lastdragon/linux-kernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Resguardo inicial

Browse Source
This commit is contained in:
lastdragon
2026-09-06 12:53:21 -06:00
parent 662efe3c2a
commit ad2088d178
94853 changed files with 43200404 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
linux-7.2.3/drivers/net/xen-netback/Makefile
+4
View File
@@ -0,0 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_XEN_NETDEV_BACKEND) := xen-netback.o
xen-netback-y := netback.o xenbus.o interface.o hash.o rx.o
linux-7.2.3/drivers/net/xen-netback/common.h
+442
View File
@@ -0,0 +1,442 @@
/*
* 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 <linux/module.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/io.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <xen/interface/io/netif.h>
#include <xen/interface/grant_table.h>
#include <xen/grant_table.h>
#include <xen/xenbus.h>
#include <xen/page.h>
#include <linux/debugfs.h>
typedef unsigned int pending_ring_idx_t;
struct pending_tx_info {
struct xen_netif_tx_request req; /* tx request */
unsigned int extra_count;
/* 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_msgzc callback_struct;
};
#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, XEN_PAGE_SIZE)
#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, XEN_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_PENDING_REQS XEN_NETIF_TX_RING_SIZE
/* The maximum number of frags is derived from the size of a grant (same
* as a Xen page size for now).
*/
#define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
#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.
*/
u64 rx_bytes;
u64 rx_packets;
u64 tx_bytes;
u64 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;
};
#define COPY_BATCH_SIZE 64
struct xenvif_copy_state {
struct gnttab_copy op[COPY_BATCH_SIZE];
RING_IDX idx[COPY_BATCH_SIZE];
unsigned int num;
struct sk_buff_head *completed;
};
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 */
/*
* TX/RX common EOI handling.
* When feature-split-event-channels = 0, interrupt handler sets
* NETBK_COMMON_EOI, otherwise NETBK_RX_EOI and NETBK_TX_EOI are set
* by the RX and TX interrupt handlers.
* RX and TX handler threads will issue an EOI when either
* NETBK_COMMON_EOI or their specific bits (NETBK_RX_EOI or
* NETBK_TX_EOI) are set and they will reset those bits.
*/
atomic_t eoi_pending;
#define NETBK_RX_EOI 0x01
#define NETBK_TX_EOI 0x02
#define NETBK_COMMON_EOI 0x04
/* 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[2 * 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;
unsigned int rx_slots_needed;
bool stalled;
struct xenvif_copy_state rx_copy;
/* 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;
bool rate_limited;
/* Statistics */
struct xenvif_stats stats;
};
enum state_bit_shift {
/* This bit marks that the vif is connected */
VIF_STATUS_CONNECTED,
};
struct xenvif_mcast_addr {
struct list_head entry;
struct rcu_head rcu;
u8 addr[6];
};
#define XEN_NETBK_MCAST_MAX 64
#define XEN_NETBK_MAX_HASH_KEY_SIZE 40
#define XEN_NETBK_MAX_HASH_MAPPING_SIZE 128
#define XEN_NETBK_HASH_TAG_SIZE 40
struct xenvif_hash_cache_entry {
struct list_head link;
struct rcu_head rcu;
u8 tag[XEN_NETBK_HASH_TAG_SIZE];
unsigned int len;
u32 val;
int seq;
};
struct xenvif_hash_cache {
spinlock_t lock;
struct list_head list;
unsigned int count;
atomic_t seq;
};
struct xenvif_hash {
unsigned int alg;
u32 flags;
bool mapping_sel;
u8 key[XEN_NETBK_MAX_HASH_KEY_SIZE];
u32 mapping[2][XEN_NETBK_MAX_HASH_MAPPING_SIZE];
unsigned int size;
struct xenvif_hash_cache cache;
};
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;
};
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
unsigned int handle;
u8 fe_dev_addr[6];
struct list_head fe_mcast_addr;
unsigned int fe_mcast_count;
/* Frontend feature information. */
int gso_mask;
u8 can_sg:1;
u8 ip_csum:1;
u8 ipv6_csum:1;
u8 multicast_control:1;
/* headroom requested by xen-netfront */
u16 xdp_headroom;
/* 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 xenvif_hash hash;
struct xenbus_watch credit_watch;
struct xenbus_watch mcast_ctrl_watch;
struct backend_info *be;
spinlock_t lock;
#ifdef CONFIG_DEBUG_FS
struct dentry *xenvif_dbg_root;
#endif
struct xen_netif_ctrl_back_ring ctrl;
unsigned int ctrl_irq;
/* 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(struct timer_list *t);
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_data(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_data(struct xenvif *vif);
int xenvif_connect_ctrl(struct xenvif *vif, grant_ref_t ring_ref,
unsigned int evtchn);
void xenvif_disconnect_ctrl(struct xenvif *vif);
void xenvif_free(struct xenvif *vif);
int xenvif_xenbus_init(void);
void xenvif_xenbus_fini(void);
/* (Un)Map communication rings. */
void xenvif_unmap_frontend_data_rings(struct xenvif_queue *queue);
int xenvif_map_frontend_data_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);
irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data);
bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread);
bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb);
void xenvif_carrier_on(struct xenvif *vif);
/* Callbacks from stack when TX packet can be released */
extern const struct ubuf_info_ops xenvif_ubuf_ops;
static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
{
return MAX_PENDING_REQS -
queue->pending_prod + queue->pending_cons;
}
irqreturn_t xenvif_interrupt(int irq, void *dev_id);
extern bool separate_tx_rx_irq;
extern bool provides_xdp_headroom;
extern unsigned int rx_drain_timeout_msecs;
extern unsigned int rx_stall_timeout_msecs;
extern unsigned int xenvif_max_queues;
extern unsigned int xenvif_hash_cache_size;
#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);
/* Multicast control */
bool xenvif_mcast_match(struct xenvif *vif, const u8 *addr);
void xenvif_mcast_addr_list_free(struct xenvif *vif);
/* Hash */
void xenvif_init_hash(struct xenvif *vif);
void xenvif_deinit_hash(struct xenvif *vif);
u32 xenvif_set_hash_alg(struct xenvif *vif, u32 alg);
u32 xenvif_get_hash_flags(struct xenvif *vif, u32 *flags);
u32 xenvif_set_hash_flags(struct xenvif *vif, u32 flags);
u32 xenvif_set_hash_key(struct xenvif *vif, u32 gref, u32 len);
u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size);
u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len,
u32 off);
void xenvif_set_skb_hash(struct xenvif *vif, struct sk_buff *skb);
#ifdef CONFIG_DEBUG_FS
void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m);
#endif
#endif /* __XEN_NETBACK__COMMON_H__ */
linux-7.2.3/drivers/net/xen-netback/hash.c
+467
View File
@@ -0,0 +1,467 @@
/*
* Copyright (c) 2016 Citrix Systems Inc.
