summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-01-22 11:28:23 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-22 11:28:23 +0200
commit1c52283265a462a100ae63ddf58b4e5884acde86 (patch)
treec0d3fa7a02fc0111bc7e56aa1be88e9b92795704 /fs
parent8205ae327e396820fb7a176a94768146ac0b87ea (diff)
parent6e61dde82e8bfe65e8ebbe43da45e615bc529236 (diff)
Merge branch 'akpm' (patches from Andrew)
Merge yet more updates from Andrew Morton: "This is the post-linux-next queue. Material which was based on or dependent upon material which was in -next. 69 patches. Subsystems affected by this patch series: mm (migration and zsmalloc), sysctl, proc, and lib" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (69 commits) mm: hide the FRONTSWAP Kconfig symbol frontswap: remove support for multiple ops mm: mark swap_lock and swap_active_head static frontswap: simplify frontswap_register_ops frontswap: remove frontswap_test mm: simplify try_to_unuse frontswap: remove the frontswap exports frontswap: simplify frontswap_init frontswap: remove frontswap_curr_pages frontswap: remove frontswap_shrink frontswap: remove frontswap_tmem_exclusive_gets frontswap: remove frontswap_writethrough mm: remove cleancache lib/stackdepot: always do filter_irq_stacks() in stack_depot_save() lib/stackdepot: allow optional init and stack_table allocation by kvmalloc() proc: remove PDE_DATA() completely fs: proc: store PDE()->data into inode->i_private zsmalloc: replace get_cpu_var with local_lock zsmalloc: replace per zpage lock with pool->migrate_lock locking/rwlocks: introduce write_lock_nested ...
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile2
-rw-r--r--fs/afs/proc.c6
-rw-r--r--fs/aio.c31
-rw-r--r--fs/binfmt_misc.c6
-rw-r--r--fs/btrfs/extent_io.c10
-rw-r--r--fs/btrfs/super.c2
-rw-r--r--fs/coredump.c66
-rw-r--r--fs/dcache.c37
-rw-r--r--fs/eventpoll.c10
-rw-r--r--fs/exec.c35
-rw-r--r--fs/ext4/mballoc.c14
-rw-r--r--fs/ext4/readpage.c6
-rw-r--r--fs/ext4/super.c3
-rw-r--r--fs/f2fs/data.c13
-rw-r--r--fs/file_table.c47
-rw-r--r--fs/inode.c39
-rw-r--r--fs/jbd2/journal.c2
-rw-r--r--fs/locks.c34
-rw-r--r--fs/mpage.c7
-rw-r--r--fs/namei.c58
-rw-r--r--fs/namespace.c24
-rw-r--r--fs/notify/dnotify/dnotify.c21
-rw-r--r--fs/notify/fanotify/fanotify_user.c10
-rw-r--r--fs/notify/inotify/inotify_user.c11
-rw-r--r--fs/ntfs3/ntfs_fs.h1
-rw-r--r--fs/ocfs2/stackglue.c25
-rw-r--r--fs/ocfs2/super.c2
-rw-r--r--fs/pipe.c64
-rw-r--r--fs/proc/generic.c6
-rw-r--r--fs/proc/inode.c1
-rw-r--r--fs/proc/internal.h5
-rw-r--r--fs/proc/proc_net.c8
-rw-r--r--fs/proc/proc_sysctl.c63
-rw-r--r--fs/super.c3
-rw-r--r--fs/sysctls.c39
35 files changed, 569 insertions, 142 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 84c5e4cdfee5..dab324aea08f 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -6,6 +6,8 @@
