linux-stable/fs/internal.h

266 lines
7.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/* fs/ internal definitions
*
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
struct super_block;
struct file_system_type;
struct iomap;
struct iomap_ops;
CRED: Make execve() take advantage of copy-on-write credentials Make execve() take advantage of copy-on-write credentials, allowing it to set up the credentials in advance, and then commit the whole lot after the point of no return. This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). The credential bits from struct linux_binprm are, for the most part, replaced with a single credentials pointer (bprm->cred). This means that all the creds can be calculated in advance and then applied at the point of no return with no possibility of failure. I would like to replace bprm->cap_effective with: cap_isclear(bprm->cap_effective) but this seems impossible due to special behaviour for processes of pid 1 (they always retain their parent's capability masks where normally they'd be changed - see cap_bprm_set_creds()). The following sequence of events now happens: (a) At the start of do_execve, the current task's cred_exec_mutex is locked to prevent PTRACE_ATTACH from obsoleting the calculation of creds that we make. (a) prepare_exec_creds() is then called to make a copy of the current task's credentials and prepare it. This copy is then assigned to bprm->cred. This renders security_bprm_alloc() and security_bprm_free() unnecessary, and so they've been removed. (b) The determination of unsafe execution is now performed immediately after (a) rather than later on in the code. The result is stored in bprm->unsafe for future reference. (c) prepare_binprm() is called, possibly multiple times. (i) This applies the result of set[ug]id binaries to the new creds attached to bprm->cred. Personality bit clearance is recorded, but now deferred on the basis that the exec procedure may yet fail. (ii) This then calls the new security_bprm_set_creds(). This should calculate the new LSM and capability credentials into *bprm->cred. This folds together security_bprm_set() and parts of security_bprm_apply_creds() (these two have been removed). Anything that might fail must be done at this point. (iii) bprm->cred_prepared is set to 1. bprm->cred_prepared is 0 on the first pass of the security calculations, and 1 on all subsequent passes. This allows SELinux in (ii) to base its calculations only on the initial script and not on the interpreter. (d) flush_old_exec() is called to commit the task to execution. This performs the following steps with regard to credentials: (i) Clear pdeath_signal and set dumpable on certain circumstances that may not be covered by commit_creds(). (ii) Clear any bits in current->personality that were deferred from (c.i). (e) install_exec_creds() [compute_creds() as was] is called to install the new credentials. This performs the following steps with regard to credentials: (i) Calls security_bprm_committing_creds() to apply any security requirements, such as flushing unauthorised files in SELinux, that must be done before the credentials are changed. This is made up of bits of security_bprm_apply_creds() and security_bprm_post_apply_creds(), both of which have been removed. This function is not allowed to fail; anything that might fail must have been done in (c.ii). (ii) Calls commit_creds() to apply the new credentials in a single assignment (more or less). Possibly pdeath_signal and dumpable should be part of struct creds. (iii) Unlocks the task's cred_replace_mutex, thus allowing PTRACE_ATTACH to take place. (iv) Clears The bprm->cred pointer as the credentials it was holding are now immutable. (v) Calls security_bprm_committed_creds() to apply any security alterations that must be done after the creds have been changed. SELinux uses this to flush signals and signal handlers. (f) If an error occurs before (d.i), bprm_free() will call abort_creds() to destroy the proposed new credentials and will then unlock cred_replace_mutex. No changes to the credentials will have been made. (2) LSM interface. A number of functions have been changed, added or removed: (*) security_bprm_alloc(), ->bprm_alloc_security() (*) security_bprm_free(), ->bprm_free_security() Removed in favour of preparing new credentials and modifying those. (*) security_bprm_apply_creds(), ->bprm_apply_creds() (*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds() Removed; split between security_bprm_set_creds(), security_bprm_committing_creds() and security_bprm_committed_creds(). (*) security_bprm_set(), ->bprm_set_security() Removed; folded into security_bprm_set_creds(). (*) security_bprm_set_creds(), ->bprm_set_creds() New. The new credentials in bprm->creds should be checked and set up as appropriate. bprm->cred_prepared is 0 on the