UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/drivers/net/pcmcia/smc91c92_cs.c

2127 lines
61 KiB
C
Raw Normal View History

Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*======================================================================
A PCMCIA ethernet driver for SMC91c92-based cards.
This driver supports Megahertz PCMCIA ethernet cards; and
Megahertz, Motorola, Ositech, and Psion Dacom ethernet/modem
multifunction cards.
Copyright (C) 1999 David A. Hinds -- dahinds@users.sourceforge.net
smc91c92_cs.c 1.122 2002/10/25 06:26:39
This driver contains code written by Donald Becker
(becker@scyld.com), Rowan Hughes (x-csrdh@jcu.edu.au),
David Hinds (dahinds@users.sourceforge.net), and Erik Stahlman
(erik@vt.edu). Donald wrote the SMC 91c92 code using parts of
Erik's SMC 91c94 driver. Rowan wrote a similar driver, and I've
incorporated some parts of his driver here. I (Dave) wrote most
of the PCMCIA glue code, and the Ositech support code. Kelly
Stephens (kstephen@holli.com) added support for the Motorola
Mariner, with help from Allen Brost.
This software may be used and distributed according to the terms of
the GNU General Public License, incorporated herein by reference.
======================================================================*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/crc32.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/ioport.h>
#include <linux/ethtool.h>
#include <linux/mii.h>
[NET PCMCIA]: drivers/net/pcmcia/smc91c92_cs.c : Use of time_after macro From: Marcelo Feitoza Parisi <marcelo@feitoza.com.br> Use of the time_after() macro, defined at linux/jiffies.h, which deal with wrapping correctly and are nicer to read. Signed-off-by: Marcelo Feitoza Parisi <marcelo@feitoza.com.br> Signed-off-by: Domen Puncer <domen@coderock.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-16 01:00:41 +08:00
#include <linux/jiffies.h>
smc91c92_cs: use request_firmware Added osi_load_firmware() instead of copying same thing twice Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
2009-03-30 22:49:54 +08:00
#include <linux/firmware.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <pcmcia/cs_types.h>
#include <pcmcia/cs.h>
#include <pcmcia/cistpl.h>
#include <pcmcia/cisreg.h>
#include <pcmcia/ciscode.h>
#include <pcmcia/ds.h>
[PATCH] pcmcia: convert remaining users of pcmcia_release_io and _irq Convert the remaining drivers which use pcmcia_release_io or pcmcia_release_irq, and remove the EXPORT of these symbols. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-01-15 17:05:19 +08:00
#include <pcmcia/ss.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <asm/io.h>
#include <asm/system.h>
#include <asm/uaccess.h>
/*====================================================================*/
Massive net driver const-ification.
2006-03-04 10:33:57 +08:00
static const char *if_names[] = { "auto", "10baseT", "10base2"};
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc91c92_cs: use request_firmware Added osi_load_firmware() instead of copying same thing twice Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
2009-03-30 22:49:54 +08:00
/* Firmware name */
#define FIRMWARE_NAME "ositech/Xilinx7OD.bin"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Module parameters */
MODULE_DESCRIPTION("SMC 91c92 series PCMCIA ethernet driver");
MODULE_LICENSE("GPL");
smc91c92_cs: use request_firmware Added osi_load_firmware() instead of copying same thing twice Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
2009-03-30 22:49:54 +08:00
MODULE_FIRMWARE(FIRMWARE_NAME);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#define INT_MODULE_PARM(n, v) static int n = v; module_param(n, int, 0)
/*
Transceiver/media type.
0 = auto
1 = 10baseT (and autoselect if #define AUTOSELECT),
2 = AUI/10base2,
*/
INT_MODULE_PARM(if_port, 0);
#define DRV_NAME "smc91c92_cs"
[PATCH] Remove more unnecessary driver printk's As I promised last week, here is the first pass at removing all unnecessary printk's that exist in network device drivers currently in promiscuous mode. The duplicate messages are not needed so they have been removed. Some of these drivers are quite old and might not need an update, but I did them all anyway. I am currently auditing the remaining conditional printk's and will send out a patch for those soon. Signed-off-by: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-12 05:39:18 +08:00
#define DRV_VERSION "1.123"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*====================================================================*/
/* Operational parameter that usually are not changed. */
/* Time in jiffies before concluding Tx hung */
#define TX_TIMEOUT ((400*HZ)/1000)
/* Maximum events (Rx packets, etc.) to handle at each interrupt. */
#define INTR_WORK 4
/* Times to check the check the chip before concluding that it doesn't
currently have room for another Tx packet. */
#define MEMORY_WAIT_TIME 8
struct smc_private {
[PATCH] pcmcia: embed dev_link_t into struct pcmcia_device Embed dev_link_t into struct pcmcia_device(), as they basically address the same entity. The actual contents of dev_link_t will be cleaned up step by step. This patch includes a bugfix from and signed-off-by Andrew Morton. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-05 17:45:09 +08:00
struct pcmcia_device *p_dev;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
spinlock_t lock;
u_short manfid;
u_short cardid;
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev_node_t node;
struct sk_buff *saved_skb;
int packets_waiting;
void __iomem *base;
u_short cfg;
struct timer_list media;
int watchdog, tx_err;
u_short media_status;
u_short fast_poll;
u_short link_status;
struct mii_if_info mii_if;
int duplex;
int rx_ovrn;
};
/* Special definitions for Megahertz multifunction cards */
#define MEGAHERTZ_ISR 0x0380
/* Special function registers for Motorola Mariner */
#define MOT_LAN 0x0000
#define MOT_UART 0x0020
#define MOT_EEPROM 0x20
#define MOT_NORMAL \
(COR_LEVEL_REQ | COR_FUNC_ENA | COR_ADDR_DECODE | COR_IREQ_ENA)
/* Special function registers for Ositech cards */
#define OSITECH_AUI_CTL 0x0c
#define OSITECH_PWRDOWN 0x0d
#define OSITECH_RESET 0x0e
#define OSITECH_ISR 0x0f
#define OSITECH_AUI_PWR 0x0c
#define OSITECH_RESET_ISR 0x0e
#define OSI_AUI_PWR 0x40
#define OSI_LAN_PWRDOWN 0x02
#define OSI_MODEM_PWRDOWN 0x01
#define OSI_LAN_RESET 0x02
#define OSI_MODEM_RESET 0x01
