From 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Tue, 4 Aug 2015 12:17:53 -0700 Subject: Add the rt linux 4.1.3-rt3 as base Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang --- kernel/drivers/net/xen-netback/Makefile | 3 + kernel/drivers/net/xen-netback/common.h | 347 +++++ kernel/drivers/net/xen-netback/interface.c | 689 ++++++++++ kernel/drivers/net/xen-netback/netback.c | 2049 ++++++++++++++++++++++++++++ kernel/drivers/net/xen-netback/xenbus.c | 1043 ++++++++++++++ 5 files changed, 4131 insertions(+) create mode 100644 kernel/drivers/net/xen-netback/Makefile create mode 100644 kernel/drivers/net/xen-netback/common.h create mode 100644 kernel/drivers/net/xen-netback/interface.c create mode 100644 kernel/drivers/net/xen-netback/netback.c create mode 100644 kernel/drivers/net/xen-netback/xenbus.c (limited to 'kernel/drivers/net/xen-netback') diff --git a/kernel/drivers/net/xen-netback/Makefile b/kernel/drivers/net/xen-netback/Makefile new file mode 100644 index 000000000..e346e8125 --- /dev/null +++ b/kernel/drivers/net/xen-netback/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_XEN_NETDEV_BACKEND) := xen-netback.o + +xen-netback-y := netback.o xenbus.o interface.o diff --git a/kernel/drivers/net/xen-netback/common.h b/kernel/drivers/net/xen-netback/common.h new file mode 100644 index 000000000..8a495b318 --- /dev/null +++ b/kernel/drivers/net/xen-netback/common.h @@ -0,0 +1,347 @@ +/* + * 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. + */ + +#ifndef __XEN_NETBACK__COMMON_H__ +#define __XEN_NETBACK__COMMON_H__ + +#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +typedef unsigned int pending_ring_idx_t; +#define INVALID_PENDING_RING_IDX (~0U) + +struct pending_tx_info { + struct xen_netif_tx_request req; /* tx request */ + /* Callback data for released SKBs. The callback is always + * xenvif_zerocopy_callback, desc contains the pending_idx, which is + * also an index in pending_tx_info array. It is initialized in + * xenvif_alloc and it never changes. + * skb_shinfo(skb)->destructor_arg points to the first mapped slot's + * callback_struct in this array of struct pending_tx_info's, then ctx + * to the next, or NULL if there is no more slot for this skb. + * ubuf_to_vif is a helper which finds the struct xenvif from a pointer + * to this field. + */ + struct ubuf_info callback_struct; +}; + +#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE) +#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE) + +struct xenvif_rx_meta { + int id; + int size; + int gso_type; + int gso_size; +}; + +#define GSO_BIT(type) \ + (1 << XEN_NETIF_GSO_TYPE_ ## type) + +/* Discriminate from any valid pending_idx value. */ +#define INVALID_PENDING_IDX 0xFFFF + +#define MAX_BUFFER_OFFSET PAGE_SIZE + +#define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE + +/* It's possible for an skb to have a maximal number of frags + * but still be less than MAX_BUFFER_OFFSET in size. Thus the + * worst-case number of copy operations is MAX_SKB_FRAGS per + * ring slot. + */ +#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE) + +#define NETBACK_INVALID_HANDLE -1 + +/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating + * the maximum slots a valid packet can use. Now this value is defined + * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by + * all backend. + */ +#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN + +/* Queue name is interface name with "-qNNN" appended */ +#define QUEUE_NAME_SIZE (IFNAMSIZ + 5) + +/* IRQ name is queue name with "-tx" or "-rx" appended */ +#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) + +struct xenvif; + +struct xenvif_stats { + /* Stats fields to be updated per-queue. + * A subset of struct net_device_stats that contains only the + * fields that are updated in netback.c for each queue. + */ + unsigned int rx_bytes; + unsigned int rx_packets; + unsigned int tx_bytes; + unsigned int tx_packets; + + /* Additional stats used by xenvif */ + unsigned long rx_gso_checksum_fixup; + unsigned long tx_zerocopy_sent; + unsigned long tx_zerocopy_success; + unsigned long tx_zerocopy_fail; + unsigned long tx_frag_overflow; +}; + +struct xenvif_queue { /* Per-queue data for xenvif */ + unsigned int id; /* Queue ID, 0-based */ + char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */ + struct xenvif *vif; /* Parent VIF */ + + /* Use NAPI for guest TX */ + struct napi_struct napi; + /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ + unsigned int tx_irq; + /* Only used when feature-split-event-channels = 1 */ + char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */ + struct xen_netif_tx_back_ring tx; + struct sk_buff_head tx_queue; + struct page *mmap_pages[MAX_PENDING_REQS]; + pending_ring_idx_t pending_prod; + pending_ring_idx_t pending_cons; + u16 pending_ring[MAX_PENDING_REQS]; + struct pending_tx_info pending_tx_info[MAX_PENDING_REQS]; + grant_handle_t grant_tx_handle[MAX_PENDING_REQS]; + + struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS]; + struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS]; + struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS]; + /* passed to gnttab_[un]map_refs with pages under (un)mapping */ + struct page *pages_to_map[MAX_PENDING_REQS]; + struct page *pages_to_unmap[MAX_PENDING_REQS]; + + /* This prevents zerocopy callbacks to race over dealloc_ring */ + spinlock_t callback_lock; + /* This prevents dealloc thread and NAPI instance to race over response + * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err + * it only protect response creation + */ + spinlock_t response_lock; + pending_ring_idx_t dealloc_prod; + pending_ring_idx_t dealloc_cons; + u16 dealloc_ring[MAX_PENDING_REQS]; + struct task_struct *dealloc_task; + wait_queue_head_t dealloc_wq; + atomic_t inflight_packets; + + /* Use kthread for guest RX */ + struct task_struct *task; + wait_queue_head_t wq; + /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ + unsigned int rx_irq; + /* Only used when feature-split-event-channels = 1 */ + char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */ + struct xen_netif_rx_back_ring rx; + struct sk_buff_head rx_queue; + + unsigned int rx_queue_max; + unsigned int rx_queue_len; + unsigned long last_rx_time; + bool stalled; + + struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS]; + + /* We create one meta structure per ring request we consume, so + * the maximum number is the same as the ring size. + */ + struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE]; + + /* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */ + unsigned long credit_bytes; + unsigned long credit_usec; + unsigned long remaining_credit; + struct timer_list credit_timeout; + u64 credit_window_start; + + /* Statistics */ + struct xenvif_stats stats; +}; + +/* Maximum number of Rx slots a to-guest packet may use, including the + * slot needed for GSO meta-data. + */ +#define XEN_NETBK_RX_SLOTS_MAX (MAX_SKB_FRAGS + 1) + +enum state_bit_shift { + /* This bit marks that the vif is connected */ + VIF_STATUS_CONNECTED, +}; + +struct xenvif { + /* Unique identifier for this interface. */ + domid_t domid; + unsigned int handle; + + u8 fe_dev_addr[6]; + + /* Frontend feature information. */ + int gso_mask; + int gso_prefix_mask; + + u8 can_sg:1; + u8 ip_csum:1; + u8 ipv6_csum:1; + + /* Is this interface disabled? True when backend discovers + * frontend is rogue. + */ + bool disabled; + unsigned long status; + unsigned long drain_timeout; + unsigned long stall_timeout; + + /* Queues */ + struct xenvif_queue *queues; + unsigned int num_queues; /* active queues, resource allocated */ + unsigned int stalled_queues; + + struct xenbus_watch credit_watch; + + spinlock_t lock; + +#ifdef CONFIG_DEBUG_FS + struct dentry *xenvif_dbg_root; +#endif + + /* Miscellaneous private stuff. */ + struct net_device *dev; +}; + +struct xenvif_rx_cb { + unsigned long expires; + int meta_slots_used; +}; + +#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) + +static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif) +{ + return to_xenbus_device(vif->dev->dev.parent); +} + +void xenvif_tx_credit_callback(unsigned long data); + +struct xenvif *xenvif_alloc(struct device *parent, + domid_t domid, + unsigned int handle); + +int xenvif_init_queue(struct xenvif_queue *queue); +void xenvif_deinit_queue(struct xenvif_queue *queue); + +int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, + unsigned long rx_ring_ref, unsigned int tx_evtchn, + unsigned int rx_evtchn); +void xenvif_disconnect(struct xenvif *vif); +void xenvif_free(struct xenvif *vif); + +int xenvif_xenbus_init(void); +void xenvif_xenbus_fini(void); + +int xenvif_schedulable(struct xenvif *vif); + +int xenvif_queue_stopped(struct xenvif_queue *queue); +void xenvif_wake_queue(struct xenvif_queue *queue); + +/* (Un)Map communication rings. */ +void xenvif_unmap_frontend_rings(struct xenvif_queue *queue); +int xenvif_map_frontend_rings(struct xenvif_queue *queue, + grant_ref_t tx_ring_ref, + grant_ref_t rx_ring_ref); + +/* Check for SKBs from frontend and schedule backend processing */ +void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue); + +/* Prevent the device from generating any further traffic. */ +void xenvif_carrier_off(struct xenvif *vif); + +int xenvif_tx_action(struct xenvif_queue *queue, int budget); + +int xenvif_kthread_guest_rx(void *data); +void xenvif_kick_thread(struct xenvif_queue *queue); + +int xenvif_dealloc_kthread(void *data); + +void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); + +/* Determine whether the needed number of slots (req) are available, + * and set req_event if not. + */ +bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed); + +void xenvif_carrier_on(struct xenvif *vif); + +/* Callback from stack when TX packet can be released */ +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); + +/* Unmap a pending page and release it back to the guest */ +void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); + +static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue) +{ + return MAX_PENDING_REQS - + queue->pending_prod + queue->pending_cons; +} + +/* Callback from stack when TX packet can be released */ +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); + +irqreturn_t xenvif_interrupt(int irq, void *dev_id); + +extern bool separate_tx_rx_irq; + +extern unsigned int rx_drain_timeout_msecs; +extern unsigned int rx_stall_timeout_msecs; +extern unsigned int xenvif_max_queues; + +#ifdef CONFIG_DEBUG_FS +extern struct dentry *xen_netback_dbg_root; +#endif + +void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue, + struct sk_buff *skb); +void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue); + +#endif /* __XEN_NETBACK__COMMON_H__ */ diff --git a/kernel/drivers/net/xen-netback/interface.c b/kernel/drivers/net/xen-netback/interface.c new file mode 100644 index 000000000..1a83e190f --- /dev/null +++ b/kernel/drivers/net/xen-netback/interface.c @@ -0,0 +1,689 @@ +/* + * Network-device interface management. + * + * Copyright (c) 2004-2005, Keir Fraser + * + * 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 "common.h" + +#include +#include +#include +#include +#include + +#include +#include +#include + +#define XENVIF_QUEUE_LENGTH 32 +#define XENVIF_NAPI_WEIGHT 64 + +/* Number of bytes allowed on the internal guest Rx queue. */ +#define XENVIF_RX_QUEUE_BYTES (XEN_NETIF_RX_RING_SIZE/2 * PAGE_SIZE) + +/* This function is used to set SKBTX_DEV_ZEROCOPY as well as + * increasing the inflight counter. We need to increase the inflight + * counter because core driver calls into xenvif_zerocopy_callback + * which calls xenvif_skb_zerocopy_complete. + */ +void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue, + struct sk_buff *skb) +{ + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + atomic_inc(&queue->inflight_packets); +} + +void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue) +{ + atomic_dec(&queue->inflight_packets); +} + +int xenvif_schedulable(struct xenvif *vif) +{ + return netif_running(vif->dev) && + test_bit(VIF_STATUS_CONNECTED, &vif->status) && + !vif->disabled; +} + +static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) +{ + struct xenvif_queue *queue = dev_id; + + if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)) + napi_schedule(&queue->napi); + + return IRQ_HANDLED; +} + +static int xenvif_poll(struct napi_struct *napi, int budget) +{ + struct xenvif_queue *queue = + container_of(napi, struct xenvif_queue, napi); + int work_done; + + /* This vif is rogue, we pretend we've there is nothing to do + * for this vif to deschedule it from NAPI. But this interface + * will be turned off in thread context later. + */ + if (unlikely(queue->vif->disabled)) { + napi_complete(napi); + return 0; + } + + work_done = xenvif_tx_action(queue, budget); + + if (work_done < budget) { + napi_complete(napi); + xenvif_napi_schedule_or_enable_events(queue); + } + + return work_done; +} + +static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) +{ + struct xenvif_queue *queue = dev_id; + + xenvif_kick_thread(queue); + + return IRQ_HANDLED; +} + +irqreturn_t xenvif_interrupt(int irq, void *dev_id) +{ + xenvif_tx_interrupt(irq, dev_id); + xenvif_rx_interrupt(irq, dev_id); + + return IRQ_HANDLED; +} + +int xenvif_queue_stopped(struct xenvif_queue *queue) +{ + struct net_device *dev = queue->vif->dev; + unsigned int id = queue->id; + return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id)); +} + +void xenvif_wake_queue(struct xenvif_queue *queue) +{ + struct net_device *dev = queue->vif->dev; + unsigned int id = queue->id; + netif_tx_wake_queue(netdev_get_tx_queue(dev, id)); +} + +static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct xenvif *vif = netdev_priv(dev); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + u16 index; + struct xenvif_rx_cb *cb; + + BUG_ON(skb->dev != dev); + + /* Drop the packet if queues are not set up */ + if (num_queues < 1) + goto drop; + + /* Obtain the queue to be used to transmit this packet */ + index = skb_get_queue_mapping(skb); + if (index >= num_queues) { + pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n.", + index, vif->dev->name); + index %= num_queues; + } + queue = &vif->queues[index]; + + /* Drop the packet if queue is not ready */ + if (queue->task == NULL || + queue->dealloc_task == NULL || + !xenvif_schedulable(vif)) + goto drop; + + cb = XENVIF_RX_CB(skb); + cb->expires = jiffies + vif->drain_timeout; + + xenvif_rx_queue_tail(queue, skb); + xenvif_kick_thread(queue); + + return NETDEV_TX_OK; + + drop: + vif->dev->stats.tx_dropped++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} + +static struct net_device_stats *xenvif_get_stats(struct net_device *dev) +{ + struct xenvif *vif = netdev_priv(dev); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned long rx_bytes = 0; + unsigned long rx_packets = 0; + unsigned long tx_bytes = 0; + unsigned long tx_packets = 0; + unsigned int index; + + if (vif->queues == NULL) + goto out; + + /* Aggregate tx and rx stats from each queue */ + for (index = 0; index < num_queues; ++index) { + queue = &vif->queues[index]; + rx_bytes += queue->stats.rx_bytes; + rx_packets += queue->stats.rx_packets; + tx_bytes += queue->stats.tx_bytes; + tx_packets += queue->stats.tx_packets; + } + +out: + vif->dev->stats.rx_bytes = rx_bytes; + vif->dev->stats.rx_packets = rx_packets; + vif->dev->stats.tx_bytes = tx_bytes; + vif->dev->stats.tx_packets = tx_packets; + + return &vif->dev->stats; +} + +static void xenvif_up(struct xenvif *vif) +{ + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + napi_enable(&queue->napi); + enable_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + enable_irq(queue->rx_irq); + xenvif_napi_schedule_or_enable_events(queue); + } +} + +static void xenvif_down(struct xenvif *vif) +{ + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + disable_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + disable_irq(queue->rx_irq); + napi_disable(&queue->napi); + del_timer_sync(&queue->credit_timeout); + } +} + +static int xenvif_open(struct net_device *dev) +{ + struct xenvif *vif = netdev_priv(dev); + if (test_bit(VIF_STATUS_CONNECTED, &vif->status)) + xenvif_up(vif); + netif_tx_start_all_queues(dev); + return 0; +} + +static int xenvif_close(struct net_device *dev) +{ + struct xenvif *vif = netdev_priv(dev); + if (test_bit(VIF_STATUS_CONNECTED, &vif->status)) + xenvif_down(vif); + netif_tx_stop_all_queues(dev); + return 0; +} + +static int xenvif_change_mtu(struct net_device *dev, int mtu) +{ + struct xenvif *vif = netdev_priv(dev); + int max = vif->can_sg ? 65535 - VLAN_ETH_HLEN : ETH_DATA_LEN; + + if (mtu > max) + return -EINVAL; + dev->mtu = mtu; + return 0; +} + +static netdev_features_t xenvif_fix_features(struct net_device *dev, + netdev_features_t features) +{ + struct xenvif *vif = netdev_priv(dev); + + if (!vif->can_sg) + features &= ~NETIF_F_SG; + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4)) + features &= ~NETIF_F_TSO; + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6)) + features &= ~NETIF_F_TSO6; + if (!vif->ip_csum) + features &= ~NETIF_F_IP_CSUM; + if (!vif->ipv6_csum) + features &= ~NETIF_F_IPV6_CSUM; + + return features; +} + +static const struct xenvif_stat { + char name[ETH_GSTRING_LEN]; + u16 offset; +} xenvif_stats[] = { + { + "rx_gso_checksum_fixup", + offsetof(struct xenvif_stats, rx_gso_checksum_fixup) + }, + /* If (sent != success + fail), there are probably packets never + * freed up properly! + */ + { + "tx_zerocopy_sent", + offsetof(struct xenvif_stats, tx_zerocopy_sent), + }, + { + "tx_zerocopy_success", + offsetof(struct xenvif_stats, tx_zerocopy_success), + }, + { + "tx_zerocopy_fail", + offsetof(struct xenvif_stats, tx_zerocopy_fail) + }, + /* Number of packets exceeding MAX_SKB_FRAG slots. You should use + * a guest with the same MAX_SKB_FRAG + */ + { + "tx_frag_overflow", + offsetof(struct xenvif_stats, tx_frag_overflow) + }, +}; + +static int xenvif_get_sset_count(struct net_device *dev, int string_set) +{ + switch (string_set) { + case ETH_SS_STATS: + return ARRAY_SIZE(xenvif_stats); + default: + return -EINVAL; + } +} + +static void xenvif_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 * data) +{ + struct xenvif *vif = netdev_priv(dev); + unsigned int num_queues = vif->num_queues; + int i; + unsigned int queue_index; + + for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) { + unsigned long accum = 0; + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + void *vif_stats = &vif->queues[queue_index].stats; + accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset); + } + data[i] = accum; + } +} + +static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data) +{ + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) + memcpy(data + i * ETH_GSTRING_LEN, + xenvif_stats[i].name, ETH_GSTRING_LEN); + break; + } +} + +static const struct ethtool_ops xenvif_ethtool_ops = { + .get_link = ethtool_op_get_link, + + .get_sset_count = xenvif_get_sset_count, + .get_ethtool_stats = xenvif_get_ethtool_stats, + .get_strings = xenvif_get_strings, +}; + +static const struct net_device_ops xenvif_netdev_ops = { + .ndo_start_xmit = xenvif_start_xmit, + .ndo_get_stats = xenvif_get_stats, + .ndo_open = xenvif_open, + .ndo_stop = xenvif_close, + .ndo_change_mtu = xenvif_change_mtu, + .ndo_fix_features = xenvif_fix_features, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + +struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, + unsigned int handle) +{ + int err; + struct net_device *dev; + struct xenvif *vif; + char name[IFNAMSIZ] = {}; + + snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle); + /* Allocate a netdev with the max. supported number of queues. + * When the guest selects the desired number, it will be updated + * via netif_set_real_num_*_queues(). + */ + dev = alloc_netdev_mq(sizeof(struct xenvif), name, NET_NAME_UNKNOWN, + ether_setup, xenvif_max_queues); + if (dev == NULL) { + pr_warn("Could not allocate netdev for %s\n", name); + return ERR_PTR(-ENOMEM); + } + + SET_NETDEV_DEV(dev, parent); + + vif = netdev_priv(dev); + + vif->domid = domid; + vif->handle = handle; + vif->can_sg = 1; + vif->ip_csum = 1; + vif->dev = dev; + vif->disabled = false; + vif->drain_timeout = msecs_to_jiffies(rx_drain_timeout_msecs); + vif->stall_timeout = msecs_to_jiffies(rx_stall_timeout_msecs); + + /* Start out with no queues. */ + vif->queues = NULL; + vif->num_queues = 0; + + spin_lock_init(&vif->lock); + + dev->netdev_ops = &xenvif_netdev_ops; + dev->hw_features = NETIF_F_SG | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO | NETIF_F_TSO6; + dev->features = dev->hw_features | NETIF_F_RXCSUM; + dev->ethtool_ops = &xenvif_ethtool_ops; + + dev->tx_queue_len = XENVIF_QUEUE_LENGTH; + + /* + * Initialise a dummy MAC address. We choose the numerically + * largest non-broadcast address to prevent the address getting + * stolen by an Ethernet bridge for STP purposes. + * (FE:FF:FF:FF:FF:FF) + */ + eth_broadcast_addr(dev->dev_addr); + dev->dev_addr[0] &= ~0x01; + + netif_carrier_off(dev); + + err = register_netdev(dev); + if (err) { + netdev_warn(dev, "Could not register device: err=%d\n", err); + free_netdev(dev); + return ERR_PTR(err); + } + + netdev_dbg(dev, "Successfully created xenvif\n"); + + __module_get(THIS_MODULE); + + return vif; +} + +int xenvif_init_queue(struct xenvif_queue *queue) +{ + int err, i; + + queue->credit_bytes = queue->remaining_credit = ~0UL; + queue->credit_usec = 0UL; + init_timer(&queue->credit_timeout); + queue->credit_timeout.function = xenvif_tx_credit_callback; + queue->credit_window_start = get_jiffies_64(); + + queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES; + + skb_queue_head_init(&queue->rx_queue); + skb_queue_head_init(&queue->tx_queue); + + queue->pending_cons = 0; + queue->pending_prod = MAX_PENDING_REQS; + for (i = 0; i < MAX_PENDING_REQS; ++i) + queue->pending_ring[i] = i; + + spin_lock_init(&queue->callback_lock); + spin_lock_init(&queue->response_lock); + + /* If ballooning is disabled, this will consume real memory, so you + * better enable it. The long term solution would be to use just a + * bunch of valid page descriptors, without dependency on ballooning + */ + err = gnttab_alloc_pages(MAX_PENDING_REQS, + queue->mmap_pages); + if (err) { + netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n"); + return -ENOMEM; + } + + for (i = 0; i < MAX_PENDING_REQS; i++) { + queue->pending_tx_info[i].callback_struct = (struct ubuf_info) + { .callback = xenvif_zerocopy_callback, + .ctx = NULL, + .desc = i }; + queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; + } + + return 0; +} + +void xenvif_carrier_on(struct xenvif *vif) +{ + rtnl_lock(); + if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) + dev_set_mtu(vif->dev, ETH_DATA_LEN); + netdev_update_features(vif->dev); + set_bit(VIF_STATUS_CONNECTED, &vif->status); + if (netif_running(vif->dev)) + xenvif_up(vif); + rtnl_unlock(); +} + +int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, + unsigned long rx_ring_ref, unsigned int tx_evtchn, + unsigned int rx_evtchn) +{ + struct task_struct *task; + int err = -ENOMEM; + + BUG_ON(queue->tx_irq); + BUG_ON(queue->task); + BUG_ON(queue->dealloc_task); + + err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref); + if (err < 0) + goto err; + + init_waitqueue_head(&queue->wq); + init_waitqueue_head(&queue->dealloc_wq); + atomic_set(&queue->inflight_packets, 0); + + netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll, + XENVIF_NAPI_WEIGHT); + + if (tx_evtchn == rx_evtchn) { + /* feature-split-event-channels == 0 */ + err = bind_interdomain_evtchn_to_irqhandler( + queue->vif->domid, tx_evtchn, xenvif_interrupt, 0, + queue->name, queue); + if (err < 0) + goto err_unmap; + queue->tx_irq = queue->rx_irq = err; + disable_irq(queue->tx_irq); + } else { + /* feature-split-event-channels == 1 */ + snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), + "%s-tx", queue->name); + err = bind_interdomain_evtchn_to_irqhandler( + queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0, + queue->tx_irq_name, queue); + if (err < 0) + goto err_unmap; + queue->tx_irq = err; + disable_irq(queue->tx_irq); + + snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), + "%s-rx", queue->name); + err = bind_interdomain_evtchn_to_irqhandler( + queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, + queue->rx_irq_name, queue); + if (err < 0) + goto err_tx_unbind; + queue->rx_irq = err; + disable_irq(queue->rx_irq); + } + + queue->stalled = true; + + task = kthread_create(xenvif_kthread_guest_rx, + (void *)queue, "%s-guest-rx", queue->name); + if (IS_ERR(task)) { + pr_warn("Could not allocate kthread for %s\n", queue->name); + err = PTR_ERR(task); + goto err_rx_unbind; + } + queue->task = task; + get_task_struct(task); + + task = kthread_create(xenvif_dealloc_kthread, + (void *)queue, "%s-dealloc", queue->name); + if (IS_ERR(task)) { + pr_warn("Could not allocate kthread for %s\n", queue->name); + err = PTR_ERR(task); + goto err_rx_unbind; + } + queue->dealloc_task = task; + + wake_up_process(queue->task); + wake_up_process(queue->dealloc_task); + + return 0; + +err_rx_unbind: + unbind_from_irqhandler(queue->rx_irq, queue); + queue->rx_irq = 0; +err_tx_unbind: + unbind_from_irqhandler(queue->tx_irq, queue); + queue->tx_irq = 0; +err_unmap: + xenvif_unmap_frontend_rings(queue); +err: + module_put(THIS_MODULE); + return err; +} + +void xenvif_carrier_off(struct xenvif *vif) +{ + struct net_device *dev = vif->dev; + + rtnl_lock(); + if (test_and_clear_bit(VIF_STATUS_CONNECTED, &vif->status)) { + netif_carrier_off(dev); /* discard queued packets */ + if (netif_running(dev)) + xenvif_down(vif); + } + rtnl_unlock(); +} + +void xenvif_disconnect(struct xenvif *vif) +{ + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + xenvif_carrier_off(vif); + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + + netif_napi_del(&queue->napi); + + if (queue->task) { + kthread_stop(queue->task); + put_task_struct(queue->task); + queue->task = NULL; + } + + if (queue->dealloc_task) { + kthread_stop(queue->dealloc_task); + queue->dealloc_task = NULL; + } + + if (queue->tx_irq) { + if (queue->tx_irq == queue->rx_irq) + unbind_from_irqhandler(queue->tx_irq, queue); + else { + unbind_from_irqhandler(queue->tx_irq, queue); + unbind_from_irqhandler(queue->rx_irq, queue); + } + queue->tx_irq = 0; + } + + xenvif_unmap_frontend_rings(queue); + } +} + +/* Reverse the relevant parts of xenvif_init_queue(). + * Used for queue teardown from xenvif_free(), and on the + * error handling paths in xenbus.c:connect(). + */ +void xenvif_deinit_queue(struct xenvif_queue *queue) +{ + gnttab_free_pages(MAX_PENDING_REQS, queue->mmap_pages); +} + +void xenvif_free(struct xenvif *vif) +{ + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + unregister_netdev(vif->dev); + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + xenvif_deinit_queue(queue); + } + + vfree(vif->queues); + vif->queues = NULL; + vif->num_queues = 0; + + free_netdev(vif->dev); + + module_put(THIS_MODULE); +} diff --git a/kernel/drivers/net/xen-netback/netback.c b/kernel/drivers/net/xen-netback/netback.c new file mode 100644 index 000000000..0d2594395 --- /dev/null +++ b/kernel/drivers/net/xen-netback/netback.c @@ -0,0 +1,2049 @@ +/* + * Back-end of the driver for virtual network devices. This portion of the + * driver exports a 'unified' network-device interface that can be accessed + * by any operating system that implements a compatible front end. A + * reference front-end implementation can be found in: + * drivers/net/xen-netfront.c + * + * Copyright (c) 2002-2005, K A Fraser + * + * 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 "common.h" + +#include +#include +#include +#include + +#include + +#include +#include +#include + +#include +#include + +/* Provide an option to disable split event channels at load time as + * event channels are limited resource. Split event channels are + * enabled by default. + */ +bool separate_tx_rx_irq = 1; +module_param(separate_tx_rx_irq, bool, 0644); + +/* The time that packets can stay on the guest Rx internal queue + * before they are dropped. + */ +unsigned int rx_drain_timeout_msecs = 10000; +module_param(rx_drain_timeout_msecs, uint, 0444); + +/* The length of time before the frontend is considered unresponsive + * because it isn't providing Rx slots. + */ +unsigned int rx_stall_timeout_msecs = 60000; +module_param(rx_stall_timeout_msecs, uint, 0444); + +unsigned int xenvif_max_queues; +module_param_named(max_queues, xenvif_max_queues, uint, 0644); +MODULE_PARM_DESC(max_queues, + "Maximum number of queues per virtual interface"); + +/* + * This is the maximum slots a skb can have. If a guest sends a skb + * which exceeds this limit it is considered malicious. + */ +#define FATAL_SKB_SLOTS_DEFAULT 20 +static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT; +module_param(fatal_skb_slots, uint, 0444); + +/* The amount to copy out of the first guest Tx slot into the skb's + * linear area. If the first slot has more data, it will be mapped + * and put into the first frag. + * + * This is sized to avoid pulling headers from the frags for most + * TCP/IP packets. + */ +#define XEN_NETBACK_TX_COPY_LEN 128 + + +static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, + u8 status); + +static void make_tx_response(struct xenvif_queue *queue, + struct xen_netif_tx_request *txp, + s8 st); +static void push_tx_responses(struct xenvif_queue *queue); + +static inline int tx_work_todo(struct xenvif_queue *queue); + +static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, + u16 id, + s8 st, + u16 offset, + u16 size, + u16 flags); + +static inline unsigned long idx_to_pfn(struct xenvif_queue *queue, + u16 idx) +{ + return page_to_pfn(queue->mmap_pages[idx]); +} + +static inline unsigned long idx_to_kaddr(struct xenvif_queue *queue, + u16 idx) +{ + return (unsigned long)pfn_to_kaddr(idx_to_pfn(queue, idx)); +} + +#define callback_param(vif, pending_idx) \ + (vif->pending_tx_info[pending_idx].callback_struct) + +/* Find the containing VIF's structure from a pointer in pending_tx_info array + */ +static inline struct xenvif_queue *ubuf_to_queue(const struct ubuf_info *ubuf) +{ + u16 pending_idx = ubuf->desc; + struct pending_tx_info *temp = + container_of(ubuf, struct pending_tx_info, callback_struct); + return container_of(temp - pending_idx, + struct xenvif_queue, + pending_tx_info[0]); +} + +static u16 frag_get_pending_idx(skb_frag_t *frag) +{ + return (u16)frag->page_offset; +} + +static void frag_set_pending_idx(skb_frag_t *frag, u16 pending_idx) +{ + frag->page_offset = pending_idx; +} + +static inline pending_ring_idx_t pending_index(unsigned i) +{ + return i & (MAX_PENDING_REQS-1); +} + +bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed) +{ + RING_IDX prod, cons; + + do { + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + if (prod - cons >= needed) + return true; + + queue->rx.sring->req_event = prod + 1; + + /* Make sure event is visible before we check prod + * again. + */ + mb(); + } while (queue->rx.sring->req_prod != prod); + + return false; +} + +void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) +{ + unsigned long flags; + + spin_lock_irqsave(&queue->rx_queue.lock, flags); + + __skb_queue_tail(&queue->rx_queue, skb); + + queue->rx_queue_len += skb->len; + if (queue->rx_queue_len > queue->rx_queue_max) + netif_tx_stop_queue(netdev_get_tx_queue(queue->vif->dev, queue->id)); + + spin_unlock_irqrestore(&queue->rx_queue.lock, flags); +} + +static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + spin_lock_irq(&queue->rx_queue.lock); + + skb = __skb_dequeue(&queue->rx_queue); + if (skb) + queue->rx_queue_len -= skb->len; + + spin_unlock_irq(&queue->rx_queue.lock); + + return skb; +} + +static void xenvif_rx_queue_maybe_wake(struct xenvif_queue *queue) +{ + spin_lock_irq(&queue->rx_queue.lock); + + if (queue->rx_queue_len < queue->rx_queue_max) + netif_tx_wake_queue(netdev_get_tx_queue(queue->vif->dev, queue->id)); + + spin_unlock_irq(&queue->rx_queue.lock); +} + + +static void xenvif_rx_queue_purge(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + while ((skb = xenvif_rx_dequeue(queue)) != NULL) + kfree_skb(skb); +} + +static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + for(;;) { + skb = skb_peek(&queue->rx_queue); + if (!skb) + break; + if (time_before(jiffies, XENVIF_RX_CB(skb)->expires)) + break; + xenvif_rx_dequeue(queue); + kfree_skb(skb); + } +} + +struct netrx_pending_operations { + unsigned copy_prod, copy_cons; + unsigned meta_prod, meta_cons; + struct gnttab_copy *copy; + struct xenvif_rx_meta *meta; + int copy_off; + grant_ref_t copy_gref; +}; + +static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, + struct netrx_pending_operations *npo) +{ + struct xenvif_rx_meta *meta; + struct xen_netif_rx_request *req; + + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); + + meta = npo->meta + npo->meta_prod++; + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; + meta->gso_size = 0; + meta->size = 0; + meta->id = req->id; + + npo->copy_off = 0; + npo->copy_gref = req->gref; + + return meta; +} + +/* + * Set up the grant operations for this fragment. If it's a flipping + * interface, we also set up the unmap request from here. + */ +static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb, + struct netrx_pending_operations *npo, + struct page *page, unsigned long size, + unsigned long offset, int *head) +{ + struct gnttab_copy *copy_gop; + struct xenvif_rx_meta *meta; + unsigned long bytes; + int gso_type = XEN_NETIF_GSO_TYPE_NONE; + + /* Data must not cross a page boundary. */ + BUG_ON(size + offset > PAGE_SIZE<meta + npo->meta_prod - 1; + + /* Skip unused frames from start of page */ + page += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; + + while (size > 0) { + struct xen_page_foreign *foreign; + + BUG_ON(offset >= PAGE_SIZE); + BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET); + + if (npo->copy_off == MAX_BUFFER_OFFSET) + meta = get_next_rx_buffer(queue, npo); + + bytes = PAGE_SIZE - offset; + if (bytes > size) + bytes = size; + + if (npo->copy_off + bytes > MAX_BUFFER_OFFSET) + bytes = MAX_BUFFER_OFFSET - npo->copy_off; + + copy_gop = npo->copy + npo->copy_prod++; + copy_gop->flags = GNTCOPY_dest_gref; + copy_gop->len = bytes; + + foreign = xen_page_foreign(page); + if (foreign) { + copy_gop->source.domid = foreign->domid; + copy_gop->source.u.ref = foreign->gref; + copy_gop->flags |= GNTCOPY_source_gref; + } else { + copy_gop->source.domid = DOMID_SELF; + copy_gop->source.u.gmfn = + virt_to_mfn(page_address(page)); + } + copy_gop->source.offset = offset; + + copy_gop->dest.domid = queue->vif->domid; + copy_gop->dest.offset = npo->copy_off; + copy_gop->dest.u.ref = npo->copy_gref; + + npo->copy_off += bytes; + meta->size += bytes; + + offset += bytes; + size -= bytes; + + /* Next frame */ + if (offset == PAGE_SIZE && size) { + BUG_ON(!PageCompound(page)); + page++; + offset = 0; + } + + /* Leave a gap for the GSO descriptor. */ + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + } + + if (*head && ((1 << gso_type) & queue->vif->gso_mask)) + queue->rx.req_cons++; + + *head = 0; /* There must be something in this buffer now. */ + + } +} + +/* + * Prepare an SKB to be transmitted to the frontend. + * + * This function is responsible for allocating grant operations, meta + * structures, etc. + * + * It returns the number of meta structures consumed. The number of + * ring slots used is always equal to the number of meta slots used + * plus the number of GSO descriptors used. Currently, we use either + * zero GSO descriptors (for non-GSO packets) or one descriptor (for + * frontend-side LRO). + */ +static int xenvif_gop_skb(struct sk_buff *skb, + struct netrx_pending_operations *npo, + struct xenvif_queue *queue) +{ + struct xenvif *vif = netdev_priv(skb->dev); + int nr_frags = skb_shinfo(skb)->nr_frags; + int i; + struct xen_netif_rx_request *req; + struct xenvif_rx_meta *meta; + unsigned char *data; + int head = 1; + int old_meta_prod; + int gso_type; + + old_meta_prod = npo->meta_prod; + + gso_type = XEN_NETIF_GSO_TYPE_NONE; + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + } + + /* Set up a GSO prefix descriptor, if necessary */ + if ((1 << gso_type) & vif->gso_prefix_mask) { + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); + meta = npo->meta + npo->meta_prod++; + meta->gso_type = gso_type; + meta->gso_size = skb_shinfo(skb)->gso_size; + meta->size = 0; + meta->id = req->id; + } + + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); + meta = npo->meta + npo->meta_prod++; + + if ((1 << gso_type) & vif->gso_mask) { + meta->gso_type = gso_type; + meta->gso_size = skb_shinfo(skb)->gso_size; + } else { + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; + meta->gso_size = 0; + } + + meta->size = 0; + meta->id = req->id; + npo->copy_off = 0; + npo->copy_gref = req->gref; + + data = skb->data; + while (data < skb_tail_pointer(skb)) { + unsigned int offset = offset_in_page(data); + unsigned int len = PAGE_SIZE - offset; + + if (data + len > skb_tail_pointer(skb)) + len = skb_tail_pointer(skb) - data; + + xenvif_gop_frag_copy(queue, skb, npo, + virt_to_page(data), len, offset, &head); + data += len; + } + + for (i = 0; i < nr_frags; i++) { + xenvif_gop_frag_copy(queue, skb, npo, + skb_frag_page(&skb_shinfo(skb)->frags[i]), + skb_frag_size(&skb_shinfo(skb)->frags[i]), + skb_shinfo(skb)->frags[i].page_offset, + &head); + } + + return npo->meta_prod - old_meta_prod; +} + +/* + * This is a twin to xenvif_gop_skb. Assume that xenvif_gop_skb was + * used to set up the operations on the top of + * netrx_pending_operations, which have since been done. Check that + * they didn't give any errors and advance over them. + */ +static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots, + struct netrx_pending_operations *npo) +{ + struct gnttab_copy *copy_op; + int status = XEN_NETIF_RSP_OKAY; + int i; + + for (i = 0; i < nr_meta_slots; i++) { + copy_op = npo->copy + npo->copy_cons++; + if (copy_op->status != GNTST_okay) { + netdev_dbg(vif->dev, + "Bad status %d from copy to DOM%d.