|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH 3/3] xen-sockfront: add support of the xen-sockfront driver
This driver will allow to use xensock sockets for the
client application for the domU domain.
Signed-off-by: Oleksandr Dmytryshyn <oleksandr.dmytryshyn@xxxxxxxxxxxxxxx>
---
drivers/net/Kconfig | 17 +-
drivers/net/Makefile | 1 +
drivers/net/xen-sockfront.c | 1364 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 1381 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/xen-sockfront.c
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index e643f42..887fe4b 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -348,6 +348,21 @@ config XEN_NETDEV_BACKEND
compile this driver as a module, chose M here: the module
will be called xen-netback.
+config XEN_SOCKDEV_FRONTEND
+ tristate "Xen frontend socket device"
+ depends on XEN_DOMU
+ select XEN_SOCKDEV_PROTO
+ help
+ This driver provides support for Xen socket devices exported
+ by a Xen socket driver domain (often domain 0).
+
+ The corresponding Linux backend driver is enabled by the
+ XEN_SOCKDEV_BACKEND option.
+
+ If you are compiling a kernel for use as Xen guest, you
+ should say Y here. To compile this driver as a module, chose
+ M here: the module will be called xen-sockfront.
+
config XEN_SOCKDEV_BACKEND
tristate "Xen backend socket device"
depends on XEN_BACKEND
@@ -369,7 +384,7 @@ config XEN_SOCKDEV_BACKEND
config XEN_SOCKDEV_PROTO
bool
default n
- depends on XEN_SOCKDEV_BACKEND
+ depends on XEN_SOCKDEV_BACKEND || XEN_SOCKDEV_FRONTEND
config VMXNET3
tristate "VMware VMXNET3 ethernet driver"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 96c6c97..8c3eee8 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o
obj-$(CONFIG_XEN_NETDEV_BACKEND) += xen-netback/
obj-$(CONFIG_XEN_SOCKDEV_PROTO) += xensock/
+obj-$(CONFIG_XEN_SOCKDEV_FRONTEND) += xen-sockfront.o
obj-$(CONFIG_XEN_SOCKDEV_BACKEND) += xen-sockback/
obj-$(CONFIG_USB_CATC) += usb/
diff --git a/drivers/net/xen-sockfront.c b/drivers/net/xen-sockfront.c
new file mode 100644
index 0000000..2aa65e4
--- /dev/null
+++ b/drivers/net/xen-sockfront.c
@@ -0,0 +1,1364 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/moduleparam.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+
+#include <net/xensock.h>
+#include <net/af_xensock.h>
+
+#include <asm/xen/page.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/page.h>
+#include <xen/grant_table.h>
+
+#include <xen/interface/io/sockif.h>
+#include <xen/interface/memory.h>
+#include <xen/interface/grant_table.h>
+
+struct sockfront_cb {
+ int pull_to;
+};
+
+#define SOCKFRONT_SKB_CB(skb) ((struct sockfront_cb *)((skb)->cb))
+
+#define RX_COPY_THRESHOLD 256
+
+#define GRANT_INVALID_REF 0
+
+#define SOCK_TX_RING_SIZE __CONST_RING_SIZE(xen_sockif_tx, PAGE_SIZE)
+#define SOCK_RX_RING_SIZE __CONST_RING_SIZE(xen_sockif_rx, PAGE_SIZE)
+#define TX_MAX_TARGET min_t(int, SOCK_TX_RING_SIZE, 256)
+
+struct sockfront_info {
+ struct list_head list;
+ struct xen_sock_dev *sockdev;
+ unsigned int irq;
+
+ struct tasklet_struct rx_poll;
+
+ unsigned int evtchn;
+ struct xenbus_device *xbdev;
+
+ spinlock_t tx_lock; /* transmitter lock */
+ struct xen_sockif_tx_front_ring tx;
+ int tx_ring_ref;
+
+ /* {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries
+ * are linked from tx_skb_freelist through skb_entry.link.
+ *
+ * NB. Freelist index entries are always going to be less than
+ * PAGE_OFFSET, whereas pointers to skbs will always be equal or
+ * greater than PAGE_OFFSET: we use this property to distinguish
+ * them.
+ */
+ union skb_entry {
+ struct sk_buff *skb;
+ unsigned long link;
+ } tx_skbs[SOCK_TX_RING_SIZE];
+ grant_ref_t gref_tx_head;
+ grant_ref_t grant_tx_ref[SOCK_TX_RING_SIZE];
+ unsigned tx_skb_freelist;
+
+ spinlock_t rx_lock ____cacheline_aligned_in_smp;
+ struct xen_sockif_rx_front_ring rx;
+ int rx_ring_ref;
+
+ /* Receive-ring batched refills. */
+#define RX_MIN_TARGET 8
+#define RX_DFL_MIN_TARGET 64
+#define RX_MAX_TARGET min_t(int, SOCK_RX_RING_SIZE, 256)
+ unsigned rx_min_target, rx_max_target, rx_target;
+ struct sk_buff_head rx_batch;
+
+ struct timer_list rx_refill_timer;
+
+ struct sk_buff *rx_skbs[SOCK_RX_RING_SIZE];
+ grant_ref_t gref_rx_head;
+ grant_ref_t grant_rx_ref[SOCK_RX_RING_SIZE];
+
+ unsigned long rx_pfn_array[SOCK_RX_RING_SIZE];
+ struct multicall_entry rx_mcl[SOCK_RX_RING_SIZE+1];
+ struct mmu_update rx_mmu[SOCK_RX_RING_SIZE];
+};
+
+struct sockfront_rx_info {
+ struct xen_sockif_rx_response rx;
+};
+
+static void skb_entry_set_link(union skb_entry *list, unsigned short id)
+{
+ list->link = id;
+}
+
+static int skb_entry_is_link(const union skb_entry *list)
+{
+ BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link));
+ return (unsigned long)list->skb < PAGE_OFFSET;
+}
+
+/* Access macros for acquiring freeing slots in tx_skbs[] */
+
+static void add_id_to_freelist(unsigned *head, union skb_entry *list,
+ unsigned short id)
+{
+ skb_entry_set_link(&list[id], *head);
+ *head = id;
+}
+
+static unsigned short get_id_from_freelist(unsigned *head,