/* Symbolic constants for the SMC91c9* series chips, from Erik Stahlman. */
#define BANK_SELECT 14 /* Window select register. */
#define SMC_SELECT_BANK(x) { outw(x, ioaddr + BANK_SELECT); }
/* Bank 0 registers. */
#define TCR 0 /* transmit control register */
#define TCR_CLEAR 0 /* do NOTHING */
#define TCR_ENABLE 0x0001 /* if this is 1, we can transmit */
#define TCR_PAD_EN 0x0080 /* pads short packets to 64 bytes */
#define TCR_MONCSN 0x0400 /* Monitor Carrier. */
#define TCR_FDUPLX 0x0800 /* Full duplex mode. */
#define TCR_NORMAL TCR_ENABLE | TCR_PAD_EN
#define EPH 2 /* Ethernet Protocol Handler report. */
#define EPH_TX_SUC 0x0001
#define EPH_SNGLCOL 0x0002
#define EPH_MULCOL 0x0004
#define EPH_LTX_MULT 0x0008
#define EPH_16COL 0x0010
#define EPH_SQET 0x0020
#define EPH_LTX_BRD 0x0040
#define EPH_TX_DEFR 0x0080
#define EPH_LAT_COL 0x0200
#define EPH_LOST_CAR 0x0400
#define EPH_EXC_DEF 0x0800
#define EPH_CTR_ROL 0x1000
#define EPH_RX_OVRN 0x2000
#define EPH_LINK_OK 0x4000
#define EPH_TX_UNRN 0x8000
#define MEMINFO 8 /* Memory Information Register */
#define MEMCFG 10 /* Memory Configuration Register */
/* Bank 1 registers. */
#define CONFIG 0
#define CFG_MII_SELECT 0x8000 /* 91C100 only */
#define CFG_NO_WAIT 0x1000
#define CFG_FULL_STEP 0x0400
#define CFG_SET_SQLCH 0x0200
#define CFG_AUI_SELECT 0x0100
#define CFG_16BIT 0x0080
#define CFG_DIS_LINK 0x0040
#define CFG_STATIC 0x0030
#define CFG_IRQ_SEL_1 0x0004
#define CFG_IRQ_SEL_0 0x0002
#define BASE_ADDR 2
#define ADDR0 4
#define GENERAL 10
#define CONTROL 12
#define CTL_STORE 0x0001
#define CTL_RELOAD 0x0002
#define CTL_EE_SELECT 0x0004
#define CTL_TE_ENABLE 0x0020
#define CTL_CR_ENABLE 0x0040
#define CTL_LE_ENABLE 0x0080
#define CTL_AUTO_RELEASE 0x0800
#define CTL_POWERDOWN 0x2000
/* Bank 2 registers. */
#define MMU_CMD 0
#define MC_ALLOC 0x20 /* or with number of 256 byte packets */
#define MC_RESET 0x40
#define MC_RELEASE 0x80 /* remove and release the current rx packet */
#define MC_FREEPKT 0xA0 /* Release packet in PNR register */
#define MC_ENQUEUE 0xC0 /* Enqueue the packet for transmit */
#define PNR_ARR 2
#define FIFO_PORTS 4
#define FP_RXEMPTY 0x8000
#define POINTER 6
#define PTR_AUTO_INC 0x0040
#define PTR_READ 0x2000
#define PTR_AUTOINC 0x4000
#define PTR_RCV 0x8000
#define DATA_1 8
#define INTERRUPT 12
#define IM_RCV_INT 0x1
#define IM_TX_INT 0x2
#define IM_TX_EMPTY_INT 0x4
#define IM_ALLOC_INT 0x8
#define IM_RX_OVRN_INT 0x10
#define IM_EPH_INT 0x20
#define RCR 4
enum RxCfg { RxAllMulti = 0x0004, RxPromisc = 0x0002,
RxEnable = 0x0100, RxStripCRC = 0x0200};
#define RCR_SOFTRESET 0x8000 /* resets the chip */
#define RCR_STRIP_CRC 0x200 /* strips CRC */
#define RCR_ENABLE 0x100 /* IFF this is set, we can receive packets */
#define RCR_ALMUL 0x4 /* receive all multicast packets */
#define RCR_PROMISC 0x2 /* enable promiscuous mode */
/* the normal settings for the RCR register : */
#define RCR_NORMAL (RCR_STRIP_CRC | RCR_ENABLE)
#define RCR_CLEAR 0x0 /* set it to a base state */
#define COUNTER 6
/* BANK 3 -- not the same values as in smc9194! */
#define MULTICAST0 0
#define MULTICAST2 2
#define MULTICAST4 4
#define MULTICAST6 6
#define MGMT 8
#define REVISION 0x0a
/* Transmit status bits. */
#define TS_SUCCESS 0x0001
#define TS_16COL 0x0010
#define TS_LATCOL 0x0200
#define TS_LOSTCAR 0x0400
/* Receive status bits. */
#define RS_ALGNERR 0x8000
#define RS_BADCRC 0x2000
#define RS_ODDFRAME 0x1000
#define RS_TOOLONG 0x0800
#define RS_TOOSHORT 0x0400
#define RS_MULTICAST 0x0001
#define RS_ERRORS (RS_ALGNERR | RS_BADCRC | RS_TOOLONG | RS_TOOSHORT)
#define set_bits(v, p) outw(inw(p)|(v), (p))
#define mask_bits(v, p) outw(inw(p)&(v), (p))
/*====================================================================*/
[PATCH] pcmcia: unify detach, REMOVAL_EVENT handlers into one remove callback Unify the "detach" and REMOVAL_EVENT handlers to one "remove" function. Old functionality is preserved, for the moment. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:23:14 +08:00
static void smc91c92_detach(struct pcmcia_device *p_dev);
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
static int smc91c92_config(struct pcmcia_device *link);
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static void smc91c92_release(struct pcmcia_device *link);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
static int smc_open(struct net_device *dev);
static int smc_close(struct net_device *dev);
static int smc_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
static void smc_tx_timeout(struct net_device *dev);
netdev: convert pcmcia drivers to netdev_tx_t Update all the pcmcia network drivers for netdev_tx_t. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-01 03:50:49 +08:00
static netdev_tx_t smc_start_xmit(struct sk_buff *skb,
struct net_device *dev);
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
static irqreturn_t smc_interrupt(int irq, void *dev_id);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
static void smc_rx(struct net_device *dev);
static void set_rx_mode(struct net_device *dev);
static int s9k_config(struct net_device *dev, struct ifmap *map);
static void smc_set_xcvr(struct net_device *dev, int if_port);
static void smc_reset(struct net_device *dev);
static void media_check(u_long arg);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
static void mdio_sync(unsigned int addr);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
static int mdio_read(struct net_device *dev, int phy_id, int loc);
static void mdio_write(struct net_device *dev, int phy_id, int loc, int value);
static int smc_link_ok(struct net_device *dev);
drivers/net: const-ify ethtool_ops declarations Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 02:30:00 +08:00
static const struct ethtool_ops ethtool_ops;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc91c92: convert to net_device_ops Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:10 +08:00
static const struct net_device_ops smc_netdev_ops = {
.ndo_open = smc_open,
.ndo_stop = smc_close,
.ndo_start_xmit = smc_start_xmit,
.ndo_tx_timeout = smc_tx_timeout,
.ndo_set_config = s9k_config,
.ndo_set_multicast_list = set_rx_mode,
.ndo_do_ioctl = &smc_ioctl,
.ndo_change_mtu = eth_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*======================================================================
smc91c92_attach() creates an "instance" of the driver, allocating
local data structures for one device. The device is registered
with Card Services.