\n", + copy_op->status, vif->domid); + status = XEN_NETIF_RSP_ERROR; + } + } + + return status; +} + +static void xenvif_add_frag_responses(struct xenvif_queue *queue, int status, + struct xenvif_rx_meta *meta, + int nr_meta_slots) +{ + int i; + unsigned long offset; + + /* No fragments used */ + if (nr_meta_slots <= 1) + return; + + nr_meta_slots--; + + for (i = 0; i < nr_meta_slots; i++) { + int flags; + if (i == nr_meta_slots - 1) + flags = 0; + else + flags = XEN_NETRXF_more_data; + + offset = 0; + make_rx_response(queue, meta[i].id, status, offset, + meta[i].size, flags); + } +} + +void xenvif_kick_thread(struct xenvif_queue *queue) +{ + wake_up(&queue->wq); +} + +static void xenvif_rx_action(struct xenvif_queue *queue) +{ + s8 status; + u16 flags; + struct xen_netif_rx_response *resp; + struct sk_buff_head rxq; + struct sk_buff *skb; + LIST_HEAD(notify); + int ret; + unsigned long offset; + bool need_to_notify = false; + + struct netrx_pending_operations npo = { + .copy = queue->grant_copy_op, + .meta = queue->meta, + }; + + skb_queue_head_init(&rxq); + + while (xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX) + && (skb = xenvif_rx_dequeue(queue)) != NULL) { + RING_IDX old_req_cons; + RING_IDX ring_slots_used; + + queue->last_rx_time = jiffies; + + old_req_cons = queue->rx.req_cons; + XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue); + ring_slots_used = queue->rx.req_cons - old_req_cons; + + __skb_queue_tail(&rxq, skb); + } + + BUG_ON(npo.meta_prod > ARRAY_SIZE(queue->meta)); + + if (!npo.copy_prod) + goto done; + + BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS); + gnttab_batch_copy(queue->grant_copy_op, npo.copy_prod); + + while ((skb = __skb_dequeue(&rxq)) != NULL) { + + if ((1 << queue->meta[npo.meta_cons].gso_type) & + queue->vif->gso_prefix_mask) { + resp = RING_GET_RESPONSE(&queue->rx, + queue->rx.rsp_prod_pvt++); + + resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data; + + resp->offset = queue->meta[npo.meta_cons].gso_size; + resp->id = queue->meta[npo.meta_cons].id; + resp->status = XENVIF_RX_CB(skb)->meta_slots_used; + + npo.meta_cons++; + XENVIF_RX_CB(skb)->meta_slots_used--; + } + + + queue->stats.tx_bytes += skb->len; + queue->stats.tx_packets++; + + status = xenvif_check_gop(queue->vif, + XENVIF_RX_CB(skb)->meta_slots_used, + &npo); + + if (XENVIF_RX_CB(skb)->meta_slots_used == 1) + flags = 0; + else + flags = XEN_NETRXF_more_data; + + if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */ + flags |= XEN_NETRXF_csum_blank | XEN_NETRXF_data_validated; + else if (skb->ip_summed == CHECKSUM_UNNECESSARY) + /* remote but checksummed. */ + flags |= XEN_NETRXF_data_validated; + + offset = 0; + resp = make_rx_response(queue, queue->meta[npo.meta_cons].id, + status, offset, + queue->meta[npo.meta_cons].size, + flags); + + if ((1 << queue->meta[npo.meta_cons].gso_type) & + queue->vif->gso_mask) { + struct xen_netif_extra_info *gso = + (struct xen_netif_extra_info *) + RING_GET_RESPONSE(&queue->rx, + queue->rx.rsp_prod_pvt++); + + resp->flags |= XEN_NETRXF_extra_info; + + gso->u.gso.type = queue->meta[npo.meta_cons].gso_type; + gso->u.gso.size = queue->meta[npo.meta_cons].gso_size; + gso->u.gso.pad = 0; + gso->u.gso.features = 0; + + gso->type = XEN_NETIF_EXTRA_TYPE_GSO; + gso->flags = 0; + } + + xenvif_add_frag_responses(queue, status, + queue->meta + npo.meta_cons + 1, + XENVIF_RX_CB(skb)->meta_slots_used); + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, ret); + + need_to_notify |= !!ret; + + npo.meta_cons += XENVIF_RX_CB(skb)->meta_slots_used; + dev_kfree_skb(skb); + } + +done: + if (need_to_notify) + notify_remote_via_irq(queue->rx_irq); +} + +void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue) +{ + int more_to_do; + + RING_FINAL_CHECK_FOR_REQUESTS(&queue->tx, more_to_do); + + if (more_to_do) + napi_schedule(&queue->napi); +} + +static void tx_add_credit(struct xenvif_queue *queue) +{ + unsigned long max_burst, max_credit; + + /* + * Allow a burst big enough to transmit a jumbo packet of up to 128kB. + * Otherwise the interface can seize up due to insufficient credit. + */ + max_burst = RING_GET_REQUEST(&queue->tx, queue->tx.req_cons)->size; + max_burst = min(max_burst, 131072UL); + max_burst = max(max_burst, queue->credit_bytes); + + /* Take care that adding a new chunk of credit doesn't wrap to zero. */ + max_credit = queue->remaining_credit + queue->credit_bytes; + if (max_credit < queue->remaining_credit) + max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */ + + queue->remaining_credit = min(max_credit, max_burst); +} + +void xenvif_tx_credit_callback(unsigned long data) +{ + struct xenvif_queue *queue = (struct xenvif_queue *)data; + tx_add_credit(queue); + xenvif_napi_schedule_or_enable_events(queue); +} + +static void xenvif_tx_err(struct xenvif_queue *queue, + struct xen_netif_tx_request *txp, RING_IDX end) +{ + RING_IDX cons = queue->tx.req_cons; + unsigned long flags; + + do { + spin_lock_irqsave(&queue->response_lock, flags); + make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR); + push_tx_responses(queue); + spin_unlock_irqrestore(&queue->response_lock, flags); + if (cons == end) + break; + txp = RING_GET_REQUEST(&queue->tx, cons++); + } while (1); + queue->tx.req_cons = cons; +} + +static void xenvif_fatal_tx_err(struct xenvif *vif) +{ + netdev_err(vif->dev, "fatal error; disabling device\n"); + vif->disabled = true; + /* Disable the vif from queue 0's kthread */ + if (vif->queues) + xenvif_kick_thread(&vif->queues[0]); +} + +static int xenvif_count_requests(struct xenvif_queue *queue, + struct xen_netif_tx_request *first, + struct xen_netif_tx_request *txp, + int work_to_do) +{ + RING_IDX cons = queue->tx.req_cons; + int slots = 0; + int drop_err = 0; + int more_data; + + if (!(first->flags & XEN_NETTXF_more_data)) + return 0; + + do { + struct xen_netif_tx_request dropped_tx = { 0 }; + + if (slots >= work_to_do) { + netdev_err(queue->vif->dev, + "Asked for %d slots but exceeds this limit\n", + work_to_do); + xenvif_fatal_tx_err(queue->vif); + return -ENODATA; + } + + /* This guest is really using too many slots and + * considered malicious. + */ + if (unlikely(slots >= fatal_skb_slots)) { + netdev_err(queue->vif->dev, + "Malicious frontend using %d slots, threshold %u\n", + slots, fatal_skb_slots); + xenvif_fatal_tx_err(queue->vif); + return -E2BIG; + } + + /* Xen network protocol had implicit dependency on + * MAX_SKB_FRAGS. XEN_NETBK_LEGACY_SLOTS_MAX is set to + * the historical MAX_SKB_FRAGS value 18 to honor the + * same behavior as before. Any packet using more than + * 18 slots but less than fatal_skb_slots slots is + * dropped + */ + if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) { + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Too many slots (%d) exceeding limit (%d), dropping packet\n", + slots, XEN_NETBK_LEGACY_SLOTS_MAX); + drop_err = -E2BIG; + } + + if (drop_err) + txp = &dropped_tx; + + memcpy(txp, RING_GET_REQUEST(&queue->tx, cons + slots), + sizeof(*txp)); + + /* If the guest submitted a frame >= 64 KiB then + * first->size overflowed and following slots will + * appear to be larger than the frame. + * + * This cannot be fatal error as there are buggy + * frontends that do this. + * + * Consume all slots and drop the packet. + */ + if (!drop_err && txp->size > first->size) { + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Invalid tx request, slot size %u > remaining size %u\n", + txp->size, first->size); + drop_err = -EIO; + } + + first->size -= txp->size; + slots++; + + if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) { + netdev_err(queue->vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n", + txp->offset, txp->size); + xenvif_fatal_tx_err(queue->vif); + return -EINVAL; + } + + more_data = txp->flags & XEN_NETTXF_more_data; + + if (!drop_err) + txp++; + + } while (more_data); + + if (drop_err) { + xenvif_tx_err(queue, first, cons + slots); + return drop_err; + } + + return slots; +} + + +struct xenvif_tx_cb { + u16 pending_idx; +}; + +#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) + +static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue, + u16 pending_idx, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *mop) +{ + queue->pages_to_map[mop-queue->tx_map_ops] = queue->mmap_pages[pending_idx]; + gnttab_set_map_op(mop, idx_to_kaddr(queue, pending_idx), + GNTMAP_host_map | GNTMAP_readonly, + txp->gref, queue->vif->domid); + + memcpy(&queue->pending_tx_info[pending_idx].req, txp, + sizeof(*txp)); +} + +static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) +{ + struct sk_buff *skb = + alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(skb == NULL)) + return NULL; + + /* Packets passed to netif_rx() must have some headroom. */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + + /* Initialize it here to avoid later surprises */ + skb_shinfo(skb)->destructor_arg = NULL; + + return skb; +} + +static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, + struct sk_buff *skb, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *gop) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + skb_frag_t *frags = shinfo->frags; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + int start; + pending_ring_idx_t index; + unsigned int nr_slots, frag_overflow = 0; + + /* At this point shinfo->nr_frags is in fact the number of + * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. + */ + if (shinfo->nr_frags > MAX_SKB_FRAGS) { + frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS; + BUG_ON(frag_overflow > MAX_SKB_FRAGS); + shinfo->nr_frags = MAX_SKB_FRAGS; + } + nr_slots = shinfo->nr_frags; + + /* Skip first skb fragment if it is on same page as header fragment. */ + start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + + for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(queue->pending_cons++); + pending_idx = queue->pending_ring[index]; + xenvif_tx_create_map_op(queue, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + } + + if (frag_overflow) { + struct sk_buff *nskb = xenvif_alloc_skb(0); + if (unlikely(nskb == NULL)) { + if (net_ratelimit()) + netdev_err(queue->vif->dev, + "Can't allocate the frag_list skb.\n"); + return NULL; + } + + shinfo = skb_shinfo(nskb); + frags = shinfo->frags; + + for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(queue->pending_cons++); + pending_idx = queue->pending_ring[index]; + xenvif_tx_create_map_op(queue, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], + pending_idx); + } + + skb_shinfo(skb)->frag_list = nskb; + } + + return gop; +} + +static inline void xenvif_grant_handle_set(struct xenvif_queue *queue, + u16 pending_idx, + grant_handle_t handle) +{ + if (unlikely(queue->grant_tx_handle[pending_idx] != + NETBACK_INVALID_HANDLE)) { + netdev_err(queue->vif->dev, + "Trying to overwrite active handle! pending_idx: %x\n", + pending_idx); + BUG(); + } + queue->grant_tx_handle[pending_idx] = handle; +} + +static inline void xenvif_grant_handle_reset(struct xenvif_queue *queue, + u16 pending_idx) +{ + if (unlikely(queue->grant_tx_handle[pending_idx] == + NETBACK_INVALID_HANDLE)) { + netdev_err(queue->vif->dev, + "Trying to unmap invalid handle! pending_idx: %x\n", + pending_idx); + BUG(); + } + queue->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE; +} + +static int xenvif_tx_check_gop(struct xenvif_queue *queue, + struct sk_buff *skb, + struct gnttab_map_grant_ref **gopp_map, + struct gnttab_copy **gopp_copy) +{ + struct gnttab_map_grant_ref *gop_map = *gopp_map; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + /* This always points to the shinfo of the skb being checked, which + * could be either the first or the one on the frag_list + */ + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* If this is non-NULL, we are currently checking the frag_list skb, and + * this points to the shinfo of the first one + */ + struct skb_shared_info *first_shinfo = NULL; + int nr_frags = shinfo->nr_frags; + const bool sharedslot = nr_frags && + frag_get_pending_idx(&shinfo->frags[0]) == pending_idx; + int i, err; + + /* Check status of header. */ + err = (*gopp_copy)->status; + if (unlikely(err)) { + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", + (*gopp_copy)->status, + pending_idx, + (*gopp_copy)->source.u.ref); + /* The first frag might still have this slot mapped */ + if (!sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + } + (*gopp_copy)++; + +check_frags: + for (i = 0; i < nr_frags; i++, gop_map++) { + int j, newerr; + + pending_idx = frag_get_pending_idx(&shinfo->frags[i]); + + /* Check error status: if okay then remember grant handle. */ + newerr = gop_map->status; + + if (likely(!newerr)) { + xenvif_grant_handle_set(queue, + pending_idx, + gop_map->handle); + /* Had a previous error? Invalidate this fragment. */ + if (unlikely(err)) { + xenvif_idx_unmap(queue, pending_idx); + /* If the mapping of the first frag was OK, but + * the header's copy failed, and they are + * sharing a slot, send an error + */ + if (i == 0 && sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + else + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } + continue; + } + + /* Error on this fragment: respond to client with an error. */ + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant map of %d. frag failed! status: %d pending_idx: %u ref: %u\n", + i, + gop_map->status, + pending_idx, + gop_map->ref); + + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); + + /* Not the first error? Preceding frags already invalidated. */ + if (err) + continue; + + /* First error: if the header haven't shared a slot with the + * first frag, release it as well. + */ + if (!sharedslot) + xenvif_idx_release(queue, + XENVIF_TX_CB(skb)->pending_idx, + XEN_NETIF_RSP_OKAY); + + /* Invalidate preceding fragments of this skb. */ + for (j = 0; j < i; j++) { + pending_idx = frag_get_pending_idx(&shinfo->frags[j]); + xenvif_idx_unmap(queue, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } + + /* And if we found the error while checking the frag_list, unmap + * the first skb's frags + */ + if (first_shinfo) { + for (j = 0; j < first_shinfo->nr_frags; j++) { + pending_idx = frag_get_pending_idx(&first_shinfo->frags[j]); + xenvif_idx_unmap(queue, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } + } + + /* Remember the error: invalidate all subsequent fragments. */ + err = newerr; + } + + if (skb_has_frag_list(skb) && !first_shinfo) { + first_shinfo = skb_shinfo(skb); + shinfo = skb_shinfo(skb_shinfo(skb)->frag_list); + nr_frags = shinfo->nr_frags; + + goto check_frags; + } + + *gopp_map = gop_map; + return err; +} + +static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + int nr_frags = shinfo->nr_frags; + int i; + u16 prev_pending_idx = INVALID_PENDING_IDX; + + for (i = 0; i < nr_frags; i++) { + skb_frag_t *frag = shinfo->frags + i; + struct xen_netif_tx_request *txp; + struct page *page; + u16 pending_idx; + + pending_idx = frag_get_pending_idx(frag); + + /* If this is not the first frag, chain it to the previous*/ + if (prev_pending_idx == INVALID_PENDING_IDX) + skb_shinfo(skb)->destructor_arg = + &callback_param(queue, pending_idx); + else + callback_param(queue, prev_pending_idx).ctx = + &callback_param(queue, pending_idx); + + callback_param(queue, pending_idx).ctx = NULL; + prev_pending_idx = pending_idx; + + txp = &queue->pending_tx_info[pending_idx].req; + page = virt_to_page(idx_to_kaddr(queue, pending_idx)); + __skb_fill_page_desc(skb, i, page, txp->offset, txp->size); + skb->len += txp->size; + skb->data_len += txp->size; + skb->truesize += txp->size; + + /* Take an extra reference to offset network stack's put_page */ + get_page(queue->mmap_pages[pending_idx]); + } +} + +static int xenvif_get_extras(struct xenvif_queue *queue, + struct xen_netif_extra_info *extras, + int work_to_do) +{ + struct xen_netif_extra_info extra; + RING_IDX cons = queue->tx.req_cons; + + do { + if (unlikely(work_to_do-- <= 0)) { + netdev_err(queue->vif->dev, "Missing extra info\n"); + xenvif_fatal_tx_err(queue->vif); + return -EBADR; + } + + memcpy(&extra, RING_GET_REQUEST(&queue->tx, cons), + sizeof(extra)); + if (unlikely(!extra.type || + extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { + queue->tx.req_cons = ++cons; + netdev_err(queue->vif->dev, + "Invalid extra type: %d\n", extra.type); + xenvif_fatal_tx_err(queue->vif); + return -EINVAL; + } + + memcpy(&extras[extra.type - 1], &extra, sizeof(extra)); + queue->tx.req_cons = ++cons; + } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE); + + return work_to_do; +} + +static int xenvif_set_skb_gso(struct xenvif *vif, + struct sk_buff *skb, + struct xen_netif_extra_info *gso) +{ + if (!gso->u.gso.size) { + netdev_err(vif->dev, "GSO size must not be zero.\n"); + xenvif_fatal_tx_err(vif); + return -EINVAL; + } + + switch (gso->u.gso.type) { + case XEN_NETIF_GSO_TYPE_TCPV4: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + break; + case XEN_NETIF_GSO_TYPE_TCPV6: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + break; + default: + netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + xenvif_fatal_tx_err(vif); + return -EINVAL; + } + + skb_shinfo(skb)->gso_size = gso->u.gso.size; + /* gso_segs will be calculated later */ + + return 0; +} + +static int checksum_setup(struct xenvif_queue *queue, struct sk_buff *skb) +{ + bool recalculate_partial_csum = false; + + /* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy + * peers can fail to set NETRXF_csum_blank when sending a GSO + * frame. In this case force the SKB to CHECKSUM_PARTIAL and + * recalculate the partial checksum. + */ + if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { + queue->stats.rx_gso_checksum_fixup++; + skb->ip_summed = CHECKSUM_PARTIAL; + recalculate_partial_csum = true; + } + + /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + return skb_checksum_setup(skb, recalculate_partial_csum); +} + +static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) +{ + u64 now = get_jiffies_64(); + u64 next_credit = queue->credit_window_start + + msecs_to_jiffies(queue->credit_usec / 1000); + + /* Timer could already be pending in rare cases. */ + if (timer_pending(&queue->credit_timeout)) + return true; + + /* Passed the point where we can replenish credit? */ + if (time_after_eq64(now, next_credit)) { + queue->credit_window_start = now; + tx_add_credit(queue); + } + + /* Still too big to send right now? Set a callback. */ + if (size > queue->remaining_credit) { + queue->credit_timeout.data = + (unsigned long)queue; + mod_timer(&queue->credit_timeout, + next_credit); + queue->credit_window_start = next_credit; + + return true; + } + + return false; +} + +static void xenvif_tx_build_gops(struct xenvif_queue *queue, + int budget, + unsigned *copy_ops, + unsigned *map_ops) +{ + struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop; + struct sk_buff *skb; + int ret; + + while (skb_queue_len(&queue->tx_queue) < budget) { + struct xen_netif_tx_request txreq; + struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; + struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1]; + u16 pending_idx; + RING_IDX idx; + int work_to_do; + unsigned int data_len; + pending_ring_idx_t index; + + if (queue->tx.sring->req_prod - queue->tx.req_cons > + XEN_NETIF_TX_RING_SIZE) { + netdev_err(queue->vif->dev, + "Impossible number of requests. " + "req_prod %d, req_cons %d, size %ld\n", + queue->tx.sring->req_prod, queue->tx.req_cons, + XEN_NETIF_TX_RING_SIZE); + xenvif_fatal_tx_err(queue->vif); + break; + } + + work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx); + if (!work_to_do) + break; + + idx = queue->tx.req_cons; + rmb(); /* Ensure that we see the request before we copy it. */ + memcpy(&txreq, RING_GET_REQUEST(&queue->tx, idx), sizeof(txreq)); + + /* Credit-based scheduling. */ + if (txreq.size > queue->remaining_credit && + tx_credit_exceeded(queue, txreq.size)) + break; + + queue->remaining_credit -= txreq.size; + + work_to_do--; + queue->tx.req_cons = ++idx; + + memset(extras, 0, sizeof(extras)); + if (txreq.flags & XEN_NETTXF_extra_info) { + work_to_do = xenvif_get_extras(queue, extras, + work_to_do); + idx = queue->tx.req_cons; + if (unlikely(work_to_do < 0)) + break; + } + + ret = xenvif_count_requests(queue, &txreq, txfrags, work_to_do); + if (unlikely(ret < 0)) + break; + + idx += ret; + + if (unlikely(txreq.size < ETH_HLEN)) { + netdev_dbg(queue->vif->dev, + "Bad packet size: %d\n", txreq.size); + xenvif_tx_err(queue, &txreq, idx); + break; + } + + /* No crossing a page as the payload mustn't fragment. */ + if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) { + netdev_err(queue->vif->dev, + "txreq.offset: %x, size: %u, end: %lu\n", + txreq.offset, txreq.size, + (unsigned long)(txreq.offset&~PAGE_MASK) + txreq.size); + xenvif_fatal_tx_err(queue->vif); + break; + } + + index = pending_index(queue->pending_cons); + pending_idx = queue->pending_ring[index]; + + data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN && + ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? + XEN_NETBACK_TX_COPY_LEN : txreq.size; + + skb = xenvif_alloc_skb(data_len); + if (unlikely(skb == NULL)) { + netdev_dbg(queue->vif->dev, + "Can't allocate a skb in start_xmit.\n"); + xenvif_tx_err(queue, &txreq, idx); + break; + } + + if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) { + struct xen_netif_extra_info *gso; + gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; + + if (xenvif_set_skb_gso(queue->vif, skb, gso)) { + /* Failure in xenvif_set_skb_gso is fatal. */ + kfree_skb(skb); + break; + } + } + + XENVIF_TX_CB(skb)->pending_idx = pending_idx; + + __skb_put(skb, data_len); + queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; + queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid; + queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset; + + queue->tx_copy_ops[*copy_ops].dest.u.gmfn = + virt_to_mfn(skb->data); + queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; + queue->tx_copy_ops[*copy_ops].dest.offset = + offset_in_page(skb->data); + + queue->tx_copy_ops[*copy_ops].len = data_len; + queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; + + (*copy_ops)++; + + skb_shinfo(skb)->nr_frags = ret; + if (data_len < txreq.size) { + skb_shinfo(skb)->nr_frags++; + frag_set_pending_idx(&skb_shinfo(skb)->frags[0], + pending_idx); + xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop); + gop++; + } else { + frag_set_pending_idx(&skb_shinfo(skb)->frags[0], + INVALID_PENDING_IDX); + memcpy(&queue->pending_tx_info[pending_idx].req, &txreq, + sizeof(txreq)); + } + + queue->pending_cons++; + + request_gop = xenvif_get_requests(queue, skb, txfrags, gop); + if (request_gop == NULL) { + kfree_skb(skb); + xenvif_tx_err(queue, &txreq, idx); + break; + } + gop = request_gop; + + __skb_queue_tail(&queue->tx_queue, skb); + + queue->tx.req_cons = idx; + + if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) || + (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops))) + break; + } + + (*map_ops) = gop - queue->tx_map_ops; + return; +} + +/* Consolidate skb with a frag_list into a brand new one with local pages on + * frags. Returns 0 or -ENOMEM if can't allocate new pages. + */ +static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *skb) +{ + unsigned int offset = skb_headlen(skb); + skb_frag_t frags[MAX_SKB_FRAGS]; + int i, f; + struct ubuf_info *uarg; + struct sk_buff *nskb = skb_shinfo(skb)->frag_list; + + queue->stats.tx_zerocopy_sent += 2; + queue->stats.tx_frag_overflow++; + + xenvif_fill_frags(queue, nskb); + /* Subtract frags size, we will correct it later */ + skb->truesize -= skb->data_len; + skb->len += nskb->len; + skb->data_len += nskb->len; + + /* create a brand new frags array and coalesce there */ + for (i = 0; offset < skb->len; i++) { + struct page *page; + unsigned int len; + + BUG_ON(i >= MAX_SKB_FRAGS); + page = alloc_page(GFP_ATOMIC); + if (!page) { + int j; + skb->truesize += skb->data_len; + for (j = 0; j < i; j++) + put_page(frags[j].page.p); + return -ENOMEM; + } + + if (offset + PAGE_SIZE < skb->len) + len = PAGE_SIZE; + else + len = skb->len - offset; + if (skb_copy_bits(skb, offset, page_address(page), len)) + BUG(); + + offset += len; + frags[i].page.p = page; + frags[i].page_offset = 0; + skb_frag_size_set(&frags[i], len); + } + + /* Copied all the bits from the frag list -- free it. */ + skb_frag_list_init(skb); + xenvif_skb_zerocopy_prepare(queue, nskb); + kfree_skb(nskb); + + /* Release all the original (foreign) frags. */ + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + skb_frag_unref(skb, f); + uarg = skb_shinfo(skb)->destructor_arg; + /* increase inflight counter to offset decrement in callback */ + atomic_inc(&queue->inflight_packets); + uarg->callback(uarg, true); + skb_shinfo(skb)->destructor_arg = NULL; + + /* Fill the skb with the new (local) frags. */ + memcpy(skb_shinfo(skb)->frags, frags, i * sizeof(skb_frag_t)); + skb_shinfo(skb)->nr_frags = i; + skb->truesize += i * PAGE_SIZE; + + return 0; +} + +static int xenvif_tx_submit(struct xenvif_queue *queue) +{ + struct gnttab_map_grant_ref *gop_map = queue->tx_map_ops; + struct gnttab_copy *gop_copy = queue->tx_copy_ops; + struct sk_buff *skb; + int work_done = 0; + + while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) { + struct xen_netif_tx_request *txp; + u16 pending_idx; + unsigned data_len; + + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + txp = &queue->pending_tx_info[pending_idx].req; + + /* Check the remap error code. */ + if (unlikely(xenvif_tx_check_gop(queue, skb, &gop_map, &gop_copy))) { + /* If there was an error, xenvif_tx_check_gop is + * expected to release all the frags which were mapped, + * so kfree_skb shouldn't do it again + */ + skb_shinfo(skb)->nr_frags = 0; + if (skb_has_frag_list(skb)) { + struct sk_buff *nskb = + skb_shinfo(skb)->frag_list; + skb_shinfo(nskb)->nr_frags = 0; + } + kfree_skb(skb); + continue; + } + + data_len = skb->len; + callback_param(queue, pending_idx).ctx = NULL; + if (data_len < txp->size) { + /* Append the packet payload as a fragment. */ + txp->offset += data_len; + txp->size -= data_len; + } else { + /* Schedule a response immediately. */ + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } + + if (txp->flags & XEN_NETTXF_csum_blank) + skb->ip_summed = CHECKSUM_PARTIAL; + else if (txp->flags & XEN_NETTXF_data_validated) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + xenvif_fill_frags(queue, skb); + + if (unlikely(skb_has_frag_list(skb))) { + if (xenvif_handle_frag_list(queue, skb)) { + if (net_ratelimit()) + netdev_err(queue->vif->dev, + "Not enough memory to consolidate frag_list!