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 <xiaohui.xin@intel.com>
Subject: [RFC][PATCH v4 15/18] Manipulate external buffers in mp device.
Date: Sun, 25 Apr 2010 17:20:02 +0800 [thread overview]
Message-ID: <1272187206-18534-15-git-send-email-xiaohui.xin@intel.com> (raw)
In-Reply-To: <1272187206-18534-14-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
How external buffer comes from, how to destroy.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
drivers/vhost/mpassthru.c | 237 ++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 236 insertions(+), 1 deletions(-)
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 = {
};
--
1.5.4.4
next prev parent reply other threads:[~2010-04-25 9:20 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-25 9:19 [RFC][PATCH v4 01/18] Add a new struct for device to manipulate external buffer xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 02/18] Export 2 func for device to assign/dassign new structure xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 03/18] Add a ndo_mp_port_prep pointer to net_device_ops xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 04/18] Add a function make external buffer owner to query capability xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 05/18] Add a function to indicate if device use external buffer xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 06/18] Add interface to get external buffers xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 07/18] Make __alloc_skb() to get external buffer xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 08/18] Ignore skb_reserve() when device is using " xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 09/18] Don't do skb recycle, if device use " xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 10/18] Use callback to deal with skb_release_data() specially xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 11/18] Add a hook to intercept external buffers from NIC driver xiaohui.xin
2010-04-25 9:19 ` [RFC][PATCH v4 12/18] To skip GRO if buffer is external xiaohui.xin
2010-04-25 9:20 ` [RFC][PATCH v4 13/18] Add header file for mp device xiaohui.xin
2010-04-25 9:20 ` [RFC][PATCH v4 14/18] Add basic func and special ioctl to " xiaohui.xin
2010-04-25 9:20 ` xiaohui.xin [this message]
2010-04-25 9:20 ` [RFC][PATCH v4 16/18] Export proto_ops to vhost-net driver xiaohui.xin
2010-04-25 9:20 ` [RFC][PATCH v4 17/18] Add a kconfig entry and make entry for mp device xiaohui.xin
2010-04-25 9:20 ` [RFC][PATCH v4 18/18] Provides multiple submits and async notifications xiaohui.xin
2010-04-25 9:20 ` [RFC][PATCH v4 00/18] Provide a zero-copy method on KVM virtio-net xiaohui.xin
2010-04-25 9:55 ` David Miller
2010-04-25 10:46 ` Michael S. Tsirkin
2010-04-29 1:33 ` Xin, Xiaohui
2010-04-25 12:14 ` Michael S. Tsirkin
2010-05-08 7:55 ` Xin, Xiaohui
2010-05-09 9:26 ` Michael S. Tsirkin
2010-04-25 9:33 ` [RFC][PATCH v4 05/18] Add a function to indicate if device use external buffer Changli Gao
2010-04-25 9:51 ` David Miller
2010-04-25 9:35 ` Changli Gao
2010-04-25 9:51 ` David Miller
2010-04-29 1:38 ` Xin, Xiaohui
2010-04-26 20:06 ` [RFC][PATCH v4 01/18] Add a new struct for device to manipulate " Andy Fleming
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1272187206-18534-15-git-send-email-xiaohui.xin@intel.com \
--to=xiaohui.xin@intel.com \
--cc=davem@davemloft.net \
--cc=jdike@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).