======================================================================*/
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
static int smc91c92_probe(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct smc_private *smc;
struct net_device *dev;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "smc91c92_attach()\n");
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Create new ethernet device */
dev = alloc_etherdev(sizeof(struct smc_private));
if (!dev)
[PATCH] pcmcia: unify attach, EVENT_CARD_INSERTION handlers into one probe callback Unify the EVENT_CARD_INSERTION and "attach" callbacks to one unified probe() callback. As all in-kernel drivers are changed to this new callback, there will be no temporary backwards-compatibility. Inside a probe() function, each driver _must_ set struct pcmcia_device *p_dev->instance and instance->handle correctly. With these patches, the basic driver interface for 16-bit PCMCIA drivers now has the classic four callbacks known also from other buses: int (*probe) (struct pcmcia_device *dev); void (*remove) (struct pcmcia_device *dev); int (*suspend) (struct pcmcia_device *dev); int (*resume) (struct pcmcia_device *dev); Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:25:51 +08:00
return -ENOMEM;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc = netdev_priv(dev);
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
smc->p_dev = link;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
link->priv = dev;
spin_lock_init(&smc->lock);
link->io.NumPorts1 = 16;
link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO;
link->io.IOAddrLines = 4;
pcmcia: rework the irq_req_t typedef Most of the irq_req_t typedef'd struct can be re-worked quite easily: (1) IRQInfo2 was unused in any case, so drop it. (2) IRQInfo1 was used write-only, so drop it. (3) Instance (private data to be passed to the IRQ handler): Most PCMCIA drivers using pcmcia_request_irq() to actually register an IRQ handler set the "dev_id" to the same pointer as the "priv" pointer in struct pcmcia_device. Modify the two exceptions (ipwireless, ibmtr_cs) to also work this waym and set the IRQ handler's "dev_id" to p_dev->priv unconditionally. (4) Handler is to be of type irq_handler_t. (5) Handler != NULL already tells whether an IRQ handler is present. Therefore, we do not need the IRQ_HANDLER_PRESENT flag in irq_req_t.Attributes. CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-ide@vger.kernel.org CC: linux-wireless@vger.kernel.org CC: linux-scsi@vger.kernel.org CC: alsa-devel@alsa-project.org CC: Jaroslav Kysela <perex@perex.cz> CC: Jiri Kosina <jkosina@suse.cz> CC: Karsten Keil <isdn@linux-pingi.de> for the Bluetooth parts: Acked-by: Marcel Holtmann <marcel@holtmann.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-11-09 00:24:46 +08:00
link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
link->irq.Handler = &smc_interrupt;
link->conf.Attributes = CONF_ENABLE_IRQ;
link->conf.IntType = INT_MEMORY_AND_IO;
/* The SMC91c92-specific entries in the device structure. */
smc91c92: convert to net_device_ops Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:10 +08:00
dev->netdev_ops = &smc_netdev_ops;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
SET_ETHTOOL_OPS(dev, &ethtool_ops);
dev->watchdog_timeo = TX_TIMEOUT;
smc->mii_if.dev = dev;
smc->mii_if.mdio_read = mdio_read;
smc->mii_if.mdio_write = mdio_write;
smc->mii_if.phy_id_mask = 0x1f;
smc->mii_if.reg_num_mask = 0x1f;
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
return smc91c92_config(link);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} /* smc91c92_attach */
/*======================================================================
This deletes a driver "instance". The device is de-registered
with Card Services. If it has been released, all local data
structures are freed. Otherwise, the structures will be freed
when the device is released.
======================================================================*/
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static void smc91c92_detach(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "smc91c92_detach\n");
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[PATCH] pcmcia: embed dev_link_t into struct pcmcia_device Embed dev_link_t into struct pcmcia_device(), as they basically address the same entity. The actual contents of dev_link_t will be cleaned up step by step. This patch includes a bugfix from and signed-off-by Andrew Morton. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-05 17:45:09 +08:00
if (link->dev_node)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
unregister_netdev(dev);
[PATCH] pcmcia: use bitfield instead of p_state and state Instead of the two status values struct pcmcia_device->p_state and state, use descriptive bitfields. Most value-checking in drivers was invalid, as the core now only calls the ->remove() (a.k.a. detach) function in case the attachement _and_ configuration was successful. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-02 07:09:29 +08:00
smc91c92_release(link);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
free_netdev(dev);
} /* smc91c92_detach */
/*====================================================================*/
static int cvt_ascii_address(struct net_device *dev, char *s)
{
int i, j, da, c;
if (strlen(s) != 12)
return -1;
for (i = 0; i < 6; i++) {
da = 0;
for (j = 0; j < 2; j++) {
c = *s++;
da <<= 4;
da += ((c >= '0') && (c <= '9')) ?
(c - '0') : ((c & 0x0f) + 9);
}
dev->dev_addr[i] = da;
}
return 0;
}
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
/*====================================================================
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
Configuration stuff for Megahertz cards
mhz_3288_power() is used to power up a 3288's ethernet chip.
mhz_mfc_config() handles socket setup for multifunction (1144
and 3288) cards. mhz_setup() gets a card's hardware ethernet
address.
======================================================================*/
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int mhz_3288_power(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
struct smc_private *smc = netdev_priv(dev);
u_char tmp;
/* Read the ISR twice... */
readb(smc->base+MEGAHERTZ_ISR);
udelay(5);
readb(smc->base+MEGAHERTZ_ISR);
/* Pause 200ms... */
mdelay(200);
/* Now read and write the COR... */
tmp = readb(smc->base + link->conf.ConfigBase + CISREG_COR);
udelay(5);
writeb(tmp, smc->base + link->conf.ConfigBase + CISREG_COR);
return 0;
}
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
static int mhz_mfc_config_check(struct pcmcia_device *p_dev,
cistpl_cftable_entry_t *cf,
pcmcia: pcmcia_config_loop() default CIS entry handling Many drivers use the default CIS entry within their pcmcia_config_loop() callback function. Therefore, factor the default CIS entry handling out. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 21:30:31 +08:00
cistpl_cftable_entry_t *dflt,
pcmcia: pcmcia_config_loop() improvement by passing vcc By passing the current Vcc setting to the pcmcia_config_loop callback function, we can remove pcmcia_get_configuration_info() calls from many drivers. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 22:12:00 +08:00
unsigned int vcc,
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
void *priv_data)
{
int k;
p_dev->io.BasePort2 = cf->io.win[0].base;
for (k = 0; k < 0x400; k += 0x10) {
if (k & 0x80)
continue;
p_dev->io.BasePort1 = k ^ 0x300;
if (!pcmcia_request_io(p_dev, &p_dev->io))
return 0;
}
return -ENODEV;
}
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int mhz_mfc_config(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
struct smc_private *smc = netdev_priv(dev);
win_req_t req;
memreq_t mem;
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
int i;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
link->conf.Attributes |= CONF_ENABLE_SPKR;
link->conf.Status = CCSR_AUDIO_ENA;
pcmcia: remove remaining unused IRQ_FIRST_SHARED parameter Komuro pointed out correctly that I missed one IRQ_FIRST_SHARED parameter in smc91c92_cs.c, and that another line could be writter more beautifully. CC: netdev@vger.kernel.org CC: Komuro <komurojun-mbn@nifty.com> Tested-by: Wolfram Sang <w.sang@pengutronix.de> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2010-01-02 00:43:08 +08:00
link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
link->io.IOAddrLines = 16;
link->io.Attributes2 = IO_DATA_PATH_WIDTH_8;
link->io.NumPorts2 = 8;
/* The Megahertz combo cards have modem-like CIS entries, so
we have to explicitly try a bunch of port combinations. */
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
if (pcmcia_loop_config(link, mhz_mfc_config_check, NULL))
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return -ENODEV;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev->base_addr = link->io.BasePort1;
/* Allocate a memory window, for accessing the ISR */
req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
req.Base = req.Size = 0;
req.AccessSpeed = 0;
pcmcia: pcmcia_request_window() doesn't need a pointer to a pointer pcmcia_request_window() only needs a pointer to struct pcmcia_device, not a pointer to a pointer. CC: netdev@vger.kernel.org CC: linux-wireless@vger.kernel.org CC: linux-scsi@vger.kernel.org CC: Jiri Kosina <jkosina@suse.cz> Acked-by: Karsten Keil <keil@b1-systems.de> (for ISDN) Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-11-03 08:31:52 +08:00
i = pcmcia_request_window(link, &req, &link->win);
