* [PATCH 1/6] shmem: make shmem_inode_acct_block() return error
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
@ 2023-04-26 10:20 ` cem
2023-04-26 10:20 ` [PATCH 2/6] shmem: make shmem_get_inode() return ERR_PTR instead of NULL cem
` (5 subsequent siblings)
6 siblings, 0 replies; 19+ messages in thread
From: cem @ 2023-04-26 10:20 UTC (permalink / raw)
To: hughd; +Cc: jack, linux-mm, linux-fsdevel, djwong
From: Lukas Czerner <lczerner@redhat.com>
Make shmem_inode_acct_block() return proper error code instead of bool.
This will be useful later when we introduce quota support.
There should be no functional change.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
mm/shmem.c | 18 ++++++++++--------
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 448f393d8ab2b..b1b3b826f6189 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -198,13 +198,14 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
}
-static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
+static inline int shmem_inode_acct_block(struct inode *inode, long pages)
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+ int err = -ENOSPC;
if (shmem_acct_block(info->flags, pages))
- return false;
+ return err;
if (sbinfo->max_blocks) {
if (percpu_counter_compare(&sbinfo->used_blocks,
@@ -213,11 +214,11 @@ static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
percpu_counter_add(&sbinfo->used_blocks, pages);
}
- return true;
+ return 0;
unacct:
shmem_unacct_blocks(info->flags, pages);
- return false;
+ return err;
}
static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
@@ -369,7 +370,7 @@ bool shmem_charge(struct inode *inode, long pages)
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long flags;
- if (!shmem_inode_acct_block(inode, pages))
+ if (shmem_inode_acct_block(inode, pages))
return false;
/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
@@ -1583,13 +1584,14 @@ static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode,
struct shmem_inode_info *info = SHMEM_I(inode);
struct folio *folio;
int nr;
- int err = -ENOSPC;
+ int err;
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
huge = false;
nr = huge ? HPAGE_PMD_NR : 1;
- if (!shmem_inode_acct_block(inode, nr))
+ err = shmem_inode_acct_block(inode, nr);
+ if (err)
goto failed;
if (huge)
@@ -2433,7 +2435,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
int ret;
pgoff_t max_off;
- if (!shmem_inode_acct_block(inode, 1)) {
+ if (shmem_inode_acct_block(inode, 1)) {
/*
* We may have got a page, returned -ENOENT triggering a retry,
* and now we find ourselves with -ENOMEM. Release the page, to
--
2.30.2
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 2/6] shmem: make shmem_get_inode() return ERR_PTR instead of NULL
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
2023-04-26 10:20 ` [PATCH 1/6] shmem: make shmem_inode_acct_block() return error cem
@ 2023-04-26 10:20 ` cem
2023-04-26 10:20 ` [PATCH 3/6] quota: Check presence of quota operation structures instead of ->quota_read and ->quota_write callbacks cem
` (4 subsequent siblings)
6 siblings, 0 replies; 19+ messages in thread
From: cem @ 2023-04-26 10:20 UTC (permalink / raw)
To: hughd; +Cc: jack, linux-mm, linux-fsdevel, djwong
From: Lukas Czerner <lczerner@redhat.com>
Make shmem_get_inode() return ERR_PTR instead of NULL on error. This will be
useful later when we introduce quota support.
There should be no functional change.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
mm/shmem.c | 206 ++++++++++++++++++++++++++++++-----------------------
1 file changed, 116 insertions(+), 90 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index b1b3b826f6189..09a44f1b2c954 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2354,65 +2354,71 @@ static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block
struct shmem_inode_info *info;
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
ino_t ino;
+ int err;
+
+ err = shmem_reserve_inode(sb, &ino);
+ if (err)
+ return ERR_PTR(err);
- if (shmem_reserve_inode(sb, &ino))
- return NULL;
inode = new_inode(sb);
- if (inode) {
- inode->i_ino = ino;
- 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();
- info = SHMEM_I(inode);
- memset(info, 0, (char *)inode - (char *)info);
- spin_lock_init(&info->lock);
- atomic_set(&info->stop_eviction, 0);
- info->seals = F_SEAL_SEAL;
- info->flags = flags & VM_NORESERVE;
- info->i_crtime = inode->i_mtime;
- info->fsflags = (dir == NULL) ? 0 :
- SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
- if (info->fsflags)
- shmem_set_inode_flags(inode, info->fsflags);
- INIT_LIST_HEAD(&info->shrinklist);
- INIT_LIST_HEAD(&info->swaplist);
- simple_xattrs_init(&info->xattrs);
- cache_no_acl(inode);
- mapping_set_large_folios(inode->i_mapping);
-
- switch (mode & S_IFMT) {
- default:
- inode->i_op = &shmem_special_inode_operations;
- init_special_inode(inode, mode, dev);
- break;
- case S_IFREG:
- inode->i_mapping->a_ops = &shmem_aops;
- inode->i_op = &shmem_inode_operations;
- inode->i_fop = &shmem_file_operations;
- mpol_shared_policy_init(&info->policy,
- shmem_get_sbmpol(sbinfo));
- break;
- case S_IFDIR:
- inc_nlink(inode);
- /* Some things misbehave if size == 0 on a directory */
- inode->i_size = 2 * BOGO_DIRENT_SIZE;
- inode->i_op = &shmem_dir_inode_operations;
- inode->i_fop = &simple_dir_operations;
- break;
- case S_IFLNK:
- /*
- * Must not load anything in the rbtree,
- * mpol_free_shared_policy will not be called.
- */
- mpol_shared_policy_init(&info->policy, NULL);
- break;
- }
- lockdep_annotate_inode_mutex_key(inode);
- } else
+ if (!inode) {
shmem_free_inode(sb);
+ return ERR_PTR(-ENOSPC);
+ }
+
+ inode->i_ino = ino;
+ 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();
+ info = SHMEM_I(inode);
+ memset(info, 0, (char *)inode - (char *)info);
+ spin_lock_init(&info->lock);
+ atomic_set(&info->stop_eviction, 0);
+ info->seals = F_SEAL_SEAL;
+ info->flags = flags & VM_NORESERVE;
+ info->i_crtime = inode->i_mtime;
+ info->fsflags = (dir == NULL) ? 0 :
+ SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
+ if (info->fsflags)
+ shmem_set_inode_flags(inode, info->fsflags);
+ INIT_LIST_HEAD(&info->shrinklist);
+ INIT_LIST_HEAD(&info->swaplist);
+ simple_xattrs_init(&info->xattrs);
+ cache_no_acl(inode);
+ mapping_set_large_folios(inode->i_mapping);
+
+ switch (mode & S_IFMT) {
+ default:
+ inode->i_op = &shmem_special_inode_operations;
+ init_special_inode(inode, mode, dev);
+ break;
+ case S_IFREG:
+ inode->i_mapping->a_ops = &shmem_aops;
+ inode->i_op = &shmem_inode_operations;
+ inode->i_fop = &shmem_file_operations;
+ mpol_shared_policy_init(&info->policy,
+ shmem_get_sbmpol(sbinfo));
+ break;
+ case S_IFDIR:
+ inc_nlink(inode);
+ /* Some things misbehave if size == 0 on a directory */
+ inode->i_size = 2 * BOGO_DIRENT_SIZE;
+ inode->i_op = &shmem_dir_inode_operations;
+ inode->i_fop = &simple_dir_operations;
+ break;
+ case S_IFLNK:
+ /*
+ * Must not load anything in the rbtree,
+ * mpol_free_shared_policy will not be called.