*
* 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.
*/
#define XEN_NETIF_DEFINE_TOEPLITZ
#include "common.h"
#include <linux/vmalloc.h>
#include <linux/rculist.h>
static void xenvif_add_hash(struct xenvif *vif, const u8 *tag,
unsigned int len, u32 val)
{
struct xenvif_hash_cache_entry *new, *entry, *oldest;
unsigned long flags;
bool found;
new = kmalloc_obj(*entry, GFP_ATOMIC);
if (!new)
return;
memcpy(new->tag, tag, len);
new->len = len;
new->val = val;
spin_lock_irqsave(&vif->hash.cache.lock, flags);
found = false;
oldest = NULL;
list_for_each_entry_rcu(entry, &vif->hash.cache.list, link,
lockdep_is_held(&vif->hash.cache.lock)) {
/* Make sure we don't add duplicate entries */
if (entry->len == len &&
memcmp(entry->tag, tag, len) == 0)
found = true;
if (!oldest || entry->seq < oldest->seq)
oldest = entry;
}
if (!found) {
new->seq = atomic_inc_return(&vif->hash.cache.seq);
list_add_rcu(&new->link, &vif->hash.cache.list);
if (++vif->hash.cache.count > xenvif_hash_cache_size) {
list_del_rcu(&oldest->link);
vif->hash.cache.count--;
kfree_rcu(oldest, rcu);
}
}
spin_unlock_irqrestore(&vif->hash.cache.lock, flags);
if (found)
kfree(new);
}
static u32 xenvif_new_hash(struct xenvif *vif, const u8 *data,
unsigned int len)
{
u32 val;
val = xen_netif_toeplitz_hash(vif->hash.key,
sizeof(vif->hash.key),
data, len);
if (xenvif_hash_cache_size != 0)
xenvif_add_hash(vif, data, len, val);
return val;
}
static void xenvif_flush_hash(struct xenvif *vif)
{
struct xenvif_hash_cache_entry *entry, *n;
unsigned long flags;
if (xenvif_hash_cache_size == 0)
return;
spin_lock_irqsave(&vif->hash.cache.lock, flags);
list_for_each_entry_safe(entry, n, &vif->hash.cache.list, link) {
list_del_rcu(&entry->link);
vif->hash.cache.count--;
kfree_rcu(entry, rcu);
}
spin_unlock_irqrestore(&vif->hash.cache.lock, flags);
}
static u32 xenvif_find_hash(struct xenvif *vif, const u8 *data,
unsigned int len)
{
struct xenvif_hash_cache_entry *entry;
u32 val;
bool found;
if (len >= XEN_NETBK_HASH_TAG_SIZE)
return 0;
if (xenvif_hash_cache_size == 0)
return xenvif_new_hash(vif, data, len);
rcu_read_lock();
found = false;
list_for_each_entry_rcu(entry, &vif->hash.cache.list, link) {
if (entry->len == len &&
memcmp(entry->tag, data, len) == 0) {
val = entry->val;
entry->seq = atomic_inc_return(&vif->hash.cache.seq);
found = true;
break;
}
}
rcu_read_unlock();
if (!found)
val = xenvif_new_hash(vif, data, len);
return val;
}
void xenvif_set_skb_hash(struct xenvif *vif, struct sk_buff *skb)
{
struct flow_keys flow;
u32 hash = 0;
enum pkt_hash_types type = PKT_HASH_TYPE_NONE;
u32 flags = vif->hash.flags;
bool has_tcp_hdr;
/* Quick rejection test: If the network protocol doesn't
* correspond to any enabled hash type then there's no point
* in parsing the packet header.
