Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-16 00:52:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
17a7b1d74b
linux/drivers/net/e1000/e1000.h
Jesse Brandeburg 835bb12983 e1000: add dynamic itr modes 
Add a new dynamic itr algorithm, with 2 modes, and make it the default
operation mode. This greatly reduces latency and increases small packet
performance, at the "cost" of some CPU utilization. Bulk traffic
throughput is unaffected.

The driver can limit the amount of interrupts per second that the
adapter will generate for incoming packets. It does this by writing a
value to the adapter that is based on the maximum amount of interrupts
that the adapter will generate per second.

Setting InterruptThrottleRate to a value greater or equal to 100 will
program the adapter to send out a maximum of that many interrupts per
second, even if more packets have come in. This reduces interrupt
load on the system and can lower CPU utilization under heavy load,
but will increase latency as packets are not processed as quickly.

The default behaviour of the driver previously assumed a static
InterruptThrottleRate value of 8000, providing a good fallback value
for all traffic types,but lacking in small packet performance and
latency. The hardware can handle many more small packets per second
however, and for this reason an adaptive interrupt moderation algorithm
was implemented.

Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in
which it dynamically adjusts the InterruptThrottleRate value based on
the traffic that it receives. After determining the type of incoming
traffic in the last timeframe, it will adjust the InterruptThrottleRate
to an appropriate value for that traffic.

The algorithm classifies the incoming traffic every interval into
classes.  Once the class is determined, the InterruptThrottleRate
value is adjusted to suit that traffic type the best. There are
three classes defined: "Bulk traffic", for large amounts of packets
of normal size; "Low latency", for small amounts of traffic and/or
a significant percentage of small packets; and "Lowest latency",
for almost completely small packets or minimal traffic.

In dynamic conservative mode, the InterruptThrottleRate value is
set to 4000 for traffic that falls in class "Bulk traffic". If
traffic falls in the "Low latency" or "Lowest latency" class, the
InterruptThrottleRate is increased stepwise to 20000. This default
mode is suitable for most applications.

For situations where low latency is vital such as cluster or
grid computing, the algorithm can reduce latency even more when
InterruptThrottleRate is set to mode 1. In this mode, which operates
the same as mode 3, the InterruptThrottleRate will be increased
stepwise to 70000 for traffic in class "Lowest latency".

Setting InterruptThrottleRate to 0 turns off any interrupt moderation
and may improve small packet latency, but is generally not suitable
for bulk throughput traffic.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Rick Jones <rick.jones2@hp.com>
Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
2006-12-02 00:12:00 -05:00