+ */
+ mpol_shared_policy_init(&info->policy, NULL);
+ break;
+ }
+
+ lockdep_annotate_inode_mutex_key(inode);
return inode;
}
@@ -2927,27 +2933,30 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
- int error = -ENOSPC;
+ int error;
inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, dev, VM_NORESERVE);
- if (inode) {
- error = simple_acl_create(dir, inode);
- if (error)
- goto out_iput;
- error = security_inode_init_security(inode, dir,
- &dentry->d_name,
- shmem_initxattrs, NULL);
- if (error && error != -EOPNOTSUPP)
- goto out_iput;
- error = 0;
- dir->i_size += BOGO_DIRENT_SIZE;
- dir->i_ctime = dir->i_mtime = current_time(dir);
- inode_inc_iversion(dir);
- d_instantiate(dentry, inode);
- dget(dentry); /* Extra count - pin the dentry in core */
- }
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ error = simple_acl_create(dir, inode);
+ if (error)
+ goto out_iput;
+ error = security_inode_init_security(inode, dir,
+ &dentry->d_name,
+ shmem_initxattrs, NULL);
+ if (error && error != -EOPNOTSUPP)
+ goto out_iput;
+
+ error = 0;
+ dir->i_size += BOGO_DIRENT_SIZE;
+ dir->i_ctime = dir->i_mtime = current_time(dir);
+ inode_inc_iversion(dir);
+ d_instantiate(dentry, inode);
+ dget(dentry); /* Extra count - pin the dentry in core */
return error;
+
out_iput:
iput(inode);
return error;
@@ -2958,20 +2967,26 @@ shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
struct file *file, umode_t mode)
{
struct inode *inode;
- int error = -ENOSPC;
+ int error;
inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE);
- if (inode) {
- error = security_inode_init_security(inode, dir,
- NULL,
- shmem_initxattrs, NULL);
- if (error && error != -EOPNOTSUPP)
- goto out_iput;
- error = simple_acl_create(dir, inode);
- if (error)
- goto out_iput;
- d_tmpfile(file, inode);
+
+ if (IS_ERR(inode)) {
+ error = PTR_ERR(inode);
+ goto err_out;
}
+
+ error = security_inode_init_security(inode, dir,
+ NULL,
+ shmem_initxattrs, NULL);
+ if (error && error != -EOPNOTSUPP)
+ goto out_iput;
+ error = simple_acl_create(dir, inode);
+ if (error)
+ goto out_iput;
+ d_tmpfile(file, inode);
+
+err_out:
return finish_open_simple(file, error);
out_iput:
iput(inode);
@@ -3146,8 +3161,9 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0,
VM_NORESERVE);
- if (!inode)
- return -ENOSPC;
+
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
error = security_inode_init_security(inode, dir, &dentry->d_name,
shmem_initxattrs, NULL);
@@ -3762,12 +3778,13 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
struct shmem_options *ctx = fc->fs_private;
struct inode *inode;
struct shmem_sb_info *sbinfo;
+ int error = -ENOMEM;
/* Round up to L1_CACHE_BYTES to resist false sharing */
sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
L1_CACHE_BYTES), GFP_KERNEL);
if (!sbinfo)
- return -ENOMEM;
+ return error;
sb->s_fs_info = sbinfo;
@@ -3829,8 +3846,10 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0,
VM_NORESERVE);
- if (!inode)
+ if (IS_ERR(inode)) {
+ error = PTR_ERR(inode);
goto failed;
+ }
inode->i_uid = sbinfo->uid;
inode->i_gid = sbinfo->gid;
sb->s_root = d_make_root(inode);
@@ -3840,7 +3859,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
failed:
shmem_put_super(sb);
- return -ENOMEM;
+ return error;
}
static int shmem_get_tree(struct fs_context *fc)
@@ -4209,10 +4228,16 @@ 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(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)
+static inline 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 = ramfs_get_inode(sb, dir, mode, dev);
+ return inode ? inode : ERR_PTR(-ENOSPC);
+}
+
#endif /* CONFIG_SHMEM */
/* common code */
@@ -4237,9 +4262,10 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL,
S_IFREG | S_IRWXUGO, 0, flags);
- if (unlikely(!inode)) {
+
+ if (IS_ERR(inode)) {
shmem_unacct_size(flags, size);
- return ERR_PTR(-ENOSPC);
+ return ERR_CAST(inode);
}
inode->i_flags |= i_flags;
inode->i_size = size;
--
2.30.2
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 3/6] quota: Check presence of quota operation structures instead of ->quota_read and ->quota_write callbacks
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
2023-04-26 10:20 ` [PATCH 1/6] shmem: make shmem_inode_acct_block() return error cem
2023-04-26 10:20 ` [PATCH 2/6] shmem: make shmem_get_inode() return ERR_PTR instead of NULL cem
@ 2023-04-26 10:20 ` cem
2023-04-26 10:20 ` [PATCH 4/6] shmem: prepare shmem quota infrastructure cem
` (3 subsequent siblings)
6 siblings, 0 replies; 19+ messages in thread
From: cem @ 2023-04-26 10:20 UTC (permalink / raw)
To: hughd; +Cc: jack, linux-mm, linux-fsdevel, djwong
From: Jan Kara <jack@suse.cz>
Currently we check whether superblock has ->quota_read and ->quota_write
operations to check whether filesystem supports quotas. However for
example for shmfs we will not read or write dquots so check whether
quota operations are set in the superblock instead.
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
fs/quota/dquot.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index a6357f728034a..81563a83b609d 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2367,7 +2367,7 @@ int dquot_load_quota_sb(struct super_block *sb, int type, int format_id,
if (!fmt)
return -ESRCH;
- if (!sb->s_op->quota_write || !sb->s_op->quota_read ||
+ if (!sb->dq_op || !sb->s_qcop ||
(type == PRJQUOTA && sb->dq_op->get_projid == NULL)) {
error = -EINVAL;
goto out_fmt;
--
2.30.2
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 4/6] shmem: prepare shmem quota infrastructure
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
` (2 preceding siblings ...)
2023-04-26 10:20 ` [PATCH 3/6] quota: Check presence of quota operation structures instead of ->quota_read and ->quota_write callbacks cem
@ 2023-04-26 10:20 ` cem
2023-04-26 10:20 ` [PATCH 5/6] shmem: quota support cem
` (2 subsequent siblings)
6 siblings, 0 replies; 19+ messages in thread
From: cem @ 2023-04-26 10:20 UTC (permalink / raw)
To: hughd; +Cc: jack, linux-mm, linux-fsdevel, djwong
From: Lukas Czerner <lczerner@redhat.com>
Add new shmem quota format, its quota_format_ops together with
dquot_operations
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
fs/Kconfig | 12 ++
include/linux/shmem_fs.h | 12 ++
include/uapi/linux/quota.h | 1 +
mm/Makefile | 2 +-
mm/shmem_quota.c | 318 +++++++++++++++++++++++++++++++++++++
5 files changed, 344 insertions(+), 1 deletion(-)
create mode 100644 mm/shmem_quota.c
diff --git a/fs/Kconfig b/fs/Kconfig
index e99830c650336..ba809882f1961 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -233,6 +233,18 @@ config TMPFS_INODE64
If unsure, say N.
+config TMPFS_QUOTA
+ bool "Tmpfs quota support"
+ depends on TMPFS
+ select QUOTA
+ help
+ Quota support allows to set per user and group limits for tmpfs
+ usage. Say Y to enable quota support. Once enabled you can control
+ user and group quota enforcement with quota, usrquota and grpquota
+ mount options.
+
+ If unsure, say N.
+
config ARCH_SUPPORTS_HUGETLBFS
def_bool n
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 103d1000a5a2e..92db49ebd5452 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -12,6 +12,10 @@
/* 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 */
@@ -163,4 +167,12 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, 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
diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h
index f17c9636a8593..52090105b8282 100644
--- a/include/uapi/linux/quota.h
+++ b/include/uapi/linux/quota.h
@@ -77,6 +77,7 @@
#define QFMT_VFS_V0 2
#define QFMT_OCFS2 3
#define QFMT_VFS_V1 4
+#define QFMT_SHMEM 5
/* Size of block in which space limits are passed through the quota
* interface */
diff --git a/mm/Makefile b/mm/Makefile
index 8e105e5b3e293..977d2b66775a9 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -52,7 +52,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o percpu.o slab_common.o \
- compaction.o \
+ compaction.o shmem_quota.o\
interval_tree.o list_lru.o workingset.o \
debug.o gup.o mmap_lock.o $(mmu-y)
diff --git a/mm/shmem_quota.c b/mm/shmem_quota.c
new file mode 100644
index 0000000000000..c0b531e2ef688
--- /dev/null
+++ b/mm/shmem_quota.c
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * In memory quota format relies on quota infrastructure to store dquot
+ * information for us. While conventional quota formats for file systems
+ * with persistent storage can load quota information into dquot from the
+ * storage on-demand and hence quota dquot shrinker can free any dquot
+ * that is not currently being used, it must be avoided here. Otherwise we
+ * can lose valuable information, user provided limits, because there is
+ * no persistent storage to load the information from afterwards.