*/
switch (skb->protocol) {
case htons(ETH_P_IP):
if (flags & (XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP |
XEN_NETIF_CTRL_HASH_TYPE_IPV4))
break;
goto done;
case htons(ETH_P_IPV6):
if (flags & (XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP |
XEN_NETIF_CTRL_HASH_TYPE_IPV6))
break;
goto done;
default:
goto done;
}
memset(&flow, 0, sizeof(flow));
if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
goto done;
has_tcp_hdr = (flow.basic.ip_proto == IPPROTO_TCP) &&
!(flow.control.flags & FLOW_DIS_IS_FRAGMENT);
switch (skb->protocol) {
case htons(ETH_P_IP):
if (has_tcp_hdr &&
(flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP)) {
u8 data[12];
memcpy(&data[0], &flow.addrs.v4addrs.src, 4);
memcpy(&data[4], &flow.addrs.v4addrs.dst, 4);
memcpy(&data[8], &flow.ports.src, 2);
memcpy(&data[10], &flow.ports.dst, 2);
hash = xenvif_find_hash(vif, data, sizeof(data));
type = PKT_HASH_TYPE_L4;
} else if (flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4) {
u8 data[8];
memcpy(&data[0], &flow.addrs.v4addrs.src, 4);
memcpy(&data[4], &flow.addrs.v4addrs.dst, 4);
hash = xenvif_find_hash(vif, data, sizeof(data));
type = PKT_HASH_TYPE_L3;
}
break;
case htons(ETH_P_IPV6):
if (has_tcp_hdr &&
(flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)) {
u8 data[36];
memcpy(&data[0], &flow.addrs.v6addrs.src, 16);
memcpy(&data[16], &flow.addrs.v6addrs.dst, 16);
memcpy(&data[32], &flow.ports.src, 2);
memcpy(&data[34], &flow.ports.dst, 2);
hash = xenvif_find_hash(vif, data, sizeof(data));
type = PKT_HASH_TYPE_L4;
} else if (flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6) {
u8 data[32];
memcpy(&data[0], &flow.addrs.v6addrs.src, 16);
memcpy(&data[16], &flow.addrs.v6addrs.dst, 16);
hash = xenvif_find_hash(vif, data, sizeof(data));
type = PKT_HASH_TYPE_L3;
}
break;
}
done:
if (type == PKT_HASH_TYPE_NONE)
skb_clear_hash(skb);
else
__skb_set_sw_hash(skb, hash, type == PKT_HASH_TYPE_L4);
}
u32 xenvif_set_hash_alg(struct xenvif *vif, u32 alg)
{
switch (alg) {
case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE:
case XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ:
break;
default:
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
}
vif->hash.alg = alg;
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
u32 xenvif_get_hash_flags(struct xenvif *vif, u32 *flags)
{
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
return XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED;
*flags = XEN_NETIF_CTRL_HASH_TYPE_IPV4 |
XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP |
XEN_NETIF_CTRL_HASH_TYPE_IPV6 |
XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP;
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
u32 xenvif_set_hash_flags(struct xenvif *vif, u32 flags)
{
if (flags & ~(XEN_NETIF_CTRL_HASH_TYPE_IPV4 |
XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP |
XEN_NETIF_CTRL_HASH_TYPE_IPV6 |
XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP))
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
vif->hash.flags = flags;
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
u32 xenvif_set_hash_key(struct xenvif *vif, u32 gref, u32 len)
{
u8 *key = vif->hash.key;
struct gnttab_copy copy_op = {
.source.u.ref = gref,
.source.domid = vif->domid,
.dest.u.gmfn = virt_to_gfn(key),
.dest.domid = DOMID_SELF,
.dest.offset = xen_offset_in_page(key),
.len = len,
.flags = GNTCOPY_source_gref
};
if (len > XEN_NETBK_MAX_HASH_KEY_SIZE)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
if (copy_op.len != 0) {
gnttab_batch_copy(&copy_op, 1);
if (copy_op.status != GNTST_okay)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
}
/* Clear any remaining key octets */
if (len < XEN_NETBK_MAX_HASH_KEY_SIZE)
memset(key + len, 0, XEN_NETBK_MAX_HASH_KEY_SIZE - len);
xenvif_flush_hash(vif);
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size)
{
if (size > XEN_NETBK_MAX_HASH_MAPPING_SIZE)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
vif->hash.size = size;
memset(vif->hash.mapping[vif->hash.mapping_sel], 0,
sizeof(u32) * size);
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len,
u32 off)
{
u32 *mapping = vif->hash.mapping[!vif->hash.mapping_sel];
unsigned int nr = 1;
struct gnttab_copy copy_op[2] = {{
.source.u.ref = gref,
.source.domid = vif->domid,
.dest.domid = DOMID_SELF,
.len = len * sizeof(*mapping),
.flags = GNTCOPY_source_gref
}};
if ((off + len < off) || (off + len > vif->hash.size) ||
len > XEN_PAGE_SIZE / sizeof(*mapping))
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
copy_op[0].dest.u.gmfn = virt_to_gfn(mapping + off);
copy_op[0].dest.offset = xen_offset_in_page(mapping + off);
if (copy_op[0].dest.offset + copy_op[0].len > XEN_PAGE_SIZE) {
copy_op[1] = copy_op[0];
copy_op[1].source.offset = XEN_PAGE_SIZE - copy_op[0].dest.offset;
copy_op[1].dest.u.gmfn = virt_to_gfn(mapping + off + len);
copy_op[1].dest.offset = 0;
copy_op[1].len = copy_op[0].len - copy_op[1].source.offset;
copy_op[0].len = copy_op[1].source.offset;
nr = 2;
}
memcpy(mapping, vif->hash.mapping[vif->hash.mapping_sel],
vif->hash.size * sizeof(*mapping));
if (copy_op[0].len != 0) {
gnttab_batch_copy(copy_op, nr);
if (copy_op[0].status != GNTST_okay ||
copy_op[nr - 1].status != GNTST_okay)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
}
while (len-- != 0)
if (mapping[off++] >= vif->num_queues)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
vif->hash.mapping_sel = !vif->hash.mapping_sel;
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