\n"); + xenvif_skb_zerocopy_prepare(queue, skb); + kfree_skb(skb); + continue; + } + } + + skb->dev = queue->vif->dev; + skb->protocol = eth_type_trans(skb, skb->dev); + skb_reset_network_header(skb); + + if (checksum_setup(queue, skb)) { + netdev_dbg(queue->vif->dev, + "Can't setup checksum in net_tx_action\n"); + /* We have to set this flag to trigger the callback */ + if (skb_shinfo(skb)->destructor_arg) + xenvif_skb_zerocopy_prepare(queue, skb); + kfree_skb(skb); + continue; + } + + skb_probe_transport_header(skb, 0); + + /* If the packet is GSO then we will have just set up the + * transport header offset in checksum_setup so it's now + * straightforward to calculate gso_segs. + */ + if (skb_is_gso(skb)) { + int mss = skb_shinfo(skb)->gso_size; + int hdrlen = skb_transport_header(skb) - + skb_mac_header(skb) + + tcp_hdrlen(skb); + + skb_shinfo(skb)->gso_segs = + DIV_ROUND_UP(skb->len - hdrlen, mss); + } + + queue->stats.rx_bytes += skb->len; + queue->stats.rx_packets++; + + work_done++; + + /* Set this flag right before netif_receive_skb, otherwise + * someone might think this packet already left netback, and + * do a skb_copy_ubufs while we are still in control of the + * skb. E.g. the __pskb_pull_tail earlier can do such thing. + */ + if (skb_shinfo(skb)->destructor_arg) { + xenvif_skb_zerocopy_prepare(queue, skb); + queue->stats.tx_zerocopy_sent++; + } + + netif_receive_skb(skb); + } + + return work_done; +} + +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success) +{ + unsigned long flags; + pending_ring_idx_t index; + struct xenvif_queue *queue = ubuf_to_queue(ubuf); + + /* This is the only place where we grab this lock, to protect callbacks + * from each other. + */ + spin_lock_irqsave(&queue->callback_lock, flags); + do { + u16 pending_idx = ubuf->desc; + ubuf = (struct ubuf_info *) ubuf->ctx; + BUG_ON(queue->dealloc_prod - queue->dealloc_cons >= + MAX_PENDING_REQS); + index = pending_index(queue->dealloc_prod); + queue->dealloc_ring[index] = pending_idx; + /* Sync with xenvif_tx_dealloc_action: + * insert idx then incr producer. + */ + smp_wmb(); + queue->dealloc_prod++; + } while (ubuf); + wake_up(&queue->dealloc_wq); + spin_unlock_irqrestore(&queue->callback_lock, flags); + + if (likely(zerocopy_success)) + queue->stats.tx_zerocopy_success++; + else + queue->stats.tx_zerocopy_fail++; + xenvif_skb_zerocopy_complete(queue); +} + +static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) +{ + struct gnttab_unmap_grant_ref *gop; + pending_ring_idx_t dc, dp; + u16 pending_idx, pending_idx_release[MAX_PENDING_REQS]; + unsigned int i = 0; + + dc = queue->dealloc_cons; + gop = queue->tx_unmap_ops; + + /* Free up any grants we have finished using */ + do { + dp = queue->dealloc_prod; + + /* Ensure we see all indices enqueued by all + * xenvif_zerocopy_callback(). + */ + smp_rmb(); + + while (dc != dp) { + BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS); + pending_idx = + queue->dealloc_ring[pending_index(dc++)]; + + pending_idx_release[gop-queue->tx_unmap_ops] = + pending_idx; + queue->pages_to_unmap[gop-queue->tx_unmap_ops] = + queue->mmap_pages[pending_idx]; + gnttab_set_unmap_op(gop, + idx_to_kaddr(queue, pending_idx), + GNTMAP_host_map, + queue->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(queue, pending_idx); + ++gop; + } + + } while (dp != queue->dealloc_prod); + + queue->dealloc_cons = dc; + + if (gop - queue->tx_unmap_ops > 0) { + int ret; + ret = gnttab_unmap_refs(queue->tx_unmap_ops, + NULL, + queue->pages_to_unmap, + gop - queue->tx_unmap_ops); + if (ret) { + netdev_err(queue->vif->dev, "Unmap fail: nr_ops %tx ret %d\n", + gop - queue->tx_unmap_ops, ret); + for (i = 0; i < gop - queue->tx_unmap_ops; ++i) { + if (gop[i].status != GNTST_okay) + netdev_err(queue->vif->dev, + " host_addr: %llx handle: %x status: %d\n", + gop[i].host_addr, + gop[i].handle, + gop[i].status); + } + BUG(); + } + } + + for (i = 0; i < gop - queue->tx_unmap_ops; ++i) + xenvif_idx_release(queue, pending_idx_release[i], + XEN_NETIF_RSP_OKAY); +} + + +/* Called after netfront has transmitted */ +int xenvif_tx_action(struct xenvif_queue *queue, int budget) +{ + unsigned nr_mops, nr_cops = 0; + int work_done, ret; + + if (unlikely(!tx_work_todo(queue))) + return 0; + + xenvif_tx_build_gops(queue, budget, &nr_cops, &nr_mops); + + if (nr_cops == 0) + return 0; + + gnttab_batch_copy(queue->tx_copy_ops, nr_cops); + if (nr_mops != 0) { + ret = gnttab_map_refs(queue->tx_map_ops, + NULL, + queue->pages_to_map, + nr_mops); + BUG_ON(ret); + } + + work_done = xenvif_tx_submit(queue); + + return work_done; +} + +static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, + u8 status) +{ + struct pending_tx_info *pending_tx_info; + pending_ring_idx_t index; + unsigned long flags; + + pending_tx_info = &queue->pending_tx_info[pending_idx]; + + spin_lock_irqsave(&queue->response_lock, flags); + + make_tx_response(queue, &pending_tx_info->req, status); + + /* Release the pending index before pusing the Tx response so + * its available before a new Tx request is pushed by the + * frontend. + */ + index = pending_index(queue->pending_prod++); + queue->pending_ring[index] = pending_idx; + + push_tx_responses(queue); + + spin_unlock_irqrestore(&queue->response_lock, flags); +} + + +static void make_tx_response(struct xenvif_queue *queue, + struct xen_netif_tx_request *txp, + s8 st) +{ + RING_IDX i = queue->tx.rsp_prod_pvt; + struct xen_netif_tx_response *resp; + + resp = RING_GET_RESPONSE(&queue->tx, i); + resp->id = txp->id; + resp->status = st; + + if (txp->flags & XEN_NETTXF_extra_info) + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + + queue->tx.rsp_prod_pvt = ++i; +} + +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + +static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, + u16 id, + s8 st, + u16 offset, + u16 size, + u16 flags) +{ + RING_IDX i = queue->rx.rsp_prod_pvt; + struct xen_netif_rx_response *resp; + + resp = RING_GET_RESPONSE(&queue->rx, i); + resp->offset = offset; + resp->flags = flags; + resp->id = id; + resp->status = (s16)size; + if (st < 0) + resp->status = (s16)st; + + queue->rx.rsp_prod_pvt = ++i; + + return resp; +} + +void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) +{ + int ret; + struct gnttab_unmap_grant_ref tx_unmap_op; + + gnttab_set_unmap_op(&tx_unmap_op, + idx_to_kaddr(queue, pending_idx), + GNTMAP_host_map, + queue->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(queue, pending_idx); + + ret = gnttab_unmap_refs(&tx_unmap_op, NULL, + &queue->mmap_pages[pending_idx], 1); + if (ret) { + netdev_err(queue->vif->dev, + "Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n", + ret, + pending_idx, + tx_unmap_op.host_addr, + tx_unmap_op.handle, + tx_unmap_op.status); + BUG(); + } +} + +static inline int tx_work_todo(struct xenvif_queue *queue) +{ + if (likely(RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))) + return 1; + + return 0; +} + +static inline bool tx_dealloc_work_todo(struct xenvif_queue *queue) +{ + return queue->dealloc_cons != queue->dealloc_prod; +} + +void xenvif_unmap_frontend_rings(struct xenvif_queue *queue) +{ + if (queue->tx.sring) + xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif), + queue->tx.sring); + if (queue->rx.sring) + xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif), + queue->rx.sring); +} + +int xenvif_map_frontend_rings(struct xenvif_queue *queue, + grant_ref_t tx_ring_ref, + grant_ref_t rx_ring_ref) +{ + void *addr; + struct xen_netif_tx_sring *txs; + struct xen_netif_rx_sring *rxs; + + int err = -ENOMEM; + + err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), + &tx_ring_ref, 1, &addr); + if (err) + goto err; + + txs = (struct xen_netif_tx_sring *)addr; + BACK_RING_INIT(&queue->tx, txs, PAGE_SIZE); + + err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), + &rx_ring_ref, 1, &addr); + if (err) + goto err; + + rxs = (struct xen_netif_rx_sring *)addr; + BACK_RING_INIT(&queue->rx, rxs, PAGE_SIZE); + + return 0; + +err: + xenvif_unmap_frontend_rings(queue); + return err; +} + +static void xenvif_queue_carrier_off(struct xenvif_queue *queue) +{ + struct xenvif *vif = queue->vif; + + queue->stalled = true; + + /* At least one queue has stalled? Disable the carrier. */ + spin_lock(&vif->lock); + if (vif->stalled_queues++ == 0) { + netdev_info(vif->dev, "Guest Rx stalled"); + netif_carrier_off(vif->dev); + } + spin_unlock(&vif->lock); +} + +static void xenvif_queue_carrier_on(struct xenvif_queue *queue) +{ + struct xenvif *vif = queue->vif; + + queue->last_rx_time = jiffies; /* Reset Rx stall detection. */ + queue->stalled = false; + + /* All queues are ready? Enable the carrier. */ + spin_lock(&vif->lock); + if (--vif->stalled_queues == 0) { + netdev_info(vif->dev, "Guest Rx ready"); + netif_carrier_on(vif->dev); + } + spin_unlock(&vif->lock); +} + +static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + return !queue->stalled + && prod - cons < XEN_NETBK_RX_SLOTS_MAX + && time_after(jiffies, + queue->last_rx_time + queue->vif->stall_timeout); +} + +static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + return queue->stalled + && prod - cons >= XEN_NETBK_RX_SLOTS_MAX; +} + +static bool xenvif_have_rx_work(struct xenvif_queue *queue) +{ + return (!skb_queue_empty(&queue->rx_queue) + && xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX)) + || (queue->vif->stall_timeout && + (xenvif_rx_queue_stalled(queue) + || xenvif_rx_queue_ready(queue))) + || kthread_should_stop() + || queue->vif->disabled; +} + +static long xenvif_rx_queue_timeout(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + long timeout; + + skb = skb_peek(&queue->rx_queue); + if (!skb) + return MAX_SCHEDULE_TIMEOUT; + + timeout = XENVIF_RX_CB(skb)->expires - jiffies; + return timeout < 0 ? 0 : timeout; +} + +/* Wait until the guest Rx thread has work. + * + * The timeout needs to be adjusted based on the current head of the + * queue (and not just the head at the beginning). In particular, if + * the queue is initially empty an infinite timeout is used and this + * needs to be reduced when a skb is queued. + * + * This cannot be done with wait_event_timeout() because it only + * calculates the timeout once. + */ +static void xenvif_wait_for_rx_work(struct xenvif_queue *queue) +{ + DEFINE_WAIT(wait); + + if (xenvif_have_rx_work(queue)) + return; + + for (;;) { + long ret; + + prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE); + if (xenvif_have_rx_work(queue)) + break; + ret = schedule_timeout(xenvif_rx_queue_timeout(queue)); + if (!ret) + break; + } + finish_wait(&queue->wq, &wait); +} + +int xenvif_kthread_guest_rx(void *data) +{ + struct xenvif_queue *queue = data; + struct xenvif *vif = queue->vif; + + if (!vif->stall_timeout) + xenvif_queue_carrier_on(queue); + + for (;;) { + xenvif_wait_for_rx_work(queue); + + if (kthread_should_stop()) + break; + + /* This frontend is found to be rogue, disable it in + * kthread context. Currently this is only set when + * netback finds out frontend sends malformed packet, + * but we cannot disable the interface in softirq + * context so we defer it here, if this thread is + * associated with queue 0. + */ + if (unlikely(vif->disabled && queue->id == 0)) { + xenvif_carrier_off(vif); + break; + } + + if (!skb_queue_empty(&queue->rx_queue)) + xenvif_rx_action(queue); + + /* If the guest hasn't provided any Rx slots for a + * while it's probably not responsive, drop the + * carrier so packets are dropped earlier. + */ + if (vif->stall_timeout) { + if (xenvif_rx_queue_stalled(queue)) + xenvif_queue_carrier_off(queue); + else if (xenvif_rx_queue_ready(queue)) + xenvif_queue_carrier_on(queue); + } + + /* Queued packets may have foreign pages from other + * domains. These cannot be queued indefinitely as + * this would starve guests of grant refs and transmit + * slots. + */ + xenvif_rx_queue_drop_expired(queue); + + xenvif_rx_queue_maybe_wake(queue); + + cond_resched(); + } + + /* Bin any remaining skbs */ + xenvif_rx_queue_purge(queue); + + return 0; +} + +static bool xenvif_dealloc_kthread_should_stop(struct xenvif_queue *queue) +{ + /* Dealloc thread must remain running until all inflight + * packets complete. + */ + return kthread_should_stop() && + !atomic_read(&queue->inflight_packets); +} + +int xenvif_dealloc_kthread(void *data) +{ + struct xenvif_queue *queue = data; + + for (;;) { + wait_event_interruptible(queue->dealloc_wq, + tx_dealloc_work_todo(queue) || + xenvif_dealloc_kthread_should_stop(queue)); + if (xenvif_dealloc_kthread_should_stop(queue)) + break; + + xenvif_tx_dealloc_action(queue); + cond_resched(); + } + + /* Unmap anything remaining*/ + if (tx_dealloc_work_todo(queue)) + xenvif_tx_dealloc_action(queue); + + return 0; +} + +static int __init netback_init(void) +{ + int rc = 0; + + if (!xen_domain()) + return -ENODEV; + + /* Allow as many queues as there are CPUs, by default */ + xenvif_max_queues = num_online_cpus(); + + if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) { + pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n", + fatal_skb_slots, XEN_NETBK_LEGACY_SLOTS_MAX); + fatal_skb_slots = XEN_NETBK_LEGACY_SLOTS_MAX; + } + + rc = xenvif_xenbus_init(); + if (rc) + goto failed_init; + +#ifdef CONFIG_DEBUG_FS + xen_netback_dbg_root = debugfs_create_dir("xen-netback", NULL); + if (IS_ERR_OR_NULL(xen_netback_dbg_root)) + pr_warn("Init of debugfs returned %ld!