# Rewritten to use lists instead of if-statements.
#
+obj-$(CONFIG_SYSCTL) += sysctls.o
+
obj-y := open.o read_write.o file_table.o super.o \
char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
ioctl.o readdir.o select.o dcache.o inode.o \
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 065a28bfa3f1..e1b863449296 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -227,7 +227,7 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
__acquires(cell->proc_lock)
{
- struct afs_cell *cell = PDE_DATA(file_inode(m->file));
+ struct afs_cell *cell = pde_data(file_inode(m->file));
rcu_read_lock();
return seq_hlist_start_head_rcu(&cell->proc_volumes, *_pos);
@@ -236,7 +236,7 @@ static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
static void *afs_proc_cell_volumes_next(struct seq_file *m, void *v,
loff_t *_pos)
{
- struct afs_cell *cell = PDE_DATA(file_inode(m->file));
+ struct afs_cell *cell = pde_data(file_inode(m->file));
return seq_hlist_next_rcu(v, &cell->proc_volumes, _pos);
}
@@ -322,7 +322,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos)
{
struct afs_vl_seq_net_private *priv = m->private;
struct afs_vlserver_list *vllist;
- struct afs_cell *cell = PDE_DATA(file_inode(m->file));
+ struct afs_cell *cell = pde_data(file_inode(m->file));
loff_t pos = *_pos;
rcu_read_lock();
diff --git a/fs/aio.c b/fs/aio.c
index f6f1cbffef9e..4ceba13a7db0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -220,9 +220,35 @@ struct aio_kiocb {
/*------ sysctl variables----*/
static DEFINE_SPINLOCK(aio_nr_lock);
-unsigned long aio_nr; /* current system wide number of aio requests */
-unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */
+static unsigned long aio_nr; /* current system wide number of aio requests */
+static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */
/*----end sysctl variables---*/
+#ifdef CONFIG_SYSCTL
+static struct ctl_table aio_sysctls[] = {
+ {
+ .procname = "aio-nr",
+ .data = &aio_nr,
+ .maxlen = sizeof(aio_nr),
+ .mode = 0444,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ {
+ .procname = "aio-max-nr",
+ .data = &aio_max_nr,
+ .maxlen = sizeof(aio_max_nr),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ {}
+};
+
+static void __init aio_sysctl_init(void)
+{
+ register_sysctl_init("fs", aio_sysctls);
+}
+#else
+#define aio_sysctl_init() do { } while (0)
+#endif
static struct kmem_cache *kiocb_cachep;
static struct kmem_cache *kioctx_cachep;
@@ -275,6 +301,7 @@ static int __init aio_setup(void)
kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
+ aio_sysctl_init();
return 0;
}
__initcall(aio_setup);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index e1eae7ea823a..ddea6acbddde 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -822,7 +822,11 @@ static int __init init_misc_binfmt(void)
int err = register_filesystem(&bm_fs_type);
if (!err)
insert_binfmt(&misc_format);
- return err;
+ if (!register_sysctl_mount_point("fs/binfmt_misc")) {
+ pr_warn("Failed to create fs/binfmt_misc sysctl mount point");
+ return -ENOMEM;
+ }
+ return 0;
}
static void __exit exit_misc_binfmt(void)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d6d48ecf823c..409bad3928db 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -12,7 +12,6 @@
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
-#include <linux/cleancache.h>
#include <linux/fsverity.h>
#include "misc.h"
#include "extent_io.h"
@@ -3578,15 +3577,6 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
goto out;
}
- if (!PageUptodate(page)) {
- if (cleancache_get_page(page) == 0) {
- BUG_ON(blocksize != PAGE_SIZE);
- unlock_extent(tree, start, end);
- unlock_page(page);
- goto out;
- }
- }
-
if (page->index == last_byte >> PAGE_SHIFT) {
size_t zero_offset = offset_in_page(last_byte);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0ec09fe01be6..4d947ba32da9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -23,7 +23,6 @@
#include <linux/miscdevice.h>
#include <linux/magic.h>
#include <linux/slab.h>
-#include <linux/cleancache.h>
#include <linux/ratelimit.h>
#include <linux/crc32c.h>
#include <linux/btrfs.h>
@@ -1374,7 +1373,6 @@ static int btrfs_fill_super(struct super_block *sb,
goto fail_close;
}
- cleancache_init_fs(sb);
sb->s_flags |= SB_ACTIVE;
return 0;
diff --git a/fs/coredump.c b/fs/coredump.c
index 7dece20b162b..1c060c0a2d72 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -41,6 +41,7 @@
#include <linux/fs.h>
#include <linux/path.h>
#include <linux/timekeeping.h>
+#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -52,9 +53,9 @@
#include <trace/events/sched.h>
-int core_uses_pid;
-unsigned int core_pipe_limit;
-char core_pattern[CORENAME_MAX_SIZE] = "core";
+static int core_uses_pid;
+static unsigned int core_pipe_limit;
+static char core_pattern[CORENAME_MAX_SIZE] = "core";
static int core_name_size = CORENAME_MAX_SIZE;
struct core_name {
@@ -62,8 +63,6 @@ struct core_name {
int used, size;
};
-/* The maximal length of core_pattern is also specified in sysctl.c */
-
static int expand_corename(struct core_name *cn, int size)
{
char *corename = krealloc(cn->corename, size, GFP_KERNEL);
@@ -893,6 +892,63 @@ int dump_align(struct coredump_params *cprm, int align)
}
EXPORT_SYMBOL(dump_align);
+#ifdef CONFIG_SYSCTL
+
+void validate_coredump_safety(void)
+{
+ if (suid_dumpable == SUID_DUMP_ROOT &&
+ core_pattern[0] != '/' && core_pattern[0] != '|') {
+ pr_warn(
+"Unsafe core_pattern used with fs.suid_dumpable=2.\n"
+"Pipe handler or fully qualified core dump path required.\n"
+"Set kernel.core_pattern before fs.suid_dumpable.\n"
+ );
+ }
+}
+
+static int proc_dostring_coredump(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ int error = proc_dostring(table, write, buffer, lenp, ppos);
+
+ if (!error)
+ validate_coredump_safety();
+ return error;
+}
+
+static struct ctl_table coredump_sysctls[] = {
+ {
+ .procname = "core_uses_pid",
+ .data = &core_uses_pid,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "core_pattern",
+ .data = core_pattern,
+ .maxlen = CORENAME_MAX_SIZE,
+ .mode = 0644,
+ .proc_handler = proc_dostring_coredump,
+ },
+ {
+ .procname = "core_pipe_limit",
+ .data = &core_pipe_limit,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ { }
+};
+
+static int __init init_fs_coredump_sysctls(void)
+{
+ register_sysctl_init("kernel", coredump_sysctls);
+ return 0;
+}
+fs_initcall(init_fs_coredump_sysctls);
+#endif /* CONFIG_SYSCTL */
+
/*
* The purpose of always_dump_vma() is to make sure that special kernel mappings
* that are useful for post-mortem analysis are included in every core dump.
