[PATCH] files: fix preemption issues

With the new fdtable locking rules, you have to protect fdtable with either
->file_lock or rcu_read_lock/unlock().  There are some places where we
aren't doing either.  This patch fixes those places.

Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 20 insertions, 2 deletions

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 0636116..01fe990d 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -37,6 +37,7 @@
 #include <linux/namei.h>
 #include <linux/uio.h>
 #include <linux/vfs.h>
+#include <linux/rcupdate.h>
 
 #include <asm/fpu.h>
 #include <asm/io.h>
@@ -975,6 +976,7 @@ osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp,
 	long timeout;
 	int ret = -EINVAL;
 	struct fdtable *fdt;
+	int max_fdset;
 
 	timeout = MAX_SCHEDULE_TIMEOUT;
 	if (tvp) {
@@ -996,8 +998,11 @@ osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp,
 		}
 	}
 
+	rcu_read_lock();
 	fdt = files_fdtable(current->files);
-	if (n < 0 || n > fdt->max_fdset)
+	max_fdset = fdt->max_fdset;
+	rcu_read_unlock();
+	if (n < 0 || n > max_fdset)
 		goto out_nofds;
 
 	/*
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index af42cda..d71731e 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2218,12 +2218,13 @@ static void
 pfm_free_fd(int fd, struct file *file)
 {
 	struct files_struct *files = current->files;
-	struct fdtable *fdt = files_fdtable(files);
+	struct fdtable *fdt;
 
 	/* 
 	 * there ie no fd_uninstall(), so we do it here
 	 */
 	spin_lock(&files->file_lock);
+	fdt = files_fdtable(files);
 	rcu_assign_pointer(fdt->fd[fd], NULL);
 	spin_unlock(&files->file_lock);
 
diff --git a/fs/locks.c b/fs/locks.c
index c2c09b4..f7daa5f 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -124,6 +124,7 @@
 #include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/time.h>
+#include <linux/rcupdate.h>
 
 #include <asm/semaphore.h>
 #include <asm/uaccess.h>
@@ -2205,6 +2206,7 @@ void steal_locks(fl_owner_t from)
 
 	lock_kernel();
 	j = 0;
+	rcu_read_lock();
 	fdt = files_fdtable(files);
 	for (;;) {
 		unsigned long set;
@@ -2222,6 +2224,7 @@ void steal_locks(fl_owner_t from)
 			set >>= 1;
 		}
 	}
+	rcu_read_unlock();
 	unlock_kernel();
 }
 EXPORT_SYMBOL(steal_locks);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index d88d518..d84eeca 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -74,6 +74,7 @@
 #include <linux/file.h>
 #include <linux/times.h>
 #include <linux/cpuset.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -180,12 +181,14 @@ static inline char * task_state(struct task_struct *p, char *buffer)
 		p->gid, p->egid, p->sgid, p->fsgid);
 	read_unlock(&tasklist_lock);
 	task_lock(p);
+	rcu_read_lock();
 	if (p->files)
 		fdt = files_fdtable(p->files);
 	buffer += sprintf(buffer,
 		"FDSize:\t%d\n"
 		"Groups:\t",
 		fdt ? fdt->max_fds : 0);
+	rcu_read_unlock();
 
 	group_info = p->group_info;
 	get_group_info(group_info);
diff --git a/kernel/exit.c b/kernel/exit.c
index 6d2089a..ee6d8b8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -371,6 +371,12 @@ static inline void close_files(struct files_struct * files)
 	struct fdtable *fdt;
 
 	j = 0;
+
+	/*
+	 * It is safe to dereference the fd table without RCU or
+	 * ->file_lock because this is the last reference to the
+	 * files structure.
+	 */
 	fdt = files_fdtable(files);
 	for (;;) {
 		unsigned long set;