+ *
+ * One information that in-memory quota format needs to keep track of is
+ * a sorted list of ids for each quota type. This is done by utilizing
+ * an rb tree which root is stored in mem_dqinfo->dqi_priv for each quota
+ * type.
+ *
+ * This format can be used to support quota on file system without persistent
+ * storage such as tmpfs.
+ *
+ * Author: Lukas Czerner <lczerner@redhat.com>
+ * Carlos Maiolino <cmaiolino@redhat.com>
+ *
+ * Copyright (C) 2023 Red Hat, Inc.
+ */
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/rbtree.h>
+#include <linux/shmem_fs.h>
+
+#include <linux/quotaops.h>
+#include <linux/quota.h>
+
+#ifdef CONFIG_TMPFS_QUOTA
+
+/*
+ * The following constants define the amount of time given a user
+ * before the soft limits are treated as hard limits (usually resulting
+ * in an allocation failure). The timer is started when the user crosses
+ * their soft limit, it is reset when they go below their soft limit.
+ */
+#define SHMEM_MAX_IQ_TIME 604800 /* (7*24*60*60) 1 week */
+#define SHMEM_MAX_DQ_TIME 604800 /* (7*24*60*60) 1 week */
+
+struct quota_id {
+ struct rb_node node;
+ qid_t id;
+ qsize_t bhardlimit;
+ qsize_t bsoftlimit;
+ qsize_t ihardlimit;
+ qsize_t isoftlimit;
+};
+
+static int shmem_check_quota_file(struct super_block *sb, int type)
+{
+ /* There is no real quota file, nothing to do */
+ return 1;
+}
+
+/*
+ * There is no real quota file. Just allocate rb_root for quota ids and
+ * set limits
+ */
+static int shmem_read_file_info(struct super_block *sb, int type)
+{
+ struct quota_info *dqopt = sb_dqopt(sb);
+ struct mem_dqinfo *info = &dqopt->info[type];
+
+ info->dqi_priv = kzalloc(sizeof(struct rb_root), GFP_NOFS);
+ if (!info->dqi_priv)
+ return -ENOMEM;
+
+ info->dqi_max_spc_limit = SHMEM_QUOTA_MAX_SPC_LIMIT;
+ info->dqi_max_ino_limit = SHMEM_QUOTA_MAX_INO_LIMIT;
+
+ info->dqi_bgrace = SHMEM_MAX_DQ_TIME;
+ info->dqi_igrace = SHMEM_MAX_IQ_TIME;
+ info->dqi_flags = 0;
+
+ return 0;
+}
+
+static int shmem_write_file_info(struct super_block *sb, int type)
+{
+ /* There is no real quota file, nothing to do */
+ return 0;
+}
+
+/*
+ * Free all the quota_id entries in the rb tree and rb_root.
+ */
+static int shmem_free_file_info(struct super_block *sb, int type)
+{
+ struct mem_dqinfo *info = &sb_dqopt(sb)->info[type];
+ struct rb_root *root = info->dqi_priv;
+ struct quota_id *entry;
+ struct rb_node *node;
+
+ info->dqi_priv = NULL;
+ node = rb_first(root);
+ while (node) {
+ entry = rb_entry(node, struct quota_id, node);
+ node = rb_next(&entry->node);
+
+ rb_erase(&entry->node, root);
+ kfree(entry);
+ }
+
+ kfree(root);
+ return 0;
+}
+
+static int shmem_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+ struct mem_dqinfo *info = sb_dqinfo(sb, qid->type);
+ struct rb_node *node = ((struct rb_root *)info->dqi_priv)->rb_node;
+ qid_t id = from_kqid(&init_user_ns, *qid);
+ struct quota_info *dqopt = sb_dqopt(sb);
+ struct quota_id *entry = NULL;
+ int ret = 0;
+
+ if (!sb_has_quota_active(sb, qid->type))
+ return -ESRCH;
+
+ down_read(&dqopt->dqio_sem);
+ while (node) {
+ entry = rb_entry(node, struct quota_id, node);
+
+ if (id < entry->id)
+ node = node->rb_left;
+ else if (id > entry->id)
+ node = node->rb_right;
+ else
+ goto got_next_id;
+ }
+
+ if (!entry) {
+ ret = -ENOENT;
+ goto out_unlock;
+ }
+
+ if (id > entry->id) {
+ node = rb_next(&entry->node);
+ if (!node) {
+ ret = -ENOENT;
+ goto out_unlock;
+ }
+ entry = rb_entry(node, struct quota_id, node);
+ }
+
+got_next_id:
+ *qid = make_kqid(&init_user_ns, qid->type, entry->id);
+out_unlock:
+ up_read(&dqopt->dqio_sem);
+ return ret;
+}
+
+/*
+ * Load dquot with limits from existing entry, or create the new entry if
+ * it does not exist.
+ */
+static int shmem_acquire_dquot(struct dquot *dquot)
+{
+ struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type);
+ struct rb_node **n = &((struct rb_root *)info->dqi_priv)->rb_node;
+ struct rb_node *parent = NULL, *new_node = NULL;
+ struct quota_id *new_entry, *entry;
+ qid_t id = from_kqid(&init_user_ns, dquot->dq_id);
+ struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
+ int ret = 0;
+
+ mutex_lock(&dquot->dq_lock);
+
+ down_write(&dqopt->dqio_sem);
+ while (*n) {
+ parent = *n;
+ entry = rb_entry(parent, struct quota_id, node);
+
+ if (id < entry->id)
+ n = &(*n)->rb_left;
+ else if (id > entry->id)
+ n = &(*n)->rb_right;
+ else
+ goto found;
+ }
+
+ /* We don't have entry for this id yet, create it */
+ new_entry = kzalloc(sizeof(struct quota_id), GFP_NOFS);
+ if (!new_entry) {
+ ret = -ENOMEM;
+ goto out_unlock;
+ }
+
+ new_entry->id = id;
+ new_node = &new_entry->node;
+ rb_link_node(new_node, parent, n);
+ rb_insert_color(new_node, (struct rb_root *)info->dqi_priv);
+ entry = new_entry;
+
+found:
+ /* Load the stored limits from the tree */
+ spin_lock(&dquot->dq_dqb_lock);
+ dquot->dq_dqb.dqb_bhardlimit = entry->bhardlimit;
+ dquot->dq_dqb.dqb_bsoftlimit = entry->bsoftlimit;
+ dquot->dq_dqb.dqb_ihardlimit = entry->ihardlimit;
+ dquot->dq_dqb.dqb_isoftlimit = entry->isoftlimit;
+
+ if (!dquot->dq_dqb.dqb_bhardlimit &&
+ !dquot->dq_dqb.dqb_bsoftlimit &&
+ !dquot->dq_dqb.dqb_ihardlimit &&
+ !dquot->dq_dqb.dqb_isoftlimit)
+ set_bit(DQ_FAKE_B, &dquot->dq_flags);
+ spin_unlock(&dquot->dq_dqb_lock);
+
+ /* Make sure flags update is visible after dquot has been filled */
+ smp_mb__before_atomic();
+ set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
+out_unlock:
+ up_write(&dqopt->dqio_sem);
+ mutex_unlock(&dquot->dq_lock);
+ return ret;
+}
+
+/*
+ * Store limits from dquot in the tree unless it's fake. If it is fake
+ * remove the id from the tree since there is no useful information in
+ * there.