diff --git a/fs/dcache.c b/fs/dcache.c
index cf871a81f4fd..c84269c6e8bf 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -115,10 +115,13 @@ static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent,
return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT);
}
-
-/* Statistics gathering. */
-struct dentry_stat_t dentry_stat = {
- .age_limit = 45,
+struct dentry_stat_t {
+ long nr_dentry;
+ long nr_unused;
+ long age_limit; /* age in seconds */
+ long want_pages; /* pages requested by system */
+ long nr_negative; /* # of unused negative dentries */
+ long dummy; /* Reserved for future use */
};
static DEFINE_PER_CPU(long, nr_dentry);
@@ -126,6 +129,10 @@ static DEFINE_PER_CPU(long, nr_dentry_unused);
static DEFINE_PER_CPU(long, nr_dentry_negative);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+/* Statistics gathering. */
+static struct dentry_stat_t dentry_stat = {
+ .age_limit = 45,
+};
/*
* Here we resort to our own counters instead of using generic per-cpu counters
@@ -167,14 +174,32 @@ static long get_nr_dentry_negative(void)
return sum < 0 ? 0 : sum;
}
-int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
- size_t *lenp, loff_t *ppos)
+static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
dentry_stat.nr_unused = get_nr_dentry_unused();
dentry_stat.nr_negative = get_nr_dentry_negative();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
+
+static struct ctl_table fs_dcache_sysctls[] = {
+ {
+ .procname = "dentry-state",
+ .data = &dentry_stat,
+ .maxlen = 6*sizeof(long),
+ .mode = 0444,
+ .proc_handler = proc_nr_dentry,
+ },
+ { }
+};
+
+static int __init init_fs_dcache_sysctls(void)
+{
+ register_sysctl_init("fs", fs_dcache_sysctls);
+ return 0;
+}
+fs_initcall(init_fs_dcache_sysctls);
#endif
/*
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 06f4c5ae1451..e2daa940ebce 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -307,7 +307,7 @@ static void unlist_file(struct epitems_head *head)
static long long_zero;
static long long_max = LONG_MAX;
-struct ctl_table epoll_table[] = {
+static struct ctl_table epoll_table[] = {
{
.procname = "max_user_watches",
.data = &max_user_watches,
@@ -319,6 +319,13 @@ struct ctl_table epoll_table[] = {
},
{ }
};
+
+static void __init epoll_sysctls_init(void)
+{
+ register_sysctl("fs/epoll", epoll_table);
+}
+#else
+#define epoll_sysctls_init() do { } while (0)
#endif /* CONFIG_SYSCTL */
static const struct file_operations eventpoll_fops;
@@ -2378,6 +2385,7 @@ static int __init eventpoll_init(void)
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
+ epoll_sysctls_init();
ephead_cache = kmem_cache_create("ep_head",
sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
diff --git a/fs/exec.c b/fs/exec.c
index 3c3c366a9bcf..79f2c9483302 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -65,6 +65,7 @@
#include <linux/vmalloc.h>
#include <linux/io_uring.h>
#include <linux/syscall_user_dispatch.h>
+#include <linux/coredump.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -2099,3 +2100,37 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
argv, envp, flags);
}
#endif
+
+#ifdef CONFIG_SYSCTL
+
+static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+ if (!error)
+ validate_coredump_safety();
+ return error;
+}
+
+static struct ctl_table fs_exec_sysctls[] = {
+ {
+ .procname = "suid_dumpable",
+ .data = &suid_dumpable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax_coredump,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
+ { }
+};
+
+static int __init init_fs_exec_sysctls(void)
+{
+ register_sysctl_init("fs", fs_exec_sysctls);
+ return 0;
+}
+
+fs_initcall(init_fs_exec_sysctls);
+#endif /* CONFIG_SYSCTL */
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cf2fd9fc7d98..9f86dd947032 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2834,7 +2834,7 @@ out:
static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group;
if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
@@ -2845,7 +2845,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group;
++*pos;
@@ -2857,7 +2857,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group = (ext4_group_t) ((unsigned long) v);
int i;
int err, buddy_loaded = 0;
@@ -2985,7 +2985,7 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset)
static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos)
__acquires(&EXT4_SB(sb)->s_mb_rb_lock)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
unsigned long position;
read_lock(&EXT4_SB(sb)->s_mb_rb_lock);
@@ -2998,7 +2998,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock)
