + if (dir) + le32_add_cpu(&lvidiu->numDirs, val); + else + le32_add_cpu(&lvidiu->numFiles, val); + udf_updated_lvid(sb); + mutex_unlock(&UDF_SB(sb)->s_alloc_mutex); } static int udf_add_nondir(struct dentry *dentry, struct inode *inode) { struct udf_inode_info *iinfo = UDF_I(inode); struct inode *dir = d_inode(dentry->d_parent); - struct udf_fileident_bh fibh; - struct fileIdentDesc cfi, *fi; + struct udf_fileident_iter iter; int err; - fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err); - if (unlikely(!fi)) { + err = udf_fiiter_add_entry(dir, dentry, &iter); + if (err) { inode_dec_link_count(inode); discard_new_inode(inode); return err; } - cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); - cfi.icb.extLocation = cpu_to_lelb(iinfo->i_location); - *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = + iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); + iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); + *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); - udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); + udf_fiiter_write_fi(&iter, NULL); dir->i_ctime = dir->i_mtime = current_time(dir); mark_inode_dirty(dir); - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); + udf_fiiter_release(&iter); + udf_add_fid_counter(dir->i_sb, false, 1); d_instantiate_new(dentry, inode); return 0; } -static int udf_create(struct user_namespace *mnt_userns, struct inode *dir, +static int udf_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode = udf_new_inode(dir, mode); @@ -614,10 +386,7 @@ static int udf_create(struct user_namespace *mnt_userns, struct inode *dir, if (IS_ERR(inode)) return PTR_ERR(inode); - if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - inode->i_data.a_ops = &udf_adinicb_aops; - else - inode->i_data.a_ops = &udf_aops; + inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; mark_inode_dirty(inode); @@ -625,7 +394,7 @@ static int udf_create(struct user_namespace *mnt_userns, struct inode *dir, return udf_add_nondir(dentry, inode); } -static int udf_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +static int udf_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode = udf_new_inode(dir, mode); @@ -633,10 +402,7 @@ static int udf_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, if (IS_ERR(inode)) return PTR_ERR(inode); - if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - inode->i_data.a_ops = &udf_adinicb_aops; - else - inode->i_data.a_ops = &udf_aops; + inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; mark_inode_dirty(inode); @@ -645,7 +411,7 @@ static int udf_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return finish_open_simple(file, 0); } -static int udf_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int udf_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; @@ -661,12 +427,11 @@ static int udf_mknod(struct user_namespace *mnt_userns, struct inode *dir, return udf_add_nondir(dentry, inode); } -static int udf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; - struct udf_fileident_bh fibh; - struct fileIdentDesc cfi, *fi; + struct udf_fileident_iter iter; int err; struct udf_inode_info *dinfo = UDF_I(dir); struct udf_inode_info *iinfo; @@ -678,183 +443,113 @@ static int udf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, iinfo = UDF_I(inode); inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; - fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err); - if (!fi) { - inode_dec_link_count(inode); + err = udf_fiiter_add_entry(inode, NULL, &iter); + if (err) { + clear_nlink(inode); discard_new_inode(inode); - goto out; + return err; } set_nlink(inode, 2); - cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); - cfi.icb.extLocation = cpu_to_lelb(dinfo->i_location); - *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = + iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); + iter.fi.icb.extLocation = cpu_to_lelb(dinfo->i_location); + *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(dinfo->i_unique & 0x00000000FFFFFFFFUL); - cfi.fileCharacteristics = + iter.fi.fileCharacteristics = FID_FILE_CHAR_DIRECTORY | FID_FILE_CHAR_PARENT; - udf_write_fi(inode, &cfi, fi, &fibh, NULL, NULL); - brelse(fibh.sbh); + udf_fiiter_write_fi(&iter, NULL); + udf_fiiter_release(&iter); mark_inode_dirty(inode); - fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err); - if (!fi) { + err = udf_fiiter_add_entry(dir, dentry, &iter); + if (err) { clear_nlink(inode); - mark_inode_dirty(inode); discard_new_inode(inode); - goto out; + return err; } - cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); - cfi.icb.extLocation = cpu_to_lelb(iinfo->i_location); - *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = + iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); + iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); + *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); - cfi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; - udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); + iter.fi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; + udf_fiiter_write_fi(&iter, NULL); + udf_fiiter_release(&iter); + udf_add_fid_counter(dir->i_sb, true, 1); inc_nlink(dir); dir->i_ctime = dir->i_mtime = current_time(dir); mark_inode_dirty(dir); d_instantiate_new(dentry, inode); - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - err = 0; -out: - return err; + return 0; } static int empty_dir(struct inode *dir) { - struct fileIdentDesc *fi, cfi; - struct udf_fileident_bh fibh; - loff_t f_pos; - loff_t size = udf_ext0_offset(dir) + dir->i_size; - udf_pblk_t block; - struct kernel_lb_addr eloc; - uint32_t elen; - sector_t offset; - struct extent_position epos = {}; - struct udf_inode_info *dinfo = UDF_I(dir); - - f_pos = udf_ext0_offset(dir); - fibh.soffset = fibh.eoffset = f_pos & (dir->i_sb->s_blocksize - 1); - - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - fibh.sbh = fibh.ebh = NULL; - else if (inode_bmap(dir, f_pos >> dir->i_sb->s_blocksize_bits, - &epos, &eloc, &elen, &offset) == - (EXT_RECORDED_ALLOCATED >> 30)) { - block = udf_get_lb_pblock(dir->i_sb, &eloc, offset); - if ((++offset << dir->i_sb->s_blocksize_bits) < elen) { - if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - epos.offset -= sizeof(struct short_ad); - else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - epos.offset -= sizeof(struct long_ad); - } else - offset = 0; - - fibh.sbh = fibh.ebh = udf_tread(dir->i_sb, block); - if (!fibh.sbh) { - brelse(epos.bh); + struct udf_fileident_iter iter; + int ret; + + for (ret = udf_fiiter_init(&iter, dir, 0); + !ret && iter.pos < dir->i_size; + ret = udf_fiiter_advance(&iter)) { + if (iter.fi.lengthFileIdent && + !(iter.fi.fileCharacteristics & FID_FILE_CHAR_DELETED)) { + udf_fiiter_release(&iter); return 0; } - } else { - brelse(epos.bh); - return 0; } - - while (f_pos < size) { - fi = udf_fileident_read(dir, &f_pos, &fibh, &cfi, &epos, &eloc, - &elen, &offset); - if (!fi) { - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - brelse(epos.bh); - return 0; - } - - if (cfi.lengthFileIdent && - (cfi.fileCharacteristics & FID_FILE_CHAR_DELETED) == 0) { - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - brelse(epos.bh); - return 0; - } - } - - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - brelse(epos.bh); + udf_fiiter_release(&iter); return 1; } static int udf_rmdir(struct inode *dir, struct dentry *dentry) { - int retval; + int ret; struct inode *inode = d_inode(dentry); - struct udf_fileident_bh fibh; - struct fileIdentDesc *fi, cfi; + struct udf_fileident_iter iter; struct kernel_lb_addr tloc; - retval = -ENOENT; - fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi); - if (IS_ERR_OR_NULL(fi)) { - if (fi) - retval = PTR_ERR(fi); + ret = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); + if (ret) goto out; - } - retval = -EIO; - tloc = lelb_to_cpu(cfi.icb.extLocation); + ret = -EFSCORRUPTED; + tloc = lelb_to_cpu(iter.fi.icb.extLocation); if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino) goto end_rmdir; - retval = -ENOTEMPTY; + ret = -ENOTEMPTY; if (!empty_dir(inode)) goto end_rmdir; - retval = udf_delete_entry(dir, fi, &fibh, &cfi); - if (retval) - goto end_rmdir; + udf_fiiter_delete_entry(&iter); if (inode->i_nlink != 2) udf_warn(inode->i_sb, "empty directory has nlink != 2 (%u)\n", inode->i_nlink); clear_nlink(inode); inode->i_size = 0; inode_dec_link_count(dir); + udf_add_fid_counter(dir->i_sb, true, -1); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); mark_inode_dirty(dir); - + ret = 0; end_rmdir: - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - + udf_fiiter_release(&iter); out: - return retval; + return ret; } static int udf_unlink(struct inode *dir, struct dentry *dentry) { - int retval; + int ret; struct inode *inode = d_inode(dentry); - struct udf_fileident_bh fibh; - struct fileIdentDesc *fi; - struct fileIdentDesc cfi; + struct udf_fileident_iter iter; struct kernel_lb_addr tloc; - retval = -ENOENT; - fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi); - - if (IS_ERR_OR_NULL(fi)) { - if (fi) - retval = PTR_ERR(fi); + ret = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); + if (ret) goto out; - } - retval = -EIO; - tloc = lelb_to_cpu(cfi.icb.extLocation); + ret = -EFSCORRUPTED; + tloc = lelb_to_cpu(iter.fi.icb.extLocation); if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino) goto end_unlink; @@ -863,25 +558,20 @@ static int udf_unlink(struct inode *dir, struct dentry *dentry) inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } - retval = udf_delete_entry(dir, fi, &fibh, &cfi); - if (retval) - goto end_unlink; + udf_fiiter_delete_entry(&iter); dir->i_ctime = dir->i_mtime = current_time(dir); mark_inode_dirty(dir); inode_dec_link_count(inode); + udf_add_fid_counter(dir->i_sb, false, -1); inode->i_ctime = dir->i_ctime; - retval = 0; - + ret = 0; end_unlink: - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - + udf_fiiter_release(&iter); out: - return retval; + return ret; } -static int udf_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int udf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode = udf_new_inode(dir, S_IFLNK | 0777); @@ -929,15 +619,20 @@ static int udf_symlink(struct user_namespace *mnt_userns, struct inode *dir, iinfo->i_location.partitionReferenceNum; bsize = sb->s_blocksize; iinfo->i_lenExtents = bsize; - udf_add_aext(inode, &epos, &eloc, bsize, 0); + err = udf_add_aext(inode, &epos, &eloc, bsize, 0); brelse(epos.bh); + if (err < 0) { + udf_free_blocks(sb, inode, &eloc, 0, 1); + goto out_no_entry; + } block = udf_get_pblock(sb, block, iinfo->i_location.partitionReferenceNum, 0); - epos.bh = udf_tgetblk(sb, block); + epos.bh = sb_getblk(sb, block); if (unlikely(!epos.bh)) { err = -ENOMEM; + udf_free_blocks(sb, inode, &eloc, 0, 1); goto out_no_entry; } lock_buffer(epos.bh); @@ -1038,28 +733,23 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); - struct udf_fileident_bh fibh; - struct fileIdentDesc cfi, *fi; + struct udf_fileident_iter iter; int err; - fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err); - if (!fi) { + err = udf_fiiter_add_entry(dir, dentry, &iter); + if (err) return err; - } - cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); - cfi.icb.extLocation = cpu_to_lelb(UDF_I(inode)->i_location); + iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); + iter.fi.icb.extLocation = cpu_to_lelb(UDF_I(inode)->i_location); if (UDF_SB(inode->i_sb)->s_lvid_bh) { - *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = + *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(lvid_get_unique_id(inode->i_sb)); } - udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); - if (UDF_I(dir)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - mark_inode_dirty(dir); + udf_fiiter_write_fi(&iter, NULL); + udf_fiiter_release(&iter); - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); inc_nlink(inode); + udf_add_fid_counter(dir->i_sb, false, 1); inode->i_ctime = current_time(inode); mark_inode_dirty(inode); dir->i_ctime = dir->i_mtime = current_time(dir); @@ -1073,84 +763,81 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, /* Anybody can rename anything with this: the permission checks are left to the * higher-level routines. */ -static int udf_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); - struct udf_fileident_bh ofibh, nfibh; - struct fileIdentDesc *ofi = NULL, *nfi = NULL, *dir_fi = NULL; - struct fileIdentDesc ocfi, ncfi; - struct buffer_head *dir_bh = NULL; - int retval = -ENOENT; + struct udf_fileident_iter oiter, niter, diriter; + bool has_diriter = false; + int retval; struct kernel_lb_addr tloc; - struct udf_inode_info *old_iinfo = UDF_I(old_inode); if (flags & ~RENAME_NOREPLACE) return -EINVAL; - ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); - if (!ofi || IS_ERR(ofi)) { - if (IS_ERR(ofi)) - retval = PTR_ERR(ofi); - goto end_rename; - } - - if (ofibh.sbh != ofibh.ebh) - brelse(ofibh.ebh); - - brelse(ofibh.sbh); - tloc = lelb_to_cpu(ocfi.icb.extLocation); - if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) - goto end_rename; + retval = udf_fiiter_find_entry(old_dir, &old_dentry->d_name, &oiter); + if (retval) + return retval; - nfi = udf_find_entry(new_dir, &new_dentry->d_name, &nfibh, &ncfi); - if (IS_ERR(nfi)) { - retval = PTR_ERR(nfi); - goto end_rename; - } - if (nfi && !new_inode) { - if (nfibh.sbh != nfibh.ebh) - brelse(nfibh.ebh); - brelse(nfibh.sbh); - nfi = NULL; + tloc = lelb_to_cpu(oiter.fi.icb.extLocation); + if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) { + retval = -ENOENT; + goto out_oiter; } - if (S_ISDIR(old_inode->i_mode)) { - int offset = udf_ext0_offset(old_inode); + if (S_ISDIR(old_inode->i_mode)) { if (new_inode) { retval = -ENOTEMPTY; if (!empty_dir(new_inode)) - goto end_rename; + goto out_oiter; + } + /* + * We need to protect against old_inode getting converted from + * ICB to normal directory. + */ + inode_lock_nested(old_inode, I_MUTEX_NONDIR2); + retval = udf_fiiter_find_entry(old_inode, &dotdot_name, + &diriter); + if (retval == -ENOENT) { + udf_err(old_inode->i_sb, + "directory (ino %lu) has no '..' entry\n", + old_inode->i_ino); + retval = -EFSCORRUPTED; } - retval = -EIO; - if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - dir_fi = udf_get_fileident( - old_iinfo->i_data - - (old_iinfo->i_efe ? - sizeof(struct extendedFileEntry) : - sizeof(struct fileEntry)), - old_inode->i_sb->s_blocksize, &offset); - } else { - dir_bh = udf_bread(old_inode, 0, 0, &retval); - if (!dir_bh) - goto end_rename; - dir_fi = udf_get_fileident(dir_bh->b_data, - old_inode->i_sb->s_blocksize, &offset); + if (retval) { + inode_unlock(old_inode); + goto out_oiter; } - if (!dir_fi) - goto end_rename; - tloc = lelb_to_cpu(dir_fi->icb.extLocation); + has_diriter = true; + tloc = lelb_to_cpu(diriter.fi.icb.extLocation); if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) != - old_dir->i_ino) - goto end_rename; + old_dir->i_ino) { + retval = -EFSCORRUPTED; + udf_err(old_inode->i_sb, + "directory (ino %lu) has parent entry pointing to another inode (%lu != %u)\n", + old_inode->i_ino, old_dir->i_ino, + udf_get_lb_pblock(old_inode->i_sb, &tloc, 0)); + goto out_oiter; + } + } + + retval = udf_fiiter_find_entry(new_dir, &new_dentry->d_name, &niter); + if (retval && retval != -ENOENT) + goto out_oiter; + /* Entry found but not passed by VFS? */ + if (!retval && !new_inode) { + retval = -EFSCORRUPTED; + udf_fiiter_release(&niter); + goto out_oiter; } - if (!nfi) { - nfi = udf_add_entry(new_dir, new_dentry, &nfibh, &ncfi, - &retval); - if (!nfi) - goto end_rename; + /* Entry not found? Need to add one... */ + if (retval) { + udf_fiiter_release(&niter); + retval = udf_fiiter_add_entry(new_dir, new_dentry, &niter); + if (retval) + goto out_oiter; } /* @@ -1163,31 +850,46 @@ static int udf_rename(struct user_namespace *mnt_userns, struct inode *old_dir, /* * ok, that's it */ - ncfi.fileVersionNum = ocfi.fileVersionNum; - ncfi.fileCharacteristics = ocfi.fileCharacteristics; - memcpy(&(ncfi.icb), &(ocfi.icb), sizeof(ocfi.icb)); - udf_write_fi(new_dir, &ncfi, nfi, &nfibh, NULL, NULL); + niter.fi.fileVersionNum = oiter.fi.fileVersionNum; + niter.fi.fileCharacteristics = oiter.fi.fileCharacteristics; + memcpy(&(niter.fi.icb), &(oiter.fi.icb), sizeof(oiter.fi.icb)); + udf_fiiter_write_fi(&niter, NULL); + udf_fiiter_release(&niter); - /* The old fid may have moved - find it again */ - ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); - udf_delete_entry(old_dir, ofi, &ofibh, &ocfi); + /* + * The old entry may have moved due to new entry allocation. Find it + * again. + */ + udf_fiiter_release(&oiter); + retval = udf_fiiter_find_entry(old_dir, &old_dentry->d_name, &oiter); + if (retval) { + udf_err(old_dir->i_sb, + "failed to find renamed entry again in directory (ino %lu)\n", + old_dir->i_ino); + } else { + udf_fiiter_delete_entry(&oiter); + udf_fiiter_release(&oiter); + } if (new_inode) { new_inode->i_ctime = current_time(new_inode); inode_dec_link_count(new_inode); + udf_add_fid_counter(old_dir->i_sb, S_ISDIR(new_inode->i_mode), + -1); } old_dir->i_ctime = old_dir->i_mtime = current_time(old_dir); new_dir->i_ctime = new_dir->i_mtime = current_time(new_dir); mark_inode_dirty(old_dir); mark_inode_dirty(new_dir); - if (dir_fi) { - dir_fi->icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location); - udf_update_tag((char *)dir_fi, udf_dir_entry_len(dir_fi)); - if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - mark_inode_dirty(old_inode); - else - mark_buffer_dirty_inode(dir_bh, old_inode); + if (has_diriter) { + diriter.fi.icb.extLocation = + cpu_to_lelb(UDF_I(new_dir)->i_location); + udf_update_tag((char *)&diriter.fi, + udf_dir_entry_len(&diriter.fi)); + udf_fiiter_write_fi(&diriter, NULL); + udf_fiiter_release(&diriter); + inode_unlock(old_inode); inode_dec_link_count(old_dir); if (new_inode) @@ -1197,22 +899,13 @@ static int udf_rename(struct user_namespace *mnt_userns, struct inode *old_dir, mark_inode_dirty(new_dir); } } - - if (ofi) { - if (ofibh.sbh != ofibh.ebh) - brelse(ofibh.ebh); - brelse(ofibh.sbh); - } - - retval = 0; - -end_rename: - brelse(dir_bh); - if (nfi) { - if (nfibh.sbh != nfibh.ebh) - brelse(nfibh.ebh); - brelse(nfibh.sbh); + return 0; +out_oiter: + if (has_diriter) { + udf_fiiter_release(&diriter); + inode_unlock(old_inode); } + udf_fiiter_release(&oiter); return retval; } @@ -1221,17 +914,15 @@ static struct dentry *udf_get_parent(struct dentry *child) { struct kernel_lb_addr tloc; struct inode *inode = NULL; - struct fileIdentDesc cfi; - struct udf_fileident_bh fibh; - - if (!udf_find_entry(d_inode(child), &dotdot_name, &fibh, &cfi)) - return ERR_PTR(-EACCES); + struct udf_fileident_iter iter; + int err; - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); + err = udf_fiiter_find_entry(d_inode(child), &dotdot_name, &iter); + if (err) + return ERR_PTR(err); - tloc = lelb_to_cpu(cfi.icb.extLocation); + tloc = lelb_to_cpu(iter.fi.icb.extLocation); + udf_fiiter_release(&iter); inode = udf_iget(child->d_sb, &tloc); if (IS_ERR(inode)) return ERR_CAST(inode); diff --git a/fs/udf/partition.c b/fs/udf/partition.c index 4cbf40575965..5bcfe78d5cab 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -54,6 +54,7 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, struct udf_part_map *map; struct udf_virtual_data *vdata; struct udf_inode_info *iinfo = UDF_I(sbi->s_vat_inode); + int err; map = &sbi->s_partmaps[partition]; vdata = &map->s_type_specific.s_virtual; @@ -79,12 +80,10 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, index = vdata->s_start_offset / sizeof(uint32_t) + block; } - loc = udf_block_map(sbi->s_vat_inode, newblock); - - bh = sb_bread(sb, loc); + bh = udf_bread(sbi->s_vat_inode, newblock, 0, &err); if (!bh) { - udf_debug("get_pblock(UDF_VIRTUAL_MAP:%p,%u,%u) VAT: %u[%u]\n", - sb, block, partition, loc, index); + udf_debug("get_pblock(UDF_VIRTUAL_MAP:%p,%u,%u)\n", + sb, block, partition); return 0xFFFFFFFF; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 06eda8177b5f..6304e3c5c3d9 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -86,6 +86,13 @@ enum { #define UDF_MAX_LVID_NESTING 1000 enum { UDF_MAX_LINKS = 0xffff }; +/* + * We limit filesize to 4TB. This is arbitrary as the on-disk format supports + * more but because the file space is described by a linked list of extents, + * each of which can have at most 1GB, the creation and handling of extents + * gets unusably slow beyond certain point... + */ +#define UDF_MAX_FILESIZE (1ULL << 42) /* These are the "meat" - everything else is stuffing */ static int udf_fill_super(struct super_block *, void *, int); @@ -147,6 +154,7 @@ static struct inode *udf_alloc_inode(struct super_block *sb) ei->i_next_alloc_goal = 0; ei->i_strat4096 = 0; ei->i_streamdir = 0; + ei->i_hidden = 0; init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); @@ -733,7 +741,7 @@ static int udf_check_vsd(struct super_block *sb) * added */ for (; !nsr && sector < VSD_MAX_SECTOR_OFFSET; sector += sectorsize) { /* Read a block */ - bh = udf_tread(sb, sector >> sb->s_blocksize_bits); + bh = sb_bread(sb, sector >> sb->s_blocksize_bits); if (!bh) break; @@ -1175,7 +1183,6 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) struct udf_part_map *map = &sbi->s_partmaps[p_index]; struct buffer_head *bh = NULL; struct udf_inode_info *vati; - uint32_t pos; struct virtualAllocationTable20 *vat20; sector_t blocks = sb_bdev_nr_blocks(sb); @@ -1197,10 +1204,14 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) } else if (map->s_partition_type == UDF_VIRTUAL_MAP20) { vati = UDF_I(sbi->s_vat_inode); if (vati->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - pos = udf_block_map(sbi->s_vat_inode, 0); - bh = sb_bread(sb, pos); - if (!bh) - return -EIO; + int err = 0; + + bh = udf_bread(sbi->s_vat_inode, 0, 0, &err); + if (!bh) { + if (!err) + err = -EFSCORRUPTED; + return err; + } vat20 = (struct virtualAllocationTable20 *)bh->b_data; } else { vat20 = (struct virtualAllocationTable20 *) @@ -1838,10 +1849,6 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block, uint16_t ident; int ret; - if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) && - udf_fixed_to_variable(block) >= sb_bdev_nr_blocks(sb)) - return -EAGAIN; - bh = udf_read_tagged(sb, block, block, &ident); if (!bh) return -EAGAIN; @@ -1860,10 +1867,10 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block, * Returns < 0 on error, 0 on success. -EAGAIN is special - try next set * of anchors. */ -static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock, +static int udf_scan_anchors(struct super_block *sb, udf_pblk_t *lastblock, struct kernel_lb_addr *fileset) { - sector_t last[6]; + udf_pblk_t last[6]; int i; struct udf_sb_info *sbi = UDF_SB(sb); int last_count = 0; @@ -1924,46 +1931,6 @@ static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock, } /* - * Find an anchor volume descriptor and load Volume Descriptor Sequence from - * area specified by it. The function expects sbi->s_lastblock to be the last - * block on the media. - * - * Return <0 on error, 0 if anchor found. -EAGAIN is special meaning anchor - * was not found. - */ -static int udf_find_anchor(struct super_block *sb, - struct kernel_lb_addr *fileset) -{ - struct udf_sb_info *sbi = UDF_SB(sb); - sector_t lastblock = sbi->s_last_block; - int ret; - - ret = udf_scan_anchors(sb, &lastblock, fileset); - if (ret != -EAGAIN) - goto out; - - /* No anchor found? Try VARCONV conversion of block numbers */ - UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); - lastblock = udf_variable_to_fixed(sbi->s_last_block); - /* Firstly, we try to not convert number of the last block */ - ret = udf_scan_anchors(sb, &lastblock, fileset); - if (ret != -EAGAIN) - goto out; - - lastblock = sbi->s_last_block; - /* Secondly, we try with converted number of the last block */ - ret = udf_scan_anchors(sb, &lastblock, fileset); - if (ret < 0) { - /* VARCONV didn't help. Clear it. */ - UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV); - } -out: - if (ret == 0) - sbi->s_last_block = lastblock; - return ret; -} - -/* * Check Volume Structure Descriptor, find Anchor block and load Volume * Descriptor Sequence. * @@ -2003,7 +1970,7 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, /* Look for anchor block and load Volume Descriptor Sequence */ sbi->s_anchor = uopt->anchor; - ret = udf_find_anchor(sb, fileset); + ret = udf_scan_anchors(sb, &sbi->s_last_block, fileset); if (ret < 0) { if (!silent && ret == -EAGAIN) udf_warn(sb, "No anchor found\n"); @@ -2297,7 +2264,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) ret = -ENOMEM; goto error_out; } - sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_maxbytes = UDF_MAX_FILESIZE; sb->s_max_links = UDF_MAX_LINKS; return 0; @@ -2454,7 +2421,7 @@ static unsigned int udf_count_free_bitmap(struct super_block *sb, if (bytes) { brelse(bh); newblock = udf_get_lb_pblock(sb, &loc, ++block); - bh = udf_tread(sb, newblock); + bh = sb_bread(sb, newblock); if (!bh) { udf_debug("read failed\n"); goto out; diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index f3642f9c23f8..a34c8c4e6d21 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -107,53 +107,45 @@ static int udf_symlink_filler(struct file *file, struct folio *folio) struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; unsigned char *symlink; - int err; + int err = 0; unsigned char *p = page_address(page); - struct udf_inode_info *iinfo; - uint32_t pos; + struct udf_inode_info *iinfo = UDF_I(inode); /* We don't support symlinks longer than one block */ if (inode->i_size > inode->i_sb->s_blocksize) { err = -ENAMETOOLONG; - goto out_unmap; + goto out_unlock; } - iinfo = UDF_I(inode); - pos = udf_block_map(inode, 0); - - down_read(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { symlink = iinfo->i_data + iinfo->i_lenEAttr; } else { - bh = sb_bread(inode->i_sb, pos); - + bh = udf_bread(inode, 0, 0, &err); if (!bh) { - err = -EIO; - goto out_unlock_inode; + if (!err) + err = -EFSCORRUPTED; + goto out_err; } - symlink = bh->b_data; } err = udf_pc_to_char(inode->i_sb, symlink, inode->i_size, p, PAGE_SIZE); brelse(bh); if (err) - goto out_unlock_inode; + goto out_err; - up_read(&iinfo->i_data_sem); SetPageUptodate(page); unlock_page(page); return 0; -out_unlock_inode: - up_read(&iinfo->i_data_sem); +out_err: SetPageError(page); -out_unmap: +out_unlock: unlock_page(page); return err; } -static int udf_symlink_getattr(struct user_namespace *mnt_userns, +static int udf_symlink_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -161,7 +153,7 @@ static int udf_symlink_getattr(struct user_namespace *mnt_userns, struct inode *inode = d_backing_inode(dentry); struct page *page; - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); page = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(page)) return PTR_ERR(page); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 036ebd892b85..871856c69df5 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -125,7 +125,7 @@ void udf_discard_prealloc(struct inode *inode) struct kernel_lb_addr eloc; uint32_t elen; uint64_t lbcount = 0; - int8_t etype = -1, netype; + int8_t etype = -1; struct udf_inode_info *iinfo = UDF_I(inode); int bsize = 1 << inode->i_blkbits; @@ -136,7 +136,7 @@ void udf_discard_prealloc(struct inode *inode) epos.block = iinfo->i_location; /* Find the last extent in the file */ - while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 0)) != -1) { + while (udf_next_aext(inode, &epos, &eloc, &elen, 0) != -1) { brelse(prev_epos.bh); prev_epos = epos; if (prev_epos.bh) @@ -240,7 +240,7 @@ int udf_truncate_extents(struct inode *inode) brelse(epos.bh); epos.offset = sizeof(struct allocExtDesc); epos.block = eloc; - epos.bh = udf_tread(sb, + epos.bh = sb_bread(sb, udf_get_lb_pblock(sb, &eloc, 0)); /* Error reading indirect block? */ if (!epos.bh) diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h index 06ff7006b822..312b7c9ef10e 100644 --- a/fs/udf/udf_i.h +++ b/fs/udf/udf_i.h @@ -44,7 +44,8 @@ struct udf_inode_info { unsigned i_use : 1; /* unallocSpaceEntry */ unsigned i_strat4096 : 1; unsigned i_streamdir : 1; - unsigned reserved : 25; + unsigned i_hidden : 1; /* hidden system inode */ + unsigned reserved : 24; __u8 *i_data; struct kernel_lb_addr i_locStreamdir; __u64 i_lenStreams; diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index 291b56dd011e..9af6ff7f9747 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -23,7 +23,6 @@ #define UDF_FLAG_STRICT 5 #define UDF_FLAG_UNDELETE 6 #define UDF_FLAG_UNHIDE 7 -#define UDF_FLAG_VARCONV 8 #define UDF_FLAG_UID_FORGET 11 /* save -1 for uid to disk */ #define UDF_FLAG_GID_FORGET 12 #define UDF_FLAG_UID_SET 13 @@ -55,6 +54,8 @@ #define MF_DUPLICATE_MD 0x01 #define MF_MIRROR_FE_LOADED 0x02 +#define EFSCORRUPTED EUCLEAN + struct udf_meta_data { __u32 s_meta_file_loc; __u32 s_mirror_file_loc; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 7e258f15b8ef..88692512a466 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -34,9 +34,6 @@ extern __printf(3, 4) void _udf_warn(struct super_block *sb, #define udf_debug(fmt, ...) \ pr_debug("%s:%d:%s: " fmt, __FILE__, __LINE__, __func__, ##__VA_ARGS__) -#define udf_fixed_to_variable(x) ( ( ( (x) >> 5 ) * 39 ) + ( (x) & 0x0000001F ) ) -#define udf_variable_to_fixed(x) ( ( ( (x) / 39 ) << 5 ) + ( (x) % 39 ) ) - #define UDF_EXTENT_LENGTH_MASK 0x3FFFFFFF #define UDF_EXTENT_FLAG_MASK 0xC0000000 @@ -83,14 +80,24 @@ extern const struct inode_operations udf_file_inode_operations; extern const struct file_operations udf_file_operations; extern const struct inode_operations udf_symlink_inode_operations; extern const struct address_space_operations udf_aops; -extern const struct address_space_operations udf_adinicb_aops; extern const struct address_space_operations udf_symlink_aops; -struct udf_fileident_bh { - struct buffer_head *sbh; - struct buffer_head *ebh; - int soffset; - int eoffset; +struct udf_fileident_iter { + struct inode *dir; /* Directory we are working with */ + loff_t pos; /* Logical position in a dir */ + struct buffer_head *bh[2]; /* Buffer containing 'pos' and possibly + * next buffer if entry straddles + * blocks */ + struct kernel_lb_addr eloc; /* Start of extent containing 'pos' */ + uint32_t elen; /* Length of extent containing 'pos' */ + sector_t loffset; /* Block offset of 'pos' within above + * extent */ + struct extent_position epos; /* Position after the above extent */ + struct fileIdentDesc fi; /* Copied directory entry */ + uint8_t *name; /* Pointer to entry name */ + uint8_t *namebuf; /* Storage for entry name in case + * the name is split between two blocks + */ }; struct udf_vds_record { @@ -121,22 +128,16 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb, u32 meta_file_loc, u32 partition_num); /* namei.c */ -extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *, - struct fileIdentDesc *, struct udf_fileident_bh *, - uint8_t *, uint8_t *); static inline unsigned int udf_dir_entry_len(struct fileIdentDesc *cfi) { return ALIGN(sizeof(struct fileIdentDesc) + le16_to_cpu(cfi->lengthOfImpUse) + cfi->lengthFileIdent, UDF_NAME_PAD); } -static inline uint8_t *udf_get_fi_ident(struct fileIdentDesc *fi) -{ - return ((uint8_t *)(fi + 1)) + le16_to_cpu(fi->lengthOfImpUse); -} /* file.c */ extern long udf_ioctl(struct file *, unsigned int, unsigned long); + /* inode.c */ extern struct inode *__udf_iget(struct super_block *, struct kernel_lb_addr *, bool hidden_inode); @@ -151,16 +152,14 @@ static inline struct inode *udf_iget(struct super_block *sb, return __udf_iget(sb, ino, false); } extern int udf_expand_file_adinicb(struct inode *); -extern struct buffer_head *udf_expand_dir_adinicb(struct inode *inode, - udf_pblk_t *block, int *err); extern struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, int create, int *err); extern int udf_setsize(struct inode *, loff_t); extern void udf_evict_inode(struct inode *); extern int udf_write_inode(struct inode *, struct writeback_control *wbc); -extern udf_pblk_t udf_block_map(struct inode *inode, sector_t block); extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *, struct kernel_lb_addr *, uint32_t *, sector_t *); +int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, struct extent_position *epos); extern int __udf_add_aext(struct inode *inode, struct extent_position *epos, @@ -177,9 +176,6 @@ extern int8_t udf_current_aext(struct inode *, struct extent_position *, extern void udf_update_extra_perms(struct inode *inode, umode_t mode); /* misc.c */ -extern struct buffer_head *udf_tgetblk(struct super_block *sb, - udf_pblk_t block); -extern struct buffer_head *udf_tread(struct super_block *sb, udf_pblk_t block); extern struct genericFormat *udf_add_extendedattr(struct inode *, uint32_t, uint32_t, uint8_t); extern struct genericFormat *udf_get_extendedattr(struct inode *, uint32_t, @@ -194,7 +190,7 @@ extern void udf_new_tag(char *, uint16_t, uint16_t, uint16_t, uint32_t, int); /* lowlevel.c */ extern unsigned int udf_get_last_session(struct super_block *); -extern unsigned long udf_get_last_block(struct super_block *); +udf_pblk_t udf_get_last_block(struct super_block *); /* partition.c */ extern uint32_t udf_get_pblock(struct super_block *, uint32_t, uint16_t, @@ -243,14 +239,13 @@ extern udf_pblk_t udf_new_block(struct super_block *sb, struct inode *inode, uint16_t partition, uint32_t goal, int *err); /* directory.c */ -extern struct fileIdentDesc *udf_fileident_read(struct inode *, loff_t *, - struct udf_fileident_bh *, - struct fileIdentDesc *, - struct extent_position *, - struct kernel_lb_addr *, uint32_t *, - sector_t *); -extern struct fileIdentDesc *udf_get_fileident(void *buffer, int bufsize, - int *offset); +int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, + loff_t pos); +int udf_fiiter_advance(struct udf_fileident_iter *iter); +void udf_fiiter_release(struct udf_fileident_iter *iter); +void udf_fiiter_write_fi(struct udf_fileident_iter *iter, uint8_t *impuse); +void udf_fiiter_update_elen(struct udf_fileident_iter *iter, uint32_t new_elen); +int udf_fiiter_append_blk(struct udf_fileident_iter *iter); extern struct long_ad *udf_get_filelongad(uint8_t *, int, uint32_t *, int); extern struct short_ad *udf_get_fileshortad(uint8_t *, int, uint32_t *, int); diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 7e3e08c0166f..06bd84d555bd 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -289,7 +289,7 @@ cg_found: ufs_mark_sb_dirty(sb); inode->i_ino = cg * uspi->s_ipg + bit; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_blocks = 0; inode->i_generation = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a873de7dec1c..a4246c83a8cd 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -1212,14 +1212,14 @@ out: return err; } -int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int ufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; int error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; @@ -1229,7 +1229,7 @@ int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, return error; } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 29d5a0e0c8f0..36154b5aca6d 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -69,7 +69,7 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsi * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ufs_create (struct user_namespace * mnt_userns, +static int ufs_create (struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { @@ -86,7 +86,7 @@ static int ufs_create (struct user_namespace * mnt_userns, return ufs_add_nondir(dentry, inode); } -static int ufs_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int ufs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; @@ -106,7 +106,7 @@ static int ufs_mknod(struct user_namespace *mnt_userns, struct inode *dir, return err; } -static int ufs_symlink (struct user_namespace * mnt_userns, struct inode * dir, +static int ufs_symlink (struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, const char * symname) { struct super_block * sb = dir->i_sb; @@ -166,7 +166,7 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, return error; } -static int ufs_mkdir(struct user_namespace * mnt_userns, struct inode * dir, +static int ufs_mkdir(struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, umode_t mode) { struct inode * inode; @@ -243,7 +243,7 @@ static int ufs_rmdir (struct inode * dir, struct dentry *dentry) return err; } -static int ufs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, +static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 550f7c5a3636..6b499180643b 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -123,7 +123,7 @@ extern struct inode *ufs_iget(struct super_block *, unsigned long); extern int ufs_write_inode (struct inode *, struct writeback_control *); extern int ufs_sync_inode (struct inode *); extern void ufs_evict_inode (struct inode *); -extern int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int ufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); /* namei.c */ diff --git a/fs/utimes.c b/fs/utimes.c index 39f356017635..3701b3946f88 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -7,6 +7,7 @@ #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> +#include <linux/filelock.h> static bool nsec_valid(long nsec) { @@ -62,7 +63,7 @@ int vfs_utimes(const struct path *path, struct timespec64 *times) } retry_deleg: inode_lock(inode); - error = notify_change(mnt_user_ns(path->mnt), path->dentry, &newattrs, + error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index c4769a9396c5..075f15c43c78 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -294,14 +294,14 @@ out: return err; } -static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns, +static int vboxsf_dir_mkfile(struct mnt_idmap *idmap, struct inode *parent, struct dentry *dentry, umode_t mode, bool excl) { return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL); } -static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, +static int vboxsf_dir_mkdir(struct mnt_idmap *idmap, struct inode *parent, struct dentry *dentry, umode_t mode) { @@ -387,7 +387,7 @@ static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) return 0; } -static int vboxsf_dir_rename(struct user_namespace *mnt_userns, +static int vboxsf_dir_rename(struct mnt_idmap *idmap, struct inode *old_parent, struct dentry *old_dentry, struct inode *new_parent, @@ -430,7 +430,7 @@ err_put_old_path: return err; } -static int vboxsf_dir_symlink(struct user_namespace *mnt_userns, +static int vboxsf_dir_symlink(struct mnt_idmap *idmap, struct inode *parent, struct dentry *dentry, const char *symname) { diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c index e1db0f3f7e5e..dd0ae1188e87 100644 --- a/fs/vboxsf/utils.c +++ b/fs/vboxsf/utils.c @@ -231,7 +231,7 @@ int vboxsf_inode_revalidate(struct dentry *dentry) return 0; } -int vboxsf_getattr(struct user_namespace *mnt_userns, const struct path *path, +int vboxsf_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *kstat, u32 request_mask, unsigned int flags) { int err; @@ -252,11 +252,11 @@ int vboxsf_getattr(struct user_namespace *mnt_userns, const struct path *path, if (err) return err; - generic_fillattr(&init_user_ns, d_inode(dentry), kstat); + generic_fillattr(&nop_mnt_idmap, d_inode(dentry), kstat); return 0; } -int vboxsf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int vboxsf_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry)); diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h index 9047befa66c5..05973eb89d52 100644 --- a/fs/vboxsf/vfsmod.h +++ b/fs/vboxsf/vfsmod.h @@ -97,10 +97,10 @@ 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(struct user_namespace *mnt_userns, const struct path *path, +int vboxsf_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *kstat, u32 request_mask, unsigned int query_flags); -int vboxsf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int vboxsf_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi, struct dentry *dentry); diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig index aad1f1d998b9..a7ffd718f171 100644 --- a/fs/verity/Kconfig +++ b/fs/verity/Kconfig @@ -34,14 +34,6 @@ config FS_VERITY If unsure, say N. -config FS_VERITY_DEBUG - bool "FS Verity debugging" - depends on FS_VERITY - help - Enable debugging messages related to fs-verity by default. - - Say N unless you are an fs-verity developer. - config FS_VERITY_BUILTIN_SIGNATURES bool "FS Verity builtin signature support" depends on FS_VERITY diff --git a/fs/verity/enable.c b/fs/verity/enable.c index df6b499bf6a1..e13db6507b38 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -7,136 +7,50 @@ #include "fsverity_private.h" -#include <crypto/hash.h> -#include <linux/backing-dev.