mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-10-05 00:20:32 +00:00
Code Issues Releases Wiki Activity

myri10ge: Convert from LRO to GRO

Browse source 
Convert myri10ge from LRO to GRO, and simplify the driver by removing
various LRO-related code which is no longer needed including
ndo_fix_features op, custom skb building from frags, and LRO
header parsing.

Signed-off-by: Andrew Gallatin <gallatin@myri.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Andrew Gallatin 2012-11-30 08:31:58 +00:00 committed by David S. Miller
parent ba57b6f204
commit 4ca3221fe4
2 changed files with 34 additions and 203 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
drivers/net/ethernet/myricom/Kconfig
View file

@ -23,7 +23,6 @@ config MYRI10GE
depends on PCI && INET
select FW_LOADER
select CRC32
select INET_LRO
---help---
This driver supports Myricom Myri-10G Dual Protocol interface in
Ethernet mode. If the eeprom on your board is not recent enough,

236
drivers/net/ethernet/myricom/myri10ge/myri10ge.c
View file

@ -50,7 +50,6 @@
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/inet_lro.h>
#include <linux/dca.h>
#include <linux/ip.h>
#include <linux/inet.h>
@ -96,8 +95,6 @@ MODULE_LICENSE("Dual BSD/GPL");
#define MYRI10GE_EEPROM_STRINGS_SIZE 256
#define MYRI10GE_MAX_SEND_DESC_TSO ((65536 / 2048) * 2)
#define MYRI10GE_MAX_LRO_DESCRIPTORS 8
#define MYRI10GE_LRO_MAX_PKTS 64
#define MYRI10GE_NO_CONFIRM_DATA htonl(0xffffffff)
#define MYRI10GE_NO_RESPONSE_RESULT 0xffffffff
@ -165,8 +162,6 @@ struct myri10ge_rx_done {
dma_addr_t bus;
int cnt;
int idx;
struct net_lro_mgr lro_mgr;
struct net_lro_desc lro_desc[MYRI10GE_MAX_LRO_DESCRIPTORS];
};
struct myri10ge_slice_netstats {
@ -338,11 +333,6 @@ static int myri10ge_debug = -1; /* defaults above */
module_param(myri10ge_debug, int, 0);
MODULE_PARM_DESC(myri10ge_debug, "Debug level (0=none,...,16=all)");
static int myri10ge_lro_max_pkts = MYRI10GE_LRO_MAX_PKTS;
module_param(myri10ge_lro_max_pkts, int, S_IRUGO);
MODULE_PARM_DESC(myri10ge_lro_max_pkts,
"Number of LRO packets to be aggregated");
static int myri10ge_fill_thresh = 256;
module_param(myri10ge_fill_thresh, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(myri10ge_fill_thresh, "Number of empty rx slots allowed");
@ -1197,36 +1187,6 @@ static inline void myri10ge_vlan_ip_csum(struct sk_buff *skb, __wsum hw_csum)
}
}
static inline void
myri10ge_rx_skb_build(struct sk_buff *skb, u8 * va,
struct skb_frag_struct *rx_frags, int len, int hlen)
{
struct skb_frag_struct *skb_frags;
skb->len = skb->data_len = len;
/* attach the page(s) */
skb_frags = skb_shinfo(skb)->frags;
while (len > 0) {
memcpy(skb_frags, rx_frags, sizeof(*skb_frags));
len -= skb_frag_size(rx_frags);
skb_frags++;
rx_frags++;
skb_shinfo(skb)->nr_frags++;
}
/* pskb_may_pull is not available in irq context, but
* skb_pull() (for ether_pad and eth_type_trans()) requires
* the beginning of the packet in skb_headlen(), move it
* manually */
skb_copy_to_linear_data(skb, va, hlen);
skb_shinfo(skb)->frags[0].page_offset += hlen;
skb_frag_size_sub(&skb_shinfo(skb)->frags[0], hlen);
skb->data_len -= hlen;
skb->tail += hlen;
skb_pull(skb, MXGEFW_PAD);
}
static void
myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
int bytes, int watchdog)
@ -1304,18 +1264,14 @@ myri10ge_unmap_rx_page(struct pci_dev *pdev,
}
}
#define MYRI10GE_HLEN 64 /* The number of bytes to copy from a
* page into an skb */
static inline int
myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum,
bool lro_enabled)
myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum)
{
struct myri10ge_priv *mgp = ss->mgp;
struct sk_buff *skb;
struct skb_frag_struct rx_frags[MYRI10GE_MAX_FRAGS_PER_FRAME];
struct skb_frag_struct *rx_frags;
struct myri10ge_rx_buf *rx;
int i, idx, hlen, remainder, bytes;
int i, idx, remainder, bytes;
struct pci_dev *pdev = mgp->pdev;
struct net_device *dev = mgp->dev;
u8 *va;
@ -1332,67 +1288,47 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum,
idx = rx->cnt & rx->mask;
va = page_address(rx->info[idx].page) + rx->info[idx].page_offset;
prefetch(va);
skb = napi_get_frags(&ss->napi);
if (unlikely(skb == NULL)) {
ss->stats.rx_dropped++;
for (i = 0, remainder = len; remainder > 0; i++) {
myri10ge_unmap_rx_page(pdev, &rx->info[idx], bytes);
put_page(rx->info[idx].page);
rx->cnt++;
idx = rx->cnt & rx->mask;
remainder -= MYRI10GE_ALLOC_SIZE;
}
return 0;
}
rx_frags = skb_shinfo(skb)->frags;
/* Fill skb_frag_struct(s) with data from our receive */
for (i = 0, remainder = len; remainder > 0; i++) {
myri10ge_unmap_rx_page(pdev, &rx->info[idx], bytes);
__skb_frag_set_page(&rx_frags[i], rx->info[idx].page);
rx_frags[i].page_offset = rx->info[idx].page_offset;
if (remainder < MYRI10GE_ALLOC_SIZE)
skb_frag_size_set(&rx_frags[i], remainder);
else
skb_frag_size_set(&rx_frags[i], MYRI10GE_ALLOC_SIZE);
skb_fill_page_desc(skb, i, rx->info[idx].page,
rx->info[idx].page_offset,
remainder < MYRI10GE_ALLOC_SIZE ?
remainder : MYRI10GE_ALLOC_SIZE);
rx->cnt++;
idx = rx->cnt & rx->mask;
remainder -= MYRI10GE_ALLOC_SIZE;
}
if (lro_enabled) {
rx_frags[0].page_offset += MXGEFW_PAD;
skb_frag_size_sub(&rx_frags[0], MXGEFW_PAD);
len -= MXGEFW_PAD;
lro_receive_frags(&ss->rx_done.lro_mgr, rx_frags,
/* opaque, will come back in get_frag_header */
len, len,
(void *)(__force unsigned long)csum, csum);
/* remove padding */
rx_frags[0].page_offset += MXGEFW_PAD;
rx_frags[0].size -= MXGEFW_PAD;
len -= MXGEFW_PAD;
return 1;
skb->len = len;
skb->data_len = len;
skb->truesize += len;
if (dev->features & NETIF_F_RXCSUM) {
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum;
}
hlen = MYRI10GE_HLEN > len ? len : MYRI10GE_HLEN;
/* allocate an skb to attach the page(s) to. This is done
* after trying LRO, so as to avoid skb allocation overheads */
skb = netdev_alloc_skb(dev, MYRI10GE_HLEN + 16);
if (unlikely(skb == NULL)) {
ss->stats.rx_dropped++;
do {
i--;
__skb_frag_unref(&rx_frags[i]);
} while (i != 0);
return 0;
}
/* Attach the pages to the skb, and trim off any padding */
myri10ge_rx_skb_build(skb, va, rx_frags, len, hlen);
if (skb_frag_size(&skb_shinfo(skb)->frags[0]) <= 0) {
skb_frag_unref(skb, 0);
skb_shinfo(skb)->nr_frags = 0;
} else {
skb->truesize += bytes * skb_shinfo(skb)->nr_frags;
}
skb->protocol = eth_type_trans(skb, dev);
skb_record_rx_queue(skb, ss - &mgp->ss[0]);
if (dev->features & NETIF_F_RXCSUM) {
if ((skb->protocol == htons(ETH_P_IP)) ||
(skb->protocol == htons(ETH_P_IPV6))) {
skb->csum = csum;
skb->ip_summed = CHECKSUM_COMPLETE;
} else
myri10ge_vlan_ip_csum(skb, csum);
}
netif_receive_skb(skb);
napi_gro_frags(&ss->napi);
return 1;
}
@ -1480,18 +1416,11 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
u16 length;
__wsum checksum;
/*
* Prevent compiler from generating more than one ->features memory
* access to avoid theoretical race condition with functions that
* change NETIF_F_LRO flag at runtime.