static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
unsigned long position;
++*pos;
@@ -3010,7 +3010,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof
static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned long position = ((unsigned long) v);
struct ext4_group_info *grp;
@@ -3058,7 +3058,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v)
__releases(&EXT4_SB(sb)->s_mb_rb_lock)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
read_unlock(&EXT4_SB(sb)->s_mb_rb_lock);
}
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 3db923403505..4cd62f1d848c 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -43,7 +43,6 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/cleancache.h>
#include "ext4.h"
@@ -350,11 +349,6 @@ int ext4_mpage_readpages(struct inode *inode,
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
- if (fully_mapped && blocks_per_page == 1 &&
- !PageUptodate(page) && cleancache_get_page(page) == 0) {
- SetPageUptodate(page);
- goto confused;
- }
/*
* This page will go to BIO. Do we need to send this
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index db9fe4843529..eee0d9ebfa6c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -39,7 +39,6 @@
#include <linux/log2.h>
#include <linux/crc16.h>
#include <linux/dax.h>
-#include <linux/cleancache.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
@@ -3149,8 +3148,6 @@ done:
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
-
- cleancache_init_fs(sb);
return err;
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0a1d236212f8..8c417864c66a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -18,7 +18,6 @@
#include <linux/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
-#include <linux/cleancache.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
#include <linux/iomap.h>
@@ -2035,12 +2034,6 @@ got_it:
block_nr = map->m_pblk + block_in_file - map->m_lblk;
SetPageMappedToDisk(page);
- if (!PageUptodate(page) && (!PageSwapCache(page) &&
- !cleancache_get_page(page))) {
- SetPageUptodate(page);
- goto confused;
- }
-
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
DATA_GENERIC_ENHANCE_READ)) {
ret = -EFSCORRUPTED;
@@ -2096,12 +2089,6 @@ submit_and_realloc:
ClearPageError(page);
*last_block_in_bio = block_nr;
goto out;
-confused:
- if (bio) {
- __submit_bio(F2FS_I_SB(inode), bio, DATA);
- bio = NULL;
- }
- unlock_page(page);
out:
*bio_ret = bio;
return ret;
diff --git a/fs/file_table.c b/fs/file_table.c
index 45437f8e1003..57edef16dce4 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -33,7 +33,7 @@
#include "internal.h"
/* sysctl tunables... */
-struct files_stat_struct files_stat = {
+static struct files_stat_struct files_stat = {
.max_files = NR_FILE
};
@@ -75,22 +75,53 @@ unsigned long get_max_files(void)
}
EXPORT_SYMBOL_GPL(get_max_files);
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+
/*
* Handle nr_files sysctl
*/
-#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-int proc_nr_files(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
+static int proc_nr_files(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
-#else
-int proc_nr_files(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
+
+static struct ctl_table fs_stat_sysctls[] = {
+ {
+ .procname = "file-nr",
+ .data = &files_stat,
+ .maxlen = sizeof(files_stat),
+ .mode = 0444,
+ .proc_handler = proc_nr_files,
+ },
+ {
+ .procname = "file-max",
+ .data = &files_stat.max_files,
+ .maxlen = sizeof(files_stat.max_files),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = SYSCTL_LONG_ZERO,
+ .extra2 = SYSCTL_LONG_MAX,
+ },
+ {
+ .procname = "nr_open",
+ .data = &sysctl_nr_open,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &sysctl_nr_open_min,
+ .extra2 = &sysctl_nr_open_max,
+ },
+ { }
+};
+
+static int __init init_fs_stat_sysctls(void)
{
- return -ENOSYS;
+ register_sysctl_init("fs", fs_stat_sysctls);
+ return 0;
}
+fs_initcall(init_fs_stat_sysctls);
#endif
static struct file *__alloc_file(int flags, const struct cred *cred)
diff --git a/fs/inode.c b/fs/inode.c
index 980e7b7a5460..63324df6fa27 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -67,11 +67,6 @@ const struct address_space_operations empty_aops = {
};
EXPORT_SYMBOL(empty_aops);
-/*
- * Statistics gathering..
- */
-struct inodes_stat_t inodes_stat;
-
static DEFINE_PER_CPU(unsigned long, nr_inodes);
static DEFINE_PER_CPU(unsigned long, nr_unused);
@@ -106,13 +101,43 @@ long get_nr_dirty_inodes(void)
* Handle nr_inode sysctl
*/
#ifdef CONFIG_SYSCTL
-int proc_nr_inodes(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
+/*
+ * Statistics gathering..