#ifdef CONFIG_DEBUG_FS
void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m)
{
unsigned int i;
switch (vif->hash.alg) {
case XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ:
seq_puts(m, "Hash Algorithm: TOEPLITZ\n");
break;
case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE:
seq_puts(m, "Hash Algorithm: NONE\n");
fallthrough;
default:
return;
}
if (vif->hash.flags) {
seq_puts(m, "\nHash Flags:\n");
if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4)
seq_puts(m, "- IPv4\n");
if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP)
seq_puts(m, "- IPv4 + TCP\n");
if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6)
seq_puts(m, "- IPv6\n");
if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)
seq_puts(m, "- IPv6 + TCP\n");
}
seq_puts(m, "\nHash Key:\n");
for (i = 0; i < XEN_NETBK_MAX_HASH_KEY_SIZE; ) {
unsigned int j, n;
n = 8;
if (i + n >= XEN_NETBK_MAX_HASH_KEY_SIZE)
n = XEN_NETBK_MAX_HASH_KEY_SIZE - i;
seq_printf(m, "[%2u - %2u]: ", i, i + n - 1);
for (j = 0; j < n; j++, i++)
seq_printf(m, "%02x ", vif->hash.key[i]);
seq_puts(m, "\n");
}
if (vif->hash.size != 0) {
const u32 *mapping = vif->hash.mapping[vif->hash.mapping_sel];
seq_puts(m, "\nHash Mapping:\n");
for (i = 0; i < vif->hash.size; ) {
unsigned int j, n;
n = 8;
if (i + n >= vif->hash.size)
n = vif->hash.size - i;
seq_printf(m, "[%4u - %4u]: ", i, i + n - 1);
for (j = 0; j < n; j++, i++)
seq_printf(m, "%4u ", mapping[i]);
seq_puts(m, "\n");
}
}
}
#endif /* CONFIG_DEBUG_FS */
void xenvif_init_hash(struct xenvif *vif)
{
if (xenvif_hash_cache_size == 0)
return;
BUG_ON(vif->hash.cache.count);
spin_lock_init(&vif->hash.cache.lock);
INIT_LIST_HEAD(&vif->hash.cache.list);
}
void xenvif_deinit_hash(struct xenvif *vif)
{
xenvif_flush_hash(vif);
}
linux-7.2.3/drivers/net/xen-netback/interface.c
+857
View File
@@ -0,0 +1,857 @@
/*
* 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 <linux/kthread.h>
#include <linux/sched/task.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <linux/vmalloc.h>
#include <xen/events.h>
#include <asm/xen/hypercall.h>
#include <xen/balloon.h>
/* 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 SKBFL_ZEROCOPY_ENABLE 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)->flags |= SKBFL_ZEROCOPY_ENABLE;
atomic_inc(&queue->inflight_packets);
}
void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
{
atomic_dec(&queue->inflight_packets);
/* Wake the dealloc thread _after_ decrementing inflight_packets so
* that if kthread_stop() has already been called, the dealloc thread
* does not wait forever with nothing to wake it.
*/
wake_up(&queue->dealloc_wq);
}
static int xenvif_schedulable(struct xenvif *vif)
{
return netif_running(vif->dev) &&
test_bit(VIF_STATUS_CONNECTED, &vif->status) &&
!vif->disabled;
}
static bool xenvif_handle_tx_interrupt(struct xenvif_queue *queue)
{
bool rc;
rc = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx);
if (rc)
napi_schedule(&queue->napi);
return rc;
}
static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
{
struct xenvif_queue *queue = dev_id;
int old;
old = atomic_fetch_or(NETBK_TX_EOI, &queue->eoi_pending);
WARN(old & NETBK_TX_EOI, "Interrupt while EOI pending\n");
if (!xenvif_handle_tx_interrupt(queue)) {
atomic_andnot(NETBK_TX_EOI, &queue->eoi_pending);
xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
}
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_done(napi, work_done);
/* If the queue is rate-limited, it shall be
* rescheduled in the timer callback.
*/
if (likely(!queue->rate_limited))
xenvif_napi_schedule_or_enable_events(queue);
}
return work_done;
}
static bool xenvif_handle_rx_interrupt(struct xenvif_queue *queue)
{
bool rc;
rc = xenvif_have_rx_work(queue, false);
if (rc)
xenvif_kick_thread(queue);
return rc;
}
static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
{
struct xenvif_queue *queue = dev_id;
int old;
old = atomic_fetch_or(NETBK_RX_EOI, &queue->eoi_pending);
WARN(old & NETBK_RX_EOI, "Interrupt while EOI pending\n");
if (!xenvif_handle_rx_interrupt(queue)) {
atomic_andnot(NETBK_RX_EOI, &queue->eoi_pending);
xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
}
return IRQ_HANDLED;
}
irqreturn_t xenvif_interrupt(int irq, void *dev_id)
{
struct xenvif_queue *queue = dev_id;
int old;
bool has_rx, has_tx;
old = atomic_fetch_or(NETBK_COMMON_EOI, &queue->eoi_pending);
WARN(old, "Interrupt while EOI pending\n");
has_tx = xenvif_handle_tx_interrupt(queue);
has_rx = xenvif_handle_rx_interrupt(queue);
if (!has_rx && !has_tx) {
atomic_andnot(NETBK_COMMON_EOI, &queue->eoi_pending);
xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
}
return IRQ_HANDLED;
}
static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev)
{
struct xenvif *vif = netdev_priv(dev);
unsigned int size = vif->hash.size;
unsigned int num_queues;
/* If queues are not set up internally - always return 0
* as the packet going to be dropped anyway */
num_queues = READ_ONCE(vif->num_queues);
if (num_queues < 1)
return 0;
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
return netdev_pick_tx(dev, skb, NULL) %
dev->real_num_tx_queues;
xenvif_set_skb_hash(vif, skb);
if (size == 0)
return skb_get_hash_raw(skb) % dev->real_num_tx_queues;
return vif->hash.mapping[vif->hash.mapping_sel]
[skb_get_hash_raw(skb) % size];
}
static netdev_tx_t
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;
u16 index;
struct xenvif_rx_cb *cb;
BUG_ON(skb->dev != dev);
/* Drop the packet if queues are not set up.