first call, 1 on the second and subsequent calls. (*) security_bprm_committing_creds(), ->bprm_committing_creds() (*) security_bprm_committed_creds(), ->bprm_committed_creds() New. Apply the security effects of the new credentials. This includes closing unauthorised files in SELinux. This function may not fail. When the former is called, the creds haven't yet been applied to the process; when the latter is called, they have. The former may access bprm->cred, the latter may not. (3) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) The bprm_security_struct struct has been removed in favour of using the credentials-under-construction approach. (c) flush_unauthorized_files() now takes a cred pointer and passes it on to inode_has_perm(), file_has_perm() and dentry_open(). Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:24 +00:00
struct linux_binprm;
struct path;
struct mount;
list_lru: introduce list_lru_shrink_{count,walk} Kmem accounting of memcg is unusable now, because it lacks slab shrinker support. That means when we hit the limit we will get ENOMEM w/o any chance to recover. What we should do then is to call shrink_slab, which would reclaim old inode/dentry caches from this cgroup. This is what this patch set is intended to do. Basically, it does two things. First, it introduces the notion of per-memcg slab shrinker. A shrinker that wants to reclaim objects per cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be passed the memory cgroup to scan from in shrink_control->memcg. For such shrinkers shrink_slab iterates over the whole cgroup subtree under the target cgroup and calls the shrinker for each kmem-active memory cgroup. Secondly, this patch set makes the list_lru structure per-memcg. It's done transparently to list_lru users - everything they have to do is to tell list_lru_init that they want memcg-aware list_lru. Then the list_lru will automatically distribute objects among per-memcg lists basing on which cgroup the object is accounted to. This way to make FS shrinkers (icache, dcache) memcg-aware we only need to make them use memcg-aware list_lru, and this is what this patch set does. As before, this patch set only enables per-memcg kmem reclaim when the pressure goes from memory.limit, not from memory.kmem.limit. Handling memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and it is still unclear whether we will have this knob in the unified hierarchy. This patch (of 9): NUMA aware slab shrinkers use the list_lru structure to distribute objects coming from different NUMA nodes to different lists. Whenever such a shrinker needs to count or scan objects from a particular node, it issues commands like this: count = list_lru_count_node(lru, sc->nid); freed = list_lru_walk_node(lru, sc->nid, isolate_func, isolate_arg, &sc->nr_to_scan); where sc is an instance of the shrink_control structure passed to it from vmscan. To simplify this, let's add special list_lru functions to be used by shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which consolidate the nid and nr_to_scan arguments in the shrink_control structure. This will also allow us to avoid patching shrinkers that use list_lru when we make shrink_slab() per-memcg - all we will have to do is extend the shrink_control structure to include the target memcg and make list_lru_shrink_{count,walk} handle this appropriately. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Suggested-by: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Glauber Costa <glommer@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 22:58:47 +00:00
struct shrink_control;
struct fs_context;
struct user_namespace;
struct pipe_inode_info;
struct iov_iter;
/*
* block/bdev.c
*/
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#ifdef CONFIG_BLOCK
extern void __init bdev_cache_init(void);
void emergency_thaw_bdev(struct super_block *sb);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#else
static inline void bdev_cache_init(void)
{
}
static inline int emergency_thaw_bdev(struct super_block *sb)
{
return 0;
}
#endif /* CONFIG_BLOCK */
/*
* buffer.c
*/
int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
get_block_t *get_block, const struct iomap *iomap);
/*
* char_dev.c
*/
extern void __init chrdev_init(void);
/*
* fs_context.c
*/