+ */
+static struct inodes_stat_t inodes_stat;
+
+static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
inodes_stat.nr_inodes = get_nr_inodes();
inodes_stat.nr_unused = get_nr_inodes_unused();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
+
+static struct ctl_table inodes_sysctls[] = {
+ {
+ .procname = "inode-nr",
+ .data = &inodes_stat,
+ .maxlen = 2*sizeof(long),
+ .mode = 0444,
+ .proc_handler = proc_nr_inodes,
+ },
+ {
+ .procname = "inode-state",
+ .data = &inodes_stat,
+ .maxlen = 7*sizeof(long),
+ .mode = 0444,
+ .proc_handler = proc_nr_inodes,
+ },
+ { }
+};
+
+static int __init init_fs_inode_sysctls(void)
+{
+ register_sysctl_init("fs", inodes_sysctls);
+ return 0;
+}
+early_initcall(init_fs_inode_sysctls);
#endif
static int no_open(struct inode *inode, struct file *file)
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0b86a4365b66..f13d548e4a7f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1212,7 +1212,7 @@ static const struct seq_operations jbd2_seq_info_ops = {
static int jbd2_seq_info_open(struct inode *inode, struct file *file)
{
- journal_t *journal = PDE_DATA(inode);
+ journal_t *journal = pde_data(inode);
struct jbd2_stats_proc_session *s;
int rc, size;
diff --git a/fs/locks.c b/fs/locks.c
index 0fca9d680978..8c6df10cd9ed 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -62,6 +62,7 @@
#include <linux/pid_namespace.h>
#include <linux/hashtable.h>
#include <linux/percpu.h>
+#include <linux/sysctl.h>
#define CREATE_TRACE_POINTS
#include <trace/events/filelock.h>
@@ -88,8 +89,37 @@ static int target_leasetype(struct file_lock *fl)
return fl->fl_type;
}
-int leases_enable = 1;
-int lease_break_time = 45;
+static int leases_enable = 1;
+static int lease_break_time = 45;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table locks_sysctls[] = {
+ {
+ .procname = "leases-enable",
+ .data = &leases_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#ifdef CONFIG_MMU
+ {
+ .procname = "lease-break-time",
+ .data = &lease_break_time,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif /* CONFIG_MMU */
+ {}
+};
+
+static int __init init_fs_locks_sysctls(void)
+{
+ register_sysctl_init("fs", locks_sysctls);
+ return 0;
+}
+early_initcall(init_fs_locks_sysctls);
+#endif /* CONFIG_SYSCTL */
/*
* The global file_lock_list is only used for displaying /proc/locks, so we
diff --git a/fs/mpage.c b/fs/mpage.c
index 334e7d09aa65..87f5cfef6caa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -29,7 +29,6 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/cleancache.h>
#include "internal.h"
/*
@@ -284,12 +283,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
SetPageMappedToDisk(page);
}
- if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
- cleancache_get_page(page) == 0) {
- SetPageUptodate(page);
- goto confused;
- }
-
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
diff --git a/fs/namei.c b/fs/namei.c
index d81f04f8d818..b867a92c078e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1020,10 +1020,60 @@ static inline void put_link(struct nameidata *nd)
path_put(&last->link);
}
-int sysctl_protected_symlinks __read_mostly = 0;
-int sysctl_protected_hardlinks __read_mostly = 0;
-int sysctl_protected_fifos __read_mostly;
-int sysctl_protected_regular __read_mostly;
+static int sysctl_protected_symlinks __read_mostly;
+static int sysctl_protected_hardlinks __read_mostly;
+static int sysctl_protected_fifos __read_mostly;
+static int sysctl_protected_regular __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table namei_sysctls[] = {
+ {
+ .procname = "protected_symlinks",
+ .data = &sysctl_protected_symlinks,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
+ .procname = "protected_hardlinks",
+ .data = &sysctl_protected_hardlinks,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
+ .procname = "protected_fifos",
+ .data = &sysctl_protected_fifos,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
+ {
+ .procname = "protected_regular",
+ .data = &sysctl_protected_regular,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
+ { }
+};
+
+static int __init init_fs_namei_sysctls(void)
+{
+ register_sysctl_init("fs", namei_sysctls);
+ return 0;
+}
+fs_initcall(init_fs_namei_sysctls);
+
+#endif /* CONFIG_SYSCTL */
/**
* may_follow_link - Check symlink following for unsafe situations
diff --git a/fs/namespace.c b/fs/namespace.c
index dc31ad6b370f..40b994a29e90 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -37,7 +37,7 @@
#include "internal.h"
/* Maximum number of mounts in a mount namespace */
-unsigned int sysctl_mount_max __read_mostly = 100000;
+static unsigned int sysctl_mount_max __read_mostly = 100000;
static unsigned int m_hash_mask __read_mostly;
static unsigned int m_hash_shift __read_mostly;
@@ -4620,3 +4620,25 @@ const struct proc_ns_operations mntns_operations = {
.install = mntns_install,
.owner = mntns_owner,
};
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table fs_namespace_sysctls[] = {
+ {
+ .procname = "mount-max",
+ .data = &sysctl_mount_max,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ONE,
+ },
+ { }
+};
+
+static int __init init_fs_namespace_sysctls(void)
+{
+ register_sysctl_init("fs", fs_namespace_sysctls);
+ return 0;
+}