+ union skb_entry *list)
+{
+ unsigned int id = *head;
+ *head = list[id].link;
+ return id;
+}
+
+static int xensock_rxidx(RING_IDX idx)
+{
+ return idx & (SOCK_RX_RING_SIZE - 1);
+}
+
+static struct sk_buff *xensock_get_rx_skb(struct sockfront_info *np,
+ RING_IDX ri)
+{
+ int i = xensock_rxidx(ri);
+ struct sk_buff *skb = np->rx_skbs[i];
+
+ np->rx_skbs[i] = NULL;
+ return skb;
+}
+
+static grant_ref_t xensock_get_rx_ref(struct sockfront_info *np,
+ RING_IDX ri)
+{
+ int i = xensock_rxidx(ri);
+ grant_ref_t ref = np->grant_rx_ref[i];
+
+ np->grant_rx_ref[i] = GRANT_INVALID_REF;
+ return ref;
+}
+
+static void rx_refill_timeout(unsigned long data)
+{
+ struct xen_sock_dev *dev = (struct xen_sock_dev *)data;
+ struct sockfront_info *np = xensock_dev_priv(dev);
+
+ tasklet_schedule(&np->rx_poll);
+}
+
+static int sockfront_tx_slot_available(struct sockfront_info *np)
+{
+ return (np->tx.req_prod_pvt - np->tx.rsp_cons) <
+ (TX_MAX_TARGET - MAX_SKB_FRAGS - 2);
+}
+
+static void xensock_maybe_wake_tx(struct xen_sock_dev *dev)
+{
+ struct sockfront_info *np = xensock_dev_priv(dev);
+
+ if (unlikely(sockif_queue_stopped(dev)) &&
+ sockfront_tx_slot_available(np))
+ sockif_wake_queue(dev);
+}
+
+static void xensock_alloc_rx_buffers(struct xen_sock_dev *dev)
+{
+ unsigned short id;
+ struct sockfront_info *np = xensock_dev_priv(dev);
+ struct sk_buff *skb;
+ struct page *page;
+ int i, batch_target, notify;
+ RING_IDX req_prod = np->rx.req_prod_pvt;
+ grant_ref_t ref;
+ unsigned long pfn;
+ void *vaddr;
+ struct xen_sockif_rx_request *req;
+
+ if (unlikely(!sockif_carrier_ok(dev)))
+ return;
+
+ /* Allocate skbuffs greedily, even though we batch updates to the
+ * receive ring. This creates a less bursty demand on the memory
+ * allocator, so should reduce the chance of failed allocation requests
+ * both for ourself and for other kernel subsystems.
+ */
+ batch_target = np->rx_target - (req_prod - np->rx.rsp_cons);
+ for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) {
+ skb = alloc_skb(RX_COPY_THRESHOLD + NET_IP_ALIGN + NET_SKB_PAD,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb))
+ goto no_skb;
+
+ /* Align ip header to a 16 bytes boundary */
+ skb_reserve(skb, NET_IP_ALIGN);
+
+ page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
+ if (!page) {
+ kfree_skb(skb);
+no_skb:
+ /* Any skbuffs queued for refill? Force them out. */
+ if (i != 0)
+ goto refill;
+ /* Could not allocate any skbuffs. Try again later. */
+ mod_timer(&np->rx_refill_timer,
+ jiffies + (HZ/10));
+ break;
+ }
+
+ __skb_fill_page_desc(skb, 0, page, 0, 0);
+ skb_shinfo(skb)->nr_frags = 1;
+ __skb_queue_tail(&np->rx_batch, skb);
+ }
+
+ /* Is the batch large enough to be worthwhile? */
+ if (i < (np->rx_target/2)) {
+ if (req_prod > np->rx.sring->req_prod)
+ goto push;
+ return;
+ }
+
+ /* Adjust our fill target if we risked running out of buffers. */
+ if ((req_prod - np->rx.sring->rsp_prod) < (np->rx_target / 4)) {
+ np->rx_target *= 2;
+ if (np->rx_target > np->rx_max_target)
+ np->rx_target = np->rx_max_target;
+ }
+
+ refill:
+ for (i = 0; ; i++) {
+ skb = __skb_dequeue(&np->rx_batch);
+ if (skb == NULL)
+ break;
+
+ id = xensock_rxidx(req_prod + i);
+
+ BUG_ON(np->rx_skbs[id]);
+ np->rx_skbs[id] = skb;
+
+ ref = gnttab_claim_grant_reference(&np->gref_rx_head);
+ BUG_ON((signed short)ref < 0);
+ np->grant_rx_ref[id] = ref;
+
+ pfn = page_to_pfn(skb_frag_page(&skb_shinfo(skb)->frags[0]));
+ vaddr = page_address(skb_frag_page(&skb_shinfo(skb)->frags[0]));
+
+ req = RING_GET_REQUEST(&np->rx, req_prod + i);
+ gnttab_grant_foreign_access_ref(ref,
+ np->xbdev->otherend_id,
+ pfn_to_mfn(pfn),
+ 0);
+
+ req->id = id;
+ req->gref = ref;
+ }
+
+ wmb(); /* barrier so backend seens requests */
+
+ /* Above is a suitable barrier to ensure backend will see requests. */
+ np->rx.req_prod_pvt = req_prod + i;
+ push:
+ RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->rx, notify);
+ if (notify)
+ notify_remote_via_irq(np->irq);
+}
+
+static void xensock_tx_buf_gc(struct xen_sock_dev *dev)
+{
+ RING_IDX cons, prod;
+ unsigned short id;
+ struct sockfront_info *np = xensock_dev_priv(dev);
+ struct sk_buff *skb;
+
+ BUG_ON(!sockif_carrier_ok(dev));
+
+ do {
+ prod = np->tx.sring->rsp_prod;
+ rmb(); /* Ensure we see responses up to 'rp'. */
+
+ for (cons = np->tx.rsp_cons; cons != prod; cons++) {
+ struct xen_sockif_tx_response *txrsp;
+
+ txrsp = RING_GET_RESPONSE(&np->tx, cons);
+
+ id = txrsp->id;
+ skb = np->tx_skbs[id].skb;
+ if (unlikely(gnttab_query_foreign_access(
+ np->grant_tx_ref[id]) != 0)) {
+ pr_alert("%s: warning -- grant still in use "
+ "by backend domain.\n", __func__);
+ BUG();
+ }
+ gnttab_end_foreign_access_ref(
+ np->grant_tx_ref[id], GNTMAP_readonly);
+ gnttab_release_grant_reference(
+ &np->gref_tx_head, np->grant_tx_ref[id]);
+ np->grant_tx_ref[id] = GRANT_INVALID_REF;
+ add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs,
+ id);
+ dev_kfree_skb_irq(skb);
+ }
+
+ np->tx.rsp_cons = prod;
+
+ /* Set a new event, then check for race with update of tx_cons.