vfs: syscall: Add fsconfig() for configuring and managing a context Add a syscall for configuring a filesystem creation context and triggering actions upon it, to be used in conjunction with fsopen, fspick and fsmount. long fsconfig(int fs_fd, unsigned int cmd, const char *key, const void *value, int aux); Where fs_fd indicates the context, cmd indicates the action to take, key indicates the parameter name for parameter-setting actions and, if needed, value points to a buffer containing the value and aux can give more information for the value. The following command IDs are proposed: (*) FSCONFIG_SET_FLAG: No value is specified. The parameter must be boolean in nature. The key may be prefixed with "no" to invert the setting. value must be NULL and aux must be 0. (*) FSCONFIG_SET_STRING: A string value is specified. The parameter can be expecting boolean, integer, string or take a path. A conversion to an appropriate type will be attempted (which may include looking up as a path). value points to a NUL-terminated string and aux must be 0. (*) FSCONFIG_SET_BINARY: A binary blob is specified. value points to the blob and aux indicates its size. The parameter must be expecting a blob. (*) FSCONFIG_SET_PATH: A non-empty path is specified. The parameter must be expecting a path object. value points to a NUL-terminated string that is the path and aux is a file descriptor at which to start a relative lookup or AT_FDCWD. (*) FSCONFIG_SET_PATH_EMPTY: As fsconfig_set_path, but with AT_EMPTY_PATH implied. (*) FSCONFIG_SET_FD: An open file descriptor is specified. value must be NULL and aux indicates the file descriptor. (*) FSCONFIG_CMD_CREATE: Trigger superblock creation. (*) FSCONFIG_CMD_RECONFIGURE: Trigger superblock reconfiguration. For the "set" command IDs, the idea is that the file_system_type will point to a list of parameters and the types of value that those parameters expect to take. The core code can then do the parse and argument conversion and then give the LSM and FS a cooked option or array of options to use. Source specification is also done the same way same way, using special keys "source", "source1", "source2", etc.. [!] Note that, for the moment, the key and value are just glued back together and handed to the filesystem. Every filesystem that uses options uses match_token() and co. to do this, and this will need to be changed - but not all at once. Example usage: fd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_path, "source", "/dev/sda1", AT_FDCWD); fsconfig(fd, fsconfig_set_path_empty, "journal_path", "", journal_fd); fsconfig(fd, fsconfig_set_fd, "journal_fd", "", journal_fd); fsconfig(fd, fsconfig_set_flag, "user_xattr", NULL, 0); fsconfig(fd, fsconfig_set_flag, "noacl", NULL, 0); fsconfig(fd, fsconfig_set_string, "sb", "1", 0); fsconfig(fd, fsconfig_set_string, "errors", "continue", 0); fsconfig(fd, fsconfig_set_string, "data", "journal", 0); fsconfig(fd, fsconfig_set_string, "context", "unconfined_u:...", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); or: fd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_string, "source", "/dev/sda1", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); or: fd = fsopen("afs", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_string, "source", "#grand.central.org:root.cell", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); or: fd = fsopen("jffs2", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_string, "source", "mtd0", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); Signed-off-by: David Howells <dhowells@redhat.com> cc: linux-api@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:36:09 +00:00
extern const struct fs_context_operations legacy_fs_context_ops;
extern int parse_monolithic_mount_data(struct fs_context *, void *);
vfs: syscall: Add fsconfig() for configuring and managing a context Add a syscall for configuring a filesystem creation context and triggering actions upon it, to be used in conjunction with fsopen, fspick and fsmount. long fsconfig(int fs_fd, unsigned int cmd, const char *key, const void *value, int aux); Where fs_fd indicates the context, cmd indicates the action to take, key indicates the parameter name for parameter-setting actions and, if needed, value points to a buffer containing the value and aux can give more information for the value. The following command IDs are proposed: (*) FSCONFIG_SET_FLAG: No value is specified. The parameter must be boolean in nature. The key may be prefixed with "no" to invert the setting. value must be NULL and aux must be 0. (*) FSCONFIG_SET_STRING: A string value is specified. The parameter can be expecting boolean, integer, string or take a path. A conversion to an appropriate type will be attempted (which may include looking up as a path). value points to a NUL-terminated string and aux must be 0. (*) FSCONFIG_SET_BINARY: A binary blob is specified. value points to the blob and aux indicates its size. The parameter must be expecting a blob. (*) FSCONFIG_SET_PATH: A non-empty path is specified. The parameter must be expecting a path object. value points to a NUL-terminated string that is the path and aux is a file descriptor at which to start a relative lookup or AT_FDCWD. (*) FSCONFIG_SET_PATH_EMPTY: As fsconfig_set_path, but with AT_EMPTY_PATH implied. (*) FSCONFIG_SET_FD: An open file descriptor is specified. value must be NULL and aux indicates the