+ */
+static int shmem_release_dquot(struct dquot *dquot)
+{
+ struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type);
+ struct rb_node *node = ((struct rb_root *)info->dqi_priv)->rb_node;
+ qid_t id = from_kqid(&init_user_ns, dquot->dq_id);
+ struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
+ struct quota_id *entry = NULL;
+
+ mutex_lock(&dquot->dq_lock);
+ /* Check whether we are not racing with some other dqget() */
+ if (dquot_is_busy(dquot))
+ goto out_dqlock;
+
+ down_write(&dqopt->dqio_sem);
+ while (node) {
+ entry = rb_entry(node, struct quota_id, node);
+
+ if (id < entry->id)
+ node = node->rb_left;
+ else if (id > entry->id)
+ node = node->rb_right;
+ else
+ goto found;
+ }
+
+ /* We should always find the entry in the rb tree */
+ WARN_ONCE(1, "quota id %u from dquot %p, not in rb tree!\n", id, dquot);
+ up_write(&dqopt->dqio_sem);
+ mutex_unlock(&dquot->dq_lock);
+ return -ENOENT;
+
+found:
+ if (test_bit(DQ_FAKE_B, &dquot->dq_flags)) {
+ /* Remove entry from the tree */
+ rb_erase(&entry->node, info->dqi_priv);
+ kfree(entry);
+ } else {
+ /* Store the limits in the tree */
+ spin_lock(&dquot->dq_dqb_lock);
+ entry->bhardlimit = dquot->dq_dqb.dqb_bhardlimit;
+ entry->bsoftlimit = dquot->dq_dqb.dqb_bsoftlimit;
+ entry->ihardlimit = dquot->dq_dqb.dqb_ihardlimit;
+ entry->isoftlimit = dquot->dq_dqb.dqb_isoftlimit;
+ spin_unlock(&dquot->dq_dqb_lock);
+ }
+
+ clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
+ up_write(&dqopt->dqio_sem);
+
+out_dqlock:
+ mutex_unlock(&dquot->dq_lock);
+ return 0;
+}
+
+int shmem_mark_dquot_dirty(struct dquot *dquot)
+{
+ return 0;
+}
+
+int shmem_dquot_write_info(struct super_block *sb, int type)
+{
+ return 0;
+}
+
+static const struct quota_format_ops shmem_format_ops = {
+ .check_quota_file = shmem_check_quota_file,
+ .read_file_info = shmem_read_file_info,
+ .write_file_info = shmem_write_file_info,
+ .free_file_info = shmem_free_file_info,
+};
+
+struct quota_format_type shmem_quota_format = {
+ .qf_fmt_id = QFMT_SHMEM,
+ .qf_ops = &shmem_format_ops,
+ .qf_owner = THIS_MODULE
+};
+
+const struct dquot_operations shmem_quota_operations = {
+ .acquire_dquot = shmem_acquire_dquot,
+ .release_dquot = shmem_release_dquot,
+ .alloc_dquot = dquot_alloc,
+ .destroy_dquot = dquot_destroy,
+ .write_info = shmem_dquot_write_info,
+ .mark_dirty = shmem_mark_dquot_dirty,
+ .get_next_id = shmem_get_next_id,
+};
+#endif /* CONFIG_TMPFS_QUOTA */
--
2.30.2
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 5/6] shmem: quota support
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
` (3 preceding siblings ...)
2023-04-26 10:20 ` [PATCH 4/6] shmem: prepare shmem quota infrastructure cem
@ 2023-04-26 10:20 ` cem
2023-04-26 10:20 ` [PATCH 6/6] Add default quota limit mount options cem
2023-05-15 8:54 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs Carlos Maiolino
6 siblings, 0 replies; 19+ messages in thread
From: cem @ 2023-04-26 10:20 UTC (permalink / raw)
To: hughd; +Cc: jack, linux-mm, linux-fsdevel, djwong
From: Lukas Czerner <lczerner@redhat.com>
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 <lczerner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
Documentation/filesystems/tmpfs.rst | 15 +++
include/linux/shmem_fs.h | 8 ++
mm/shmem.c | 180 ++++++++++++++++++++++++++--
3 files changed, 195 insertions(+), 8 deletions(-)
diff --git a/Documentation/filesystems/tmpfs.rst b/Documentation/filesystems/tmpfs.rst
index 0408c245785e3..595e607274afb 100644
--- a/Documentation/filesystems/tmpfs.rst
+++ b/Documentation/filesystems/tmpfs.rst
@@ -86,6 +86,21 @@ use up all the memory on the machine; but enhances the scalability of
that instance in a system with many CPUs making intensive use of it.
+tmpfs also supports quota with the following mount options
+
+======== =============================================================
+quota User and group quota accounting and enforcement is enabled on
+ the mount. Tmpfs is using hidden system quota files that are
+ initialized on mount.
+usrquota User quota accounting and enforcement is enabled on the
+ mount.
+grpquota Group quota accounting and enforcement is enabled on the
+ mount.
+======== =============================================================
+
+Note that tmpfs quotas do not support user namespaces so no uid/gid
+translation is done if quotas are enabled inside user namespaces.
+
tmpfs has a mount option to set the NUMA memory allocation policy for
all files in that instance (if CONFIG_NUMA is enabled) - which can be
adjusted on the fly via 'mount -o remount ...'
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 92db49ebd5452..b8e421e349868 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -30,6 +30,9 @@ 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;
};
@@ -175,4 +178,9 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, 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
diff --git a/mm/shmem.c b/mm/shmem.c
index 09a44f1b2c954..623d258af39f8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -79,6 +79,7 @@ static struct vfsmount *shm_mnt;
#include <linux/userfaultfd_k.h>
#include <linux/rmap.h>
#include <linux/uuid.h>
+#include <linux/quotaops.h>
#include <linux/uaccess.h>
@@ -116,10 +117,12 @@ struct shmem_options {
bool full_inums;
int huge;
int seen;
+ unsigned short quota_types;
#define SHMEM_SEEN_BLOCKS 1
#define SHMEM_SEEN_INODES 2
#define SHMEM_SEEN_HUGE 4
#define SHMEM_SEEN_INUMS 8
+#define SHMEM_SEEN_QUOTA 16
};
#ifdef CONFIG_TMPFS
@@ -211,7 +214,16 @@ static inline int shmem_inode_acct_block(struct inode *inode, long pages)
if (percpu_counter_compare(&sbinfo->used_blocks,
sbinfo->max_blocks - pages) > 0)
goto unacct;
+
+ err = dquot_alloc_block_nodirty(inode, pages);
+ if (err)
+ goto unacct;
+
percpu_counter_add(&sbinfo->used_blocks, pages);
+ } else {
+ err = dquot_alloc_block_nodirty(inode, pages);
+ if (err)
+ goto unacct;
}
return 0;
@@ -226,6 +238,8 @@ static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+ dquot_free_block_nodirty(inode, pages);
+
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks, pages);
shmem_unacct_blocks(info->flags, pages);
@@ -254,6 +268,47 @@ bool vma_is_shmem(struct vm_area_struct *vma)
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
+#ifdef CONFIG_TMPFS_QUOTA
+
+static int shmem_enable_quotas(struct super_block *sb,
+ unsigned short quota_types)
+{
+ int type, err = 0;
+
+ sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY;
+ for (type = 0; type < SHMEM_MAXQUOTAS; type++) {
+ if (!(quota_types & (1 << type)))
+ continue;
+ err = dquot_load_quota_sb(sb, type, QFMT_SHMEM,
+ DQUOT_USAGE_ENABLED |
+ DQUOT_LIMITS_ENABLED);
+ if (err)
+ goto out_err;
+ }
+ return 0;
+
+out_err:
+ pr_warn("tmpfs: failed to enable quota tracking (type=%d, err=%d)\n",
+ type, err);
+ for (type--; type >= 0; type--)
+ dquot_quota_off(sb, type);
+ return err;
+}
+
+static void shmem_disable_quotas(struct super_block *sb)
+{
+ int type;
+
+ for (type = 0; type < SHMEM_MAXQUOTAS; type++)
+ dquot_quota_off(sb, type);
+}
+
+static struct dquot **shmem_get_dquots(struct inode *inode)
+{
+ return SHMEM_I(inode)->i_dquot;
+}
+#endif /* CONFIG_TMPFS_QUOTA */
+
/*
* shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and
* produces a novel ino for the newly allocated inode.