pcmcia: deprecate CS_SUCCESS Instead of using own error or success codes, the PCMCIA code should rely on the generic return values. Therefore, replace all occurrences of CS_SUCCESS with 0. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-03 16:07:45 +08:00
if (i != 0)
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return -ENODEV;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc->base = ioremap(req.Base, req.Size);
mem.CardOffset = mem.Page = 0;
if (smc->manfid == MANFID_MOTOROLA)
mem.CardOffset = link->conf.ConfigBase;
pcmcia: Pass struct pcmcia_device to pcmcia_map_mem_page() No logic changes, just pass struct pcmcia_device to pcmcia_map_mem_page() [linux@dominikbrodowski.net: update to 2.6.31] CC: netdev@vger.kernel.org CC: linux-wireless@vger.kernel.org CC: linux-scsi@vger.kernel.org CC: Jiri Kosina <jkosina@suse.cz> Acked-by: Karsten Keil <keil@b1-systems.de> (for ISDN) Signed-off-by: Magnus Damm <damm@opensource.se> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-12-13 18:46:43 +08:00
i = pcmcia_map_mem_page(link, link->win, &mem);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
drivers/net: Move && and || to end of previous line Only files where David Miller is the primary git-signer. wireless, wimax, ixgbe, etc are not modified. Compile tested x86 allyesconfig only Not all files compiled (not x86 compatible) Added a few > 80 column lines, which I ignored. Existing checkpatch complaints ignored. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 15:58:21 +08:00
if ((i == 0) &&
(smc->manfid == MANFID_MEGAHERTZ) &&
(smc->cardid == PRODID_MEGAHERTZ_EM3288))
mhz_3288_power(link);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
static int pcmcia_get_versmac(struct pcmcia_device *p_dev,
tuple_t *tuple,
void *priv)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
struct net_device *dev = priv;
cisparse_t parse;
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if (pcmcia_parse_tuple(tuple, &parse))
return -EINVAL;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if ((parse.version_1.ns > 3) &&
(cvt_ascii_address(dev,
(parse.version_1.str + parse.version_1.ofs[3]))))
return 0;
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return -EINVAL;
};
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int mhz_setup(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
size_t len;
u8 *buf;
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
int rc;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Read the station address from the CIS. It is stored as the last
(fourth) string in the Version 1 Version/ID tuple. */
pcmcia: use pre-determined values A few PCMCIA network drivers can make use of values provided by the pcmcia core, instead of tedious, independent CIS parsing. xirc32ps_cs.c: manf_id hostap_cs.c: multifunction count b43/pcmcia.c: ConfigBase address and "Present" smc91c92_cs.c: By default, mhz_setup() can use VERS_1 as it is stored in struct pcmcia_device. Only some cards require workarounds, such as reading out VERS_1 twice. CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org CC: linux-wireless@vger.kernel.org Acked-by: John W. Linville <linville@tuxdriver.com> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 00:22:32 +08:00
if ((link->prod_id[3]) &&
(cvt_ascii_address(dev, link->prod_id[3]) == 0))
return 0;
/* Workarounds for broken cards start here. */
Fix station address detection in smc Megahertz EM1144 PCMCIA ethernet adapter needs special handling because it has two VERS_1 tuples and the station address is in the second one. Conversion to generic handling of these fields broke it. Reverting that fixes the device. https://bugzilla.redhat.com/show_bug.cgi?id=233255 Thanks go to Jon Stanley for not giving up on this one until the problem was found. Signed-off-by: Chuck Ebbert <cebbert@redhat.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2008-02-14 08:47:11 +08:00
/* Ugh -- the EM1144 card has two VERS_1 tuples!?! */
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if (!pcmcia_loop_tuple(link, CISTPL_VERS_1, pcmcia_get_versmac, dev))
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Another possibility: for the EM3288, in a special tuple */
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
rc = -1;
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
len = pcmcia_get_tuple(link, 0x81, &buf);
if (buf && len >= 13) {
buf[12] = '\0';
if (cvt_ascii_address(dev, buf))
rc = 0;
}
kfree(buf);
return rc;
};
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*======================================================================
Configuration stuff for the Motorola Mariner
mot_config() writes directly to the Mariner configuration
registers because the CIS is just bogus.
======================================================================*/
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static void mot_config(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
unsigned int iouart = link->io.BasePort2;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Set UART base address and force map with COR bit 1 */
writeb(iouart & 0xff, smc->base + MOT_UART + CISREG_IOBASE_0);
writeb((iouart >> 8) & 0xff, smc->base + MOT_UART + CISREG_IOBASE_1);
writeb(MOT_NORMAL, smc->base + MOT_UART + CISREG_COR);
/* Set SMC base address and force map with COR bit 1 */
writeb(ioaddr & 0xff, smc->base + MOT_LAN + CISREG_IOBASE_0);
writeb((ioaddr >> 8) & 0xff, smc->base + MOT_LAN + CISREG_IOBASE_1);
writeb(MOT_NORMAL, smc->base + MOT_LAN + CISREG_COR);
/* Wait for things to settle down */
mdelay(100);
}
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int mot_setup(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
int i, wait, loop;
u_int addr;
/* Read Ethernet address from Serial EEPROM */
for (i = 0; i < 3; i++) {
SMC_SELECT_BANK(2);
outw(MOT_EEPROM + i, ioaddr + POINTER);
SMC_SELECT_BANK(1);
outw((CTL_RELOAD | CTL_EE_SELECT), ioaddr + CONTROL);
for (loop = wait = 0; loop < 200; loop++) {
udelay(10);
wait = ((CTL_RELOAD | CTL_STORE) & inw(ioaddr + CONTROL));
if (wait == 0) break;
}
if (wait)
return -1;
addr = inw(ioaddr + GENERAL);
dev->dev_addr[2*i] = addr & 0xff;
dev->dev_addr[2*i+1] = (addr >> 8) & 0xff;
}
return 0;
}
/*====================================================================*/
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
static int smc_configcheck(struct pcmcia_device *p_dev,
cistpl_cftable_entry_t *cf,
pcmcia: pcmcia_config_loop() default CIS entry handling Many drivers use the default CIS entry within their pcmcia_config_loop() callback function. Therefore, factor the default CIS entry handling out. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 21:30:31 +08:00
cistpl_cftable_entry_t *dflt,
pcmcia: pcmcia_config_loop() improvement by passing vcc By passing the current Vcc setting to the pcmcia_config_loop callback function, we can remove pcmcia_get_configuration_info() calls from many drivers. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 22:12:00 +08:00
unsigned int vcc,
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
void *priv_data)
{
p_dev->io.BasePort1 = cf->io.win[0].base;
p_dev->io.IOAddrLines = cf->io.flags & CISTPL_IO_LINES_MASK;
return pcmcia_request_io(p_dev, &p_dev->io);
}
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int smc_config(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
int i;
link->io.NumPorts1 = 16;
pcmcia: use pcmcia_loop_config in net pcmcia drivers Use the config loop helper in (some) net pcmcia drivers. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-02 20:28:43 +08:00
i = pcmcia_loop_config(link, smc_configcheck, NULL);
if (!i)
dev->base_addr = link->io.BasePort1;
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return i;
}
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int smc_setup(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
/* Check for a LAN function extension tuple */
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if (!pcmcia_get_mac_from_cis(link, dev))
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Try the third string in the Version 1 Version/ID tuple. */
[PATCH] pcmcia: remove prod_id indirection As we read out the product information strings (VERS_1) from the PCMCIA device in the PCMCIA core, and device drivers can access those reliably in struct pcmcia_device's fields prod_id[], remove additional product information string detection logic from PCMCIA device drivers. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-06-05 00:06:13 +08:00
if (link->prod_id[2]) {
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if (cvt_ascii_address(dev, link->prod_id[2]) == 0)
return 0;
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
}
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return -1;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/*====================================================================*/
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int osi_config(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
static const unsigned int com[4] = { 0x3f8, 0x2f8, 0x3e8, 0x2e8 };
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
int i, j;
link->conf.Attributes |= CONF_ENABLE_SPKR;
link->conf.Status = CCSR_AUDIO_ENA;
pcmcia: remove remaining unused IRQ_FIRST_SHARED parameter Komuro pointed out correctly that I missed one IRQ_FIRST_SHARED parameter in smc91c92_cs.c, and that another line could be writter more beautifully. CC: netdev@vger.kernel.org CC: Komuro <komurojun-mbn@nifty.com> Tested-by: Wolfram Sang <w.sang@pengutronix.de> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2010-01-02 00:43:08 +08:00
link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
