OpenCloudOS-Kernel/drivers/net/ethernet/ibm/ibmveth.h

223 lines
6.8 KiB
C
Raw Normal View History

/*
* IBM Power Virtual Ethernet Device Driver
*
* 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 <http://www.gnu.org/licenses/>.
*
* Copyright (C) IBM Corporation, 2003, 2010
*
* Authors: Dave Larson <larson1@us.ibm.com>
* Santiago Leon <santil@linux.vnet.ibm.com>
* Brian King <brking@linux.vnet.ibm.com>
* Robert Jennings <rcj@linux.vnet.ibm.com>
* Anton Blanchard <anton@au.ibm.com>
*/
#ifndef _IBMVETH_H
#define _IBMVETH_H
/* constants for H_MULTICAST_CTRL */
#define IbmVethMcastReceptionModifyBit 0x80000UL
#define IbmVethMcastReceptionEnableBit 0x20000UL
#define IbmVethMcastFilterModifyBit 0x40000UL
#define IbmVethMcastFilterEnableBit 0x10000UL
#define IbmVethMcastEnableRecv (IbmVethMcastReceptionModifyBit | IbmVethMcastReceptionEnableBit)
#define IbmVethMcastDisableRecv (IbmVethMcastReceptionModifyBit)
#define IbmVethMcastEnableFiltering (IbmVethMcastFilterModifyBit | IbmVethMcastFilterEnableBit)
#define IbmVethMcastDisableFiltering (IbmVethMcastFilterModifyBit)
#define IbmVethMcastAddFilter 0x1UL
#define IbmVethMcastRemoveFilter 0x2UL
#define IbmVethMcastClearFilterTable 0x3UL
#define IBMVETH_ILLAN_LRG_SR_ENABLED 0x0000000000010000UL
#define IBMVETH_ILLAN_LRG_SND_SUPPORT 0x0000000000008000UL
#define IBMVETH_ILLAN_PADDED_PKT_CSUM 0x0000000000002000UL
#define IBMVETH_ILLAN_TRUNK_PRI_MASK 0x0000000000000F00UL
#define IBMVETH_ILLAN_IPV6_TCP_CSUM 0x0000000000000004UL
#define IBMVETH_ILLAN_IPV4_TCP_CSUM 0x0000000000000002UL
#define IBMVETH_ILLAN_ACTIVE_TRUNK 0x0000000000000001UL
/* hcall macros */
#define h_register_logical_lan(ua, buflst, rxq, fltlst, mac) \
plpar_hcall_norets(H_REGISTER_LOGICAL_LAN, ua, buflst, rxq, fltlst, mac)
#define h_free_logical_lan(ua) \
plpar_hcall_norets(H_FREE_LOGICAL_LAN, ua)
#define h_add_logical_lan_buffer(ua, buf) \
plpar_hcall_norets(H_ADD_LOGICAL_LAN_BUFFER, ua, buf)
static inline long h_send_logical_lan(unsigned long unit_address,
unsigned long desc1, unsigned long desc2, unsigned long desc3,
unsigned long desc4, unsigned long desc5, unsigned long desc6,
unsigned long corellator_in, unsigned long *corellator_out,
unsigned long mss, unsigned long large_send_support)
{
long rc;
unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
if (large_send_support)
rc = plpar_hcall9(H_SEND_LOGICAL_LAN, retbuf, unit_address,
desc1, desc2, desc3, desc4, desc5, desc6,
corellator_in, mss);
else
rc = plpar_hcall9(H_SEND_LOGICAL_LAN, retbuf, unit_address,
desc1, desc2, desc3, desc4, desc5, desc6,
corellator_in);
*corellator_out = retbuf[0];
return rc;
}
static inline long h_illan_attributes(unsigned long unit_address,
unsigned long reset_mask, unsigned long set_mask,
unsigned long *ret_attributes)
{
long rc;
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
rc = plpar_hcall(H_ILLAN_ATTRIBUTES, retbuf, unit_address,
reset_mask, set_mask);
*ret_attributes = retbuf[0];
return rc;
}
#define h_multicast_ctrl(ua, cmd, mac) \
plpar_hcall_norets(H_MULTICAST_CTRL, ua, cmd, mac)
#define h_change_logical_lan_mac(ua, mac) \
plpar_hcall_norets(H_CHANGE_LOGICAL_LAN_MAC, ua, mac)
#define IBMVETH_NUM_BUFF_POOLS 5
#define IBMVETH_IO_ENTITLEMENT_DEFAULT 4243456 /* MTU of 1500 needs 4.2Mb */
#define IBMVETH_BUFF_OH 22 /* Overhead: 14 ethernet header + 8 opaque handle */
#define IBMVETH_MIN_MTU 68
#define IBMVETH_MAX_POOL_COUNT 4096
#define IBMVETH_BUFF_LIST_SIZE 4096
#define IBMVETH_FILT_LIST_SIZE 4096
#define IBMVETH_MAX_BUF_SIZE (1024 * 128)
static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
static int pool_count[] = { 256, 512, 256, 256, 256 };