@@ -360,7 +415,6 @@ static void shmem_recalc_inode(struct inode *inode)
freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
if (freed > 0) {
info->alloced -= freed;
- inode->i_blocks -= freed * BLOCKS_PER_PAGE;
shmem_inode_unacct_blocks(inode, freed);
}
}
@@ -378,7 +432,6 @@ bool shmem_charge(struct inode *inode, long pages)
spin_lock_irqsave(&info->lock, flags);
info->alloced += pages;
- inode->i_blocks += pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
@@ -394,7 +447,6 @@ void shmem_uncharge(struct inode *inode, long pages)
spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
- inode->i_blocks -= pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
@@ -1133,6 +1185,21 @@ static int shmem_setattr(struct mnt_idmap *idmap,
}
}
+ if (is_quota_modification(idmap, inode, attr)) {
+ error = dquot_initialize(inode);
+ if (error)
+ return error;
+ }
+
+ /* Transfer quota accounting */
+ if (i_uid_needs_update(idmap, attr, inode) ||
+ i_gid_needs_update(idmap, attr, inode)) {
+ error = dquot_transfer(idmap, inode, attr);
+
+ if (error)
+ return error;
+ }
+
setattr_copy(idmap, inode, attr);
if (attr->ia_valid & ATTR_MODE)
error = posix_acl_chmod(idmap, dentry, inode->i_mode);
@@ -1179,6 +1246,10 @@ static void shmem_evict_inode(struct inode *inode)
WARN_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
clear_inode(inode);
+#ifdef CONFIG_TMPFS_QUOTA
+ dquot_free_inode(inode);
+ dquot_drop(inode);
+#endif
}
static int shmem_find_swap_entries(struct address_space *mapping,
@@ -1975,7 +2046,6 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
spin_lock_irq(&info->lock);
info->alloced += folio_nr_pages(folio);
- inode->i_blocks += (blkcnt_t)BLOCKS_PER_PAGE << folio_order(folio);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
alloced = true;
@@ -2346,9 +2416,10 @@ static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags)
#define shmem_initxattrs NULL
#endif
-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)
+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;
@@ -2422,6 +2493,43 @@ static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block
return inode;
}
+#ifdef CONFIG_TMPFS_QUOTA
+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)
+{
+ int err;
+ struct inode *inode;
+
+ inode = __shmem_get_inode(idmap, sb, dir, mode, dev, flags);
+ if (IS_ERR(inode))
+ return inode;
+
+ err = dquot_initialize(inode);
+ if (err)
+ goto errout;
+
+ err = dquot_alloc_inode(inode);
+ if (err) {
+ dquot_drop(inode);
+ goto errout;
+ }
+ return inode;
+
+errout:
+ inode->i_flags |= S_NOQUOTA;
+ iput(inode);
+ return ERR_PTR(err);
+}
+#else
+static inline 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)
+{
+ return __shmem_get_inode(idmap, sb, dir, mode, dev, flags);
+}
+#endif /* CONFIG_TMPFS_QUOTA */
+
#ifdef CONFIG_USERFAULTFD
int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
pmd_t *dst_pmd,
@@ -2525,7 +2633,6 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
spin_lock_irq(&info->lock);
info->alloced++;
- inode->i_blocks += BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
@@ -3375,6 +3482,7 @@ static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
static const struct inode_operations shmem_short_symlink_operations = {
.getattr = shmem_getattr,
+ .setattr = shmem_setattr,
.get_link = simple_get_link,
#ifdef CONFIG_TMPFS_XATTR
.listxattr = shmem_listxattr,
@@ -3383,6 +3491,7 @@ static const struct inode_operations shmem_short_symlink_operations = {
static const struct inode_operations shmem_symlink_inode_operations = {
.getattr = shmem_getattr,
+ .setattr = shmem_setattr,
.get_link = shmem_get_link,
#ifdef CONFIG_TMPFS_XATTR
.listxattr = shmem_listxattr,
@@ -3481,6 +3590,9 @@ enum shmem_param {
Opt_uid,
Opt_inode32,
Opt_inode64,
+ Opt_quota,
+ Opt_usrquota,
+ Opt_grpquota,
};
static const struct constant_table shmem_param_enums_huge[] = {
@@ -3502,6 +3614,11 @@ const struct fs_parameter_spec shmem_fs_parameters[] = {
fsparam_u32 ("uid", Opt_uid),
fsparam_flag ("inode32", Opt_inode32),
fsparam_flag ("inode64", Opt_inode64),
+#ifdef CONFIG_TMPFS_QUOTA
+ fsparam_flag ("quota", Opt_quota),
+ fsparam_flag ("usrquota", Opt_usrquota),
+ fsparam_flag ("grpquota", Opt_grpquota),
+#endif
{}
};
@@ -3585,6 +3702,18 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
ctx->full_inums = true;
ctx->seen |= SHMEM_SEEN_INUMS;
break;
+ case Opt_quota:
+ ctx->seen |= SHMEM_SEEN_QUOTA;
+ ctx->quota_types |= (QTYPE_MASK_USR | QTYPE_MASK_GRP);
+ break;
+ case Opt_usrquota:
+ ctx->seen |= SHMEM_SEEN_QUOTA;
+ ctx->quota_types |= QTYPE_MASK_USR;
+ break;
+ case Opt_grpquota:
+ ctx->seen |= SHMEM_SEEN_QUOTA;
+ ctx->quota_types |= QTYPE_MASK_GRP;
+ break;
}
return 0;
@@ -3684,6 +3813,12 @@ static int shmem_reconfigure(struct fs_context *fc)
goto out;
}
+ if (ctx->seen & SHMEM_SEEN_QUOTA &&
+ !sb_any_quota_loaded(fc->root->d_sb)) {
+ err = "Cannot enable quota on remount";
+ goto out;
+ }
+
if (ctx->seen & SHMEM_SEEN_HUGE)
sbinfo->huge = ctx->huge;
if (ctx->seen & SHMEM_SEEN_INUMS)
@@ -3766,6 +3901,9 @@ static void shmem_put_super(struct super_block *sb)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+#ifdef CONFIG_TMPFS_QUOTA
+ shmem_disable_quotas(sb);
+#endif
free_percpu(sbinfo->ino_batch);
percpu_counter_destroy(&sbinfo->used_blocks);
mpol_put(sbinfo->mpol);
@@ -3844,6 +3982,17 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
#endif
uuid_gen(&sb->s_uuid);
+#ifdef CONFIG_TMPFS_QUOTA
+ if (ctx->seen & SHMEM_SEEN_QUOTA) {
+ sb->dq_op = &shmem_quota_operations;
+ sb->s_qcop = &dquot_quotactl_sysfile_ops;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
+
+ if (shmem_enable_quotas(sb, ctx->quota_types))
+ goto failed;
+ }
+#endif /* CONFIG_TMPFS_QUOTA */
+
inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0,
VM_NORESERVE);
if (IS_ERR(inode)) {
@@ -4019,6 +4168,9 @@ static const struct super_operations shmem_ops = {
#ifdef CONFIG_TMPFS
.statfs = shmem_statfs,
.show_options = shmem_show_options,
+#endif
+#ifdef CONFIG_TMPFS_QUOTA
+ .get_dquots = shmem_get_dquots,
#endif
.evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
@@ -4085,6 +4237,14 @@ void __init shmem_init(void)
shmem_init_inodecache();
+#ifdef CONFIG_TMPFS_QUOTA
+ error = register_quota_format(&shmem_quota_format);
+ if (error < 0) {
+ pr_err("Could not register quota format\n");
+ goto out3;
+ }
+#endif
+
error = register_filesystem(&shmem_fs_type);
if (error) {
pr_err("Could not register tmpfs\n");
@@ -4109,6 +4269,10 @@ void __init shmem_init(void)
out1:
unregister_filesystem(&shmem_fs_type);
out2:
+#ifdef CONFIG_TMPFS_QUOTA
+ unregister_quota_format(&shmem_quota_format);
+out3:
+#endif
shmem_destroy_inodecache();
shm_mnt = ERR_PTR(error);
}
--
2.30.2
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 6/6] Add default quota limit mount options
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
` (4 preceding siblings ...)
2023-04-26 10:20 ` [PATCH 5/6] shmem: quota support cem
@ 2023-04-26 10:20 ` cem
2023-05-15 8:54 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs Carlos Maiolino
6 siblings, 0 replies; 19+ messages in thread
From: cem @ 2023-04-26 10:20 UTC (permalink / raw)
To: hughd; +Cc: jack, linux-mm, linux-fsdevel, djwong
From: Lukas Czerner <lczerner@redhat.com>
Allow system administrator to set default global quota limits at tmpfs
mount time.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
Documentation/filesystems/tmpfs.rst | 34 +++++++++++-----
include/linux/shmem_fs.h | 8 ++++
mm/shmem.c | 61 +++++++++++++++++++++++++++++
mm/shmem_quota.c | 34 +++++++++++++++-
4 files changed, 127 insertions(+), 10 deletions(-)
diff --git a/Documentation/filesystems/tmpfs.rst b/Documentation/filesystems/tmpfs.rst
index 595e607274afb..0c7bfba34baa6 100644
--- a/Documentation/filesystems/tmpfs.rst
+++ b/Documentation/filesystems/tmpfs.rst
@@ -88,15 +88,31 @@ that instance in a system with many CPUs making intensive use of it.
tmpfs also supports quota with the following mount options
-======== =============================================================
-quota User and group quota accounting and enforcement is enabled on
- the mount. Tmpfs is using hidden system quota files that are
- initialized on mount.