367 lines
10 KiB
C
Raw Blame History

/*******************************************************************************
Intel PRO/1000 Linux driver
Copyright(c) 1999 - 2006 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
version 2, as published by the Free Software Foundation.
This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
Contact Information:
Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
*******************************************************************************/
/* Linux PRO/1000 Ethernet Driver main header file */
#ifndef _E1000_H_
#define _E1000_H_
#include <linux/stddef.h>
#include <linux/module.h>
#include <linux/types.h>
#include <asm/byteorder.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/delay.h>
#include <linux/timer.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/interrupt.h>
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/dma-mapping.h>
#include <linux/bitops.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <linux/capability.h>
#include <linux/in.h>
#include <linux/ip.h>
#ifdef NETIF_F_TSO6
#include <linux/ipv6.h>
#endif
#include <linux/tcp.h>
#include <linux/udp.h>
#include <net/pkt_sched.h>
#include <linux/list.h>
#include <linux/reboot.h>
#ifdef NETIF_F_TSO
#include <net/checksum.h>
#endif
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#define BAR_0 0
#define BAR_1 1
#define BAR_5 5
#define INTEL_E1000_ETHERNET_DEVICE(device_id) {\
PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
struct e1000_adapter;
#include "e1000_hw.h"
#ifdef DBG
#define E1000_DBG(args...) printk(KERN_DEBUG "e1000: " args)
#else
#define E1000_DBG(args...)
#endif
#define E1000_ERR(args...) printk(KERN_ERR "e1000: " args)
#define PFX "e1000: "
#define DPRINTK(nlevel, klevel, fmt, args...) \
(void)((NETIF_MSG_##nlevel & adapter->msg_enable) && \
printk(KERN_##klevel PFX "%s: %s: " fmt, adapter->netdev->name, \
__FUNCTION__ , ## args))
#define E1000_MAX_INTR 10
/* TX/RX descriptor defines */
#define E1000_DEFAULT_TXD 256
#define E1000_MAX_TXD 256
#define E1000_MIN_TXD 80
#define E1000_MAX_82544_TXD 4096
#define E1000_DEFAULT_RXD 256
#define E1000_MAX_RXD 256
#define E1000_MIN_RXD 80
#define E1000_MAX_82544_RXD 4096
/* this is the size past which hardware will drop packets when setting LPE=0 */
#define MAXIMUM_ETHERNET_VLAN_SIZE 1522
/* Supported Rx Buffer Sizes */
#define E1000_RXBUFFER_128 128 /* Used for packet split */
#define E1000_RXBUFFER_256 256 /* Used for packet split */
#define E1000_RXBUFFER_512 512
#define E1000_RXBUFFER_1024 1024
#define E1000_RXBUFFER_2048 2048
#define E1000_RXBUFFER_4096 4096
#define E1000_RXBUFFER_8192 8192
#define E1000_RXBUFFER_16384 16384
/* SmartSpeed delimiters */
#define E1000_SMARTSPEED_DOWNSHIFT 3
#define E1000_SMARTSPEED_MAX 15
/* Packet Buffer allocations */
#define E1000_PBA_BYTES_SHIFT 0xA
#define E1000_TX_HEAD_ADDR_SHIFT 7
#define E1000_PBA_TX_MASK 0xFFFF0000
/* Flow Control Watermarks */
#define E1000_FC_HIGH_DIFF 0x1638 /* High: 5688 bytes below Rx FIFO size */
#define E1000_FC_LOW_DIFF 0x1640 /* Low: 5696 bytes below Rx FIFO size */
#define E1000_FC_PAUSE_TIME 0x0680 /* 858 usec */
/* How many Tx Descriptors do we need to call netif_wake_queue ? */
#define E1000_TX_QUEUE_WAKE 16
/* How many Rx Buffers do we bundle into one write to the hardware ? */
#define E1000_RX_BUFFER_WRITE 16 /* Must be power of 2 */
#define AUTO_ALL_MODES 0
#define E1000_EEPROM_82544_APM 0x0004
#define E1000_EEPROM_ICH8_APME 0x0004
#define E1000_EEPROM_APME 0x0400
#ifndef E1000_MASTER_SLAVE
/* Switch to override PHY master/slave setting */
#define E1000_MASTER_SLAVE e1000_ms_hw_default
#endif
#define E1000_MNG_VLAN_NONE -1
/* Number of packet split data buffers (not including the header buffer) */
#define PS_PAGE_BUFFERS MAX_PS_BUFFERS-1
/* only works for sizes that are powers of 2 */
#define E1000_ROUNDUP(i, size) ((i) = (((i) + (size) - 1) & ~((size) - 1)))
/* wrapper around a pointer to a socket buffer,
* so a DMA handle can be stored along with the buffer */
struct e1000_buffer {
struct sk_buff *skb;
dma_addr_t dma;
unsigned long time_stamp;
uint16_t length;
uint16_t next_to_watch;
};
struct e1000_ps_page { struct page *ps_page[PS_PAGE_BUFFERS]; };
struct e1000_ps_page_dma { uint64_t ps_page_dma[PS_PAGE_BUFFERS]; };
struct e1000_tx_ring {
/* pointer to the descriptor ring memory */
void *desc;
/* physical address of the descriptor ring */
dma_addr_t dma;
/* length of descriptor ring in bytes */
unsigned int size;
/* number of descriptors in the ring */
