summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTrond Myklebust <Trond.Myklebust@netapp.com>2006-11-13 16:23:44 -0500
committerTrond Myklebust <Trond.Myklebust@netapp.com>2006-12-06 10:46:26 -0500
commit8aca67f0ae2d8811165c22326825a645cc8e1b48 (patch)
tree19e82f4bc7b4f865a9dcf4744e7c224ea517ba10
parente6b3c4db6fbcd0d33720696f37790d6b8be12313 (diff)
SUNRPC: Fix a potential race in rpc_wake_up_task()
Use RCU to ensure that we can safely call rpc_finish_wakeup after we've called __rpc_do_wake_up_task. If not, there is a theoretical race, in which the rpc_task finishes executing, and gets freed first. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-rw-r--r--fs/nfs/read.c8
-rw-r--r--fs/nfs/write.c20
-rw-r--r--include/linux/nfs_fs.h7
-rw-r--r--include/linux/sunrpc/sched.h2
-rw-r--r--net/sunrpc/sched.c30
5 files changed, 47 insertions, 20 deletions
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index c2e49c397a27..8b58bbf6e39e 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -65,13 +65,19 @@ struct nfs_read_data *nfs_readdata_alloc(size_t len)
return p;
}
-static void nfs_readdata_free(struct nfs_read_data *p)
+static void nfs_readdata_rcu_free(struct rcu_head *head)
{
+ struct nfs_read_data *p = container_of(head, struct nfs_read_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_rdata_mempool);
}
+static void nfs_readdata_free(struct nfs_read_data *rdata)
+{
+ call_rcu_bh(&rdata->task.u.tk_rcu, nfs_readdata_rcu_free);
+}
+
void nfs_readdata_release(void *data)
{
nfs_readdata_free(data);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 883dd4a1c157..29d88209199d 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -102,13 +102,19 @@ struct nfs_write_data *nfs_commit_alloc(void)
return p;
}
-void nfs_commit_free(struct nfs_write_data *p)
+void nfs_commit_rcu_free(struct rcu_head *head)
{
+ struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_commit_mempool);
}
+void nfs_commit_free(struct nfs_write_data *wdata)
+{
+ call_rcu_bh(&wdata->task.u.tk_rcu, nfs_commit_rcu_free);
+}
+
struct nfs_write_data *nfs_writedata_alloc(size_t len)
{
unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -131,13 +137,19 @@ struct nfs_write_data *nfs_writedata_alloc(size_t len)
return p;
}
-static void nfs_writedata_free(struct nfs_write_data *p)
+static void nfs_writedata_rcu_free(struct rcu_head *head)
{
+ struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_wdata_mempool);
}
+static void nfs_writedata_free(struct nfs_write_data *wdata)
+{
+ call_rcu_bh(&wdata->task.u.tk_rcu, nfs_writedata_rcu_free);
+}
+
void nfs_writedata_release(void *wdata)
{
nfs_writedata_free(wdata);
@@ -258,7 +270,7 @@ static int nfs_writepage_sync(struct nfs_open_context *ctx, struct inode *inode,
io_error:
nfs_end_data_update(inode);
end_page_writeback(page);
- nfs_writedata_free(wdata);
+ nfs_writedata_release(wdata);
return written ? written : result;
}
@@ -1043,7 +1055,7 @@ out_bad:
while (!list_empty(&list)) {
data = list_entry(list.next, struct nfs_write_data, pages);
list_del(&data->pages);
- nfs_writedata_free(data);
+ nfs_writedata_release(data);
}
nfs_mark_request_dirty(req);
nfs_clear_page_writeback(req);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 625ffea98561..02f38189d180 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -428,11 +428,6 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned
extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
extern void nfs_writedata_release(void *);
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-struct nfs_write_data *nfs_commit_alloc(void);
-void nfs_commit_free(struct nfs_write_data *p);
-#endif
-
/*
* Try to write back everything synchronously (but check the
* return value!)