+fs_initcall(init_fs_namespace_sysctls);
+
+#endif /* CONFIG_SYSCTL */
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index d5ebebb034ff..829dd4a61b66 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -19,7 +19,25 @@
#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
-int dir_notify_enable __read_mostly = 1;
+static int dir_notify_enable __read_mostly = 1;
+#ifdef CONFIG_SYSCTL
+static struct ctl_table dnotify_sysctls[] = {
+ {
+ .procname = "dir-notify-enable",
+ .data = &dir_notify_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {}
+};
+static void __init dnotify_sysctl_init(void)
+{
+ register_sysctl_init("fs", dnotify_sysctls);
+}
+#else
+#define dnotify_sysctl_init() do { } while (0)
+#endif
static struct kmem_cache *dnotify_struct_cache __read_mostly;
static struct kmem_cache *dnotify_mark_cache __read_mostly;
@@ -386,6 +404,7 @@ static int __init dnotify_init(void)
dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops);
if (IS_ERR(dnotify_group))
panic("unable to allocate fsnotify group for dnotify\n");
+ dnotify_sysctl_init();
return 0;
}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 73a3e939c921..73b1615f9d96 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -59,7 +59,7 @@ static int fanotify_max_queued_events __read_mostly;
static long ft_zero = 0;
static long ft_int_max = INT_MAX;
-struct ctl_table fanotify_table[] = {
+static struct ctl_table fanotify_table[] = {
{
.procname = "max_user_groups",
.data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
@@ -88,6 +88,13 @@ struct ctl_table fanotify_table[] = {
},
{ }
};
+
+static void __init fanotify_sysctls_init(void)
+{
+ register_sysctl("fs/fanotify", fanotify_table);
+}
+#else
+#define fanotify_sysctls_init() do { } while (0)
#endif /* CONFIG_SYSCTL */
/*
@@ -1743,6 +1750,7 @@ static int __init fanotify_user_setup(void)
init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
FANOTIFY_DEFAULT_MAX_GROUPS;
init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks;
+ fanotify_sysctls_init();
return 0;
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 29fca3284bb5..54583f62dc44 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
static long it_zero = 0;
static long it_int_max = INT_MAX;
-struct ctl_table inotify_table[] = {
+static struct ctl_table inotify_table[] = {
{
.procname = "max_user_instances",
.data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
@@ -87,6 +87,14 @@ struct ctl_table inotify_table[] = {
},
{ }
};
+
+static void __init inotify_sysctls_init(void)
+{
+ register_sysctl("fs/inotify", inotify_table);
+}
+
+#else
+#define inotify_sysctls_init() do { } while (0)
#endif /* CONFIG_SYSCTL */
static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
@@ -849,6 +857,7 @@ static int __init inotify_user_setup(void)
inotify_max_queued_events = 16384;
init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max;
+ inotify_sysctls_init();
return 0;
}
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 8aaec7e0804e..fb825059d488 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -11,7 +11,6 @@
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
-#include <linux/cleancache.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 16f1bfc407f2..731558a6f27d 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -672,31 +672,8 @@ static struct ctl_table ocfs2_mod_table[] = {
{ }
};
-static struct ctl_table ocfs2_kern_table[] = {
- {
- .procname = "ocfs2",
- .data = NULL,
- .maxlen = 0,
- .mode = 0555,
- .child = ocfs2_mod_table
- },
- { }
-};
-
-static struct ctl_table ocfs2_root_table[] = {
- {
- .procname = "fs",
- .data = NULL,
- .maxlen = 0,
- .mode = 0555,
- .child = ocfs2_kern_table
- },
- { }
-};
-
static struct ctl_table_header *ocfs2_table_header;
-
/*
* Initialization
*/
@@ -705,7 +682,7 @@ static int __init ocfs2_stack_glue_init(void)
{
strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB);
- ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
+ ocfs2_table_header = register_sysctl("fs/ocfs2", ocfs2_mod_table);
if (!ocfs2_table_header) {
printk(KERN_ERR
"ocfs2 stack glue: unable to register sysctl\n");
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 1286b88b6fa1..2772dec9dcea 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -25,7 +25,6 @@
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/quotaops.h>
-#include <linux/cleancache.h>
#include <linux/signal.h>
#define CREATE_TRACE_POINTS
@@ -2283,7 +2282,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
mlog_errno(status);
goto bail;
}
- cleancache_init_shared_fs(sb);
osb->ocfs2_wq = alloc_ordered_workqueue("ocfs2_wq", WQ_MEM_RECLAIM);
if (!osb->ocfs2_wq) {
diff --git a/fs/pipe.c b/fs/pipe.c
index 6d4342bad9f1..cc28623a67b6 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -25,6 +25,7 @@
#include <linux/fcntl.h>
#include <linux/memcontrol.h>
#include <linux/watch_queue.h>
+#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
@@ -50,13 +51,13 @@
* The max size that a non-root user is allowed to grow the pipe. Can
* be set by root in /proc/sys/fs/pipe-max-size
*/
-unsigned int pipe_max_size = 1048576;
+static unsigned int pipe_max_size = 1048576;
/* Maximum allocatable pages per user. Hard limit is unset by default, soft
* matches default values.