*/
bool lro_enabled = !!(ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO);
while (rx_done->entry[idx].length != 0 && work_done < budget) {
length = ntohs(rx_done->entry[idx].length);
rx_done->entry[idx].length = 0;
checksum = csum_unfold(rx_done->entry[idx].checksum);
rx_ok = myri10ge_rx_done(ss, length, checksum, lro_enabled);
rx_ok = myri10ge_rx_done(ss, length, checksum);
rx_packets += rx_ok;
rx_bytes += rx_ok * (unsigned long)length;
cnt++;
@ -1503,9 +1432,6 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
ss->stats.rx_packets += rx_packets;
ss->stats.rx_bytes += rx_bytes;
if (lro_enabled)
lro_flush_all(&rx_done->lro_mgr);
/* restock receive rings if needed */
if (ss->rx_small.fill_cnt - ss->rx_small.cnt < myri10ge_fill_thresh)
myri10ge_alloc_rx_pages(mgp, &ss->rx_small,
@ -1779,7 +1705,6 @@ static const char myri10ge_gstrings_slice_stats[][ETH_GSTRING_LEN] = {
"tx_pkt_start", "tx_pkt_done", "tx_req", "tx_done",
"rx_small_cnt", "rx_big_cnt",
"wake_queue", "stop_queue", "tx_linearized",
"LRO aggregated", "LRO flushed", "LRO avg aggr", "LRO no_desc",
};
#define MYRI10GE_NET_STATS_LEN 21
@ -1880,14 +1805,6 @@ myri10ge_get_ethtool_stats(struct net_device *netdev,
data[i++] = (unsigned int)ss->tx.wake_queue;
data[i++] = (unsigned int)ss->tx.stop_queue;
data[i++] = (unsigned int)ss->tx.linearized;
data[i++] = ss->rx_done.lro_mgr.stats.aggregated;
data[i++] = ss->rx_done.lro_mgr.stats.flushed;
if (ss->rx_done.lro_mgr.stats.flushed)
data[i++] = ss->rx_done.lro_mgr.stats.aggregated /
ss->rx_done.lro_mgr.stats.flushed;
else
data[i++] = 0;
data[i++] = ss->rx_done.lro_mgr.stats.no_desc;
}
}
@ -2271,67 +2188,6 @@ static void myri10ge_free_irq(struct myri10ge_priv *mgp)
pci_disable_msix(pdev);
}
static int
myri10ge_get_frag_header(struct skb_frag_struct *frag, void **mac_hdr,
void **ip_hdr, void **tcpudp_hdr,
u64 * hdr_flags, void *priv)
{
struct ethhdr *eh;
struct vlan_ethhdr *veh;
struct iphdr *iph;
u8 *va = skb_frag_address(frag);
unsigned long ll_hlen;
/* passed opaque through lro_receive_frags() */
__wsum csum = (__force __wsum) (unsigned long)priv;
/* find the mac header, aborting if not IPv4 */
eh = (struct ethhdr *)va;
*mac_hdr = eh;
ll_hlen = ETH_HLEN;
if (eh->h_proto != htons(ETH_P_IP)) {
if (eh->h_proto == htons(ETH_P_8021Q)) {
veh = (struct vlan_ethhdr *)va;
if (veh->h_vlan_encapsulated_proto != htons(ETH_P_IP))
return -1;
ll_hlen += VLAN_HLEN;
/*
* HW checksum starts ETH_HLEN bytes into
* frame, so we must subtract off the VLAN
* header's checksum before csum can be used
*/