-usrquota User quota accounting and enforcement is enabled on the
- mount.
-grpquota Group quota accounting and enforcement is enabled on the
- mount.
-======== =============================================================
+======================== =================================================
+quota User and group quota accounting and enforcement
+ is enabled on the mount. Tmpfs is using hidden
+ system quota files that are initialized on mount.
+usrquota User quota accounting and enforcement is enabled
+ on the mount.
+grpquota Group quota accounting and enforcement is enabled
+ on the mount.
+usrquota_block_hardlimit Set global user quota block hard limit.
+usrquota_inode_hardlimit Set global user quota inode hard limit.
+grpquota_block_hardlimit Set global group quota block hard limit.
+grpquota_inode_hardlimit Set global group quota inode hard limit.
+======================== =================================================
+
+None of the quota related mount options can be set or changed on remount.
+
+Quota limit parameters accept a suffix k, m or g for kilo, mega and giga
+and can't be changed on remount. Default global quota limits are taking
+effect for any and all user/group/project except root the first time the
+quota entry for user/group/project id is being accessed - typically the
+first time an inode with a particular id ownership is being created after
+the mount. In other words, instead of the limits being initialized to zero,
+they are initialized with the particular value provided with these mount
+options. The limits can be changed for any user/group id at any time as they
+normally can be.
Note that tmpfs quotas do not support user namespaces so no uid/gid
translation is done if quotas are enabled inside user namespaces.
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index b8e421e349868..8ca5e969f00fc 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -41,6 +41,13 @@ 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 */
@@ -58,6 +65,7 @@ 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)
diff --git a/mm/shmem.c b/mm/shmem.c
index 623d258af39f8..24bcb374ad27b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -118,6 +118,7 @@ struct shmem_options {
int huge;
int seen;
unsigned short quota_types;
+ struct shmem_quota_limits qlimits;
#define SHMEM_SEEN_BLOCKS 1
#define SHMEM_SEEN_INODES 2
#define SHMEM_SEEN_HUGE 4
@@ -3593,6 +3594,10 @@ enum shmem_param {
Opt_quota,
Opt_usrquota,
Opt_grpquota,
+ Opt_usrquota_block_hardlimit,
+ Opt_usrquota_inode_hardlimit,
+ Opt_grpquota_block_hardlimit,
+ Opt_grpquota_inode_hardlimit,
};
static const struct constant_table shmem_param_enums_huge[] = {
@@ -3618,6 +3623,10 @@ const struct fs_parameter_spec shmem_fs_parameters[] = {
fsparam_flag ("quota", Opt_quota),
fsparam_flag ("usrquota", Opt_usrquota),
fsparam_flag ("grpquota", Opt_grpquota),
+ fsparam_string("usrquota_block_hardlimit", Opt_usrquota_block_hardlimit),
+ fsparam_string("usrquota_inode_hardlimit", Opt_usrquota_inode_hardlimit),
+ fsparam_string("grpquota_block_hardlimit", Opt_grpquota_block_hardlimit),
+ fsparam_string("grpquota_inode_hardlimit", Opt_grpquota_inode_hardlimit),
#endif
{}
};
@@ -3714,6 +3723,42 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
ctx->seen |= SHMEM_SEEN_QUOTA;
ctx->quota_types |= QTYPE_MASK_GRP;
break;
+ case Opt_usrquota_block_hardlimit:
+ size = memparse(param->string, &rest);
+ if (*rest || !size)
+ goto bad_value;
+ if (size > SHMEM_QUOTA_MAX_SPC_LIMIT)
+ return invalfc(fc,
+ "User quota block hardlimit too large.");
+ ctx->qlimits.usrquota_bhardlimit = size;
+ break;
+ case Opt_grpquota_block_hardlimit:
+ size = memparse(param->string, &rest);
+ if (*rest || !size)
+ goto bad_value;
+ if (size > SHMEM_QUOTA_MAX_SPC_LIMIT)
+ return invalfc(fc,
+ "Group quota block hardlimit too large.");
+ ctx->qlimits.grpquota_bhardlimit = size;
+ break;
+ case Opt_usrquota_inode_hardlimit:
+ size = memparse(param->string, &rest);
+ if (*rest || !size)
+ goto bad_value;
+ if (size > SHMEM_QUOTA_MAX_INO_LIMIT)
+ return invalfc(fc,
+ "User quota inode hardlimit too large.");
+ ctx->qlimits.usrquota_ihardlimit = size;
+ break;
+ case Opt_grpquota_inode_hardlimit:
+ size = memparse(param->string, &rest);
+ if (*rest || !size)
+ goto bad_value;
+ if (size > SHMEM_QUOTA_MAX_INO_LIMIT)
+ return invalfc(fc,
+ "Group quota inode hardlimit too large.");
+ ctx->qlimits.grpquota_ihardlimit = size;
+ break;
}
return 0;
@@ -3819,6 +3864,18 @@ static int shmem_reconfigure(struct fs_context *fc)
goto out;
}
+#ifdef CONFIG_TMPFS_QUOTA
+#define CHANGED_LIMIT(name) \
+ (ctx->qlimits.name## hardlimit && \
+ (ctx->qlimits.name## hardlimit != sbinfo->qlimits.name## hardlimit))
+
+ if (CHANGED_LIMIT(usrquota_b) || CHANGED_LIMIT(usrquota_i) ||
+ CHANGED_LIMIT(grpquota_b) || CHANGED_LIMIT(grpquota_i)) {
+ err = "Cannot change global quota limit on remount";
+ goto out;
+ }
+#endif /* CONFIG_TMPFS_QUOTA */
+
if (ctx->seen & SHMEM_SEEN_HUGE)
sbinfo->huge = ctx->huge;
if (ctx->seen & SHMEM_SEEN_INUMS)
@@ -3988,6 +4045,10 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
sb->s_qcop = &dquot_quotactl_sysfile_ops;
sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
+ /* Copy the default limits from ctx into sbinfo */
+ memcpy(&sbinfo->qlimits, &ctx->qlimits,
+ sizeof(struct shmem_quota_limits));
+
if (shmem_enable_quotas(sb, ctx->quota_types))
goto failed;
}
diff --git a/mm/shmem_quota.c b/mm/shmem_quota.c
index c0b531e2ef688..e349c0901bced 100644
--- a/mm/shmem_quota.c
+++ b/mm/shmem_quota.c
@@ -166,6 +166,7 @@ static int shmem_acquire_dquot(struct dquot *dquot)
{
struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type);
struct rb_node **n = &((struct rb_root *)info->dqi_priv)->rb_node;
+ struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info;
struct rb_node *parent = NULL, *new_node = NULL;
struct quota_id *new_entry, *entry;
qid_t id = from_kqid(&init_user_ns, dquot->dq_id);
@@ -195,6 +196,14 @@ static int shmem_acquire_dquot(struct dquot *dquot)
}
new_entry->id = id;
+ if (dquot->dq_id.type == USRQUOTA) {
+ new_entry->bhardlimit = sbinfo->qlimits.usrquota_bhardlimit;
+ new_entry->ihardlimit = sbinfo->qlimits.usrquota_ihardlimit;
+ } else if (dquot->dq_id.type == GRPQUOTA) {
+ new_entry->bhardlimit = sbinfo->qlimits.grpquota_bhardlimit;
+ new_entry->ihardlimit = sbinfo->qlimits.grpquota_ihardlimit;
+ }
+
new_node = &new_entry->node;
rb_link_node(new_node, parent, n);
rb_insert_color(new_node, (struct rb_root *)info->dqi_priv);
@@ -224,6 +233,29 @@ static int shmem_acquire_dquot(struct dquot *dquot)
return ret;
}
+static bool shmem_is_empty_dquot(struct dquot *dquot)
+{
+ struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info;
+ qsize_t bhardlimit;
+ qsize_t ihardlimit;
+
+ if (dquot->dq_id.type == USRQUOTA) {
+ bhardlimit = sbinfo->qlimits.usrquota_bhardlimit;
+ ihardlimit = sbinfo->qlimits.usrquota_ihardlimit;
+ } else if (dquot->dq_id.type == GRPQUOTA) {
+ bhardlimit = sbinfo->qlimits.grpquota_bhardlimit;
+ ihardlimit = sbinfo->qlimits.grpquota_ihardlimit;
+ }
+
+ if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
+ (dquot->dq_dqb.dqb_curspace == 0 &&
+ dquot->dq_dqb.dqb_curinodes == 0 &&
+ dquot->dq_dqb.dqb_bhardlimit == bhardlimit &&
+ dquot->dq_dqb.dqb_ihardlimit == ihardlimit))
+ return true;
+
+ return false;
+}
/*
* Store limits from dquot in the tree unless it's fake. If it is fake
* remove the id from the tree since there is no useful information in
@@ -261,7 +293,7 @@ static int shmem_release_dquot(struct dquot *dquot)
return -ENOENT;
found:
- if (test_bit(DQ_FAKE_B, &dquot->dq_flags)) {
+ if (shmem_is_empty_dquot(dquot)) {
/* Remove entry from the tree */
rb_erase(&entry->node, info->dqi_priv);
kfree(entry);
--
2.30.2
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs
2023-04-26 10:20 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs cem
` (5 preceding siblings ...)