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> -/* - * Read a file data page for Merkle tree construction. Do aggressive readahead, - * since we're sequentially reading the entire file. - */ -static struct page *read_file_data_page(struct file *file, pgoff_t index, - struct file_ra_state *ra, - unsigned long remaining_pages) -{ - DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, index); - struct folio *folio; - - folio = __filemap_get_folio(ractl.mapping, index, FGP_ACCESSED, 0); - if (!folio || !folio_test_uptodate(folio)) { - if (folio) - folio_put(folio); - else - page_cache_sync_ra(&ractl, remaining_pages); - folio = read_cache_folio(ractl.mapping, index, NULL, file); - if (IS_ERR(folio)) - return &folio->page; - } - if (folio_test_readahead(folio)) - page_cache_async_ra(&ractl, folio, remaining_pages); - return folio_file_page(folio, index); -} +struct block_buffer { + u32 filled; + u8 *data; +}; -static int build_merkle_tree_level(struct file *filp, unsigned int level, - u64 num_blocks_to_hash, - const struct merkle_tree_params *params, - u8 *pending_hashes, - struct ahash_request *req) +/* Hash a block, writing the result to the next level's pending block buffer. */ +static int hash_one_block(struct inode *inode, + const struct merkle_tree_params *params, + struct ahash_request *req, struct block_buffer *cur) { - struct inode *inode = file_inode(filp); - const struct fsverity_operations *vops = inode->i_sb->s_vop; - struct file_ra_state ra = { 0 }; - unsigned int pending_size = 0; - u64 dst_block_num; - u64 i; + struct block_buffer *next = cur + 1; int err; - if (WARN_ON(params->block_size != PAGE_SIZE)) /* checked earlier too */ - return -EINVAL; - - if (level < params->num_levels) { - dst_block_num = params->level_start[level]; - } else { - if (WARN_ON(num_blocks_to_hash != 1)) - return -EINVAL; - dst_block_num = 0; /* unused */ - } + /* Zero-pad the block if it's shorter than the block size. */ + memset(&cur->data[cur->filled], 0, params->block_size - cur->filled); - file_ra_state_init(&ra, filp->f_mapping); - - for (i = 0; i < num_blocks_to_hash; i++) { - struct page *src_page; - - if ((pgoff_t)i % 10000 == 0 || i + 1 == num_blocks_to_hash) - pr_debug("Hashing block %llu of %llu for level %u\n", - i + 1, num_blocks_to_hash, level); - - if (level == 0) { - /* Leaf: hashing a data block */ - src_page = read_file_data_page(filp, i, &ra, - num_blocks_to_hash - i); - if (IS_ERR(src_page)) { - err = PTR_ERR(src_page); - fsverity_err(inode, - "Error %d reading data page %llu", - err, i); - return err; - } - } else { - unsigned long num_ra_pages = - min_t(unsigned long, num_blocks_to_hash - i, - inode->i_sb->s_bdi->io_pages); - - /* Non-leaf: hashing hash block from level below */ - src_page = vops->read_merkle_tree_page(inode, - params->level_start[level - 1] + i, - num_ra_pages); - if (IS_ERR(src_page)) { - err = PTR_ERR(src_page); - fsverity_err(inode, - "Error %d reading Merkle tree page %llu", - err, params->level_start[level - 1] + i); - return err; - } - } + err = fsverity_hash_block(params, inode, req, virt_to_page(cur->data), + offset_in_page(cur->data), + &next->data[next->filled]); + if (err) + return err; + next->filled += params->digest_size; + cur->filled = 0; + return 0; +} - err = fsverity_hash_page(params, inode, req, src_page, - &pending_hashes[pending_size]); - put_page(src_page); - if (err) - return err; - pending_size += params->digest_size; - - if (level == params->num_levels) /* Root hash? */ - return 0; - - if (pending_size + params->digest_size > params->block_size || - i + 1 == num_blocks_to_hash) { - /* Flush the pending hash block */ - memset(&pending_hashes[pending_size], 0, - params->block_size - pending_size); - err = vops->write_merkle_tree_block(inode, - pending_hashes, - dst_block_num, - params->log_blocksize); - if (err) { - fsverity_err(inode, - "Error %d writing Merkle tree block %llu", - err, dst_block_num); - return err; - } - dst_block_num++; - pending_size = 0; - } +static int write_merkle_tree_block(struct inode *inode, const u8 *buf, + unsigned long index, + const struct merkle_tree_params *params) +{ + u64 pos = (u64)index << params->log_blocksize; + int err; - if (fatal_signal_pending(current)) - return -EINTR; - cond_resched(); - } - return 0; + err = inode->i_sb->s_vop->write_merkle_tree_block(inode, buf, pos, + params->block_size); + if (err) + fsverity_err(inode, "Error %d writing Merkle tree block %lu", + err, index); + return err; } /* @@ -152,13 +66,17 @@ static int build_merkle_tree(struct file *filp, u8 *root_hash) { struct inode *inode = file_inode(filp); - u8 *pending_hashes; + const u64 data_size = inode->i_size; + const int num_levels = params->num_levels; struct ahash_request *req; - u64 blocks; - unsigned int level; - int err = -ENOMEM; + struct block_buffer _buffers[1 + FS_VERITY_MAX_LEVELS + 1] = {}; + struct block_buffer *buffers = &_buffers[1]; + unsigned long level_offset[FS_VERITY_MAX_LEVELS]; + int level; + u64 offset; + int err; - if (inode->i_size == 0) { + if (data_size == 0) { /* Empty file is a special case; root hash is all 0's */ memset(root_hash, 0, params->digest_size); return 0; @@ -167,29 +85,95 @@ static int build_merkle_tree(struct file *filp, /* This allocation never fails, since it's mempool-backed. */ req = fsverity_alloc_hash_request(params->hash_alg, GFP_KERNEL); - pending_hashes = kmalloc(params->block_size, GFP_KERNEL); - if (!pending_hashes) - goto out; - /* - * Build each level of the Merkle tree, starting at the leaf level - * (level 0) and ascending to the root node (level 'num_levels - 1'). - * Then at the end (level 'num_levels'), calculate the root hash. + * Allocate the block buffers. Buffer "-1" is for data blocks. + * Buffers 0 <= level < num_levels are for the actual tree levels. + * Buffer 'num_levels' is for the root hash. */ - blocks = ((u64)inode->i_size + params->block_size - 1) >> - params->log_blocksize; - for (level = 0; level <= params->num_levels; level++) { - err = build_merkle_tree_level(filp, level, blocks, params, - pending_hashes, req); + for (level = -1; level < num_levels; level++) { + buffers[level].data = kzalloc(params->block_size, GFP_KERNEL); + if (!buffers[level].data) { + err = -ENOMEM; + goto out; + } + } + buffers[num_levels].data = root_hash; + + BUILD_BUG_ON(sizeof(level_offset) != sizeof(params->level_start)); + memcpy(level_offset, params->level_start, sizeof(level_offset)); + + /* Hash each data block, also hashing the tree blocks as they fill up */ + for (offset = 0; offset < data_size; offset += params->block_size) { + ssize_t bytes_read; + loff_t pos = offset; + + buffers[-1].filled = min_t(u64, params->block_size, + data_size - offset); + bytes_read = __kernel_read(filp, buffers[-1].data, + buffers[-1].filled, &pos); + if (bytes_read < 0) { + err = bytes_read; + fsverity_err(inode, "Error %d reading file data", err); + goto out; + } + if (bytes_read != buffers[-1].filled) { + err = -EINVAL; + fsverity_err(inode, "Short read of file data"); + goto out; + } + err = hash_one_block(inode, params, req, &buffers[-1]); if (err) goto out; - blocks = (blocks + params->hashes_per_block - 1) >> - params->log_arity; + for (level = 0; level < num_levels; level++) { + if (buffers[level].filled + params->digest_size <= + params->block_size) { + /* Next block at @level isn't full yet */ + break; + } + /* Next block at @level is full */ + + err = hash_one_block(inode, params, req, + &buffers[level]); + if (err) + goto out; + err = write_merkle_tree_block(inode, + buffers[level].data, + level_offset[level], + params); + if (err) + goto out; + level_offset[level]++; + } + if (fatal_signal_pending(current)) { + err = -EINTR; + goto out; + } + cond_resched(); + } + /* Finish all nonempty pending tree blocks. */ + for (level = 0; level < num_levels; level++) { + if (buffers[level].filled != 0) { + err = hash_one_block(inode, params, req, + &buffers[level]); + if (err) + goto out; + err = write_merkle_tree_block(inode, + buffers[level].data, + level_offset[level], + params); + if (err) + goto out; + } + } + /* The root hash was filled by the last call to hash_one_block(). */ + if (WARN_ON(buffers[num_levels].filled != params->digest_size)) { + err = -EINVAL; + goto out; } - memcpy(root_hash, pending_hashes, params->digest_size); err = 0; out: - kfree(pending_hashes); + for (level = -1; level < num_levels; level++) + kfree(buffers[level].data); fsverity_free_hash_request(params->hash_alg, req); return err; } @@ -263,15 +247,12 @@ static int enable_verity(struct file *filp, * ->begin_enable_verity() and ->end_enable_verity() using the inode * lock and only allow one process to be here at a time on a given file. */ - pr_debug("Building Merkle tree...\n"); BUILD_BUG_ON(sizeof(desc->root_hash) < FS_VERITY_MAX_DIGEST_SIZE); err = build_merkle_tree(filp, ¶ms, desc->root_hash); if (err) { fsverity_err(inode, "Error %d building Merkle tree", err); goto rollback; } - pr_debug("Done building Merkle tree. Root hash is %s:%*phN\n", - params.hash_alg->name, params.digest_size, desc->root_hash); /* * Create the fsverity_info. Don't bother trying to save work by @@ -286,10 +267,6 @@ static int enable_verity(struct file *filp, goto rollback; } - if (arg->sig_size) - pr_debug("Storing a %u-byte PKCS#7 signature alongside the file\n", - arg->sig_size); - /* * Tell the filesystem to finish enabling verity on the file. * Serialized with ->begin_enable_verity() by the inode lock. @@ -352,7 +329,7 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) memchr_inv(arg.__reserved2, 0, sizeof(arg.__reserved2))) return -EINVAL; - if (arg.block_size != PAGE_SIZE) + if (!is_power_of_2(arg.block_size)) return -EINVAL; if (arg.salt_size > sizeof_field(struct fsverity_descriptor, salt)) diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index c7fcb855e068..d34dcc033d72 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -8,10 +8,6 @@ #ifndef _FSVERITY_PRIVATE_H #define _FSVERITY_PRIVATE_H -#ifdef CONFIG_FS_VERITY_DEBUG -#define DEBUG -#endif - #define pr_fmt(fmt) "fs-verity: " fmt #include <linux/fsverity.h> @@ -46,17 +42,20 @@ struct merkle_tree_params { unsigned int digest_size; /* same as hash_alg->digest_size */ unsigned int block_size; /* size of data and tree blocks */ unsigned int hashes_per_block; /* number of hashes per tree block */ - unsigned int log_blocksize; /* log2(block_size) */ - unsigned int log_arity; /* log2(hashes_per_block) */ + unsigned int blocks_per_page; /* PAGE_SIZE / block_size */ + u8 log_digestsize; /* log2(digest_size) */ + u8 log_blocksize; /* log2(block_size) */ + u8 log_arity; /* log2(hashes_per_block) */ + u8 log_blocks_per_page; /* log2(blocks_per_page) */ unsigned int num_levels; /* number of levels in Merkle tree */ u64 tree_size; /* Merkle tree size in bytes */ - unsigned long level0_blocks; /* number of blocks in tree level 0 */ + unsigned long tree_pages; /* Merkle tree size in pages */ /* * Starting block index for each tree level, ordered from leaf level (0) * to root level ('num_levels - 1') */ - u64 level_start[FS_VERITY_MAX_LEVELS]; + unsigned long level_start[FS_VERITY_MAX_LEVELS]; }; /* @@ -73,9 +72,10 @@ struct fsverity_info { u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE]; u8 file_digest[FS_VERITY_MAX_DIGEST_SIZE]; const struct inode *inode; + unsigned long *hash_block_verified; + spinlock_t hash_page_init_lock; }; - #define FS_VERITY_MAX_SIGNATURE_SIZE (FS_VERITY_MAX_DESCRIPTOR_SIZE - \ sizeof(struct fsverity_descriptor)) @@ -91,9 +91,9 @@ void fsverity_free_hash_request(struct fsverity_hash_alg *alg, struct ahash_request *req); const u8 *fsverity_prepare_hash_state(struct fsverity_hash_alg *alg, const u8 *salt, size_t salt_size); -int fsverity_hash_page(const struct merkle_tree_params *params, - const struct inode *inode, - struct ahash_request *req, struct page *page, u8 *out); +int fsverity_hash_block(const struct merkle_tree_params *params, + const struct inode *inode, struct ahash_request *req, + struct page *page, unsigned int offset, u8 *out); int fsverity_hash_buffer(struct fsverity_hash_alg *alg, const void *data, size_t size, u8 *out); void __init fsverity_check_hash_algs(void); diff --git a/fs/verity/hash_algs.c b/fs/verity/hash_algs.c index 6f8170cf4ae7..13fcf31be844 100644 --- a/fs/verity/hash_algs.c +++ b/fs/verity/hash_algs.c @@ -220,35 +220,33 @@ err_free: } /** - * fsverity_hash_page() - hash a single data or hash page + * fsverity_hash_block() - hash a single data or hash block * @params: the Merkle tree's parameters * @inode: inode for which the hashing is being done * @req: preallocated hash request - * @page: the page to hash + * @page: the page containing the block to hash + * @offset: the offset of the block within @page * @out: output digest, size 'params->digest_size' bytes * - * Hash a single data or hash block, assuming block_size == PAGE_SIZE. - * The hash is salted if a salt is specified in the Merkle tree parameters. + * Hash a single data or hash block. The hash is salted if a salt is specified + * in the Merkle tree parameters. * * Return: 0 on success, -errno on failure */ -int fsverity_hash_page(const struct merkle_tree_params *params, - const struct inode *inode, - struct ahash_request *req, struct page *page, u8 *out) +int fsverity_hash_block(const struct merkle_tree_params *params, + const struct inode *inode, struct ahash_request *req, + struct page *page, unsigned int offset, u8 *out) { struct scatterlist sg; DECLARE_CRYPTO_WAIT(wait); int err; - if (WARN_ON(params->block_size != PAGE_SIZE)) - return -EINVAL; - sg_init_table(&sg, 1); - sg_set_page(&sg, page, PAGE_SIZE, 0); + sg_set_page(&sg, page, params->block_size, offset); ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &wait); - ahash_request_set_crypt(req, &sg, out, PAGE_SIZE); + ahash_request_set_crypt(req, &sg, out, params->block_size); if (params->hashstate) { err = crypto_ahash_import(req, params->hashstate); @@ -264,7 +262,7 @@ int fsverity_hash_page(const struct merkle_tree_params *params, err = crypto_wait_req(err, &wait); if (err) - fsverity_err(inode, "Error %d computing page hash", err); + fsverity_err(inode, "Error %d computing block hash", err); return err; } diff --git a/fs/verity/init.c b/fs/verity/init.c index c98b7016f446..023905151035 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -49,7 +49,6 @@ static int __init fsverity_init(void) if (err) goto err_exit_workqueue; - pr_debug("Initialized fs-verity\n"); return 0; err_exit_workqueue: diff --git a/fs/verity/open.c b/fs/verity/open.c index 81ff94442f7b..9366b441d01c 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -7,6 +7,7 @@ #include "fsverity_private.h" +#include <linux/mm.h> #include <linux/slab.h> static struct kmem_cache *fsverity_info_cachep; @@ -34,6 +35,7 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, struct fsverity_hash_alg *hash_alg; int err; u64 blocks; + u64 blocks_in_level[FS_VERITY_MAX_LEVELS]; u64 offset; int level; @@ -54,7 +56,23 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, goto out_err; } - if (log_blocksize != PAGE_SHIFT) { + /* + * fs/verity/ directly assumes that the Merkle tree block size is a + * power of 2 less than or equal to PAGE_SIZE. Another restriction + * arises from the interaction between fs/verity/ and the filesystems + * themselves: filesystems expect to be able to verify a single + * filesystem block of data at a time. Therefore, the Merkle tree block + * size must also be less than or equal to the filesystem block size. + * + * The above are the only hard limitations, so in theory the Merkle tree + * block size could be as small as twice the digest size. However, + * that's not useful, and it would result in some unusually deep and + * large Merkle trees. So we currently require that the Merkle tree + * block size be at least 1024 bytes. That's small enough to test the + * sub-page block case on systems with 4K pages, but not too small. + */ + if (log_blocksize < 10 || log_blocksize > PAGE_SHIFT || + log_blocksize > inode->i_blkbits) { fsverity_warn(inode, "Unsupported log_blocksize: %u", log_blocksize); err = -EINVAL; @@ -62,6 +80,8 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, } params->log_blocksize = log_blocksize; params->block_size = 1 << log_blocksize; + params->log_blocks_per_page = PAGE_SHIFT - log_blocksize; + params->blocks_per_page = 1 << params->log_blocks_per_page; if (WARN_ON(!is_power_of_2(params->digest_size))) { err = -EINVAL; @@ -74,13 +94,10 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, err = -EINVAL; goto out_err; } - params->log_arity = params->log_blocksize - ilog2(params->digest_size); + params->log_digestsize = ilog2(params->digest_size); + params->log_arity = log_blocksize - params->log_digestsize; params->hashes_per_block = 1 << params->log_arity; - pr_debug("Merkle tree uses %s with %u-byte blocks (%u hashes/block), salt=%*phN\n", - hash_alg->name, params->block_size, params->hashes_per_block, - (int)salt_size, salt); - /* * Compute the number of levels in the Merkle tree and create a map from * level to the starting block of that level. Level 'num_levels - 1' is @@ -90,31 +107,45 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, /* Compute number of levels and the number of blocks in each level */ blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize; - pr_debug("Data is %lld bytes (%llu blocks)\n", inode->i_size, blocks); while (blocks > 1) { if (params->num_levels >= FS_VERITY_MAX_LEVELS) { fsverity_err(inode, "Too many levels in Merkle tree"); - err = -EINVAL; + err = -EFBIG; goto out_err; } blocks = (blocks + params->hashes_per_block - 1) >> params->log_arity; - /* temporarily using level_start[] to store blocks in level */ - params->level_start[params->num_levels++] = blocks; + blocks_in_level[params->num_levels++] = blocks; } - params->level0_blocks = params->level_start[0]; /* Compute the starting block of each level */ offset = 0; for (level = (int)params->num_levels - 1; level >= 0; level--) { - blocks = params->level_start[level]; params->level_start[level] = offset; - pr_debug("Level %d is %llu blocks starting at index %llu\n", - level, blocks, offset); - offset += blocks; + offset += blocks_in_level[level]; + } + + /* + * With block_size != PAGE_SIZE, an in-memory bitmap will need to be + * allocated to track the "verified" status of hash blocks. Don't allow + * this bitmap to get too large. For now, limit it to 1 MiB, which + * limits the file size to about 4.4 TB with SHA-256 and 4K blocks. + * + * Together with the fact that the data, and thus also the Merkle tree, + * cannot have more than ULONG_MAX pages, this implies that hash block + * indices can always fit in an 'unsigned long'. But to be safe, we + * explicitly check for that too. Note, this is only for hash block + * indices; data block indices might not fit in an 'unsigned long'. + */ + if ((params->block_size != PAGE_SIZE && offset > 1 << 23) || + offset > ULONG_MAX) { + fsverity_err(inode, "Too many blocks in Merkle tree"); + err = -EFBIG; + goto out_err; } params->tree_size = offset << log_blocksize; + params->tree_pages = PAGE_ALIGN(params->tree_size) >> PAGE_SHIFT; return 0; out_err: @@ -165,7 +196,7 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode, fsverity_err(inode, "Error %d initializing Merkle tree parameters", err); - goto out; + goto fail; } memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size); @@ -174,20 +205,48 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode, vi->file_digest); if (err) { fsverity_err(inode, "Error %d computing file digest", err); - goto out; + goto fail; } - pr_debug("Computed file digest: %s:%*phN\n", - vi->tree_params.hash_alg->name, - vi->tree_params.digest_size, vi->file_digest); err = fsverity_verify_signature(vi, desc->signature, le32_to_cpu(desc->sig_size)); -out: - if (err) { - fsverity_free_info(vi); - vi = ERR_PTR(err); + if (err) + goto fail; + + if (vi->tree_params.block_size != PAGE_SIZE) { + /* + * When the Merkle tree block size and page size differ, we use + * a bitmap to keep track of which hash blocks have been + * verified. This bitmap must contain one bit per hash block, + * including alignment to a page boundary at the end. + * + * Eventually, to support extremely large files in an efficient + * way, it might be necessary to make pages of this bitmap + * reclaimable. But for now, simply allocating the whole bitmap + * is a simple solution that works well on the files on which + * fsverity is realistically used. E.g., with SHA-256 and 4K + * blocks, a 100MB file only needs a 24-byte bitmap, and the + * bitmap for any file under 17GB fits in a 4K page. + */ + unsigned long num_bits = + vi->tree_params.tree_pages << + vi->tree_params.log_blocks_per_page; + + vi->hash_block_verified = kvcalloc(BITS_TO_LONGS(num_bits), + sizeof(unsigned long), + GFP_KERNEL); + if (!vi->hash_block_verified) { + err = -ENOMEM; + goto fail; + } + spin_lock_init(&vi->hash_page_init_lock); } + return vi; + +fail: + fsverity_free_info(vi); + return ERR_PTR(err); } void fsverity_set_info(struct inode *inode, struct fsverity_info *vi) @@ -214,6 +273,7 @@ void fsverity_free_info(struct fsverity_info *vi) if (!vi) return; kfree(vi->tree_params.hashstate); + kvfree(vi->hash_block_verified); kmem_cache_free(fsverity_info_cachep, vi); } @@ -325,67 +385,28 @@ out_free_desc: return err; } -/** - * fsverity_file_open() - prepare to open a verity file - * @inode: the inode being opened - * @filp: the struct file being set up - * - * When opening a verity file, deny the open if it is for writing. Otherwise, - * set up the inode's ->i_verity_info if not already done. - * - * When combined with fscrypt, this must be called after fscrypt_file_open(). - * Otherwise, we won't have the key set up to decrypt the verity metadata. - * - * Return: 0 on success, -errno on failure - */ -int fsverity_file_open(struct inode *inode, struct file *filp) +int __fsverity_file_open(struct inode *inode, struct file *filp) { - if (!IS_VERITY(inode)) - return 0; - - if (filp->f_mode & FMODE_WRITE) { - pr_debug("Denying opening verity file (ino %lu) for write\n", - inode->i_ino); + if (filp->f_mode & FMODE_WRITE) return -EPERM; - } - return ensure_verity_info(inode); } -EXPORT_SYMBOL_GPL(fsverity_file_open); +EXPORT_SYMBOL_GPL(__fsverity_file_open); -/** - * fsverity_prepare_setattr() - prepare to change a verity inode's attributes - * @dentry: dentry through which the inode is being changed - * @attr: attributes to change - * - * Verity files are immutable, so deny truncates. This isn't covered by the - * open-time check because sys_truncate() takes a path, not a file descriptor. - * - * Return: 0 on success, -errno on failure - */ -int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr) +int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr) { - if (IS_VERITY(d_inode(dentry)) && (attr->ia_valid & ATTR_SIZE)) { - pr_debug("Denying truncate of verity file (ino %lu)\n", - d_inode(dentry)->i_ino); + if (attr->ia_valid & ATTR_SIZE) return -EPERM; - } return 0; } -EXPORT_SYMBOL_GPL(fsverity_prepare_setattr); +EXPORT_SYMBOL_GPL(__fsverity_prepare_setattr); -/** - * fsverity_cleanup_inode() - free the inode's verity info, if present - * @inode: an inode being evicted - * - * Filesystems must call this on inode eviction to free ->i_verity_info. - */ -void fsverity_cleanup_inode(struct inode *inode) +void __fsverity_cleanup_inode(struct inode *inode) { fsverity_free_info(inode->i_verity_info); inode->i_verity_info = NULL; } -EXPORT_SYMBOL_GPL(fsverity_cleanup_inode); +EXPORT_SYMBOL_GPL(__fsverity_cleanup_inode); int __init fsverity_init_info_cache(void) { diff --git a/fs/verity/signature.c b/fs/verity/signature.c index 143a530a8008..e7d3ca919a1e 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -82,8 +82,6 @@ int fsverity_verify_signature(const struct fsverity_info *vi, return err; } - pr_debug("Valid signature for file digest %s:%*phN\n", - hash_alg->name, hash_alg->digest_size, vi->file_digest); return 0; } diff --git a/fs/verity/verify.c b/fs/verity/verify.c index 961ba248021f..f50e3b5b52c9 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -9,39 +9,12 @@ #include <crypto/hash.h> #include <linux/bio.h> -#include <linux/ratelimit.h> static struct workqueue_struct *fsverity_read_workqueue; -/** - * hash_at_level() - compute the location of the block's hash at the given level - * - * @params: (in) the Merkle tree parameters - * @dindex: (in) the index of the data block being verified - * @level: (in) the level of hash we want (0 is leaf level) - * @hindex: (out) the index of the hash block containing the wanted hash - * @hoffset: (out) the byte offset to the wanted hash within the hash block - */ -static void hash_at_level(const struct merkle_tree_params *params, - pgoff_t dindex, unsigned int level, pgoff_t *hindex, - unsigned int *hoffset) -{ - pgoff_t position; - - /* Offset of the hash within the level's region, in hashes */ - position = dindex >> (level * params->log_arity); - - /* Index of the hash block in the tree overall */ - *hindex = params->level_start[level] + (position >> params->log_arity); - - /* Offset of the wanted hash (in bytes) within the hash block */ - *hoffset = (position & ((1 << params->log_arity) - 1)) << - (params->log_blocksize - params->log_arity); -} - static inline int cmp_hashes(const struct fsverity_info *vi, const u8 *want_hash, const u8 *real_hash, - pgoff_t index, int level) + u64 data_pos, int level) { const unsigned int hsize = vi->tree_params.digest_size; @@ -49,159 +22,312 @@ static inline int cmp_hashes(const struct fsverity_info *vi, return 0; fsverity_err(vi->inode, - "FILE CORRUPTED! index=%lu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN", - index, level, + "FILE CORRUPTED! pos=%llu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN", + data_pos, level, vi->tree_params.hash_alg->name, hsize, want_hash, vi->tree_params.hash_alg->name, hsize, real_hash); return -EBADMSG; } +static bool data_is_zeroed(struct inode *inode, struct page *page, + unsigned int len, unsigned int offset) +{ + void *virt = kmap_local_page(page); + + if (memchr_inv(virt + offset, 0, len)) { + kunmap_local(virt); + fsverity_err(inode, + "FILE CORRUPTED! Data past EOF is not zeroed"); + return false; + } + kunmap_local(virt); + return true; +} + +/* + * Returns true if the hash block with index @hblock_idx in the tree, located in + * @hpage, has already been verified. + */ +static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage, + unsigned long hblock_idx) +{ + bool verified; + unsigned int blocks_per_page; + unsigned int i; + + /* + * When the Merkle tree block size and page size are the same, then the + * ->hash_block_verified bitmap isn't allocated, and we use PG_checked + * to directly indicate whether the page's block has been verified. + * + * Using PG_checked also guarantees that we re-verify hash pages that + * get evicted and re-instantiated from the backing storage, as new + * pages always start out with PG_checked cleared. + */ + if (!vi->hash_block_verified) + return PageChecked(hpage); + + /* + * When the Merkle tree block size and page size differ, we use a bitmap + * to indicate whether each hash block has been verified. + * + * However, we still need to ensure that hash pages that get evicted and + * re-instantiated from the backing storage are re-verified. To do + * this, we use PG_checked again, but now it doesn't really mean + * "checked". Instead, now it just serves as an indicator for whether + * the hash page is newly instantiated or not. + * + * The first thread that sees PG_checked=0 must clear the corresponding + * bitmap bits, then set PG_checked=1. This requires a spinlock. To + * avoid having to take this spinlock in the common case of + * PG_checked=1, we start with an opportunistic lockless read. + */ + if (PageChecked(hpage)) { + /* + * A read memory barrier is needed here to give ACQUIRE + * semantics to the above PageChecked() test. + */ + smp_rmb(); + return test_bit(hblock_idx, vi->hash_block_verified); + } + spin_lock(&vi->hash_page_init_lock); + if (PageChecked(hpage)) { + verified = test_bit(hblock_idx, vi->hash_block_verified); + } else { + blocks_per_page = vi->tree_params.blocks_per_page; + hblock_idx = round_down(hblock_idx, blocks_per_page); + for (i = 0; i < blocks_per_page; i++) + clear_bit(hblock_idx + i, vi->hash_block_verified); + /* + * A write memory barrier is needed here to give RELEASE + * semantics to the below SetPageChecked() operation. + */ + smp_wmb(); + SetPageChecked(hpage); + verified = false; + } + spin_unlock(&vi->hash_page_init_lock); + return verified; +} + /* - * Verify a single data page against the file's Merkle tree. + * Verify a single data block against the file's Merkle tree. * * In principle, we need to verify the entire path to the root node. However, - * for efficiency the filesystem may cache the hash pages. Therefore we need - * only ascend the tree until an already-verified page is seen, as indicated by - * the PageChecked bit being set; then verify the path to that page. - * - * This code currently only supports the case where the verity block size is - * equal to PAGE_SIZE. Doing otherwise would be possible but tricky, since we - * wouldn't be able to use the PageChecked bit. - * - * Note that multiple processes may race to verify a hash page and mark it - * Checked, but it doesn't matter; the result will be the same either way. + * for efficiency the filesystem may cache the hash blocks. Therefore we need + * only ascend the tree until an already-verified hash block is seen, and then + * verify the path to that block. * - * Return: true if the page is valid, else false. + * Return: %true if the data block is valid, else %false. */ -static bool verify_page(struct inode *inode, const struct fsverity_info *vi, - struct ahash_request *req, struct page *data_page, - unsigned long level0_ra_pages) +static bool +verify_data_block(struct inode *inode, struct fsverity_info *vi, + struct ahash_request *req, struct page *data_page, + u64 data_pos, unsigned int dblock_offset_in_page, + unsigned long max_ra_pages) { const struct merkle_tree_params *params = &vi->tree_params; const unsigned int hsize = params->digest_size; - const pgoff_t index = data_page->index; int level; u8 _want_hash[FS_VERITY_MAX_DIGEST_SIZE]; const u8 *want_hash; u8 real_hash[FS_VERITY_MAX_DIGEST_SIZE]; - struct page *hpages[FS_VERITY_MAX_LEVELS]; - unsigned int hoffsets[FS_VERITY_MAX_LEVELS]; + /* The hash blocks that are traversed, indexed by level */ + struct { + /* Page containing the hash block */ + struct page *page; + /* Index of the hash block in the tree overall */ + unsigned long index; + /* Byte offset of the hash block within @page */ + unsigned int offset_in_page; + /* Byte offset of the wanted hash within @page */ + unsigned int hoffset; + } hblocks[FS_VERITY_MAX_LEVELS]; + /* + * The index of the previous level's block within that level; also the + * index of that block's hash within the current level. + */ + u64 hidx = data_pos >> params->log_blocksize; int err; - if (WARN_ON_ONCE(!PageLocked(data_page) || PageUptodate(data_page))) - return false; - - pr_debug_ratelimited("Verifying data page %lu...\n", index); + if (unlikely(data_pos >= inode->i_size)) { + /* + * This can happen in the data page spanning EOF when the Merkle + * tree block size is less than the page size. The Merkle tree + * doesn't cover data blocks fully past EOF. But the entire + * page spanning EOF can be visible to userspace via a mmap, and + * any part past EOF should be all zeroes. Therefore, we need + * to verify that any data blocks fully past EOF are all zeroes. + */ + return data_is_zeroed(inode, data_page, params->block_size, + dblock_offset_in_page); + } /* - * Starting at the leaf level, ascend the tree saving hash pages along - * the way until we find a verified hash page, indicated by PageChecked; - * or until we reach the root. + * Starting at the leaf level, ascend the tree saving hash blocks along + * the way until we find a hash block that has already been verified, or + * until we reach the root. */ for (level = 0; level < params->num_levels; level++) { - pgoff_t hindex; + unsigned long next_hidx; + unsigned long hblock_idx; + pgoff_t hpage_idx; + unsigned int hblock_offset_in_page; unsigned int hoffset; struct page *hpage; - hash_at_level(params, index, level, &hindex, &hoffset); + /* + * The index of the block in the current level; also the index + * of that block's hash within the next level. + */ + next_hidx = hidx >> params->log_arity; + + /* Index of the hash block in the tree overall */ + hblock_idx = params->level_start[level] + next_hidx; + + /* Index of the hash page in the tree overall */ + hpage_idx = hblock_idx >> params->log_blocks_per_page; - pr_debug_ratelimited("Level %d: hindex=%lu, hoffset=%u\n", - level, hindex, hoffset); + /* Byte offset of the hash block within the page */ + hblock_offset_in_page = + (hblock_idx << params->log_blocksize) & ~PAGE_MASK; - hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode, hindex, - level == 0 ? level0_ra_pages : 0); + /* Byte offset of the hash within the page */ + hoffset = hblock_offset_in_page + + ((hidx << params->log_digestsize) & + (params->block_size - 1)); + + hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode, + hpage_idx, level == 0 ? min(max_ra_pages, + params->tree_pages - hpage_idx) : 0); if (IS_ERR(hpage)) { err = PTR_ERR(hpage); fsverity_err(inode, "Error %d reading Merkle tree page %lu", - err, hindex); + err, hpage_idx); goto out; } - - if (PageChecked(hpage)) { + if (is_hash_block_verified(vi, hpage, hblock_idx)) { memcpy_from_page(_want_hash, hpage, hoffset, hsize); want_hash = _want_hash; put_page(hpage); - pr_debug_ratelimited("Hash page already checked, want %s:%*phN\n", - params->hash_alg->name, - hsize, want_hash); goto descend; } - pr_debug_ratelimited("Hash page not yet checked\n"); - hpages[level] = hpage; - hoffsets[level] = hoffset; + hblocks[level].page = hpage; + hblocks[level].index = hblock_idx; + hblocks[level].offset_in_page = hblock_offset_in_page; + hblocks[level].hoffset = hoffset; + hidx = next_hidx; } want_hash = vi->root_hash; - pr_debug("Want root hash: %s:%*phN\n", - params->hash_alg->name, hsize, want_hash); descend: - /* Descend the tree verifying hash pages */ + /* Descend the tree verifying hash blocks. */ for (; level > 0; level--) { - struct page *hpage = hpages[level - 1]; - unsigned int hoffset = hoffsets[level - 1]; - - err = fsverity_hash_page(params, inode, req, hpage, real_hash); + struct page *hpage = hblocks[level - 1].page; + unsigned long hblock_idx = hblocks[level - 1].index; + unsigned int hblock_offset_in_page = + hblocks[level - 1].offset_in_page; + unsigned int hoffset = hblocks[level - 1].hoffset; + + err = fsverity_hash_block(params, inode, req, hpage, + hblock_offset_in_page, real_hash); if (err) goto out; - err = cmp_hashes(vi, want_hash, real_hash, index, level - 1); + err = cmp_hashes(vi, want_hash, real_hash, data_pos, level - 1); if (err) goto out; - SetPageChecked(hpage); + /* + * Mark the hash block as verified. This must be atomic and + * idempotent, as the same hash block might be verified by + * multiple threads concurrently. + */ + if (vi->hash_block_verified) + set_bit(hblock_idx, vi->hash_block_verified); + else + SetPageChecked(hpage); memcpy_from_page(_want_hash, hpage, hoffset, hsize); want_hash = _want_hash; put_page(hpage); - pr_debug("Verified hash page at level %d, now want %s:%*phN\n", - level - 1, params->hash_alg->name, hsize, want_hash); } - /* Finally, verify the data page */ - err = fsverity_hash_page(params, inode, req, data_page, real_hash); + /* Finally, verify the data block. */ + err = fsverity_hash_block(params, inode, req, data_page, + dblock_offset_in_page, real_hash); if (err) goto out; - err = cmp_hashes(vi, want_hash, real_hash, index, -1); + err = cmp_hashes(vi, want_hash, real_hash, data_pos, -1); out: for (; level > 0; level--) - put_page(hpages[level - 1]); + put_page(hblocks[level - 1].page); return err == 0; } +static bool +verify_data_blocks(struct inode *inode, struct fsverity_info *vi, + struct ahash_request *req, struct folio *data_folio, + size_t len, size_t offset, unsigned long max_ra_pages) +{ + const unsigned int block_size = vi->tree_params.block_size; + u64 pos = (u64)data_folio->index << PAGE_SHIFT; + + if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offset, block_size))) + return false; + if (WARN_ON_ONCE(!folio_test_locked(data_folio) || + folio_test_uptodate(data_folio))) + return false; + do { + struct page *data_page = + folio_page(data_folio, offset >> PAGE_SHIFT); + + if (!verify_data_block(inode, vi, req, data_page, pos + offset, + offset & ~PAGE_MASK, max_ra_pages)) + return false; + offset += block_size; + len -= block_size; + } while (len); + return true; +} + /** - * fsverity_verify_page() - verify a data page - * @page: the page to verity + * fsverity_verify_blocks() - verify data in a folio + * @folio: the folio containing the data to verify + * @len: the length of the data to verify in the folio + * @offset: the offset of the data to verify in the folio * - * Verify a page that has just been read from a verity file. The page must be a - * pagecache page that is still locked and not yet uptodate. + * Verify data that has just been read from a verity file. The data must be + * located in a pagecache folio that is still locked and not yet uptodate. The + * length and offset of the data must be Merkle tree block size aligned. * - * Return: true if the page is valid, else false. + * Return: %true if the data is valid, else %false. */ -bool fsverity_verify_page(struct page *page) +bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset) { - struct inode *inode = page->mapping->host; - const struct fsverity_info *vi = inode->i_verity_info; + struct inode *inode = folio->mapping->host; + struct fsverity_info *vi = inode->i_verity_info; struct ahash_request *req; bool valid; /* This allocation never fails, since it's mempool-backed. */ req = fsverity_alloc_hash_request(vi->tree_params.hash_alg, GFP_NOFS); - valid = verify_page(inode, vi, req, page, 0); + valid = verify_data_blocks(inode, vi, req, folio, len, offset, 0); fsverity_free_hash_request(vi->tree_params.hash_alg, req); return valid; } -EXPORT_SYMBOL_GPL(fsverity_verify_page); +EXPORT_SYMBOL_GPL(fsverity_verify_blocks); #ifdef CONFIG_BLOCK /** * fsverity_verify_bio() - verify a 'read' bio that has just completed * @bio: the bio to verify * - * Verify a set of pages that have just been read from a verity file. The pages - * must be pagecache pages that are still locked and not yet uptodate. If a - * page fails verification, then bio->bi_status is set to an error status. + * Verify the bio's data against the file's Merkle tree. All bio data segments + * must be aligned to the file's Merkle tree block size. If any data fails + * verification, then bio->bi_status is set to an error status. * * This is a helper function for use by the ->readahead() method of filesystems * that issue bios to read data directly into the page cache. Filesystems that @@ -212,15 +338,13 @@ EXPORT_SYMBOL_GPL(fsverity_verify_page); void fsverity_verify_bio(struct bio *bio) { struct inode *inode = bio_first_page_all(bio)->mapping->host; - const struct fsverity_info *vi = inode->i_verity_info; - const struct merkle_tree_params *params = &vi->tree_params; + struct fsverity_info *vi = inode->i_verity_info; struct ahash_request *req; - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; unsigned long max_ra_pages = 0; /* This allocation never fails, since it's mempool-backed. */ - req = fsverity_alloc_hash_request(params->hash_alg, GFP_NOFS); + req = fsverity_alloc_hash_request(vi->tree_params.hash_alg, GFP_NOFS); if (bio->bi_opf & REQ_RAHEAD) { /* @@ -232,24 +356,18 @@ void fsverity_verify_bio(struct bio *bio) * This improves sequential read performance, as it greatly * reduces the number of I/O requests made to the Merkle tree. */ - bio_for_each_segment_all(bv, bio, iter_all) - max_ra_pages++; - max_ra_pages /= 4; + max_ra_pages = bio->bi_iter.bi_size >> (PAGE_SHIFT + 2); } - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; - unsigned long level0_index = page->index >> params->log_arity; - unsigned long level0_ra_pages = - min(max_ra_pages, params->level0_blocks - level0_index); - - if (!verify_page(inode, vi, req, page, level0_ra_pages)) { + bio_for_each_folio_all(fi, bio) { + if (!verify_data_blocks(inode, vi, req, fi.folio, fi.length, + fi.offset, max_ra_pages)) { bio->bi_status = BLK_STS_IOERR; break; } } - fsverity_free_hash_request(params->hash_alg, req); + fsverity_free_hash_request(vi->tree_params.hash_alg, req); } EXPORT_SYMBOL_GPL(fsverity_verify_bio); #endif /* CONFIG_BLOCK */ diff --git a/fs/xattr.c b/fs/xattr.c index adab9a70b536..14a7eb3c8fa8 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -9,6 +9,7 @@ Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> @@ -82,7 +83,7 @@ xattr_resolve_name(struct inode *inode, const char **name) /** * may_write_xattr - check whether inode allows writing xattr - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: the inode on which to set an xattr * * Check whether the inode allows writing xattrs. Specifically, we can never @@ -94,13 +95,13 @@ xattr_resolve_name(struct inode *inode, const char **name) * * Return: On success zero is returned. On error a negative errno is returned. */ -int may_write_xattr(struct user_namespace *mnt_userns, struct inode *inode) +int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode) { if (IS_IMMUTABLE(inode)) return -EPERM; if (IS_APPEND(inode)) return -EPERM; - if (HAS_UNMAPPED_ID(mnt_userns, inode)) + if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; return 0; } @@ -110,13 +111,13 @@ int may_write_xattr(struct user_namespace *mnt_userns, struct inode *inode) * because different namespaces have very different rules. */ static int -xattr_permission(struct user_namespace *mnt_userns, struct inode *inode, +xattr_permission(struct mnt_idmap *idmap, struct inode *inode, const char *name, int mask) { if (mask & MAY_WRITE) { int ret; - ret = may_write_xattr(mnt_userns, inode); + ret = may_write_xattr(idmap, inode); if (ret) return ret; } @@ -148,11 +149,11 @@ xattr_permission(struct user_namespace *mnt_userns, struct inode *inode, return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && - !inode_owner_or_capable(mnt_userns, inode)) + !inode_owner_or_capable(idmap, inode)) return -EPERM; } - return inode_permission(mnt_userns, inode, mask); + return inode_permission(idmap, inode, mask); } /* @@ -183,7 +184,7 @@ xattr_supported_namespace(struct inode *inode, const char *prefix) EXPORT_SYMBOL(xattr_supported_namespace); int -__vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, +__vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { @@ -199,7 +200,7 @@ __vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ - return handler->set(handler, mnt_userns, dentry, inode, name, value, + return handler->set(handler, idmap, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); @@ -208,7 +209,7 @@ EXPORT_SYMBOL(__vfs_setxattr); * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to @@ -221,7 +222,7 @@ EXPORT_SYMBOL(__vfs_setxattr); * is executed. It also assumes that the caller will make the appropriate * permission checks. */ -int __vfs_setxattr_noperm(struct user_namespace *mnt_userns, +int __vfs_setxattr_noperm(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { @@ -233,7 +234,7 @@ int __vfs_setxattr_noperm(struct user_namespace *mnt_userns, if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { - error = __vfs_setxattr(mnt_userns, dentry, inode, name, value, + error = __vfs_setxattr(idmap, dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); @@ -264,7 +265,7 @@ int __vfs_setxattr_noperm(struct user_namespace *mnt_userns, * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * - * @mnt_userns: user namespace of the mount of the target inode + * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to @@ -274,18 +275,18 @@ int __vfs_setxattr_noperm(struct user_namespace *mnt_userns, * a delegation was broken on, NULL if none. */ int -__vfs_setxattr_locked(struct user_namespace *mnt_userns, struct dentry *dentry, +__vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; - error = xattr_permission(mnt_userns, inode, name, MAY_WRITE); + error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; - error = security_inode_setxattr(mnt_userns, dentry, name, value, size, + error = security_inode_setxattr(idmap, dentry, name, value, size, flags); if (error) goto out; @@ -294,7 +295,7 @@ __vfs_setxattr_locked(struct user_namespace *mnt_userns, struct dentry *dentry, if (error) goto out; - error = __vfs_setxattr_noperm(mnt_userns, dentry, name, value, + error = __vfs_setxattr_noperm(idmap, dentry, name, value, size, flags); out: @@ -303,7 +304,7 @@ out: EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int -vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, +vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; @@ -312,7 +313,7 @@ vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, int error; if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { - error = cap_convert_nscap(mnt_userns, dentry, &value, size); + error = cap_convert_nscap(idmap, dentry, &value, size); if (error < 0) return error; size = error; @@ -320,7 +321,7 @@ vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, retry_deleg: inode_lock(inode); - error = __vfs_setxattr_locked(mnt_userns, dentry, name, value, size, + error = __vfs_setxattr_locked(idmap, dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); @@ -337,19 +338,19 @@ retry_deleg: EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t -xattr_getsecurity(struct user_namespace *mnt_userns, struct inode *inode, +xattr_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { - len = security_inode_getsecurity(mnt_userns, inode, name, + len = security_inode_getsecurity(idmap, inode, name, &buffer, false); goto out_noalloc; } - len = security_inode_getsecurity(mnt_userns, inode, name, &buffer, + len = security_inode_getsecurity(idmap, inode, name, &buffer, true); if (len < 0) return len; @@ -374,7 +375,7 @@ out_noalloc: * Returns the result of alloc, if failed, or the getxattr operation. */ int -vfs_getxattr_alloc(struct user_namespace *mnt_userns, struct dentry *dentry, +vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { @@ -383,7 +384,7 @@ vfs_getxattr_alloc(struct user_namespace *mnt_userns, struct dentry *dentry, char *value = *xattr_value; int error; - error = xattr_permission(mnt_userns, inode, name, MAY_READ); + error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; @@ -427,13 +428,13 @@ __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, EXPORT_SYMBOL(__vfs_getxattr); ssize_t -vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry, +vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; - error = xattr_permission(mnt_userns, inode, name, MAY_READ); + error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; @@ -444,7 +445,7 @@ vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - int ret = xattr_getsecurity(mnt_userns, inode, suffix, value, + int ret = xattr_getsecurity(idmap, inode, suffix, value, size); /* * Only overwrite the return value if a security module @@ -480,7 +481,7 @@ vfs_listxattr(struct dentry *dentry, char *list, size_t size) EXPORT_SYMBOL_GPL(vfs_listxattr); int -__vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, +__vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); @@ -494,7 +495,7 @@ __vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; - return handler->set(handler, mnt_userns, dentry, inode, name, NULL, 0, + return handler->set(handler, idmap, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); @@ -503,25 +504,25 @@ EXPORT_SYMBOL(__vfs_removexattr); * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * - * @mnt_userns: user namespace of the mount of the target inode + * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int -__vfs_removexattr_locked(struct user_namespace *mnt_userns, +__vfs_removexattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; - error = xattr_permission(mnt_userns, inode, name, MAY_WRITE); + error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; - error = security_inode_removexattr(mnt_userns, dentry, name); + error = security_inode_removexattr(idmap, dentry, name); if (error) goto out; @@ -529,7 +530,7 @@ __vfs_removexattr_locked(struct user_namespace *mnt_userns, if (error) goto out; - error = __vfs_removexattr(mnt_userns, dentry, name); + error = __vfs_removexattr(idmap, dentry, name); if (!error) { fsnotify_xattr(dentry); @@ -542,7 +543,7 @@ out: EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int -vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, +vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; @@ -551,7 +552,7 @@ vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, retry_deleg: inode_lock(inode); - error = __vfs_removexattr_locked(mnt_userns, dentry, + error = __vfs_removexattr_locked(idmap, dentry, name, &delegated_inode); inode_unlock(inode); @@ -605,7 +606,7 @@ int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, return do_set_acl(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size); - return vfs_setxattr(mnt_idmap_owner(idmap), dentry, ctx->kname->name, + return vfs_setxattr(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size, ctx->flags); } @@ -714,8 +715,7 @@ do_getxattr(struct mnt_idmap *idmap, struct dentry *d, if (is_posix_acl_xattr(ctx->kname->name)) error = do_get_acl(idmap, d, kname, ctx->kvalue, ctx->size); else - error = vfs_getxattr(mnt_idmap_owner(idmap), d, kname, - ctx->kvalue, ctx->size); + error = vfs_getxattr(idmap, d, kname, ctx->kvalue, ctx->size); if (error > 0) { if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error)) error = -EFAULT; @@ -892,9 +892,9 @@ removexattr(struct mnt_idmap *idmap, struct dentry *d, return error; if (is_posix_acl_xattr(kname)) - return vfs_remove_acl(mnt_idmap_owner(idmap), d, kname); + return vfs_remove_acl(idmap, d, kname); - return vfs_removexattr(mnt_idmap_owner(idmap), d, kname); + return vfs_removexattr(idmap, d, kname); } static int path_removexattr(const char __user *pathname, diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index a05f44eb8178..791db7d9c849 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -242,7 +242,7 @@ xfs_acl_set_mode( } int -xfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +xfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { umode_t mode; @@ -258,7 +258,7 @@ xfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, return error; if (type == ACL_TYPE_ACCESS) { - error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl); + error = posix_acl_update_mode(idmap, inode, &mode, &acl); if (error) return error; set_mode = true; diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index dcd176149c7a..bf7f960997d3 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -11,7 +11,7 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type, bool rcu); -extern int xfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int xfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); void xfs_forget_acl(struct inode *inode, const char *name); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 595a5bcf46b9..d06c0cc62f61 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1047,7 +1047,7 @@ xfs_file_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = xfs_vn_setattr_size(file_mnt_user_ns(file), + error = xfs_vn_setattr_size(file_mnt_idmap(file), file_dentry(file), &iattr); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index d354ea2b74f9..7f1d715faab5 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -777,7 +777,7 @@ xfs_inode_inherit_flags2( */ int xfs_init_new_inode( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct xfs_trans *tp, struct xfs_inode *pip, xfs_ino_t ino, @@ -823,11 +823,11 @@ xfs_init_new_inode( ip->i_projid = prid; if (dir && !(dir->i_mode & S_ISGID) && xfs_has_grpid(mp)) { - inode_fsuid_set(inode, mnt_userns); + inode_fsuid_set(inode, idmap); inode->i_gid = dir->i_gid; inode->i_mode = mode; } else { - inode_init_owner(mnt_userns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); } /* @@ -836,7 +836,7 @@ xfs_init_new_inode( * (and only if the irix_sgid_inherit compatibility variable is set). */ if (irix_sgid_inherit && (inode->i_mode & S_ISGID) && - !vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode))) + !vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode))) inode->i_mode &= ~S_ISGID; ip->i_disk_size = 0; @@ -946,7 +946,7 @@ xfs_bumplink( int xfs_create( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, xfs_inode_t *dp, struct xfs_name *name, umode_t mode, @@ -978,8 +978,8 @@ xfs_create( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), - mapped_fsgid(mnt_userns, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns), + mapped_fsgid(idmap, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1020,7 +1020,7 @@ xfs_create( */ error = xfs_dialloc(&tp, dp->i_ino, mode, &ino); if (!error) - error = xfs_init_new_inode(mnt_userns, tp, dp, ino, mode, + error = xfs_init_new_inode(idmap, tp, dp, ino, mode, is_dir ? 2 : 1, rdev, prid, init_xattrs, &ip); if (error) goto out_trans_cancel; @@ -1102,7 +1102,7 @@ xfs_create( int xfs_create_tmpfile( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct xfs_inode *dp, umode_t mode, struct xfs_inode **ipp) @@ -1127,8 +1127,8 @@ xfs_create_tmpfile( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), - mapped_fsgid(mnt_userns, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns), + mapped_fsgid(idmap, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1144,7 +1144,7 @@ xfs_create_tmpfile( error = xfs_dialloc(&tp, dp->i_ino, mode, &ino); if (!error) - error = xfs_init_new_inode(mnt_userns, tp, dp, ino, mode, + error = xfs_init_new_inode(idmap, tp, dp, ino, mode, 0, 0, prid, false, &ip); if (error) goto out_trans_cancel; @@ -2709,7 +2709,7 @@ out_trans_abort: */ static int xfs_rename_alloc_whiteout( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct xfs_name *src_name, struct xfs_inode *dp, struct xfs_inode **wip) @@ -2718,7 +2718,7 @@ xfs_rename_alloc_whiteout( struct qstr name; int error; - error = xfs_create_tmpfile(mnt_userns, dp, S_IFCHR | WHITEOUT_MODE, + error = xfs_create_tmpfile(idmap, dp, S_IFCHR | WHITEOUT_MODE, &tmpfile); if (error) return error; @@ -2750,7 +2750,7 @@ xfs_rename_alloc_whiteout( */ int xfs_rename( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, @@ -2782,7 +2782,7 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - error = xfs_rename_alloc_whiteout(mnt_userns, src_name, + error = xfs_rename_alloc_whiteout(idmap, src_name, target_dp, &wip); if (error) return error; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index fa780f08dc89..69d21e42c10a 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -473,18 +473,18 @@ int xfs_release(struct xfs_inode *ip); void xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, const struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); -int xfs_create(struct user_namespace *mnt_userns, +int xfs_create(struct mnt_idmap *idmap, struct xfs_inode *dp, struct xfs_name *name, umode_t mode, dev_t rdev, bool need_xattr, struct xfs_inode **ipp); -int xfs_create_tmpfile(struct user_namespace *mnt_userns, +int xfs_create_tmpfile(struct mnt_idmap *idmap, struct xfs_inode *dp, umode_t mode, struct xfs_inode **ipp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, struct xfs_name *target_name); -int xfs_rename(struct user_namespace *mnt_userns, +int xfs_rename(struct mnt_idmap *idmap, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, @@ -515,7 +515,7 @@ void xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode, xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); -int xfs_init_new_inode(struct user_namespace *mnt_userns, struct xfs_trans *tp, +int xfs_init_new_inode(struct mnt_idmap *idmap, struct xfs_trans *tp, struct xfs_inode *pip, xfs_ino_t ino, umode_t mode, xfs_nlink_t nlink, dev_t rdev, prid_t prid, bool init_xattrs, struct xfs_inode **ipp); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 736510bc241b..55bb01173cde 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -665,7 +665,7 @@ xfs_ioc_fsbulkstat( struct xfs_fsop_bulkreq bulkreq; struct xfs_ibulk breq = { .mp = mp, - .mnt_userns = file_mnt_user_ns(file), + .idmap = file_mnt_idmap(file), .ocount = 0, }; xfs_ino_t lastino; @@ -844,7 +844,7 @@ xfs_ioc_bulkstat( struct xfs_bulk_ireq hdr; struct xfs_ibulk breq = { .mp = mp, - .mnt_userns = file_mnt_user_ns(file), + .idmap = file_mnt_idmap(file), }; int error; @@ -1297,7 +1297,7 @@ xfs_ioctl_setattr_check_projid( int xfs_fileattr_set( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { @@ -1371,7 +1371,7 @@ xfs_fileattr_set( */ if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) && - !capable_wrt_inode_uidgid(mnt_userns, VFS_I(ip), CAP_FSETID)) + !capable_wrt_inode_uidgid(idmap, VFS_I(ip), CAP_FSETID)) VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID); /* Change the ownerships and register project quota modifications */ diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h index d4abba2c13c1..38be600b5e1e 100644 --- a/fs/xfs/xfs_ioctl.h +++ b/fs/xfs/xfs_ioctl.h @@ -49,7 +49,7 @@ xfs_fileattr_get( extern int xfs_fileattr_set( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 2f54b701eead..ee35eea1ecce 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -204,7 +204,7 @@ xfs_compat_ioc_fsbulkstat( struct xfs_fsop_bulkreq bulkreq; struct xfs_ibulk breq = { .mp = mp, - .mnt_userns = file_mnt_user_ns(file), + .idmap = file_mnt_idmap(file), .ocount = 0, }; xfs_ino_t lastino; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 515318dfbc38..24718adb3c16 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -162,12 +162,12 @@ xfs_create_need_xattr( STATIC int xfs_generic_create( - struct user_namespace *mnt_userns, - struct inode *dir, - struct dentry *dentry, - umode_t mode, - dev_t rdev, - struct file *tmpfile) /* unnamed file */ + struct mnt_idmap *idmap, + struct inode *dir, + struct dentry *dentry, + umode_t mode, + dev_t rdev, + struct file *tmpfile) /* unnamed file */ { struct inode *inode; struct xfs_inode *ip = NULL; @@ -196,11 +196,11 @@ xfs_generic_create( goto out_free_acl; if (!tmpfile) { - error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev, + error = xfs_create(idmap, XFS_I(dir), &name, mode, rdev, xfs_create_need_xattr(dir, default_acl, acl), &ip); } else { - error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip); + error = xfs_create_tmpfile(idmap, XFS_I(dir), mode, &ip); } if (unlikely(error)) goto out_free_acl; @@ -255,35 +255,34 @@ xfs_generic_create( STATIC int xfs_vn_mknod( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { - return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, NULL); + return xfs_generic_create(idmap, dir, dentry, mode, rdev, NULL); } STATIC int xfs_vn_create( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool flags) { - return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, NULL); + return xfs_generic_create(idmap, dir, dentry, mode, 0, NULL); } STATIC int xfs_vn_mkdir( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0, - NULL); + return xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL); } STATIC struct dentry * @@ -400,7 +399,7 @@ xfs_vn_unlink( STATIC int xfs_vn_symlink( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) @@ -417,7 +416,7 @@ xfs_vn_symlink( if (unlikely(error)) goto out; - error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip); + error = xfs_symlink(idmap, XFS_I(dir), &name, symname, mode, &cip); if (unlikely(error)) goto out; @@ -443,7 +442,7 @@ xfs_vn_symlink( STATIC int xfs_vn_rename( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *odir, struct dentry *odentry, struct inode *ndir, @@ -472,7 +471,7 @@ xfs_vn_rename( if (unlikely(error)) return error; - return xfs_rename(mnt_userns, XFS_I(odir), &oname, + return xfs_rename(idmap, XFS_I(odir), &oname, XFS_I(d_inode(odentry)), XFS_I(ndir), &nname, new_inode ? XFS_I(new_inode) : NULL, flags); } @@ -549,7 +548,7 @@ xfs_stat_blksize( STATIC int xfs_vn_getattr( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, @@ -558,8 +557,8 @@ xfs_vn_getattr( struct inode *inode = d_inode(path->dentry); struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); - vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); trace_xfs_getattr(ip); @@ -627,7 +626,7 @@ xfs_vn_getattr( static int xfs_vn_change_ok( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { @@ -639,7 +638,7 @@ xfs_vn_change_ok( if (xfs_is_shutdown(mp)) return -EIO; - return setattr_prepare(mnt_userns, dentry, iattr); + return setattr_prepare(idmap, dentry, iattr); } /* @@ -650,7 +649,7 @@ xfs_vn_change_ok( */ static int xfs_setattr_nonsize( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct xfs_inode *ip, struct iattr *iattr) @@ -679,14 +678,14 @@ xfs_setattr_nonsize( uint qflags = 0; if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) { - uid = from_vfsuid(mnt_userns, i_user_ns(inode), + uid = from_vfsuid(idmap, i_user_ns(inode), iattr->ia_vfsuid); qflags |= XFS_QMOPT_UQUOTA; } else { uid = inode->i_uid; } if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) { - gid = from_vfsgid(mnt_userns, i_user_ns(inode), + gid = from_vfsgid(idmap, i_user_ns(inode), iattr->ia_vfsgid); qflags |= XFS_QMOPT_GQUOTA; } else { @@ -719,18 +718,18 @@ xfs_setattr_nonsize( * also. */ if (XFS_IS_UQUOTA_ON(mp) && - i_uid_needs_update(mnt_userns, iattr, inode)) { + i_uid_needs_update(idmap, iattr, inode)) { ASSERT(udqp); old_udqp = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp); } if (XFS_IS_GQUOTA_ON(mp) && - i_gid_needs_update(mnt_userns, iattr, inode)) { + i_gid_needs_update(idmap, iattr, inode)) { ASSERT(xfs_has_pquotino(mp) || !XFS_IS_PQUOTA_ON(mp)); ASSERT(gdqp); old_gdqp = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp); } - setattr_copy(mnt_userns, inode, iattr); + setattr_copy(idmap, inode, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(mp, xs_ig_attrchg); @@ -758,7 +757,7 @@ xfs_setattr_nonsize( * Posix ACL code seems to care about this issue either. */ if (mask & ATTR_MODE) { - error = posix_acl_chmod(mnt_userns, dentry, inode->i_mode); + error = posix_acl_chmod(idmap, dentry, inode->i_mode); if (error) return error; } @@ -779,7 +778,7 @@ out_dqrele: */ STATIC int xfs_setattr_size( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct xfs_inode *ip, struct iattr *iattr) @@ -812,7 +811,7 @@ xfs_setattr_size( * Use the regular setattr path to update the timestamps. */ iattr->ia_valid &= ~ATTR_SIZE; - return xfs_setattr_nonsize(mnt_userns, dentry, ip, iattr); + return xfs_setattr_nonsize(idmap, dentry, ip, iattr); } /* @@ -956,7 +955,7 @@ xfs_setattr_size( } ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); - setattr_copy(mnt_userns, inode, iattr); + setattr_copy(idmap, inode, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(mp, xs_ig_attrchg); @@ -977,7 +976,7 @@ out_trans_cancel: int xfs_vn_setattr_size( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { @@ -986,15 +985,15 @@ xfs_vn_setattr_size( trace_xfs_setattr(ip); - error = xfs_vn_change_ok(mnt_userns, dentry, iattr); + error = xfs_vn_change_ok(idmap, dentry, iattr); if (error) return error; - return xfs_setattr_size(mnt_userns, dentry, ip, iattr); + return xfs_setattr_size(idmap, dentry, ip, iattr); } STATIC int xfs_vn_setattr( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { @@ -1014,14 +1013,14 @@ xfs_vn_setattr( return error; } - error = xfs_vn_setattr_size(mnt_userns, dentry, iattr); + error = xfs_vn_setattr_size(idmap, dentry, iattr); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); } else { trace_xfs_setattr(ip); - error = xfs_vn_change_ok(mnt_userns, dentry, iattr); + error = xfs_vn_change_ok(idmap, dentry, iattr); if (!error) - error = xfs_setattr_nonsize(mnt_userns, dentry, ip, iattr); + error = xfs_setattr_nonsize(idmap, dentry, ip, iattr); } return error; @@ -1092,12 +1091,12 @@ xfs_vn_fiemap( STATIC int xfs_vn_tmpfile( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { - int err = xfs_generic_create(mnt_userns, dir, file->f_path.dentry, mode, 0, file); + int err = xfs_generic_create(idmap, dir, file->f_path.dentry, mode, 0, file); return finish_open_simple(file, err); } diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index e570dcb5df8d..7f84a0843b24 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -13,7 +13,7 @@ extern const struct file_operations xfs_dir_file_operations; extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); -int xfs_vn_setattr_size(struct user_namespace *mnt_userns, +int xfs_vn_setattr_size(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *vap); int xfs_inode_init_security(struct inode *inode, struct inode *dir, diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index a1c2bcf65d37..f225413a993c 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -55,7 +55,7 @@ struct xfs_bstat_chunk { STATIC int xfs_bulkstat_one_int( struct xfs_mount *mp, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct xfs_trans *tp, xfs_ino_t ino, struct xfs_bstat_chunk *bc) @@ -83,8 +83,8 @@ xfs_bulkstat_one_int( ASSERT(ip != NULL); ASSERT(ip->i_imap.im_blkno != 0); inode = VFS_I(ip); - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); - vfsgid = i_gid_into_vfsgid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid = i_gid_into_vfsgid(idmap, inode); /* xfs_iget returns the following without needing * further change. @@ -178,7 +178,7 @@ xfs_bulkstat_one( struct xfs_trans *tp; int error; - if (breq->mnt_userns != &init_user_ns) { + if (breq->idmap != &nop_mnt_idmap) { xfs_warn_ratelimited(breq->mp, "bulkstat not supported inside of idmapped mounts."); return -EINVAL; @@ -199,7 +199,7 @@ xfs_bulkstat_one( if (error) goto out; - error = xfs_bulkstat_one_int(breq->mp, breq->mnt_userns, tp, + error = xfs_bulkstat_one_int(breq->mp, breq->idmap, tp, breq->startino, &bc); xfs_trans_cancel(tp); out: @@ -225,7 +225,7 @@ xfs_bulkstat_iwalk( struct xfs_bstat_chunk *bc = data; int error; - error = xfs_bulkstat_one_int(mp, bc->breq->mnt_userns, tp, ino, data); + error = xfs_bulkstat_one_int(mp, bc->breq->idmap, tp, ino, data); /* bulkstat just skips over missing inodes */ if (error == -ENOENT || error == -EINVAL) return 0; @@ -270,7 +270,7 @@ xfs_bulkstat( unsigned int iwalk_flags = 0; int error; - if (breq->mnt_userns != &init_user_ns) { + if (breq->idmap != &nop_mnt_idmap) { xfs_warn_ratelimited(breq->mp, "bulkstat not supported inside of idmapped mounts."); return -EINVAL; diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h index e2d0eba43f35..1659f13f17a8 100644 --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -8,7 +8,7 @@ /* In-memory representation of a userspace request for batch inode data. */ struct xfs_ibulk { struct xfs_mount *mp; - struct user_namespace *mnt_userns; + struct mnt_idmap *idmap; void __user *ubuffer; /* user output buffer */ xfs_ino_t startino; /* start with this inode */ unsigned int icount; /* number of elements in ubuffer */ diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index f9878021e7d0..e88f18f85e4b 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -34,6 +34,7 @@ typedef __u32 xfs_nlink_t; #include <linux/module.h> #include <linux/mutex.h> #include <linux/file.h> +#include <linux/filelock.h> #include <linux/swap.h> #include <linux/errno.h> #include <linux/sched/signal.h> diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 38d23f0e703a..23d16186e1a3 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -322,7 +322,7 @@ xfs_fs_commit_blocks( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); if (update_isize) { i_size_write(inode, iattr->ia_size); ip->i_disk_size = iattr->ia_size; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index e2c542f6dcd4..7dc0db7f5a76 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -787,7 +787,7 @@ xfs_qm_qino_alloc( error = xfs_dialloc(&tp, 0, S_IFREG, &ino); if (!error) - error = xfs_init_new_inode(&init_user_ns, tp, NULL, ino, + error = xfs_init_new_inode(&nop_mnt_idmap, tp, NULL, ino, S_IFREG, 1, 0, 0, false, ipp); if (error) { xfs_trans_cancel(tp); diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 8389f3ef88ef..85e433df6a3f 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -144,7 +144,7 @@ xfs_readlink( int xfs_symlink( - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct xfs_inode *dp, struct xfs_name *link_name, const char *target_path, @@ -193,8 +193,8 @@ xfs_symlink( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), - mapped_fsgid(mnt_userns, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns), + mapped_fsgid(idmap, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -231,7 +231,7 @@ xfs_symlink( */ error = xfs_dialloc(&tp, dp->i_ino, S_IFLNK, &ino); if (!error) - error = xfs_init_new_inode(mnt_userns, tp, dp, ino, + error = xfs_init_new_inode(idmap, tp, dp, ino, S_IFLNK | (mode & ~S_IFMT), 1, 0, prid, false, &ip); if (error) diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h index 2586b7e393f3..d1ca1ce62a93 100644 --- a/fs/xfs/xfs_symlink.h +++ b/fs/xfs/xfs_symlink.h @@ -7,7 +7,7 @@ /* Kernel only symlink definitions */ -int xfs_symlink(struct user_namespace *mnt_userns, struct xfs_inode *dp, +int xfs_symlink(struct mnt_idmap *idmap, struct xfs_inode *dp, struct xfs_name *link_name, const char *target_path, umode_t mode, struct xfs_inode **ipp); int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link); diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 10aa1fd39d2b..7b9a0ed1b11f 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -133,7 +133,7 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused, static int xfs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, struct dentry *unused, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index a9c5c3f720ad..72ef97320b99 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -604,7 +604,7 @@ unlock: return ret; } -static int zonefs_inode_setattr(struct user_namespace *mnt_userns, +static int zonefs_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); @@ -613,7 +613,7 @@ static int zonefs_inode_setattr(struct user_namespace *mnt_userns, if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; - ret = setattr_prepare(&init_user_ns, dentry, iattr); + ret = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (ret) return ret; @@ -630,7 +630,7 @@ static int zonefs_inode_setattr(struct user_namespace *mnt_userns, !uid_eq(iattr->ia_uid, inode->i_uid)) || ((iattr->ia_valid & ATTR_GID) && !gid_eq(iattr->ia_gid, inode->i_gid))) { - ret = dquot_transfer(mnt_userns, inode, iattr); + ret = dquot_transfer(&nop_mnt_idmap, inode, iattr); if (ret) return ret; } @@ -641,7 +641,7 @@ static int zonefs_inode_setattr(struct user_namespace *mnt_userns, return ret; } - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); return 0; } @@ -1427,7 +1427,7 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode, struct super_block *sb = parent->i_sb; inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1; - inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555); + inode_init_owner(&nop_mnt_idmap, inode, parent, S_IFDIR | 0555); inode->i_op = &zonefs_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index 7b9571e00cc4..832c6464f063 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -443,6 +443,7 @@ struct acpi_tpm2_phy { #define ACPI_TPM2_RESERVED10 10 #define ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC 11 /* V1.2 Rev 8 */ #define ACPI_TPM2_RESERVED 12 +#define ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON 13 /* Optional trailer appears after any start_method subtables */ diff --git a/include/linux/audit.h b/include/linux/audit.h index 3608992848d3..31086a72e32a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -14,6 +14,7 @@ #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> +#include <uapi/linux/fanotify.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) @@ -416,7 +417,7 @@ extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); -extern void __audit_fanotify(unsigned int response); +extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, @@ -523,10 +524,10 @@ static inline void audit_log_kern_module(char *name) __audit_log_kern_module(name); } -static inline void audit_fanotify(unsigned int response) +static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (!audit_dummy_context()) - __audit_fanotify(response); + __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) @@ -679,7 +680,7 @@ static inline void audit_log_kern_module(char *name) { } -static inline void audit_fanotify(unsigned int response) +static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) diff --git a/include/linux/capability.h b/include/linux/capability.h index 65efb74c3585..03c2a613ad40 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -42,6 +42,7 @@ struct inode; struct dentry; struct task_struct; struct user_namespace; +struct mnt_idmap; extern const kernel_cap_t __cap_empty_set; extern const kernel_cap_t __cap_init_eff_set; @@ -248,9 +249,9 @@ static inline bool ns_capable_setid(struct user_namespace *ns, int cap) } #endif /* CONFIG_MULTIUSER */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const struct inode *inode); -bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, +bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); @@ -271,11 +272,11 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) } /* audit system wants to get cap info from files as well */ -int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, +int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, +int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/evm.h b/include/linux/evm.h index 7a9ee2157f69..7dc1ee74169f 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -21,34 +21,34 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, void *xattr_value, size_t xattr_value_len, struct integrity_iint_cache *iint); -extern int evm_inode_setattr(struct user_namespace *mnt_userns, +extern int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); -extern int evm_inode_setxattr(struct user_namespace *mnt_userns, +extern int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size); extern void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); -extern int evm_inode_removexattr(struct user_namespace *mnt_userns, +extern int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name); extern void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name); -static inline void evm_inode_post_remove_acl(struct user_namespace *mnt_userns, +static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { evm_inode_post_removexattr(dentry, acl_name); } -extern int evm_inode_set_acl(struct user_namespace *mnt_userns, +extern int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -static inline int evm_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { - return evm_inode_set_acl(mnt_userns, dentry, acl_name, NULL); + return evm_inode_set_acl(idmap, dentry, acl_name, NULL); } static inline void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, @@ -90,7 +90,7 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif -static inline int evm_inode_setattr(struct user_namespace *mnt_userns, +static inline int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return 0; @@ -101,7 +101,7 @@ static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) return; } -static inline int evm_inode_setxattr(struct user_namespace *mnt_userns, +static inline int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size) { @@ -116,7 +116,7 @@ static inline void evm_inode_post_setxattr(struct dentry *dentry, return; } -static inline int evm_inode_removexattr(struct user_namespace *mnt_userns, +static inline int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { @@ -129,21 +129,21 @@ static inline void evm_inode_post_removexattr(struct dentry *dentry, return; } -static inline void evm_inode_post_remove_acl(struct user_namespace *mnt_userns, +static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return; } -static inline int evm_inode_set_acl(struct user_namespace *mnt_userns, +static inline int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return 0; } -static inline int evm_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index fe848901fcc3..9f4d4bcbf251 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -213,7 +213,6 @@ struct export_operations { bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); - u64 (*fetch_iversion)(struct inode *); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 8ad743def6f3..4f1c4f603118 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -122,6 +122,11 @@ #define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ FANOTIFY_EVENT_FLAGS) +/* These masks check for invalid bits in permission responses. */ +#define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY) +#define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO) +#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS) + /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS #undef FAN_ALL_INIT_FLAGS diff --git a/include/linux/fb.h b/include/linux/fb.h index 96b96323e9cb..73eb1f85ea8e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -662,6 +662,7 @@ extern int fb_deferred_io_init(struct fb_info *info); extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); +extern void fb_deferred_io_release(struct fb_info *info); extern void fb_deferred_io_cleanup(struct fb_info *info); extern int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h index 9e37e063ac69..47c05a9851d0 100644 --- a/include/linux/fileattr.h +++ b/include/linux/fileattr.h @@ -53,7 +53,7 @@ static inline bool fileattr_has_fsx(const struct fileattr *fa) } int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); #endif /* _LINUX_FILEATTR_H */ diff --git a/include/linux/filelock.h b/include/linux/filelock.h new file mode 100644 index 000000000000..efcdd1631d9b --- /dev/null +++ b/include/linux/filelock.h @@ -0,0 +1,439 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FILELOCK_H +#define _LINUX_FILELOCK_H + +#include <linux/fs.h> + +#define FL_POSIX 1 +#define FL_FLOCK 2 +#define FL_DELEG 4 /* NFSv4 delegation */ +#define FL_ACCESS 8 /* not trying to lock, just looking */ +#define FL_EXISTS 16 /* when unlocking, test for existence */ +#define FL_LEASE 32 /* lease held on this file */ +#define FL_CLOSE 64 /* unlock on close */ +#define FL_SLEEP 128 /* A blocking lock */ +#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ +#define FL_UNLOCK_PENDING 512 /* Lease is being broken */ +#define FL_OFDLCK 1024 /* lock is "owned" by struct file */ +#define FL_LAYOUT 2048 /* outstanding pNFS layout */ +#define FL_RECLAIM 4096 /* reclaiming from a reboot server */ + +#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) + +/* + * Special return value from posix_lock_file() and vfs_lock_file() for + * asynchronous locking. + */ +#define FILE_LOCK_DEFERRED 1 + +struct file_lock; + +struct file_lock_operations { + void (*fl_copy_lock)(struct file_lock *, struct file_lock *); + void (*fl_release_private)(struct file_lock *); +}; + +struct lock_manager_operations { + void *lm_mod_owner; + fl_owner_t (*lm_get_owner)(fl_owner_t); + void (*lm_put_owner)(fl_owner_t); + void (*lm_notify)(struct file_lock *); /* unblock callback */ + int (*lm_grant)(struct file_lock *, int); + bool (*lm_break)(struct file_lock *); + int (*lm_change)(struct file_lock *, int, struct list_head *); + void (*lm_setup)(struct file_lock *, void **); + bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *cfl); + void (*lm_expire_lock)(void); +}; + +struct lock_manager { + struct list_head list; + /* + * NFSv4 and up also want opens blocked during the grace period; + * NLM doesn't care: + */ + bool block_opens; +}; + +struct net; +void locks_start_grace(struct net *, struct lock_manager *); +void locks_end_grace(struct lock_manager *); +bool locks_in_grace(struct net *); +bool opens_in_grace(struct net *); + +/* + * struct file_lock has a union that some filesystems use to track + * their own private info. The NFS side of things is defined here: + */ +#include <linux/nfs_fs_i.h> + +/* + * struct file_lock represents a generic "file lock". It's used to represent + * POSIX byte range locks, BSD (flock) locks, and leases. It's important to + * note that the same struct is used to represent both a request for a lock and + * the lock itself, but the same object is never used for both. + * + * FIXME: should we create a separate "struct lock_request" to help distinguish + * these two uses? + * + * The varous i_flctx lists are ordered by: + * + * 1) lock owner + * 2) lock range start + * 3) lock range end + * + * Obviously, the last two criteria only matter for POSIX locks. + */ +struct file_lock { + struct file_lock *fl_blocker; /* The lock, that is blocking us */ + struct list_head fl_list; /* link into file_lock_context */ + struct hlist_node fl_link; /* node in global lists */ + struct list_head fl_blocked_requests; /* list of requests with + * ->fl_blocker pointing here + */ + struct list_head fl_blocked_member; /* node in + * ->fl_blocker->fl_blocked_requests + */ + fl_owner_t fl_owner; + unsigned int fl_flags; + unsigned char fl_type; + unsigned int fl_pid; + int fl_link_cpu; /* what cpu's list is this on? */ + wait_queue_head_t fl_wait; + struct file *fl_file; + loff_t fl_start; + loff_t fl_end; + + struct fasync_struct * fl_fasync; /* for lease break notifications */ + /* for lease breaks: */ + unsigned long fl_break_time; + unsigned long fl_downgrade_time; + + const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ + const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ + union { + struct nfs_lock_info nfs_fl; + struct nfs4_lock_info nfs4_fl; + struct { + struct list_head link; /* link in AFS vnode's pending_locks list */ + int state; /* state of grant or error if -ve */ + unsigned int debug_id; + } afs; + struct { + struct inode *inode; + } ceph; + } fl_u; +} __randomize_layout; + +struct file_lock_context { + spinlock_t flc_lock; + struct list_head flc_flock; + struct list_head flc_posix; + struct list_head flc_lease; +}; + +#ifdef CONFIG_FILE_LOCKING +int fcntl_getlk(struct file *, unsigned int, struct flock *); +int fcntl_setlk(unsigned int, struct file *, unsigned int, + struct flock *); + +#if BITS_PER_LONG == 32 +int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); +int fcntl_setlk64(unsigned int, struct file *, unsigned int, + struct flock64 *); +#endif + +int fcntl_setlease(unsigned int fd, struct file *filp, long arg); +int fcntl_getlease(struct file *filp); + +/* fs/locks.c */ +void locks_free_lock_context(struct inode *inode); +void locks_free_lock(struct file_lock *fl); +void locks_init_lock(struct file_lock *); +struct file_lock * locks_alloc_lock(void); +void locks_copy_lock(struct file_lock *, struct file_lock *); +void locks_copy_conflock(struct file_lock *, struct file_lock *); +void locks_remove_posix(struct file *, fl_owner_t); +void locks_remove_file(struct file *); +void locks_release_private(struct file_lock *); +void posix_test_lock(struct file *, struct file_lock *); +int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); +int locks_delete_block(struct file_lock *); +int vfs_test_lock(struct file *, struct file_lock *); +int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); +int vfs_cancel_lock(struct file *filp, struct file_lock *fl); +bool vfs_inode_has_locks(struct inode *inode); +int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); +int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); +void lease_get_mtime(struct inode *, struct timespec64 *time); +int generic_setlease(struct file *, long, struct file_lock **, void **priv); +int vfs_setlease(struct file *, long, struct file_lock **, void **); +int lease_modify(struct file_lock *, int, struct list_head *); + +struct notifier_block; +int lease_register_notifier(struct notifier_block *); +void lease_unregister_notifier(struct notifier_block *); + +struct files_struct; +void show_fd_locks(struct seq_file *f, + struct file *filp, struct files_struct *files); +bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner); + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return smp_load_acquire(&inode->i_flctx); +} + +#else /* !CONFIG_FILE_LOCKING */ +static inline int fcntl_getlk(struct file *file, unsigned int cmd, + struct flock __user *user) +{ + return -EINVAL; +} + +static inline int fcntl_setlk(unsigned int fd, struct file *file, + unsigned int cmd, struct flock __user *user) +{ + return -EACCES; +} + +#if BITS_PER_LONG == 32 +static inline int fcntl_getlk64(struct file *file, unsigned int cmd, + struct flock64 *user) +{ + return -EINVAL; +} + +static inline int fcntl_setlk64(unsigned int fd, struct file *file, + unsigned int cmd, struct flock64 *user) +{ + return -EACCES; +} +#endif +static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) +{ + return -EINVAL; +} + +static inline int fcntl_getlease(struct file *filp) +{ + return F_UNLCK; +} + +static inline void +locks_free_lock_context(struct inode *inode) +{ +} + +static inline void locks_init_lock(struct file_lock *fl) +{ + return; +} + +static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) +{ + return; +} + +static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) +{ + return; +} + +static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) +{ + return; +} + +static inline void locks_remove_file(struct file *filp) +{ + return; +} + +static inline void posix_test_lock(struct file *filp, struct file_lock *fl) +{ + return; +} + +static inline int posix_lock_file(struct file *filp, struct file_lock *fl, + struct file_lock *conflock) +{ + return -ENOLCK; +} + +static inline int locks_delete_block(struct file_lock *waiter) +{ + return -ENOENT; +} + +static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) +{ + return 0; +} + +static inline int vfs_lock_file(struct file *filp, unsigned int cmd, + struct file_lock *fl, struct file_lock *conf) +{ + return -ENOLCK; +} + +static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) +{ + return 0; +} + +static inline bool vfs_inode_has_locks(struct inode *inode) +{ + return false; +} + +static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) +{ + return -ENOLCK; +} + +static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) +{ + return 0; +} + +static inline void lease_get_mtime(struct inode *inode, + struct timespec64 *time) +{ + return; +} + +static inline int generic_setlease(struct file *filp, long arg, + struct file_lock **flp, void **priv) +{ + return -EINVAL; +} + +static inline int vfs_setlease(struct file *filp, long arg, + struct file_lock **lease, void **priv) +{ + return -EINVAL; +} + +static inline int lease_modify(struct file_lock *fl, int arg, + struct list_head *dispose) +{ + return -EINVAL; +} + +struct files_struct; +static inline void show_fd_locks(struct seq_file *f, + struct file *filp, struct files_struct *files) {} +static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + return false; +} + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return NULL; +} + +#endif /* !CONFIG_FILE_LOCKING */ + +static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return locks_lock_inode_wait(file_inode(filp), fl); +} + +#ifdef CONFIG_FILE_LOCKING +static inline int break_lease(struct inode *inode, unsigned int mode) +{ + /* + * Since this check is lockless, we must ensure that any refcounts + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. + */ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, mode, FL_LEASE); + return 0; +} + +static inline int break_deleg(struct inode *inode, unsigned int mode) +{ + /* + * Since this check is lockless, we must ensure that any refcounts + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. + */ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, mode, FL_DELEG); + return 0; +} + +static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +{ + int ret; + + ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); + if (ret == -EWOULDBLOCK && delegated_inode) { + *delegated_inode = inode; + ihold(inode); + } + return ret; +} + +static inline int break_deleg_wait(struct inode **delegated_inode) +{ + int ret; + + ret = break_deleg(*delegated_inode, O_WRONLY); + iput(*delegated_inode); + *delegated_inode = NULL; + return ret; +} + +static inline int break_layout(struct inode *inode, bool wait) +{ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, + wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, + FL_LAYOUT); + return 0; +} + +#else /* !CONFIG_FILE_LOCKING */ +static inline int break_lease(struct inode *inode, unsigned int mode) +{ + return 0; +} + +static inline int break_deleg(struct inode *inode, unsigned int mode) +{ + return 0; +} + +static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +{ + return 0; +} + +static inline int break_deleg_wait(struct inode **delegated_inode) +{ + BUG(); + return 0; +} + +static inline int break_layout(struct inode *inode, bool wait) +{ + return 0; +} + +#endif /* CONFIG_FILE_LOCKING */ + +#endif /* _LINUX_FILELOCK_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index c1769a2c5d70..2acc46fb5f97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1003,135 +1003,11 @@ static inline struct file *get_file(struct file *f) #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif -#define FL_POSIX 1 -#define FL_FLOCK 2 -#define FL_DELEG 4 /* NFSv4 delegation */ -#define FL_ACCESS 8 /* not trying to lock, just looking */ -#define FL_EXISTS 16 /* when unlocking, test for existence */ -#define FL_LEASE 32 /* lease held on this file */ -#define FL_CLOSE 64 /* unlock on close */ -#define FL_SLEEP 128 /* A blocking lock */ -#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ -#define FL_UNLOCK_PENDING 512 /* Lease is being broken */ -#define FL_OFDLCK 1024 /* lock is "owned" by struct file */ -#define FL_LAYOUT 2048 /* outstanding pNFS layout */ -#define FL_RECLAIM 4096 /* reclaiming from a reboot server */ - -#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) - -/* - * Special return value from posix_lock_file() and vfs_lock_file() for - * asynchronous locking. - */ -#define FILE_LOCK_DEFERRED 1 - /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; -struct file_lock_operations { - void (*fl_copy_lock)(struct file_lock *, struct file_lock *); - void (*fl_release_private)(struct file_lock *); -}; - -struct lock_manager_operations { - void *lm_mod_owner; - fl_owner_t (*lm_get_owner)(fl_owner_t); - void (*lm_put_owner)(fl_owner_t); - void (*lm_notify)(struct file_lock *); /* unblock callback */ - int (*lm_grant)(struct file_lock *, int); - bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock *, int, struct list_head *); - void (*lm_setup)(struct file_lock *, void **); - bool (*lm_breaker_owns_lease)(struct file_lock *); - bool (*lm_lock_expirable)(struct file_lock *cfl); - void (*lm_expire_lock)(void); -}; - -struct lock_manager { - struct list_head list; - /* - * NFSv4 and up also want opens blocked during the grace period; - * NLM doesn't care: - */ - bool block_opens; -}; - -struct net; -void locks_start_grace(struct net *, struct lock_manager *); -void locks_end_grace(struct lock_manager *); -bool locks_in_grace(struct net *); -bool opens_in_grace(struct net *); - -/* that will die - we need it for nfs_lock_info */ -#include <linux/nfs_fs_i.h> - -/* - * struct file_lock represents a generic "file lock". It's used to represent - * POSIX byte range locks, BSD (flock) locks, and leases. It's important to - * note that the same struct is used to represent both a request for a lock and - * the lock itself, but the same object is never used for both. - * - * FIXME: should we create a separate "struct lock_request" to help distinguish - * these two uses? - * - * The varous i_flctx lists are ordered by: - * - * 1) lock owner - * 2) lock range start - * 3) lock range end - * - * Obviously, the last two criteria only matter for POSIX locks. - */ -struct file_lock { - struct file_lock *fl_blocker; /* The lock, that is blocking us */ - struct list_head fl_list; /* link into file_lock_context */ - struct hlist_node fl_link; /* node in global lists */ - struct list_head fl_blocked_requests; /* list of requests with - * ->fl_blocker pointing here - */ - struct list_head fl_blocked_member; /* node in - * ->fl_blocker->fl_blocked_requests - */ - fl_owner_t fl_owner; - unsigned int fl_flags; - unsigned char fl_type; - unsigned int fl_pid; - int fl_link_cpu; /* what cpu's list is this on? */ - wait_queue_head_t fl_wait; - struct file *fl_file; - loff_t fl_start; - loff_t fl_end; - - struct fasync_struct * fl_fasync; /* for lease break notifications */ - /* for lease breaks: */ - unsigned long fl_break_time; - unsigned long fl_downgrade_time; - - const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ - const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ - union { - struct nfs_lock_info nfs_fl; - struct nfs4_lock_info nfs4_fl; - struct { - struct list_head link; /* link in AFS vnode's pending_locks list */ - int state; /* state of grant or error if -ve */ - unsigned int debug_id; - } afs; - struct { - struct inode *inode; - } ceph; - } fl_u; -} __randomize_layout; - -struct file_lock_context { - spinlock_t flc_lock; - struct list_head flc_flock; - struct list_head flc_posix; - struct list_head flc_lease; -}; - /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) @@ -1140,216 +1016,6 @@ struct file_lock_context { extern void send_sigio(struct fown_struct *fown, int fd, int band); -#define locks_inode(f) file_inode(f) - -#ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, unsigned int, struct flock *); -extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock *); - -#if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); -extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 *); -#endif - -extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); -extern int fcntl_getlease(struct file *filp); - -/* fs/locks.c */ -void locks_free_lock_context(struct inode *inode); -void locks_free_lock(struct file_lock *fl); -extern void locks_init_lock(struct file_lock *); -extern struct file_lock * locks_alloc_lock(void); -extern void locks_copy_lock(struct file_lock *, struct file_lock *); -extern void locks_copy_conflock(struct file_lock *, struct file_lock *); -extern void locks_remove_posix(struct file *, fl_owner_t); -extern void locks_remove_file(struct file *); -extern void locks_release_private(struct file_lock *); -extern void posix_test_lock(struct file *, struct file_lock *); -extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int locks_delete_block(struct file_lock *); -extern int vfs_test_lock(struct file *, struct file_lock *); -extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); -extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); -bool vfs_inode_has_locks(struct inode *inode); -extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); -extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); -extern void lease_get_mtime(struct inode *, struct timespec64 *time); -extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); -extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock *, int, struct list_head *); - -struct notifier_block; -extern int lease_register_notifier(struct notifier_block *); -extern void lease_unregister_notifier(struct notifier_block *); - -struct files_struct; -extern void show_fd_locks(struct seq_file *f, - struct file *filp, struct files_struct *files); -extern bool locks_owner_has_blockers(struct file_lock_context *flctx, - fl_owner_t owner); - -static inline struct file_lock_context * -locks_inode_context(const struct inode *inode) -{ - return smp_load_acquire(&inode->i_flctx); -} - -#else /* !CONFIG_FILE_LOCKING */ -static inline int fcntl_getlk(struct file *file, unsigned int cmd, - struct flock __user *user) -{ - return -EINVAL; -} - -static inline int fcntl_setlk(unsigned int fd, struct file *file, - unsigned int cmd, struct flock __user *user) -{ - return -EACCES; -} - -#if BITS_PER_LONG == 32 -static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 *user) -{ - return -EINVAL; -} - -static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 *user) -{ - return -EACCES; -} -#endif -static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) -{ - return -EINVAL; -} - -static inline int fcntl_getlease(struct file *filp) -{ - return F_UNLCK; -} - -static inline void -locks_free_lock_context(struct inode *inode) -{ -} - -static inline void locks_init_lock(struct file_lock *fl) -{ - return; -} - -static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) -{ - return; -} - -static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) -{ - return; -} - -static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) -{ - return; -} - -static inline void locks_remove_file(struct file *filp) -{ - return; -} - -static inline void posix_test_lock(struct file *filp, struct file_lock *fl) -{ - return; -} - -static inline int posix_lock_file(struct file *filp, struct file_lock *fl, - struct file_lock *conflock) -{ - return -ENOLCK; -} - -static inline int locks_delete_block(struct file_lock *waiter) -{ - return -ENOENT; -} - -static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) -{ - return 0; -} - -static inline int vfs_lock_file(struct file *filp, unsigned int cmd, - struct file_lock *fl, struct file_lock *conf) -{ - return -ENOLCK; -} - -static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) -{ - return 0; -} - -static inline bool vfs_inode_has_locks(struct inode *inode) -{ - return false; -} - -static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) -{ - return -ENOLCK; -} - -static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) -{ - return 0; -} - -static inline void lease_get_mtime(struct inode *inode, - struct timespec64 *time) -{ - return; -} - -static inline int generic_setlease(struct file *filp, long arg, - struct file_lock **flp, void **priv) -{ - return -EINVAL; -} - -static inline int vfs_setlease(struct file *filp, long arg, - struct file_lock **lease, void **priv) -{ - return -EINVAL; -} - -static inline int lease_modify(struct file_lock *fl, int arg, - struct list_head *dispose) -{ - return -EINVAL; -} - -struct files_struct; -static inline void show_fd_locks(struct seq_file *f, - struct file *filp, struct files_struct *files) {} -static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, - fl_owner_t owner) -{ - return false; -} - -static inline struct file_lock_context * -locks_inode_context(const struct inode *inode) -{ - return NULL; -} - -#endif /* !CONFIG_FILE_LOCKING */ - static inline struct inode *file_inode(const struct file *f) { return f->f_inode; @@ -1360,11 +1026,6 @@ static inline struct dentry *file_dentry(const struct file *file) return d_real(file->f_path.dentry, file_inode(file)); } -static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return locks_lock_inode_wait(locks_inode(filp), fl); -} - struct fasync_struct { rwlock_t fa_lock; int magic; @@ -1635,22 +1296,22 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) } /** - * i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns - * @mnt_userns: user namespace of the mount the inode was found from + * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping + * @idmap: idmap of the mount the inode was found from * @inode: inode to map * - * Return: whe inode's i_uid mapped down according to @mnt_userns. + * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ -static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns, +static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { - return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid); + return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * @@ -1659,50 +1320,50 @@ static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns, * * Return: true if @inode's i_uid field needs to be updated, false if not. */ -static inline bool i_uid_needs_update(struct user_namespace *mnt_userns, +static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, - i_uid_into_vfsuid(mnt_userns, inode))); + i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ -static inline void i_uid_update(struct user_namespace *mnt_userns, +static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) - inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode), + inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** - * i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns - * @mnt_userns: user namespace of the mount the inode was found from + * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping + * @idmap: idmap of the mount the inode was found from * @inode: inode to map * - * Return: the inode's i_gid mapped down according to @mnt_userns. + * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ -static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns, +static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { - return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid); + return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * @@ -1711,83 +1372,83 @@ static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns, * * Return: true if @inode's i_gid field needs to be updated, false if not. */ -static inline bool i_gid_needs_update(struct user_namespace *mnt_userns, +static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, - i_gid_into_vfsgid(mnt_userns, inode))); + i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ -static inline void i_gid_update(struct user_namespace *mnt_userns, +static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) - inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode), + inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via - * an idmapped mount map the caller's fsuid according to @mnt_users. + * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { - inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); + inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via - * an idmapped mount map the caller's fsgid according to @mnt_users. + * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { - inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); + inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in - * @mnt_userns: user namespace of the relevant mount + * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map - * the caller's fsuid and fsgid according to the @mnt_userns first. + * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; - kuid = mapped_fsuid(mnt_userns, fs_userns); + kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns, fs_userns); + kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && @@ -1941,42 +1602,42 @@ static inline bool sb_start_intwrite_trylock(struct super_block *sb) return __sb_start_write_trylock(sb, SB_FREEZE_FS); } -bool inode_owner_or_capable(struct user_namespace *mnt_userns, +bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ -int vfs_create(struct user_namespace *, struct inode *, +int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int vfs_mkdir(struct user_namespace *, struct inode *, +int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); -int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *, +int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); -int vfs_symlink(struct user_namespace *, struct inode *, +int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); -int vfs_link(struct dentry *, struct user_namespace *, struct inode *, +int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); -int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *); -int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *, +int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); +int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming - * @old_mnt_userns: old user namespace of the mount the inode was found from + * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source - * @new_mnt_userns: new user namespace of the mount the inode was found from + * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { - struct user_namespace *old_mnt_userns; + struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; - struct user_namespace *new_mnt_userns; + struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; @@ -1985,14 +1646,14 @@ struct renamedata { int vfs_rename(struct renamedata *); -static inline int vfs_whiteout(struct user_namespace *mnt_userns, +static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { - return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE, + return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } -struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, +struct file *vfs_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); @@ -2016,10 +1677,10 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, /* * VFS file helper functions. */ -void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, +void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); -umode_t mode_strip_sgid(struct user_namespace *mnt_userns, +umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); /* @@ -2137,27 +1798,26 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct user_namespace *, struct inode *, int); + int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); - int (*create) (struct user_namespace *, struct inode *,struct dentry *, + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct user_namespace *, struct inode *,struct dentry *, + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *, + int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct user_namespace *, struct inode *,struct dentry *, + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); - int (*rename) (struct user_namespace *, struct inode *, struct dentry *, + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); - int (*setattr) (struct user_namespace *, struct dentry *, - struct iattr *); - int (*getattr) (struct user_namespace *, const struct path *, + int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); + int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, @@ -2166,13 +1826,13 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct user_namespace *, struct inode *, + int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); - struct posix_acl *(*get_acl)(struct user_namespace *, struct dentry *, + struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); - int (*set_acl)(struct user_namespace *, struct dentry *, + int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); - int (*fileattr_set)(struct user_namespace *mnt_userns, + int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); } ____cacheline_aligned; @@ -2326,11 +1986,11 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, +static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { - return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || - !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)); + return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) @@ -2624,96 +2284,6 @@ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) -#ifdef CONFIG_FILE_LOCKING -static inline int break_lease(struct inode *inode, unsigned int mode) -{ - /* - * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking i_flctx->flc_lease. Otherwise, we - * could end up racing with tasks trying to set a new lease on this - * file. - */ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, mode, FL_LEASE); - return 0; -} - -static inline int break_deleg(struct inode *inode, unsigned int mode) -{ - /* - * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking i_flctx->flc_lease. Otherwise, we - * could end up racing with tasks trying to set a new lease on this - * file. - */ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, mode, FL_DELEG); - return 0; -} - -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) -{ - int ret; - - ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); - if (ret == -EWOULDBLOCK && delegated_inode) { - *delegated_inode = inode; - ihold(inode); - } - return ret; -} - -static inline int break_deleg_wait(struct inode **delegated_inode) -{ - int ret; - - ret = break_deleg(*delegated_inode, O_WRONLY); - iput(*delegated_inode); - *delegated_inode = NULL; - return ret; -} - -static inline int break_layout(struct inode *inode, bool wait) -{ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, - wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, - FL_LAYOUT); - return 0; -} - -#else /* !CONFIG_FILE_LOCKING */ -static inline int break_lease(struct inode *inode, unsigned int mode) -{ - return 0; -} - -static inline int break_deleg(struct inode *inode, unsigned int mode) -{ - return 0; -} - -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) -{ - return 0; -} - -static inline int break_deleg_wait(struct inode **delegated_inode) -{ - BUG(); - return 0; -} - -static inline int break_layout(struct inode *inode, bool wait) -{ - return 0; -} - -#endif /* CONFIG_FILE_LOCKING */ - /* fs/open.c */ struct audit_names; struct filename { @@ -2725,11 +2295,6 @@ struct filename { }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); -static inline struct user_namespace *file_mnt_user_ns(struct file *file) -{ - return mnt_user_ns(file->f_path.mnt); -} - static inline struct mnt_idmap *file_mnt_idmap(struct file *file) { return mnt_idmap(file->f_path.mnt); @@ -2749,7 +2314,7 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) } extern long vfs_truncate(const struct path *, loff_t); -int do_truncate(struct user_namespace *, struct dentry *, loff_t start, +int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); @@ -2904,21 +2469,21 @@ static inline int bmap(struct inode *inode, sector_t *block) } #endif -int notify_change(struct user_namespace *, struct dentry *, +int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); -int inode_permission(struct user_namespace *, struct inode *, int); -int generic_permission(struct user_namespace *, struct inode *, int); +int inode_permission(struct mnt_idmap *, struct inode *, int); +int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { - return inode_permission(file_mnt_user_ns(file), + return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { - return inode_permission(mnt_user_ns(path->mnt), + return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } -int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, +int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) @@ -3106,7 +2671,7 @@ extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); -extern int setattr_should_drop_suidgid(struct user_namespace *, struct inode *); +extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); /* @@ -3265,7 +2830,7 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); +void generic_fillattr(struct mnt_idmap *, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); @@ -3316,9 +2881,9 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); -extern int simple_setattr(struct user_namespace *, struct dentry *, +extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); -extern int simple_getattr(struct user_namespace *, const struct path *, +extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); @@ -3327,7 +2892,7 @@ extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); -extern int simple_rename(struct user_namespace *, struct inode *, +extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, @@ -3369,11 +2934,11 @@ extern int generic_check_addressable(unsigned, u64); extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); -int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, +int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); -int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); +int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -void setattr_copy(struct user_namespace *, struct inode *inode, +void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); @@ -3540,13 +3105,13 @@ static inline bool is_sxid(umode_t mode) return mode & (S_ISUID | S_ISGID); } -static inline int check_sticky(struct user_namespace *mnt_userns, +static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; - return __check_sticky(mnt_userns, dir, inode); + return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 4f5f8a651213..e0a49c3125eb 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -257,8 +257,8 @@ int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num, gfp_t gfp_flags); -int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, - unsigned int offs); +int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, + size_t offs); int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num); @@ -309,8 +309,6 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) /* keyring.c */ void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); -int fscrypt_add_test_dummy_key(struct super_block *sb, - const struct fscrypt_dummy_policy *dummy_policy); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); @@ -422,9 +420,8 @@ static inline int fscrypt_encrypt_block_inplace(const struct inode *inode, return -EOPNOTSUPP; } -static inline int fscrypt_decrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs) +static inline int fscrypt_decrypt_pagecache_blocks(struct folio *folio, + size_t len, size_t offs) { return -EOPNOTSUPP; } @@ -530,13 +527,6 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) return -EOPNOTSUPP; } -static inline int -fscrypt_add_test_dummy_key(struct super_block *sb, - const struct fscrypt_dummy_policy *dummy_policy) -{ - return 0; -} - static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 40f14e5fed9d..119a3266791f 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -12,6 +12,7 @@ #define _LINUX_FSVERITY_H #include <linux/fs.h> +#include <linux/mm.h> #include <crypto/hash_info.h> #include <crypto/sha2.h> #include <uapi/linux/fsverity.h> @@ -93,8 +94,7 @@ struct fsverity_operations { * isn't already cached. Implementations may ignore this * argument; it's only a performance optimization. * - * This can be called at any time on an open verity file, as well as - * between ->begin_enable_verity() and ->end_enable_verity(). It may be + * This can be called at any time on an open verity file. It may be * called by multiple processes concurrently, even with the same page. * * Note that this must retrieve a *page*, not necessarily a *block*. @@ -109,9 +109,9 @@ struct fsverity_operations { * Write a Merkle tree block to the given inode. * * @inode: the inode for which the Merkle tree is being built - * @buf: block to write - * @index: 0-based index of the block within the Merkle tree - * @log_blocksize: log base 2 of the Merkle tree block size + * @buf: the Merkle tree block to write + * @pos: the position of the block in the Merkle tree (in bytes) + * @size: the Merkle tree block size (in bytes) * * This is only called between ->begin_enable_verity() and * ->end_enable_verity(). @@ -119,7 +119,7 @@ struct fsverity_operations { * Return: 0 on success, -errno on failure */ int (*write_merkle_tree_block)(struct inode *inode, const void *buf, - u64 index, int log_blocksize); + u64 pos, unsigned int size); }; #ifdef CONFIG_FS_VERITY @@ -148,9 +148,21 @@ int fsverity_get_digest(struct inode *inode, /* open.c */ -int fsverity_file_open(struct inode *inode, struct file *filp); -int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); -void fsverity_cleanup_inode(struct inode *inode); +int __fsverity_file_open(struct inode *inode, struct file *filp); +int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); +void __fsverity_cleanup_inode(struct inode *inode); + +/** + * fsverity_cleanup_inode() - free the inode's verity info, if present + * @inode: an inode being evicted + * + * Filesystems must call this on inode eviction to free ->i_verity_info. + */ +static inline void fsverity_cleanup_inode(struct inode *inode) +{ + if (inode->i_verity_info) + __fsverity_cleanup_inode(inode); +} /* read_metadata.c */ @@ -158,7 +170,7 @@ int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg); /* verify.c */ -bool fsverity_verify_page(struct page *page); +bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset); void fsverity_verify_bio(struct bio *bio); void fsverity_enqueue_verify_work(struct work_struct *work); @@ -193,15 +205,15 @@ static inline int fsverity_get_digest(struct inode *inode, /* open.c */ -static inline int fsverity_file_open(struct inode *inode, struct file *filp) +static inline int __fsverity_file_open(struct inode *inode, struct file *filp) { - return IS_VERITY(inode) ? -EOPNOTSUPP : 0; + return -EOPNOTSUPP; } -static inline int fsverity_prepare_setattr(struct dentry *dentry, - struct iattr *attr) +static inline int __fsverity_prepare_setattr(struct dentry *dentry, + struct iattr *attr) { - return IS_VERITY(d_inode(dentry)) ? -EOPNOTSUPP : 0; + return -EOPNOTSUPP; } static inline void fsverity_cleanup_inode(struct inode *inode) @@ -218,7 +230,8 @@ static inline int fsverity_ioctl_read_metadata(struct file *filp, /* verify.c */ -static inline bool fsverity_verify_page(struct page *page) +static inline bool fsverity_verify_blocks(struct folio *folio, size_t len, + size_t offset) { WARN_ON(1); return false; @@ -236,6 +249,16 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) #endif /* !CONFIG_FS_VERITY */ +static inline bool fsverity_verify_folio(struct folio *folio) +{ + return fsverity_verify_blocks(folio, folio_size(folio), 0); +} + +static inline bool fsverity_verify_page(struct page *page) +{ + return fsverity_verify_blocks(page_folio(page), PAGE_SIZE, 0); +} + /** * fsverity_active() - do reads from the inode need to go through fs-verity? * @inode: inode to check @@ -254,4 +277,42 @@ static inline bool fsverity_active(const struct inode *inode) return fsverity_get_info(inode) != NULL; } +/** + * fsverity_file_open() - prepare to open a verity file + * @inode: the inode being opened + * @filp: the struct file being set up + * + * When opening a verity file, deny the open if it is for writing. Otherwise, + * set up the inode's ->i_verity_info if not already done. + * + * When combined with fscrypt, this must be called after fscrypt_file_open(). + * Otherwise, we won't have the key set up to decrypt the verity metadata. + * + * Return: 0 on success, -errno on failure + */ +static inline int fsverity_file_open(struct inode *inode, struct file *filp) +{ + if (IS_VERITY(inode)) + return __fsverity_file_open(inode, filp); + return 0; +} + +/** + * fsverity_prepare_setattr() - prepare to change a verity inode's attributes + * @dentry: dentry through which the inode is being changed + * @attr: attributes to change + * + * Verity files are immutable, so deny truncates. This isn't covered by the + * open-time check because sys_truncate() takes a path, not a file descriptor. + * + * Return: 0 on success, -errno on failure + */ +static inline int fsverity_prepare_setattr(struct dentry *dentry, + struct iattr *attr) +{ + if (IS_VERITY(d_inode(dentry))) + return __fsverity_prepare_setattr(dentry, attr); + return 0; +} + #endif /* _LINUX_FSVERITY_H */ diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index e098f38422af..a3028e400a9c 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -152,7 +152,10 @@ static inline void totalhigh_pages_add(long count) static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; - return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP); + + return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || + (addr >= __fix_to_virt(FIX_KMAP_END) && + addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index db194e2ba69f..9ab9d3105d5c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -743,7 +743,10 @@ static inline struct hstate *hstate_sizelog(int page_size_log) if (!page_size_log) return &default_hstate; - return size_to_hstate(1UL << page_size_log); + if (page_size_log < BITS_PER_LONG) + return size_to_hstate(1UL << page_size_log); + + return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) diff --git a/include/linux/ima.h b/include/linux/ima.h index 5a0b2a285a18..172b113a9864 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,7 +18,7 @@ struct linux_binprm; extern enum hash_algo ima_get_current_hash_algo(void); extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); -extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns, +extern void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); @@ -30,7 +30,7 @@ extern int ima_read_file(struct file *file, enum kernel_read_file_id id, bool contents); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); -extern void ima_post_path_mknod(struct user_namespace *mnt_userns, +extern void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); @@ -66,7 +66,7 @@ static inline int ima_file_check(struct file *file, int mask) return 0; } -static inline void ima_post_create_tmpfile(struct user_namespace *mnt_userns, +static inline void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { } @@ -111,7 +111,7 @@ static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, return 0; } -static inline void ima_post_path_mknod(struct user_namespace *mnt_userns, +static inline void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { return; @@ -183,18 +183,18 @@ static inline void ima_post_key_create_or_update(struct key *keyring, #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); -extern void ima_inode_post_setattr(struct user_namespace *mnt_userns, +extern void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); -extern int ima_inode_set_acl(struct user_namespace *mnt_userns, +extern int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -static inline int ima_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { - return ima_inode_set_acl(mnt_userns, dentry, acl_name, NULL); + return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name); #else @@ -203,7 +203,7 @@ static inline bool is_ima_appraise_enabled(void) return 0; } -static inline void ima_inode_post_setattr(struct user_namespace *mnt_userns, +static inline void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry) { return; @@ -217,7 +217,7 @@ static inline int ima_inode_setxattr(struct dentry *dentry, return 0; } -static inline int ima_inode_set_acl(struct user_namespace *mnt_userns, +static inline int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { @@ -231,7 +231,7 @@ static inline int ima_inode_removexattr(struct dentry *dentry, return 0; } -static inline int ima_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { diff --git a/include/linux/iversion.h b/include/linux/iversion.h index e27bd4f55d84..f174ff1b59ee 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -9,8 +9,26 @@ * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must - * appear different to observers if there was a change to the inode's data or - * metadata since it was last queried. + * appear larger to observers if there was an explicit change to the inode's + * data or metadata since it was last queried. + * + * An explicit change is one that would ordinarily result in a change to the + * inode status change time (aka ctime). i_version must appear to change, even + * if the ctime does not (since the whole point is to avoid missing updates due + * to timestamp granularity). If POSIX or other relevant spec mandates that the + * ctime must change due to an operation, then the i_version counter must be + * incremented as well. + * + * Making the i_version update completely atomic with the operation itself would + * be prohibitively expensive. Traditionally the kernel has updated the times on + * directories after an operation that changes its contents. For regular files, + * the ctime is usually updated before the data is copied into the cache for a + * write. This means that there is a window of time when an observer can + * associate a new timestamp with old file contents. Since the purpose of the + * i_version is to allow for better cache coherency, the i_version must always + * be updated after the results of the operation are visible. Updating it before + * and after a change is also permitted. (Note that no filesystems currently do + * this. Fixing that is a work-in-progress). * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the @@ -234,42 +252,6 @@ inode_peek_iversion(const struct inode *inode) return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } -/** - * inode_query_iversion - read i_version for later use - * @inode: inode from which i_version should be read - * - * Read the inode i_version counter. This should be used by callers that wish - * to store the returned i_version for later comparison. This will guarantee - * that a later query of the i_version will result in a different value if - * anything has changed. - * - * In this implementation, we fetch the current value, set the QUERIED flag and - * then try to swap it into place with a cmpxchg, if it wasn't already set. If - * that fails, we try again with the newly fetched value from the cmpxchg. - */ -static inline u64 -inode_query_iversion(struct inode *inode) -{ - u64 cur, new; - - cur = inode_peek_iversion_raw(inode); - do { - /* If flag is already set, then no need to swap */ - if (cur & I_VERSION_QUERIED) { - /* - * This barrier (and the implicit barrier in the - * cmpxchg below) pairs with the barrier in - * inode_maybe_inc_iversion(). - */ - smp_mb(); - break; - } - - new = cur | I_VERSION_QUERIED; - } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); - return cur >> I_VERSION_QUERIED_SHIFT; -} - /* * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: @@ -283,6 +265,8 @@ static inline u64 time_to_chattr(struct timespec64 *t) return chattr; } +u64 inode_query_iversion(struct inode *inode); + /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check diff --git a/include/linux/key.h b/include/linux/key.h index d27477faf00d..8dc7f7c3088b 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -386,6 +386,14 @@ extern int wait_for_key_construction(struct key *key, bool intr); extern int key_validate(const struct key *key); +extern key_ref_t key_create(key_ref_t keyring, + const char *type, + const char *description, + const void *payload, + size_t plen, + key_perm_t perm, + unsigned long flags); + extern key_ref_t key_create_or_update(key_ref_t keyring, const char *type, const char *description, diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 70ce419e2709..2b7f067af3c4 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -312,7 +312,7 @@ static inline struct file *nlmsvc_file_file(struct nlm_file *file) static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(nlmsvc_file_file(file)); + return file_inode(nlmsvc_file_file(file)); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) @@ -372,7 +372,7 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return locks_inode(fl1->fl_file) == locks_inode(fl2->fl_file) + return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) && fl1->fl_pid == fl2->fl_pid && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 67e4a2c5500b..b60fbcd8cdfa 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -11,6 +11,7 @@ #define LOCKD_XDR_H #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/nfs.h> #include <linux/sunrpc/xdr.h> diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ed6cb2ac55fa..094b76dc7164 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -136,25 +136,25 @@ LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr) LSM_HOOK(int, 0, inode_getattr, const struct path *path) -LSM_HOOK(int, 0, inode_setxattr, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) -LSM_HOOK(int, 0, inode_removexattr, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name) -LSM_HOOK(int, 0, inode_set_acl, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) -LSM_HOOK(int, 0, inode_get_acl, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_get_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) -LSM_HOOK(int, 0, inode_remove_acl, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) -LSM_HOOK(int, 0, inode_killpriv, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_killpriv, struct mnt_idmap *idmap, struct dentry *dentry) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct user_namespace *mnt_userns, +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0a5ba81f7367..6e156d2acffc 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -475,7 +475,7 @@ * @inode_killpriv: * The setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. - * @mnt_userns: user namespace of the mount. + * @idmap: idmap of the mount. * @dentry is the dentry being changed. * Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. diff --git a/include/linux/mm.h b/include/linux/mm.h index 8f857163ac89..bd3197748562 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -137,7 +137,7 @@ extern int mmap_rnd_compat_bits __read_mostly; * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 -/* This function must be updated when the size of struct page grows above 80 +/* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, @@ -148,12 +148,18 @@ static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; - /* Check that struct page is either 56, 64, 72, or 80 bytes */ + /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); - BUILD_BUG_ON(sizeof(struct page) > 80); + BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { + case 96: + _pp[11] = 0; + fallthrough; + case 88: + _pp[10] = 0; + fallthrough; case 80: _pp[9] = 0; fallthrough; @@ -2095,8 +2101,6 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; -int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, - struct page **pages); struct page *get_dump_page(unsigned long addr); bool folio_mark_dirty(struct folio *folio); diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 0ccca33a7a6d..057c89867aa2 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -113,167 +113,23 @@ static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid) #define AS_KUIDT(val) (kuid_t){ __vfsuid_val(val) } #define AS_KGIDT(val) (kgid_t){ __vfsgid_val(val) } -#ifdef CONFIG_MULTIUSER -/** - * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups - * @vfsgid: the mnt gid to match - * - * This function can be used to determine whether @vfsuid matches any of the - * caller's groups. - * - * Return: 1 if vfsuid matches caller's groups, 0 if not. - */ -static inline int vfsgid_in_group_p(vfsgid_t vfsgid) -{ - return in_group_p(AS_KGIDT(vfsgid)); -} -#else -static inline int vfsgid_in_group_p(vfsgid_t vfsgid) -{ - return 1; -} -#endif +int vfsgid_in_group_p(vfsgid_t vfsgid); -/** - * initial_idmapping - check whether this is the initial mapping - * @ns: idmapping to check - * - * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, - * [...], 1000 to 1000 [...]