From eafc474e202978ac735c551d5ee1eb8c02e2be54 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 25 Jul 2023 16:45:07 +0200 Subject: shmem: prepare shmem quota infrastructure Add new shmem quota format, its quota_format_ops together with dquot_operations Signed-off-by: Lukas Czerner Signed-off-by: Carlos Maiolino Reviewed-by: Jan Kara Message-Id: <20230725144510.253763-5-cem@kernel.org> Signed-off-by: Christian Brauner --- include/linux/shmem_fs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 9029abd29b1c..7abfaf70b58a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -13,6 +13,10 @@ /* inode in-kernel data */ +#ifdef CONFIG_TMPFS_QUOTA +#define SHMEM_MAXQUOTAS 2 +#endif + struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ @@ -172,4 +176,12 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ +/* + * Used space is stored as unsigned 64-bit value in bytes but + * quota core supports only signed 64-bit values so use that + * as a limit + */ +#define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */ +#define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL + #endif -- cgit v1.2.3 From e09764cff44b5d31c2ca5477444565e3080637d2 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 25 Jul 2023 16:45:08 +0200 Subject: shmem: quota support Now the basic infra-structure is in place, enable quota support for tmpfs. This offers user and group quotas to tmpfs (project quotas will be added later). Also, as other filesystems, the tmpfs quota is not supported within user namespaces yet, so idmapping is not translated. Signed-off-by: Lukas Czerner Signed-off-by: Carlos Maiolino Reviewed-by: Jan Kara Message-Id: <20230725144510.253763-6-cem@kernel.org> Signed-off-by: Christian Brauner --- include/linux/shmem_fs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 7abfaf70b58a..1a568a0f542f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -31,6 +31,9 @@ struct shmem_inode_info { atomic_t stop_eviction; /* hold when working on inode */ struct timespec64 i_crtime; /* file creation time */ unsigned int fsflags; /* flags for FS_IOC_[SG]ETFLAGS */ +#ifdef CONFIG_TMPFS_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif struct inode vfs_inode; }; @@ -184,4 +187,9 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, #define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */ #define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL +#ifdef CONFIG_TMPFS_QUOTA +extern const struct dquot_operations shmem_quota_operations; +extern struct quota_format_type shmem_quota_format; +#endif /* CONFIG_TMPFS_QUOTA */ + #endif -- cgit v1.2.3 From de4c0e7ca8b526a82ff7e5ee5533787bb6d01724 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 25 Jul 2023 16:45:09 +0200 Subject: shmem: Add default quota limit mount options Allow system administrator to set default global quota limits at tmpfs mount time. Signed-off-by: Lukas Czerner Signed-off-by: Carlos Maiolino Reviewed-by: Jan Kara Message-Id: <20230725144510.253763-7-cem@kernel.org> Signed-off-by: Christian Brauner --- include/linux/shmem_fs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 1a568a0f542f..c0058f3bba70 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -42,6 +42,13 @@ struct shmem_inode_info { (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) #define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) +struct shmem_quota_limits { + qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ + qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */ + qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */ + qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */ +}; + struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ @@ -60,6 +67,7 @@ struct shmem_sb_info { spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ unsigned long shrinklist_len; /* Length of shrinklist */ + struct shmem_quota_limits qlimits; /* Default quota limits */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) -- cgit v1.2.3 From 6faddda69f623d38bb097640689901a4b5ff881a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 30 Jun 2023 13:48:49 -0400 Subject: libfs: Add directory operations for stable offsets Create a vector of directory operations in fs/libfs.c that handles directory seeks and readdir via stable offsets instead of the current cursor-based mechanism. For the moment these are unused. Signed-off-by: Chuck Lever Message-Id: <168814732984.530310.11190772066786107220.stgit@manet.1015granger.net> Signed-off-by: Christian Brauner --- include/linux/fs.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6867512907d6..59a4129ce14c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1770,6 +1770,7 @@ struct dir_context { struct iov_iter; struct io_uring_cmd; +struct offset_ctx; struct file_operations { struct module *owner; @@ -1857,6 +1858,7 @@ struct inode_operations { int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); + struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, @@ -2971,6 +2973,22 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); +struct offset_ctx { + struct xarray xa; + u32 next_offset; +}; + +void simple_offset_init(struct offset_ctx *octx); +int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); +void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); +int simple_offset_rename_exchange(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry); +void simple_offset_destroy(struct offset_ctx *octx); + +extern const struct file_operations simple_offset_dir_operations; + extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); -- cgit v1.2.3 From a2e459555c5f9da3e619b7e47a63f98574dc75f1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 30 Jun 2023 13:49:03 -0400 Subject: shmem: stable directory offsets The current cursor-based directory offset mechanism doesn't work when a tmpfs filesystem is exported via NFS. This is because NFS clients do not open directories. Each server-side READDIR operation has to open the directory, read it, then close it. The cursor state for that directory, being associated strictly with the opened struct file, is thus discarded after each NFS READDIR operation. Directory offsets are cached not only by NFS clients, but also by user space libraries on those clients. Essentially there is no way to invalidate those caches when directory offsets have changed