* This handler should be called inside an RCU read section
* so we don't need to enter it here explicitly.
*/
num_queues = READ_ONCE(vif->num_queues);
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;
if (vif->multicast_control && skb->pkt_type == PACKET_MULTICAST) {
struct ethhdr *eth = (struct ethhdr *)skb->data;
if (!xenvif_mcast_match(vif, eth->h_dest))
goto drop;
}
cb = XENVIF_RX_CB(skb);
cb->expires = jiffies + vif->drain_timeout;
/* If there is no hash algorithm configured then make sure there
* is no hash information in the socket buffer otherwise it
* would be incorrectly forwarded to the frontend.
*/
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
skb_clear_hash(skb);
/* timestamp packet in software */
skb_tx_timestamp(skb);
if (!xenvif_rx_queue_tail(queue, skb))
goto drop;
xenvif_kick_thread(queue);
return NETDEV_TX_OK;
drop:
vif->dev->stats.tx_dropped++;
dev_kfree_skb_any(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;
u64 rx_bytes = 0;
u64 rx_packets = 0;
u64 tx_bytes = 0;
u64 tx_packets = 0;
unsigned int index;
rcu_read_lock();
num_queues = READ_ONCE(vif->num_queues);
/* 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;
}
rcu_read_unlock();
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);
timer_delete_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 ? ETH_MAX_MTU - VLAN_ETH_HLEN : ETH_DATA_LEN;
if (mtu > max)
return -EINVAL;
WRITE_ONCE(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) & GSO_BIT(TCPV4))
features &= ~NETIF_F_TSO;
if (~(vif->gso_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;
int i;
unsigned int queue_index;
rcu_read_lock();
num_queues = READ_ONCE(vif->num_queues);
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;
}
rcu_read_unlock();
}
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_ts_info = ethtool_op_get_ts_info,
.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_select_queue = xenvif_select_queue,
.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)
{
static const u8 dummy_addr[ETH_ALEN] = {
0xfe, 0xff, 0xff, 0xff, 0xff, 0xff,
};
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;
vif->xdp_headroom = 0;
spin_lock_init(&vif->lock);
INIT_LIST_HEAD(&vif->fe_mcast_addr);
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 | NETIF_F_FRAGLIST;
dev->features = dev->hw_features | NETIF_F_RXCSUM;
dev->ethtool_ops = &xenvif_ethtool_ops;
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = ETH_MAX_MTU - VLAN_ETH_HLEN;
/*
* 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_hw_addr_set(dev, dummy_addr);
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;
timer_setup(&queue->credit_timeout, xenvif_tx_credit_callback, 0);
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_msgzc)
{ { .ops = &xenvif_ubuf_ops },
{ { .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_ctrl(struct xenvif *vif, grant_ref_t ring_ref,
unsigned int evtchn)
{
struct net_device *dev = vif->dev;
struct xenbus_device *xendev = xenvif_to_xenbus_device(vif);
void *addr;
struct xen_netif_ctrl_sring *shared;
RING_IDX rsp_prod, req_prod;
int err;
err = xenbus_map_ring_valloc(xendev, &ring_ref, 1, &addr);
if (err)
goto err;
shared = (struct xen_netif_ctrl_sring *)addr;
rsp_prod = READ_ONCE(shared->rsp_prod);
req_prod = READ_ONCE(shared->req_prod);
BACK_RING_ATTACH(&vif->ctrl, shared, rsp_prod, XEN_PAGE_SIZE);
err = -EIO;
if (req_prod - rsp_prod > RING_SIZE(&vif->ctrl))
goto err_unmap;
err = bind_interdomain_evtchn_to_irq_lateeoi(xendev, evtchn);
if (err < 0)
goto err_unmap;
vif->ctrl_irq = err;
xenvif_init_hash(vif);
err = request_threaded_irq(vif->ctrl_irq, NULL, xenvif_ctrl_irq_fn,
IRQF_ONESHOT, "xen-netback-ctrl", vif);
if (err) {
pr_warn("Could not setup irq handler for %s\n", dev->name);
goto err_deinit;
}
return 0;
err_deinit:
xenvif_deinit_hash(vif);
unbind_from_irqhandler(vif->ctrl_irq, vif);
vif->ctrl_irq = 0;
err_unmap:
xenbus_unmap_ring_vfree(xendev, vif->ctrl.sring);
vif->ctrl.sring = NULL;
err:
return err;
}
static void xenvif_disconnect_queue(struct xenvif_queue *queue)
{
if (queue->task) {
kthread_stop_put(queue->task);
queue->task = NULL;
}
if (queue->dealloc_task) {
kthread_stop(queue->dealloc_task);
queue->dealloc_task = NULL;
}
if (queue->napi.poll) {
netif_napi_del(&queue->napi);
queue->napi.poll = NULL;
}
if (queue->tx_irq) {
unbind_from_irqhandler(queue->tx_irq, queue);
if (queue->tx_irq == queue->rx_irq)
queue->rx_irq = 0;
queue->tx_irq = 0;
}
if (queue->rx_irq) {
unbind_from_irqhandler(queue->rx_irq, queue);
queue->rx_irq = 0;
}
xenvif_unmap_frontend_data_rings(queue);
}
int xenvif_connect_data(struct xenvif_queue *queue,
unsigned long tx_ring_ref,
unsigned long rx_ring_ref,
unsigned int tx_evtchn,
unsigned int rx_evtchn)
{
struct xenbus_device *dev = xenvif_to_xenbus_device(queue->vif);
struct task_struct *task;
int err;
BUG_ON(queue->tx_irq);
BUG_ON(queue->task);
BUG_ON(queue->dealloc_task);
err = xenvif_map_frontend_data_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);
queue->stalled = true;
task = kthread_run(xenvif_kthread_guest_rx, queue,
"%s-guest-rx", queue->name);
if (IS_ERR(task))
goto kthread_err;
queue->task = task;
/*
* Take a reference to the task in order to prevent it from being freed
* if the thread function returns before kthread_stop is called.