2023-04-26 10:20 ` [PATCH 6/6] Add default quota limit mount options cem
@ 2023-05-15 8:54 ` Carlos Maiolino
2023-05-17 10:50 ` Hugh Dickins
6 siblings, 1 reply; 19+ messages in thread
From: Carlos Maiolino @ 2023-05-15 8:54 UTC (permalink / raw)
To: hughd, jack, linux-mm, linux-fsdevel, djwong
On Wed, Apr 26, 2023 at 12:20:02PM +0200, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
>
> Hello folks.
>
> This is the final version of the quota support from tmpfs, with all the issues
> addressed, and now including RwB tags on all patches, and should be ready for
> merge. Details are within each patch, and the original cover-letter below.
>
Ping? Can somebody manage to pickup these patches?
Thanks!
> Hi folks. this work has been done originally by Lukas, but he left the company,
> so I'm taking over his work from where he left it of. This series is virtually
> done, and he had updated it with comments from the last version, but, I'm
> initially posting it as a RFC because it's been a while since he posted the
> last version.
> Most of what I did here was rebase his last work on top of current Linus's tree.
>
> Honza, there is one patch from you in this series, which I believe you had it
> suggested to Lukas on a previous version.
>
> The original cover-letter follows...
>
> people have been asking for quota support in tmpfs many times in the past
> mostly to avoid one malicious user, or misbehaving user/program to consume
> all of the system memory. This has been partially solved with the size
> mount option, but some problems still prevail.
>
> One of the problems is the fact that /dev/shm is still generally unprotected
> with this and another is administration overhead of managing multiple tmpfs
> mounts and lack of more fine grained control.
>
> Quota support can solve all these problems in a somewhat standard way
> people are already familiar with from regular file systems. It can give us
> more fine grained control over how much memory user/groups can consume.
> Additionally it can also control number of inodes and with special quota
> mount options introduced with a second patch we can set global limits
> allowing us to replace the size mount option with quota entirely.
>
> Currently the standard userspace quota tools (quota, xfs_quota) are only
> using quotactl ioctl which is expecting a block device. I patched quota [1]
> and xfs_quota [2] to use quotactl_fd in case we want to run the tools on
> mount point directory to work nicely with tmpfs.
>
> The implementation was tested on patched version of xfstests [3].
>
> [1] https://github.com/lczerner/quota/tree/quotactl_fd_support
> [2] https://github.com/lczerner/xfsprogs/tree/quotactl_fd_support
> [3] https://github.com/lczerner/xfstests/tree/tmpfs_quota_support
>
>
> Jan Kara (1):
> quota: Check presence of quota operation structures instead of
> ->quota_read and ->quota_write callbacks
>
> Lukas Czerner (5):
> shmem: make shmem_inode_acct_block() return error
> shmem: make shmem_get_inode() return ERR_PTR instead of NULL
> shmem: prepare shmem quota infrastructure
> shmem: quota support
> Add default quota limit mount options
>
> Documentation/filesystems/tmpfs.rst | 31 ++
> fs/Kconfig | 12 +
> fs/quota/dquot.c | 2 +-
> include/linux/shmem_fs.h | 28 ++
> include/uapi/linux/quota.h | 1 +
> mm/Makefile | 2 +-
> mm/shmem.c | 465 +++++++++++++++++++++-------
> mm/shmem_quota.c | 350 +++++++++++++++++++++
> 8 files changed, 783 insertions(+), 108 deletions(-)
> create mode 100644 mm/shmem_quota.c
>
> Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
> --
> 2.30.2
>
--
Carlos Maiolino
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs
2023-05-15 8:54 ` [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs Carlos Maiolino
@ 2023-05-17 10:50 ` Hugh Dickins
2023-05-17 12:22 ` Carlos Maiolino
0 siblings, 1 reply; 19+ messages in thread
From: Hugh Dickins @ 2023-05-17 10:50 UTC (permalink / raw)
To: Carlos Maiolino
Cc: Andrew Morton, Christian Brauner, hughd, jack, linux-mm,
linux-fsdevel, djwong
Hi Carlos,
On Mon, 15 May 2023, Carlos Maiolino wrote:
> On Wed, Apr 26, 2023 at 12:20:02PM +0200, cem@kernel.org wrote:
> > From: Carlos Maiolino <cem@kernel.org>
> >
> > Hello folks.
> >
> > This is the final version of the quota support from tmpfs, with all the issues
> > addressed, and now including RwB tags on all patches, and should be ready for
> > merge. Details are within each patch, and the original cover-letter below.
> >
>
> Ping? Can somebody manage to pickup these patches?
Sorry, but it won't be me picking them up. Let's Cc Andrew Morton,
through whose mm tree mm/shmem.c patches usually go. fs-wide updates
often go through the fs tree, but this is not really in that category:
it's a specific addition of a feature new to tmpfs; plus I see that
Andrew did have plenty of quota involvement back in the day. And let's
Cc Christian Brauner, who was raising namespace questions in November.
tmpfs quotas: not a feature that I was ever hoping for, though I might
have joked about it twenty years ago. Already we had the nr_blocks=
or size= restriction; and the vm_enough_memory strict-non-overcommit
restriction; and later the memcg charging restriction. Nowadays,
with namespaces (and tmpfs FS_USERNS_MOUNT), I'd have imagined that
the natural way to proceed would be to mount a size-limited tmpfs
into the namespace of the user to be limited - but I'm no system
designer, and likely just boasting my ignorance of namespaces again.
It does look as if Lukas and you have done a good job here:
it's a much lighter "invasion" than I was expecting (and the
de-indentation changes looked reasonable to me too, though I didn't
check through them). I was puzzled where the i_blocks accounting
had vanished, but found it eventually in the dquot stubs.
So, I don't have an actual objection, and it counts for a lot that
you have Jan Kara on board; but this is not work that I shall be able
to support myself (I'll rarely even turn the CONFIG on). If Andrew
thinks it should go in, then you will be needed to maintain it.
IIRC there's an outstanding issue, that namespaces are not properly
supported here. Given Christian's work on idmapping, that will be
unfortunate; but if it's just that you were waiting for the base
series to go in, before correcting the namespace situation, that's
understandable and should not delay further - but I hope that you
know what more is needed, and that it won't add much more code.
Hugh
>
> Thanks!
>
> > Hi folks. this work has been done originally by Lukas, but he left the company,
> > so I'm taking over his work from where he left it of. This series is virtually
> > done, and he had updated it with comments from the last version, but, I'm
> > initially posting it as a RFC because it's been a while since he posted the
> > last version.
> > Most of what I did here was rebase his last work on top of current Linus's tree.
> >
> > Honza, there is one patch from you in this series, which I believe you had it
> > suggested to Lukas on a previous version.
> >
> > The original cover-letter follows...
> >
> > people have been asking for quota support in tmpfs many times in the past
> > mostly to avoid one malicious user, or misbehaving user/program to consume
> > all of the system memory. This has been partially solved with the size
> > mount option, but some problems still prevail.
> >
> > One of the problems is the fact that /dev/shm is still generally unprotected
> > with this and another is administration overhead of managing multiple tmpfs
> > mounts and lack of more fine grained control.
> >
> > Quota support can solve all these problems in a somewhat standard way
> > people are already familiar with from regular file systems. It can give us
> > more fine grained control over how much memory user/groups can consume.