+ * Note that it is essential to schedule a callback, no matter
+ * how few buffers are pending. Even if there is space in the
+ * transmit ring, higher layers may be blocked because too much
+ * data is outstanding: in such cases notification from Xen is
+ * likely to be the only kick that we'll get.
+ */
+ np->tx.sring->rsp_event =
+ prod + ((np->tx.sring->req_prod - prod) >> 1) + 1;
+ mb(); /* update shared area */
+ } while ((cons == prod) && (prod != np->tx.sring->rsp_prod));
+
+ xensock_maybe_wake_tx(dev);
+}
+
+static void xensock_make_frags(struct sk_buff *skb, struct xen_sock_dev *dev,
+ struct xen_sockif_tx_request *tx)
+{
+ struct sockfront_info *np = xensock_dev_priv(dev);
+ char *data = skb->data;
+ unsigned long mfn;
+ RING_IDX prod = np->tx.req_prod_pvt;
+ int frags = skb_shinfo(skb)->nr_frags;
+ unsigned int offset = offset_in_page(data);
+ unsigned int len = skb_headlen(skb);
+ unsigned int id;
+ grant_ref_t ref;
+ int i;
+
+ /* While the header overlaps a page boundary (including being
+ * larger than a page), split it it into page-sized chunks.
+ */
+ while (len > PAGE_SIZE - offset) {
+ tx->size = PAGE_SIZE - offset;
+ tx->flags |= XEN_SOCKTXF_more_data;
+ len -= tx->size;
+ data += tx->size;
+ offset = 0;
+
+ id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
+ np->tx_skbs[id].skb = skb_get(skb);
+ tx = RING_GET_REQUEST(&np->tx, prod++);
+ tx->id = id;
+ ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+ BUG_ON((signed short)ref < 0);
+
+ mfn = virt_to_mfn(data);
+ gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
+ mfn, GNTMAP_readonly);
+
+ tx->gref = ref;
+ np->grant_tx_ref[id] = ref;
+ tx->offset = offset;
+ tx->size = len;
+ tx->flags = 0;
+ }
+
+ /* Grant backend access to each skb fragment page. */
+ for (i = 0; i < frags; i++) {
+ skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+ struct page *page = skb_frag_page(frag);
+
+ len = skb_frag_size(frag);
+ offset = frag->page_offset;
+
+ /* Data must not cross a page boundary. */
+ BUG_ON(len + offset > PAGE_SIZE<<compound_order(page));
+
+ /* Skip unused frames from start of page */
+ page += offset >> PAGE_SHIFT;
+ offset &= ~PAGE_MASK;
+
+ while (len > 0) {
+ unsigned long bytes;
+
+ BUG_ON(offset >= PAGE_SIZE);
+
+ bytes = PAGE_SIZE - offset;
+ if (bytes > len)
+ bytes = len;
+
+ tx->flags |= XEN_SOCKTXF_more_data;
+
+ id = get_id_from_freelist(&np->tx_skb_freelist,
+ np->tx_skbs);
+ np->tx_skbs[id].skb = skb_get(skb);
+ tx = RING_GET_REQUEST(&np->tx, prod++);
+ tx->id = id;
+ ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+ BUG_ON((signed short)ref < 0);
+
+ mfn = pfn_to_mfn(page_to_pfn(page));
+ gnttab_grant_foreign_access_ref(ref,
+ np->xbdev->otherend_id,
+ mfn, GNTMAP_readonly);
+
+ tx->gref = ref;
+ np->grant_tx_ref[id] = ref;
+ tx->offset = offset;
+ tx->size = bytes;
+ tx->flags = 0;
+
+ offset += bytes;
+ len -= bytes;
+
+ /* Next frame */
+ if (offset == PAGE_SIZE && len) {
+ BUG_ON(!PageCompound(page));
+ page++;
+ offset = 0;
+ }
+ }
+ }
+
+ np->tx.req_prod_pvt = prod;
+}
+
+/* Count how many ring slots are required to send the frags of this
+ * skb. Each frag might be a compound page.
