/* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. * * (C) Copyright 2020 Hewlett Packard Enterprise Development LP * Copyright (C) 1999-2009 Silicon Graphics, Inc. All rights reserved.
*/
/* * Cross Partition Network Interface (XPNET) support * * XPNET provides a virtual network layered on top of the Cross * Partition communication layer. * * XPNET provides direct point-to-point and broadcast-like support * for an ethernet-like device. The ethernet broadcast medium is * replaced with a point-to-point message structure which passes * pointers to a DMA-capable block that a remote partition should * retrieve and pass to the upper level networking layer. *
*/
/* * The message payload transferred by XPC. * * buf_pa is the physical address where the DMA should pull from. * * NOTE: for performance reasons, buf_pa should _ALWAYS_ begin on a * cacheline boundary. To accomplish this, we record the number of * bytes from the beginning of the first cacheline to the first useful * byte of the skb (leadin_ignore) and the number of bytes from the * last useful byte of the skb to the end of the last cacheline * (tailout_ignore). * * size is the number of bytes to transfer which includes the skb->len * (useful bytes of the senders skb) plus the leadin and tailout
*/ struct xpnet_message {
u16 version; /* Version for this message */
u16 embedded_bytes; /* #of bytes embedded in XPC message */
u32 magic; /* Special number indicating this is xpnet */ unsignedlong buf_pa; /* phys address of buffer to retrieve */
u32 size; /* #of bytes in buffer */
u8 leadin_ignore; /* #of bytes to ignore at the beginning */
u8 tailout_ignore; /* #of bytes to ignore at the end */ unsignedchar data; /* body of small packets */
};
/* * Determine the size of our message, the cacheline aligned size, * and then the number of message will request from XPC. * * XPC expects each message to exist in an individual cacheline.
*/ #define XPNET_MSG_SIZE XPC_MSG_PAYLOAD_MAX_SIZE #define XPNET_MSG_DATA_MAX \
(XPNET_MSG_SIZE - offsetof(struct xpnet_message, data)) #define XPNET_MSG_NENTRIES (PAGE_SIZE / XPC_MSG_MAX_SIZE)
/* * Version number of XPNET implementation. XPNET can always talk to versions * with same major #, and never talk to versions with a different version.
*/ #define _XPNET_VERSION(_major, _minor) (((_major) << 4) | (_minor)) #define XPNET_VERSION_MAJOR(_v) ((_v) >> 4) #define XPNET_VERSION_MINOR(_v) ((_v) & 0xf)
/* * When messages are queued with xpc_send_notify, a kmalloc'd buffer * of the following type is passed as a notification cookie. When the * notification function is called, we use the cookie to decide * whether all outstanding message sends have completed. The skb can * then be released.
*/ struct xpnet_pending_msg { struct sk_buff *skb;
atomic_t use_count;
};
staticstruct net_device *xpnet_device;
/* * When we are notified of other partitions activating, we add them to * our bitmask of partitions to which we broadcast.
*/ staticunsignedlong *xpnet_broadcast_partitions; /* protect above */ static DEFINE_SPINLOCK(xpnet_broadcast_lock);
/* * Since the Block Transfer Engine (BTE) is being used for the transfer * and it relies upon cache-line size transfers, we need to reserve at * least one cache-line for head and tail alignment. The BTE is * limited to 8MB transfers. * * Testing has shown that changing MTU to greater than 64KB has no effect * on TCP as the two sides negotiate a Max Segment Size that is limited * to 64K. Other protocols May use packets greater than this, but for * now, the default is 64KB.
*/ #define XPNET_MAX_MTU (0x800000UL - L1_CACHE_BYTES) /* 68 comes from min TCP+IP+MAC header */ #define XPNET_MIN_MTU 68 /* 32KB has been determined to be the ideal */ #define XPNET_DEF_MTU (0x8000UL)
/* * The partid is encapsulated in the MAC address beginning in the following * octet and it consists of two octets.
*/ #define XPNET_PARTID_OCTET 2
/* Define the XPNET debug device structures to be used with dev_dbg() et al */
/* reserve an extra cache line */
skb = dev_alloc_skb(msg->size + L1_CACHE_BYTES); if (!skb) {
dev_err(xpnet, "failed on dev_alloc_skb(%d)\n",
msg->size + L1_CACHE_BYTES);
xpc_received(partid, channel, (void *)msg);
xpnet_device->stats.rx_errors++;
return;
}
/* * The allocated skb has some reserved space. * In order to use xp_remote_memcpy(), we need to get the * skb->data pointer moved forward.
*/
skb_reserve(skb, (L1_CACHE_BYTES - ((u64)skb->data &
(L1_CACHE_BYTES - 1)) +
msg->leadin_ignore));
/* * Update the tail pointer to indicate data actually * transferred.
*/
skb_put(skb, (msg->size - msg->leadin_ignore - msg->tailout_ignore));
/* * Move the data over from the other side.
*/ if ((XPNET_VERSION_MINOR(msg->version) == 1) &&
(msg->embedded_bytes != 0)) {
dev_dbg(xpnet, "copying embedded message. memcpy(0x%p, 0x%p, " "%lu)\n", skb->data, &msg->data,
(size_t)msg->embedded_bytes);
/* * This is the handler which XPC calls during any sort of change in * state or message reception on a connection.