. - * - * Return: true if this is the initial mapping, false if not. - */ -static inline bool initial_idmapping(const struct user_namespace *ns) -{ - return ns == &init_user_ns; -} +vfsuid_t make_vfsuid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, kuid_t kuid); -/** - * no_idmapping - check whether we can skip remapping a kuid/gid - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * - * This function can be used to check whether a remapping between two - * idmappings is required. - * An idmapped mount is a mount that has an idmapping attached to it that - * is different from the filsystem's idmapping and the initial idmapping. - * If the initial mapping is used or the idmapping of the mount and the - * filesystem are identical no remapping is required. - * - * Return: true if remapping can be skipped, false if not. - */ -static inline bool no_idmapping(const struct user_namespace *mnt_userns, - const struct user_namespace *fs_userns) -{ - return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; -} +vfsgid_t make_vfsgid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, kgid_t kgid); -/** - * make_vfsuid - map a filesystem kuid into a mnt_userns - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @kuid : kuid to be mapped - * - * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this - * function when preparing a @kuid to be reported to userspace. - * - * If no_idmapping() determines that this is not an idmapped mount we can - * simply return @kuid unchanged. - * If initial_idmapping() tells us that the filesystem is not mounted with an - * idmapping we know the value of @kuid won't change when calling - * from_kuid() so we can simply retrieve the value via __kuid_val() - * directly. - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is - * returned. - */ +kuid_t from_vfsuid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, vfsuid_t vfsuid); -static inline vfsuid_t make_vfsuid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - kuid_t kuid) -{ - uid_t uid; - - if (no_idmapping(mnt_userns, fs_userns)) - return VFSUIDT_INIT(kuid); - if (initial_idmapping(fs_userns)) - uid = __kuid_val(kuid); - else - uid = from_kuid(fs_userns, kuid); - if (uid == (uid_t)-1) - return INVALID_VFSUID; - return VFSUIDT_INIT(make_kuid(mnt_userns, uid)); -} - -/** - * make_vfsgid - map a filesystem kgid into a mnt_userns - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @kgid : kgid to be mapped - * - * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this - * function when preparing a @kgid to be reported to userspace. - * - * If no_idmapping() determines that this is not an idmapped mount we can - * simply return @kgid unchanged. - * If initial_idmapping() tells us that the filesystem is not mounted with an - * idmapping we know the value of @kgid won't change when calling - * from_kgid() so we can simply retrieve the value via __kgid_val() - * directly. - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is - * returned. - */ - -static inline vfsgid_t make_vfsgid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - kgid_t kgid) -{ - gid_t gid; - - if (no_idmapping(mnt_userns, fs_userns)) - return VFSGIDT_INIT(kgid); - if (initial_idmapping(fs_userns)) - gid = __kgid_val(kgid); - else - gid = from_kgid(fs_userns, kgid); - if (gid == (gid_t)-1) - return INVALID_VFSGID; - return VFSGIDT_INIT(make_kgid(mnt_userns, gid)); -} - -/** - * from_vfsuid - map a vfsuid into the filesystem idmapping - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @vfsuid : vfsuid to be mapped - * - * Map @vfsuid into the filesystem idmapping. This function has to be used in - * order to e.g. write @vfsuid to inode->i_uid. - * - * Return: @vfsuid mapped into the filesystem idmapping - */ -static inline kuid_t from_vfsuid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - vfsuid_t vfsuid) -{ - uid_t uid; - - if (no_idmapping(mnt_userns, fs_userns)) - return AS_KUIDT(vfsuid); - uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid)); - if (uid == (uid_t)-1) - return INVALID_UID; - if (initial_idmapping(fs_userns)) - return KUIDT_INIT(uid); - return make_kuid(fs_userns, uid); -} +kgid_t from_vfsgid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, vfsgid_t vfsgid); /** * vfsuid_has_fsmapping - check whether a vfsuid maps into the filesystem - * @mnt_userns: the mount's idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid: vfsuid to be mapped * @@ -283,11 +139,11 @@ static inline kuid_t from_vfsuid(struct user_namespace *mnt_userns, * * Return: true if @vfsuid has a mapping in the filesystem, false if not. */ -static inline bool vfsuid_has_fsmapping(struct user_namespace *mnt_userns, +static inline bool vfsuid_has_fsmapping(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { - return uid_valid(from_vfsuid(mnt_userns, fs_userns, vfsuid)); + return uid_valid(from_vfsuid(idmap, fs_userns, vfsuid)); } static inline bool vfsuid_has_mapping(struct user_namespace *userns, @@ -310,35 +166,8 @@ static inline kuid_t vfsuid_into_kuid(vfsuid_t vfsuid) } /** - * from_vfsgid - map a vfsgid into the filesystem idmapping - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @vfsgid : vfsgid to be mapped - * - * Map @vfsgid into the filesystem idmapping. This function has to be used in - * order to e.g. write @vfsgid to inode->i_gid. - * - * Return: @vfsgid mapped into the filesystem idmapping - */ -static inline kgid_t from_vfsgid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - vfsgid_t vfsgid) -{ - gid_t gid; - - if (no_idmapping(mnt_userns, fs_userns)) - return AS_KGIDT(vfsgid); - gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid)); - if (gid == (gid_t)-1) - return INVALID_GID; - if (initial_idmapping(fs_userns)) - return KGIDT_INIT(gid); - return make_kgid(fs_userns, gid); -} - -/** * vfsgid_has_fsmapping - check whether a vfsgid maps into the filesystem - * @mnt_userns: the mount's idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid: vfsgid to be mapped * @@ -348,11 +177,11 @@ static inline kgid_t from_vfsgid(struct user_namespace *mnt_userns, * * Return: true if @vfsgid has a mapping in the filesystem, false if not. */ -static inline bool vfsgid_has_fsmapping(struct user_namespace *mnt_userns, +static inline bool vfsgid_has_fsmapping(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { - return gid_valid(from_vfsgid(mnt_userns, fs_userns, vfsgid)); + return gid_valid(from_vfsgid(idmap, fs_userns, vfsgid)); } static inline bool vfsgid_has_mapping(struct user_namespace *userns, @@ -375,8 +204,8 @@ static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) } /** - * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: the mount's idmapping + * mapped_fsuid - return caller's fsuid mapped according to an idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on @@ -385,18 +214,17 @@ static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) * O_CREAT. Other examples include the allocation of quotas for a specific * user. * - * Return: the caller's current fsuid mapped up according to @mnt_userns. + * Return: the caller's current fsuid mapped up according to @idmap. */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, +static inline kuid_t mapped_fsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns) { - return from_vfsuid(mnt_userns, fs_userns, - VFSUIDT_INIT(current_fsuid())); + return from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(current_fsuid())); } /** - * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: the mount's idmapping + * mapped_fsgid - return caller's fsgid mapped according to an idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on @@ -405,13 +233,15 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, * O_CREAT. Other examples include the allocation of quotas for a specific * user. * - * Return: the caller's current fsgid mapped up according to @mnt_userns. + * Return: the caller's current fsgid mapped up according to @idmap. */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, +static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns) { - return from_vfsgid(mnt_userns, fs_userns, - VFSGIDT_INIT(current_fsgid())); + return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid())); } +bool check_fsmapping(const struct mnt_idmap *idmap, + const struct super_block *sb); + #endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/include/linux/mount.h b/include/linux/mount.h index 62475996fac6..52f452b2259a 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -74,8 +74,6 @@ struct vfsmount { struct mnt_idmap *mnt_idmap; } __randomize_layout; -struct user_namespace *mnt_user_ns(const struct vfsmount *mnt); -struct user_namespace *mnt_idmap_owner(const struct mnt_idmap *idmap); static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt) { /* Pairs with smp_store_release() in do_idmap_mount(). */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 00fee52df842..0d4531fd46e7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -68,11 +68,11 @@ extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); -struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int); -struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, +struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); +struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); -struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, +struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index aad12a179e54..e6e02184c25a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2839,8 +2839,6 @@ int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); -void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, - struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d92fdfd2444c..d6c119e31d7a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -392,11 +392,11 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); -extern int nfs_getattr(struct user_namespace *, const struct path *, +extern int nfs_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); -extern int nfs_permission(struct user_namespace *, struct inode *, int); +extern int nfs_permission(struct mnt_idmap *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags); @@ -405,7 +405,7 @@ extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); +extern int nfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); diff --git a/include/linux/pci.h b/include/linux/pci.h index adffd65e84b4..254c8a4126a8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1621,6 +1621,18 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, + const struct irq_affinity_desc *affdesc) +{ + struct msi_map map = { .index = -ENOSYS, }; + + return map; +} + +static inline void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map) +{ +} + static inline void pci_free_irq_vectors(struct pci_dev *dev) { } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index ef914a600087..525b5d64e394 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -100,7 +100,6 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); - bool (*filter)(struct pmu *pmu, int cpu); int num_events; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 diff --git a/include/linux/poison.h b/include/linux/poison.h index 2d3249eb0e62..0e8a1f2ceb2f 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -84,4 +84,7 @@ /********** kernel/bpf/ **********/ #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) +/********** VFS **********/ +#define VFS_PTR_POISON ((void *)(0xF5 + POISON_POINTER_DELTA)) + #endif diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index ee608d22ecb9..21cc29b8a9e8 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -69,20 +69,20 @@ extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -int set_posix_acl(struct user_namespace *, struct dentry *, int, +int set_posix_acl(struct mnt_idmap *, struct dentry *, int, struct posix_acl *); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); struct posix_acl *posix_acl_clone(const struct posix_acl *acl, gfp_t flags); #ifdef CONFIG_FS_POSIX_ACL -int posix_acl_chmod(struct user_namespace *, struct dentry *, umode_t); +int posix_acl_chmod(struct mnt_idmap *, struct dentry *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); -int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, +int posix_acl_update_mode(struct mnt_idmap *, struct inode *, umode_t *, struct posix_acl **); -int simple_set_acl(struct user_namespace *, struct dentry *, +int simple_set_acl(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); @@ -91,7 +91,7 @@ void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); int posix_acl_valid(struct user_namespace *, const struct posix_acl *); -int posix_acl_permission(struct user_namespace *, struct inode *, +int posix_acl_permission(struct mnt_idmap *, struct inode *, const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) @@ -100,14 +100,14 @@ static inline void cache_no_acl(struct inode *inode) inode->i_default_acl = NULL; } -int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); -int vfs_remove_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); #else -static inline int posix_acl_chmod(struct user_namespace *mnt_userns, +static inline int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { return 0; @@ -134,21 +134,21 @@ static inline void forget_all_cached_acls(struct inode *inode) { } -static inline int vfs_set_acl(struct user_namespace *mnt_userns, +static inline int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *acl) { return -EOPNOTSUPP; } -static inline struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, +static inline struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ERR_PTR(-EOPNOTSUPP); } -static inline int vfs_remove_acl(struct user_namespace *mnt_userns, +static inline int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return -EOPNOTSUPP; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 0d8625d71733..11a4becff3a9 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -20,12 +20,12 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb) } /* i_mutex must being held */ -static inline bool is_quota_modification(struct user_namespace *mnt_userns, +static inline bool is_quota_modification(struct mnt_idmap *idmap, struct inode *inode, struct iattr *ia) { return ((ia->ia_valid & ATTR_SIZE) || - i_uid_needs_update(mnt_userns, ia, inode) || - i_gid_needs_update(mnt_userns, ia, inode)); + i_uid_needs_update(idmap, ia, inode) || + i_gid_needs_update(idmap, ia, inode)); } #if defined(CONFIG_QUOTA) @@ -116,7 +116,7 @@ int dquot_set_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); -int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, +int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr); static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) @@ -236,7 +236,7 @@ static inline void dquot_free_inode(struct inode *inode) { } -static inline int dquot_transfer(struct user_namespace *mnt_userns, +static inline int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr) { return 0; diff --git a/include/linux/security.h b/include/linux/security.h index 5b67f208f7de..5984d0d550b4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -153,12 +153,11 @@ extern int cap_capset(struct cred *new, const struct cred *old, extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -int cap_inode_removexattr(struct user_namespace *mnt_userns, +int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name); int cap_inode_need_killpriv(struct dentry *dentry); -int cap_inode_killpriv(struct user_namespace *mnt_userns, - struct dentry *dentry); -int cap_inode_getsecurity(struct user_namespace *mnt_userns, +int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry); +int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc); extern int cap_mmap_addr(unsigned long addr); @@ -356,29 +355,28 @@ int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu); int security_inode_permission(struct inode *inode, int mask); -int security_inode_setattr(struct user_namespace *mnt_userns, +int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); -int security_inode_setxattr(struct user_namespace *mnt_userns, +int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -int security_inode_set_acl(struct user_namespace *mnt_userns, +int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -int security_inode_get_acl(struct user_namespace *mnt_userns, +int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); -int security_inode_remove_acl(struct user_namespace *mnt_userns, +int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int security_inode_getxattr(struct dentry *dentry, const char *name); int security_inode_listxattr(struct dentry *dentry); -int security_inode_removexattr(struct user_namespace *mnt_userns, +int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name); int security_inode_need_killpriv(struct dentry *dentry); -int security_inode_killpriv(struct user_namespace *mnt_userns, - struct dentry *dentry); -int security_inode_getsecurity(struct user_namespace *mnt_userns, +int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry); +int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); @@ -862,7 +860,7 @@ static inline int security_inode_permission(struct inode *inode, int mask) return 0; } -static inline int security_inode_setattr(struct user_namespace *mnt_userns, +static inline int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { @@ -874,14 +872,14 @@ static inline int security_inode_getattr(const struct path *path) return 0; } -static inline int security_inode_setxattr(struct user_namespace *mnt_userns, +static inline int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { return cap_inode_setxattr(dentry, name, value, size, flags); } -static inline int security_inode_set_acl(struct user_namespace *mnt_userns, +static inline int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) @@ -889,14 +887,14 @@ static inline int security_inode_set_acl(struct user_namespace *mnt_userns, return 0; } -static inline int security_inode_get_acl(struct user_namespace *mnt_userns, +static inline int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return 0; } -static inline int security_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { @@ -918,11 +916,11 @@ static inline int security_inode_listxattr(struct dentry *dentry) return 0; } -static inline int security_inode_removexattr(struct user_namespace *mnt_userns, +static inline int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { - return cap_inode_removexattr(mnt_userns, dentry, name); + return cap_inode_removexattr(idmap, dentry, name); } static inline int security_inode_need_killpriv(struct dentry *dentry) @@ -930,18 +928,18 @@ static inline int security_inode_need_killpriv(struct dentry *dentry) return cap_inode_need_killpriv(dentry); } -static inline int security_inode_killpriv(struct user_namespace *mnt_userns, +static inline int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { - return cap_inode_killpriv(mnt_userns, dentry); + return cap_inode_killpriv(idmap, dentry); } -static inline int security_inode_getsecurity(struct user_namespace *mnt_userns, +static inline int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { - return cap_inode_getsecurity(mnt_userns, inode, name, buffer, alloc); + return cap_inode_getsecurity(idmap, inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 71310efe2fab..7bde8e1c228a 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,7 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern void shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,8 +115,9 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline void shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) { + return NULL; } static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) diff --git a/include/linux/stat.h b/include/linux/stat.h index ff277ced50e9..52150570d37a 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -52,6 +52,15 @@ struct kstat { u64 mnt_id; u32 dio_mem_align; u32 dio_offset_align; + u64 change_cookie; }; +/* These definitions are internal to the kernel for now. Mainly used by nfsd. */ + +/* mask values */ +#define STATX_CHANGE_COOKIE 0x40000000U /* Want/got stx_change_attr */ + +/* file attribute values */ +#define STATX_ATTR_CHANGE_MONOTONIC 0x8000000000000000ULL /* version monotonically increases */ + #endif diff --git a/include/linux/tpm.h b/include/linux/tpm.h index dfeb25a0362d..4dc97b9f65fb 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -265,6 +265,7 @@ enum tpm2_startup_types { enum tpm2_cc_attrs { TPM2_CC_ATTR_CHANDLES = 25, TPM2_CC_ATTR_RHANDLE = 28, + TPM2_CC_ATTR_VENDOR = 29, }; #define TPM_VID_INTEL 0x8086 diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 2e7dd44926e4..6af72461397d 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -42,7 +42,7 @@ struct xattr_handler { struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, - struct user_namespace *mnt_userns, struct dentry *dentry, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; @@ -56,25 +56,25 @@ struct xattr { }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); -ssize_t vfs_getxattr(struct user_namespace *, struct dentry *, const char *, +ssize_t vfs_getxattr(struct mnt_idmap *, struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); -int __vfs_setxattr(struct user_namespace *, struct dentry *, struct inode *, +int __vfs_setxattr(struct mnt_idmap *, struct dentry *, struct inode *, const char *, const void *, size_t, int); -int __vfs_setxattr_noperm(struct user_namespace *, struct dentry *, +int __vfs_setxattr_noperm(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); -int __vfs_setxattr_locked(struct user_namespace *, struct dentry *, +int __vfs_setxattr_locked(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int, struct inode **); -int vfs_setxattr(struct user_namespace *, struct dentry *, const char *, +int vfs_setxattr(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); -int __vfs_removexattr(struct user_namespace *, struct dentry *, const char *); -int __vfs_removexattr_locked(struct user_namespace *, struct dentry *, +int __vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); +int __vfs_removexattr_locked(struct mnt_idmap *, struct dentry *, const char *, struct inode **); -int vfs_removexattr(struct user_namespace *, struct dentry *, const char *); +int vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); -int vfs_getxattr_alloc(struct user_namespace *mnt_userns, +int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); diff --git a/include/net/sock.h b/include/net/sock.h index dcd72e6285b2..556209727633 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2434,6 +2434,19 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) +{ + skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + if (skb) { + if (sk_rmem_schedule(sk, skb, skb->truesize)) { + skb_set_owner_r(skb, sk); + return skb; + } + __kfree_skb(skb); + } + return NULL; +} + static inline void skb_prepare_for_gro(struct sk_buff *skb) { if (skb->destructor != sock_wfree) { diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h index 4f4c44ea3a65..cf4a0d28b178 100644 --- a/include/trace/events/erofs.h +++ b/include/trace/events/erofs.h @@ -19,12 +19,17 @@ struct erofs_map_blocks; { 1, "DIR" }) #define show_map_flags(flags) __print_flags(flags, "|", \ - { EROFS_GET_BLOCKS_RAW, "RAW" }) + { EROFS_GET_BLOCKS_FIEMAP, "FIEMAP" }, \ + { EROFS_GET_BLOCKS_READMORE, "READMORE" }, \ + { EROFS_GET_BLOCKS_FINDTAIL, "FINDTAIL" }) #define show_mflags(flags) __print_flags(flags, "", \ - { EROFS_MAP_MAPPED, "M" }, \ - { EROFS_MAP_META, "I" }, \ - { EROFS_MAP_ENCODED, "E" }) + { EROFS_MAP_MAPPED, "M" }, \ + { EROFS_MAP_META, "I" }, \ + { EROFS_MAP_ENCODED, "E" }, \ + { EROFS_MAP_FULL_MAPPED, "F" }, \ + { EROFS_MAP_FRAGMENT, "R" }, \ + { EROFS_MAP_PARTIAL_REF, "P" }) TRACE_EVENT(erofs_lookup, @@ -66,8 +71,8 @@ TRACE_EVENT(erofs_fill_inode, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->nid = EROFS_I(inode)->nid; - __entry->blkaddr = erofs_blknr(iloc(EROFS_I_SB(inode), __entry->nid)); - __entry->ofs = erofs_blkoff(iloc(EROFS_I_SB(inode), __entry->nid)); + __entry->blkaddr = erofs_blknr(erofs_iloc(inode)); + __entry->ofs = erofs_blkoff(erofs_iloc(inode)); ), TP_printk("dev = (%d,%d), nid = %llu, blkaddr %u ofs %u", diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 436258214bb0..cd14c94e9a1e 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -188,15 +188,43 @@ struct fanotify_event_info_error { __u32 error_count; }; +/* + * User space may need to record additional information about its decision. + * The extra information type records what kind of information is included. + * The default is none. We also define an extra information buffer whose + * size is determined by the extra information type. + * + * If the information type is Audit Rule, then the information following + * is the rule number that triggered the user space decision that + * requires auditing. + */ + +#define FAN_RESPONSE_INFO_NONE 0 +#define FAN_RESPONSE_INFO_AUDIT_RULE 1 + struct fanotify_response { __s32 fd; __u32 response; }; +struct fanotify_response_info_header { + __u8 type; + __u8 pad; + __u16 len; +}; + +struct fanotify_response_info_audit_rule { + struct fanotify_response_info_header hdr; + __u32 rule_number; + __u32 subj_trust; + __u32 obj_trust; +}; + /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 -#define FAN_AUDIT 0x10 /* Bit mask to create audit record for result */ +#define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ +#define FAN_INFO 0x20 /* Bitmask to indicate additional information */ /* No fd set in event */ #define FAN_NOFD -1 diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d09aa1c1e3e6..0160e9f2b07c 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -608,7 +608,7 @@ out_unlock: return error; } -static int mqueue_create(struct user_namespace *mnt_userns, struct inode *dir, +static int mqueue_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return mqueue_create_attr(dentry, mode, NULL); @@ -887,7 +887,7 @@ static int prepare_open(struct dentry *dentry, int oflag, int ro, if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) return -EINVAL; acc = oflag2acc[oflag & O_ACCMODE]; - return inode_permission(&init_user_ns, d_inode(dentry), acc); + return inode_permission(&nop_mnt_idmap, d_inode(dentry), acc); } static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, @@ -979,7 +979,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) err = -ENOENT; } else { ihold(inode); - err = vfs_unlink(&init_user_ns, d_inode(dentry->d_parent), + err = vfs_unlink(&nop_mnt_idmap, d_inode(dentry->d_parent), dentry, NULL); } dput(dentry); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 547c88be8a28..93d0b87f3283 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -64,6 +64,7 @@ #include <uapi/linux/limits.h> #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/openat2.h> // struct open_how +#include <uapi/linux/fanotify.h> #include "audit.h" @@ -2252,7 +2253,7 @@ static inline int audit_copy_fcaps(struct audit_names *name, if (!dentry) return 0; - rc = get_vfs_caps_from_disk(&init_user_ns, dentry, &caps); + rc = get_vfs_caps_from_disk(&nop_mnt_idmap, dentry, &caps); if (rc) return rc; @@ -2807,7 +2808,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->d.next = context->aux; context->aux = (void *)ax; - get_vfs_caps_from_disk(&init_user_ns, + get_vfs_caps_from_disk(&nop_mnt_idmap, bprm->file->f_path.dentry, &vcaps); ax->fcap.permitted = vcaps.permitted; @@ -2877,10 +2878,21 @@ void __audit_log_kern_module(char *name) context->type = AUDIT_KERN_MODULE; } -void __audit_fanotify(unsigned int response) +void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { - audit_log(audit_context(), GFP_KERNEL, - AUDIT_FANOTIFY, "resp=%u", response); + /* {subj,obj}_trust values are {0,1,2}: no,yes,unknown */ + switch (friar->hdr.type) { + case FAN_RESPONSE_INFO_NONE: + audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY, + "resp=%u fan_type=%u fan_info=0 subj_trust=2 obj_trust=2", + response, FAN_RESPONSE_INFO_NONE); + break; + case FAN_RESPONSE_INFO_AUDIT_RULE: + audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY, + "resp=%u fan_type=%u fan_info=%X subj_trust=%u obj_trust=%u", + response, friar->hdr.type, friar->rule_number, + friar->subj_trust, friar->obj_trust); + } } void __audit_tk_injoffset(struct timespec64 offset) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 4f841e16779e..9948b542a470 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -122,7 +122,7 @@ static struct inode *bpf_get_inode(struct super_block *sb, inode->i_mtime = inode->i_atime; inode->i_ctime = inode->i_atime; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); return inode; } @@ -152,7 +152,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, dir->i_ctime = dir->i_mtime; } -static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -382,7 +382,7 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) return simple_lookup(dir, dentry, flags); } -static int bpf_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); @@ -559,7 +559,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; - int ret = inode_permission(&init_user_ns, inode, MAY_READ); + int ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); if (ret) return ERR_PTR(ret); diff --git a/kernel/capability.c b/kernel/capability.c index 860fd22117c1..339a44dfe2f4 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -486,11 +486,11 @@ EXPORT_SYMBOL(file_ns_capable); * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const struct inode *inode) { - return vfsuid_has_mapping(ns, i_uid_into_vfsuid(mnt_userns, inode)) && - vfsgid_has_mapping(ns, i_gid_into_vfsgid(mnt_userns, inode)); + return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && + vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode)); } /** @@ -502,13 +502,13 @@ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ -bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, +bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && - privileged_wrt_inode_uidgid(ns, mnt_userns, inode); + privileged_wrt_inode_uidgid(ns, idmap, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c099cf3fa02d..935e8121b21e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5065,7 +5065,7 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) if (!inode) return -ENOMEM; - ret = inode_permission(&init_user_ns, inode, MAY_WRITE); + ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); iput(inode); return ret; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e838feb6adc5..2a4918a1faa9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2951,8 +2951,11 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, } if (!(ctx->flags & SCA_MIGRATE_ENABLE)) { - if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) + if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) { + if (ctx->flags & SCA_USER) + swap(p->user_cpus_ptr, ctx->user_mask); goto out; + } if (WARN_ON_ONCE(p == current && is_migration_disabled(p) && diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 8ac8b81bfee6..02e011cabe91 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1343,10 +1343,11 @@ void psi_trigger_destroy(struct psi_trigger *t) group = t->group; /* - * Wakeup waiters to stop polling. Can happen if cgroup is deleted - * from under a polling process. + * Wakeup waiters to stop polling and clear the queue to prevent it from + * being accessed later. Can happen if cgroup is deleted from under a + * polling process. */ - wake_up_interruptible(&t->event_wait); + wake_up_pollfree(&t->event_wait); mutex_lock(&group->trigger_lock); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 5897828b9d7e..7e5dff602585 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -470,11 +470,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward); -u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle) { struct alarm_base *base = &alarm_bases[alarm->type]; + ktime_t now = base->get_ktime(); + + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) { + /* + * Same issue as with posix_timer_fn(). Timers which are + * periodic but the signal is ignored can starve the system + * with a very small interval. The real fix which was + * promised in the context of posix_timer_fn() never + * materialized, but someone should really work on it. + * + * To prevent DOS fake @now to be 1 jiffie out which keeps + * the overrun accounting correct but creates an + * inconsistency vs. timer_gettime(2). + */ + ktime_t kj = NSEC_PER_SEC / HZ; + + if (interval < kj) + now = ktime_add(now, kj); + } + + return alarm_forward(alarm, now, interval); +} - return alarm_forward(alarm, base->get_ktime(), interval); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + return __alarm_forward_now(alarm, interval, false); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -551,9 +575,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, if (posix_timer_event(ptr, si_private) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. + * away once we handle ignored signals proper. Ensure that + * small intervals cannot starve the system. */ - ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval); + ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); ++ptr->it_requeue_pending; ptr->it_active = 1; result = ALARMTIMER_RESTART; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6a4696719297..6a942fa275c7 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -155,7 +155,7 @@ int trace_define_field(struct trace_event_call *call, const char *type, } EXPORT_SYMBOL_GPL(trace_define_field); -int trace_define_field_ext(struct trace_event_call *call, const char *type, +static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len) { diff --git a/kernel/umh.c b/kernel/umh.c index 850631518665..fbf872c624cb 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -438,21 +438,27 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; - if (wait & UMH_KILLABLE) - state |= TASK_KILLABLE; - if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; - retval = wait_for_completion_state(&done, state); - if (!retval) - goto wait_done; - if (wait & UMH_KILLABLE) { + retval = wait_for_completion_state(&done, state | TASK_KILLABLE); + if (!retval) + goto wait_done; + /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; + + /* + * fallthrough; in case of -ERESTARTSYS now do uninterruptible + * wait_for_completion_state(). Since umh_complete() shall call + * complete() in a moment if xchg() above returned NULL, this + * uninterruptible wait_for_completion_state() will not block + * SIGKILL'ed processes for long. + */ } + wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; diff --git a/lib/parser.c b/lib/parser.c index bcb23484100e..2b5e2b480253 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -11,6 +11,15 @@ #include <linux/slab.h> #include <linux/string.h> +/* + * max size needed by different bases to express U64 + * HEX: "0xFFFFFFFFFFFFFFFF" --> 18 + * DEC: "18446744073709551615" --> 20 + * OCT: "01777777777777777777777" --> 23 + * pick the max one to define NUMBER_BUF_LEN + */ +#define NUMBER_BUF_LEN 24 + /** * match_one - Determines if a string matches a simple pattern * @s: the string to examine for presence of the pattern @@ -129,14 +138,12 @@ EXPORT_SYMBOL(match_token); static int match_number(substring_t *s, int *result, int base) { char *endp; - char *buf; + char buf[NUMBER_BUF_LEN]; int ret; long val; - buf = match_strdup(s); - if (!buf) - return -ENOMEM; - + if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN) + return -ERANGE; ret = 0; val = simple_strtol(buf, &endp, base); if (endp == buf) @@ -145,7 +152,6 @@ static int match_number(substring_t *s, int *result, int base) ret = -ERANGE; else *result = (int) val; - kfree(buf); return ret; } @@ -163,18 +169,15 @@ static int match_number(substring_t *s, int *result, int base) */ static int match_u64int(substring_t *s, u64 *result, int base) { - char *buf; + char buf[NUMBER_BUF_LEN]; int ret; u64 val; - buf = match_strdup(s); - if (!buf) - return -ENOMEM; - + if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN) + return -ERANGE; ret = kstrtoull(buf, base, &val); if (!ret) *result = val; - kfree(buf); return ret; } @@ -206,14 +209,12 @@ EXPORT_SYMBOL(match_int); */ int match_uint(substring_t *s, unsigned int *result) { - int err = -ENOMEM; - char *buf = match_strdup(s); + char buf[NUMBER_BUF_LEN]; - if (buf) { - err = kstrtouint(buf, 10, result); - kfree(buf); - } - return err; + if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN) + return -ERANGE; + + return kstrtouint(buf, 10, result); } EXPORT_SYMBOL(match_uint); diff --git a/mm/filemap.c b/mm/filemap.c index c4d4ace9cc70..0e20a8d6dd93 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2588,18 +2588,19 @@ static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter, struct folio *folio; int err = 0; + /* "last_index" is the index of the page beyond the end of the read */ last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE); retry: if (fatal_signal_pending(current)) return -EINTR; - filemap_get_read_batch(mapping, index, last_index, fbatch); + filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); - filemap_get_read_batch(mapping, index, last_index, fbatch); + filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) @@ -1914,7 +1914,7 @@ static unsigned long collect_longterm_unpinnable_pages( drain_allow = false; } - if (!folio_isolate_lru(folio)) + if (folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_page_list); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index abe6cfd92ffa..1b791b26d72d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3272,8 +3272,6 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); - if (is_writable_migration_entry(entry)) - pmde = maybe_pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); if (!is_migration_entry_young(entry)) @@ -3281,6 +3279,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) /* NOTE: this may contain setting soft-dirty on some archs */ if (PageDirty(new) && is_migration_entry_dirty(entry)) pmde = pmd_mkdirty(pmde); + if (is_writable_migration_entry(entry)) + pmde = maybe_pmd_mkwrite(pmde, vma); + else + pmde = pmd_wrprotect(pmde); if (PageAnon(new)) { rmap_t rmap_flags = RMAP_COMPOUND; diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 833bf2cfd2a3..21e66d7f261d 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -246,6 +246,9 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object, static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip) { + if (!kasan_arch_is_ready()) + return false; + if (ptr != page_address(virt_to_head_page(ptr))) { kasan_report_invalid_free(ptr, ip, KASAN_REPORT_INVALID_FREE); return true; diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index b076f597a378..cb762982c8ba 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -191,7 +191,12 @@ bool kasan_check_range(unsigned long addr, size_t size, bool write, bool kasan_byte_accessible(const void *addr) { - s8 shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr)); + s8 shadow_byte; + + if (!kasan_arch_is_ready()) + return true; + + shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr)); return shadow_byte >= 0 && shadow_byte < KASAN_GRANULE_SIZE; } diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 2fba1f51f042..15cfb34d16a1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -291,6 +291,9 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) unsigned long shadow_start, shadow_end; int ret; + if (!kasan_arch_is_ready()) + return 0; + if (!is_vmalloc_or_module_addr((void *)addr)) return 0; @@ -459,6 +462,9 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long region_start, region_end; unsigned long size; + if (!kasan_arch_is_ready()) + return; + region_start = ALIGN(start, KASAN_MEMORY_PER_SHADOW_PAGE); region_end = ALIGN_DOWN(end, KASAN_MEMORY_PER_SHADOW_PAGE); @@ -502,6 +508,9 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, * with setting memory tags, so the KASAN_VMALLOC_INIT flag is ignored. */ + if (!kasan_arch_is_ready()) + return (void *)start; + if (!is_vmalloc_or_module_addr(start)) return (void *)start; @@ -524,6 +533,9 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, */ void __kasan_poison_vmalloc(const void *start, unsigned long size) { + if (!kasan_arch_is_ready()) + return; + if (!is_vmalloc_or_module_addr(start)) return; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 90acfea40c13..a26a28e3738c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2611,6 +2611,7 @@ static int madvise_collapse_errno(enum scan_result r) case SCAN_CGROUP_CHARGE_FAIL: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ + case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: @@ -2629,8 +2629,11 @@ struct page *ksm_might_need_to_copy(struct page *page, new_page = NULL; } if (new_page) { - copy_user_highpage(new_page, page, address, vma); - + if (copy_mc_user_highpage(new_page, page, address, vma)) { + put_page(new_page); + memory_failure_queue(page_to_pfn(page), 0); + return ERR_PTR(-EHWPOISON); + } SetPageDirty(new_page); __SetPageUptodate(new_page); __SetPageLocked(new_page); diff --git a/mm/madvise.c b/mm/madvise.c index b6ea204d4e23..18c2e2affac4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -329,7 +329,7 @@ static inline bool can_do_file_pageout(struct vm_area_struct *vma) * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ - return inode_owner_or_capable(&init_user_ns, + return inode_owner_or_capable(&nop_mnt_idmap, file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/memory.c b/mm/memory.c index 3e836fecd035..f526b9152bef 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3840,6 +3840,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (unlikely(!page)) { ret = VM_FAULT_OOM; goto out_page; + } else if (unlikely(PTR_ERR(page) == -EHWPOISON)) { + ret = VM_FAULT_HWPOISON; + goto out_page; } folio = page_folio(page); diff --git a/mm/migrate.c b/mm/migrate.c index a4d3fc65085f..cc5455614e01 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -224,6 +224,8 @@ static bool remove_migration_pte(struct folio *folio, pte = maybe_mkwrite(pte, vma); else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); + else + pte = pte_wrprotect(pte); if (folio_test_anon(folio) && !is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; diff --git a/mm/mincore.c b/mm/mincore.c index a085a2aeabd8..cd69b9db0081 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -168,7 +168,7 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) * for writing; otherwise we'd be including shared non-exclusive * mappings, which opens a side channel. */ - return inode_owner_or_capable(&init_user_ns, + return inode_owner_or_capable(&nop_mnt_idmap, file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/secretmem.c b/mm/secretmem.c index 04c3ac9448a1..afcf46e99cda 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -162,7 +162,7 @@ const struct address_space_operations secretmem_aops = { .migrate_folio = secretmem_migrate_folio, }; -static int secretmem_setattr(struct user_namespace *mnt_userns, +static int secretmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); @@ -175,7 +175,7 @@ static int secretmem_setattr(struct user_namespace *mnt_userns, if ((ia_valid & ATTR_SIZE) && inode->i_size) ret = -EINVAL; else - ret = simple_setattr(mnt_userns, dentry, iattr); + ret = simple_setattr(idmap, dentry, iattr); filemap_invalidate_unlock(mapping); diff --git a/mm/shmem.c b/mm/shmem.c index 0005ab2c29af..41f82c5a5e28 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1045,7 +1045,7 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } EXPORT_SYMBOL_GPL(shmem_truncate_range); -static int shmem_getattr(struct user_namespace *mnt_userns, +static int shmem_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -1066,7 +1066,7 @@ static int shmem_getattr(struct user_namespace *mnt_userns, stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(idmap, inode, stat); if (shmem_is_huge(NULL, inode, 0, false)) stat->blksize = HPAGE_PMD_SIZE; @@ -1080,7 +1080,7 @@ static int shmem_getattr(struct user_namespace *mnt_userns, return 0; } -static int shmem_setattr(struct user_namespace *mnt_userns, +static int shmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -1089,7 +1089,7 @@ static int shmem_setattr(struct user_namespace *mnt_userns, bool update_mtime = false; bool update_ctime = true; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(idmap, dentry, attr); if (error) return error; @@ -1127,9 +1127,9 @@ static int shmem_setattr(struct user_namespace *mnt_userns, } } - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(idmap, inode, attr); if (attr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode); + error = posix_acl_chmod(idmap, dentry, inode->i_mode); if (!error && update_ctime) { inode->i_ctime = current_time(inode); if (update_mtime) @@ -2327,8 +2327,9 @@ static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) #define shmem_initxattrs NULL #endif -static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, - umode_t mode, dev_t dev, unsigned long flags) +static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, + struct inode *dir, umode_t mode, dev_t dev, + unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; @@ -2341,7 +2342,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, inode = new_inode(sb); if (inode) { inode->i_ino = ino; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_generation = get_random_u32(); @@ -2913,13 +2914,13 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) * File creation. Allocate an inode, and we're done.. */ static int -shmem_mknod(struct user_namespace *mnt_userns, struct inode *dir, +shmem_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; int error = -ENOSPC; - inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); + inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = simple_acl_create(dir, inode); if (error) @@ -2944,13 +2945,13 @@ out_iput: } static int -shmem_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, +shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; int error = -ENOSPC; - inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); + inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, @@ -2968,22 +2969,22 @@ out_iput: return error; } -static int shmem_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int shmem_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int error; - if ((error = shmem_mknod(&init_user_ns, dir, dentry, - mode | S_IFDIR, 0))) + error = shmem_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); + if (error) return error; inc_nlink(dir); return 0; } -static int shmem_create(struct user_namespace *mnt_userns, struct inode *dir, +static int shmem_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return shmem_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); + return shmem_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } /* @@ -3043,7 +3044,7 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) return shmem_unlink(dir, dentry); } -static int shmem_whiteout(struct user_namespace *mnt_userns, +static int shmem_whiteout(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry) { struct dentry *whiteout; @@ -3053,7 +3054,7 @@ static int shmem_whiteout(struct user_namespace *mnt_userns, if (!whiteout) return -ENOMEM; - error = shmem_mknod(&init_user_ns, old_dir, whiteout, + error = shmem_mknod(idmap, old_dir, whiteout, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); dput(whiteout); if (error) @@ -3076,7 +3077,7 @@ static int shmem_whiteout(struct user_namespace *mnt_userns, * it exists so that the VFS layer correctly free's it when it * gets overwritten. */ -static int shmem_rename2(struct user_namespace *mnt_userns, +static int shmem_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -3096,7 +3097,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns, if (flags & RENAME_WHITEOUT) { int error; - error = shmem_whiteout(&init_user_ns, old_dir, old_dentry); + error = shmem_whiteout(idmap, old_dir, old_dentry); if (error) return error; } @@ -3122,7 +3123,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns, return 0; } -static int shmem_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int error; @@ -3134,7 +3135,7 @@ static int shmem_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (len > PAGE_SIZE) return -ENAMETOOLONG; - inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK | 0777, 0, + inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0, VM_NORESERVE); if (!inode) return -ENOSPC; @@ -3227,7 +3228,7 @@ static int shmem_fileattr_get(struct dentry *dentry, struct fileattr *fa) return 0; } -static int shmem_fileattr_set(struct user_namespace *mnt_userns, +static int shmem_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); @@ -3301,7 +3302,7 @@ static int shmem_xattr_handler_get(const struct xattr_handler *handler, } static int shmem_xattr_handler_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -3817,7 +3818,8 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) #endif uuid_gen(&sb->s_uuid); - inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); + inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0, + VM_NORESERVE); if (!inode) goto failed; inode->i_uid = sbinfo->uid; @@ -4042,7 +4044,11 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, +#ifdef CONFIG_SHMEM + .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP, +#else .fs_flags = FS_USERNS_MOUNT, +#endif }; void __init shmem_init(void) @@ -4194,7 +4200,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_vm_ops generic_file_vm_ops #define shmem_anon_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations -#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) +#define shmem_get_inode(idmap, sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) @@ -4217,8 +4223,11 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l if (shmem_acct_size(flags, size)) return ERR_PTR(-ENOMEM); - inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, - flags); + if (is_idmapped_mnt(mnt)) + return ERR_PTR(-EINVAL); + + inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL, + S_IFREG | S_IRWXUGO, 0, flags); if (unlikely(!inode)) { shmem_unacct_size(flags, size); return ERR_PTR(-ENOSPC); diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index b05295bab322..39c3491e28a3 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -246,18 +246,21 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -void shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) { + struct dentry *entry = shrinker->debugfs_entry; + lockdep_assert_held(&shrinker_rwsem); kfree_const(shrinker->name); shrinker->name = NULL; - if (!shrinker->debugfs_entry) - return; + if (entry) { + ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); + shrinker->debugfs_entry = NULL; + } - debugfs_remove_recursive(shrinker->debugfs_entry); - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); + return entry; } static int __init shrinker_debugfs_init(void) diff --git a/mm/swap.c b/mm/swap.c index 70e2063ef43a..4c03ecab698e 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -158,36 +158,6 @@ void put_pages_list(struct list_head *pages) } EXPORT_SYMBOL(put_pages_list); -/* - * get_kernel_pages() - pin kernel pages in memory - * @kiov: An array of struct kvec structures - * @nr_segs: number of segments to pin - * @write: pinning for read/write, currently ignored - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_segs long. - * - * Returns number of pages pinned. This may be fewer than the number requested. - * If nr_segs is 0 or negative, returns 0. If no pages were pinned, returns 0. - * Each page returned must be released with a put_page() call when it is - * finished with. - */ -int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, - struct page **pages) -{ - int seg; - - for (seg = 0; seg < nr_segs; seg++) { - if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) - return seg; - - pages[seg] = kmap_to_page(kiov[seg].iov_base); - get_page(pages[seg]); - } - - return seg; -} -EXPORT_SYMBOL_GPL(get_kernel_pages); - typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add_fn(struct lruvec *lruvec, struct folio *folio) diff --git a/mm/swapfile.c b/mm/swapfile.c index 4fa440e87cd6..eb9b0bf1fcdd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1764,12 +1764,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, struct page *swapcache; spinlock_t *ptl; pte_t *pte, new_pte; + bool hwposioned = false; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; + else if (unlikely(PTR_ERR(page) == -EHWPOISON)) + hwposioned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { @@ -1777,15 +1780,19 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, goto out; } - if (unlikely(!PageUptodate(page))) { - pte_t pteval; + if (unlikely(hwposioned || !PageUptodate(page))) { + swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); - pteval = swp_entry_to_pte(make_swapin_error_entry()); - set_pte_at(vma->vm_mm, addr, pte, pteval); - swap_free(entry); + if (hwposioned) { + swp_entry = make_hwpoison_entry(swapcache); + page = swapcache; + } else { + swp_entry = make_swapin_error_entry(); + } + new_pte = swp_entry_to_pte(swp_entry); ret = 0; - goto out; + goto setpte; } /* See do_swap_page() */ @@ -1817,6 +1824,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(*pte)) new_pte = pte_mkuffd_wp(new_pte); +setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: diff --git a/mm/vmscan.c b/mm/vmscan.c index bf3eedf0209c..5b7b8d4f5297 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -741,6 +741,8 @@ EXPORT_SYMBOL(register_shrinker); */ void unregister_shrinker(struct shrinker *shrinker) { + struct dentry *debugfs_entry; + if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -749,9 +751,11 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_remove(shrinker); up_write(&shrinker_rwsem); + debugfs_remove_recursive(debugfs_entry); + kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 748be7253248..78c9729a6057 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1015,6 +1015,7 @@ static void caif_sock_destructor(struct sock *sk) return; } sk_stream_kill_queues(&cf_sk->sk); + WARN_ON_ONCE(sk->sk_forward_alloc); caif_free_client(&cf_sk->layer); } diff --git a/net/core/dev.c b/net/core/dev.c index b76fb37b381e..f23e287602b7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1869,14 +1869,6 @@ static void __move_netdevice_notifier_net(struct net *src_net, __register_netdevice_notifier_net(dst_net, nb, true); } -void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, - struct notifier_block *nb) -{ - rtnl_lock(); - __move_netdevice_notifier_net(src_net, dst_net, nb); - rtnl_unlock(); -} - int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -10375,7 +10367,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = atomic_long_read(&src[i]); + dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); diff --git a/net/core/devlink.c b/net/core/devlink.c index 909a10e4b0dd..0bfc144df8b9 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4742,11 +4742,8 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, if (err) return err; - if (dest_net && !net_eq(dest_net, curr_net)) { - move_netdevice_notifier_net(curr_net, dest_net, - &devlink->netdevice_nb); + if (dest_net && !net_eq(dest_net, curr_net)) write_pnet(&devlink->_net, dest_net); - } err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 078a0a420c8a..7b69cf882b8e 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -304,6 +304,12 @@ struct net *get_net_ns_by_id(const struct net *net, int id) } EXPORT_SYMBOL_GPL(get_net_ns_by_id); +/* init code that must occur even if setup_net() is not called. */ +static __net_init void preinit_net(struct net *net) +{ + ref_tracker_dir_init(&net->notrefcnt_tracker, 128); +} + /* * setup_net runs the initializers for the network namespace object. */ @@ -316,7 +322,6 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128); - ref_tracker_dir_init(&net->notrefcnt_tracker, 128); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); @@ -472,6 +477,8 @@ struct net *copy_net_ns(unsigned long flags, rv = -ENOMEM; goto dec_ucounts; } + + preinit_net(net); refcount_set(&net->passive, 1); net->ucounts = ucounts; get_user_ns(user_ns); @@ -1118,6 +1125,7 @@ void __init net_ns_init(void) init_net.key_domain = &init_net_key_domain; #endif down_write(&pernet_ops_rwsem); + preinit_net(&init_net); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); diff --git a/net/core/stream.c b/net/core/stream.c index cd06750dd329..434446ab14c5 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -209,7 +209,6 @@ void sk_stream_kill_queues(struct sock *sk) sk_mem_reclaim_final(sk); WARN_ON_ONCE(sk->sk_wmem_queued); - WARN_ON_ONCE(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4260fe466993..b9d7c3dd1cb3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -551,11 +551,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) - skb_set_owner_r(newnp->pktoptions, newsk); } return newsk; @@ -615,7 +613,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) @@ -679,7 +677,6 @@ ipv6_pktoptions: np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index e624497fa992..9b6818453afe 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -51,7 +51,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; - fl6->flowlabel = np->flow_label; + fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk->sk_uid; if (!oif) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 11b736a76bd7..a52a4f12f146 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -272,6 +272,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; + fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; @@ -1387,14 +1388,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, - sk_gfp_mask(sk, GFP_ATOMIC)); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) { + if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); - skb_set_owner_r(newnp->pktoptions, newsk); - } } } else { if (!req_unhash && found_dup_sk) { @@ -1466,7 +1464,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + opt_skb = skb_clone_and_charge_r(skb, sk); reason = SKB_DROP_REASON_NOT_SPECIFIED; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ @@ -1552,7 +1550,6 @@ ipv6_pktoptions: if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { diff --git a/net/key/af_key.c b/net/key/af_key.c index 2bdbcec781cd..a815f5ab4c49 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1261,7 +1261,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, const struct sadb_x_nat_t_type* n_type; struct xfrm_encap_tmpl *natt; - x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL); + x->encap = kzalloc(sizeof(*x->encap), GFP_KERNEL); if (!x->encap) { err = -ENOMEM; goto out; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 35b5f806fdda..dc5165d3eec4 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1428,6 +1428,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, free: kfree(table); out: + mdev->sysctl = NULL; return -ENOBUFS; } @@ -1437,6 +1438,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct net *net = dev_net(dev); struct ctl_table *table; + if (!mdev->sysctl) + return; + table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 6e38f68f88c2..f2698d2316df 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -449,7 +449,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) err = attach_meter(meter_tbl, meter); if (err) - goto exit_unlock; + goto exit_free_old_meter; ovs_unlock(); @@ -472,6 +472,8 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); +exit_free_old_meter: + ovs_meter_free(old_meter); exit_unlock: ovs_unlock(); nlmsg_free(reply); diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 4b1b59da5c0b..4d15b6a6169c 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -93,7 +93,7 @@ TC_INDIRECT_SCOPE int tcf_ctinfo_act(struct sk_buff *skb, cp = rcu_dereference_bh(ca->params); tcf_lastuse_update(&ca->tcf_tm); - bstats_update(&ca->tcf_bstats, skb); + tcf_action_update_bstats(&ca->common, skb); action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); @@ -212,8 +212,8 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, index = actparm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, index, est, a, - &act_ctinfo_ops, bind, false, flags); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_ctinfo_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index ee2a050c887b..6640e75eaa02 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -12,6 +12,7 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/refcount.h> +#include <linux/rcupdate.h> #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> @@ -339,6 +340,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; + bool update_h = false; err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) @@ -456,10 +458,13 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } } - if (cp->perfect) + if (cp->perfect) { r = cp->perfect + handle; - else - r = tcindex_lookup(cp, handle) ? : &new_filter_result; + } else { + /* imperfect area is updated in-place using rcu */ + update_h = !!tcindex_lookup(cp, handle); + r = &new_filter_result; + } if (r == &new_filter_result) { f = kzalloc(sizeof(*f), GFP_KERNEL); @@ -485,7 +490,28 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, rcu_assign_pointer(tp->root, cp); - if (r == &new_filter_result) { + if (update_h) { + struct tcindex_filter __rcu **fp; + struct tcindex_filter *cf; + + f->result.res = r->res; + tcf_exts_change(&f->result.exts, &r->exts); + + /* imperfect area bucket */ + fp = cp->h + (handle % cp->hash); + + /* lookup the filter, guaranteed to exist */ + for (cf = rcu_dereference_bh_rtnl(*fp); cf; + fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) + if (cf->key == (u16)handle) + break; + + f->next = cf->next; + + cf = rcu_replace_pointer(*fp, f, 1); + tcf_exts_get_net(&cf->result.exts); + tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work); + } else if (r == &new_filter_result) { struct tcindex_filter *nfp; struct tcindex_filter __rcu **fp; diff --git a/net/sctp/diag.c b/net/sctp/diag.c index a557009e9832..c3d6b92dd386 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -343,11 +343,9 @@ static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *r = commp->r; - struct sctp_association *assoc = - list_entry(ep->asocs.next, struct sctp_association, asocs); /* find the ep only once through the transports by this condition */ - if (tsp->asoc != assoc) + if (!list_is_first(&tsp->asoc->asocs, &ep->asocs)) return 0; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) diff --git a/net/socket.c b/net/socket.c index 888cd618a968..c6c44e26e954 100644 --- a/net/socket.c +++ b/net/socket.c @@ -385,7 +385,7 @@ static const struct xattr_handler sockfs_xattr_handler = { }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -589,10 +589,10 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, return used; } -static int sockfs_setattr(struct user_namespace *mnt_userns, +static int sockfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { - int err = simple_setattr(&init_user_ns, dentry, iattr); + int err = simple_setattr(&nop_mnt_idmap, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); @@ -971,9 +971,12 @@ static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, static void sock_recv_mark(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - if (sock_flag(sk, SOCK_RCVMARK) && skb) - put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), - &skb->mark); + if (sock_flag(sk, SOCK_RCVMARK) && skb) { + /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ + __u32 mark = skb->mark; + + put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), &mark); + } } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b35c8701876a..a38733f2197a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2614,6 +2614,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, /* Send a 'SYN-' to destination */ m.msg_name = dest; m.msg_namelen = destlen; + iov_iter_kvec(&m.msg_iter, ITER_SOURCE, NULL, 0, 0); /* If connect is in non-blocking case, set MSG_DONTWAIT to * indicate send_msg() is never blocked. @@ -2776,6 +2777,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } + iov_iter_kvec(&m.msg_iter, ITER_SOURCE, NULL, 0, 0); __tipc_sendstream(new_sock, &m, 0); release_sock(new_sk); exit: diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f0c2293f1d3b..81ff98298996 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1190,7 +1190,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); struct net *net = sock_net(sk); - struct user_namespace *ns; // barf... + struct mnt_idmap *idmap; struct unix_address *addr; struct dentry *dentry; struct path parent; @@ -1217,10 +1217,10 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, /* * All right, let's create it. */ - ns = mnt_user_ns(parent.mnt); + idmap = mnt_idmap(parent.mnt); err = security_path_mknod(&parent, dentry, mode, 0); if (!err) - err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0); + err = vfs_mknod(idmap, d_inode(parent.dentry), dentry, mode, 0); if (err) goto out_path; err = mutex_lock_interruptible(&u->bindlock); @@ -1245,7 +1245,7 @@ out_unlock: err = -EINVAL; out_unlink: /* failed after successful mknod? unlink what we'd created... */ - vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL); + vfs_unlink(idmap, d_inode(parent.dentry), dentry, NULL); out_path: done_path_create(&parent, dentry); out: diff --git a/rust/Makefile b/rust/Makefile index ff70c4c916f8..8a521f2b6422 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -50,6 +50,7 @@ core-cfgs = \ --cfg no_fp_fmt_parse alloc-cfgs = \ + --cfg no_borrow \ --cfg no_fmt \ --cfg no_global_oom_handling \ --cfg no_macros \ @@ -359,8 +360,22 @@ rust-analyzer: $(Q)$(srctree)/scripts/generate_rust_analyzer.py $(srctree) $(objtree) \ $(RUST_LIB_SRC) > $(objtree)/rust-project.json +redirect-intrinsics = \ + __eqsf2 __gesf2 __lesf2 __nesf2 __unordsf2 \ + __unorddf2 \ + __muloti4 __multi3 \ + __udivmodti4 __udivti3 __umodti3 + +ifneq ($(or $(CONFIG_ARM64),$(and $(CONFIG_RISCV),$(CONFIG_64BIT))),) + # These intrinsics are defined for ARM64 and RISCV64 + redirect-intrinsics += \ + __ashrti3 \ + __ashlti3 __lshrti3 +endif + $(obj)/core.o: private skip_clippy = 1 $(obj)/core.o: private skip_flags = -Dunreachable_pub +$(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) $(obj)/core.o: private rustc_target_flags = $(core-cfgs) $(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs $(obj)/target.json FORCE $(call if_changed_dep,rustc_library) diff --git a/rust/alloc/borrow.rs b/rust/alloc/borrow.rs deleted file mode 100644 index dde4957200d4..000000000000 --- a/rust/alloc/borrow.rs +++ /dev/null @@ -1,498 +0,0 @@ -// SPDX-License-Identifier: Apache-2.0 OR MIT - -//! A module for working with borrowed data. - -#![stable(feature = "rust1", since = "1.0.0")] - -use core::cmp::Ordering; -use core::hash::{Hash, Hasher}; -use core::ops::Deref; -#[cfg(not(no_global_oom_handling))] -use core::ops::{Add, AddAssign}; - -#[stable(feature = "rust1", since = "1.0.0")] -pub use core::borrow::{Borrow, BorrowMut}; - -use core::fmt; -#[cfg(not(no_global_oom_handling))] -use crate::string::String; - -use Cow::*; - -#[stable(feature = "rust1", since = "1.0.0")] -impl<'a, B: ?Sized> Borrow<B> for Cow<'a, B> -where - B: ToOwned, - <B as ToOwned>::Owned: 'a, -{ - fn borrow(&self) -> &B { - &**self - } -} - -/// A generalization of `Clone` to borrowed data. -/// -/// Some types make it possible to go from borrowed to owned, usually by -/// implementing the `Clone` trait. But `Clone` works only for going from `&T` -/// to `T`. The `ToOwned` trait generalizes `Clone` to construct owned data -/// from any borrow of a given type. -#[cfg_attr(not(test), rustc_diagnostic_item = "ToOwned")] -#[stable(feature = "rust1", since = "1.0.0")] -pub trait ToOwned { - /// The resulting type after obtaining ownership. - #[stable(feature = "rust1", since = "1.0.0")] - type Owned: Borrow<Self>; - - /// Creates owned data from borrowed data, usually by cloning. - /// - /// # Examples - /// - /// Basic usage: - /// - /// ``` - /// let s: &str = "a"; - /// let ss: String = s.to_owned(); - /// - /// let v: &[i32] = &[1, 2]; - /// let vv: Vec<i32> = v.to_owned(); - /// ``` - #[stable(feature = "rust1", since = "1.0.0")] - #[must_use = "cloning is often expensive and is not expected to have side effects"] - fn to_owned(&self) -> Self::Owned; - - /// Uses borrowed data to replace owned data, usually by cloning. - /// - /// This is borrow-generalized version of `Clone::clone_from`. - /// - /// # Examples - /// - /// Basic usage: - /// - /// ``` - /// # #![feature(toowned_clone_into)] - /// let mut s: String = String::new(); - /// "hello".clone_into(&mut s); - /// - /// let mut v: Vec<i32> = Vec::new(); - /// [1, 2][..].clone_into(&mut v); - /// ``` - #[unstable(feature = "toowned_clone_into", reason = "recently added", issue = "41263")] - fn clone_into(&self, target: &mut Self::Owned) { - *target = self.to_owned(); - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<T> ToOwned for T -where - T: Clone, -{ - type Owned = T; - fn to_owned(&self) -> T { - self.clone() - } - - fn clone_into(&self, target: &mut T) { - target.clone_from(self); - } -} - -/// A clone-on-write smart pointer. -/// -/// The type `Cow` is a smart pointer providing clone-on-write functionality: it -/// can enclose and provide immutable access to borrowed data, and clone the -/// data lazily when mutation or ownership is required. The type is designed to -/// work with general borrowed data via the `Borrow` trait. -/// -/// `Cow` implements `Deref`, which means that you can call -/// non-mutating methods directly on the data it encloses. If mutation -/// is desired, `to_mut` will obtain a mutable reference to an owned -/// value, cloning if necessary. -/// -/// If you need reference-counting pointers, note that -/// [`Rc::make_mut`][crate::rc::Rc::make_mut] and -/// [`Arc::make_mut`][crate::sync::Arc::make_mut] can provide clone-on-write -/// functionality as well. -/// -/// # Examples -/// -/// ``` -/// use std::borrow::Cow; -/// -/// fn abs_all(input: &mut Cow<[i32]>) { -/// for i in 0..input.len() { -/// let v = input[i]; -/// if v < 0 { -/// // Clones into a vector if not already owned. -/// input.to_mut()[i] = -v; -/// } -/// } -/// } -/// -/// // No clone occurs because `input` doesn't need to be mutated. -/// let slice = [0, 1, 2]; -/// let mut input = Cow::from(&slice[..]); -/// abs_all(&mut input); -/// -/// // Clone occurs because `input` needs to be mutated. -/// let slice = [-1, 0, 1]; -/// let mut input = Cow::from(&slice[..]); -/// abs_all(&mut input); -/// -/// // No clone occurs because `input` is already owned. -/// let mut input = Cow::from(vec![-1, 0, 1]); -/// abs_all(&mut input); -/// ``` -/// -/// Another example showing how to keep `Cow` in a struct: -/// -/// ``` -/// use std::borrow::Cow; -/// -/// struct Items<'a, X: 'a> where [X]: ToOwned<Owned = Vec<X>> { -/// values: Cow<'a, [X]>, -/// } -/// -/// impl<'a, X: Clone + 'a> Items<'a, X> where [X]: ToOwned<Owned = Vec<X>> { -/// fn new(v: Cow<'a, [X]>) -> Self { -/// Items { values: v } -/// } -/// } -/// -/// // Creates a container from borrowed values of a slice -/// let readonly = [1, 2]; -/// let borrowed = Items::new((&readonly[..]).into()); -/// match borrowed { -/// Items { values: Cow::Borrowed(b) } => println!("borrowed {b:?}"), -/// _ => panic!("expect borrowed value"), -/// } -/// -/// let mut clone_on_write = borrowed; -/// // Mutates the data from slice into owned vec and pushes a new value on top -/// clone_on_write.values.to_mut().push(3); -/// println!("clone_on_write = {:?}", clone_on_write.values); -/// -/// // The data was mutated. Let's check it out. -/// match clone_on_write { -/// Items { values: Cow::Owned(_) } => println!("clone_on_write contains owned data"), -/// _ => panic!("expect owned data"), -/// } -/// ``` -#[stable(feature = "rust1", since = "1.0.0")] -#[cfg_attr(not(test), rustc_diagnostic_item = "Cow")] -pub enum Cow<'a, B: ?Sized + 'a> -where - B: ToOwned, -{ - /// Borrowed data. - #[stable(feature = "rust1", since = "1.0.0")] - Borrowed(#[stable(feature = "rust1", since = "1.0.0")] &'a B), - - /// Owned data. - #[stable(feature = "rust1", since = "1.0.0")] - Owned(#[stable(feature = "rust1", since = "1.0.0")] <B as ToOwned>::Owned), -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<B: ?Sized + ToOwned> Clone for Cow<'_, B> { - fn clone(&self) -> Self { - match *self { - Borrowed(b) => Borrowed(b), - Owned(ref o) => { - let b: &B = o.borrow(); - Owned(b.to_owned()) - } - } - } - - fn clone_from(&mut self, source: &Self) { - match (self, source) { - (&mut Owned(ref mut dest), &Owned(ref o)) => o.borrow().clone_into(dest), - (t, s) => *t = s.clone(), - } - } -} - -impl<B: ?Sized + ToOwned> Cow<'_, B> { - /// Returns true if the data is borrowed, i.e. if `to_mut` would require additional work. - /// - /// # Examples - /// - /// ``` - /// #![feature(cow_is_borrowed)] - /// use std::borrow::Cow; - /// - /// let cow = Cow::Borrowed("moo"); - /// assert!(cow.is_borrowed()); - /// - /// let bull: Cow<'_, str> = Cow::Owned("...moo?".to_string()); - /// assert!(!bull.is_borrowed()); - /// ``` - #[unstable(feature = "cow_is_borrowed", issue = "65143")] - #[rustc_const_unstable(feature = "const_cow_is_borrowed", issue = "65143")] - pub const fn is_borrowed(&self) -> bool { - match *self { - Borrowed(_) => true, - Owned(_) => false, - } - } - - /// Returns true if the data is owned, i.e. if `to_mut` would be a no-op. - /// - /// # Examples - /// - /// ``` - /// #![feature(cow_is_borrowed)] - /// use std::borrow::Cow; - /// - /// let cow: Cow<'_, str> = Cow::Owned("moo".to_string()); - /// assert!(cow.is_owned()); - /// - /// let bull = Cow::Borrowed("...moo?"); - /// assert!(!bull.is_owned()); - /// ``` - #[unstable(feature = "cow_is_borrowed", issue = "65143")] - #[rustc_const_unstable(feature = "const_cow_is_borrowed", issue = "65143")] - pub const fn is_owned(&self) -> bool { - !self.is_borrowed() - } - - /// Acquires a mutable reference to the owned form of the data. - /// - /// Clones the data if it is not already owned. - /// - /// # Examples - /// - /// ``` - /// use std::borrow::Cow; - /// - /// let mut cow = Cow::Borrowed("foo"); - /// cow.to_mut().make_ascii_uppercase(); - /// - /// assert_eq!( - /// cow, - /// Cow::Owned(String::from("FOO")) as Cow<str> - /// ); - /// ``` - #[stable(feature = "rust1", since = "1.0.0")] - pub fn to_mut(&mut self) -> &mut <B as ToOwned>::Owned { - match *self { - Borrowed(borrowed) => { - *self = Owned(borrowed.to_owned()); - match *self { - Borrowed(..) => unreachable!(), - Owned(ref mut owned) => owned, - } - } - Owned(ref mut owned) => owned, - } - } - - /// Extracts the owned data. - /// - /// Clones the data if it is not already owned. - /// - /// # Examples - /// - /// Calling `into_owned` on a `Cow::Borrowed` returns a clone of the borrowed data: - /// - /// ``` - /// use std::borrow::Cow; - /// - /// let s = "Hello world!"; - /// let cow = Cow::Borrowed(s); - /// - /// assert_eq!( - /// cow.into_owned(), - /// String::from(s) - /// ); - /// ``` - /// - /// Calling `into_owned` on a `Cow::Owned` returns the owned data. The data is moved out of the - /// `Cow` without being cloned. - /// - /// ``` - /// use std::borrow::Cow; - /// - /// let s = "Hello world!"; - /// let cow: Cow<str> = Cow::Owned(String::from(s)); - /// - /// assert_eq!( - /// cow.into_owned(), - /// String::from(s) - /// ); - /// ``` - #[stable(feature = "rust1", since = "1.0.0")] - pub fn into_owned(self) -> <B as ToOwned>::Owned { - match self { - Borrowed(borrowed) => borrowed.to_owned(), - Owned(owned) => owned, - } - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -#[rustc_const_unstable(feature = "const_deref", issue = "88955")] -impl<B: ?Sized + ToOwned> const Deref for Cow<'_, B> -where - B::Owned: ~const Borrow<B>, -{ - type Target = B; - - fn deref(&self) -> &B { - match *self { - Borrowed(borrowed) => borrowed, - Owned(ref owned) => owned.borrow(), - } - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<B: ?Sized> Eq for Cow<'_, B> where B: Eq + ToOwned {} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<B: ?Sized> Ord for Cow<'_, B> -where - B: Ord + ToOwned, -{ - #[inline] - fn cmp(&self, other: &Self) -> Ordering { - Ord::cmp(&**self, &**other) - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<'a, 'b, B: ?Sized, C: ?Sized> PartialEq<Cow<'b, C>> for Cow<'a, B> -where - B: PartialEq<C> + ToOwned, - C: ToOwned, -{ - #[inline] - fn eq(&self, other: &Cow<'b, C>) -> bool { - PartialEq::eq(&**self, &**other) - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<'a, B: ?Sized> PartialOrd for Cow<'a, B> -where - B: PartialOrd + ToOwned, -{ - #[inline] - fn partial_cmp(&self, other: &Cow<'a, B>) -> Option<Ordering> { - PartialOrd::partial_cmp(&**self, &**other) - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<B: ?Sized> fmt::Debug for Cow<'_, B> -where - B: fmt::Debug + ToOwned<Owned: fmt::Debug>, -{ - fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - match *self { - Borrowed(ref b) => fmt::Debug::fmt(b, f), - Owned(ref o) => fmt::Debug::fmt(o, f), - } - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<B: ?Sized> fmt::Display for Cow<'_, B> -where - B: fmt::Display + ToOwned<Owned: fmt::Display>, -{ - fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - match *self { - Borrowed(ref b) => fmt::Display::fmt(b, f), - Owned(ref o) => fmt::Display::fmt(o, f), - } - } -} - -#[stable(feature = "default", since = "1.11.0")] -impl<B: ?Sized> Default for Cow<'_, B> -where - B: ToOwned<Owned: Default>, -{ - /// Creates an owned Cow<'a, B> with the default value for the contained owned value. - fn default() -> Self { - Owned(<B as ToOwned>::Owned::default()) - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<B: ?Sized> Hash for Cow<'_, B> -where - B: Hash + ToOwned, -{ - #[inline] - fn hash<H: Hasher>(&self, state: &mut H) { - Hash::hash(&**self, state) - } -} - -#[stable(feature = "rust1", since = "1.0.0")] -impl<T: ?Sized + ToOwned> AsRef<T> for Cow<'_, T> { - fn as_ref(&self) -> &T { - self - } -} - -#[cfg(not(no_global_oom_handling))] -#[stable(feature = "cow_add", since = "1.14.0")] -impl<'a> Add<&'a str> for Cow<'a, str> { - type Output = Cow<'a, str>; - - #[inline] - fn add(mut self, rhs: &'a str) -> Self::Output { - self += rhs; - self - } -} - -#[cfg(not(no_global_oom_handling))] -#[stable(feature = "cow_add", since = "1.14.0")] -impl<'a> Add<Cow<'a, str>> for Cow<'a, str> { - type Output = Cow<'a, str>; - - #[inline] - fn add(mut self, rhs: Cow<'a, str>) -> Self::Output { - self += rhs; - self - } -} - -#[cfg(not(no_global_oom_handling))] -#[stable(feature = "cow_add", since = "1.14.0")] -impl<'a> AddAssign<&'a str> for Cow<'a, str> { - fn add_assign(&mut self, rhs: &'a str) { - if self.is_empty() { - *self = Cow::Borrowed(rhs) - } else if !rhs.is_empty() { - if let Cow::Borrowed(lhs) = *self { - let mut s = String::with_capacity(lhs.len() + rhs.len()); - s.push_str(lhs); - *self = Cow::Owned(s); - } - self.to_mut().push_str(rhs); - } - } -} - -#[cfg(not(no_global_oom_handling))] -#[stable(feature = "cow_add", since = "1.14.0")] -impl<'a> AddAssign<Cow<'a, str>> for Cow<'a, str> { - fn add_assign(&mut self, rhs: Cow<'a, str>) { - if self.is_empty() { - *self = rhs - } else if !rhs.is_empty() { - if let Cow::Borrowed(lhs) = *self { - let mut s = String::with_capacity(lhs.len() + rhs.len()); - s.push_str(lhs); - *self = Cow::Owned(s); - } - self.to_mut().push_str(&rhs); - } - } -} diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs index 233bcd5e4654..3aebf83c9967 100644 --- a/rust/alloc/lib.rs +++ b/rust/alloc/lib.rs @@ -100,7 +100,7 @@ #![cfg_attr(not(no_global_oom_handling), feature(const_alloc_error))] #![feature(const_box)] #![cfg_attr(not(no_global_oom_handling), feature(const_btree_new))] -#![feature(const_cow_is_borrowed)] +#![cfg_attr(not(no_borrow), feature(const_cow_is_borrowed))] #![feature(const_convert)] #![feature(const_size_of_val)] #![feature(const_align_of_val)] @@ -215,6 +215,7 @@ pub mod boxed; mod boxed { pub use std::boxed::Box; } +#[cfg(not(no_borrow))] pub mod borrow; pub mod collections; #[cfg(not(no_global_oom_handling))] diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs index 8ac6c1e3b2a8..f77c7368d534 100644 --- a/rust/alloc/vec/mod.rs +++ b/rust/alloc/vec/mod.rs @@ -72,6 +72,7 @@ use core::ptr::{self, NonNull}; use core::slice::{self, SliceIndex}; use crate::alloc::{Allocator, Global}; +#[cfg(not(no_borrow))] use crate::borrow::{Cow, ToOwned}; use crate::boxed::Box; use crate::collections::TryReserveError; @@ -94,6 +95,7 @@ pub use self::drain::Drain; mod drain; +#[cfg(not(no_borrow))] #[cfg(not(no_global_oom_handling))] mod cow; @@ -3103,6 +3105,7 @@ impl<T, const N: usize> From<[T; N]> for Vec<T> { } } +#[cfg(not(no_borrow))] #[stable(feature = "vec_from_cow_slice", since = "1.14.0")] impl<'a, T> From<Cow<'a, [T]>> for Vec<T> where diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index c48bc284214a..75d85bd6c592 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -7,6 +7,7 @@ */ #include <linux/slab.h> +#include <linux/refcount.h> /* `bindgen` gets confused at certain things. */ const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL; diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs index 6c50ee62c56b..7b246454e009 100644 --- a/rust/bindings/lib.rs +++ b/rust/bindings/lib.rs @@ -41,6 +41,7 @@ mod bindings_raw { #[allow(dead_code)] mod bindings_helper { // Import the generated bindings for types. + use super::bindings_raw::*; include!(concat!( env!("OBJTREE"), "/rust/bindings/bindings_helpers_generated.rs" diff --git a/rust/compiler_builtins.rs b/rust/compiler_builtins.rs index f8f39a3e6855..43378357ece9 100644 --- a/rust/compiler_builtins.rs +++ b/rust/compiler_builtins.rs @@ -28,7 +28,7 @@ macro_rules! define_panicking_intrinsics( ($reason: tt, { $($ident: ident, )* }) => { $( #[doc(hidden)] - #[no_mangle] + #[export_name = concat!("__rust", stringify!($ident))] pub extern "C" fn $ident() { panic!($reason); } @@ -61,3 +61,6 @@ define_panicking_intrinsics!