file descriptor. (*) FSCONFIG_CMD_CREATE: Trigger superblock creation. (*) FSCONFIG_CMD_RECONFIGURE: Trigger superblock reconfiguration. For the "set" command IDs, the idea is that the file_system_type will point to a list of parameters and the types of value that those parameters expect to take. The core code can then do the parse and argument conversion and then give the LSM and FS a cooked option or array of options to use. Source specification is also done the same way same way, using special keys "source", "source1", "source2", etc.. [!] Note that, for the moment, the key and value are just glued back together and handed to the filesystem. Every filesystem that uses options uses match_token() and co. to do this, and this will need to be changed - but not all at once. Example usage: fd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_path, "source", "/dev/sda1", AT_FDCWD); fsconfig(fd, fsconfig_set_path_empty, "journal_path", "", journal_fd); fsconfig(fd, fsconfig_set_fd, "journal_fd", "", journal_fd); fsconfig(fd, fsconfig_set_flag, "user_xattr", NULL, 0); fsconfig(fd, fsconfig_set_flag, "noacl", NULL, 0); fsconfig(fd, fsconfig_set_string, "sb", "1", 0); fsconfig(fd, fsconfig_set_string, "errors", "continue", 0); fsconfig(fd, fsconfig_set_string, "data", "journal", 0); fsconfig(fd, fsconfig_set_string, "context", "unconfined_u:...", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); or: fd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_string, "source", "/dev/sda1", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); or: fd = fsopen("afs", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_string, "source", "#grand.central.org:root.cell", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); or: fd = fsopen("jffs2", FSOPEN_CLOEXEC); fsconfig(fd, fsconfig_set_string, "source", "mtd0", 0); fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0); mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC); Signed-off-by: David Howells <dhowells@redhat.com> cc: linux-api@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:36:09 +00:00
extern void vfs_clean_context(struct fs_context *fc);
extern int finish_clean_context(struct fs_context *fc);
/*
* namei.c
*/
vfs: Add configuration parser helpers Because the new API passes in key,value parameters, match_token() cannot be used with it. Instead, provide three new helpers to aid with parsing: (1) fs_parse(). This takes a parameter and a simple static description of all the parameters and maps the key name to an ID. It returns 1 on a match, 0 on no match if unknowns should be ignored and some other negative error code on a parse error. The parameter description includes a list of key names to IDs, desired parameter types and a list of enumeration name -> ID mappings. [!] Note that for the moment I've required that the key->ID mapping array is expected to be sorted and unterminated. The size of the array is noted in the fsconfig_parser struct. This allows me to use bsearch(), but I'm not sure any performance gain is worth the hassle of requiring people to keep the array sorted. The parameter type array is sized according to the number of parameter IDs and is indexed directly. The optional enum mapping array is an unterminated, unsorted list and the size goes into the fsconfig_parser struct. The function can do some additional things: (a) If it's not ambiguous and no value is given, the prefix "no" on a key name is permitted to indicate that the parameter should be considered negatory. (b) If the desired type is a single simple integer, it will perform an appropriate conversion and store the result in a union in the parse result. (c) If the desired type is an enumeration, {key ID, name} will be looked up in the enumeration list and the matching value will be stored in the parse result union. (d) Optionally generate an error if the key is unrecognised. This is called something like: enum rdt_param { Opt_cdp, Opt_cdpl2, Opt_mba_mpbs, nr__rdt_params }; const struct fs_parameter_spec rdt_param_specs[nr__rdt_params] = { [Opt_cdp] = { fs_param_is_bool }, [Opt_cdpl2] = { fs_param_is_bool }, [Opt_mba_mpbs] = { fs_param_is_bool }, }; const const char *const rdt_param_keys[nr__rdt_params] = { [Opt_cdp] = "cdp", [Opt_cdpl2] = "cdpl2", [Opt_mba_mpbs] = "mba_mbps", }; const struct fs_parameter_description rdt_parser = { .name = "rdt", .nr_params = nr__rdt_params, .keys = rdt_param_keys, .specs = rdt_param_specs, .no_source = true, }; int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result parse; struct rdt_fs_context *ctx = rdt_fc2context(fc); int ret; ret = fs_parse(fc, &rdt_parser, param, &parse); if (ret < 0) return ret; switch (parse.key) { case Opt_cdp: ctx->enable_cdpl3 = true; return 0; case Opt_cdpl2: ctx->enable_cdpl2 = true; return 0; case Opt_mba_mpbs: ctx->enable_mba_mbps = true; return 