\n", + PTR_ERR(xen_netback_dbg_root)); +#endif /* CONFIG_DEBUG_FS */ + + return 0; + +failed_init: + return rc; +} + +module_init(netback_init); + +static void __exit netback_fini(void) +{ +#ifdef CONFIG_DEBUG_FS + if (!IS_ERR_OR_NULL(xen_netback_dbg_root)) + debugfs_remove_recursive(xen_netback_dbg_root); +#endif /* CONFIG_DEBUG_FS */ + xenvif_xenbus_fini(); +} +module_exit(netback_fini); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("xen-backend:vif"); diff --git a/kernel/drivers/net/xen-netback/xenbus.c b/kernel/drivers/net/xen-netback/xenbus.c new file mode 100644 index 000000000..ec383b0f5 --- /dev/null +++ b/kernel/drivers/net/xen-netback/xenbus.c @@ -0,0 +1,1043 @@ +/* + * Xenbus code for netif backend + * + * Copyright (C) 2005 Rusty Russell + * Copyright (C) 2005 XenSource Ltd + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . +*/ + +#include "common.h" +#include +#include + +struct backend_info { + struct xenbus_device *dev; + struct xenvif *vif; + + /* This is the state that will be reflected in xenstore when any + * active hotplug script completes. + */ + enum xenbus_state state; + + enum xenbus_state frontend_state; + struct xenbus_watch hotplug_status_watch; + u8 have_hotplug_status_watch:1; + + const char *hotplug_script; +}; + +static int connect_rings(struct backend_info *be, struct xenvif_queue *queue); +static void connect(struct backend_info *be); +static int read_xenbus_vif_flags(struct backend_info *be); +static int backend_create_xenvif(struct backend_info *be); +static void unregister_hotplug_status_watch(struct backend_info *be); +static void xen_unregister_watchers(struct xenvif *vif); +static void set_backend_state(struct backend_info *be, + enum xenbus_state state); + +#ifdef CONFIG_DEBUG_FS +struct dentry *xen_netback_dbg_root = NULL; + +static int xenvif_read_io_ring(struct seq_file *m, void *v) +{ + struct xenvif_queue *queue = m->private; + struct xen_netif_tx_back_ring *tx_ring = &queue->tx; + struct xen_netif_rx_back_ring *rx_ring = &queue->rx; + struct netdev_queue *dev_queue; + + if (tx_ring->sring) { + struct xen_netif_tx_sring *sring = tx_ring->sring; + + seq_printf(m, "Queue %d\nTX: nr_ents %u\n", queue->id, + tx_ring->nr_ents); + seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n", + sring->req_prod, + sring->req_prod - sring->rsp_prod, + tx_ring->req_cons, + tx_ring->req_cons - sring->rsp_prod, + sring->req_event, + sring->req_event - sring->rsp_prod); + seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n", + sring->rsp_prod, + tx_ring->rsp_prod_pvt, + tx_ring->rsp_prod_pvt - sring->rsp_prod, + sring->rsp_event, + sring->rsp_event - sring->rsp_prod); + seq_printf(m, "pending prod %u pending cons %u nr_pending_reqs %u\n", + queue->pending_prod, + queue->pending_cons, + nr_pending_reqs(queue)); + seq_printf(m, "dealloc prod %u dealloc cons %u dealloc_queue %u\n\n", + queue->dealloc_prod, + queue->dealloc_cons, + queue->dealloc_prod - queue->dealloc_cons); + } + + if (rx_ring->sring) { + struct xen_netif_rx_sring *sring = rx_ring->sring; + + seq_printf(m, "RX: nr_ents %u\n", rx_ring->nr_ents); + seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n", + sring->req_prod, + sring->req_prod - sring->rsp_prod, + rx_ring->req_cons, + rx_ring->req_cons - sring->rsp_prod, + sring->req_event, + sring->req_event - sring->rsp_prod); + seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n\n", + sring->rsp_prod, + rx_ring->rsp_prod_pvt, + rx_ring->rsp_prod_pvt - sring->rsp_prod, + sring->rsp_event, + sring->rsp_event - sring->rsp_prod); + } + + seq_printf(m, "NAPI state: %lx NAPI weight: %d TX queue len %u\n" + "Credit timer_pending: %d, credit: %lu, usec: %lu\n" + "remaining: %lu, expires: %lu, now: %lu\n", + queue->napi.state, queue->napi.weight, + skb_queue_len(&queue->tx_queue), + timer_pending(&queue->credit_timeout), + queue->credit_bytes, + queue->credit_usec, + queue->remaining_credit, + queue->credit_timeout.expires, + jiffies); + + dev_queue = netdev_get_tx_queue(queue->vif->dev, queue->id); + + seq_printf(m, "\nRx internal queue: len %u max %u pkts %u %s\n", + queue->rx_queue_len, queue->rx_queue_max, + skb_queue_len(&queue->rx_queue), + netif_tx_queue_stopped(dev_queue) ? "stopped" : "running"); + + return 0; +} + +#define XENVIF_KICK_STR "kick" +#define BUFFER_SIZE 32 + +static ssize_t +xenvif_write_io_ring(struct file *filp, const char __user *buf, size_t count, + loff_t *ppos) +{ + struct xenvif_queue *queue = + ((struct seq_file *)filp->private_data)->private; + int len; + char write[BUFFER_SIZE]; + + /* don't allow partial writes and check the length */ + if (*ppos != 0) + return 0; + if (count >= sizeof(write)) + return -ENOSPC; + + len = simple_write_to_buffer(write, + sizeof(write) - 1, + ppos, + buf, + count); + if (len < 0) + return len; + + write[len] = '\0'; + + if (!strncmp(write, XENVIF_KICK_STR, sizeof(XENVIF_KICK_STR) - 1)) + xenvif_interrupt(0, (void *)queue); + else { + pr_warn("Unknown command to io_ring_q%d. Available: kick\n", + queue->id); + count = -EINVAL; + } + return count; +} + +static int xenvif_dump_open(struct inode *inode, struct file *filp) +{ + int ret; + void *queue = NULL; + + if (inode->i_private) + queue = inode->i_private; + ret = single_open(filp, xenvif_read_io_ring, queue); + filp->f_mode |= FMODE_PWRITE; + return ret; +} + +static const struct file_operations xenvif_dbg_io_ring_ops_fops = { + .owner = THIS_MODULE, + .open = xenvif_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = xenvif_write_io_ring, +}; + +static void xenvif_debugfs_addif(struct xenvif *vif) +{ + struct dentry *pfile; + int i; + + if (IS_ERR_OR_NULL(xen_netback_dbg_root)) + return; + + vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name, + xen_netback_dbg_root); + if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) { + for (i = 0; i < vif->num_queues; ++i) { + char filename[sizeof("io_ring_q") + 4]; + + snprintf(filename, sizeof(filename), "io_ring_q%d", i); + pfile = debugfs_create_file(filename, + S_IRUSR | S_IWUSR, + vif->xenvif_dbg_root, + &vif->queues[i], + &xenvif_dbg_io_ring_ops_fops); + if (IS_ERR_OR_NULL(pfile)) + pr_warn("Creation of io_ring file returned %ld!\n", + PTR_ERR(pfile)); + } + } else + netdev_warn(vif->dev, + "Creation of vif debugfs dir returned %ld!\n", + PTR_ERR(vif->xenvif_dbg_root)); +} + +static void xenvif_debugfs_delif(struct xenvif *vif) +{ + if (IS_ERR_OR_NULL(xen_netback_dbg_root)) + return; + + if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) + debugfs_remove_recursive(vif->xenvif_dbg_root); + vif->xenvif_dbg_root = NULL; +} +#endif /* CONFIG_DEBUG_FS */ + +static int netback_remove(struct xenbus_device *dev) +{ + struct backend_info *be = dev_get_drvdata(&dev->dev); + + set_backend_state(be, XenbusStateClosed); + + unregister_hotplug_status_watch(be); + if (be->vif) { + kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); + xen_unregister_watchers(be->vif); + xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); + xenvif_free(be->vif); + be->vif = NULL; + } + kfree(be->hotplug_script); + kfree(be); + dev_set_drvdata(&dev->dev, NULL); + return 0; +} + + +/** + * Entry point to this code when a new device is created. Allocate the basic + * structures and switch to InitWait. + */ +static int netback_probe(struct xenbus_device *dev, + const struct xenbus_device_id *id) +{ + const char *message; + struct xenbus_transaction xbt; + int err; + int sg; + const char *script; + struct backend_info *be = kzalloc(sizeof(struct backend_info), + GFP_KERNEL); + if (!be) { + xenbus_dev_fatal(dev, -ENOMEM, + "allocating backend structure"); + return -ENOMEM; + } + + be->dev = dev; + dev_set_drvdata(&dev->dev, be); + + sg = 1; + + do { + err = xenbus_transaction_start(&xbt); + if (err) { + xenbus_dev_fatal(dev, err, "starting transaction"); + goto fail; + } + + err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", sg); + if (err) { + message = "writing feature-sg"; + goto abort_transaction; + } + + err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4", + "%d", sg); + if (err) { + message = "writing feature-gso-tcpv4"; + goto abort_transaction; + } + + err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6", + "%d", sg); + if (err) { + message = "writing feature-gso-tcpv6"; + goto abort_transaction; + } + + /* We support partial checksum setup for IPv6 packets */ + err = xenbus_printf(xbt, dev->nodename, + "feature-ipv6-csum-offload", + "%d", 1); + if (err) { + message = "writing feature-ipv6-csum-offload"; + goto abort_transaction; + } + + /* We support rx-copy path. */ + err = xenbus_printf(xbt, dev->nodename, + "feature-rx-copy", "%d", 1); + if (err) { + message = "writing feature-rx-copy"; + goto abort_transaction; + } + + /* + * We don't support rx-flip path (except old guests who don't + * grok this feature flag). + */ + err = xenbus_printf(xbt, dev->nodename, + "feature-rx-flip", "%d", 0); + if (err) { + message = "writing feature-rx-flip"; + goto abort_transaction; + } + + err = xenbus_transaction_end(xbt, 0); + } while (err == -EAGAIN); + + if (err) { + xenbus_dev_fatal(dev, err, "completing transaction"); + goto fail; + } + + /* + * Split event channels support, this is optional so it is not + * put inside the above loop. + */ + err = xenbus_printf(XBT_NIL, dev->nodename, + "feature-split-event-channels", + "%u", separate_tx_rx_irq); + if (err) + pr_debug("Error writing feature-split-event-channels\n"); + + /* Multi-queue support: This is an optional feature. */ + err = xenbus_printf(XBT_NIL, dev->nodename, + "multi-queue-max-queues", "%u", xenvif_max_queues); + if (err) + pr_debug("Error writing multi-queue-max-queues\n"); + + script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL); + if (IS_ERR(script)) { + err = PTR_ERR(script); + xenbus_dev_fatal(dev, err, "reading script"); + goto fail; + } + + be->hotplug_script = script; + + err = xenbus_switch_state(dev, XenbusStateInitWait); + if (err) + goto fail; + + be->state = XenbusStateInitWait; + + /* This kicks hotplug scripts, so do it immediately. */ + err = backend_create_xenvif(be); + if (err) + goto fail; + + return 0; + +abort_transaction: + xenbus_transaction_end(xbt, 1); + xenbus_dev_fatal(dev, err, "%s", message); +fail: + pr_debug("failed\n"); + netback_remove(dev); + return err; +} + + +/* + * Handle the creation of the hotplug script environment. We add the script + * and vif variables to the environment, for the benefit of the vif-* hotplug + * scripts. + */ +static int netback_uevent(struct xenbus_device *xdev, + struct kobj_uevent_env *env) +{ + struct backend_info *be = dev_get_drvdata(&xdev->dev); + + if (!be) + return 0; + + if (add_uevent_var(env, "script=%s", be->hotplug_script)) + return -ENOMEM; + + if (!be->vif) + return 0; + + return add_uevent_var(env, "vif=%s", be->vif->dev->name); +} + + +static int backend_create_xenvif(struct backend_info *be) +{ + int err; + long handle; + struct xenbus_device *dev = be->dev; + struct xenvif *vif; + + if (be->vif != NULL) + return 0; + + err = xenbus_scanf(XBT_NIL, dev->nodename, "handle", "%li", &handle); + if (err != 1) { + xenbus_dev_fatal(dev, err, "reading handle"); + return (err < 0) ? err : -EINVAL; + } + + vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle); + if (IS_ERR(vif)) { + err = PTR_ERR(vif); + xenbus_dev_fatal(dev, err, "creating interface"); + return err; + } + be->vif = vif; + + kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE); + return 0; +} + +static void backend_disconnect(struct backend_info *be) +{ + if (be->vif) { + xen_unregister_watchers(be->vif); +#ifdef CONFIG_DEBUG_FS + xenvif_debugfs_delif(be->vif); +#endif /* CONFIG_DEBUG_FS */ + xenvif_disconnect(be->vif); + } +} + +static void backend_connect(struct backend_info *be) +{ + if (be->vif) + connect(be); +} + +static inline void backend_switch_state(struct backend_info *be, + enum xenbus_state state) +{ + struct xenbus_device *dev = be->dev; + + pr_debug("%s -> %s\n", dev->nodename, xenbus_strstate(state)); + be->state = state; + + /* If we are waiting for a hotplug script then defer the + * actual xenbus state change. + */ + if (!be->have_hotplug_status_watch) + xenbus_switch_state(dev, state); +} + +/* Handle backend state transitions: + * + * The backend state starts in InitWait and the following transitions are + * allowed. + * + * InitWait -> Connected + * + * ^ \ | + * | \ | + * | \ | + * | \ | + * | \ | + * | \ | + * | V V + * + * Closed <-> Closing + * + * The state argument specifies the eventual state of the backend and the + * function transitions to that state via the shortest path. + */ +static void set_backend_state(struct backend_info *be, + enum xenbus_state state) +{ + while (be->state != state) { + switch (be->state) { + case XenbusStateClosed: + switch (state) { + case XenbusStateInitWait: + case XenbusStateConnected: + pr_info("%s: prepare for reconnect\n", + be->dev->nodename); + backend_switch_state(be, XenbusStateInitWait); + break; + case