Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 5fe6eaa1 authored by Chuck Lever's avatar Chuck Lever Committed by Anna Schumaker
Browse files

SUNRPC: Generalize the RPC buffer allocation API 



xprtrdma needs to allocate the Call and Reply buffers separately.
TBH, the reliance on using a single buffer for the pair of XDR
buffers is transport implementation-specific.

Transports that want to allocate separate Call and Reply buffers
will ignore the "size" argument anyway.  Don't bother passing it.

The buf_alloc method can't return two pointers. Instead, make the
method's return value an error code, and set the rq_buffer pointer
in the method itself.

This gives call_allocate an opportunity to terminate an RPC instead
of looping forever when a permanent problem occurs. If a request is
just bogus, or the transport is in a state where it can't allocate
resources for any request, there needs to be a way to kill the RPC
right there and not loop.

This immediately fixes a rare problem in the backchannel send path,
which loops if the server happens to send a CB request whose
call+reply size is larger than a page (which it shouldn't do yet).

One more issue: looks like xprt_inject_disconnect was incorrectly
placed in the failure path in call_allocate. It needs to be in the
success path, as it is for other call-sites.

Signed-off-by: default avatarChuck Lever <chuck.lever@oracle.com>
Signed-off-by: default avatarAnna Schumaker <Anna.Schumaker@Netapp.com>
parent b9c5bc03

include/linux/sunrpc/sched.h

+1 −1
Original line number Diff line number Diff line
@@ -239,7 +239,7 @@ struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *, 
					void *);

void		rpc_wake_up_status(struct rpc_wait_queue *, int);

void		rpc_delay(struct rpc_task *, unsigned long);

void *		rpc_malloc(struct rpc_task *, size_t);

int		rpc_malloc(struct rpc_task *);

void		rpc_free(void *);

int		rpciod_up(void);

void		rpciod_down(void);

include/linux/sunrpc/xprt.h

+1 −1
Original line number Diff line number Diff line
@@ -127,7 +127,7 @@ struct rpc_xprt_ops { 
	void		(*rpcbind)(struct rpc_task *task);

	void		(*set_port)(struct rpc_xprt *xprt, unsigned short port);

	void		(*connect)(struct rpc_xprt *xprt, struct rpc_task *task);

	void *		(*buf_alloc)(struct rpc_task *task, size_t size);

	int		(*buf_alloc)(struct rpc_task *task);

	void		(*buf_free)(void *buffer);

	int		(*send_request)(struct rpc_task *task);

	void		(*set_retrans_timeout)(struct rpc_task *task);

net/sunrpc/clnt.c

+8 −4
Original line number Diff line number Diff line
@@ -1691,6 +1691,7 @@ call_allocate(struct rpc_task *task) 
	struct rpc_rqst *req = task->tk_rqstp;

	struct rpc_xprt *xprt = req->rq_xprt;

	struct rpc_procinfo *proc = task->tk_msg.rpc_proc;

	int status;



	dprint_status(task);
@@ -1716,11 +1717,14 @@ call_allocate(struct rpc_task *task) 
	req->rq_rcvsize = RPC_REPHDRSIZE + slack + proc->p_replen;

	req->rq_rcvsize <<= 2;



	req->rq_buffer = xprt->ops->buf_alloc(task,

					req->rq_callsize + req->rq_rcvsize);

	if (req->rq_buffer != NULL)

		return;

	status = xprt->ops->buf_alloc(task);

	xprt_inject_disconnect(xprt);

	if (status == 0)

		return;

	if (status != -ENOMEM) {

		rpc_exit(task, status);

		return;

	}



	dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid);

net/sunrpc/sched.c

+15 −9
Original line number Diff line number Diff line
@@ -849,14 +849,17 @@ static void rpc_async_schedule(struct work_struct *work) 
}



/**

 * rpc_malloc - allocate an RPC buffer

 * @task: RPC task that will use this buffer

 * @size: requested byte size

 * rpc_malloc - allocate RPC buffer resources

 * @task: RPC task

 *

 * A single memory region is allocated, which is split between the

 * RPC call and RPC reply that this task is being used for. When

 * this RPC is retired, the memory is released by calling rpc_free.

 *

 * To prevent rpciod from hanging, this allocator never sleeps,

 * returning NULL and suppressing warning if the request cannot be serviced

 * immediately.

 * The caller can arrange to sleep in a way that is safe for rpciod.

 * returning -ENOMEM and suppressing warning if the request cannot

 * be serviced immediately. The caller can arrange to sleep in a

 * way that is safe for rpciod.

 *

 * Most requests are 'small' (under 2KiB) and can be serviced from a

 * mempool, ensuring that NFS reads and writes can always proceed,
@@ -865,8 +868,10 @@ static void rpc_async_schedule(struct work_struct *work) 
 * In order to avoid memory starvation triggering more writebacks of

 * NFS requests, we avoid using GFP_KERNEL.

 */

void *rpc_malloc(struct rpc_task *task, size_t size)

int rpc_malloc(struct rpc_task *task)

{

	struct rpc_rqst *rqst = task->tk_rqstp;

	size_t size = rqst->rq_callsize + rqst->rq_rcvsize;

	struct rpc_buffer *buf;

	gfp_t gfp = GFP_NOIO | __GFP_NOWARN;
@@ -880,12 +885,13 @@ void *rpc_malloc(struct rpc_task *task, size_t size) 
		buf = kmalloc(size, gfp);



	if (!buf)

		return NULL;

		return -ENOMEM;



	buf->len = size;

	dprintk("RPC: %5u allocated buffer of size %zu at %p\n",

			task->tk_pid, size, buf);

	return &buf->data;

	rqst->rq_buffer = buf->data;

	return 0;

}

EXPORT_SYMBOL_GPL(rpc_malloc);

net/sunrpc/xprtrdma/svc_rdma_backchannel.c

+9 −8
Original line number Diff line number Diff line
@@ -159,29 +159,30 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, 
/* Server-side transport endpoint wants a whole page for its send

 * buffer. The client RPC code constructs the RPC header in this

 * buffer before it invokes ->send_request.

 *

 * Returns NULL if there was a temporary allocation failure.

 */

static void *

xprt_rdma_bc_allocate(struct rpc_task *task, size_t size)

static int

xprt_rdma_bc_allocate(struct rpc_task *task)

{

	struct rpc_rqst *rqst = task->tk_rqstp;

	struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt;

	size_t size = rqst->rq_callsize;

	struct svcxprt_rdma *rdma;

	struct page *page;



	rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt);



	/* Prevent an infinite loop: try to make this case work */

	if (size > PAGE_SIZE)

	if (size > PAGE_SIZE) {

		WARN_ONCE(1, "svcrdma: large bc buffer request (size %zu)\n",

			  size);

		return -EINVAL;

	}



	page = alloc_page(RPCRDMA_DEF_GFP);

	if (!page)

		return NULL;

		return -ENOMEM;



	return page_address(page);

	rqst->rq_buffer = page_address(page);

	return 0;

}



static void