0; } return -EINVAL; } (2) fs_lookup_param(). This takes a { dirfd, path, LOOKUP_EMPTY? } or string value and performs an appropriate path lookup to convert it into a path object, which it will then return. If the desired type was a blockdev, the type of the looked up inode will be checked to make sure it is one. This can be used like: enum foo_param { Opt_source, nr__foo_params }; const struct fs_parameter_spec foo_param_specs[nr__foo_params] = { [Opt_source] = { fs_param_is_blockdev }, }; const char *char foo_param_keys[nr__foo_params] = { [Opt_source] = "source", }; const struct constant_table foo_param_alt_keys[] = { { "device", Opt_source }, }; const struct fs_parameter_description foo_parser = { .name = "foo", .nr_params = nr__foo_params, .nr_alt_keys = ARRAY_SIZE(foo_param_alt_keys), .keys = foo_param_keys, .alt_keys = foo_param_alt_keys, .specs = foo_param_specs, }; int foo_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result parse; struct foo_fs_context *ctx = foo_fc2context(fc); int ret; ret = fs_parse(fc, &foo_parser, param, &parse); if (ret < 0) return ret; switch (parse.key) { case Opt_source: return fs_lookup_param(fc, &foo_parser, param, &parse, &ctx->source); default: return -EINVAL; } } (3) lookup_constant(). This takes a table of named constants and looks up the given name within it. The table is expected to be sorted such that bsearch() be used upon it. Possibly I should require the table be terminated and just use a for-loop to scan it instead of using bsearch() to reduce hassle. Tables look something like: static const struct constant_table bool_names[] = { { "0", false }, { "1", true }, { "false", false }, { "no", false }, { "true", true }, { "yes", true }, }; and a lookup is done with something like: b = lookup_constant(bool_names, param->string, -1); Additionally, optional validation routines for the parameter description are provided that can be enabled at compile time. A later patch will invoke these when a filesystem is registered. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:07:24 +00:00
extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
struct path *path, struct path *root);
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 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);
int do_symlinkat(struct filename *from, int newdfd, struct filename *to);
int do_linkat(int olddfd, struct filename *old, int newdfd,
struct filename *new, int flags);
/*
* namespace.c
*/
extern struct vfsmount *lookup_mnt(const struct path *);
extern int finish_automount(struct vfsmount *, const struct path *);
extern int sb_prepare_remount_readonly(struct super_block *);
extern void __init mnt_init(void);
extern int __mnt_want_write_file(struct file *);
extern void __mnt_drop_write_file(struct file *);
extern void dissolve_on_fput(struct vfsmount *);
extern bool may_mount(void);
int path_mount(const char *dev_name, struct path *path,
const char *type_page, unsigned long flags, void *data_page);
int path_umount(struct path *path, int flags);
/*
* fs_struct.c
*/
extern void chroot_fs_refs(const struct path *, const struct path *);
/*
* file_table.c
*/
extern struct file *alloc_empty_file(int, const struct cred *);
extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
static inline void put_file_access(struct file *file)
{
if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) {
i_readcount_dec(file->f_inode);
} else if (file->f_mode & FMODE_WRITER) {
put_write_access(file->f_inode);
__mnt_drop_write(file->f_path.mnt);
}
}
/*
* super.c
*/
extern int reconfigure_super(struct fs_context *);
extern bool trylock_super(struct super_block *sb);
struct super_block *user_get_super(dev_t, bool excl);
void put_super(struct super_block *sb);
extern bool mount_capable(struct fs_context *);
/*
* open.c
*/
struct open_flags {
int open_flag;
umode_t mode;
int acc_mode;
int intent;
int lookup_flags;
};
extern struct file *do_filp_open(int dfd, struct filename *pathname,
const struct open_flags *op);
extern struct file *do_file_open_root(const struct path *,
const char *, const struct open_flags *);
extern struct open_how build_open_how(int flags, umode_t mode);
extern int build_open_flags(const struct open_how *how, struct open_flags *op);
extern struct file *__close_fd_get_file(unsigned int fd);
long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
int chmod_common(const struct path *path, umode_t mode);
int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
int flag);
int chown_common(const struct path *path, uid_t user, gid_t group);
extern int vfs_open(const struct path *, struct file *);
/*
* inode.c
*/