*/ staticvoid
xpnet_connection_activity(enum xp_retval reason, short partid, int channel, void *data, void *key)
{
DBUG_ON(partid < 0 || partid >= xp_max_npartitions);
DBUG_ON(channel != XPC_NET_CHANNEL);
switch (reason) { case xpMsgReceived: /* message received */
DBUG_ON(data == NULL);
case xpConnected: /* connection completed to a partition */
spin_lock_bh(&xpnet_broadcast_lock);
__set_bit(partid, xpnet_broadcast_partitions);
spin_unlock_bh(&xpnet_broadcast_lock);
netif_carrier_on(xpnet_device);
dev_dbg(xpnet, "%s connected to partition %d\n",
xpnet_device->name, partid); break;
dev_dbg(xpnet, "ifconfig down of %s; XPC disconnected\n", dev->name);
return 0;
}
/* * Notification that the other end has received the message and * DMA'd the skb information. At this point, they are done with * our side. When all recipients are done processing, we * release the skb and then release our pending message structure.
*/ staticvoid
xpnet_send_completed(enum xp_retval reason, short partid, int channel, void *__qm)
{ struct xpnet_pending_msg *queued_msg = (struct xpnet_pending_msg *)__qm;
DBUG_ON(queued_msg == NULL);
dev_dbg(xpnet, "message to %d notified with reason %d\n",
partid, reason);
if (atomic_dec_return(&queued_msg->use_count) == 0) {
dev_dbg(xpnet, "all acks for skb->head=-x%p\n",
(void *)queued_msg->skb->head);
ret = xpc_send_notify(dest_partid, XPC_NET_CHANNEL, XPC_NOWAIT, msg,
msg_size, xpnet_send_completed, queued_msg); if (unlikely(ret != xpSuccess))
atomic_dec(&queued_msg->use_count);
}
/* * Network layer has formatted a packet (skb) and is ready to place it * "on the wire". Prepare and send an xpnet_message to all partitions * which have connected with us and are targets of this packet. * * MAC-NOTE: For the XPNET driver, the MAC address contains the * destination partid. If the destination partid octets are 0xffff, * this packet is to be broadcast to all connected partitions.
*/ static netdev_tx_t
xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{ struct xpnet_pending_msg *queued_msg;
u64 start_addr, end_addr; short dest_partid;
u16 embedded_bytes = 0;
if (skb->data[0] == 0x33) {
dev_kfree_skb(skb); return NETDEV_TX_OK; /* nothing needed to be done */
}
/* * The xpnet_pending_msg tracks how many outstanding * xpc_send_notifies are relying on this skb. When none * remain, release the skb.
*/
queued_msg = kmalloc(sizeof(struct xpnet_pending_msg), GFP_ATOMIC); if (queued_msg == NULL) {
dev_warn(xpnet, "failed to kmalloc %ld bytes; dropping " "packet\n", sizeof(struct xpnet_pending_msg));
/* get the beginning of the first cacheline and end of last */
start_addr = ((u64)skb->data & ~(L1_CACHE_BYTES - 1));
end_addr = L1_CACHE_ALIGN((u64)skb_tail_pointer(skb));
/* calculate how many bytes to embed in the XPC message */ if (unlikely(skb->len <= XPNET_MSG_DATA_MAX)) { /* skb->data does fit so embed */
embedded_bytes = skb->len;
}
/* * Since the send occurs asynchronously, we set the count to one * and begin sending. Any sends that happen to complete before * we are done sending will not free the skb. We will be left * with that task during exit. This also handles the case of * a packet destined for a partition which is no longer up.
*/
atomic_set(&queued_msg->use_count, 1);
queued_msg->skb = skb;
if (skb->data[0] == 0xff) { /* we are being asked to broadcast to all partitions */
for_each_set_bit(dest_partid, xpnet_broadcast_partitions,
xp_max_npartitions) {
xpnet_broadcast_partitions = bitmap_zalloc(xp_max_npartitions,
GFP_KERNEL); if (xpnet_broadcast_partitions == NULL) return -ENOMEM;
/* * use ether_setup() to init the majority of our device * structure and then override the necessary pieces.
*/
xpnet_device = alloc_netdev(0, XPNET_DEVICE_NAME, NET_NAME_UNKNOWN,
ether_setup); if (xpnet_device == NULL) {
bitmap_free(xpnet_broadcast_partitions); return -ENOMEM;
}
memset(addr, 0, sizeof(addr)); /* * Multicast assumes the LSB of the first octet is set for multicast * MAC addresses. We chose the first octet of the MAC to be unlikely * to collide with any vendor's officially issued MAC.
*/
addr[0] = 0x02; /* locally administered, no OUI */
/* * ether_setup() sets this to a multicast device. We are * really not supporting multicast at this time.
*/
xpnet_device->flags &= ~IFF_MULTICAST;
/* * No need to checksum as it is a DMA transfer. The BTE will * report an error if the data is not retrievable and the * packet will be dropped.
*/
xpnet_device->features = NETIF_F_HW_CSUM;
result = register_netdev(xpnet_device); if (result != 0) {
free_netdev(xpnet_device);
bitmap_free(xpnet_broadcast_partitions);
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.