+ */
+static int xensock_count_skb_frag_slots(struct sk_buff *skb)
+{
+ int i, frags = skb_shinfo(skb)->nr_frags;
+ int pages = 0;
+
+ for (i = 0; i < frags; i++) {
+ skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+ unsigned long size = skb_frag_size(frag);
+ unsigned long offset = frag->page_offset;
+
+ /* Skip unused frames from start of page */
+ offset &= ~PAGE_MASK;
+
+ pages += PFN_UP(offset + size);
+ }
+
+ return pages;
+}
+
+static int xensock_start_xmit(struct sk_buff *skb, struct xen_sock_dev *dev)
+{
+ unsigned short id;
+ struct sockfront_info *np = xensock_dev_priv(dev);
+ struct xen_sockif_tx_request *tx;
+ char *data = skb->data;
+ RING_IDX i;
+ grant_ref_t ref;
+ unsigned long mfn;
+ int notify;
+ int slots;
+ unsigned int offset = offset_in_page(data);
+ unsigned int len = skb_headlen(skb);
+ unsigned long flags;
+
+ slots = DIV_ROUND_UP(offset + len, PAGE_SIZE) +
+ xensock_count_skb_frag_slots(skb);
+ if (unlikely(slots > MAX_SKB_FRAGS + 1)) {
+ pr_err_ratelimited("xensock: skb rides the rocket: %d slots\n",
+ slots);
+ goto drop;
+ }
+
+ spin_lock_irqsave(&np->tx_lock, flags);
+
+ if (unlikely(!sockif_carrier_ok(dev))) {
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+ goto drop;
+ }
+
+ i = np->tx.req_prod_pvt;
+
+ id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
+ np->tx_skbs[id].skb = skb;
+
+ tx = RING_GET_REQUEST(&np->tx, i);
+
+ tx->id = id;
+ ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+ BUG_ON((signed short)ref < 0);
+ mfn = virt_to_mfn(data);
+ gnttab_grant_foreign_access_ref(
+ ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
+ tx->gref = ref;
+ np->grant_tx_ref[id] = ref;
+ tx->offset = offset;
+ tx->size = len;
+
+ tx->flags = 0;
+
+ np->tx.req_prod_pvt = i + 1;
+
+ xensock_make_frags(skb, dev, tx);
+ tx->size = skb->len;
+
+ RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->tx, notify);
+ if (notify)
+ notify_remote_via_irq(np->irq);
+
+ /* Note: It is not safe to access skb after xensock_tx_buf_gc()! */
+ xensock_tx_buf_gc(dev);
+
+ if (!sockfront_tx_slot_available(np))
+ sockif_stop_queue(dev);
+
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+
+ return 0;
+
+ drop:
+ dev_kfree_skb(skb);
+ return 0;
+}
+
+static void xensock_move_rx_slot(struct sockfront_info *np, struct sk_buff
*skb,
+ grant_ref_t ref)
+{
+ int new = xensock_rxidx(np->rx.req_prod_pvt);
+
+ BUG_ON(np->rx_skbs[new]);
+ np->rx_skbs[new] = skb;
+ np->grant_rx_ref[new] = ref;
+ RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->id = new;
+ RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->gref = ref;
+ np->rx.req_prod_pvt++;
+}
+
+static int xensock_get_responses(struct sockfront_info *np,
+ struct sockfront_rx_info *rinfo, RING_IDX rp,
+ struct sk_buff_head *list)
+{
+ struct xen_sockif_rx_response *rx = &rinfo->rx;
+ struct device *dev = &np->xbdev->dev;
+ RING_IDX cons = np->rx.rsp_cons;
+ struct sk_buff *skb = xensock_get_rx_skb(np, cons);
+ grant_ref_t ref = xensock_get_rx_ref(np, cons);
+ int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD);
+ int frags = 1;
+ int err = 0;
+ unsigned long ret;
+
+ for (;;) {
+ if (unlikely(rx->status < 0 ||
+ rx->offset + rx->status > PAGE_SIZE)) {
+ dev_warn_ratelimited(dev, "rx->offset: %x, size: %u\n",
+ rx->offset, rx->status);
+ xensock_move_rx_slot(np, skb, ref);
+ err = -EINVAL;
+ goto next;
+ }
+
+ /* This definitely indicates a bug, either in this driver or in
+ * the backend driver. In future this should flag the bad
+ * situation to the system controller to reboot the backed.
+ */
+ if (ref == GRANT_INVALID_REF) {
+ dev_warn_ratelimited(dev, "Bad rx response id %d.\n",
+ rx->id);
+ err = -EINVAL;
+ goto next;
+ }
+
+ ret = gnttab_end_foreign_access_ref(ref, 0);
+ BUG_ON(!ret);
+
+ gnttab_release_grant_reference(&np->gref_rx_head, ref);
+
+ __skb_queue_tail(list, skb);
+
+next:
+ if (!(rx->flags & XEN_SOCKRXF_more_data))
+ break;
+
+ if (cons + frags == rp) {
+ dev_warn_ratelimited(dev, "Need more frags\n");
+ err = -ENOENT;
+ break;
+ }
+
+ rx = RING_GET_RESPONSE(&np->rx, cons + frags);
+ skb = xensock_get_rx_skb(np, cons + frags);
+ ref = xensock_get_rx_ref(np, cons + frags);
+ frags++;
+ }
+
+ if (unlikely(frags > max)) {
+ dev_warn_ratelimited(dev, "Too many frags\n");
+ err = -E2BIG;
+ }
+
+ if (unlikely(err))
+ np->rx.rsp_cons = cons + frags;
+
+ return err;
+}
+