list_lru: introduce list_lru_shrink_{count,walk} Kmem accounting of memcg is unusable now, because it lacks slab shrinker support. That means when we hit the limit we will get ENOMEM w/o any chance to recover. What we should do then is to call shrink_slab, which would reclaim old inode/dentry caches from this cgroup. This is what this patch set is intended to do. Basically, it does two things. First, it introduces the notion of per-memcg slab shrinker. A shrinker that wants to reclaim objects per cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be passed the memory cgroup to scan from in shrink_control->memcg. For such shrinkers shrink_slab iterates over the whole cgroup subtree under the target cgroup and calls the shrinker for each kmem-active memory cgroup. Secondly, this patch set makes the list_lru structure per-memcg. It's done transparently to list_lru users - everything they have to do is to tell list_lru_init that they want memcg-aware list_lru. Then the list_lru will automatically distribute objects among per-memcg lists basing on which cgroup the object is accounted to. This way to make FS shrinkers (icache, dcache) memcg-aware we only need to make them use memcg-aware list_lru, and this is what this patch set does. As before, this patch set only enables per-memcg kmem reclaim when the pressure goes from memory.limit, not from memory.kmem.limit. Handling memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and it is still unclear whether we will have this knob in the unified hierarchy. This patch (of 9): NUMA aware slab shrinkers use the list_lru structure to distribute objects coming from different NUMA nodes to different lists. Whenever such a shrinker needs to count or scan objects from a particular node, it issues commands like this: count = list_lru_count_node(lru, sc->nid); freed = list_lru_walk_node(lru, sc->nid, isolate_func, isolate_arg, &sc->nr_to_scan); where sc is an instance of the shrink_control structure passed to it from vmscan. To simplify this, let's add special list_lru functions to be used by shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which consolidate the nid and nr_to_scan arguments in the shrink_control structure. This will also allow us to avoid patching shrinkers that use list_lru when we make shrink_slab() per-memcg - all we will have to do is extend the shrink_control structure to include the target memcg and make list_lru_shrink_{count,walk} handle this appropriately. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Suggested-by: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Glauber Costa <glommer@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 22:58:47 +00:00
extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
attr: use consistent sgid stripping checks Currently setgid stripping in file_remove_privs()'s should_remove_suid() helper is inconsistent with other parts of the vfs. Specifically, it only raises ATTR_KILL_SGID if the inode is S_ISGID and S_IXGRP but not if the inode isn't in the caller's groups and the caller isn't privileged over the inode although we require this already in setattr_prepare() and setattr_copy() and so all filesystem implement this requirement implicitly because they have to use setattr_{prepare,copy}() anyway. But the inconsistency shows up in setgid stripping bugs for overlayfs in xfstests (e.g., generic/673, generic/683, generic/685, generic/686, generic/687). For example, we test whether suid and setgid stripping works correctly when performing various write-like operations as an unprivileged user (fallocate, reflink, write, etc.): echo "Test 1 - qa_user, non-exec file $verb" setup_testfile chmod a+rws $junk_file commit_and_check "$qa_user" "$verb" 64k 64k The test basically creates a file with 6666 permissions. While the file has the S_ISUID and S_ISGID bits set it does not have the S_IXGRP set. On a regular filesystem like xfs what will happen is: sys_fallocate() -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> setattr_copy() In should_remove_suid() we can see that ATTR_KILL_SUID is raised unconditionally because the file in the test has S_ISUID set. But we also see that ATTR_KILL_SGID won't be set because while the file is S_ISGID it is not S_IXGRP (see above) which is a condition for ATTR_KILL_SGID being raised. So by the time we call notify_change() we have attr->ia_valid set to ATTR_KILL_SUID | ATTR_FORCE. Now notify_change() sees that ATTR_KILL_SUID is set and does: ia_valid = attr->ia_valid |= ATTR_MODE attr->ia_mode = (inode->i_mode & ~S_ISUID); which means that when we call setattr_copy() later we will definitely update inode->i_mode. Note that attr->ia_mode still contains S_ISGID. Now we call into the filesystem's ->setattr() inode operation which will end up calling setattr_copy(). Since ATTR_MODE is set we will hit: if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); if (!vfsgid_in_group_p(vfsgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } and since the caller in the test is neither capable nor in the group of the inode the S_ISGID bit