link->io.NumPorts1 = 64;
link->io.Attributes2 = IO_DATA_PATH_WIDTH_8;
link->io.NumPorts2 = 8;
link->io.IOAddrLines = 16;
/* Enable Hard Decode, LAN, Modem */
link->conf.ConfigIndex = 0x23;
for (i = j = 0; j < 4; j++) {
link->io.BasePort2 = com[j];
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
i = pcmcia_request_io(link, &link->io);
pcmcia: deprecate CS_SUCCESS Instead of using own error or success codes, the PCMCIA code should rely on the generic return values. Therefore, replace all occurrences of CS_SUCCESS with 0. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-03 16:07:45 +08:00
if (i == 0)
break;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
pcmcia: deprecate CS_SUCCESS Instead of using own error or success codes, the PCMCIA code should rely on the generic return values. Therefore, replace all occurrences of CS_SUCCESS with 0. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2008-08-03 16:07:45 +08:00
if (i != 0) {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Fallback: turn off hard decode */
link->conf.ConfigIndex = 0x03;
link->io.NumPorts2 = 0;
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
i = pcmcia_request_io(link, &link->io);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
dev->base_addr = link->io.BasePort1 + 0x10;
return i;
}
smc91c92_cs: use request_firmware Added osi_load_firmware() instead of copying same thing twice Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
2009-03-30 22:49:54 +08:00
static int osi_load_firmware(struct pcmcia_device *link)
{
const struct firmware *fw;
int i, err;
err = request_firmware(&fw, FIRMWARE_NAME, &link->dev);
if (err) {
pr_err("Failed to load firmware \"%s\"\n", FIRMWARE_NAME);
return err;
}
/* Download the Seven of Diamonds firmware */
for (i = 0; i < fw->size; i++) {
outb(fw->data[i], link->io.BasePort1 + 2);
udelay(50);
}
release_firmware(fw);
return err;
}
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
static int pcmcia_osi_mac(struct pcmcia_device *p_dev,
tuple_t *tuple,
void *priv)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
struct net_device *dev = priv;
int i;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if (tuple->TupleDataLen < 8)
return -EINVAL;
if (tuple->TupleData[0] != 0x04)
return -EINVAL;
for (i = 0; i < 6; i++)
dev->dev_addr[i] = tuple->TupleData[i+2];
return 0;
};
[PATCH] smc91c92_cs: Reduce stack usage in smc91c92_event() This patch reduces the stack usage of the function smc91c92_event() in smc91c92_cs driver from 3540 to 132. Currently this is the highest stack user in linux-2.6.12-rc2-mm3. I used a patched version of gcc 3.4.3 on i386 with -fno-unit-at-a-time disabled. The patch has only been compile tested. Acked-by: Jrn Engel <joern@wohnheim.fh-wedel.de> Acked-by: Randy Dunlap <rddunlap@osdl.org> Signed-off-by: Yum Rayan <yum.rayan@gmail.com> Cc: Jeff Garzik <jgarzik@pobox.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-05-06 06:14:10 +08:00
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
static int osi_setup(struct pcmcia_device *link, u_short manfid, u_short cardid)
{
struct net_device *dev = link->priv;
int rc;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Read the station address from tuple 0x90, subtuple 0x04 */
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
if (pcmcia_loop_tuple(link, 0x90, pcmcia_osi_mac, dev))
return -1;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (((manfid == MANFID_OSITECH) &&
(cardid == PRODID_OSITECH_SEVEN)) ||
((manfid == MANFID_PSION) &&
(cardid == PRODID_PSION_NET100))) {
smc91c92_cs: use request_firmware Added osi_load_firmware() instead of copying same thing twice Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
2009-03-30 22:49:54 +08:00
rc = osi_load_firmware(link);
if (rc)
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return rc;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} else if (manfid == MANFID_OSITECH) {
/* Make sure both functions are powered up */
set_bits(0x300, link->io.BasePort1 + OSITECH_AUI_PWR);
/* Now, turn on the interrupt for both card functions */
set_bits(0x300, link->io.BasePort1 + OSITECH_RESET_ISR);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "AUI/PWR: %4.4x RESET/ISR: %4.4x\n",
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
inw(link->io.BasePort1 + OSITECH_AUI_PWR),
inw(link->io.BasePort1 + OSITECH_RESET_ISR));
}
pcmcia: convert net pcmcia drivers to use new CIS helpers Use the new CIS helpers in net pcmcia drivers, which allows for a few code cleanups. This revision does not remove the phys_addr assignment in 3c589_cs.c -- a bug noted by Komuro <komurojun-mbn@nifty.com> CC: David S. Miller <davem@davemloft.net> CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-19 05:54:24 +08:00
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int smc91c92_suspend(struct pcmcia_device *link)
[PATCH] pcmcia: new suspend core Move the suspend and resume methods out of the event handler, and into special functions. Also use these functions for pre- and post-reset, as almost all drivers already do, and the remaining ones can easily be converted. Bugfix to include/pcmcia/ds.c Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:21:18 +08:00
{
struct net_device *dev = link->priv;
[PATCH] pcmcia: use bitfield instead of p_state and state Instead of the two status values struct pcmcia_device->p_state and state, use descriptive bitfields. Most value-checking in drivers was invalid, as the core now only calls the ->remove() (a.k.a. detach) function in case the attachement _and_ configuration was successful. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-02 07:09:29 +08:00
if (link->open)
[PATCH] pcmcia: remove export of pcmcia_release_configuration Handle the _modifying_ operation sm91c92_cs requires in pcmcia_modify_configuration, so that the only remaining users of pcmcia_release_configuration() are within the pcmcia core module. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-01-15 18:18:12 +08:00
netif_device_detach(dev);
[PATCH] pcmcia: new suspend core Move the suspend and resume methods out of the event handler, and into special functions. Also use these functions for pre- and post-reset, as almost all drivers already do, and the remaining ones can easily be converted. Bugfix to include/pcmcia/ds.c Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:21:18 +08:00
return 0;
}
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int smc91c92_resume(struct pcmcia_device *link)
[PATCH] pcmcia: new suspend core Move the suspend and resume methods out of the event handler, and into special functions. Also use these functions for pre- and post-reset, as almost all drivers already do, and the remaining ones can easily be converted. Bugfix to include/pcmcia/ds.c Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:21:18 +08:00
{
struct net_device *dev = link->priv;
struct smc_private *smc = netdev_priv(dev);
int i;
[PATCH] pcmcia: use bitfield instead of p_state and state Instead of the two status values struct pcmcia_device->p_state and state, use descriptive bitfields. Most value-checking in drivers was invalid, as the core now only calls the ->remove() (a.k.a. detach) function in case the attachement _and_ configuration was successful. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-02 07:09:29 +08:00
if ((smc->manfid == MANFID_MEGAHERTZ) &&
(smc->cardid == PRODID_MEGAHERTZ_EM3288))
mhz_3288_power(link);
if (smc->manfid == MANFID_MOTOROLA)
mot_config(link);
if ((smc->manfid == MANFID_OSITECH) &&
(smc->cardid != PRODID_OSITECH_SEVEN)) {
/* Power up the card and enable interrupts */
set_bits(0x0300, dev->base_addr-0x10+OSITECH_AUI_PWR);
set_bits(0x0300, dev->base_addr-0x10+OSITECH_RESET_ISR);
}
if (((smc->manfid == MANFID_OSITECH) &&
(smc->cardid == PRODID_OSITECH_SEVEN)) ||
((smc->manfid == MANFID_PSION) &&
(smc->cardid == PRODID_PSION_NET100))) {
smc91c92_cs: use request_firmware Added osi_load_firmware() instead of copying same thing twice Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
2009-03-30 22:49:54 +08:00
i = osi_load_firmware(link);
if (i) {
pr_err("smc91c92_cs: Failed to load firmware\n");
return i;
[PATCH] pcmcia: new suspend core Move the suspend and resume methods out of the event handler, and into special functions. Also use these functions for pre- and post-reset, as almost all drivers already do, and the remaining ones can easily be converted. Bugfix to include/pcmcia/ds.c Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:21:18 +08:00
}
}
[PATCH] pcmcia: use bitfield instead of p_state and state Instead of the two status values struct pcmcia_device->p_state and state, use descriptive bitfields. Most value-checking in drivers was invalid, as the core now only calls the ->remove() (a.k.a. detach) function in case the attachement _and_ configuration was successful. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-02 07:09:29 +08:00
if (link->open) {
smc_reset(dev);
netif_device_attach(dev);
}
[PATCH] pcmcia: new suspend core Move the suspend and resume methods out of the event handler, and into special functions. Also use these functions for pre- and post-reset, as almost all drivers already do, and the remaining ones can easily be converted. Bugfix to include/pcmcia/ds.c Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:21:18 +08:00
return 0;
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*======================================================================
This verifies that the chip is some SMC91cXX variant, and returns
the revision code if successful. Otherwise, it returns -ENODEV.