unsigned int count;
/* next descriptor to associate a buffer with */
unsigned int next_to_use;
/* next descriptor to check for DD status bit */
unsigned int next_to_clean;
/* array of buffer information structs */
struct e1000_buffer *buffer_info;
spinlock_t tx_lock;
uint16_t tdh;
uint16_t tdt;
boolean_t last_tx_tso;
};
struct e1000_rx_ring {
/* pointer to the descriptor ring memory */
void *desc;
/* physical address of the descriptor ring */
dma_addr_t dma;
/* length of descriptor ring in bytes */
unsigned int size;
/* number of descriptors in the ring */
unsigned int count;
/* next descriptor to associate a buffer with */
unsigned int next_to_use;
/* next descriptor to check for DD status bit */
unsigned int next_to_clean;
/* array of buffer information structs */
struct e1000_buffer *buffer_info;
/* arrays of page information for packet split */
struct e1000_ps_page *ps_page;
struct e1000_ps_page_dma *ps_page_dma;
/* cpu for rx queue */
int cpu;
uint16_t rdh;
uint16_t rdt;
};
#define E1000_DESC_UNUSED(R) \
((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
(R)->next_to_clean - (R)->next_to_use - 1)
#define E1000_RX_DESC_PS(R, i) \
(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
#define E1000_RX_DESC_EXT(R, i) \
(&(((union e1000_rx_desc_extended *)((R).desc))[i]))
#define E1000_GET_DESC(R, i, type) (&(((struct type *)((R).desc))[i]))
#define E1000_RX_DESC(R, i) E1000_GET_DESC(R, i, e1000_rx_desc)
#define E1000_TX_DESC(R, i) E1000_GET_DESC(R, i, e1000_tx_desc)
#define E1000_CONTEXT_DESC(R, i) E1000_GET_DESC(R, i, e1000_context_desc)
/* board specific private data structure */
struct e1000_adapter {
struct timer_list tx_fifo_stall_timer;
struct timer_list watchdog_timer;
struct timer_list phy_info_timer;
struct vlan_group *vlgrp;
uint16_t mng_vlan_id;
uint32_t bd_number;
uint32_t rx_buffer_len;
uint32_t wol;
uint32_t smartspeed;
uint32_t en_mng_pt;
uint16_t link_speed;
uint16_t link_duplex;
spinlock_t stats_lock;
#ifdef CONFIG_E1000_NAPI
spinlock_t tx_queue_lock;
#endif
atomic_t irq_sem;
unsigned int detect_link;
unsigned int total_tx_bytes;
unsigned int total_tx_packets;
unsigned int total_rx_bytes;
unsigned int total_rx_packets;
/* Interrupt Throttle Rate */
uint32_t itr;
uint32_t itr_setting;
uint16_t tx_itr;
uint16_t rx_itr;
struct work_struct reset_task;
uint8_t fc_autoneg;
struct timer_list blink_timer;
unsigned long led_status;
/* TX */
struct e1000_tx_ring *tx_ring; /* One per active queue */
unsigned int restart_queue;
unsigned long tx_queue_len;
uint32_t txd_cmd;
uint32_t tx_int_delay;
uint32_t tx_abs_int_delay;
uint32_t gotcl;
uint64_t gotcl_old;
uint64_t tpt_old;
uint64_t colc_old;
uint32_t tx_timeout_count;
uint32_t tx_fifo_head;
uint32_t tx_head_addr;
uint32_t tx_fifo_size;
uint8_t tx_timeout_factor;
atomic_t tx_fifo_stall;
boolean_t pcix_82544;
boolean_t detect_tx_hung;
/* RX */
#ifdef CONFIG_E1000_NAPI
boolean_t (*clean_rx) (struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring,
int *work_done, int work_to_do);
#else
boolean_t (*clean_rx) (struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring);
#endif
void (*alloc_rx_buf) (struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring,
int cleaned_count);
struct e1000_rx_ring *rx_ring; /* One per active queue */
#ifdef CONFIG_E1000_NAPI
struct net_device *polling_netdev; /* One per active queue */
#endif
int num_tx_queues;
int num_rx_queues;
uint64_t hw_csum_err;
uint64_t hw_csum_good;
uint64_t rx_hdr_split;
uint32_t alloc_rx_buff_failed;
uint32_t rx_int_delay;
uint32_t rx_abs_int_delay;
boolean_t rx_csum;
unsigned int rx_ps_pages;
uint32_t gorcl;
uint64_t gorcl_old;
uint16_t rx_ps_bsize0;
/* OS defined structs */
struct net_device *netdev;
struct pci_dev *pdev;
struct net_device_stats net_stats;
/* structs defined in e1000_hw.h */
struct e1000_hw hw;
struct e1000_hw_stats stats;
struct e1000_phy_info phy_info;
struct e1000_phy_stats phy_stats;
uint32_t test_icr;
struct e1000_tx_ring test_tx_ring;
struct e1000_rx_ring test_rx_ring;
uint32_t *config_space;
int msg_enable;
#ifdef CONFIG_PCI_MSI
boolean_t have_msi;
#endif
/* to not mess up cache alignment, always add to the bottom */
#ifdef NETIF_F_TSO
boolean_t tso_force;
#endif
boolean_t smart_power_down; /* phy smart power down */
boolean_t quad_port_a;
unsigned long flags;
uint32_t eeprom_wol;
};
enum e1000_state_t {
__E1000_TESTING,
__E1000_RESETTING,
__E1000_DOWN
};
#endif /* _E1000_H_ */
Reference in New Issue View Git Blame Copy Permalink