get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
- /* per fileystem reservation list head & lock */
+ /* per filesystem reservation list head & lock */
spin_lock_init(&sbi->s_rsv_window_lock);
sbi->s_rsv_window_root = RB_ROOT;
/*
struct super_block *sb = dentry->d_sb;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
- u64 fsid;
spin_lock(&sbi->s_lock);
buf->f_ffree = ext2_count_free_inodes(sb);
es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT2_NAME_LEN;
- fsid = le64_to_cpup((void *)es->s_uuid) ^
- le64_to_cpup((void *)es->s_uuid + sizeof(u64));
- buf->f_fsid = u64_to_fsid(fsid);
+ buf->f_fsid = uuid_to_fsid(es->s_uuid);
spin_unlock(&sbi->s_lock);
return 0;
}
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
percpu_free_rwsem(&sbi->s_writepages_rwsem);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
if (!err)
+ err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
+ GFP_KERNEL);
+ if (!err)
err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
if (err) {
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
percpu_free_rwsem(&sbi->s_writepages_rwsem);
failed_mount5:
ext4_ext_release(sb);
failed_mount3a:
ext4_es_unregister_shrinker(sbi);
failed_mount3:
- del_timer_sync(&sbi->s_err_report);
flush_work(&sbi->s_error_work);
+ del_timer_sync(&sbi->s_err_report);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
ext4_fsblk_t overhead = 0, resv_blocks;
- u64 fsid;
s64 bfree;
resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters));
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
buf->f_namelen = EXT4_NAME_LEN;
- fsid = le64_to_cpup((void *)es->s_uuid) ^
- le64_to_cpup((void *)es->s_uuid + sizeof(u64));
- buf->f_fsid = u64_to_fsid(fsid);
+ buf->f_fsid = uuid_to_fsid(es->s_uuid);
#ifdef CONFIG_QUOTA
if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) &&
return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
}
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *span)
+{
+ struct inode *inode = file_inode(swap_file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+ if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
+ zonefs_err(inode->i_sb,
+ "swap file: not a conventional zone file\n");
+ return -EINVAL;
+ }
+
+ return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+}
+
static const struct address_space_operations zonefs_file_aops = {
.readpage = zonefs_readpage,
.readahead = zonefs_readahead,
.is_partially_uptodate = iomap_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.direct_IO = noop_direct_IO,
+ .swap_activate = zonefs_swap_activate,
};
static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
}
/*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+ loff_t count)
+{
+ struct inode *inode = file_inode(file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ loff_t limit = rlimit(RLIMIT_FSIZE);
+ loff_t max_size = zi->i_max_size;
+
+ if (limit != RLIM_INFINITY) {
+ if (pos >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ return -EFBIG;
+ }
+ count = min(count, limit - pos);
+ }
+
+ if (!(file->f_flags & O_LARGEFILE))
+ max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+ if (unlikely(pos >= max_size))
+ return -EFBIG;
+
+ return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ loff_t count;
+
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
+
+ if (!iov_iter_count(from))
+ return 0;
+
+ if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+ return -EINVAL;
+
+ if (iocb->ki_flags & IOCB_APPEND) {
+ if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+ return -EINVAL;
+ mutex_lock(&zi->i_truncate_mutex);
+ iocb->ki_pos = zi->i_wpoffset;
+ mutex_unlock(&zi->i_truncate_mutex);
+ }
+
+ count = zonefs_write_check_limits(file, iocb->ki_pos,
+ iov_iter_count(from));
+ if (count < 0)
+ return count;
+
+ iov_iter_truncate(from, count);
+ return iov_iter_count(from);
+}
+
+/*
* Handle direct writes. For sequential zone files, this is the only possible
* write path. For these files, check that the user is issuing writes
* sequentially from the end of the file. This code assumes that the block layer
struct super_block *sb = inode->i_sb;
bool sync = is_sync_kiocb(iocb);
bool append = false;
- size_t count;
- ssize_t ret;
+ ssize_t ret, count;
/*
* For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
inode_lock(inode);
}
- ret = generic_write_checks(iocb, from);
- if (ret <= 0)
+ count = zonefs_write_checks(iocb, from);
+ if (count <= 0) {
+ ret = count;
goto inode_unlock;
-
- iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
- count = iov_iter_count(from);
+ }
if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
ret = -EINVAL;
inode_lock(inode);
}
- ret = generic_write_checks(iocb, from);
+ ret = zonefs_write_checks(iocb, from);
if (ret <= 0)
goto inode_unlock;
- iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-
ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
if (ret > 0)
iocb->ki_pos += ret;
mutex_lock(&zi->i_truncate_mutex);
- zi->i_wr_refcnt++;
- if (zi->i_wr_refcnt == 1) {
-
+ if (!zi->i_wr_refcnt) {
if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
atomic_dec(&sbi->s_open_zones);
ret = -EBUSY;
if (i_size_read(inode) < zi->i_max_size) {
ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
if (ret) {
- zi->i_wr_refcnt--;
atomic_dec(&sbi->s_open_zones);
goto unlock;
}
}
}
+ zi->i_wr_refcnt++;
+
unlock:
mutex_unlock(&zi->i_truncate_mutex);
struct super_block *sb = dentry->d_sb;
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
enum zonefs_ztype t;
- u64 fsid;
buf->f_type = ZONEFS_MAGIC;
buf->f_bsize = sb->s_blocksize;
spin_unlock(&sbi->s_lock);
- fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^
- le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64));
- buf->f_fsid = u64_to_fsid(fsid);
+ buf->f_fsid = uuid_to_fsid(sbi->s_uuid.b);
return 0;
}
UCOUNT_INOTIFY_INSTANCES,
UCOUNT_INOTIFY_WATCHES,
#endif
+ #ifdef CONFIG_FANOTIFY
+ UCOUNT_FANOTIFY_GROUPS,
+ UCOUNT_FANOTIFY_MARKS,
+ #endif
UCOUNT_COUNTS,
};
kgid_t group;
struct ns_common ns;
unsigned long flags;
+ /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP
+ * in its effective capability set at the child ns creation time. */
+ bool parent_could_setfcap;
#ifdef CONFIG_KEYS
/* List of joinable keyrings in this namespace. Modification access of
#ifdef CONFIG_INOTIFY_USER
#include <linux/inotify.h>
#endif
+ #ifdef CONFIG_FANOTIFY
+ #include <linux/fanotify.h>
+ #endif
#ifdef CONFIG_PROC_SYSCTL
int sysctl_legacy_va_layout;
#endif
-#ifdef CONFIG_SCHED_DEBUG
-static int min_sched_granularity_ns = 100000; /* 100 usecs */
-static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */
-static int min_wakeup_granularity_ns; /* 0 usecs */
-static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */
-#ifdef CONFIG_SMP
-static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
-static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-#endif /* CONFIG_SMP */
-#endif /* CONFIG_SCHED_DEBUG */
-
#ifdef CONFIG_COMPACTION
static int min_extfrag_threshold;
static int max_extfrag_threshold = 1000;
.mode = 0644,
.proc_handler = proc_dointvec,
},
-#ifdef CONFIG_SCHED_DEBUG
- {
- .procname = "sched_min_granularity_ns",
- .data = &sysctl_sched_min_granularity,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_proc_update_handler,
- .extra1 = &min_sched_granularity_ns,
- .extra2 = &max_sched_granularity_ns,
- },
- {
- .procname = "sched_latency_ns",
- .data = &sysctl_sched_latency,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_proc_update_handler,
- .extra1 = &min_sched_granularity_ns,
- .extra2 = &max_sched_granularity_ns,
- },
- {
- .procname = "sched_wakeup_granularity_ns",
- .data = &sysctl_sched_wakeup_granularity,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_proc_update_handler,
- .extra1 = &min_wakeup_granularity_ns,
- .extra2 = &max_wakeup_granularity_ns,
- },
-#ifdef CONFIG_SMP
- {
- .procname = "sched_tunable_scaling",
- .data = &sysctl_sched_tunable_scaling,
- .maxlen = sizeof(enum sched_tunable_scaling),
- .mode = 0644,
- .proc_handler = sched_proc_update_handler,
- .extra1 = &min_sched_tunable_scaling,
- .extra2 = &max_sched_tunable_scaling,
- },
- {
- .procname = "sched_migration_cost_ns",
- .data = &sysctl_sched_migration_cost,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sched_nr_migrate",
- .data = &sysctl_sched_nr_migrate,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
#ifdef CONFIG_SCHEDSTATS
{
.procname = "sched_schedstats",
.extra2 = SYSCTL_ONE,
},
#endif /* CONFIG_SCHEDSTATS */
-#endif /* CONFIG_SMP */
#ifdef CONFIG_NUMA_BALANCING
{
- .procname = "numa_balancing_scan_delay_ms",
- .data = &sysctl_numa_balancing_scan_delay,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "numa_balancing_scan_period_min_ms",
- .data = &sysctl_numa_balancing_scan_period_min,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "numa_balancing_scan_period_max_ms",
- .data = &sysctl_numa_balancing_scan_period_max,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "numa_balancing_scan_size_mb",
- .data = &sysctl_numa_balancing_scan_size,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ONE,
- },
- {
.procname = "numa_balancing",
.data = NULL, /* filled in by handler */
.maxlen = sizeof(unsigned int),
.extra2 = SYSCTL_ONE,
},
#endif /* CONFIG_NUMA_BALANCING */
-#endif /* CONFIG_SCHED_DEBUG */
{
.procname = "sched_rt_period_us",
.data = &sysctl_sched_rt_period,
.mode = 0555,
.child = inotify_table,
},
- #endif
+ #endif
+ #ifdef CONFIG_FANOTIFY
+ {
+ .procname = "fanotify",
+ .mode = 0555,
+ .child = fanotify_table,
+ },
+ #endif
#ifdef CONFIG_EPOLL
{
.procname = "epoll",