======================================================================*/
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static int check_sig(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
int width;
u_short s;
SMC_SELECT_BANK(1);
if (inw(ioaddr + BANK_SELECT) >> 8 != 0x33) {
/* Try powering up the chip */
outw(0, ioaddr + CONTROL);
mdelay(55);
}
/* Try setting bus width */
width = (link->io.Attributes1 == IO_DATA_PATH_WIDTH_AUTO);
s = inb(ioaddr + CONFIG);
if (width)
s |= CFG_16BIT;
else
s &= ~CFG_16BIT;
outb(s, ioaddr + CONFIG);
/* Check Base Address Register to make sure bus width is OK */
s = inw(ioaddr + BASE_ADDR);
if ((inw(ioaddr + BANK_SELECT) >> 8 == 0x33) &&
((s >> 8) != (s & 0xff))) {
SMC_SELECT_BANK(3);
s = inw(ioaddr + REVISION);
return (s & 0xff);
}
if (width) {
[PATCH] pcmcia: remove export of pcmcia_release_configuration Handle the _modifying_ operation sm91c92_cs requires in pcmcia_modify_configuration, so that the only remaining users of pcmcia_release_configuration() are within the pcmcia core module. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-01-15 18:18:12 +08:00
modconf_t mod = {
.Attributes = CONF_IO_CHANGE_WIDTH,
};
printk(KERN_INFO "smc91c92_cs: using 8-bit IO window.\n");
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
smc91c92_suspend(link);
pcmcia_modify_configuration(link, &mod);
smc91c92_resume(link);
[PATCH] pcmcia: remove export of pcmcia_release_configuration Handle the _modifying_ operation sm91c92_cs requires in pcmcia_modify_configuration, so that the only remaining users of pcmcia_release_configuration() are within the pcmcia core module. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-01-15 18:18:12 +08:00
return check_sig(link);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
return -ENODEV;
}
/*======================================================================
smc91c92_config() is scheduled to run after a CARD_INSERTION event
is received, to configure the PCMCIA socket, and to make the
ethernet device available to the system.
======================================================================*/
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
static int smc91c92_config(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = link->priv;
struct smc_private *smc = netdev_priv(dev);
char *name;
int i, j, rev;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_long mir;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "smc91c92_config\n");
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[PATCH] pcmcia: remove manf_id and card_id indirection As we read out the manufactor and card_id from the PCMCIA device in the PCMCIA core, and device drivers can access those reliably in struct pcmcia_device's fields manf_id and card_id, remove additional (and partly broken) manf_id and card_id detection logic from PCMCIA device drivers. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-10-26 09:28:53 +08:00
smc->manfid = link->manf_id;
smc->cardid = link->card_id;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if ((smc->manfid == MANFID_OSITECH) &&
(smc->cardid != PRODID_OSITECH_SEVEN)) {
i = osi_config(link);
} else if ((smc->manfid == MANFID_MOTOROLA) ||
((smc->manfid == MANFID_MEGAHERTZ) &&
((smc->cardid == PRODID_MEGAHERTZ_VARIOUS) ||
(smc->cardid == PRODID_MEGAHERTZ_EM3288)))) {
i = mhz_mfc_config(link);
} else {
i = smc_config(link);
}
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
if (i)
goto config_failed;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
i = pcmcia_request_irq(link, &link->irq);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
if (i)
goto config_failed;
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
i = pcmcia_request_configuration(link, &link->conf);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
if (i)
goto config_failed;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (smc->manfid == MANFID_MOTOROLA)
mot_config(link);
dev->irq = link->irq.AssignedIRQ;
if ((if_port >= 0) && (if_port <= 2))
dev->if_port = if_port;
else
printk(KERN_NOTICE "smc91c92_cs: invalid if_port requested\n");
switch (smc->manfid) {
case MANFID_OSITECH:
case MANFID_PSION:
i = osi_setup(link, smc->manfid, smc->cardid); break;
case MANFID_SMC:
case MANFID_NEW_MEDIA:
i = smc_setup(link); break;
case 0x128: /* For broken Megahertz cards */
case MANFID_MEGAHERTZ:
i = mhz_setup(link); break;
case MANFID_MOTOROLA:
default: /* get the hw address from EEPROM */
i = mot_setup(link); break;
}
if (i != 0) {
printk(KERN_NOTICE "smc91c92_cs: Unable to find hardware address.\n");
goto config_undo;
}
smc->duplex = 0;
smc->rx_ovrn = 0;
rev = check_sig(link);
name = "???";
if (rev > 0)
switch (rev >> 4) {
case 3: name = "92"; break;
case 4: name = ((rev & 15) >= 6) ? "96" : "94"; break;
case 5: name = "95"; break;
case 7: name = "100"; break;
case 8: name = "100-FD"; break;
case 9: name = "110"; break;
}
ioaddr = dev->base_addr;
if (rev > 0) {
u_long mcr;
SMC_SELECT_BANK(0);
mir = inw(ioaddr + MEMINFO) & 0xff;
if (mir == 0xff) mir++;
/* Get scale factor for memory size */
mcr = ((rev >> 4) > 3) ? inw(ioaddr + MEMCFG) : 0x0200;
mir *= 128 * (1<<((mcr >> 9) & 7));
SMC_SELECT_BANK(1);
smc->cfg = inw(ioaddr + CONFIG) & ~CFG_AUI_SELECT;
smc->cfg |= CFG_NO_WAIT | CFG_16BIT | CFG_STATIC;
if (smc->manfid == MANFID_OSITECH)
smc->cfg |= CFG_IRQ_SEL_1 | CFG_IRQ_SEL_0;
if ((rev >> 4) >= 7)
smc->cfg |= CFG_MII_SELECT;
} else
mir = 0;
if (smc->cfg & CFG_MII_SELECT) {
SMC_SELECT_BANK(3);
for (i = 0; i < 32; i++) {
j = mdio_read(dev, i, 1);
if ((j != 0) && (j != 0xffff)) break;
}
smc->mii_if.phy_id = (i < 32) ? i : -1;
SMC_SELECT_BANK(0);
}
[PATCH] pcmcia: embed dev_link_t into struct pcmcia_device Embed dev_link_t into struct pcmcia_device(), as they basically address the same entity. The actual contents of dev_link_t will be cleaned up step by step. This patch includes a bugfix from and signed-off-by Andrew Morton. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-05 17:45:09 +08:00
link->dev_node = &smc->node;
pcmcia: remove deprecated handle_to_dev() macro Update remaining users and remove deprecated handle_to_dev() macro CC: Harald Welte <laforge@gnumonks.org> CC: netdev@vger.kernel.org CC: linux-wireless@vger.kernel.org CC: linux-serial@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-11-03 17:27:34 +08:00
SET_NETDEV_DEV(dev, &link->dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (register_netdev(dev) != 0) {
printk(KERN_ERR "smc91c92_cs: register_netdev() failed\n");
[PATCH] pcmcia: embed dev_link_t into struct pcmcia_device Embed dev_link_t into struct pcmcia_device(), as they basically address the same entity. The actual contents of dev_link_t will be cleaned up step by step. This patch includes a bugfix from and signed-off-by Andrew Morton. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-05 17:45:09 +08:00
link->dev_node = NULL;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
goto config_undo;
}
strcpy(smc->node.dev_name, dev->name);
printk(KERN_INFO "%s: smc91c%s rev %d: io %#3lx, irq %d, "
net: convert print_mac to %pM This converts pretty much everything to print_mac. There were a few things that had conflicts which I have just dropped for now, no harm done. I've built an allyesconfig with this and looked at the files that weren't built very carefully, but it's a huge patch. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-28 06:59:26 +08:00
"hw_addr %pM\n",
[NET]: Introduce and use print_mac() and DECLARE_MAC_BUF() This is nicer than the MAC_FMT stuff. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:59:30 +08:00
dev->name, name, (rev & 0x0f), dev->base_addr, dev->irq,
net: convert print_mac to %pM This converts pretty much everything to print_mac. There were a few things that had conflicts which I have just dropped for now, no harm done. I've built an allyesconfig with this and looked at the files that weren't built very carefully, but it's a huge patch. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-28 06:59:26 +08:00
dev->dev_addr);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (rev > 0) {
if (mir & 0x3ff)
printk(KERN_INFO " %lu byte", mir);
else
printk(KERN_INFO " %lu kb", mir>>10);
printk(" buffer, %s xcvr\n", (smc->cfg & CFG_MII_SELECT) ?