static int pool_count_cmo[] = { 256, 512, 256, 256, 64 };
static int pool_active[] = { 1, 1, 0, 0, 1};
#define IBM_VETH_INVALID_MAP ((u16)0xffff)
struct ibmveth_buff_pool {
u32 size;
u32 index;
u32 buff_size;
u32 threshold;
atomic_t available;
u32 consumer_index;
u32 producer_index;
u16 *free_map;
dma_addr_t *dma_addr;
struct sk_buff **skbuff;
int active;
struct kobject kobj;
};
struct ibmveth_rx_q {
u64 index;
u64 num_slots;
u64 toggle;
dma_addr_t queue_dma;
u32 queue_len;
struct ibmveth_rx_q_entry *queue_addr;
};
struct ibmveth_adapter {
struct vio_dev *vdev;
struct net_device *netdev;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
struct napi_struct napi;
unsigned int mcastFilterSize;
void * buffer_list_addr;
void * filter_list_addr;
dma_addr_t buffer_list_dma;
dma_addr_t filter_list_dma;
struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
struct ibmveth_rx_q rx_queue;
int pool_config;
int rx_csum;
int large_send;
ibmveth: Support to enable LSO/CSO for Trunk VEA. Current largesend and checksum offload feature in ibmveth driver, - Source VM sends the TCP packets with ip_summed field set as CHECKSUM_PARTIAL and TCP pseudo header checksum is placed in checksum field - CHECKSUM_PARTIAL flag in SKB will enable ibmveth driver to mark "no checksum" and "checksum good" bits in transmit buffer descriptor before the packet is delivered to pseries PowerVM Hypervisor - If ibmveth has largesend capability enabled, transmit buffer descriptors are market accordingly before packet is delivered to Hypervisor (along with mss value for packets with length > MSS) - Destination VM's ibmveth driver receives the packet with "checksum good" bit set and so, SKB's ip_summed field is set with CHECKSUM_UNNECESSARY - If "largesend" bit was on, mss value is copied from receive descriptor into SKB's gso_size and other flags are appropriately set for packets > MSS size - The packet is now successfully delivered up the stack in destination VM The offloads described above works fine for TCP communication among VMs in the same pseries server ( VM A <=> PowerVM Hypervisor <=> VM B ) We are now enabling support for OVS in pseries PowerVM environment. One of our requirements is to have ibmveth driver configured in "Trunk" mode, when they are used with OVS. This is because, PowerVM Hypervisor will no more bridge the packets between VMs, instead the packets are delivered to IO Server which hosts OVS to bridge them between VMs or to external networks (flow shown below), VM A <=> PowerVM Hypervisor <=> IO Server(OVS) <=> PowerVM Hypervisor <=> VM B In "IO server" the packet is received by inbound Trunk ibmveth and then delivered to OVS, which is then bridged to outbound Trunk ibmveth (shown below), Inbound Trunk ibmveth <=> OVS <=> Outbound Trunk ibmveth In this model, we hit the following issues which impacted the VM communication performance, - Issue 1: ibmveth doesn't support largesend and checksum offload features when configured as "Trunk". Driver has explicit checks to prevent enabling these offloads. - Issue 2: SYN packet drops seen at destination VM. When the packet originates, it has CHECKSUM_PARTIAL flag set and as it gets delivered to IO server's inbound Trunk ibmveth, on validating "checksum good" bits in ibmveth receive routine, SKB's ip_summed field is set with CHECKSUM_UNNECESSARY flag. This packet is then bridged by OVS (or Linux Bridge) and delivered to outbound Trunk ibmveth. At this point the outbound ibmveth transmit routine will not set "no checksum" and "checksum good" bits in transmit buffer descriptor, as it does so only when