@@ -440,6 +435,8 @@ void nfs_commit_free(struct nfs_write_data *p);
extern int nfs_sync_inode_wait(struct inode *, unsigned long, unsigned int, int);
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
extern int nfs_commit_inode(struct inode *, int);
+extern struct nfs_write_data *nfs_commit_alloc(void);
+extern void nfs_commit_free(struct nfs_write_data *wdata);
extern void nfs_commit_release(void *wdata);
#else
static inline int
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 9fdb8c9d09f2..14fc813ddd0c 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -11,6 +11,7 @@
#include <linux/timer.h>
#include <linux/sunrpc/types.h>
+#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
@@ -85,6 +86,7 @@ struct rpc_task {
union {
struct work_struct tk_work; /* Async task work queue */
struct rpc_wait tk_wait; /* RPC wait */
+ struct rcu_head tk_rcu; /* for task deletion */
} u;
unsigned short tk_timeouts; /* maj timeouts */
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 66d01365f3a5..6b808c03fb72 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -427,16 +427,19 @@ __rpc_default_timer(struct rpc_task *task)
*/
void rpc_wake_up_task(struct rpc_task *task)
{
+ rcu_read_lock_bh();
if (rpc_start_wakeup(task)) {
if (RPC_IS_QUEUED(task)) {
struct rpc_wait_queue *queue = task->u.tk_wait.rpc_waitq;
- spin_lock_bh(&queue->lock);
+ /* Note: we're already in a bh-safe context */
+ spin_lock(&queue->lock);
__rpc_do_wake_up_task(task);
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
}
rpc_finish_wakeup(task);
}
+ rcu_read_unlock_bh();
}
/*
@@ -499,14 +502,16 @@ struct rpc_task * rpc_wake_up_next(struct rpc_wait_queue *queue)
struct rpc_task *task = NULL;
dprintk("RPC: wake_up_next(%p \"%s\")\n", queue, rpc_qname(queue));
- spin_lock_bh(&queue->lock);
+ rcu_read_lock_bh();
+ spin_lock(&queue->lock);
if (RPC_IS_PRIORITY(queue))
task = __rpc_wake_up_next_priority(queue);
else {
task_for_first(task, &queue->tasks[0])
__rpc_wake_up_task(task);
}
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
+ rcu_read_unlock_bh();
return task;
}
@@ -522,7 +527,8 @@ void rpc_wake_up(struct rpc_wait_queue *queue)
struct rpc_task *task, *next;
struct list_head *head;
- spin_lock_bh(&queue->lock);
+ rcu_read_lock_bh();
+ spin_lock(&queue->lock);
head = &queue->tasks[queue->maxpriority];
for (;;) {
list_for_each_entry_safe(task, next, head, u.tk_wait.list)
@@ -531,7 +537,8 @@ void rpc_wake_up(struct rpc_wait_queue *queue)
break;
head--;
}
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
+ rcu_read_unlock_bh();
}
/**
@@ -546,7 +553,8 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
struct rpc_task *task, *next;
struct list_head *head;
- spin_lock_bh(&queue->lock);
+ rcu_read_lock_bh();
+ spin_lock(&queue->lock);
head = &queue->tasks[queue->maxpriority];
for (;;) {
list_for_each_entry_safe(task, next, head, u.tk_wait.list) {
@@ -557,7 +565,8 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
break;
head--;
}
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
+ rcu_read_unlock_bh();
}
static void __rpc_atrun(struct rpc_task *task)
@@ -817,8 +826,9 @@ rpc_alloc_task(void)
return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
}
-static void rpc_free_task(struct rpc_task *task)
+static void rpc_free_task(struct rcu_head *rcu)
{
+ struct rpc_task *task = container_of(rcu, struct rpc_task, u.tk_rcu);
dprintk("RPC: %4d freeing task\n", task->tk_pid);
mempool_free(task, rpc_task_mempool);
}
@@ -872,7 +882,7 @@ void rpc_put_task(struct rpc_task *task)
task->tk_client = NULL;
}
if (task->tk_flags & RPC_TASK_DYNAMIC)
- rpc_free_task(task);
+ call_rcu_bh(&task->u.tk_rcu, rpc_free_task);
if (tk_ops->rpc_release)
tk_ops->rpc_release(calldata);
}