"MII" : if_names[dev->if_port]);
}
if (smc->cfg & CFG_MII_SELECT) {
if (smc->mii_if.phy_id != -1) {
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, " MII transceiver at index %d, status %x.\n",
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc->mii_if.phy_id, j);
} else {
printk(KERN_NOTICE " No MII transceivers found!\n");
}
}
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
config_undo:
unregister_netdev(dev);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
config_failed:
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc91c92_release(link);
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
return -ENODEV;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} /* smc91c92_config */
/*======================================================================
After a card is removed, smc91c92_release() will unregister the net
device, and release the PCMCIA configuration. If the device is
still open, this will be postponed until it is closed.
======================================================================*/
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
static void smc91c92_release(struct pcmcia_device *link)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "smc91c92_release\n");
[PATCH] pcmcia: add pcmcia_disable_device pcmcia_disable_device(struct pcmcia_device *p_dev) performs the necessary cleanups upon device or driver removal: it calls the appropriate pcmcia_release_* functions, and can replace (most) of the current drivers' _release() functions. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-01-15 16:32:39 +08:00
if (link->win) {
struct net_device *dev = link->priv;
struct smc_private *smc = netdev_priv(dev);
iounmap(smc->base);
}
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
pcmcia_disable_device(link);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/*======================================================================
MII interface support for SMC91cXX based cards
======================================================================*/
#define MDIO_SHIFT_CLK 0x04
#define MDIO_DATA_OUT 0x01
#define MDIO_DIR_WRITE 0x08
#define MDIO_DATA_WRITE0 (MDIO_DIR_WRITE)
#define MDIO_DATA_WRITE1 (MDIO_DIR_WRITE | MDIO_DATA_OUT)
#define MDIO_DATA_READ 0x02
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
static void mdio_sync(unsigned int addr)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
int bits;
for (bits = 0; bits < 32; bits++) {
outb(MDIO_DATA_WRITE1, addr);
outb(MDIO_DATA_WRITE1 | MDIO_SHIFT_CLK, addr);
}
}
static int mdio_read(struct net_device *dev, int phy_id, int loc)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int addr = dev->base_addr + MGMT;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_int cmd = (0x06<<10)|(phy_id<<5)|loc;
int i, retval = 0;
mdio_sync(addr);
for (i = 13; i >= 0; i--) {
int dat = (cmd&(1<<i)) ? MDIO_DATA_WRITE1 : MDIO_DATA_WRITE0;
outb(dat, addr);
outb(dat | MDIO_SHIFT_CLK, addr);
}
for (i = 19; i > 0; i--) {
outb(0, addr);
retval = (retval << 1) | ((inb(addr) & MDIO_DATA_READ) != 0);
outb(MDIO_SHIFT_CLK, addr);
}
return (retval>>1) & 0xffff;
}
static void mdio_write(struct net_device *dev, int phy_id, int loc, int value)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int addr = dev->base_addr + MGMT;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_int cmd = (0x05<<28)|(phy_id<<23)|(loc<<18)|(1<<17)|value;
int i;
mdio_sync(addr);
for (i = 31; i >= 0; i--) {
int dat = (cmd&(1<<i)) ? MDIO_DATA_WRITE1 : MDIO_DATA_WRITE0;
outb(dat, addr);
outb(dat | MDIO_SHIFT_CLK, addr);
}
for (i = 1; i >= 0; i--) {
outb(0, addr);
outb(MDIO_SHIFT_CLK, addr);
}
}
/*======================================================================
The driver core code, most of which should be common with a
non-PCMCIA implementation.
======================================================================*/
#ifdef PCMCIA_DEBUG
static void smc_dump(struct net_device *dev)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_short i, w, save;
save = inw(ioaddr + BANK_SELECT);
for (w = 0; w < 4; w++) {
SMC_SELECT_BANK(w);
printk(KERN_DEBUG "bank %d: ", w);
for (i = 0; i < 14; i += 2)
printk(" %04x", inw(ioaddr + i));
printk("\n");
}
outw(save, ioaddr + BANK_SELECT);
}
#endif
static int smc_open(struct net_device *dev)
{
struct smc_private *smc = netdev_priv(dev);
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
struct pcmcia_device *link = smc->p_dev;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "%s: smc_open(%p), ID/Window %4.4x.\n",
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev->name, dev, inw(dev->base_addr + BANK_SELECT));
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
#ifdef PCMCIA_DEBUG
smc_dump(dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#endif
/* Check that the PCMCIA card is still here. */
[PATCH] pcmcia: convert DEV_OK to pcmcia_dev_present Instead of the DEV_OK macro, drivers should use pcmcia_dev_present(). Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-05 18:04:33 +08:00
if (!pcmcia_dev_present(link))
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return -ENODEV;
/* Physical device present signature. */
if (check_sig(link) < 0) {
printk("smc91c92_cs: Yikes! Bad chip signature!\n");
return -ENODEV;
}
link->open++;
netif_start_queue(dev);
smc->saved_skb = NULL;
smc->packets_waiting = 0;
smc_reset(dev);
init_timer(&smc->media);
smc->media.function = &media_check;
smc->media.data = (u_long) dev;
smc->media.expires = jiffies + HZ;
add_timer(&smc->media);
return 0;
} /* smc_open */
/*====================================================================*/
static int smc_close(struct net_device *dev)
{
struct smc_private *smc = netdev_priv(dev);
[PATCH] pcmcia: remove dev_link_t and client_handle_t indirection dev_link_t * and client_handle_t both mean struct pcmcai_device * by now. Therefore, remove all such indirections. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:21:06 +08:00
struct pcmcia_device *link = smc->p_dev;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
dev_dbg(&link->dev, "%s: smc_close(), status %4.4x.\n",
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev->name, inw(ioaddr + BANK_SELECT));
netif_stop_queue(dev);
/* Shut off all interrupts, and turn off the Tx and Rx sections.