on an NFS server after the offset-to-dentry mapping changes. Thus the whole application stack depends on unchanging directory offsets. The solution we've come up with is to make the directory offset for each file in a tmpfs filesystem stable for the life of the directory entry it represents. shmem_readdir() and shmem_dir_llseek() now use an xarray to map each directory offset (an loff_t integer) to the memory address of a struct dentry. Signed-off-by: Chuck Lever Message-Id: <168814734331.530310.3911190551060453102.stgit@manet.1015granger.net> Signed-off-by: Christian Brauner --- include/linux/shmem_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index c0058f3bba70..9b2d2faff1d0 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -34,6 +34,7 @@ struct shmem_inode_info { #ifdef CONFIG_TMPFS_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif + struct offset_ctx dir_offsets; /* stable entry offsets */ struct inode vfs_inode; }; -- cgit v1.2.3 From 5de75970c9fd7220e394b76e6d20fbafa1369b5a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 8 Aug 2023 21:30:59 -0700 Subject: xattr: simple_xattr_set() return old_xattr to be freed tmpfs wants to support limited user extended attributes, but kernfs (or cgroupfs, the only kernfs with KERNFS_ROOT_SUPPORT_USER_XATTR) already supports user extended attributes through simple xattrs: but limited by a policy (128KiB per inode) too liberal to be used on tmpfs. To allow a different limiting policy for tmpfs, without affecting the policy for kernfs, change simple_xattr_set() to return the replaced or removed xattr (if any), leaving the caller to update their accounting then free the xattr (by simple_xattr_free(), renamed from the static free_simple_xattr()). Signed-off-by: Hugh Dickins Reviewed-by: Jan Kara Reviewed-by: Christian Brauner Reviewed-by: Carlos Maiolino Message-Id: <158c6585-2aa7-d4aa-90ff-f7c3f8fe407c@google.com> Signed-off-by: Christian Brauner --- include/linux/xattr.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d591ef59aa98..e37fe667ae04 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -116,11 +116,12 @@ struct simple_xattr { void simple_xattrs_init(struct simple_xattrs *xattrs); void simple_xattrs_free(struct simple_xattrs *xattrs); struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); +void simple_xattr_free(struct simple_xattr *xattr); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); -int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags, - ssize_t *removed_size); +struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs, + const char *name, const void *value, + size_t size, int flags); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_add(struct simple_xattrs *xattrs, -- cgit v1.2.3 From e07c469e979c104464300aaa3b7923f929055cd0 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 8 Aug 2023 21:32:21 -0700 Subject: tmpfs: track free_ispace instead of free_inodes In preparation for assigning some inode space to extended attributes, keep track of free_ispace instead of number of free_inodes: as if one tmpfs inode (and accompanying dentry) occupies very approximately 1KiB. Unsigned long is large enough for free_ispace, on 64-bit and on 32-bit: but take care to enforce the maximum. And fix the nr_blocks maximum on 32-bit: S64_MAX would be too big for it there, so say LONG_MAX instead. Delete the incorrect limited<->unlimited blocks/inodes comment above shmem_reconfigure(): leave it to the error messages below to describe. Signed-off-by: Hugh Dickins Reviewed-by: Jan Kara Reviewed-by: Carlos Maiolino Message-Id: <4fe1739-d9e7-8dfd-5bce-12e7339711da@google.com> Signed-off-by: Christian Brauner --- include/linux/shmem_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 9b2d2faff1d0..6b0c626620f5 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -54,7 +54,7 @@ struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ - unsigned long free_inodes; /* How many are left for allocation */ + unsigned long free_ispace; /* How much ispace left for allocation */ raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ -- cgit v1.2.3 From 2daf18a7884dc03d5164ab9c7dc3f2ea70638469 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 8 Aug 2023 21:33:56 -0700 Subject: tmpfs,xattr: enable limited user extended attributes Enable "user." extended attributes on tmpfs, limiting them by tracking the space they occupy, and deducting that space from the limited ispace (unless tmpfs mounted with nr_inodes=0 to leave that ispace unlimited). tmpfs inodes and simple xattrs are both unswappable, and have to be in lowmem on a 32-bit highmem kernel: so the ispace limit is appropriate for xattrs, without any need for a further mount option. Add simple_xattr_space() to give approximate but deterministic estimate of the space taken up by each xattr: with simple_xattrs_free() outputting the space freed if required (but kernfs and even some tmpfs usages do not require that, so don't waste time on strlen'ing if not needed). Security and trusted xattrs were already supported: for consistency and simplicity, account them from the same pool; though there's a small risk that a tmpfs with enough space before would now be considered too small. When extended attributes are used, "df -i" does show more IUsed and less IFree than can be explained by the inodes: document that (manpage later). xfstests tests/generic which were not run on tmpfs before but now pass: 020 037 062 070 077 097 103 117 337 377 454 486 523 533 611 618 728 with no new failures. Signed-off-by: Hugh Dickins Reviewed-by: Jan Kara Reviewed-by: Carlos Maiolino Message-Id: <2e63b26e-df46-5baa-c7d6-f9a8dd3282c5@google.com> Signed-off-by: Christian Brauner --- include/linux/xattr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index e37fe667ae04..d20051865800 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -114,7 +114,8 @@ struct simple_xattr { }; void simple_xattrs_init(struct simple_xattrs *xattrs); -void simple_xattrs_free(struct simple_xattrs *xattrs); +void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space); +size_t simple_xattr_space(const char *name, size_t size); struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); void simple_xattr_free(struct simple_xattr *xattr); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, -- cgit v1.2.3