+static RING_IDX xensock_fill_frags(struct sockfront_info *np,
+ struct sk_buff *skb,
+ struct sk_buff_head *list)
+{
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+ int nr_frags = shinfo->nr_frags;
+ RING_IDX cons = np->rx.rsp_cons;
+ struct sk_buff *nskb;
+
+ while ((nskb = __skb_dequeue(list))) {
+ struct xen_sockif_rx_response *rx =
+ RING_GET_RESPONSE(&np->rx, ++cons);
+ skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
+
+ __skb_fill_page_desc(skb, nr_frags,
+ skb_frag_page(nfrag),
+ rx->offset, rx->status);
+
+ skb->data_len += rx->status;
+
+ skb_shinfo(nskb)->nr_frags = 0;
+ kfree_skb(nskb);
+
+ nr_frags++;
+ }
+
+ shinfo->nr_frags = nr_frags;
+ return cons;
+}
+
+static int handle_incoming_queue(struct xen_sock_dev *dev,
+ struct sk_buff_head *rxq)
+{
+ int packets_dropped = 0;
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue(rxq)) != NULL) {
+ int pull_to = SOCKFRONT_SKB_CB(skb)->pull_to;
+
+ __pskb_pull_tail(skb, pull_to - skb_headlen(skb));
+
+ /* Pass it up. */
+ xensock_dev_queue_rx_skb(skb, dev);
+ }
+
+ return packets_dropped;
+}
+
+static void xensock_poll(long unsigned int data)
+{
+ struct sockfront_info *np = (struct sockfront_info *)data;
+ struct xen_sock_dev *dev = np->sockdev;
+ struct sk_buff *skb;
+ struct sockfront_rx_info rinfo;
+ struct xen_sockif_rx_response *rx = &rinfo.rx;
+ RING_IDX i, rp;
+ int work_done;
+ struct sk_buff_head rxq;
+ struct sk_buff_head errq;
+ struct sk_buff_head tmpq;
+ unsigned long flags;
+ int err;
+ int budget = 16;
+ int more_to_do = 1;
+
+ spin_lock(&np->rx_lock);
+
+ skb_queue_head_init(&rxq);
+ skb_queue_head_init(&errq);
+ skb_queue_head_init(&tmpq);
+
+ rp = np->rx.sring->rsp_prod;
+ rmb(); /* Ensure we see queued responses up to 'rp'. */
+
+ i = np->rx.rsp_cons;
+ work_done = 0;
+ while ((i != rp) && (work_done < budget)) {
+ memcpy(rx, RING_GET_RESPONSE(&np->rx, i), sizeof(*rx));
+
+ err = xensock_get_responses(np, &rinfo, rp, &tmpq);
+
+ if (unlikely(err)) {
+ while ((skb = __skb_dequeue(&tmpq)))
+ __skb_queue_tail(&errq, skb);
+ i = np->rx.rsp_cons;
+ continue;
+ }
+
+ skb = __skb_dequeue(&tmpq);
+
+ SOCKFRONT_SKB_CB(skb)->pull_to = rx->status;
+ if (SOCKFRONT_SKB_CB(skb)->pull_to > RX_COPY_THRESHOLD)
+ SOCKFRONT_SKB_CB(skb)->pull_to = RX_COPY_THRESHOLD;
+
+ skb_shinfo(skb)->frags[0].page_offset = rx->offset;
+ skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status);
+ skb->data_len = rx->status;
+
+ i = xensock_fill_frags(np, skb, &tmpq);
+
+ /* Truesize is the actual allocation size, even if the
+ * allocation is only partially used.
+ */
+ skb->truesize += PAGE_SIZE * skb_shinfo(skb)->nr_frags;
+ skb->len += skb->data_len;
+
+ __skb_queue_tail(&rxq, skb);
+
+ np->rx.rsp_cons = ++i;
+ work_done++;
+ }
+
+ __skb_queue_purge(&errq);
+
+ work_done -= handle_incoming_queue(dev, &rxq);
+
+ /* If we get a callback with very few responses, reduce fill target. */
+ /* NB. Note exponential increase, linear decrease. */
+ if (((np->rx.req_prod_pvt - np->rx.sring->rsp_prod) >
+ ((3*np->rx_target) / 4)) &&
+ (--np->rx_target < np->rx_min_target))
+ np->rx_target = np->rx_min_target;
+
+ xensock_alloc_rx_buffers(dev);
+
+ if (work_done < budget) {
+ local_irq_save(flags);
+
+ RING_FINAL_CHECK_FOR_RESPONSES(&np->rx, more_to_do);
+
+ local_irq_restore(flags);
+ }
+
+ spin_unlock(&np->rx_lock);
+ if (more_to_do)
+ tasklet_schedule(&np->rx_poll);
+}
+
+static void xensock_release_tx_bufs(struct sockfront_info *np)
+{
+ struct sk_buff *skb;
+ int i;
+
+ for (i = 0; i < SOCK_TX_RING_SIZE; i++) {
+ /* Skip over entries which are actually freelist references */
+ if (skb_entry_is_link(&np->tx_skbs[i]))
+ continue;
+
+ skb = np->tx_skbs[i].skb;
+ gnttab_end_foreign_access_ref(np->grant_tx_ref[i],
+ GNTMAP_readonly);
+ gnttab_release_grant_reference(&np->gref_tx_head,
+ np->grant_tx_ref[i]);
+ np->grant_tx_ref[i] = GRANT_INVALID_REF;
+ add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
+ dev_kfree_skb_irq(skb);
+ }
+}
+
+static void xensock_release_rx_bufs(struct sockfront_info *np)
+{
+ struct mmu_update *mmu = np->rx_mmu;
+ struct multicall_entry *mcl = np->rx_mcl;
+ struct sk_buff_head free_list;
+ struct sk_buff *skb;
+ unsigned long mfn;
+ int xfer = 0, noxfer = 0, unused = 0;
+ int id, ref;
+
+ dev_warn(&np->xbdev->dev, "%s: fix me for copying receiver.\n",
+ __func__);
+ return;
+
+ skb_queue_head_init(&free_list);
+