*/
-unsigned long pipe_user_pages_hard;
-unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+static unsigned long pipe_user_pages_hard;
+static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
/*
* We use head and tail indices that aren't masked off, except at the point of
@@ -1428,6 +1429,60 @@ static struct file_system_type pipe_fs_type = {
.kill_sb = kill_anon_super,
};
+#ifdef CONFIG_SYSCTL
+static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data)
+{
+ if (write) {
+ unsigned int val;
+
+ val = round_pipe_size(*lvalp);
+ if (val == 0)
+ return -EINVAL;
+
+ *valp = val;
+ } else {
+ unsigned int val = *valp;
+ *lvalp = (unsigned long) val;
+ }
+
+ return 0;
+}
+
+static int proc_dopipe_max_size(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_douintvec(table, write, buffer, lenp, ppos,
+ do_proc_dopipe_max_size_conv, NULL);
+}
+
+static struct ctl_table fs_pipe_sysctls[] = {
+ {
+ .procname = "pipe-max-size",
+ .data = &pipe_max_size,
+ .maxlen = sizeof(pipe_max_size),
+ .mode = 0644,
+ .proc_handler = proc_dopipe_max_size,
+ },
+ {
+ .procname = "pipe-user-pages-hard",
+ .data = &pipe_user_pages_hard,
+ .maxlen = sizeof(pipe_user_pages_hard),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ {
+ .procname = "pipe-user-pages-soft",
+ .data = &pipe_user_pages_soft,
+ .maxlen = sizeof(pipe_user_pages_soft),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ { }
+};
+#endif
+
static int __init init_pipe_fs(void)
{
int err = register_filesystem(&pipe_fs_type);
@@ -1439,6 +1494,9 @@ static int __init init_pipe_fs(void)
unregister_filesystem(&pipe_fs_type);
}
}
+#ifdef CONFIG_SYSCTL
+ register_sysctl_init("fs", fs_pipe_sysctls);
+#endif
return err;
}
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 5b78739e60e4..f2132407e133 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -791,12 +791,6 @@ void proc_remove(struct proc_dir_entry *de)
}
EXPORT_SYMBOL(proc_remove);
-void *PDE_DATA(const struct inode *inode)
-{
- return __PDE_DATA(inode);
-}
-EXPORT_SYMBOL(PDE_DATA);
-
/*
* Pull a user buffer into memory and pass it to the file's write handler if
* one is supplied. The ->write() method is permitted to modify the
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 599eb724ff2d..f84355c5a36d 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -650,6 +650,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
return NULL;
}
+ inode->i_private = de->data;
inode->i_ino = de->low_ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
PROC_I(inode)->pde = de;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 03415f3fb3a8..06a80f78433d 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -115,11 +115,6 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode)
return PROC_I(inode)->pde;
}
-static inline void *__PDE_DATA(const struct inode *inode)
-{
- return PDE(inode)->data;
-}
-
static inline struct pid *proc_pid(const struct inode *inode)
{
return PROC_I(inode)->pid;
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 39b823ab2564..e1cfeda397f3 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -138,7 +138,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data);
* @parent: The parent directory in which to create.
* @ops: The seq_file ops with which to read the file.
* @write: The write method with which to 'modify' the file.
- * @data: Data for retrieval by PDE_DATA().
+ * @data: Data for retrieval by pde_data().
*
* Create a network namespaced proc file in the @parent directory with the
* specified @name and @mode that allows reading of a file that displays a
@@ -153,7 +153,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data);
* modified by the @write function. @write should return 0 on success.
*
* The @data value is accessible from the @show and @write functions by calling
- * PDE_DATA() on the file inode. The network namespace must be accessed by
+ * pde_data() on the file inode. The network namespace must be accessed by
* calling seq_file_net() on the seq_file struct.
*/
struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode,
@@ -230,7 +230,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single);
* @parent: The parent directory in which to create.
* @show: The seqfile show method with which to read the file.
* @write: The write method with which to 'modify' the file.
- * @data: Data for retrieval by PDE_DATA().
+ * @data: Data for retrieval by pde_data().
*
* Create a network-namespaced proc file in the @parent directory with the
* specified @name and @mode that allows reading of a file that displays a
@@ -245,7 +245,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single);
* modified by the @write function. @write should return 0 on success.
*
* The @data value is accessible from the @show and @write functions by calling
- * PDE_DATA() on the file inode. The network namespace must be accessed by
+ * pde_data() on the file inode. The network namespace must be accessed by
* calling seq_file_single_net() on the seq_file struct.
