From patchwork Sun Apr 25 09:20:02 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Xin, Xiaohui" X-Patchwork-Id: 94923 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.3/8.14.3) with ESMTP id o3P9LrGv030605 for ; Sun, 25 Apr 2010 09:21:58 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753617Ab0DYJRn (ORCPT ); Sun, 25 Apr 2010 05:17:43 -0400 Received: from mga11.intel.com ([192.55.52.93]:55113 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752847Ab0DYJRS (ORCPT ); Sun, 25 Apr 2010 05:17:18 -0400 Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga102.fm.intel.com with ESMTP; 25 Apr 2010 02:16:01 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.52,269,1270450800"; d="scan'208";a="561295894" Received: from unknown (HELO localhost.localdomain) ([10.239.36.200]) by fmsmga002.fm.intel.com with ESMTP; 25 Apr 2010 02:16:43 -0700 From: xiaohui.xin@intel.com To: netdev@vger.kernel.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, mst@redhat.com, mingo@elte.hu, davem@davemloft.net, jdike@linux.intel.com Cc: Xin Xiaohui Subject: [RFC][PATCH v4 15/18] Manipulate external buffers in mp device. Date: Sun, 25 Apr 2010 17:20:02 +0800 Message-Id: <1272187206-18534-15-git-send-email-xiaohui.xin@intel.com> X-Mailer: git-send-email 1.5.4.4 In-Reply-To: <1272187206-18534-14-git-send-email-xiaohui.xin@intel.com> References: <1272187206-18534-1-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-2-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-3-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-4-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-5-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-6-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-7-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-8-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-9-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-10-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-11-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-12-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-13-git-send-email-xiaohui.xin@intel.com> <1272187206-18534-14-git-send-email-xiaohui.xin@intel.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter.kernel.org [140.211.167.41]); Sun, 25 Apr 2010 09:21:59 +0000 (UTC) diff --git a/drivers/vhost/mpassthru.c b/drivers/vhost/mpassthru.c index c5ede17..b171f21 100644 --- a/drivers/vhost/mpassthru.c +++ b/drivers/vhost/mpassthru.c @@ -159,6 +159,39 @@ static int mp_dev_change_flags(struct net_device *dev, unsigned flags) return ret; } +/* The main function to allocate external buffers */ +static struct skb_external_page *page_ctor(struct mpassthru_port *port, + struct sk_buff *skb, int npages) +{ + int i; + unsigned long flags; + struct page_ctor *ctor; + struct page_info *info = NULL; + + ctor = container_of(port, struct page_ctor, port); + + spin_lock_irqsave(&ctor->read_lock, flags); + if (!list_empty(&ctor->readq)) { + info = list_first_entry(&ctor->readq, struct page_info, list); + list_del(&info->list); + } + spin_unlock_irqrestore(&ctor->read_lock, flags); + if (!info) + return NULL; + + for (i = 0; i < info->pnum; i++) { + get_page(info->pages[i]); + info->frag[i].page = info->pages[i]; + info->frag[i].page_offset = i ? 0 : info->offset; + info->frag[i].size = port->npages > 1 ? PAGE_SIZE : + port->data_len; + } + info->skb = skb; + info->ext_page.frags = info->frag; + info->ext_page.ushinfo = &info->ushinfo; + return &info->ext_page; +} + static int page_ctor_attach(struct mp_struct *mp) { int rc; @@ -191,7 +224,7 @@ static int page_ctor_attach(struct mp_struct *mp) dev_hold(dev); ctor->dev = dev; - ctor->port.ctor = NULL; + ctor->port.ctor = page_ctor; ctor->port.sock = &mp->socket; ctor->lock_pages = 0; rc = netdev_mp_port_attach(dev, &ctor->port); @@ -258,6 +291,52 @@ static int set_memlock_rlimit(struct page_ctor *ctor, int resource, task_unlock(current->group_leader); return 0; } +static void mp_ki_dtor(struct kiocb *iocb) +{ + struct page_info *info = (struct page_info *)(iocb->private); + int i; + + if (info->flags == INFO_READ) { + for (i = 0; i < info->pnum; i++) { + if (info->pages[i]) { + set_page_dirty_lock(info->pages[i]); + put_page(info->pages[i]); + } + } + skb_shinfo(info->skb)->destructor_arg = &info->ext_page; + info->skb->destructor = NULL; + kfree_skb(info->skb); + } + /* Decrement the number of locked pages */ + info->ctor->lock_pages -= info->pnum; + kmem_cache_free(info->ctor->cache, info); + + return; +} + +static struct kiocb *create_iocb(struct page_info *info, int size) +{ + struct kiocb *iocb = NULL; + + iocb = info->iocb; + if (!iocb) + return iocb; + iocb->ki_flags = 0; + iocb->ki_users = 1; + iocb->ki_key = 0; + iocb->ki_ctx = NULL; + iocb->ki_cancel = NULL; + iocb->ki_retry = NULL; + iocb->ki_iovec = NULL; + iocb->ki_eventfd = NULL; + iocb->ki_pos = info->desc_pos; + iocb->ki_nbytes = size; + iocb->ki_dtor(iocb); + iocb->private = (void *)info; + iocb->ki_dtor = mp_ki_dtor; + + return iocb; +} static int page_ctor_detach(struct mp_struct *mp) { @@ -275,6 +354,7 @@ static int page_ctor_detach(struct mp_struct *mp) for (i = 0; i < info->pnum; i++) if (info->pages[i]) put_page(info->pages[i]); + create_iocb(info, 0); kmem_cache_free(ctor->cache, info); } set_memlock_rlimit(ctor, RLIMIT_MEMLOCK, @@ -328,6 +408,161 @@ static void mp_put(struct mp_file *mfile) mp_detach(mfile->mp); } +/* The callback to destruct the external buffers or skb */ +static void page_dtor(struct skb_external_page *ext_page) +{ + struct page_info *info; + struct page_ctor *ctor; + struct sock *sk; + struct sk_buff *skb; + struct kiocb *iocb = NULL; + unsigned long flags; + + if (!ext_page) + return; + info = container_of(ext_page, struct page_info, ext_page); + if (!info) + return; + ctor = info->ctor; + skb = info->skb; + + if ((info->flags == INFO_READ) && info->skb) + info->skb->head = NULL; + + /* If the info->total is 0, make it to be reused */ + if (!info->total) { + spin_lock_irqsave(&ctor->read_lock, flags); + list_add(&info->list, &ctor->readq); + spin_unlock_irqrestore(&ctor->read_lock, flags); + return; + } + + if (info->flags == INFO_READ) + return; + + /* For transmit, we should wait for the DMA finish by hardware. + * Queue the notifier to wake up the backend driver + */ + + iocb = create_iocb(info, info->total); + + sk = ctor->port.sock->sk; + sk->sk_write_space(sk); + + return; +} + +/* For small exteranl buffers transmit, we don't need to call + * get_user_pages(). + */ +static struct page_info *alloc_small_page_info(struct page_ctor *ctor, + struct kiocb *iocb, int total) +{ + struct page_info *info = kmem_cache_zalloc(ctor->cache, GFP_KERNEL); + + if (!info) + return NULL; + info->total = total; + info->ext_page.dtor = page_dtor; + info->ctor = ctor; + info->flags = INFO_WRITE; + info->iocb = iocb; + return info; +} + +/* The main function to transform the guest user space address + * to host kernel address via get_user_pages(). Thus the hardware + * can do DMA directly to the external buffer address. + */ +static struct page_info *alloc_page_info(struct page_ctor *ctor, + struct kiocb *iocb, struct iovec *iov, + int count, struct frag *frags, + int npages, int total) +{ + int rc; + int i, j, n = 0; + int len; + unsigned long base, lock_limit; + struct page_info *info = NULL; + + lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + lock_limit >>= PAGE_SHIFT; + + if (ctor->lock_pages + count > lock_limit) { + printk(KERN_INFO "exceed the locked memory rlimit."); + return NULL; + } + + info = kmem_cache_zalloc(ctor->cache, GFP_KERNEL); + + if (!info) + return NULL; + + for (i = j = 0; i < count; i++) { + base = (unsigned long)iov[i].iov_base; + len = iov[i].iov_len; + + if (!len) + continue; + n = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + + rc = get_user_pages_fast(base, n, npages ? 1 : 0, + &info->pages[j]); + if (rc != n) + goto failed; + + while (n--) { + frags[j].offset = base & ~PAGE_MASK; + frags[j].size = min_t(int, len, + PAGE_SIZE - frags[j].offset); + len -= frags[j].size; + base += frags[j].size; + j++; + } + } + +#ifdef CONFIG_HIGHMEM + if (npages && !(dev->features & NETIF_F_HIGHDMA)) { + for (i = 0; i < j; i++) { + if (PageHighMem(info->pages[i])) + goto failed; + } + } +#endif + + info->total = total; + info->ext_page.dtor = page_dtor; + info->ctor = ctor; + info->pnum = j; + info->iocb = iocb; + if (!npages) + info->flags = INFO_WRITE; + if (info->flags == INFO_READ) { + info->ext_page.start = (u8 *)(((unsigned long) + (pfn_to_kaddr(page_to_pfn(info->pages[0]))) + + frags[0].offset)); +#ifdef NET_SKBUFF_DATA_USES_OFFSET + info->ext_page.size = SKB_DATA_ALIGN( + iov[0].iov_len + NET_IP_ALIGN + NET_SKB_PAD); +#else + info->ext_page.size = SKB_DATA_ALIGN( + iov[0].iov_len + NET_IP_ALIGN + NET_SKB_PAD) - + NET_IP_ALIGN - NET_SKB_PAD; +#endif + } + /* increment the number of locked pages */ + ctor->lock_pages += j; + return info; + +failed: + for (i = 0; i < j; i++) + put_page(info->pages[i]); + + kmem_cache_free(ctor->cache, info); + + return NULL; +} + /* Ops structure to mimic raw sockets with mp device */ static const struct proto_ops mp_socket_ops = { };