+ spin_lock_bh(&np->rx_lock);
+
+ for (id = 0; id < SOCK_RX_RING_SIZE; id++) {
+ ref = np->grant_rx_ref[id];
+ if (ref == GRANT_INVALID_REF) {
+ unused++;
+ continue;
+ }
+
+ skb = np->rx_skbs[id];
+ mfn = gnttab_end_foreign_transfer_ref(ref);
+ gnttab_release_grant_reference(&np->gref_rx_head, ref);
+ np->grant_rx_ref[id] = GRANT_INVALID_REF;
+
+ if (0 == mfn) {
+ skb_shinfo(skb)->nr_frags = 0;
+ dev_kfree_skb(skb);
+ noxfer++;
+ continue;
+ }
+
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ /* Remap the page. */
+ const struct page *page =
+ skb_frag_page(&skb_shinfo(skb)->frags[0]);
+ unsigned long pfn = page_to_pfn(page);
+ void *vaddr = page_address(page);
+
+ MULTI_update_va_mapping(mcl, (unsigned long)vaddr,
+ mfn_pte(mfn, PAGE_KERNEL),
+ 0);
+ mcl++;
+ mmu->ptr = ((u64)mfn << PAGE_SHIFT)
+ | MMU_MACHPHYS_UPDATE;
+ mmu->val = pfn;
+ mmu++;
+
+ set_phys_to_machine(pfn, mfn);
+ }
+ __skb_queue_tail(&free_list, skb);
+ xfer++;
+ }
+
+ dev_info(&np->xbdev->dev, "%s: %d xfer, %d noxfer, %d unused\n",
+ __func__, xfer, noxfer, unused);
+
+ if (xfer) {
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ /* Do all the remapping work and M2P updates. */
+ MULTI_mmu_update(mcl, np->rx_mmu, mmu - np->rx_mmu,
+ NULL, DOMID_SELF);
+ mcl++;
+ HYPERVISOR_multicall(np->rx_mcl, mcl - np->rx_mcl);
+ }
+ }
+
+ __skb_queue_purge(&free_list);
+
+ spin_unlock_bh(&np->rx_lock);
+}
+
+static void xensock_uninit(struct xen_sock_dev *dev)
+{
+ struct sockfront_info *np = xensock_dev_priv(dev);
+
+ xensock_release_tx_bufs(np);
+ xensock_release_rx_bufs(np);
+ gnttab_free_grant_references(np->gref_tx_head);
+ gnttab_free_grant_references(np->gref_rx_head);
+}
+
+static irqreturn_t xensock_interrupt(int irq, void *dev_id)
+{
+ struct xen_sock_dev *dev = dev_id;
+ struct sockfront_info *np = xensock_dev_priv(dev);
+ unsigned long flags;
+
+ spin_lock_irqsave(&np->tx_lock, flags);
+
+ if (likely(sockif_carrier_ok(dev))) {
+ xensock_tx_buf_gc(dev);
+ /* Under tx_lock: protects access to rx shared-ring indexes. */
+ if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
+ tasklet_schedule(&np->rx_poll);
+ }
+
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+
+ return IRQ_HANDLED;
+}
+
+static struct xen_sock_dev *xensock_create_dev(struct xenbus_device *dev)
+{
+ int i, err;
+ struct xen_sock_dev *sockdev;
+ struct sockfront_info *np;
+
+ sockdev = alloc_xen_sock_dev(sizeof(struct sockfront_info), "vsock");
+ if (!sockdev)
+ return ERR_PTR(-ENOMEM);
+
+ np = xensock_dev_priv(sockdev);
+ np->xbdev = dev;
+
+ spin_lock_init(&np->tx_lock);
+ spin_lock_init(&np->rx_lock);
+
+ skb_queue_head_init(&np->rx_batch);
+ np->rx_target = RX_DFL_MIN_TARGET;
+ np->rx_min_target = RX_DFL_MIN_TARGET;
+ np->rx_max_target = RX_MAX_TARGET;
+
+ init_timer(&np->rx_refill_timer);
+ np->rx_refill_timer.data = (unsigned long)sockdev;
+ np->rx_refill_timer.function = rx_refill_timeout;
+
+ /* Initialise tx_skbs as a free chain containing every entry. */
+ np->tx_skb_freelist = 0;
+ for (i = 0; i < SOCK_TX_RING_SIZE; i++) {
+ skb_entry_set_link(&np->tx_skbs[i], i+1);
+ np->grant_tx_ref[i] = GRANT_INVALID_REF;
+ }
+
+ /* Clear out rx_skbs */
+ for (i = 0; i < SOCK_RX_RING_SIZE; i++) {
+ np->rx_skbs[i] = NULL;
+ np->grant_rx_ref[i] = GRANT_INVALID_REF;
+ }
+
+ /* A grant for every tx ring slot */
+ if (gnttab_alloc_grant_references(TX_MAX_TARGET,
+ &np->gref_tx_head) < 0) {
+ pr_alert("#### sockfront can't alloc tx grant refs\n");
+ err = -ENOMEM;
+ goto exit;
+ }
+ /* A grant for every rx ring slot */
+ if (gnttab_alloc_grant_references(RX_MAX_TARGET,
+ &np->gref_rx_head) < 0) {
+ pr_alert("#### sockfront can't alloc rx grant refs\n");
+ err = -ENOMEM;
+ goto exit_free_tx;
+ }
+
+ tasklet_init(&np->rx_poll, xensock_poll, (unsigned long)np);
+
+ sockdev->start_xmit = xensock_start_xmit;
+
+ np->sockdev = sockdev;
+
+ sockif_carrier_off(sockdev);
+
+ return sockdev;
+
+ exit_free_tx:
+ gnttab_free_grant_references(np->gref_tx_head);
+ exit:
+ free_xen_sock_dev(sockdev);
+ return ERR_PTR(err);
+}
+
+static void xensock_end_access(int ref, void *page)
+{
+ /* This frees the page as a side-effect */
+ if (ref != GRANT_INVALID_REF)
+ gnttab_end_foreign_access(ref, 0, (unsigned long)page);
+}
+
+static void xensock_disconnect_backend(struct sockfront_info *info)
+{
+ /* Stop old i/f to prevent errors whilst we rebuild the state. */
+ spin_lock_bh(&info->rx_lock);