XenbusStateClosing: + backend_switch_state(be, XenbusStateClosing); + break; + default: + BUG(); + } + break; + case XenbusStateInitWait: + switch (state) { + case XenbusStateConnected: + backend_connect(be); + backend_switch_state(be, XenbusStateConnected); + break; + case XenbusStateClosing: + case XenbusStateClosed: + backend_switch_state(be, XenbusStateClosing); + break; + default: + BUG(); + } + break; + case XenbusStateConnected: + switch (state) { + case XenbusStateInitWait: + case XenbusStateClosing: + case XenbusStateClosed: + backend_disconnect(be); + backend_switch_state(be, XenbusStateClosing); + break; + default: + BUG(); + } + break; + case XenbusStateClosing: + switch (state) { + case XenbusStateInitWait: + case XenbusStateConnected: + case XenbusStateClosed: + backend_switch_state(be, XenbusStateClosed); + break; + default: + BUG(); + } + break; + default: + BUG(); + } + } +} + +/** + * Callback received when the frontend's state changes. + */ +static void frontend_changed(struct xenbus_device *dev, + enum xenbus_state frontend_state) +{ + struct backend_info *be = dev_get_drvdata(&dev->dev); + + pr_debug("%s -> %s\n", dev->otherend, xenbus_strstate(frontend_state)); + + be->frontend_state = frontend_state; + + switch (frontend_state) { + case XenbusStateInitialising: + set_backend_state(be, XenbusStateInitWait); + break; + + case XenbusStateInitialised: + break; + + case XenbusStateConnected: + set_backend_state(be, XenbusStateConnected); + break; + + case XenbusStateClosing: + set_backend_state(be, XenbusStateClosing); + break; + + case XenbusStateClosed: + set_backend_state(be, XenbusStateClosed); + if (xenbus_dev_is_online(dev)) + break; + /* fall through if not online */ + case XenbusStateUnknown: + set_backend_state(be, XenbusStateClosed); + device_unregister(&dev->dev); + break; + + default: + xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend", + frontend_state); + break; + } +} + + +static void xen_net_read_rate(struct xenbus_device *dev, + unsigned long *bytes, unsigned long *usec) +{ + char *s, *e; + unsigned long b, u; + char *ratestr; + + /* Default to unlimited bandwidth. */ + *bytes = ~0UL; + *usec = 0; + + ratestr = xenbus_read(XBT_NIL, dev->nodename, "rate", NULL); + if (IS_ERR(ratestr)) + return; + + s = ratestr; + b = simple_strtoul(s, &e, 10); + if ((s == e) || (*e != ',')) + goto fail; + + s = e + 1; + u = simple_strtoul(s, &e, 10); + if ((s == e) || (*e != '\0')) + goto fail; + + *bytes = b; + *usec = u; + + kfree(ratestr); + return; + + fail: + pr_warn("Failed to parse network rate limit. Traffic unlimited.\n"); + kfree(ratestr); +} + +static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[]) +{ + char *s, *e, *macstr; + int i; + + macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL); + if (IS_ERR(macstr)) + return PTR_ERR(macstr); + + for (i = 0; i < ETH_ALEN; i++) { + mac[i] = simple_strtoul(s, &e, 16); + if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) { + kfree(macstr); + return -ENOENT; + } + s = e+1; + } + + kfree(macstr); + return 0; +} + +static void xen_net_rate_changed(struct xenbus_watch *watch, + const char **vec, unsigned int len) +{ + struct xenvif *vif = container_of(watch, struct xenvif, credit_watch); + struct xenbus_device *dev = xenvif_to_xenbus_device(vif); + unsigned long credit_bytes; + unsigned long credit_usec; + unsigned int queue_index; + + xen_net_read_rate(dev, &credit_bytes, &credit_usec); + for (queue_index = 0; queue_index < vif->num_queues; queue_index++) { + struct xenvif_queue *queue = &vif->queues[queue_index]; + + queue->credit_bytes = credit_bytes; + queue->credit_usec = credit_usec; + if (!mod_timer_pending(&queue->credit_timeout, jiffies) && + queue->remaining_credit > queue->credit_bytes) { + queue->remaining_credit = queue->credit_bytes; + } + } +} + +static int xen_register_watchers(struct xenbus_device *dev, struct xenvif *vif) +{ + int err = 0; + char *node; + unsigned maxlen = strlen(dev->nodename) + sizeof("/rate"); + + if (vif->credit_watch.node) + return -EADDRINUSE; + + node = kmalloc(maxlen, GFP_KERNEL); + if (!node) + return -ENOMEM; + snprintf(node, maxlen, "%s/rate", dev->nodename); + vif->credit_watch.node = node; + vif->credit_watch.callback = xen_net_rate_changed; + err = register_xenbus_watch(&vif->credit_watch); + if (err) { + pr_err("Failed to set watcher %s\n", vif->credit_watch.node); + kfree(node); + vif->credit_watch.node = NULL; + vif->credit_watch.callback = NULL; + } + return err; +} + +static void xen_unregister_watchers(struct xenvif *vif) +{ + if (vif->credit_watch.node) { + unregister_xenbus_watch(&vif->credit_watch); + kfree(vif->credit_watch.node); + vif->credit_watch.node = NULL; + } +} + +static void unregister_hotplug_status_watch(struct backend_info *be) +{ + if (be->have_hotplug_status_watch) { + unregister_xenbus_watch(&be->hotplug_status_watch); + kfree(be->hotplug_status_watch.node); + } + be->have_hotplug_status_watch = 0; +} + +static void hotplug_status_changed(struct xenbus_watch *watch, + const char **vec, + unsigned int vec_size) +{ + struct backend_info *be = container_of(watch, + struct backend_info, + hotplug_status_watch); + char *str; + unsigned int len; + + str = xenbus_read(XBT_NIL, be->dev->nodename, "hotplug-status", &len); + if (IS_ERR(str)) + return; + if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) { + /* Complete any pending state change */ + xenbus_switch_state(be->dev, be->state); + + /* Not interested in this watch anymore. */ + unregister_hotplug_status_watch(be); + } + kfree(str); +} + +static void connect(struct backend_info *be) +{ + int err; + struct xenbus_device *dev = be->dev; + unsigned long credit_bytes, credit_usec; + unsigned int queue_index; + unsigned int requested_num_queues; + struct xenvif_queue *queue; + + /* Check whether the frontend requested multiple queues + * and read the number requested. + */ + err = xenbus_scanf(XBT_NIL, dev->otherend, + "multi-queue-num-queues", + "%u", &requested_num_queues); + if (err < 0) { + requested_num_queues = 1; /* Fall back to single queue */ + } else if (requested_num_queues > xenvif_max_queues) { + /* buggy or malicious guest */ + xenbus_dev_fatal(dev, err, + "guest requested %u queues, exceeding the maximum of %u.", + requested_num_queues, xenvif_max_queues); + return; + } + + err = xen_net_read_mac(dev, be->vif->fe_dev_addr); + if (err) { + xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename); + return; + } + + xen_net_read_rate(dev, &credit_bytes, &credit_usec); + xen_unregister_watchers(be->vif); + xen_register_watchers(dev, be->vif); + read_xenbus_vif_flags(be); + + /* Use the number of queues requested by the frontend */ + be->vif->queues = vzalloc(requested_num_queues * + sizeof(struct xenvif_queue)); + be->vif->num_queues = requested_num_queues; + be->vif->stalled_queues = requested_num_queues; + + for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) { + queue = &be->vif->queues[queue_index]; + queue->vif = be->vif; + queue->id = queue_index; + snprintf(queue->name, sizeof(queue->name), "%s-q%u", + be->vif->dev->name, queue->id); + + err = xenvif_init_queue(queue); + if (err) { + /* xenvif_init_queue() cleans up after itself on + * failure, but we need to clean up any previously + * initialised queues. Set num_queues to i so that + * earlier queues can be destroyed using the regular + * disconnect logic. + */ + be->vif->num_queues = queue_index; + goto err; + } + + queue->credit_bytes = credit_bytes; + queue->remaining_credit = credit_bytes; + queue->credit_usec = credit_usec; + + err = connect_rings(be, queue); + if (err) { + /* connect_rings() cleans up after itself on failure, + * but we need to clean up after xenvif_init_queue() here, + * and also clean up any previously initialised queues. + */ + xenvif_deinit_queue(queue); + be->vif->num_queues = queue_index; + goto err; + } + } + +#ifdef CONFIG_DEBUG_FS + xenvif_debugfs_addif(be->vif); +#endif /* CONFIG_DEBUG_FS */ + + /* Initialisation completed, tell core driver the number of + * active queues. + */ + rtnl_lock(); + netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues); + netif_set_real_num_rx_queues(be->vif->dev, requested_num_queues); + rtnl_unlock(); + + xenvif_carrier_on(be->vif); + + unregister_hotplug_status_watch(be); + err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, + hotplug_status_changed, + "%s/%s", dev->nodename, "hotplug-status"); + if (!err) + be->have_hotplug_status_watch = 1; + + netif_tx_wake_all_queues(be->vif->dev); + + return; + +err: + if (be->vif->num_queues > 0) + xenvif_disconnect(be->vif); /* Clean up existing queues */ + vfree(be->vif->queues); + be->vif->queues = NULL; + be->vif->num_queues = 0; + return; +} + + +static int connect_rings(struct backend_info *be, struct xenvif_queue *queue) +{ + struct xenbus_device *dev = be->dev; + unsigned int num_queues = queue->vif->num_queues; + unsigned long tx_ring_ref, rx_ring_ref; + unsigned int tx_evtchn, rx_evtchn; + int err; + char *xspath; + size_t xspathsize; + const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */ + + /* If the frontend requested 1 queue, or we have fallen back + * to single queue due to lack of frontend support for multi- + * queue, expect the remaining XenStore keys in the toplevel + * directory. Otherwise, expect them in a subdirectory called + * queue-N. + */ + if (num_queues == 1) { + xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL); + if (!xspath) { + xenbus_dev_fatal(dev, -ENOMEM, + "reading ring references"); + return -ENOMEM; + } + strcpy(xspath, dev->otherend); + } else { + xspathsize = strlen(dev->otherend) + xenstore_path_ext_size; + xspath = kzalloc(xspathsize, GFP_KERNEL); + if (!xspath) { + xenbus_dev_fatal(dev, -ENOMEM, + "reading ring references"); + return -ENOMEM; + } + snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend, + queue->id); + } + + err = xenbus_gather(XBT_NIL, xspath, + "tx-ring-ref", "%lu", &tx_ring_ref, + "rx-ring-ref", "%lu", &rx_ring_ref, NULL); + if (err) { + xenbus_dev_fatal(dev, err, + "reading %s/ring-ref", + xspath); + goto err; + } + + /* Try split event channels first, then single event channel. */ + err = xenbus_gather(XBT_NIL, xspath, + "event-channel-tx", "%u", &tx_evtchn, + "event-channel-rx", "%u", &rx_evtchn, NULL); + if (err < 0) { + err = xenbus_scanf(XBT_NIL, xspath, + "event-channel", "%u", &tx_evtchn); + if (err < 0) { + xenbus_dev_fatal(dev, err, + "reading %s/event-channel(-tx/rx)", + xspath); + goto err; + } + rx_evtchn = tx_evtchn; + } + + /* Map the shared frame, irq etc. */ + err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref, + tx_evtchn, rx_evtchn); + if (err) { + xenbus_dev_fatal(dev, err, + "mapping shared-frames %lu/%lu port tx %u rx %u", + tx_ring_ref, rx_ring_ref, + tx_evtchn, rx_evtchn); + goto err; + } + + err = 0; +err: /* Regular return falls through with err == 0 */ + kfree(xspath); + return err; +} + +static int read_xenbus_vif_flags(struct backend_info *be) +{ + struct xenvif *vif = be->vif; + struct xenbus_device *dev = be->dev; + unsigned int rx_copy; + int err, val; + + err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u", + &rx_copy); + if (err == -ENOENT) { + err = 0; + rx_copy = 0; + } + if (err < 0) { + xenbus_dev_fatal(dev, err, "reading %s/request-rx-copy", + dev->otherend); + return err; + } + if (!rx_copy) + return -EOPNOTSUPP; + + if (xenbus_scanf(XBT_NIL, dev->otherend, + "feature-rx-notify", "%d", &val) < 0) + val = 0; + if (!val) { + /* - Reduce drain timeout to poll more frequently for + * Rx requests. + * - Disable Rx stall detection. + */ + be->vif->drain_timeout = msecs_to_jiffies(30); + be->vif->stall_timeout = 0; + } + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg", + "%d", &val) < 0) + val = 0; + vif->can_sg = !!val; + + vif->gso_mask = 0; + vif->gso_prefix_mask = 0; + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_mask |= GSO_BIT(TCPV4); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV4); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_mask |= GSO_BIT(TCPV6); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV6); + + if (vif->gso_mask & vif->gso_prefix_mask) { + xenbus_dev_fatal(dev, err, + "%s: gso and gso prefix flags are not " + "mutually exclusive", + dev->otherend); + return -EOPNOTSUPP; + } + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", + "%d", &val) < 0) + val = 0; + vif->ip_csum = !val; + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload", + "%d", &val) < 0) + val = 0; + vif->ipv6_csum = !!val; + + return 0; +} + +static const struct xenbus_device_id netback_ids[] = { + { "vif" }, + { "" } +}; + +static struct xenbus_driver netback_driver = { + .ids = netback_ids, + .probe = netback_probe, + .remove = netback_remove, + .uevent = netback_uevent, + .otherend_changed = frontend_changed, +}; + +int xenvif_xenbus_init(void) +{ + return xenbus_register_backend(&netback_driver); +} + +void xenvif_xenbus_fini(void) +{ + return xenbus_unregister_driver(&netback_driver); +} -- cgit 1.2.3-korg