> > Additionally it can also control number of inodes and with special quota
> > mount options introduced with a second patch we can set global limits
> > allowing us to replace the size mount option with quota entirely.
> >
> > Currently the standard userspace quota tools (quota, xfs_quota) are only
> > using quotactl ioctl which is expecting a block device. I patched quota [1]
> > and xfs_quota [2] to use quotactl_fd in case we want to run the tools on
> > mount point directory to work nicely with tmpfs.
> >
> > The implementation was tested on patched version of xfstests [3].
> >
> > [1] https://github.com/lczerner/quota/tree/quotactl_fd_support
> > [2] https://github.com/lczerner/xfsprogs/tree/quotactl_fd_support
> > [3] https://github.com/lczerner/xfstests/tree/tmpfs_quota_support
> >
> >
> > Jan Kara (1):
> > quota: Check presence of quota operation structures instead of
> > ->quota_read and ->quota_write callbacks
> >
> > Lukas Czerner (5):
> > shmem: make shmem_inode_acct_block() return error
> > shmem: make shmem_get_inode() return ERR_PTR instead of NULL
> > shmem: prepare shmem quota infrastructure
> > shmem: quota support
> > Add default quota limit mount options
> >
> > Documentation/filesystems/tmpfs.rst | 31 ++
> > fs/Kconfig | 12 +
> > fs/quota/dquot.c | 2 +-
> > include/linux/shmem_fs.h | 28 ++
> > include/uapi/linux/quota.h | 1 +
> > mm/Makefile | 2 +-
> > mm/shmem.c | 465 +++++++++++++++++++++-------
> > mm/shmem_quota.c | 350 +++++++++++++++++++++
> > 8 files changed, 783 insertions(+), 108 deletions(-)
> > create mode 100644 mm/shmem_quota.c
> >
> > Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
> > --
> > 2.30.2
> >
>
> --
> Carlos Maiolino
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH V4 0/6] shmem: Add user and group quota support for tmpfs
2023-05-17 10:50 ` Hugh Dickins
@ 2023-05-17 12:22 ` Carlos Maiolino
0 siblings, 0 replies; 19+ messages in thread
From: Carlos Maiolino @ 2023-05-17 12:22 UTC (permalink / raw)
To: Hugh Dickins
Cc: Andrew Morton, Christian Brauner, jack, linux-mm, linux-fsdevel,
djwong
On Wed, May 17, 2023 at 03:50:47AM -0700, Hugh Dickins wrote:
> Hi Carlos,
>
> On Mon, 15 May 2023, Carlos Maiolino wrote:
> > On Wed, Apr 26, 2023 at 12:20:02PM +0200, cem@kernel.org wrote:
> > > From: Carlos Maiolino <cem@kernel.org>
> > >
> > > Hello folks.
> > >
> > > This is the final version of the quota support from tmpfs, with all the issues
> > > addressed, and now including RwB tags on all patches, and should be ready for
> > > merge. Details are within each patch, and the original cover-letter below.
> > >
> >
> > Ping? Can somebody manage to pickup these patches?
>
> Sorry, but it won't be me picking them up. Let's Cc Andrew Morton,
> through whose mm tree mm/shmem.c patches usually go. fs-wide updates
> often go through the fs tree, but this is not really in that category:
> it's a specific addition of a feature new to tmpfs; plus I see that
> Andrew did have plenty of quota involvement back in the day. And let's
> Cc Christian Brauner, who was raising namespace questions in November.
Thanks, I spoke with Christian on the previous thread. I believe we are all set
in there by now.
>
> tmpfs quotas: not a feature that I was ever hoping for, though I might
> have joked about it twenty years ago. Already we had the nr_blocks=
> or size= restriction; and the vm_enough_memory strict-non-overcommit
> restriction; and later the memcg charging restriction. Nowadays,
> with namespaces (and tmpfs FS_USERNS_MOUNT), I'd have imagined that
> the natural way to proceed would be to mount a size-limited tmpfs
> into the namespace of the user to be limited - but I'm no system
> designer, and likely just boasting my ignorance of namespaces again.
>
> It does look as if Lukas and you have done a good job here:
> it's a much lighter "invasion" than I was expecting (and the
> de-indentation changes looked reasonable to me too, though I didn't
> check through them). I was puzzled where the i_blocks accounting
> had vanished, but found it eventually in the dquot stubs.
>
> So, I don't have an actual objection, and it counts for a lot that
> you have Jan Kara on board; but this is not work that I shall be able
> to support myself (I'll rarely even turn the CONFIG on). If Andrew
> thinks it should go in, then you will be needed to maintain it.
Sounds reasonable.
>
> IIRC there's an outstanding issue, that namespaces are not properly
> supported here. Given Christian's work on idmapping, that will be
> unfortunate; but if it's just that you were waiting for the base
> series to go in, before correcting the namespace situation, that's
> understandable and should not delay further - but I hope that you
> know what more is needed, and that it won't add much more code.
Yup, I didn't want to add more features here by now to avoid further delays to
have the basic series merged, both things I plan to implement here by now are
userns support and prjquotas. Both AFAIK won't really need too much extra code,
but will add more overhead on people to review, so having them as separated series
and not part of the basic quota implementation, should ease the burden a bit.
>
> Hugh
>
> >
> > Thanks!
> >
> > > Hi folks. this work has been done originally by Lukas, but he left the company,
> > > so I'm taking over his work from where he left it of. This series is virtually
> > > done, and he had updated it with comments from the last version, but, I'm
> > > initially posting it as a RFC because it's been a while since he posted the
> > > last version.
> > > Most of what I did here was rebase his last work on top of current Linus's tree.
> > >
> > > Honza, there is one patch from you in this series, which I believe you had it
> > > suggested to Lukas on a previous version.
> > >
> > > The original cover-letter follows...
> > >
> > > people have been asking for quota support in tmpfs many times in the past
> > > mostly to avoid one malicious user, or misbehaving user/program to consume
> > > all of the system memory. This has been partially solved with the size
> > > mount option, but some problems still prevail.
> > >
> > > One of the problems is the fact that /dev/shm is still generally unprotected
> > > with this and another is administration overhead of managing multiple tmpfs
> > > mounts and lack of more fine grained control.
> > >
> > > Quota support can solve all these problems in a somewhat standard way
> > > people are already familiar with from regular file systems. It can give us
> > > more fine grained control over how much memory user/groups can consume.
> > > Additionally it can also control number of inodes and with special quota
> > > mount options introduced with a second patch we can set global limits
> > > allowing us to replace the size mount option with quota entirely.
> > >
> > > Currently the standard userspace quota tools (quota, xfs_quota) are only
> > > using quotactl ioctl which is expecting a block device. I patched quota [1]
> > > and xfs_quota [2] to use quotactl_fd in case we want to run the tools on
> > > mount point directory to work nicely with tmpfs.
> > >
> > > The implementation was tested on patched version of xfstests [3].
> > >
> > > [1] https://github.com/lczerner/quota/tree/quotactl_fd_support
> > > [2] https://github.com/lczerner/xfsprogs/tree/quotactl_fd_support
> > > [3] https://github.com/lczerner/xfstests/tree/tmpfs_quota_support
> > >
> > >
> > > Jan Kara (1):
> > > quota: Check presence of quota operation structures instead of
> > > ->quota_read and ->quota_write callbacks
> > >
> > > Lukas Czerner (5):
> > > shmem: make shmem_inode_acct_block() return error
> > > shmem: make shmem_get_inode() return ERR_PTR instead of NULL
> > > shmem: prepare shmem quota infrastructure
> > > shmem: quota support
> > > Add default quota limit mount options
> > >
> > > Documentation/filesystems/tmpfs.rst | 31 ++
> > > fs/Kconfig | 12 +
> > > fs/quota/dquot.c | 2 +-
> > > include/linux/shmem_fs.h | 28 ++
> > > include/uapi/linux/quota.h | 1 +
> > > mm/Makefile | 2 +-
> > > mm/shmem.c | 465 +++++++++++++++++++++-------
> > > mm/shmem_quota.c | 350 +++++++++++++++++++++
> > > 8 files changed, 783 insertions(+), 108 deletions(-)
> > > create mode 100644 mm/shmem_quota.c
> > >
> > > Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
> > > --
> > > 2.30.2
> > >
> >
> > --
> > Carlos Maiolino
--
Carlos Maiolino
^ permalink raw reply [flat|nested] 19+ messages in thread