*/
get_task_struct(task);
task = kthread_run(xenvif_dealloc_kthread, queue,
"%s-dealloc", queue->name);
if (IS_ERR(task))
goto kthread_err;
queue->dealloc_task = task;
if (tx_evtchn == rx_evtchn) {
/* feature-split-event-channels == 0 */
err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
dev, tx_evtchn, xenvif_interrupt, 0,
queue->name, queue);
if (err < 0)
goto err;
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_lateeoi(
dev, tx_evtchn, xenvif_tx_interrupt, 0,
queue->tx_irq_name, queue);
if (err < 0)
goto err;
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_lateeoi(
dev, rx_evtchn, xenvif_rx_interrupt, 0,
queue->rx_irq_name, queue);
if (err < 0)
goto err;
queue->rx_irq = err;
disable_irq(queue->rx_irq);
}
return 0;
kthread_err:
pr_warn("Could not allocate kthread for %s\n", queue->name);
err = PTR_ERR(task);
err:
xenvif_disconnect_queue(queue);
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_data(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];
xenvif_disconnect_queue(queue);
}
xenvif_mcast_addr_list_free(vif);
}
void xenvif_disconnect_ctrl(struct xenvif *vif)
{
if (vif->ctrl_irq) {
xenvif_deinit_hash(vif);
unbind_from_irqhandler(vif->ctrl_irq, vif);
vif->ctrl_irq = 0;
}
if (vif->ctrl.sring) {
xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
vif->ctrl.sring);
vif->ctrl.sring = NULL;
}
}
/* 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 *queues = vif->queues;
unsigned int num_queues = vif->num_queues;
unsigned int queue_index;
unregister_netdev(vif->dev);
free_netdev(vif->dev);
for (queue_index = 0; queue_index < num_queues; ++queue_index)
xenvif_deinit_queue(&queues[queue_index]);
vfree(queues);
module_put(THIS_MODULE);
}
linux-7.2.3/drivers/net/xen-netback/netback.c
+1790
View File
File diff suppressed because it is too large Load Diff
linux-7.2.3/drivers/net/xen-netback/rx.c
+680
View File
@@ -0,0 +1,680 @@
/*
* Copyright (c) 2016 Citrix Systems Inc.
* 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 <linux/kthread.h>
#include <xen/xen.h>
#include <xen/events.h>
/*
* Update the needed ring page slots for the first SKB queued.
* Note that any call sequence outside the RX thread calling this function
* needs to wake up the RX thread via a call of xenvif_kick_thread()
* afterwards in order to avoid a race with putting the thread to sleep.
*/
static void xenvif_update_needed_slots(struct xenvif_queue *queue,
const struct sk_buff *skb)
{
unsigned int needed = 0;
if (skb) {
needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE);
if (skb_is_gso(skb))
needed++;
if (skb->sw_hash)
needed++;
}
WRITE_ONCE(queue->rx_slots_needed, needed);
}
static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue)
{
RING_IDX prod, cons;
unsigned int needed;
needed = READ_ONCE(queue->rx_slots_needed);
if (!needed)
return false;
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;
}
bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb)
{
unsigned long flags;
bool ret = true;
spin_lock_irqsave(&queue->rx_queue.lock, flags);
if (queue->rx_queue_len >= queue->rx_queue_max) {
struct net_device *dev = queue->vif->dev;
netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
ret = false;
} else {
if (skb_queue_empty(&queue->rx_queue))
xenvif_update_needed_slots(queue, skb);
__skb_queue_tail(&queue->rx_queue, skb);
queue->rx_queue_len += skb->len;
}
spin_unlock_irqrestore(&queue->rx_queue.lock, flags);
return ret;
}
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) {
xenvif_update_needed_slots(queue, skb_peek(&queue->rx_queue));
queue->rx_queue_len -= skb->len;
if (queue->rx_queue_len < queue->rx_queue_max) {
struct netdev_queue *txq;
txq = netdev_get_tx_queue(queue->vif->dev, queue->id);
netif_tx_wake_queue(txq);
}
}
spin_unlock_irq(&queue->rx_queue.lock);
return skb;
}
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);
queue->vif->dev->stats.rx_dropped++;
}
}
static void xenvif_rx_copy_flush(struct xenvif_queue *queue)
{
unsigned int i;
int notify;
gnttab_batch_copy(queue->rx_copy.op, queue->rx_copy.num);
for (i = 0; i < queue->rx_copy.num; i++) {
struct gnttab_copy *op;
op = &queue->rx_copy.op[i];
/* If the copy failed, overwrite the status field in
* the corresponding response.