*/
struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode,
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 389e1e42e7d9..7d9cfc730bd4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -16,6 +16,7 @@
#include <linux/module.h>
#include <linux/bpf-cgroup.h>
#include <linux/mount.h>
+#include <linux/kmemleak.h>
#include "internal.h"
static const struct dentry_operations proc_sys_dentry_operations;
@@ -25,15 +26,32 @@ static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;
/* shared constants to be used in various sysctls */
-const int sysctl_vals[] = { 0, 1, INT_MAX };
+const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX, 65535 };
EXPORT_SYMBOL(sysctl_vals);
+const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX };
+EXPORT_SYMBOL_GPL(sysctl_long_vals);
+
/* Support for permanently empty directories */
struct ctl_table sysctl_mount_point[] = {
{ }
};
+/**
+ * register_sysctl_mount_point() - registers a sysctl mount point
+ * @path: path for the mount point
+ *
+ * Used to create a permanently empty directory to serve as mount point.
+ * There are some subtle but important permission checks this allows in the
+ * case of unprivileged mounts.
+ */
+struct ctl_table_header *register_sysctl_mount_point(const char *path)
+{
+ return register_sysctl(path, sysctl_mount_point);
+}
+EXPORT_SYMBOL(register_sysctl_mount_point);
+
static bool is_empty_dir(struct ctl_table_header *head)
{
return head->ctl_table[0].child == sysctl_mount_point;
@@ -1383,6 +1401,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab
}
EXPORT_SYMBOL(register_sysctl);
+/**
+ * __register_sysctl_init() - register sysctl table to path
+ * @path: path name for sysctl base
+ * @table: This is the sysctl table that needs to be registered to the path
+ * @table_name: The name of sysctl table, only used for log printing when
+ * registration fails
+ *
+ * The sysctl interface is used by userspace to query or modify at runtime
+ * a predefined value set on a variable. These variables however have default
+ * values pre-set. Code which depends on these variables will always work even
+ * if register_sysctl() fails. If register_sysctl() fails you'd just loose the
+ * ability to query or modify the sysctls dynamically at run time. Chances of
+ * register_sysctl() failing on init are extremely low, and so for both reasons
+ * this function does not return any error as it is used by initialization code.
+ *
+ * Context: Can only be called after your respective sysctl base path has been
+ * registered. So for instance, most base directories are registered early on
+ * init before init levels are processed through proc_sys_init() and
+ * sysctl_init_bases().
+ */
+void __init __register_sysctl_init(const char *path, struct ctl_table *table,
+ const char *table_name)
+{
+ struct ctl_table_header *hdr = register_sysctl(path, table);
+
+ if (unlikely(!hdr)) {
+ pr_err("failed when register_sysctl %s to %s\n", table_name, path);
+ return;
+ }
+ kmemleak_not_leak(hdr);
+}
+
static char *append_path(const char *path, char *pos, const char *name)
{
int namelen;
@@ -1596,6 +1646,15 @@ struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
}
EXPORT_SYMBOL(register_sysctl_table);
+int __register_sysctl_base(struct ctl_table *base_table)
+{
+ struct ctl_table_header *hdr;
+
+ hdr = register_sysctl_table(base_table);
+ kmemleak_not_leak(hdr);
+ return 0;
+}
+
static void put_links(struct ctl_table_header *header)
{
struct ctl_table_set *root_set = &sysctl_table_root.default_set;
@@ -1709,7 +1768,7 @@ int __init proc_sys_init(void)
proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations;
proc_sys_root->nlink = 0;
- return sysctl_init();
+ return sysctl_init_bases();
}
struct sysctl_alias {
diff --git a/fs/super.c b/fs/super.c
index a6405d44d4ca..7af820ba5ad5 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -31,7 +31,6 @@
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
-#include <linux/cleancache.h>
#include <linux/fscrypt.h>
#include <linux/fsnotify.h>
#include <linux/lockdep.h>
@@ -260,7 +259,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
s->s_time_gran = 1000000000;
s->s_time_min = TIME64_MIN;
s->s_time_max = TIME64_MAX;
- s->cleancache_poolid = CLEANCACHE_NO_POOL;
s->s_shrink.seeks = DEFAULT_SEEKS;
s->s_shrink.scan_objects = super_cache_scan;
@@ -330,7 +328,6 @@ void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
- cleancache_invalidate_fs(s);
unregister_shrinker(&s->s_shrink);
fs->kill_sb(s);
diff --git a/fs/sysctls.c b/fs/sysctls.c
new file mode 100644
index 000000000000..c701273c9432
--- /dev/null
+++ b/fs/sysctls.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * /proc/sys/fs shared sysctls
+ *
+ * These sysctls are shared between different filesystems.
+ */
+#include <linux/init.h>
+#include <linux/sysctl.h>
+
+static struct ctl_table fs_shared_sysctls[] = {
+ {
+ .procname = "overflowuid",
+ .data = &fs_overflowuid,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_MAXOLDUID,
+ },
+ {
+ .procname = "overflowgid",
+ .data = &fs_overflowgid,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_MAXOLDUID,
+ },
+ { }
+};
+
+DECLARE_SYSCTL_BASE(fs, fs_shared_sysctls);
+
+static int __init init_fs_sysctls(void)
+{
+ return register_sysctl_base(fs);
+}
+
+early_initcall(init_fs_sysctls);