("`u128` should not be used", { __udivti3, __umodti3, }); + +// NOTE: if you are adding a new intrinsic here, you should also add it to +// `redirect-intrinsics` in `rust/Makefile`. diff --git a/rust/helpers.c b/rust/helpers.c index b4f15eee2ffd..09a4d93f9d62 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -20,6 +20,7 @@ #include <linux/bug.h> #include <linux/build_bug.h> +#include <linux/refcount.h> __noreturn void rust_helper_BUG(void) { @@ -27,6 +28,24 @@ __noreturn void rust_helper_BUG(void) } EXPORT_SYMBOL_GPL(rust_helper_BUG); +refcount_t rust_helper_REFCOUNT_INIT(int n) +{ + return (refcount_t)REFCOUNT_INIT(n); +} +EXPORT_SYMBOL_GPL(rust_helper_REFCOUNT_INIT); + +void rust_helper_refcount_inc(refcount_t *r) +{ + refcount_inc(r); +} +EXPORT_SYMBOL_GPL(rust_helper_refcount_inc); + +bool rust_helper_refcount_dec_and_test(refcount_t *r) +{ + return refcount_dec_and_test(r); +} +EXPORT_SYMBOL_GPL(rust_helper_refcount_dec_and_test); + /* * We use `bindgen`'s `--size_t-is-usize` option to bind the C `size_t` type * as the Rust `usize` type, so we can use it in contexts where Rust diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 53040fa9e897..223564f9f0cc 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -13,7 +13,12 @@ #![no_std] #![feature(allocator_api)] +#![feature(coerce_unsized)] #![feature(core_ffi_c)] +#![feature(dispatch_from_dyn)] +#![feature(generic_associated_types)] +#![feature(receiver_trait)] +#![feature(unsize)] // Ensure conditional compilation based on the kernel configuration works; // otherwise we may silently break things like initcall handling. @@ -31,6 +36,7 @@ mod static_assert; #[doc(hidden)] pub mod std_vendor; pub mod str; +pub mod sync; pub mod types; #[doc(hidden)] diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index 7a90249ee9b9..0bc1c97e5604 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -11,15 +11,21 @@ //! use kernel::prelude::*; //! ``` +#[doc(no_inline)] pub use core::pin::Pin; +#[doc(no_inline)] pub use alloc::{boxed::Box, vec::Vec}; +#[doc(no_inline)] pub use macros::{module, vtable}; pub use super::build_assert; -pub use super::{dbg, pr_alert, pr_crit, pr_debug, pr_emerg, pr_err, pr_info, pr_notice, pr_warn}; +// `super::std_vendor` is hidden, which makes the macro inline for some reason. +#[doc(no_inline)] +pub use super::dbg; +pub use super::{pr_alert, pr_crit, pr_debug, pr_emerg, pr_err, pr_info, pr_notice, pr_warn}; pub use super::static_assert; diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs new file mode 100644 index 000000000000..33da23e3076d --- /dev/null +++ b/rust/kernel/sync.rs @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Synchronisation primitives. +//! +//! This module contains the kernel APIs related to synchronisation that have been ported or +//! wrapped for usage by Rust code in the kernel. + +mod arc; + +pub use arc::{Arc, ArcBorrow, UniqueArc}; diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs new file mode 100644 index 000000000000..f2f1c83d72ba --- /dev/null +++ b/rust/kernel/sync/arc.rs @@ -0,0 +1,524 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! A reference-counted pointer. +//! +//! This module implements a way for users to create reference-counted objects and pointers to +//! them. Such a pointer automatically increments and decrements the count, and drops the +//! underlying object when it reaches zero. It is also safe to use concurrently from multiple +//! threads. +//! +//! It is different from the standard library's [`Arc`] in a few ways: +//! 1. It is backed by the kernel's `refcount_t` type. +//! 2. It does not support weak references, which allows it to be half the size. +//! 3. It saturates the reference count instead of aborting when it goes over a threshold. +//! 4. It does not provide a `get_mut` method, so the ref counted object is pinned. +//! +//! [`Arc`]: https://doc.rust-lang.org/std/sync/struct.Arc.html + +use crate::{ + bindings, + error::Result, + types::{ForeignOwnable, Opaque}, +}; +use alloc::boxed::Box; +use core::{ + marker::{PhantomData, Unsize}, + mem::{ManuallyDrop, MaybeUninit}, + ops::{Deref, DerefMut}, + pin::Pin, + ptr::NonNull, +}; + +/// A reference-counted pointer to an instance of `T`. +/// +/// The reference count is incremented when new instances of [`Arc`] are created, and decremented +/// when they are dropped. When the count reaches zero, the underlying `T` is also dropped. +/// +/// # Invariants +/// +/// The reference count on an instance of [`Arc`] is always non-zero. +/// The object pointed to by [`Arc`] is always pinned. +/// +/// # Examples +/// +/// ``` +/// use kernel::sync::Arc; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// // Create a ref-counted instance of `Example`. +/// let obj = Arc::try_new(Example { a: 10, b: 20 })?; +/// +/// // Get a new pointer to `obj` and increment the refcount. +/// let cloned = obj.clone(); +/// +/// // Assert that both `obj` and `cloned` point to the same underlying object. +/// assert!(core::ptr::eq(&*obj, &*cloned)); +/// +/// // Destroy `obj` and decrement its refcount. +/// drop(obj); +/// +/// // Check that the values are still accessible through `cloned`. +/// assert_eq!(cloned.a, 10); +/// assert_eq!(cloned.b, 20); +/// +/// // The refcount drops to zero when `cloned` goes out of scope, and the memory is freed. +/// ``` +/// +/// Using `Arc<T>` as the type of `self`: +/// +/// ``` +/// use kernel::sync::Arc; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// impl Example { +/// fn take_over(self: Arc<Self>) { +/// // ... +/// } +/// +/// fn use_reference(self: &Arc<Self>) { +/// // ... +/// } +/// } +/// +/// let obj = Arc::try_new(Example { a: 10, b: 20 })?; +/// obj.use_reference(); +/// obj.take_over(); +/// ``` +/// +/// Coercion from `Arc<Example>` to `Arc<dyn MyTrait>`: +/// +/// ``` +/// use kernel::sync::{Arc, ArcBorrow}; +/// +/// trait MyTrait { +/// // Trait has a function whose `self` type is `Arc<Self>`. +/// fn example1(self: Arc<Self>) {} +/// +/// // Trait has a function whose `self` type is `ArcBorrow<'_, Self>`. +/// fn example2(self: ArcBorrow<'_, Self>) {} +/// } +/// +/// struct Example; +/// impl MyTrait for Example {} +/// +/// // `obj` has type `Arc<Example>`. +/// let obj: Arc<Example> = Arc::try_new(Example)?; +/// +/// // `coerced` has type `Arc<dyn MyTrait>`. +/// let coerced: Arc<dyn MyTrait> = obj; +/// ``` +pub struct Arc<T: ?Sized> { + ptr: NonNull<ArcInner<T>>, + _p: PhantomData<ArcInner<T>>, +} + +#[repr(C)] +struct ArcInner<T: ?Sized> { + refcount: Opaque<bindings::refcount_t>, + data: T, +} + +// This is to allow [`Arc`] (and variants) to be used as the type of `self`. +impl<T: ?Sized> core::ops::Receiver for Arc<T> {} + +// This is to allow coercion from `Arc<T>` to `Arc<U>` if `T` can be converted to the +// dynamically-sized type (DST) `U`. +impl<T: ?Sized + Unsize<U>, U: ?Sized> core::ops::CoerceUnsized<Arc<U>> for Arc<T> {} + +// This is to allow `Arc<U>` to be dispatched on when `Arc<T>` can be coerced into `Arc<U>`. +impl<T: ?Sized + Unsize<U>, U: ?Sized> core::ops::DispatchFromDyn<Arc<U>> for Arc<T> {} + +// SAFETY: It is safe to send `Arc<T>` to another thread when the underlying `T` is `Sync` because +// it effectively means sharing `&T` (which is safe because `T` is `Sync`); additionally, it needs +// `T` to be `Send` because any thread that has an `Arc<T>` may ultimately access `T` directly, for +// example, when the reference count reaches zero and `T` is dropped. +unsafe impl<T: ?Sized + Sync + Send> Send for Arc<T> {} + +// SAFETY: It is safe to send `&Arc<T>` to another thread when the underlying `T` is `Sync` for the +// same reason as above. `T` needs to be `Send` as well because a thread can clone an `&Arc<T>` +// into an `Arc<T>`, which may lead to `T` being accessed by the same reasoning as above. +unsafe impl<T: ?Sized + Sync + Send> Sync for Arc<T> {} + +impl<T> Arc<T> { + /// Constructs a new reference counted instance of `T`. + pub fn try_new(contents: T) -> Result<Self> { + // INVARIANT: The refcount is initialised to a non-zero value. + let value = ArcInner { + // SAFETY: There are no safety requirements for this FFI call. + refcount: Opaque::new(unsafe { bindings::REFCOUNT_INIT(1) }), + data: contents, + }; + + let inner = Box::try_new(value)?; + + // SAFETY: We just created `inner` with a reference count of 1, which is owned by the new + // `Arc` object. + Ok(unsafe { Self::from_inner(Box::leak(inner).into()) }) + } +} + +impl<T: ?Sized> Arc<T> { + /// Constructs a new [`Arc`] from an existing [`ArcInner`]. + /// + /// # Safety + /// + /// The caller must ensure that `inner` points to a valid location and has a non-zero reference + /// count, one of which will be owned by the new [`Arc`] instance. + unsafe fn from_inner(inner: NonNull<ArcInner<T>>) -> Self { + // INVARIANT: By the safety requirements, the invariants hold. + Arc { + ptr: inner, + _p: PhantomData, + } + } + + /// Returns an [`ArcBorrow`] from the given [`Arc`]. + /// + /// This is useful when the argument of a function call is an [`ArcBorrow`] (e.g., in a method + /// receiver), but we have an [`Arc`] instead. Getting an [`ArcBorrow`] is free when optimised. + #[inline] + pub fn as_arc_borrow(&self) -> ArcBorrow<'_, T> { + // SAFETY: The constraint that the lifetime of the shared reference must outlive that of + // the returned `ArcBorrow` ensures that the object remains alive and that no mutable + // reference can be created. + unsafe { ArcBorrow::new(self.ptr) } + } +} + +impl<T: 'static> ForeignOwnable for Arc<T> { + type Borrowed<'a> = ArcBorrow<'a, T>; + + fn into_foreign(self) -> *const core::ffi::c_void { + ManuallyDrop::new(self).ptr.as_ptr() as _ + } + + unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> ArcBorrow<'a, T> { + // SAFETY: By the safety requirement of this function, we know that `ptr` came from + // a previous call to `Arc::into_foreign`. + let inner = NonNull::new(ptr as *mut ArcInner<T>).unwrap(); + + // SAFETY: The safety requirements of `from_foreign` ensure that the object remains alive + // for the lifetime of the returned value. Additionally, the safety requirements of + // `ForeignOwnable::borrow_mut` ensure that no new mutable references are created. + unsafe { ArcBorrow::new(inner) } + } + + unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self { + // SAFETY: By the safety requirement of this function, we know that `ptr` came from + // a previous call to `Arc::into_foreign`, which guarantees that `ptr` is valid and + // holds a reference count increment that is transferrable to us. + unsafe { Self::from_inner(NonNull::new(ptr as _).unwrap()) } + } +} + +impl<T: ?Sized> Deref for Arc<T> { + type Target = T; + + fn deref(&self) -> &Self::Target { + // SAFETY: By the type invariant, there is necessarily a reference to the object, so it is + // safe to dereference it. + unsafe { &self.ptr.as_ref().data } + } +} + +impl<T: ?Sized> Clone for Arc<T> { + fn clone(&self) -> Self { + // INVARIANT: C `refcount_inc` saturates the refcount, so it cannot overflow to zero. + // SAFETY: By the type invariant, there is necessarily a reference to the object, so it is + // safe to increment the refcount. + unsafe { bindings::refcount_inc(self.ptr.as_ref().refcount.get()) }; + + // SAFETY: We just incremented the refcount. This increment is now owned by the new `Arc`. + unsafe { Self::from_inner(self.ptr) } + } +} + +impl<T: ?Sized> Drop for Arc<T> { + fn drop(&mut self) { + // SAFETY: By the type invariant, there is necessarily a reference to the object. We cannot + // touch `refcount` after it's decremented to a non-zero value because another thread/CPU + // may concurrently decrement it to zero and free it. It is ok to have a raw pointer to + // freed/invalid memory as long as it is never dereferenced. + let refcount = unsafe { self.ptr.as_ref() }.refcount.get(); + + // INVARIANT: If the refcount reaches zero, there are no other instances of `Arc`, and + // this instance is being dropped, so the broken invariant is not observable. + // SAFETY: Also by the type invariant, we are allowed to decrement the refcount. + let is_zero = unsafe { bindings::refcount_dec_and_test(refcount) }; + if is_zero { + // The count reached zero, we must free the memory. + // + // SAFETY: The pointer was initialised from the result of `Box::leak`. + unsafe { Box::from_raw(self.ptr.as_ptr()) }; + } + } +} + +impl<T: ?Sized> From<UniqueArc<T>> for Arc<T> { + fn from(item: UniqueArc<T>) -> Self { + item.inner + } +} + +impl<T: ?Sized> From<Pin<UniqueArc<T>>> for Arc<T> { + fn from(item: Pin<UniqueArc<T>>) -> Self { + // SAFETY: The type invariants of `Arc` guarantee that the data is pinned. + unsafe { Pin::into_inner_unchecked(item).inner } + } +} + +/// A borrowed reference to an [`Arc`] instance. +/// +/// For cases when one doesn't ever need to increment the refcount on the allocation, it is simpler +/// to use just `&T`, which we can trivially get from an `Arc<T>` instance. +/// +/// However, when one may need to increment the refcount, it is preferable to use an `ArcBorrow<T>` +/// over `&Arc<T>` because the latter results in a double-indirection: a pointer (shared reference) +/// to a pointer (`Arc<T>`) to the object (`T`). An [`ArcBorrow`] eliminates this double +/// indirection while still allowing one to increment the refcount and getting an `Arc<T>` when/if +/// needed. +/// +/// # Invariants +/// +/// There are no mutable references to the underlying [`Arc`], and it remains valid for the +/// lifetime of the [`ArcBorrow`] instance. +/// +/// # Example +/// +/// ``` +/// use crate::sync::{Arc, ArcBorrow}; +/// +/// struct Example; +/// +/// fn do_something(e: ArcBorrow<'_, Example>) -> Arc<Example> { +/// e.into() +/// } +/// +/// let obj = Arc::try_new(Example)?; +/// let cloned = do_something(obj.as_arc_borrow()); +/// +/// // Assert that both `obj` and `cloned` point to the same underlying object. +/// assert!(core::ptr::eq(&*obj, &*cloned)); +/// ``` +/// +/// Using `ArcBorrow<T>` as the type of `self`: +/// +/// ``` +/// use crate::sync::{Arc, ArcBorrow}; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// impl Example { +/// fn use_reference(self: ArcBorrow<'_, Self>) { +/// // ... +/// } +/// } +/// +/// let obj = Arc::try_new(Example { a: 10, b: 20 })?; +/// obj.as_arc_borrow().use_reference(); +/// ``` +pub struct ArcBorrow<'a, T: ?Sized + 'a> { + inner: NonNull<ArcInner<T>>, + _p: PhantomData<&'a ()>, +} + +// This is to allow [`ArcBorrow`] (and variants) to be used as the type of `self`. +impl<T: ?Sized> core::ops::Receiver for ArcBorrow<'_, T> {} + +// This is to allow `ArcBorrow<U>` to be dispatched on when `ArcBorrow<T>` can be coerced into +// `ArcBorrow<U>`. +impl<T: ?Sized + Unsize<U>, U: ?Sized> core::ops::DispatchFromDyn<ArcBorrow<'_, U>> + for ArcBorrow<'_, T> +{ +} + +impl<T: ?Sized> Clone for ArcBorrow<'_, T> { + fn clone(&self) -> Self { + *self + } +} + +impl<T: ?Sized> Copy for ArcBorrow<'_, T> {} + +impl<T: ?Sized> ArcBorrow<'_, T> { + /// Creates a new [`ArcBorrow`] instance. + /// + /// # Safety + /// + /// Callers must ensure the following for the lifetime of the returned [`ArcBorrow`] instance: + /// 1. That `inner` remains valid; + /// 2. That no mutable references to `inner` are created. + unsafe fn new(inner: NonNull<ArcInner<T>>) -> Self { + // INVARIANT: The safety requirements guarantee the invariants. + Self { + inner, + _p: PhantomData, + } + } +} + +impl<T: ?Sized> From<ArcBorrow<'_, T>> for Arc<T> { + fn from(b: ArcBorrow<'_, T>) -> Self { + // SAFETY: The existence of `b` guarantees that the refcount is non-zero. `ManuallyDrop` + // guarantees that `drop` isn't called, so it's ok that the temporary `Arc` doesn't own the + // increment. + ManuallyDrop::new(unsafe { Arc::from_inner(b.inner) }) + .deref() + .clone() + } +} + +impl<T: ?Sized> Deref for ArcBorrow<'_, T> { + type Target = T; + + fn deref(&self) -> &Self::Target { + // SAFETY: By the type invariant, the underlying object is still alive with no mutable + // references to it, so it is safe to create a shared reference. + unsafe { &self.inner.as_ref().data } + } +} + +/// A refcounted object that is known to have a refcount of 1. +/// +/// It is mutable and can be converted to an [`Arc`] so that it can be shared. +/// +/// # Invariants +/// +/// `inner` always has a reference count of 1. +/// +/// # Examples +/// +/// In the following example, we make changes to the inner object before turning it into an +/// `Arc<Test>` object (after which point, it cannot be mutated directly). Note that `x.into()` +/// cannot fail. +/// +/// ``` +/// use kernel::sync::{Arc, UniqueArc}; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn test() -> Result<Arc<Example>> { +/// let mut x = UniqueArc::try_new(Example { a: 10, b: 20 })?; +/// x.a += 1; +/// x.b += 1; +/// Ok(x.into()) +/// } +/// +/// # test().unwrap(); +/// ``` +/// +/// In the following example we first allocate memory for a ref-counted `Example` but we don't +/// initialise it on allocation. We do initialise it later with a call to [`UniqueArc::write`], +/// followed by a conversion to `Arc<Example>`. This is particularly useful when allocation happens +/// in one context (e.g., sleepable) and initialisation in another (e.g., atomic): +/// +/// ``` +/// use kernel::sync::{Arc, UniqueArc}; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn test() -> Result<Arc<Example>> { +/// let x = UniqueArc::try_new_uninit()?; +/// Ok(x.write(Example { a: 10, b: 20 }).into()) +/// } +/// +/// # test().unwrap(); +/// ``` +/// +/// In the last example below, the caller gets a pinned instance of `Example` while converting to +/// `Arc<Example>`; this is useful in scenarios where one needs a pinned reference during +/// initialisation, for example, when initialising fields that are wrapped in locks. +/// +/// ``` +/// use kernel::sync::{Arc, UniqueArc}; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn test() -> Result<Arc<Example>> { +/// let mut pinned = Pin::from(UniqueArc::try_new(Example { a: 10, b: 20 })?); +/// // We can modify `pinned` because it is `Unpin`. +/// pinned.as_mut().a += 1; +/// Ok(pinned.into()) +/// } +/// +/// # test().unwrap(); +/// ``` +pub struct UniqueArc<T: ?Sized> { + inner: Arc<T>, +} + +impl<T> UniqueArc<T> { + /// Tries to allocate a new [`UniqueArc`] instance. + pub fn try_new(value: T) -> Result<Self> { + Ok(Self { + // INVARIANT: The newly-created object has a ref-count of 1. + inner: Arc::try_new(value)?, + }) + } + + /// Tries to allocate a new [`UniqueArc`] instance whose contents are not initialised yet. + pub fn try_new_uninit() -> Result<UniqueArc<MaybeUninit<T>>> { + Ok(UniqueArc::<MaybeUninit<T>> { + // INVARIANT: The newly-created object has a ref-count of 1. + inner: Arc::try_new(MaybeUninit::uninit())?, + }) + } +} + +impl<T> UniqueArc<MaybeUninit<T>> { + /// Converts a `UniqueArc<MaybeUninit<T>>` into a `UniqueArc<T>` by writing a value into it. + pub fn write(mut self, value: T) -> UniqueArc<T> { + self.deref_mut().write(value); + let inner = ManuallyDrop::new(self).inner.ptr; + UniqueArc { + // SAFETY: The new `Arc` is taking over `ptr` from `self.inner` (which won't be + // dropped). The types are compatible because `MaybeUninit<T>` is compatible with `T`. + inner: unsafe { Arc::from_inner(inner.cast()) }, + } + } +} + +impl<T: ?Sized> From<UniqueArc<T>> for Pin<UniqueArc<T>> { + fn from(obj: UniqueArc<T>) -> Self { + // SAFETY: It is not possible to move/replace `T` inside a `Pin<UniqueArc<T>>` (unless `T` + // is `Unpin`), so it is ok to convert it to `Pin<UniqueArc<T>>`. + unsafe { Pin::new_unchecked(obj) } + } +} + +impl<T: ?Sized> Deref for UniqueArc<T> { + type Target = T; + + fn deref(&self) -> &Self::Target { + self.inner.deref() + } +} + +impl<T: ?Sized> DerefMut for UniqueArc<T> { + fn deref_mut(&mut self) -> &mut Self::Target { + // SAFETY: By the `Arc` type invariant, there is necessarily a reference to the object, so + // it is safe to dereference it. Additionally, we know there is only one reference when + // it's inside a `UniqueArc`, so it is safe to get a mutable reference. + unsafe { &mut self.inner.ptr.as_mut().data } + } +} diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index e84e51ec9716..9d0fdbc55843 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -2,7 +2,220 @@ //! Kernel types. -use core::{cell::UnsafeCell, mem::MaybeUninit}; +use alloc::boxed::Box; +use core::{ + cell::UnsafeCell, + mem::MaybeUninit, + ops::{Deref, DerefMut}, +}; + +/// Used to transfer ownership to and from foreign (non-Rust) languages. +/// +/// Ownership is transferred from Rust to a foreign language by calling [`Self::into_foreign`] and +/// later may be transferred back to Rust by calling [`Self::from_foreign`]. +/// +/// This trait is meant to be used in cases when Rust objects are stored in C objects and +/// eventually "freed" back to Rust. +pub trait ForeignOwnable: Sized { + /// Type of values borrowed between calls to [`ForeignOwnable::into_foreign`] and + /// [`ForeignOwnable::from_foreign`]. + type Borrowed<'a>; + + /// Converts a Rust-owned object to a foreign-owned one. + /// + /// The foreign representation is a pointer to void. + fn into_foreign(self) -> *const core::ffi::c_void; + + /// Borrows a foreign-owned object. + /// + /// # Safety + /// + /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for + /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. + /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow_mut`] + /// for this object must have been dropped. + unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Self::Borrowed<'a>; + + /// Mutably borrows a foreign-owned object. + /// + /// # Safety + /// + /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for + /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. + /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] and + /// [`ForeignOwnable::borrow_mut`] for this object must have been dropped. + unsafe fn borrow_mut(ptr: *const core::ffi::c_void) -> ScopeGuard<Self, fn(Self)> { + // SAFETY: The safety requirements ensure that `ptr` came from a previous call to + // `into_foreign`. + ScopeGuard::new_with_data(unsafe { Self::from_foreign(ptr) }, |d| { + d.into_foreign(); + }) + } + + /// Converts a foreign-owned object back to a Rust-owned one. + /// + /// # Safety + /// + /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for + /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. + /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] and + /// [`ForeignOwnable::borrow_mut`] for this object must have been dropped. + unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self; +} + +impl<T: 'static> ForeignOwnable for Box<T> { + type Borrowed<'a> = &'a T; + + fn into_foreign(self) -> *const core::ffi::c_void { + Box::into_raw(self) as _ + } + + unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> &'a T { + // SAFETY: The safety requirements for this function ensure that the object is still alive, + // so it is safe to dereference the raw pointer. + // The safety requirements of `from_foreign` also ensure that the object remains alive for + // the lifetime of the returned value. + unsafe { &*ptr.cast() } + } + + unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self { + // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous + // call to `Self::into_foreign`. + unsafe { Box::from_raw(ptr as _) } + } +} + +impl ForeignOwnable for () { + type Borrowed<'a> = (); + + fn into_foreign(self) -> *const core::ffi::c_void { + core::ptr::NonNull::dangling().as_ptr() + } + + unsafe fn borrow<'a>(_: *const core::ffi::c_void) -> Self::Borrowed<'a> {} + + unsafe fn from_foreign(_: *const core::ffi::c_void) -> Self {} +} + +/// Runs a cleanup function/closure when dropped. +/// +/// The [`ScopeGuard::dismiss`] function prevents the cleanup function from running. +/// +/// # Examples +/// +/// In the example below, we have multiple exit paths and we want to log regardless of which one is +/// taken: +/// ``` +/// # use kernel::ScopeGuard; +/// fn example1(arg: bool) { +/// let _log = ScopeGuard::new(|| pr_info!("example1 completed\n")); +/// +/// if arg { +/// return; +/// } +/// +/// pr_info!("Do something...\n"); +/// } +/// +/// # example1(false); +/// # example1(true); +/// ``` +/// +/// In the example below, we want to log the same message on all early exits but a different one on +/// the main exit path: +/// ``` +/// # use kernel::ScopeGuard; +/// fn example2(arg: bool) { +/// let log = ScopeGuard::new(|| pr_info!("example2 returned early\n")); +/// +/// if arg { +/// return; +/// } +/// +/// // (Other early returns...) +/// +/// log.dismiss(); +/// pr_info!("example2 no early return\n"); +/// } +/// +/// # example2(false); +/// # example2(true); +/// ``` +/// +/// In the example below, we need a mutable object (the vector) to be accessible within the log +/// function, so we wrap it in the [`ScopeGuard`]: +/// ``` +/// # use kernel::ScopeGuard; +/// fn example3(arg: bool) -> Result { +/// let mut vec = +/// ScopeGuard::new_with_data(Vec::new(), |v| pr_info!("vec had {} elements\n", v.len())); +/// +/// vec.try_push(10u8)?; +/// if arg { +/// return Ok(()); +/// } +/// vec.try_push(20u8)?; +/// Ok(()) +/// } +/// +/// # assert_eq!(example3(false), Ok(())); +/// # assert_eq!(example3(true), Ok(())); +/// ``` +/// +/// # Invariants +/// +/// The value stored in the struct is nearly always `Some(_)`, except between +/// [`ScopeGuard::dismiss`] and [`ScopeGuard::drop`]: in this case, it will be `None` as the value +/// will have been returned to the caller. Since [`ScopeGuard::dismiss`] consumes the guard, +/// callers won't be able to use it anymore. +pub struct ScopeGuard<T, F: FnOnce(T)>(Option<(T, F)>); + +impl<T, F: FnOnce(T)> ScopeGuard<T, F> { + /// Creates a new guarded object wrapping the given data and with the given cleanup function. + pub fn new_with_data(data: T, cleanup_func: F) -> Self { + // INVARIANT: The struct is being initialised with `Some(_)`. + Self(Some((data, cleanup_func))) + } + + /// Prevents the cleanup function from running and returns the guarded data. + pub fn dismiss(mut self) -> T { + // INVARIANT: This is the exception case in the invariant; it is not visible to callers + // because this function consumes `self`. + self.0.take().unwrap().0 + } +} + +impl ScopeGuard<(), fn(())> { + /// Creates a new guarded object with the given cleanup function. + pub fn new(cleanup: impl FnOnce()) -> ScopeGuard<(), impl FnOnce(())> { + ScopeGuard::new_with_data((), move |_| cleanup()) + } +} + +impl<T, F: FnOnce(T)> Deref for ScopeGuard<T, F> { + type Target = T; + + fn deref(&self) -> &T { + // The type invariants guarantee that `unwrap` will succeed. + &self.0.as_ref().unwrap().0 + } +} + +impl<T, F: FnOnce(T)> DerefMut for ScopeGuard<T, F> { + fn deref_mut(&mut self) -> &mut T { + // The type invariants guarantee that `unwrap` will succeed. + &mut self.0.as_mut().unwrap().0 + } +} + +impl<T, F: FnOnce(T)> Drop for ScopeGuard<T, F> { + fn drop(&mut self) { + // Run the cleanup function if one is still present. + if let Some((data, cleanup)) = self.0.take() { + cleanup(data) + } + } +} /// Stores an opaque value. /// diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 15fc4626d236..9ee99f9fae8d 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -163,7 +163,7 @@ def get_current_task(cpu): task_ptr_type = task_type.get_type().pointer() if utils.is_target_arch("x86"): - var_ptr = gdb.parse_and_eval("¤t_task") + var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") return per_cpu(var_ptr, cpu).dereference() elif utils.is_target_arch("aarch64"): current_task_addr = gdb.parse_and_eval("$SP_EL0") diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 424b2c1e586d..db7a51acf9db 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -1793,7 +1793,7 @@ fail2: return error; } -static int ns_mkdir_op(struct user_namespace *mnt_userns, struct inode *dir, +static int ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct aa_ns *ns, *parent; diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 6dd3cc5309bf..f3715cda59c5 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -313,7 +313,7 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, d = bprm->file->f_path.dentry; for (i = 0; i < attach->xattr_count; i++) { - size = vfs_getxattr_alloc(&init_user_ns, d, attach->xattrs[i], + size = vfs_getxattr_alloc(&nop_mnt_idmap, d, attach->xattrs[i], &value, value_size, GFP_KERNEL); if (size >= 0) { u32 index, perm; @@ -862,7 +862,7 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) const char *info = NULL; int error = 0; bool unsafe = false; - vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_user_ns(bprm->file), + vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(bprm->file), file_inode(bprm->file)); struct path_cond cond = { vfsuid_into_kuid(vfsuid), diff --git a/security/apparmor/file.c b/security/apparmor/file.c index cb3d3060d104..9119ddda6217 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -459,7 +459,7 @@ static int __file_path_perm(const char *op, struct aa_label *label, { struct aa_profile *profile; struct aa_perms perms = {}; - vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_user_ns(file), + vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(file), file_inode(file)); struct path_cond cond = { .uid = vfsuid_into_kuid(vfsuid), diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index c6728a629437..d6cc4812ca53 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -227,8 +227,7 @@ static int common_perm(const char *op, const struct path *path, u32 mask, */ static int common_perm_cond(const char *op, const struct path *path, u32 mask) { - struct user_namespace *mnt_userns = mnt_user_ns(path->mnt); - vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, + vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(path->mnt), d_backing_inode(path->dentry)); struct path_cond cond = { vfsuid_into_kuid(vfsuid), @@ -273,14 +272,13 @@ static int common_perm_rm(const char *op, const struct path *dir, struct dentry *dentry, u32 mask) { struct inode *inode = d_backing_inode(dentry); - struct user_namespace *mnt_userns = mnt_user_ns(dir->mnt); struct path_cond cond = { }; vfsuid_t vfsuid; if (!inode || !path_mediated_fs(dentry)) return 0; - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(mnt_idmap(dir->mnt), inode); cond.uid = vfsuid_into_kuid(vfsuid); cond.mode = inode->i_mode; @@ -379,7 +377,7 @@ static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_d label = begin_current_label_crit_section(); if (!unconfined(label)) { - struct user_namespace *mnt_userns = mnt_user_ns(old_dir->mnt); + struct mnt_idmap *idmap = mnt_idmap(old_dir->mnt); vfsuid_t vfsuid; struct path old_path = { .mnt = old_dir->mnt, .dentry = old_dentry }; @@ -388,14 +386,14 @@ static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_d struct path_cond cond = { .mode = d_backing_inode(old_dentry)->i_mode }; - vfsuid = i_uid_into_vfsuid(mnt_userns, d_backing_inode(old_dentry)); + vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry)); cond.uid = vfsuid_into_kuid(vfsuid); if (flags & RENAME_EXCHANGE) { struct path_cond cond_exchange = { .mode = d_backing_inode(new_dentry)->i_mode, }; - vfsuid = i_uid_into_vfsuid(mnt_userns, d_backing_inode(old_dentry)); + vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry)); cond_exchange.uid = vfsuid_into_kuid(vfsuid); error = aa_path_perm(OP_RENAME_SRC, label, &new_path, 0, @@ -460,13 +458,13 @@ static int apparmor_file_open(struct file *file) label = aa_get_newest_cred_label(file->f_cred); if (!unconfined(label)) { - struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); vfsuid_t vfsuid; struct path_cond cond = { .mode = inode->i_mode, }; - vfsuid = i_uid_into_vfsuid(mnt_userns, inode); + vfsuid = i_uid_into_vfsuid(idmap, inode); cond.uid = vfsuid_into_kuid(vfsuid); error = aa_path_perm(OP_OPEN, label, &file->f_path, 0, diff --git a/security/apparmor/policy_compat.c b/security/apparmor/policy_compat.c index 9e52e218bf30..cc89d1e88fb7 100644 --- a/security/apparmor/policy_compat.c +++ b/security/apparmor/policy_compat.c @@ -160,8 +160,7 @@ static struct aa_perms *compute_fperms(struct aa_dfa *dfa) if (!table) return NULL; - /* zero init so skip the trap state (state == 0) */ - for (state = 1; state < state_count; state++) { + for (state = 0; state < state_count; state++) { table[state * 2] = compute_fperms_user(dfa, state); table[state * 2 + 1] = compute_fperms_other(dfa, state); } diff --git a/security/commoncap.c b/security/commoncap.c index 1164278b97fd..aec62db55271 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -305,24 +305,24 @@ int cap_inode_need_killpriv(struct dentry *dentry) /** * cap_inode_killpriv - Erase the security markings on an inode * - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. * * Return: 0 if successful, -ve on error. */ -int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry) +int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { int error; - error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS); + error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; @@ -377,7 +377,7 @@ static bool is_v3header(int size, const struct vfs_cap_data *cap) * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ -int cap_inode_getsecurity(struct user_namespace *mnt_userns, +int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { @@ -398,7 +398,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; - size = vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS, &tmpbuf, + size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf, sizeof(struct vfs_ns_cap_data), GFP_NOFS); dput(dentry); /* gcc11 complains if we don't check for !tmpbuf */ @@ -420,7 +420,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ - vfsroot = make_vfsuid(mnt_userns, fs_ns, kroot); + vfsroot = make_vfsuid(idmap, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ @@ -510,7 +510,7 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap) /** * cap_convert_nscap - check vfs caps * - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue @@ -518,15 +518,15 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap) * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. * * Return: On success, return the new size; on error, return < 0. */ -int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, +int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; @@ -544,9 +544,9 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, return -EINVAL; if (!validheader(size, cap)) return -EINVAL; - if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) + if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; - if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) + if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; @@ -555,7 +555,7 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, if (!vfsuid_valid(vfsrootid)) return -EINVAL; - rootid = from_vfsuid(mnt_userns, fs_ns, vfsrootid); + rootid = from_vfsuid(idmap, fs_ns, vfsrootid); if (!uid_valid(rootid)) return -EINVAL; @@ -626,19 +626,19 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply passs @nop_mnt_idmap. */ -int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, +int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { @@ -695,7 +695,7 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, return -EINVAL; } - rootvfsuid = make_vfsuid(mnt_userns, fs_ns, rootkuid); + rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid); if (!vfsuid_valid(rootvfsuid)) return -ENODATA; @@ -747,7 +747,7 @@ static int get_file_caps(struct linux_binprm *bprm, struct file *file, if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; - rc = get_vfs_caps_from_disk(file_mnt_user_ns(file), + rc = get_vfs_caps_from_disk(file_mnt_idmap(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) @@ -1016,23 +1016,23 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name, /** * cap_inode_removexattr - Determine whether an xattr may be removed * - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * - * If the inode has been found through an idmapped mount the user namespace of - * the vfsmount must be passed through @mnt_userns. This function will then - * take care to map the inode according to @mnt_userns before checking + * If the inode has been found through an idmapped mount the idmap of + * the vfsmount must be passed through @idmap. This function will then + * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs init_user_ns. + * performed on the raw inode simply pass @nop_mnt_idmap. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ -int cap_inode_removexattr(struct user_namespace *mnt_userns, +int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; @@ -1047,7 +1047,7 @@ int cap_inode_removexattr(struct user_namespace *mnt_userns, struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; - if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) + if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; return 0; } diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index fa5ff13fa8c9..52b811da6989 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -265,7 +265,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry, req_xattr_value_len); continue; } - size = vfs_getxattr_alloc(&init_user_ns, dentry, xattr->name, + size = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr->name, &xattr_value, xattr_size, GFP_NOFS); if (size == -ENOMEM) { error = -ENOMEM; @@ -274,7 +274,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry, if (size < 0) continue; - user_space_size = vfs_getxattr(&init_user_ns, dentry, + user_space_size = vfs_getxattr(&nop_mnt_idmap, dentry, xattr->name, NULL, 0); if (user_space_size != size) pr_debug("file %s: xattr %s size mismatch (kernel: %d, user: %d)\n", @@ -331,7 +331,7 @@ static int evm_is_immutable(struct dentry *dentry, struct inode *inode) return 1; /* Do this the hard way */ - rc = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_EVM, + rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { if (rc == -ENODATA) @@ -376,12 +376,12 @@ int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name, xattr_value_len, &data); if (rc == 0) { data.hdr.xattr.sha1.type = EVM_XATTR_HMAC; - rc = __vfs_setxattr_noperm(&init_user_ns, dentry, + rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, &data.hdr.xattr.data[1], SHA1_DIGEST_SIZE + 1, 0); } else if (rc == -ENODATA && (inode->i_opflags & IOP_XATTR)) { - rc = __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_EVM); + rc = __vfs_removexattr(&nop_mnt_idmap, dentry, XATTR_NAME_EVM); } return rc; } diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index f02e609460e2..cf24c5255583 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -184,7 +184,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry, /* if status is not PASS, try to check again - against -ENOMEM */ /* first need to know the sig type */ - rc = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_EVM, + rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { evm_status = INTEGRITY_FAIL; @@ -436,7 +436,7 @@ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) /* * evm_xattr_change - check if passed xattr value differs from current value - * @mnt_userns: user namespace of the idmapped mount + * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: requested xattr * @xattr_value: requested xattr value @@ -446,14 +446,14 @@ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) * * Returns 1 if passed xattr value differs from current value, 0 otherwise. */ -static int evm_xattr_change(struct user_namespace *mnt_userns, +static int evm_xattr_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { char *xattr_data = NULL; int rc = 0; - rc = vfs_getxattr_alloc(&init_user_ns, dentry, xattr_name, &xattr_data, + rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr_name, &xattr_data, 0, GFP_NOFS); if (rc < 0) { rc = 1; @@ -482,7 +482,7 @@ out: * For posix xattr acls only, permit security.evm, even if it currently * doesn't exist, to be updated unless the EVM signature is immutable. */ -static int evm_protect_xattr(struct user_namespace *mnt_userns, +static int evm_protect_xattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { @@ -538,7 +538,7 @@ out: return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && - !evm_xattr_change(mnt_userns, dentry, xattr_name, xattr_value, + !evm_xattr_change(idmap, dentry, xattr_name, xattr_value, xattr_value_len)) return 0; @@ -553,7 +553,7 @@ out: /** * evm_inode_setxattr - protect the EVM extended attribute - * @mnt_userns: user namespace of the idmapped mount + * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value @@ -565,7 +565,7 @@ out: * userspace from writing HMAC value. Writing 'security.evm' requires * requires CAP_SYS_ADMIN privileges. */ -int evm_inode_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { @@ -584,20 +584,20 @@ int evm_inode_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) return -EPERM; } - return evm_protect_xattr(mnt_userns, dentry, xattr_name, xattr_value, + return evm_protect_xattr(idmap, dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_removexattr - protect the EVM extended attribute - * @mnt_userns: user namespace of the idmapped mount + * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that * the current value is valid. */ -int evm_inode_removexattr(struct user_namespace *mnt_userns, +int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { /* Policy permits modification of the protected xattrs even though @@ -606,11 +606,11 @@ int evm_inode_removexattr(struct user_namespace *mnt_userns, if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; - return evm_protect_xattr(mnt_userns, dentry, xattr_name, NULL, 0); + return evm_protect_xattr(idmap, dentry, xattr_name, NULL, 0); } #ifdef CONFIG_FS_POSIX_ACL -static int evm_inode_set_acl_change(struct user_namespace *mnt_userns, +static int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { @@ -622,14 +622,14 @@ static int evm_inode_set_acl_change(struct user_namespace *mnt_userns, if (!kacl) return 1; - rc = posix_acl_update_mode(mnt_userns, inode, &mode, &kacl); + rc = posix_acl_update_mode(idmap, inode, &mode, &kacl); if (rc || (inode->i_mode != mode)) return 1; return 0; } #else -static inline int evm_inode_set_acl_change(struct user_namespace *mnt_userns, +static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) @@ -640,7 +640,7 @@ static inline int evm_inode_set_acl_change(struct user_namespace *mnt_userns, /** * evm_inode_set_acl - protect the EVM extended attribute from posix acls - * @mnt_userns: user namespace of the idmapped mount + * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls @@ -649,7 +649,7 @@ static inline int evm_inode_set_acl_change(struct user_namespace *mnt_userns, * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. */ -int evm_inode_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { enum integrity_status evm_status; @@ -678,7 +678,7 @@ int evm_inode_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && - !evm_inode_set_acl_change(mnt_userns, dentry, acl_name, kacl)) + !evm_inode_set_acl_change(idmap, dentry, acl_name, kacl)) return 0; if (evm_status != INTEGRITY_PASS_IMMUTABLE) @@ -779,14 +779,14 @@ void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) evm_update_evmxattr(dentry, xattr_name, NULL, 0); } -static int evm_attr_change(struct user_namespace *mnt_userns, +static int evm_attr_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = attr->ia_valid; - if (!i_uid_needs_update(mnt_userns, attr, inode) && - !i_gid_needs_update(mnt_userns, attr, inode) && + if (!i_uid_needs_update(idmap, attr, inode) && + !i_gid_needs_update(idmap, attr, inode) && (!