fs: icache RCU free inodes
RCU free the struct inode. This will allow:
- Subsequent store-free path walking patch. The inode must be consulted for
permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
to take i_lock no longer need to take sb_inode_list_lock to walk the list in
the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
page lock to follow page->mapping.
The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.
In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.
The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
diff --git a/net/socket.c b/net/socket.c
index 088fb3f..97fff3a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -262,20 +262,20 @@
}
-static void wq_free_rcu(struct rcu_head *head)
+static void sock_free_rcu(struct rcu_head *head)
{
- struct socket_wq *wq = container_of(head, struct socket_wq, rcu);
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ struct socket_alloc *ei = container_of(inode, struct socket_alloc,
+ vfs_inode);
- kfree(wq);
+ kfree(ei->socket.wq);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(sock_inode_cachep, ei);
}
static void sock_destroy_inode(struct inode *inode)
{
- struct socket_alloc *ei;
-
- ei = container_of(inode, struct socket_alloc, vfs_inode);
- call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
- kmem_cache_free(sock_inode_cachep, ei);
+ call_rcu(&inode->i_rcu, sock_free_rcu);
}
static void init_once(void *foo)
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index a0dc1a8..2899fe2 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -162,9 +162,17 @@
}
static void
+rpc_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(rpc_inode_cachep, RPC_I(inode));
+}
+
+static void
rpc_destroy_inode(struct inode *inode)
{
- kmem_cache_free(rpc_inode_cachep, RPC_I(inode));
+ call_rcu(&inode->i_rcu, rpc_i_callback);
}
static int