*/
if (unlikely(op->status != GNTST_okay)) {
struct xen_netif_rx_response *rsp;
rsp = RING_GET_RESPONSE(&queue->rx,
queue->rx_copy.idx[i]);
rsp->status = op->status;
}
}
queue->rx_copy.num = 0;
/* Push responses for all completed packets. */
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, notify);
if (notify)
notify_remote_via_irq(queue->rx_irq);
__skb_queue_purge(queue->rx_copy.completed);
}
static void xenvif_rx_copy_add(struct xenvif_queue *queue,
struct xen_netif_rx_request *req,
unsigned int offset, void *data, size_t len)
{
struct gnttab_copy *op;
struct page *page;
struct xen_page_foreign *foreign;
if (queue->rx_copy.num == COPY_BATCH_SIZE)
xenvif_rx_copy_flush(queue);
op = &queue->rx_copy.op[queue->rx_copy.num];
page = virt_to_page(data);
op->flags = GNTCOPY_dest_gref;
foreign = xen_page_foreign(page);
if (foreign) {
op->source.domid = foreign->domid;
op->source.u.ref = foreign->gref;
op->flags |= GNTCOPY_source_gref;
} else {
op->source.u.gmfn = virt_to_gfn(data);
op->source.domid = DOMID_SELF;
}
op->source.offset = xen_offset_in_page(data);
op->dest.u.ref = req->gref;
op->dest.domid = queue->vif->domid;
op->dest.offset = offset;
op->len = len;
queue->rx_copy.idx[queue->rx_copy.num] = queue->rx.req_cons;
queue->rx_copy.num++;
}
static unsigned int xenvif_gso_type(struct sk_buff *skb)
{
if (skb_is_gso(skb)) {
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
return XEN_NETIF_GSO_TYPE_TCPV4;
else
return XEN_NETIF_GSO_TYPE_TCPV6;
}
return XEN_NETIF_GSO_TYPE_NONE;
}
struct xenvif_pkt_state {
struct sk_buff *skb;
size_t remaining_len;
struct sk_buff *frag_iter;
int frag; /* frag == -1 => frag_iter->head */
unsigned int frag_offset;
struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
unsigned int extra_count;
unsigned int slot;
};
static void xenvif_rx_next_skb(struct xenvif_queue *queue,
struct xenvif_pkt_state *pkt)
{
struct sk_buff *skb;
unsigned int gso_type;
skb = xenvif_rx_dequeue(queue);
queue->stats.tx_bytes += skb->len;
queue->stats.tx_packets++;
/* Reset packet state. */
memset(pkt, 0, sizeof(struct xenvif_pkt_state));
pkt->skb = skb;
pkt->frag_iter = skb;
pkt->remaining_len = skb->len;
pkt->frag = -1;
gso_type = xenvif_gso_type(skb);
if ((1 << gso_type) & queue->vif->gso_mask) {
struct xen_netif_extra_info *extra;
extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
extra->u.gso.type = gso_type;
extra->u.gso.size = skb_shinfo(skb)->gso_size;
extra->u.gso.pad = 0;
extra->u.gso.features = 0;
extra->type = XEN_NETIF_EXTRA_TYPE_GSO;
extra->flags = 0;
pkt->extra_count++;
}
if (queue->vif->xdp_headroom) {
struct xen_netif_extra_info *extra;
extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_XDP - 1];
memset(extra, 0, sizeof(struct xen_netif_extra_info));
extra->u.xdp.headroom = queue->vif->xdp_headroom;
extra->type = XEN_NETIF_EXTRA_TYPE_XDP;
extra->flags = 0;
pkt->extra_count++;
}
if (skb->sw_hash) {
struct xen_netif_extra_info *extra;
extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_HASH - 1];
extra->u.hash.algorithm =
XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ;
if (skb->l4_hash)
extra->u.hash.type =
skb->protocol == htons(ETH_P_IP) ?
_XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP :
_XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP;
else
extra->u.hash.type =
skb->protocol == htons(ETH_P_IP) ?
_XEN_NETIF_CTRL_HASH_TYPE_IPV4 :
_XEN_NETIF_CTRL_HASH_TYPE_IPV6;
*(uint32_t *)extra->u.hash.value = skb_get_hash_raw(skb);
extra->type = XEN_NETIF_EXTRA_TYPE_HASH;
extra->flags = 0;
pkt->extra_count++;
}
}
static void xenvif_rx_complete(struct xenvif_queue *queue,
struct xenvif_pkt_state *pkt)
{
/* All responses are ready to be pushed. */
queue->rx.rsp_prod_pvt = queue->rx.req_cons;
__skb_queue_tail(queue->rx_copy.completed, pkt->skb);
}
static void xenvif_rx_next_frag(struct xenvif_pkt_state *pkt)
{
struct sk_buff *frag_iter = pkt->frag_iter;
unsigned int nr_frags = skb_shinfo(frag_iter)->nr_frags;
pkt->frag++;
pkt->frag_offset = 0;
if (pkt->frag >= nr_frags) {
if (frag_iter == pkt->skb)
pkt->frag_iter = skb_shinfo(frag_iter)->frag_list;
else
pkt->frag_iter = frag_iter->next;
pkt->frag = -1;
}
}
static void xenvif_rx_next_chunk(struct xenvif_queue *queue,
struct xenvif_pkt_state *pkt,
unsigned int offset, void **data,
size_t *len)
{
struct sk_buff *frag_iter = pkt->frag_iter;
void *frag_data;
size_t frag_len, chunk_len;
BUG_ON(!frag_iter);
if (pkt->frag == -1) {
frag_data = frag_iter->data;
frag_len = skb_headlen(frag_iter);
} else {
skb_frag_t *frag = &skb_shinfo(frag_iter)->frags[pkt->frag];
frag_data = skb_frag_address(frag);
