sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 190 insertions, 0 deletions

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
new file mode 100644
index 000000000..924726dcc
--- /dev/null
+++ b/fs/ext4/fsync.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/fsync.c
+ *
+ *  Copyright (C) 1993  Stephen Tweedie (sct@redhat.com)
+ *  from
+ *  Copyright (C) 1992  Remy Card (card@masi.ibp.fr)
+ *                      Laboratoire MASI - Institut Blaise Pascal
+ *                      Universite Pierre et Marie Curie (Paris VI)
+ *  from
+ *  linux/fs/minix/truncate.c   Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4fs fsync primitive
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ *  Removed unnecessary code duplication for little endian machines
+ *  and excessive __inline__s.
+ *        Andi Kleen, 1997
+ *
+ * Major simplications and cleanup - we only need to do the metadata, because
+ * we can depend on generic_block_fdatasync() to sync the data blocks.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+
+#include <trace/events/ext4.h>
+
+/*
+ * If we're not journaling and this is a just-created file, we have to
+ * sync our parent directory (if it was freshly created) since
+ * otherwise it will only be written by writeback, leaving a huge
+ * window during which a crash may lose the file.  This may apply for
+ * the parent directory's parent as well, and so on recursively, if
+ * they are also freshly created.
+ */
+static int ext4_sync_parent(struct inode *inode)
+{
+	struct dentry *dentry, *next;
+	int ret = 0;
+
+	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
+		return 0;
+	dentry = d_find_any_alias(inode);
+	if (!dentry)
+		return 0;
+	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
+
+		next = dget_parent(dentry);
+		dput(dentry);
+		dentry = next;
+		inode = dentry->d_inode;
+
+		/*
+		 * The directory inode may have gone through rmdir by now. But
+		 * the inode itself and its blocks are still allocated (we hold
+		 * a reference to the inode via its dentry), so it didn't go
+		 * through ext4_evict_inode()) and so we are safe to flush
+		 * metadata blocks and the inode.
+		 */
+		ret = mmb_sync(&EXT4_I(inode)->i_metadata_bhs);
+		if (ret)
+			break;
+		ret = sync_inode_metadata(inode, 1);
+		if (ret)
+			break;
+	}
+	dput(dentry);
+	return ret;
+}
+
+static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
+				int datasync, bool *needs_barrier)
+{
+	struct inode *inode = file->f_inode;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = 0,
+	};
+	int ret;
+
+	ret = mmb_fsync_noflush(file, &EXT4_I(inode)->i_metadata_bhs,
+				start, end, datasync);
+	if (ret)
+		return ret;
+
+	/* Force writeout of inode table buffer to disk */
+	ret = ext4_write_inode(inode, &wbc);
+	if (ret)
+		return ret;
+
+	ret = ext4_sync_parent(inode);
+
+	if (test_opt(inode->i_sb, BARRIER))
+		*needs_barrier = true;
+
+	return ret;
+}
+
+static int ext4_fsync_journal(struct inode *inode, bool datasync,
+			     bool *needs_barrier)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+	tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+
+	/*
+	 * Fastcommit does not really support fsync on directories or other
+	 * special files. Force a full commit.
+	 */
+	if (!S_ISREG(inode->i_mode))
+		return ext4_force_commit(inode->i_sb);
+
+	if (journal->j_flags & JBD2_BARRIER &&
+	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+		*needs_barrier = true;
+
+	return ext4_fc_commit(journal, commit_tid);
+}
+
+/*
+ * akpm: A new design for ext4_sync_file().
+ *
+ * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
+ * There cannot be a transaction open by this task.
+ * Another task could have dirtied this inode.  Its data can be in any
+ * state in the journalling system.
+ *
+ * What we do is just kick off a commit and wait on it.  This will snapshot the
+ * inode to disk.
+ */
+int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret = 0, err;
+	bool needs_barrier = false;
+	struct inode *inode = file->f_mapping->host;
+
+	ret = ext4_emergency_state(inode->i_sb);
+	if (unlikely(ret))
+		return ret;
+
+	ASSERT(ext4_journal_current_handle() == NULL);
+
+	trace_ext4_sync_file_enter(file, datasync);
+
+	if (sb_rdonly(inode->i_sb))
+		goto out;
+
+	if (!EXT4_SB(inode->i_sb)->s_journal) {
+		ret = ext4_fsync_nojournal(file, start, end, datasync,
+					   &needs_barrier);
+		if (needs_barrier)
+			goto issue_flush;
+		goto out;
+	}
+
+	ret = file_write_and_wait_range(file, start, end);
+	if (ret)
+		goto out;
+
+	/*
+	 *  The caller's filemap_fdatawrite()/wait will sync the data.
+	 *  Metadata is in the journal, we wait for proper transaction to
+	 *  commit here.
+	 */
+	ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
+
+issue_flush:
+	if (needs_barrier) {
+		err = blkdev_issue_flush(inode->i_sb->s_bdev);
+		if (!ret)
+			ret = err;
+	}
+out:
+	err = file_check_and_advance_wb_err(file);
+	if (ret == 0)
+		ret = err;
+	trace_ext4_sync_file_exit(inode, ret);
+	return ret;
+}