the ip_summed field is CHECKSUM_PARTIAL. When this packet gets delivered to destination VM, TCP layer receives the packet with checksum value of 0 and with no checksum related flags in ip_summed field. This leads to packet drops. So, TCP connections never goes through fine. - Issue 3: First packet of a TCP connection will be dropped, if there is no OVS flow cached in datapath. OVS while trying to identify the flow, computes the checksum. The computed checksum will be invalid at the receiving end, as ibmveth transmit routine zeroes out the pseudo checksum value in the packet. This leads to packet drop. - Issue 4: ibmveth driver doesn't have support for SKB's with frag_list. When Physical NIC has GRO enabled and when OVS bridges these packets, OVS vport send code will end up calling dev_queue_xmit, which in turn calls validate_xmit_skb. In validate_xmit_skb routine, the larger packets will get segmented into MSS sized segments, if SKB has a frag_list and if the driver to which they are delivered to doesn't support NETIF_F_FRAGLIST feature. This patch addresses the above four issues, thereby enabling end to end largesend and checksum offload support for better performance. - Fix for Issue 1 : Remove checks which prevent enabling TCP largesend and checksum offloads. - Fix for Issue 2 : When ibmveth receives a packet with "checksum good" bit set and if its configured in Trunk mode, set appropriate SKB fields using skb_partial_csum_set (ip_summed field is set with CHECKSUM_PARTIAL) - Fix for Issue 3: Recompute the pseudo header checksum before sending the SKB up the stack. - Fix for Issue 4: Linearize the SKBs with frag_list. Though we end up allocating buffers and copying data, this fix gives upto 4X throughput increase. Note: All these fixes need to be dropped together as fixing just one of them will lead to other issues immediately (especially for Issues 1,2 & 3). Signed-off-by: Sivakumar Krishnasamy <ksiva@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-19 17:30:38 +08:00
bool is_active_trunk;
void *bounce_buffer;
dma_addr_t bounce_buffer_dma;
u64 fw_ipv6_csum_support;
u64 fw_ipv4_csum_support;
u64 fw_large_send_support;
/* adapter specific stats */
u64 replenish_task_cycles;
u64 replenish_no_mem;
u64 replenish_add_buff_failure;
u64 replenish_add_buff_success;
u64 rx_invalid_buffer;
u64 rx_no_buffer;
u64 tx_map_failed;
u64 tx_send_failed;
u64 tx_large_packets;
u64 rx_large_packets;
};
/*
* We pass struct ibmveth_buf_desc_fields to the hypervisor in registers,
* so we don't need to byteswap the two elements. However since we use
* a union (ibmveth_buf_desc) to convert from the struct to a u64 we
* do end up with endian specific ordering of the elements and that
* needs correcting.
*/
struct ibmveth_buf_desc_fields {
#ifdef __BIG_ENDIAN
u32 flags_len;
u32 address;
#else
u32 address;
u32 flags_len;
#endif
#define IBMVETH_BUF_VALID 0x80000000
#define IBMVETH_BUF_TOGGLE 0x40000000
#define IBMVETH_BUF_LRG_SND 0x04000000
#define IBMVETH_BUF_NO_CSUM 0x02000000
#define IBMVETH_BUF_CSUM_GOOD 0x01000000
#define IBMVETH_BUF_LEN_MASK 0x00FFFFFF
};
union ibmveth_buf_desc {
u64 desc;
struct ibmveth_buf_desc_fields fields;
};
struct ibmveth_rx_q_entry {
__be32 flags_off;
#define IBMVETH_RXQ_TOGGLE 0x80000000
#define IBMVETH_RXQ_TOGGLE_SHIFT 31
#define IBMVETH_RXQ_VALID 0x40000000
#define IBMVETH_RXQ_LRG_PKT 0x04000000
#define IBMVETH_RXQ_NO_CSUM 0x02000000
#define IBMVETH_RXQ_CSUM_GOOD 0x01000000
#define IBMVETH_RXQ_OFF_MASK 0x0000FFFF
__be32 length;
/* correlator is only used by the OS, no need to byte swap */
u64 correlator;
};
#endif /* _IBMVETH_H */