frag_len = skb_frag_size(frag);
}
frag_data += pkt->frag_offset;
frag_len -= pkt->frag_offset;
chunk_len = min_t(size_t, frag_len, XEN_PAGE_SIZE - offset);
chunk_len = min_t(size_t, chunk_len, XEN_PAGE_SIZE -
xen_offset_in_page(frag_data));
pkt->frag_offset += chunk_len;
/* Advance to next frag? */
if (frag_len == chunk_len)
xenvif_rx_next_frag(pkt);
*data = frag_data;
*len = chunk_len;
}
static void xenvif_rx_data_slot(struct xenvif_queue *queue,
struct xenvif_pkt_state *pkt,
struct xen_netif_rx_request *req,
struct xen_netif_rx_response *rsp)
{
unsigned int offset = queue->vif->xdp_headroom;
unsigned int flags;
do {
size_t len;
void *data;
xenvif_rx_next_chunk(queue, pkt, offset, &data, &len);
xenvif_rx_copy_add(queue, req, offset, data, len);
offset += len;
pkt->remaining_len -= len;
} while (offset < XEN_PAGE_SIZE && pkt->remaining_len > 0);
if (pkt->remaining_len > 0)
flags = XEN_NETRXF_more_data;
else
flags = 0;
if (pkt->slot == 0) {
struct sk_buff *skb = pkt->skb;
if (skb->ip_summed == CHECKSUM_PARTIAL)
flags |= XEN_NETRXF_csum_blank |
XEN_NETRXF_data_validated;
else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
flags |= XEN_NETRXF_data_validated;
if (pkt->extra_count != 0)
flags |= XEN_NETRXF_extra_info;
}
rsp->offset = 0;
rsp->flags = flags;
rsp->id = req->id;
rsp->status = (s16)offset;
}
static void xenvif_rx_extra_slot(struct xenvif_queue *queue,
struct xenvif_pkt_state *pkt,
struct xen_netif_rx_request *req,
struct xen_netif_rx_response *rsp)
{
struct xen_netif_extra_info *extra = (void *)rsp;
unsigned int i;
pkt->extra_count--;
for (i = 0; i < ARRAY_SIZE(pkt->extras); i++) {
if (pkt->extras[i].type) {
*extra = pkt->extras[i];
if (pkt->extra_count != 0)
extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE;
pkt->extras[i].type = 0;
return;
}
}
BUG();
}
static void xenvif_rx_skb(struct xenvif_queue *queue)
{
struct xenvif_pkt_state pkt;
xenvif_rx_next_skb(queue, &pkt);
queue->last_rx_time = jiffies;
do {
struct xen_netif_rx_request *req;
struct xen_netif_rx_response *rsp;
req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons);
rsp = RING_GET_RESPONSE(&queue->rx, queue->rx.req_cons);
/* Extras must go after the first data slot */
if (pkt.slot != 0 && pkt.extra_count != 0)
xenvif_rx_extra_slot(queue, &pkt, req, rsp);
else
xenvif_rx_data_slot(queue, &pkt, req, rsp);
queue->rx.req_cons++;
pkt.slot++;
} while (pkt.remaining_len > 0 || pkt.extra_count != 0);
xenvif_rx_complete(queue, &pkt);
}
#define RX_BATCH_SIZE 64
static void xenvif_rx_action(struct xenvif_queue *queue)
{
struct sk_buff_head completed_skbs;
unsigned int work_done = 0;
__skb_queue_head_init(&completed_skbs);
queue->rx_copy.completed = &completed_skbs;
while (xenvif_rx_ring_slots_available(queue) &&
!skb_queue_empty(&queue->rx_queue) &&
work_done < RX_BATCH_SIZE) {
xenvif_rx_skb(queue);
work_done++;
}
/* Flush any pending copies and complete all skbs. */
xenvif_rx_copy_flush(queue);
}
static RING_IDX xenvif_rx_queue_slots(const struct xenvif_queue *queue)
{
RING_IDX prod, cons;
prod = queue->rx.sring->req_prod;
cons = queue->rx.req_cons;
return prod - cons;
}
static bool xenvif_rx_queue_stalled(const struct xenvif_queue *queue)
{
unsigned int needed = READ_ONCE(queue->rx_slots_needed);
return !queue->stalled &&
xenvif_rx_queue_slots(queue) < needed &&
time_after(jiffies,
queue->last_rx_time + queue->vif->stall_timeout);
}
static bool xenvif_rx_queue_ready(struct xenvif_queue *queue)
{
unsigned int needed = READ_ONCE(queue->rx_slots_needed);
return queue->stalled && xenvif_rx_queue_slots(queue) >= needed;
}
bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread)
{
return xenvif_rx_ring_slots_available(queue) ||
(queue->vif->stall_timeout &&
(xenvif_rx_queue_stalled(queue) ||
xenvif_rx_queue_ready(queue))) ||
(test_kthread && 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, true))
return;
for (;;) {
long ret;
prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE);
if (xenvif_have_rx_work(queue, true))
break;
if (atomic_fetch_andnot(NETBK_RX_EOI | NETBK_COMMON_EOI,
&queue->eoi_pending) &
(NETBK_RX_EOI | NETBK_COMMON_EOI))
xen_irq_lateeoi(queue->rx_irq, 0);
ret = schedule_timeout(xenvif_rx_queue_timeout(queue));
if (!ret)
break;
}
finish_wait(&queue->wq, &wait);
}
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);
}
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);
cond_resched();
}
/* Bin any remaining skbs */
xenvif_rx_queue_purge(queue);
return 0;
}
linux-7.2.3/drivers/net/xen-netback/xenbus.c
+1180
View File
File diff suppressed because it is too large Load Diff