From badf16621c1f9d1ac753be056fce11b43d6e0be5 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 9 Sep 2005 13:04:10 -0700 Subject: [PATCH] files: break up files struct In order for the RCU to work, the file table array, sets and their sizes must be updated atomically. Instead of ensuring this through too many memory barriers, we put the arrays and their sizes in a separate structure. This patch takes the first step of putting the file table elements in a separate structure fdtable that is embedded withing files_struct. It also changes all the users to refer to the file table using files_fdtable() macro. Subsequent applciation of RCU becomes easier after this. Signed-off-by: Dipankar Sarma Signed-Off-By: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 5b0fb9f09f2..83beb1e93b1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -368,17 +368,19 @@ EXPORT_SYMBOL(daemonize); static inline void close_files(struct files_struct * files) { int i, j; + struct fdtable *fdt; j = 0; + fdt = files_fdtable(files); for (;;) { unsigned long set; i = j * __NFDBITS; - if (i >= files->max_fdset || i >= files->max_fds) + if (i >= fdt->max_fdset || i >= fdt->max_fds) break; - set = files->open_fds->fds_bits[j++]; + set = fdt->open_fds->fds_bits[j++]; while (set) { if (set & 1) { - struct file * file = xchg(&files->fd[i], NULL); + struct file * file = xchg(&fdt->fd[i], NULL); if (file) filp_close(file, files); } @@ -403,16 +405,19 @@ struct files_struct *get_files_struct(struct task_struct *task) void fastcall put_files_struct(struct files_struct *files) { + struct fdtable *fdt; + if (atomic_dec_and_test(&files->count)) { close_files(files); /* * Free the fd and fdset arrays if we expanded them. */ - if (files->fd != &files->fd_array[0]) - free_fd_array(files->fd, files->max_fds); - if (files->max_fdset > __FD_SETSIZE) { - free_fdset(files->open_fds, files->max_fdset); - free_fdset(files->close_on_exec, files->max_fdset); + fdt = files_fdtable(files); + if (fdt->fd != &files->fd_array[0]) + free_fd_array(fdt->fd, fdt->max_fds); + if (fdt->max_fdset > __FD_SETSIZE) { + free_fdset(fdt->open_fds, fdt->max_fdset); + free_fdset(fdt->close_on_exec, fdt->max_fdset); } kmem_cache_free(files_cachep, files); } -- cgit v1.2.3 From ab2af1f5005069321c5d130f09cce577b03f43ef Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 9 Sep 2005 13:04:13 -0700 Subject: [PATCH] files: files struct with RCU Patch to eliminate struct files_struct.file_lock spinlock on the reader side and use rcu refcounting rcuref_xxx api for the f_count refcounter. The updates to the fdtable are done by allocating a new fdtable structure and setting files->fdt to point to the new structure. The fdtable structure is protected by RCU thereby allowing lock-free lookup. For fd arrays/sets that are vmalloced, we use keventd to free them since RCU callbacks can't sleep. A global list of fdtable to be freed is not scalable, so we use a per-cpu list. If keventd is already handling the current cpu's work, we use a timer to defer queueing of that work. Since the last publication, this patch has been re-written to avoid using explicit memory barriers and use rcu_assign_pointer(), rcu_dereference() premitives instead. This required that the fd information is kept in a separate structure (fdtable) and updated atomically. Signed-off-by: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 83beb1e93b1..6d2089a1bce 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -411,15 +411,16 @@ void fastcall put_files_struct(struct files_struct *files) close_files(files); /* * Free the fd and fdset arrays if we expanded them. + * If the fdtable was embedded, pass files for freeing + * at the end of the RCU grace period. Otherwise, + * you can free files immediately. */ fdt = files_fdtable(files); - if (fdt->fd != &files->fd_array[0]) - free_fd_array(fdt->fd, fdt->max_fds); - if (fdt->max_fdset > __FD_SETSIZE) { - free_fdset(fdt->open_fds, fdt->max_fdset); - free_fdset(fdt->close_on_exec, fdt->max_fdset); - } - kmem_cache_free(files_cachep, files); + if (fdt == &files->fdtab) + fdt->free_files = files; + else + kmem_cache_free(files_cachep, files); + free_fdtable(fdt); } } -- cgit v1.2.3