is stripped. But assume the file isn't suid then ATTR_KILL_SUID won't be raised which has the consequence that neither the setgid nor the suid bits are stripped even though it should be stripped because the inode isn't in the caller's groups and the caller isn't privileged over the inode. If overlayfs is in the mix things become a bit more complicated and the bug shows up more clearly. When e.g., ovl_setattr() is hit from ovl_fallocate()'s call to file_remove_privs() then ATTR_KILL_SUID and ATTR_KILL_SGID might be raised but because the check in notify_change() is questioning the ATTR_KILL_SGID flag again by requiring S_IXGRP for it to be stripped the S_ISGID bit isn't removed even though it should be stripped: sys_fallocate() -> vfs_fallocate() -> ovl_fallocate() -> file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> ovl_setattr() // TAKE ON MOUNTER'S CREDS -> ovl_do_notify_change() -> notify_change() // GIVE UP MOUNTER'S CREDS // TAKE ON MOUNTER'S CREDS -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = attr_force | kill; -> notify_change() The fix for all of this is to make file_remove_privs()'s should_remove_suid() helper to perform the same checks as we already require in setattr_prepare() and setattr_copy() and have notify_change() not pointlessly requiring S_IXGRP again. It doesn't make any sense in the first place because the caller must calculate the flags via should_remove_suid() anyway which would raise ATTR_KILL_SGID. While we're at it we move should_remove_suid() from inode.c to attr.c where it belongs with the rest of the iattr helpers. Especially since it returns ATTR_KILL_S{G,U}ID flags. We also rename it to setattr_should_drop_suidgid() to better reflect that it indicates both setuid and setgid bit removal and also that it returns attr flags. Running xfstests with this doesn't report any regressions. We should really try and use consistent checks. Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-10-17 15:06:37 +00:00
int dentry_needs_remove_privs(struct user_namespace *, struct dentry *dentry);
bool in_group_or_capable(struct user_namespace *mnt_userns,
const struct inode *inode, vfsgid_t vfsgid);
/*
* fs-writeback.c
*/
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Chinner <dchinner@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 00:17:53 +00:00
extern long get_nr_dirty_inodes(void);
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 06:25:47 +00:00
extern int invalidate_inodes(struct super_block *, bool);
/*
* dcache.c
*/
extern int d_set_mounted(struct dentry *dentry);
list_lru: introduce list_lru_shrink_{count,walk} Kmem accounting of memcg is unusable now, because it lacks slab shrinker support. That means when we hit the limit we will get ENOMEM w/o any chance to recover. What we should do then is to call shrink_slab, which would reclaim old inode/dentry caches from this cgroup. This is what this patch set is intended to do. Basically, it does two things. First, it introduces the notion of per-memcg slab shrinker. A shrinker that wants to reclaim objects per cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be passed the memory cgroup to scan from in shrink_control->memcg. For such shrinkers shrink_slab iterates over the whole cgroup subtree under the target cgroup and calls the shrinker for each kmem-active memory cgroup. Secondly, this patch set makes the list_lru structure per-memcg. It's done transparently to list_lru users - everything they have to do is to tell list_lru_init that they want memcg-aware list_lru. Then the list_lru will automatically distribute objects among per-memcg lists basing on which cgroup the object is accounted to. This way to make FS shrinkers (icache, dcache) memcg-aware we only need to make them use memcg-aware list_lru, and this is what this patch set does. As before, this patch set only enables per-memcg kmem reclaim when the pressure goes from memory.limit, not from memory.kmem.limit. Handling memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and it is still unclear whether we will have this knob in the unified hierarchy. This patch (of 9): NUMA aware slab shrinkers use the list_lru structure to distribute objects coming from different NUMA nodes to different lists. Whenever such a shrinker needs to count or scan objects from a particular node, it issues commands like this: count = list_lru_count_node(lru, sc->nid); freed = list_lru_walk_node(lru, sc->nid, isolate_func, isolate_arg, &sc->nr_to_scan); where sc is an instance of the shrink_control structure passed to it from vmscan. To simplify this, let's add special list_lru functions to be used by shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which consolidate the nid and nr_to_scan arguments in the shrink_control structure. This will also allow us to avoid patching shrinkers that use list_lru when we make shrink_slab() per-memcg - all we will have to do is extend the shrink_control structure to include the target memcg and make list_lru_shrink_{count,walk} handle this appropriately. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Suggested-by: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Glauber Costa <glommer@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 22:58:47 +00:00
extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
extern struct dentry *d_alloc_cursor(struct dentry *);
extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *);
extern char *simple_dname(struct dentry *, char *, int);
Teach shrink_dcache_parent() to cope with mixed-filesystem shrink lists Currently, running into a shrink list that contains dentries from different filesystems can cause several unpleasant things for shrink_dcache_parent() and for umount(2). The first problem is that there's a window during shrink_dentry_list() between __dentry_kill() takes a victim out and dropping reference to its parent. During that window the parent looks like a genuine busy dentry. shrink_dcache_parent() (or, worse yet, shrink_dcache_for_umount()) coming at that time will see no eviction candidates and no indication that it needs to wait for some shrink_dentry_list() to proceed further. That applies for any shrink list that might intersect with the subtree we are trying to shrink; the only reason it does not blow on umount(2) in the mainline is that we unregister the memory shrinker before hitting shrink_dcache_for_umount(). Another problem happens if something in a mixed-filesystem shrink list gets be stuck in e.g. iput(), getting umount of unrelated fs to spin waiting for the stuck shrinker to get around to our dentries. Solution: 1) have shrink_dentry_list() decrement the parent's refcount and make sure it's on a shrink list (ours unless it already had been on some other) before calling __dentry_kill(). That eliminates the window when shrink_dcache_parent() would've blown past the entire subtree without noticing anything with zero refcount not on shrink lists. 2) when shrink_dcache_parent() has found no eviction candidates, but some dentries are still sitting on shrink lists, rather than repeating the scan in hope that shrinkers have progressed, scan looking for something on shrink lists with zero refcount. If such a thing is found, grab rcu_read_lock() and stop the scan, with caller locking it for eviction, dropping out of RCU and doing __dentry_kill(), with the same treatment for parent as shrink_dentry_list() would do. Note that right now mixed-filesystem shrink lists do not occur, so this is not a mainline bug. Howevere, there's a bunch of uses for such beasts (e.g. the "try and evict everything we can out of given page" patches; there are potential uses in mount-related code, considerably simplifying the life in fs/namespace.c, etc.) Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-06-29 22:31:24 +00:00
extern void dput_to_list(struct dentry *, struct list_head *);
extern void shrink_dentry_list(struct list_head *);
/*
* pipe.c
*/
extern const struct file_operations pipefifo_fops;
/*
* fs_pin.c
*/
extern void group_pin_kill(struct hlist_head *p);
extern void mnt_pin_kill(struct mount *m);
/*
* fs/nsfs.c
*/
extern const struct dentry_operations ns_dentry_operations;
/* direct-io.c: */
int sb_init_dio_done_wq(struct super_block *sb);
/*
* fs/stat.c:
*/
int getname_statx_lookup_flags(int flags);
int do_statx(int dfd, struct filename *filename, unsigned int flags,
unsigned int mask, struct statx __user *buffer);
/*
* fs/splice.c:
*/
long splice_file_to_pipe(struct file *in,
struct pipe_inode_info *opipe,
loff_t *offset,
size_t len, unsigned int flags);
/*
* fs/xattr.c:
*/
struct xattr_name {
char name[XATTR_NAME_MAX + 1];
};
struct xattr_ctx {
/* Value of attribute */
union {
const void __user *cvalue;
void __user *value;
};
void *kvalue;
size_t size;
/* Attribute name */
struct xattr_name *kname;
unsigned int flags;
};
ssize_t do_getxattr(struct mnt_idmap *idmap,
struct dentry *d,
struct xattr_ctx *ctx);
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);
#ifdef CONFIG_FS_POSIX_ACL
int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
const char *acl_name, const void *kvalue, size_t size);
ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry,
const char *acl_name, void *kvalue, size_t size);
#else
static inline int do_set_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name,
const void *kvalue, size_t size)
{
return -EOPNOTSUPP;
}
static inline ssize_t do_get_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name,
void *kvalue, size_t size)
{
return -EOPNOTSUPP;
}
#endif
ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos);
/*
* fs/attr.c
*/
int setattr_should_drop_sgid(struct user_namespace *mnt_userns,
const struct inode *inode);