csum = csum_sub(csum, csum_partial(va + ETH_HLEN,
VLAN_HLEN, 0));
} else {
return -1;
}
}
*hdr_flags = LRO_IPV4;
iph = (struct iphdr *)(va + ll_hlen);
*ip_hdr = iph;
if (iph->protocol != IPPROTO_TCP)
return -1;
if (ip_is_fragment(iph))
return -1;
*hdr_flags |= LRO_TCP;
*tcpudp_hdr = (u8 *) (*ip_hdr) + (iph->ihl << 2);
/* verify the IP checksum */
if (unlikely(ip_fast_csum((u8 *) iph, iph->ihl)))
return -1;
/* verify the checksum */
if (unlikely(csum_tcpudp_magic(iph->saddr, iph->daddr,
ntohs(iph->tot_len) - (iph->ihl << 2),
IPPROTO_TCP, csum)))
return -1;
return 0;
}
static int myri10ge_get_txrx(struct myri10ge_priv *mgp, int slice)
{
struct myri10ge_cmd cmd;
@ -2402,7 +2258,6 @@ static int myri10ge_open(struct net_device *dev)
struct myri10ge_cmd cmd;
int i, status, big_pow2, slice;
u8 *itable;
struct net_lro_mgr *lro_mgr;
if (mgp->running != MYRI10GE_ETH_STOPPED)
return -EBUSY;
@ -2513,19 +2368,6 @@ static int myri10ge_open(struct net_device *dev)
goto abort_with_rings;
}
lro_mgr = &ss->rx_done.lro_mgr;
lro_mgr->dev = dev;
lro_mgr->features = LRO_F_NAPI;
lro_mgr->ip_summed = CHECKSUM_COMPLETE;
lro_mgr->ip_summed_aggr = CHECKSUM_UNNECESSARY;
lro_mgr->max_desc = MYRI10GE_MAX_LRO_DESCRIPTORS;
lro_mgr->lro_arr = ss->rx_done.lro_desc;
lro_mgr->get_frag_header = myri10ge_get_frag_header;
lro_mgr->max_aggr = myri10ge_lro_max_pkts;
lro_mgr->frag_align_pad = 2;
if (lro_mgr->max_aggr > MAX_SKB_FRAGS)
lro_mgr->max_aggr = MAX_SKB_FRAGS;
/* must happen prior to any irq */
napi_enable(&(ss)->napi);
}
@ -3143,15 +2985,6 @@ static int myri10ge_set_mac_address(struct net_device *dev, void *addr)
return 0;
}
static netdev_features_t myri10ge_fix_features(struct net_device *dev,
netdev_features_t features)
{
if (!(features & NETIF_F_RXCSUM))
features &= ~NETIF_F_LRO;
return features;
}
static int myri10ge_change_mtu(struct net_device *dev, int new_mtu)
{
struct myri10ge_priv *mgp = netdev_priv(dev);
@ -3878,7 +3711,6 @@ static const struct net_device_ops myri10ge_netdev_ops = {
.ndo_get_stats64 = myri10ge_get_stats,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = myri10ge_change_mtu,
.ndo_fix_features = myri10ge_fix_features,
.ndo_set_rx_mode = myri10ge_set_multicast_list,
.ndo_set_mac_address = myri10ge_set_mac_address,
};
@ -4018,7 +3850,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->netdev_ops = &myri10ge_netdev_ops;
netdev->mtu = myri10ge_initial_mtu;
netdev->hw_features = mgp->features | NETIF_F_LRO | NETIF_F_RXCSUM;
netdev->hw_features = mgp->features | NETIF_F_RXCSUM;
netdev->features = netdev->hw_features;
if (dac_enabled)