+ spin_lock_irq(&info->tx_lock);
+ sockif_carrier_off(info->sockdev);
+ spin_unlock_irq(&info->tx_lock);
+ spin_unlock_bh(&info->rx_lock);
+
+ if (info->irq)
+ unbind_from_irqhandler(info->irq, info);
+ info->evtchn = 0;
+ info->irq = 0;
+
+ /* End access and free the pages */
+ xensock_end_access(info->tx_ring_ref, info->tx.sring);
+ xensock_end_access(info->rx_ring_ref, info->rx.sring);
+
+ info->tx_ring_ref = GRANT_INVALID_REF;
+ info->rx_ring_ref = GRANT_INVALID_REF;
+ info->tx.sring = NULL;
+ info->rx.sring = NULL;
+}
+
+static int setup_sockfront(struct xenbus_device *dev,
+ struct sockfront_info *info)
+{
+ struct xen_sockif_tx_sring *txs;
+ struct xen_sockif_rx_sring *rxs;
+ int err;
+
+ info->tx_ring_ref = GRANT_INVALID_REF;
+ info->rx_ring_ref = GRANT_INVALID_REF;
+ info->rx.sring = NULL;
+ info->tx.sring = NULL;
+ info->irq = 0;
+
+ txs = (struct xen_sockif_tx_sring *)get_zeroed_page(GFP_NOIO |
+ __GFP_HIGH);
+ if (!txs) {
+ err = -ENOMEM;
+ xenbus_dev_fatal(dev, err, "allocating tx ring page");
+ goto fail;
+ }
+ SHARED_RING_INIT(txs);
+ FRONT_RING_INIT(&info->tx, txs, PAGE_SIZE);
+
+ err = xenbus_grant_ring(dev, virt_to_mfn(txs));
+ if (err < 0) {
+ free_page((unsigned long)txs);
+ goto fail;
+ }
+
+ info->tx_ring_ref = err;
+ rxs = (struct xen_sockif_rx_sring *)get_zeroed_page(GFP_NOIO |
+ __GFP_HIGH);
+ if (!rxs) {
+ err = -ENOMEM;
+ xenbus_dev_fatal(dev, err, "allocating rx ring page");
+ goto fail;
+ }
+ SHARED_RING_INIT(rxs);
+ FRONT_RING_INIT(&info->rx, rxs, PAGE_SIZE);
+
+ err = xenbus_grant_ring(dev, virt_to_mfn(rxs));
+ if (err < 0) {
+ free_page((unsigned long)rxs);
+ goto fail;
+ }
+ info->rx_ring_ref = err;
+
+ err = xenbus_alloc_evtchn(dev, &info->evtchn);
+ if (err)
+ goto fail;
+
+ err = bind_evtchn_to_irqhandler(info->evtchn, xensock_interrupt,
+ 0, "sockif", info->sockdev);
+ if (err < 0)
+ goto fail;
+ info->irq = err;
+ return 0;
+
+ fail:
+ return err;
+}
+
+/* Common code used when first setting up, and when resuming. */
+static int talk_to_sockback(struct xenbus_device *dev,
+ struct sockfront_info *info)
+{
+ const char *message;
+ struct xenbus_transaction xbt;
+ int err;
+
+ /* Create shared ring, alloc event channel. */
+ err = setup_sockfront(dev, info);
+ if (err)
+ goto out;
+
+again:
+ err = xenbus_transaction_start(&xbt);
+ if (err) {
+ xenbus_dev_fatal(dev, err, "starting transaction");
+ goto destroy_ring;
+ }
+
+ err = xenbus_printf(xbt, dev->nodename, "tx-ring-ref", "%u",
+ info->tx_ring_ref);
+ if (err) {
+ message = "writing tx ring-ref";
+ goto abort_transaction;
+ }
+ err = xenbus_printf(xbt, dev->nodename, "rx-ring-ref", "%u",
+ info->rx_ring_ref);
+ if (err) {
+ message = "writing rx ring-ref";
+ goto abort_transaction;
+ }
+ err = xenbus_printf(xbt, dev->nodename,
+ "event-channel", "%u", info->evtchn);
+ if (err) {
+ message = "writing event-channel";
+ goto abort_transaction;
+ }
+
+ err = xenbus_printf(xbt, dev->nodename, "request-rx-copy", "%u",
+ 1);
+ if (err) {
+ message = "writing request-rx-copy";
+ goto abort_transaction;
+ }
+
+ err = xenbus_printf(xbt, dev->nodename, "feature-rx-notify", "%d", 1);
+ if (err) {
+ message = "writing feature-rx-notify";
+ goto abort_transaction;
+ }
+
+ err = xenbus_transaction_end(xbt, 0);
+ if (err) {
+ if (err == -EAGAIN)
+ goto again;
+ xenbus_dev_fatal(dev, err, "completing transaction");
+ goto destroy_ring;
+ }
+
+ xenbus_switch_state(dev, XenbusStateInitialised);
+ return 0;
+
+ abort_transaction:
+ xenbus_transaction_end(xbt, 1);
+ xenbus_dev_fatal(dev, err, "%s", message);
+ destroy_ring:
+ xensock_disconnect_backend(info);
+ out:
+ return err;
+}
+
+/**
+ * We are reconnecting to the backend, due to a suspend/resume, or a backend
+ * driver restart. We tear down our sockif structure and recreate it, but
+ * leave the device-layer structures intact so that this is transparent to the
+ * rest of the kernel.
+ */
+static int sockfront_resume(struct xenbus_device *dev)
+{
+ struct sockfront_info *info = dev_get_drvdata(&dev->dev);
+
+ dev_dbg(&dev->dev, "%s\n", dev->nodename);
+
+ xensock_disconnect_backend(info);
+ return talk_to_sockback(info->xbdev, info);
+}
+
+/**
+ * Entry point to this code when a new device is created. Allocate the basic
+ * structures and the ring buffers for communication with the backend, and
+ * inform the backend of the appropriate details for those.
