Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751894AbdIOXBm (ORCPT ); Fri, 15 Sep 2017 19:01:42 -0400 Received: from mail.kernel.org ([198.145.29.99]:37042 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751621AbdIOXAq (ORCPT ); Fri, 15 Sep 2017 19:00:46 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 8F41622A7F Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=sstabellini@kernel.org From: Stefano Stabellini To: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org, sstabellini@kernel.org, jgross@suse.com, boris.ostrovsky@oracle.com, Stefano Stabellini Subject: [PATCH v4 09/13] xen/pvcalls: implement sendmsg Date: Fri, 15 Sep 2017 16:00:36 -0700 Message-Id: <1505516440-11111-9-git-send-email-sstabellini@kernel.org> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1505516440-11111-1-git-send-email-sstabellini@kernel.org> References: <1505516440-11111-1-git-send-email-sstabellini@kernel.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4841 Lines: 175 Send data to an active socket by copying data to the "out" ring. Take the active socket out_mutex so that only one function can access the ring at any given time. If not enough room is available on the ring, rather than returning immediately or sleep-waiting, spin for up to 5000 cycles. This small optimization turns out to improve performance significantly. Signed-off-by: Stefano Stabellini CC: boris.ostrovsky@oracle.com CC: jgross@suse.com --- drivers/xen/pvcalls-front.c | 119 ++++++++++++++++++++++++++++++++++++++++++++ drivers/xen/pvcalls-front.h | 3 ++ 2 files changed, 122 insertions(+) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 414eafd..2907e85 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -29,6 +29,7 @@ #define PVCALLS_INVALID_ID UINT_MAX #define PVCALLS_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE) +#define PVCALLS_FRONT_MAX_SPIN 5000 struct pvcalls_bedata { struct xen_pvcalls_front_ring ring; @@ -101,6 +102,22 @@ static inline int get_request(struct pvcalls_bedata *bedata, int *req_id) return 0; } +static bool pvcalls_front_write_todo(struct sock_mapping *map) +{ + struct pvcalls_data_intf *intf = map->active.ring; + RING_IDX cons, prod, size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER); + int32_t error; + + cons = intf->out_cons; + prod = intf->out_prod; + error = intf->out_error; + if (error == -ENOTCONN) + return false; + if (error != 0) + return true; + return !!(size - pvcalls_queued(prod, cons, size)); +} + static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) { struct xenbus_device *dev = dev_id; @@ -363,6 +380,108 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, return ret; } +static int __write_ring(struct pvcalls_data_intf *intf, + struct pvcalls_data *data, + struct iov_iter *msg_iter, + int len) +{ + RING_IDX cons, prod, size, masked_prod, masked_cons; + RING_IDX array_size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER); + int32_t error; + + error = intf->out_error; + if (error < 0) + return error; + cons = intf->out_cons; + prod = intf->out_prod; + /* read indexes before continuing */ + virt_mb(); + + size = pvcalls_queued(prod, cons, array_size); + if (size >= array_size) + return 0; + if (len > array_size - size) + len = array_size - size; + + masked_prod = pvcalls_mask(prod, array_size); + masked_cons = pvcalls_mask(cons, array_size); + + if (masked_prod < masked_cons) { + copy_from_iter(data->out + masked_prod, len, msg_iter); + } else { + if (len > array_size - masked_prod) { + copy_from_iter(data->out + masked_prod, + array_size - masked_prod, msg_iter); + copy_from_iter(data->out, + len - (array_size - masked_prod), + msg_iter); + } else { + copy_from_iter(data->out + masked_prod, len, msg_iter); + } + } + /* write to ring before updating pointer */ + virt_wmb(); + intf->out_prod += len; + + return len; +} + +int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) +{ + struct pvcalls_bedata *bedata; + struct sock_mapping *map; + int sent, tot_sent = 0; + int count = 0, flags; + + pvcalls_enter; + if (!pvcalls_front_dev) { + pvcalls_exit; + return -ENOTCONN; + } + bedata = dev_get_drvdata(&pvcalls_front_dev->dev); + + map = (struct sock_mapping *) sock->sk->sk_send_head; + if (!map) { + pvcalls_exit; + return -ENOTSOCK; + } + + flags = msg->msg_flags; + if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB)) { + pvcalls_exit; + return -EOPNOTSUPP; + } + + mutex_lock(&map->active.out_mutex); + if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) { + mutex_unlock(&map->active.out_mutex); + pvcalls_exit; + return -EAGAIN; + } + if (len > INT_MAX) + len = INT_MAX; + +again: + count++; + sent = __write_ring(map->active.ring, + &map->active.data, &msg->msg_iter, + len); + if (sent > 0) { + len -= sent; + tot_sent += sent; + notify_remote_via_irq(map->active.irq); + } + if (sent >= 0 && len > 0 && count < PVCALLS_FRONT_MAX_SPIN) + goto again; + if (sent < 0) + tot_sent = sent; + + mutex_unlock(&map->active.out_mutex); + pvcalls_exit; + return tot_sent; +} + int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct pvcalls_bedata *bedata; diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index ab4f1da..d937c24 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -13,5 +13,8 @@ int pvcalls_front_bind(struct socket *sock, int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags); +int pvcalls_front_sendmsg(struct socket *sock, + struct msghdr *msg, + size_t len); #endif -- 1.9.1