Merge branch 'for-6.0/dax' into libnvdimm-fixes

Pick up another "Soft Reservation" fix for v6.0-final on top of some
straggling nvdimm fixes that missed v5.19.

1 files changed, 58 insertions, 1 deletions

diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index e2ae15a6225e..367044d7708c 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -18,6 +18,7 @@
 #include <linux/uidgid.h>
 #include <linux/wait.h>
 #include <linux/rwsem.h>
+#include <linux/cache.h>
 
 struct file;
 struct dentry;
@@ -34,6 +35,62 @@ struct kernfs_fs_context;
 struct kernfs_open_node;
 struct kernfs_iattrs;
 
+/*
+ * NR_KERNFS_LOCK_BITS determines size (NR_KERNFS_LOCKS) of hash
+ * table of locks.
+ * Having a small hash table would impact scalability, since
+ * more and more kernfs_node objects will end up using same lock
+ * and having a very large hash table would waste memory.
+ *
+ * At the moment size of hash table of locks is being set based on
+ * the number of CPUs as follows:
+ *
+ * NR_CPU      NR_KERNFS_LOCK_BITS      NR_KERNFS_LOCKS
+ *   1                  1                       2
+ *  2-3                 2                       4
+ *  4-7                 4                       16
+ *  8-15                6                       64
+ *  16-31               8                       256
+ *  32 and more         10                      1024
+ *
+ * The above relation between NR_CPU and number of locks is based
+ * on some internal experimentation which involved booting qemu
+ * with different values of smp, performing some sysfs operations
+ * on all CPUs and observing how increase in number of locks impacts
+ * completion time of these sysfs operations on each CPU.
+ */
+#ifdef CONFIG_SMP
+#define NR_KERNFS_LOCK_BITS (2 * (ilog2(NR_CPUS < 32 ? NR_CPUS : 32)))
+#else
+#define NR_KERNFS_LOCK_BITS     1
+#endif
+
+#define NR_KERNFS_LOCKS     (1 << NR_KERNFS_LOCK_BITS)
+
+/*
+ * There's one kernfs_open_file for each open file and one kernfs_open_node
+ * for each kernfs_node with one or more open files.
+ *
+ * filp->private_data points to seq_file whose ->private points to
+ * kernfs_open_file.
+ *
+ * kernfs_open_files are chained at kernfs_open_node->files, which is
+ * protected by kernfs_global_locks.open_file_mutex[i].
+ *
+ * To reduce possible contention in sysfs access, arising due to single
+ * locks, use an array of locks (e.g. open_file_mutex) and use kernfs_node
+ * object address as hash keys to get the index of these locks.
+ *
+ * Hashed mutexes are safe to use here because operations using these don't
+ * rely on global exclusion.
+ *
+ * In future we intend to replace other global locks with hashed ones as well.
+ * kernfs_global_locks acts as a holder for all such hash tables.
+ */
+struct kernfs_global_locks {
+	struct mutex open_file_mutex[NR_KERNFS_LOCKS];
+};
+
 enum kernfs_node_type {
 	KERNFS_DIR		= 0x0001,
 	KERNFS_FILE		= 0x0002,
@@ -114,7 +171,7 @@ struct kernfs_elem_symlink {
 
 struct kernfs_elem_attr {
 	const struct kernfs_ops	*ops;
-	struct kernfs_open_node	*open;
+	struct kernfs_open_node __rcu	*open;
 	loff_t			size;
 	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
 };