+ */
+static int sockfront_probe(struct xenbus_device *dev,
+ const struct xenbus_device_id *id)
+{
+ int err;
+ struct xen_sock_dev *sockdev;
+ struct sockfront_info *info;
+
+ sockdev = xensock_create_dev(dev);
+ if (IS_ERR(sockdev)) {
+ err = PTR_ERR(sockdev);
+ xenbus_dev_fatal(dev, err, "creating sockdev");
+ return err;
+ }
+
+ info = xensock_dev_priv(sockdev);
+ dev_set_drvdata(&dev->dev, info);
+
+ err = xensock_register_dev(info->sockdev);
+ if (err) {
+ pr_warn("%s: xensock_register_dev err=%d\n",
+ __func__, err);
+ goto fail;
+ }
+
+ err = talk_to_sockback(info->xbdev, info);
+ if (err)
+ goto fail;
+
+ return 0;
+
+ fail:
+ free_xen_sock_dev(sockdev);
+ dev_set_drvdata(&dev->dev, NULL);
+ return err;
+}
+
+static int xensock_connect(struct xen_sock_dev *dev)
+{
+ struct sockfront_info *np = xensock_dev_priv(dev);
+ int i, requeue_idx, err;
+ struct sk_buff *skb;
+ grant_ref_t ref;
+ struct xen_sockif_rx_request *req;
+ unsigned int feature_rx_copy;
+
+ err = xenbus_scanf(XBT_NIL, np->xbdev->otherend,
+ "feature-rx-copy", "%u", &feature_rx_copy);
+ if (err != 1)
+ feature_rx_copy = 0;
+
+ if (!feature_rx_copy) {
+ dev_info(&np->xbdev->dev,
+ "backend does not support copying receive path\n");
+ return -ENODEV;
+ }
+
+ spin_lock_bh(&np->rx_lock);
+ spin_lock_irq(&np->tx_lock);
+
+ /* Step 1: Discard all pending TX packet fragments. */
+ xensock_release_tx_bufs(np);
+
+ /* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */
+ for (requeue_idx = 0, i = 0; i < SOCK_RX_RING_SIZE; i++) {
+ skb_frag_t *frag;
+ const struct page *page;
+
+ if (!np->rx_skbs[i])
+ continue;
+
+ skb = xensock_get_rx_skb(np, i);
+ np->rx_skbs[requeue_idx] = skb;
+ ref = xensock_get_rx_ref(np, i);
+ np->grant_rx_ref[requeue_idx] = ref;
+ req = RING_GET_REQUEST(&np->rx, requeue_idx);
+
+ frag = &skb_shinfo(skb)->frags[0];
+ page = skb_frag_page(frag);
+ gnttab_grant_foreign_access_ref(
+ ref, np->xbdev->otherend_id,
+ pfn_to_mfn(page_to_pfn(page)),
+ 0);
+ req->gref = ref;
+ req->id = requeue_idx;
+
+ requeue_idx++;
+ }
+
+ np->rx.req_prod_pvt = requeue_idx;
+
+ /* Step 3: All public and private state should now be sane. Get
+ * ready to start sending and receiving packets and give the driver
+ * domain a kick because we've probably just requeued some
+ * packets.
+ */
+ sockif_carrier_on(np->sockdev);
+ notify_remote_via_irq(np->irq);
+ xensock_tx_buf_gc(dev);
+ xensock_alloc_rx_buffers(dev);
+
+ spin_unlock_irq(&np->tx_lock);
+ spin_unlock_bh(&np->rx_lock);
+
+ return 0;
+}
+
+/**
+ * Callback received when the backend's state changes.
+ */
+static void sockback_changed(struct xenbus_device *dev,
+ enum xenbus_state backend_state)
+{
+ struct sockfront_info *np = dev_get_drvdata(&dev->dev);
+ struct xen_sock_dev *sockdev = np->sockdev;
+
+ dev_dbg(&dev->dev, "sockfront:sndback_changed to state %s\n",
+ xenbus_strstate(backend_state));
+
+ switch (backend_state) {
+ case XenbusStateInitialising:
+ case XenbusStateInitWait:
+ case XenbusStateInitialised:
+ case XenbusStateReconfiguring:
+ case XenbusStateReconfigured:
+ case XenbusStateUnknown:
+ case XenbusStateClosed:
+ break;
+
+ case XenbusStateConnected:
+ if (xensock_connect(sockdev) != 0)
+ break;
+ xenbus_switch_state(dev, XenbusStateConnected);
+ break;
+
+ case XenbusStateClosing:
+ xenbus_frontend_closed(dev);
+ break;
+ }
+}
+
+static const struct xenbus_device_id sockfront_ids[] = {
+ { "vsock" },
+ { "" }
+};
+
+
+static int sockfront_remove(struct xenbus_device *dev)
+{
+ struct sockfront_info *info = dev_get_drvdata(&dev->dev);
+
+ dev_dbg(&dev->dev, "%s\n", dev->nodename);
+
+ xensock_disconnect_backend(info);
+
+ xensock_unregister_dev(info->sockdev);
+
+ tasklet_disable(&info->rx_poll);
+ tasklet_kill(&info->rx_poll);
+ xensock_uninit(info->sockdev);
+
+ del_timer_sync(&info->rx_refill_timer);
+
+ free_xen_sock_dev(info->sockdev);
+
+ return 0;
+}
+
+static DEFINE_XENBUS_DRIVER(sockfront, ,
+ .probe = sockfront_probe,
+ .remove = sockfront_remove,
+ .resume = sockfront_resume,
+ .otherend_changed = sockback_changed,
+);
+
+static int __init sockif_init(void)
+{
+ int ret;
+
+ /*FIXME: xen_pv_domain() should be here, but ARM hardcoded to hvm*/
+ if (!xen_domain())
+ return -ENODEV;
+
+ /* Nothing to do if running in dom0. */
+ if (xen_initial_domain())
+ return -ENODEV;
+
+ pr_info("Initialising Xen socket driver.\n");
+
+ ret = xenbus_register_frontend(&sockfront_driver);
+ if (ret < 0)
+ return ret;
+
+ ret = xensock_proto_client_init();
+ if (ret)
+ goto err_unregister_frontend;
+
+ return ret;
+
+err_unregister_frontend:
+ xenbus_unregister_driver(&sockfront_driver);
+ return ret;
+}
+module_init(sockif_init);
+
+
+static void __exit sockif_exit(void)
+{
+ xensock_proto_cleanup();
+ xenbus_unregister_driver(&sockfront_driver);
+}
+module_exit(sockif_exit);
+
+MODULE_DESCRIPTION("Xensock device frontend");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:xensock");
--
1.8.2.rc2
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |