linux_dsm_epyc7002/drivers/net/e1000/e1000.h

369 lines
10 KiB
C
Raw Normal View 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>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <net/pkt_sched.h>
#include <linux/list.h>
#include <linux/reboot.h>
#include <net/checksum.h>
#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...) \
do { \
if (NETIF_MSG_##nlevel & adapter->msg_enable) \
printk(KERN_##klevel PFX "%s: %s: " fmt, \
adapter->netdev->name, __func__, ##args); \
} while (0)
#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)
/* 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;
u16 length;
u16 next_to_watch;
};
struct e1000_ps_page {
struct page *ps_page[PS_PAGE_BUFFERS];
};
struct e1000_ps_page_dma {
u64 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;
u16 tdh;
u16 tdt;
bool 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;
u16 rdh;
u16 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;
u16 mng_vlan_id;
u32 bd_number;
u32 rx_buffer_len;
u32 wol;
u32 smartspeed;
u32 en_mng_pt;
u16 link_speed;
u16 link_duplex;
spinlock_t stats_lock;
spinlock_t tx_queue_lock;
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>
2006-11-01 23:48:13 +07:00
unsigned int total_tx_bytes;
unsigned int total_tx_packets;
unsigned int total_rx_bytes;
unsigned int total_rx_packets;
/* Interrupt Throttle Rate */
u32 itr;
u32 itr_setting;
u16 tx_itr;
u16 rx_itr;
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>
2006-11-01 23:48:13 +07:00
struct work_struct reset_task;
u8 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;
u32 txd_cmd;
u32 tx_int_delay;
u32 tx_abs_int_delay;
u32 gotcl;
u64 gotcl_old;
u64 tpt_old;
u64 colc_old;
u32 tx_timeout_count;
u32 tx_fifo_head;
u32 tx_head_addr;
u32 tx_fifo_size;
u8 tx_timeout_factor;
atomic_t tx_fifo_stall;
bool pcix_82544;
bool detect_tx_hung;
/* RX */
bool (*clean_rx)(struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring,
int *work_done, int work_to_do);
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 */
[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 06:41:36 +07:00
struct napi_struct napi;
struct net_device *polling_netdev; /* One per active queue */
int num_tx_queues;
int num_rx_queues;
u64 hw_csum_err;
u64 hw_csum_good;
u64 rx_hdr_split;
u32 alloc_rx_buff_failed;
u32 rx_int_delay;
u32 rx_abs_int_delay;
bool rx_csum;
unsigned int rx_ps_pages;
u32 gorcl;
u64 gorcl_old;
u16 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;
u32 test_icr;
struct e1000_tx_ring test_tx_ring;
struct e1000_rx_ring test_rx_ring;
int msg_enable;
bool have_msi;
/* to not mess up cache alignment, always add to the bottom */
bool tso_force;
bool smart_power_down; /* phy smart power down */
bool quad_port_a;
unsigned long flags;
u32 eeprom_wol;
};
enum e1000_state_t {
__E1000_TESTING,
__E1000_RESETTING,
__E1000_DOWN
};
extern char e1000_driver_name[];
extern const char e1000_driver_version[];
extern int e1000_up(struct e1000_adapter *adapter);
extern void e1000_down(struct e1000_adapter *adapter);
extern void e1000_reinit_locked(struct e1000_adapter *adapter);
extern void e1000_reset(struct e1000_adapter *adapter);
extern int e1000_set_spd_dplx(struct e1000_adapter *adapter, u16 spddplx);
extern int e1000_setup_all_rx_resources(struct e1000_adapter *adapter);
extern int e1000_setup_all_tx_resources(struct e1000_adapter *adapter);
extern void e1000_free_all_rx_resources(struct e1000_adapter *adapter);
extern void e1000_free_all_tx_resources(struct e1000_adapter *adapter);
extern void e1000_update_stats(struct e1000_adapter *adapter);
extern void e1000_power_up_phy(struct e1000_adapter *);
extern void e1000_set_ethtool_ops(struct net_device *netdev);
extern void e1000_check_options(struct e1000_adapter *adapter);
#endif /* _E1000_H_ */