(ia_valid & ATTR_MODE) || attr->ia_mode == inode->i_mode)) return 0; @@ -800,7 +800,7 @@ static int evm_attr_change(struct user_namespace *mnt_userns, * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. */ -int evm_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; @@ -827,7 +827,7 @@ int evm_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && - !evm_attr_change(mnt_userns, dentry, attr)) + !evm_attr_change(idmap, dentry, attr)) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c index 8a9db7dfca7e..9b907c2fee60 100644 --- a/security/integrity/evm/evm_secfs.c +++ b/security/integrity/evm/evm_secfs.c @@ -228,7 +228,7 @@ static ssize_t evm_write_xattrs(struct file *file, const char __user *buf, newattrs.ia_valid = ATTR_MODE; inode = evm_xattrs->d_inode; inode_lock(inode); - err = simple_setattr(&init_user_ns, evm_xattrs, &newattrs); + err = simple_setattr(&nop_mnt_idmap, evm_xattrs, &newattrs); inode_unlock(inode); if (!err) err = count; diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 03b440921e61..d8530e722515 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -254,7 +254,7 @@ static inline void ima_process_queued_keys(void) {} #endif /* CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS */ /* LIM API function definitions */ -int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode, +int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, u32 secid, int mask, enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, @@ -268,7 +268,7 @@ void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig, int pcr, struct ima_template_desc *template_desc); -int process_buffer_measurement(struct user_namespace *mnt_userns, +int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, @@ -285,7 +285,7 @@ void ima_free_template_entry(struct ima_template_entry *entry); const char *ima_d_path(const struct path *path, char **pathbuf, char *filename); /* IMA policy related functions */ -int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode, +int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, u32 secid, enum ima_hooks func, int mask, int flags, int *pcr, struct ima_template_desc **template_desc, @@ -318,7 +318,7 @@ int ima_appraise_measurement(enum ima_hooks func, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig); -int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode, +int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func); void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file); enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint, @@ -346,7 +346,7 @@ static inline int ima_appraise_measurement(enum ima_hooks func, return INTEGRITY_UNKNOWN; } -static inline int ima_must_appraise(struct user_namespace *mnt_userns, +static inline int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index c1e76282b5ee..9345fd66f5b8 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -163,7 +163,7 @@ err_out: /** * ima_get_action - appraise & measure decision based on policy. - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: pointer to the inode associated with the object being validated * @cred: pointer to credentials structure to validate * @secid: secid of the task being validated @@ -186,7 +186,7 @@ err_out: * Returns IMA_MEASURE, IMA_APPRAISE mask. * */ -int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode, +int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, u32 secid, int mask, enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, @@ -196,7 +196,7 @@ int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode, flags &= ima_policy_flag; - return ima_match_policy(mnt_userns, inode, cred, secid, func, mask, + return ima_match_policy(idmap, inode, cred, secid, func, mask, flags, pcr, template_desc, func_data, allowed_algos); } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index ee6f7e237f2e..555342d337f9 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -70,7 +70,7 @@ bool is_ima_appraise_enabled(void) * * Return 1 to appraise or hash */ -int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode, +int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { u32 secid; @@ -79,7 +79,7 @@ int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode, return 0; security_current_getsecid_subj(&secid); - return ima_match_policy(mnt_userns, inode, current_cred(), secid, + return ima_match_policy(idmap, inode, current_cred(), secid, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } @@ -98,7 +98,7 @@ static int ima_fix_xattr(struct dentry *dentry, iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } - rc = __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_IMA, + rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); @@ -225,7 +225,7 @@ int ima_read_xattr(struct dentry *dentry, { int ret; - ret = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_IMA, + ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, (char **)xattr_value, xattr_len, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; @@ -456,7 +456,7 @@ int ima_check_blacklist(struct integrity_iint_cache *iint, rc = is_binary_blacklisted(digest, digestsize); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) - process_buffer_measurement(&init_user_ns, NULL, digest, digestsize, + process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL, false, NULL, 0); } @@ -622,7 +622,7 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file) /** * ima_inode_post_setattr - reflect file metadata changes - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: pointer to the affected dentry * * Changes to a dentry's metadata might result in needing to appraise. @@ -630,7 +630,7 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file) * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ -void ima_inode_post_setattr(struct user_namespace *mnt_userns, +void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); @@ -641,7 +641,7 @@ void ima_inode_post_setattr(struct user_namespace *mnt_userns, || !(inode->i_opflags & IOP_XATTR)) return; - action = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, POST_SETATTR); + action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR); iint = integrity_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); @@ -774,7 +774,7 @@ int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, return result; } -int ima_inode_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (evm_revalidate_status(acl_name)) diff --git a/security/integrity/ima/ima_asymmetric_keys.c b/security/integrity/ima/ima_asymmetric_keys.c index f6aa0b47a772..caacfe6860b1 100644 --- a/security/integrity/ima/ima_asymmetric_keys.c +++ b/security/integrity/ima/ima_asymmetric_keys.c @@ -60,7 +60,7 @@ void ima_post_key_create_or_update(struct key *keyring, struct key *key, * if the IMA policy is configured to measure a key linked * to the given keyring. */ - process_buffer_measurement(&init_user_ns, NULL, payload, payload_len, + process_buffer_measurement(&nop_mnt_idmap, NULL, payload, payload_len, keyring->description, KEY_CHECK, 0, keyring->description, false, NULL, 0); } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 377300973e6c..358578267fea 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -224,7 +224,7 @@ static int process_measurement(struct file *file, const struct cred *cred, * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ - action = ima_get_action(file_mnt_user_ns(file), inode, cred, secid, + action = ima_get_action(file_mnt_idmap(file), inode, cred, secid, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK) && @@ -451,7 +451,7 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) security_current_getsecid_subj(&secid); inode = file_inode(vma->vm_file); - action = ima_get_action(file_mnt_user_ns(vma->vm_file), inode, + action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); @@ -638,14 +638,14 @@ EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ -void ima_post_create_tmpfile(struct user_namespace *mnt_userns, +void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct integrity_iint_cache *iint; @@ -654,7 +654,7 @@ void ima_post_create_tmpfile(struct user_namespace *mnt_userns, if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; - must_appraise = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, + must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; @@ -671,13 +671,13 @@ void ima_post_create_tmpfile(struct user_namespace *mnt_userns, /** * ima_post_path_mknod - mark as a new inode - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ -void ima_post_path_mknod(struct user_namespace *mnt_userns, +void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct integrity_iint_cache *iint; @@ -687,7 +687,7 @@ void ima_post_path_mknod(struct user_namespace *mnt_userns, if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; - must_appraise = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, + must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; @@ -869,7 +869,7 @@ int ima_post_load_data(char *buf, loff_t size, /** * process_buffer_measurement - Measure the buffer or the buffer data hash - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). @@ -887,7 +887,7 @@ int ima_post_load_data(char *buf, loff_t size, * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ -int process_buffer_measurement(struct user_namespace *mnt_userns, +int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, @@ -931,7 +931,7 @@ int process_buffer_measurement(struct user_namespace *mnt_userns, */ if (func) { security_current_getsecid_subj(&secid); - action = ima_get_action(mnt_userns, inode, current_cred(), + action = ima_get_action(idmap, inode, current_cred(), secid, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) @@ -1011,7 +1011,7 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) if (!f.file) return; - process_buffer_measurement(file_mnt_user_ns(f.file), file_inode(f.file), + process_buffer_measurement(file_mnt_idmap(f.file), file_inode(f.file), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); fdput(f); @@ -1044,7 +1044,7 @@ int ima_measure_critical_data(const char *event_label, if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; - return process_buffer_measurement(&init_user_ns, NULL, buf, buf_len, + return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 6a68ec270822..fc128a6b4abe 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -552,7 +552,7 @@ static bool ima_match_rule_data(struct ima_rule_entry *rule, /** * ima_match_rules - determine whether an inode matches the policy rule. * @rule: a pointer to a rule - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: a pointer to an inode * @cred: a pointer to a credentials structure for user validation * @secid: the secid of the task to be validated @@ -563,7 +563,7 @@ static bool ima_match_rule_data(struct ima_rule_entry *rule, * Returns true on rule match, false on failure. */ static bool ima_match_rules(struct ima_rule_entry *rule, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, u32 secid, enum ima_hooks func, int mask, const char *func_data) @@ -624,11 +624,11 @@ static bool ima_match_rules(struct ima_rule_entry *rule, return false; } if ((rule->flags & IMA_FOWNER) && - !rule->fowner_op(i_uid_into_vfsuid(mnt_userns, inode), + !rule->fowner_op(i_uid_into_vfsuid(idmap, inode), rule->fowner)) return false; if ((rule->flags & IMA_FGROUP) && - !rule->fgroup_op(i_gid_into_vfsgid(mnt_userns, inode), + !rule->fgroup_op(i_gid_into_vfsgid(idmap, inode), rule->fgroup)) return false; for (i = 0; i < MAX_LSM_RULES; i++) { @@ -713,7 +713,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) /** * ima_match_policy - decision based on LSM and other conditions - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: pointer to an inode for which the policy decision is being made * @cred: pointer to a credentials structure for which the policy decision is * being made @@ -732,7 +732,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) * list when walking it. Reads are many orders of magnitude more numerous * than writes so ima_match_policy() is classical RCU candidate. */ -int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode, +int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, u32 secid, enum ima_hooks func, int mask, int flags, int *pcr, struct ima_template_desc **template_desc, @@ -752,7 +752,7 @@ int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode, if (!(entry->action & actmask)) continue; - if (!ima_match_rules(entry, mnt_userns, inode, cred, secid, + if (!ima_match_rules(entry, idmap, inode, cred, secid, func, mask, func_data)) continue; diff --git a/security/integrity/ima/ima_queue_keys.c b/security/integrity/ima/ima_queue_keys.c index 93056c03bf5a..4f0aea155bf9 100644 --- a/security/integrity/ima/ima_queue_keys.c +++ b/security/integrity/ima/ima_queue_keys.c @@ -159,7 +159,7 @@ void ima_process_queued_keys(void) list_for_each_entry_safe(entry, tmp, &ima_keys, list) { if (!timer_expired) - process_buffer_measurement(&init_user_ns, NULL, + process_buffer_measurement(&nop_mnt_idmap, NULL, entry->payload, entry->payload_len, entry->keyring_name, diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 4564faae7d67..6cd0add524cd 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -598,7 +598,7 @@ int ima_eventevmsig_init(struct ima_event_data *event_data, if (!event_data->file) return 0; - rc = vfs_getxattr_alloc(&init_user_ns, file_dentry(event_data->file), + rc = vfs_getxattr_alloc(&nop_mnt_idmap, file_dentry(event_data->file), XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0 || xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) { diff --git a/security/keys/key.c b/security/keys/key.c index c45afdd1dfbb..5c0c7df833f8 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -788,38 +788,18 @@ error: goto out; } -/** - * key_create_or_update - Update or create and instantiate a key. - * @keyring_ref: A pointer to the destination keyring with possession flag. - * @type: The type of key. - * @description: The searchable description for the key. - * @payload: The data to use to instantiate or update the key. - * @plen: The length of @payload. - * @perm: The permissions mask for a new key. - * @flags: The quota flags for a new key. - * - * Search the destination keyring for a key of the same description and if one - * is found, update it, otherwise create and instantiate a new one and create a - * link to it from that keyring. - * - * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be - * concocted. - * - * Returns a pointer to the new key if successful, -ENODEV if the key type - * wasn't available, -ENOTDIR if the keyring wasn't a keyring, -EACCES if the - * caller isn't permitted to modify the keyring or the LSM did not permit - * creation of the key. - * - * On success, the possession flag from the keyring ref will be tacked on to - * the key ref before it is returned. +/* + * Create or potentially update a key. The combined logic behind + * key_create_or_update() and key_create() */ -key_ref_t key_create_or_update(key_ref_t keyring_ref, - const char *type, - const char *description, - const void *payload, - size_t plen, - key_perm_t perm, - unsigned long flags) +static key_ref_t __key_create_or_update(key_ref_t keyring_ref, + const char *type, + const char *description, + const void *payload, + size_t plen, + key_perm_t perm, + unsigned long flags, + bool allow_update) { struct keyring_index_key index_key = { .description = description, @@ -906,14 +886,23 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref, goto error_link_end; } - /* if it's possible to update this type of key, search for an existing - * key of the same type and description in the destination keyring and - * update that instead if possible + /* if it's requested and possible to update this type of key, search + * for an existing key of the same type and description in the + * destination keyring and update that instead if possible */ - if (index_key.type->update) { + if (allow_update) { + if (index_key.type->update) { + key_ref = find_key_to_update(keyring_ref, &index_key); + if (key_ref) + goto found_matching_key; + } + } else { key_ref = find_key_to_update(keyring_ref, &index_key); - if (key_ref) - goto found_matching_key; + if (key_ref) { + key_ref_put(key_ref); + key_ref = ERR_PTR(-EEXIST); + goto error_link_end; + } } /* if the client doesn't provide, decide on the permissions we want */ @@ -985,9 +974,83 @@ error: goto error_free_prep; } + +/** + * key_create_or_update - Update or create and instantiate a key. + * @keyring_ref: A pointer to the destination keyring with possession flag. + * @type: The type of key. + * @description: The searchable description for the key. + * @payload: The data to use to instantiate or update the key. + * @plen: The length of @payload. + * @perm: The permissions mask for a new key. + * @flags: The quota flags for a new key. + * + * Search the destination keyring for a key of the same description and if one + * is found, update it, otherwise create and instantiate a new one and create a + * link to it from that keyring. + * + * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be + * concocted. + * + * Returns a pointer to the new key if successful, -ENODEV if the key type + * wasn't available, -ENOTDIR if the keyring wasn't a keyring, -EACCES if the + * caller isn't permitted to modify the keyring or the LSM did not permit + * creation of the key. + * + * On success, the possession flag from the keyring ref will be tacked on to + * the key ref before it is returned. + */ +key_ref_t key_create_or_update(key_ref_t keyring_ref, + const char *type, + const char *description, + const void *payload, + size_t plen, + key_perm_t perm, + unsigned long flags) +{ + return __key_create_or_update(keyring_ref, type, description, payload, + plen, perm, flags, true); +} EXPORT_SYMBOL(key_create_or_update); /** + * key_create - Create and instantiate a key. + * @keyring_ref: A pointer to the destination keyring with possession flag. + * @type: The type of key. + * @description: The searchable description for the key. + * @payload: The data to use to instantiate or update the key. + * @plen: The length of @payload. + * @perm: The permissions mask for a new key. + * @flags: The quota flags for a new key. + * + * Create and instantiate a new key and link to it from the destination keyring. + * + * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be + * concocted. + * + * Returns a pointer to the new key if successful, -EEXIST if a key with the + * same description already exists, -ENODEV if the key type wasn't available, + * -ENOTDIR if the keyring wasn't a keyring, -EACCES if the caller isn't + * permitted to modify the keyring or the LSM did not permit creation of the + * key. + * + * On success, the possession flag from the keyring ref will be tacked on to + * the key ref before it is returned. + */ +key_ref_t key_create(key_ref_t keyring_ref, + const char *type, + const char *description, + const void *payload, + size_t plen, + key_perm_t perm, + unsigned long flags) +{ + return __key_create_or_update(keyring_ref, type, description, payload, + plen, perm, flags, false); +} +EXPORT_SYMBOL(key_create); + +/** * key_update - Update a key's contents. * @key_ref: The pointer (plus possession flag) to the key. * @payload: The data to be used to update the key. diff --git a/security/security.c b/security/security.c index d1571900a8c7..4e1150c44ab7 100644 --- a/security/security.c +++ b/security/security.c @@ -1354,7 +1354,7 @@ int security_inode_permission(struct inode *inode, int mask) return call_int_hook(inode_permission, 0, inode, mask); } -int security_inode_setattr(struct user_namespace *mnt_userns, +int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int ret; @@ -1364,7 +1364,7 @@ int security_inode_setattr(struct user_namespace *mnt_userns, ret = call_int_hook(inode_setattr, 0, dentry, attr); if (ret) return ret; - return evm_inode_setattr(mnt_userns, dentry, attr); + return evm_inode_setattr(idmap, dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); @@ -1375,7 +1375,7 @@ int security_inode_getattr(const struct path *path) return call_int_hook(inode_getattr, 0, path); } -int security_inode_setxattr(struct user_namespace *mnt_userns, +int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { @@ -1387,7 +1387,7 @@ int security_inode_setxattr(struct user_namespace *mnt_userns, * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ - ret = call_int_hook(inode_setxattr, 1, mnt_userns, dentry, name, value, + ret = call_int_hook(inode_setxattr, 1, idmap, dentry, name, value, size, flags); if (ret == 1) @@ -1397,10 +1397,10 @@ int security_inode_setxattr(struct user_namespace *mnt_userns, ret = ima_inode_setxattr(dentry, name, value, size); if (ret) return ret; - return evm_inode_setxattr(mnt_userns, dentry, name, value, size); + return evm_inode_setxattr(idmap, dentry, name, value, size); } -int security_inode_set_acl(struct user_namespace *mnt_userns, +int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { @@ -1408,38 +1408,38 @@ int security_inode_set_acl(struct user_namespace *mnt_userns, if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - ret = call_int_hook(inode_set_acl, 0, mnt_userns, dentry, acl_name, + ret = call_int_hook(inode_set_acl, 0, idmap, dentry, acl_name, kacl); if (ret) return ret; - ret = ima_inode_set_acl(mnt_userns, dentry, acl_name, kacl); + ret = ima_inode_set_acl(idmap, dentry, acl_name, kacl); if (ret) return ret; - return evm_inode_set_acl(mnt_userns, dentry, acl_name, kacl); + return evm_inode_set_acl(idmap, dentry, acl_name, kacl); } -int security_inode_get_acl(struct user_namespace *mnt_userns, +int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - return call_int_hook(inode_get_acl, 0, mnt_userns, dentry, acl_name); + return call_int_hook(inode_get_acl, 0, idmap, dentry, acl_name); } -int security_inode_remove_acl(struct user_namespace *mnt_userns, +int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - ret = call_int_hook(inode_remove_acl, 0, mnt_userns, dentry, acl_name); + ret = call_int_hook(inode_remove_acl, 0, idmap, dentry, acl_name); if (ret) return ret; - ret = ima_inode_remove_acl(mnt_userns, dentry, acl_name); + ret = ima_inode_remove_acl(idmap, dentry, acl_name); if (ret) return ret; - return evm_inode_remove_acl(mnt_userns, dentry, acl_name); + return evm_inode_remove_acl(idmap, dentry, acl_name); } void security_inode_post_setxattr(struct dentry *dentry, const char *name, @@ -1465,7 +1465,7 @@ int security_inode_listxattr(struct dentry *dentry) return call_int_hook(inode_listxattr, 0, dentry); } -int security_inode_removexattr(struct user_namespace *mnt_userns, +int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { int ret; @@ -1476,15 +1476,15 @@ int security_inode_removexattr(struct user_namespace *mnt_userns, * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ - ret = call_int_hook(inode_removexattr, 1, mnt_userns, dentry, name); + ret = call_int_hook(inode_removexattr, 1, idmap, dentry, name); if (ret == 1) - ret = cap_inode_removexattr(mnt_userns, dentry, name); + ret = cap_inode_removexattr(idmap, dentry, name); if (ret) return ret; ret = ima_inode_removexattr(dentry, name); if (ret) return ret; - return evm_inode_removexattr(mnt_userns, dentry, name); + return evm_inode_removexattr(idmap, dentry, name); } int security_inode_need_killpriv(struct dentry *dentry) @@ -1492,13 +1492,13 @@ int security_inode_need_killpriv(struct dentry *dentry) return call_int_hook(inode_need_killpriv, 0, dentry); } -int security_inode_killpriv(struct user_namespace *mnt_userns, +int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { - return call_int_hook(inode_killpriv, 0, mnt_userns, dentry); + return call_int_hook(inode_killpriv, 0, idmap, dentry); } -int security_inode_getsecurity(struct user_namespace *mnt_userns, +int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { @@ -1511,7 +1511,7 @@ int security_inode_getsecurity(struct user_namespace *mnt_userns, * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) { - rc = hp->hook.inode_getsecurity(mnt_userns, inode, name, buffer, alloc); + rc = hp->hook.inode_getsecurity(idmap, inode, name, buffer, alloc); if (rc != LSM_RET_DEFAULT(inode_getsecurity)) return rc; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 3c5be76a9199..9a5bdfc21314 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3145,7 +3145,7 @@ static bool has_cap_mac_admin(bool audit) return true; } -static int selinux_inode_setxattr(struct user_namespace *mnt_userns, +static int selinux_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { @@ -3167,13 +3167,13 @@ static int selinux_inode_setxattr(struct user_namespace *mnt_userns, } if (!selinux_initialized(&selinux_state)) - return (inode_owner_or_capable(mnt_userns, inode) ? 0 : -EPERM); + return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; @@ -3240,20 +3240,20 @@ static int selinux_inode_setxattr(struct user_namespace *mnt_userns, &ad); } -static int selinux_inode_set_acl(struct user_namespace *mnt_userns, +static int selinux_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } -static int selinux_inode_get_acl(struct user_namespace *mnt_userns, +static int selinux_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__GETATTR); } -static int selinux_inode_remove_acl(struct user_namespace *mnt_userns, +static int selinux_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); @@ -3313,11 +3313,11 @@ static int selinux_inode_listxattr(struct dentry *dentry) return dentry_has_perm(cred, dentry, FILE__GETATTR); } -static int selinux_inode_removexattr(struct user_namespace *mnt_userns, +static int selinux_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { if (strcmp(name, XATTR_NAME_SELINUX)) { - int rc = cap_inode_removexattr(mnt_userns, dentry, name); + int rc = cap_inode_removexattr(idmap, dentry, name); if (rc) return rc; @@ -3383,7 +3383,7 @@ static int selinux_path_notify(const struct path *path, u64 mask, * * Permission check is handled by selinux_inode_getxattr hook. */ -static int selinux_inode_getsecurity(struct user_namespace *mnt_userns, +static int selinux_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { @@ -6588,14 +6588,14 @@ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { - return __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_SELINUX, + return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; - len = selinux_inode_getsecurity(&init_user_ns, inode, + len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 9a82a15685d1..cfcbb748da25 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1207,7 +1207,7 @@ static int smack_inode_getattr(const struct path *path) /** * smack_inode_setxattr - Smack check for setting xattrs - * @mnt_userns: active user namespace + * @idmap: idmap of the mount * @dentry: the object * @name: name of the attribute * @value: value of the attribute @@ -1218,7 +1218,7 @@ static int smack_inode_getattr(const struct path *path) * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_setxattr(struct user_namespace *mnt_userns, +static int smack_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { @@ -1334,7 +1334,7 @@ static int smack_inode_getxattr(struct dentry *dentry, const char *name) /** * smack_inode_removexattr - Smack check on removexattr - * @mnt_userns: active user namespace + * @idmap: idmap of the mount * @dentry: the object * @name: name of the attribute * @@ -1342,7 +1342,7 @@ static int smack_inode_getxattr(struct dentry *dentry, const char *name) * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_removexattr(struct user_namespace *mnt_userns, +static int smack_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode_smack *isp; @@ -1358,7 +1358,7 @@ static int smack_inode_removexattr(struct user_namespace *mnt_userns, if (!smack_privileged(CAP_MAC_ADMIN)) rc = -EPERM; } else - rc = cap_inode_removexattr(mnt_userns, dentry, name); + rc = cap_inode_removexattr(idmap, dentry, name); if (rc != 0) return rc; @@ -1394,14 +1394,14 @@ static int smack_inode_removexattr(struct user_namespace *mnt_userns, /** * smack_inode_set_acl - Smack check for setting posix acls - * @mnt_userns: the userns attached to the mnt this request came from + * @idmap: idmap of the mnt this request came from * @dentry: the object * @acl_name: name of the posix acl * @kacl: the posix acls * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_set_acl(struct user_namespace *mnt_userns, +static int smack_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { @@ -1418,13 +1418,13 @@ static int smack_inode_set_acl(struct user_namespace *mnt_userns, /** * smack_inode_get_acl - Smack check for getting posix acls - * @mnt_userns: the userns attached to the mnt this request came from + * @idmap: idmap of the mnt this request came from * @dentry: the object * @acl_name: name of the posix acl * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_get_acl(struct user_namespace *mnt_userns, +static int smack_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct smk_audit_info ad; @@ -1440,13 +1440,13 @@ static int smack_inode_get_acl(struct user_namespace *mnt_userns, /** * smack_inode_remove_acl - Smack check for getting posix acls - * @mnt_userns: the userns attached to the mnt this request came from + * @idmap: idmap of the mnt this request came from * @dentry: the object * @acl_name: name of the posix acl * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_remove_acl(struct user_namespace *mnt_userns, +static int smack_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct smk_audit_info ad; @@ -1462,7 +1462,7 @@ static int smack_inode_remove_acl(struct user_namespace *mnt_userns, /** * smack_inode_getsecurity - get smack xattrs - * @mnt_userns: active user namespace + * @idmap: idmap of the mount * @inode: the object * @name: attribute name * @buffer: where to put the result @@ -1470,7 +1470,7 @@ static int smack_inode_remove_acl(struct user_namespace *mnt_userns, * * Returns the size of the attribute or an error code */ -static int smack_inode_getsecurity(struct user_namespace *mnt_userns, +static int smack_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { @@ -3507,7 +3507,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) */ if (isp->smk_flags & SMK_INODE_CHANGED) { isp->smk_flags &= ~SMK_INODE_CHANGED; - rc = __vfs_setxattr(&init_user_ns, dp, inode, + rc = __vfs_setxattr(&nop_mnt_idmap, dp, inode, XATTR_NAME_SMACKTRANSMUTE, TRANS_TRUE, TRANS_TRUE_SIZE, 0); @@ -4686,7 +4686,7 @@ static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { - return __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_SMACK, + return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SMACK, ctx, ctxlen, 0); } diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index ac1cc7c5290e..2e728aad6771 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -927,7 +927,6 @@ snd_hda_codec_device_init(struct hda_bus *bus, unsigned int codec_addr, codec->depop_delay = -1; codec->fixup_id = HDA_FIXUP_ID_NOT_SET; codec->core.dev.release = snd_hda_codec_dev_release; - codec->core.exec_verb = codec_exec_verb; codec->core.type = HDA_DEV_LEGACY; mutex_init(&codec->spdif_mutex); @@ -998,6 +997,7 @@ int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card, if (snd_BUG_ON(codec_addr > HDA_MAX_CODEC_ADDRESS)) return -EINVAL; + codec->core.exec_verb = codec_exec_verb; codec->card = card; codec->addr = codec_addr; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 7b1a30a551f6..75e1d00074b9 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1125,6 +1125,7 @@ static const struct hda_device_id snd_hda_id_conexant[] = { HDA_CODEC_ENTRY(0x14f11f87, "SN6140", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto), + HDA_CODEC_ENTRY(0x14f120d1, "SN6180", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1134a493d225..e103bb3693c0 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -832,7 +832,7 @@ do_sku: alc_setup_gpio(codec, 0x02); break; case 7: - alc_setup_gpio(codec, 0x03); + alc_setup_gpio(codec, 0x04); break; case 5: default: @@ -9432,10 +9432,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8b, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8d, "HP", ALC236_FIXUP_HP_GPIO_LED), diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index 1c3d4887aa30..a642c3067ec5 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -216,6 +216,10 @@ static int hda_link_dma_hw_params(struct snd_pcm_substream *substream, sdev = snd_soc_component_get_drvdata(cpu_dai->component); bus = sof_to_bus(sdev); + hlink = snd_hdac_ext_bus_get_hlink_by_name(bus, codec_dai->component->name); + if (!hlink) + return -EINVAL; + hext_stream = snd_soc_dai_get_dma_data(cpu_dai, substream); if (!hext_stream) { hext_stream = hda_link_stream_assign(bus, substream); @@ -225,10 +229,6 @@ static int hda_link_dma_hw_params(struct snd_pcm_substream *substream, snd_soc_dai_set_dma_data(cpu_dai, substream, (void *)hext_stream); } - hlink = snd_hdac_ext_bus_get_hlink_by_name(bus, codec_dai->component->name); - if (!hlink) - return -EINVAL; - /* set the hdac_stream in the codec dai */ snd_soc_dai_set_stream(codec_dai, hdac_stream(hext_stream), substream->stream); diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h index c52752250565..3b3f3cf7af38 100644 --- a/sound/soc/sof/ops.h +++ b/sound/soc/sof/ops.h @@ -357,7 +357,7 @@ static inline u64 snd_sof_dsp_read64(struct snd_sof_dev *sdev, u32 bar, } static inline void snd_sof_dsp_update8(struct snd_sof_dev *sdev, u32 bar, - u32 offset, u8 value, u8 mask) + u32 offset, u8 mask, u8 value) { u8 reg; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 92331053dba3..7bd76b9e0f98 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -826,7 +826,7 @@ out: SEC("kprobe/vfs_link") int BPF_KPROBE(kprobe__vfs_link, - struct dentry* old_dentry, struct user_namespace *mnt_userns, + struct dentry* old_dentry, struct mnt_idmap *idmap, struct inode* dir, struct dentry* new_dentry, struct inode** delegated_inode) { diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index c245476fa29d..63c3eaec8d30 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -10,8 +10,10 @@ ret=0 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} IP="ip -netns testns" +IP_PEER="ip -netns peerns" RTABLE=100 +RTABLE_PEER=101 GW_IP4=192.51.100.2 SRC_IP=192.51.100.3 GW_IP6=2001:db8:1::2 @@ -20,7 +22,9 @@ SRC_IP6=2001:db8:1::3 DEV_ADDR=192.51.100.1 DEV_ADDR6=2001:db8:1::1 DEV=dummy0 -TESTS="fib_rule6 fib_rule4" +TESTS="fib_rule6 fib_rule4 fib_rule6_connect fib_rule4_connect" + +SELFTEST_PATH="" log_test() { @@ -52,6 +56,31 @@ log_section() echo "######################################################################" } +check_nettest() +{ + if which nettest > /dev/null 2>&1; then + return 0 + fi + + # Add the selftest directory to PATH if not already done + if [ "${SELFTEST_PATH}" = "" ]; then + SELFTEST_PATH="$(dirname $0)" + PATH="${PATH}:${SELFTEST_PATH}" + + # Now retry with the new path + if which nettest > /dev/null 2>&1; then + return 0 + fi + + if [ "${ret}" -eq 0 ]; then + ret="${ksft_skip}" + fi + echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')" + fi + + return 1 +} + setup() { set -e @@ -72,6 +101,39 @@ cleanup() ip netns del testns } +setup_peer() +{ + set -e + + ip netns add peerns + $IP_PEER link set dev lo up + + ip link add name veth0 netns testns type veth \ + peer name veth1 netns peerns + $IP link set dev veth0 up + $IP_PEER link set dev veth1 up + + $IP address add 192.0.2.10 peer 192.0.2.11/32 dev veth0 + $IP_PEER address add 192.0.2.11 peer 192.0.2.10/32 dev veth1 + + $IP address add 2001:db8::10 peer 2001:db8::11/128 dev veth0 nodad + $IP_PEER address add 2001:db8::11 peer 2001:db8::10/128 dev veth1 nodad + + $IP_PEER address add 198.51.100.11/32 dev lo + $IP route add table $RTABLE_PEER 198.51.100.11/32 via 192.0.2.11 + + $IP_PEER address add 2001:db8::1:11/128 dev lo + $IP route add table $RTABLE_PEER 2001:db8::1:11/128 via 2001:db8::11 + + set +e +} + +cleanup_peer() +{ + $IP link del dev veth0 + ip netns del peerns +} + fib_check_iproute_support() { ip rule help 2>&1 | grep -q $1 @@ -190,6 +252,37 @@ fib_rule6_test() fi } +# Verify that the IPV6_TCLASS option of UDPv6 and TCPv6 sockets is properly +# taken into account when connecting the socket and when sending packets. +fib_rule6_connect_test() +{ + local dsfield + + if ! check_nettest; then + echo "SKIP: Could not run test without nettest tool" + return + fi + + setup_peer + $IP -6 rule add dsfield 0x04 table $RTABLE_PEER + + # Combine the base DS Field value (0x04) with all possible ECN values + # (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3). + # The ECN bits shouldn't influence the result of the test. + for dsfield in 0x04 0x05 0x06 0x07; do + nettest -q -6 -B -t 5 -N testns -O peerns -U -D \ + -Q "${dsfield}" -l 2001:db8::1:11 -r 2001:db8::1:11 + log_test $? 0 "rule6 dsfield udp connect (dsfield ${dsfield})" + + nettest -q -6 -B -t 5 -N testns -O peerns -Q "${dsfield}" \ + -l 2001:db8::1:11 -r 2001:db8::1:11 + log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})" + done + + $IP -6 rule del dsfield 0x04 table $RTABLE_PEER + cleanup_peer +} + fib_rule4_del() { $IP rule del $1 @@ -296,6 +389,37 @@ fib_rule4_test() fi } +# Verify that the IP_TOS option of UDPv4 and TCPv4 sockets is properly taken +# into account when connecting the socket and when sending packets. +fib_rule4_connect_test() +{ + local dsfield + + if ! check_nettest; then + echo "SKIP: Could not run test without nettest tool" + return + fi + + setup_peer + $IP -4 rule add dsfield 0x04 table $RTABLE_PEER + + # Combine the base DS Field value (0x04) with all possible ECN values + # (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3). + # The ECN bits shouldn't influence the result of the test. + for dsfield in 0x04 0x05 0x06 0x07; do + nettest -q -B -t 5 -N testns -O peerns -D -U -Q "${dsfield}" \ + -l 198.51.100.11 -r 198.51.100.11 + log_test $? 0 "rule4 dsfield udp connect (dsfield ${dsfield})" + + nettest -q -B -t 5 -N testns -O peerns -Q "${dsfield}" \ + -l 198.51.100.11 -r 198.51.100.11 + log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})" + done + + $IP -4 rule del dsfield 0x04 table $RTABLE_PEER + cleanup_peer +} + run_fibrule_tests() { log_section "IPv4 fib rule" @@ -345,6 +469,8 @@ do case $t in fib_rule6_test|fib_rule6) fib_rule6_test;; fib_rule4_test|fib_rule4) fib_rule4_test;; + fib_rule6_connect_test|fib_rule6_connect) fib_rule6_connect_test;; + fib_rule4_connect_test|fib_rule4_connect) fib_rule4_connect_test;; help) echo "Test names: $TESTS"; exit 0;; diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index 7900fa98eccb..ee9a72982705 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -87,6 +87,7 @@ struct sock_args { int use_setsockopt; int use_freebind; int use_cmsg; + uint8_t dsfield; const char *dev; const char *server_dev; int ifindex; @@ -580,6 +581,36 @@ static int set_reuseaddr(int sd) return rc; } +static int set_dsfield(int sd, int version, int dsfield) +{ + if (!dsfield) + return 0; + + switch (version) { + case AF_INET: + if (setsockopt(sd, SOL_IP, IP_TOS, &dsfield, + sizeof(dsfield)) < 0) { + log_err_errno("setsockopt(IP_TOS)"); + return -1; + } + break; + + case AF_INET6: + if (setsockopt(sd, SOL_IPV6, IPV6_TCLASS, &dsfield, + sizeof(dsfield)) < 0) { + log_err_errno("setsockopt(IPV6_TCLASS)"); + return -1; + } + break; + + default: + log_error("Invalid address family\n"); + return -1; + } + + return 0; +} + static int str_to_uint(const char *str, int min, int max, unsigned int *value) { int number; @@ -1317,6 +1348,9 @@ static int msock_init(struct sock_args *args, int server) (char *)&one, sizeof(one)) < 0) log_err_errno("Setting SO_BROADCAST error"); + if (set_dsfield(sd, AF_INET, args->dsfield) != 0) + goto out_err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto out_err; else if (args->use_setsockopt && @@ -1445,6 +1479,9 @@ static int lsock_init(struct sock_args *args) if (set_reuseport(sd) != 0) goto err; + if (set_dsfield(sd, args->version, args->dsfield) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1658,6 +1695,9 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (set_reuseport(sd) != 0) goto err; + if (set_dsfield(sd, args->version, args->dsfield) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1862,7 +1902,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) return client_status; } -#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf" +#define GETOPT_STR "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf" #define OPT_FORCE_BIND_KEY_IFINDEX 1001 #define OPT_NO_BIND_KEY_IFINDEX 1002 @@ -1893,6 +1933,8 @@ static void print_usage(char *prog) " -D|R datagram (D) / raw (R) socket (default stream)\n" " -l addr local address to bind to in server mode\n" " -c addr local address to bind to in client mode\n" + " -Q dsfield DS Field value of the socket (the IP_TOS or\n" + " IPV6_TCLASS socket option)\n" " -x configure XFRM policy on socket\n" "\n" " -d dev bind socket to given device name\n" @@ -1971,6 +2013,13 @@ int main(int argc, char *argv[]) args.has_local_ip = 1; args.client_local_addr_str = optarg; break; + case 'Q': + if (str_to_uint(optarg, 0, 255, &tmp) != 0) { + fprintf(stderr, "Invalid DS Field\n"); + return 1; + } + args.dsfield = tmp; + break; case 'p': if (str_to_uint(optarg, 1, 65535, &tmp) != 0) { fprintf(stderr, "Invalid port\n"); |