Don't bother to check for chip present. */
SMC_SELECT_BANK(2); /* Nominally paranoia, but do no assume... */
outw(0, ioaddr + INTERRUPT);
SMC_SELECT_BANK(0);
mask_bits(0xff00, ioaddr + RCR);
mask_bits(0xff00, ioaddr + TCR);
/* Put the chip into power-down mode. */
SMC_SELECT_BANK(1);
outw(CTL_POWERDOWN, ioaddr + CONTROL );
link->open--;
del_timer_sync(&smc->media);
return 0;
} /* smc_close */
/*======================================================================
Transfer a packet to the hardware and trigger the packet send.
This may be called at either from either the Tx queue code
or the interrupt handler.
======================================================================*/
static void smc_hardware_send_packet(struct net_device * dev)
{
struct smc_private *smc = netdev_priv(dev);
struct sk_buff *skb = smc->saved_skb;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_char packet_no;
if (!skb) {
printk(KERN_ERR "%s: In XMIT with no packet to send.\n", dev->name);
return;
}
/* There should be a packet slot waiting. */
packet_no = inw(ioaddr + PNR_ARR) >> 8;
if (packet_no & 0x80) {
/* If not, there is a hardware problem! Likely an ejected card. */
printk(KERN_WARNING "%s: 91c92 hardware Tx buffer allocation"
" failed, status %#2.2x.\n", dev->name, packet_no);
dev_kfree_skb_irq(skb);
smc->saved_skb = NULL;
netif_start_queue(dev);
return;
}
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_bytes += skb->len;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* The card should use the just-allocated buffer. */
outw(packet_no, ioaddr + PNR_ARR);
/* point to the beginning of the packet */
outw(PTR_AUTOINC , ioaddr + POINTER);
/* Send the packet length (+6 for status, length and ctl byte)
and the status word (set to zeros). */
{
u_char *buf = skb->data;
u_int length = skb->len; /* The chip will pad to ethernet min. */
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: Trying to xmit packet of length %d.\n",
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev->name, length);
/* send the packet length: +6 for status word, length, and ctl */
outw(0, ioaddr + DATA_1);
outw(length + 6, ioaddr + DATA_1);
outsw(ioaddr + DATA_1, buf, length >> 1);
/* The odd last byte, if there is one, goes in the control word. */
outw((length & 1) ? 0x2000 | buf[length-1] : 0, ioaddr + DATA_1);
}
/* Enable the Tx interrupts, both Tx (TxErr) and TxEmpty. */
outw(((IM_TX_INT|IM_TX_EMPTY_INT)<<8) |
(inw(ioaddr + INTERRUPT) & 0xff00),
ioaddr + INTERRUPT);
/* The chip does the rest of the work. */
outw(MC_ENQUEUE , ioaddr + MMU_CMD);
smc->saved_skb = NULL;
dev_kfree_skb_irq(skb);
dev->trans_start = jiffies;
netif_start_queue(dev);
return;
}
/*====================================================================*/
static void smc_tx_timeout(struct net_device *dev)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
printk(KERN_NOTICE "%s: SMC91c92 transmit timed out, "
"Tx_status %2.2x status %4.4x.\n",
dev->name, inw(ioaddr)&0xff, inw(ioaddr + 2));
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc_reset(dev);
dev->trans_start = jiffies;
smc->saved_skb = NULL;
netif_wake_queue(dev);
}
netdev: convert pcmcia drivers to netdev_tx_t Update all the pcmcia network drivers for netdev_tx_t. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-01 03:50:49 +08:00
static netdev_tx_t smc_start_xmit(struct sk_buff *skb,
struct net_device *dev)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_short num_pages;
short time_out, ir;
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
unsigned long flags;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
netif_stop_queue(dev);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: smc_start_xmit(length = %d) called,"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
" status %4.4x.\n", dev->name, skb->len, inw(ioaddr + 2));
if (smc->saved_skb) {
/* THIS SHOULD NEVER HAPPEN. */
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_aborted_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
printk(KERN_DEBUG "%s: Internal error -- sent packet while busy.\n",
dev->name);
net: use symbolic values for ndo_start_xmit() return codes Convert magic values 1 and -1 to NETDEV_TX_BUSY and NETDEV_TX_LOCKED respectively. 0 (NETDEV_TX_OK) is not changed to keep the noise down, except in very few cases where its in direct proximity to one of the other values. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-12 14:22:29 +08:00
return NETDEV_TX_BUSY;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
smc->saved_skb = skb;
num_pages = skb->len >> 8;
if (num_pages > 7) {
printk(KERN_ERR "%s: Far too big packet error.\n", dev->name);
dev_kfree_skb (skb);
smc->saved_skb = NULL;
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_dropped++;
net: use NETDEV_TX_OK instead of 0 in ndo_start_xmit() functions This patch is the result of an automatic spatch transformation to convert all ndo_start_xmit() return values of 0 to NETDEV_TX_OK. Some occurences are missed by the automatic conversion, those will be handled in a seperate patch. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-23 14:03:08 +08:00
return NETDEV_TX_OK; /* Do not re-queue this packet. */
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/* A packet is now waiting. */
smc->packets_waiting++;
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_lock_irqsave(&smc->lock, flags);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
SMC_SELECT_BANK(2); /* Paranoia, we should always be in window 2 */
/* need MC_RESET to keep the memory consistent. errata? */
if (smc->rx_ovrn) {
outw(MC_RESET, ioaddr + MMU_CMD);
smc->rx_ovrn = 0;
}
/* Allocate the memory; send the packet now if we win. */
outw(MC_ALLOC | num_pages, ioaddr + MMU_CMD);
for (time_out = MEMORY_WAIT_TIME; time_out >= 0; time_out--) {
ir = inw(ioaddr+INTERRUPT);
if (ir & IM_ALLOC_INT) {
/* Acknowledge the interrupt, send the packet. */
outw((ir&0xff00) | IM_ALLOC_INT, ioaddr + INTERRUPT);
smc_hardware_send_packet(dev); /* Send the packet now.. */
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irqrestore(&smc->lock, flags);
net: use NETDEV_TX_OK instead of 0 in ndo_start_xmit() functions This patch is the result of an automatic spatch transformation to convert all ndo_start_xmit() return values of 0 to NETDEV_TX_OK. Some occurences are missed by the automatic conversion, those will be handled in a seperate patch. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-23 14:03:08 +08:00
return NETDEV_TX_OK;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
}
/* Otherwise defer until the Tx-space-allocated interrupt. */
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: memory allocation deferred.\n", dev->name);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
outw((IM_ALLOC_INT << 8) | (ir & 0xff00), ioaddr + INTERRUPT);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irqrestore(&smc->lock, flags);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net: use NETDEV_TX_OK instead of 0 in ndo_start_xmit() functions This patch is the result of an automatic spatch transformation to convert all ndo_start_xmit() return values of 0 to NETDEV_TX_OK. Some occurences are missed by the automatic conversion, those will be handled in a seperate patch. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-23 14:03:08 +08:00
return NETDEV_TX_OK;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/*======================================================================
Handle a Tx anomolous event. Entered while in Window 2.
======================================================================*/
static void smc_tx_err(struct net_device * dev)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
int saved_packet = inw(ioaddr + PNR_ARR) & 0xff;
int packet_no = inw(ioaddr + FIFO_PORTS) & 0x7f;
int tx_status;
/* select this as the packet to read from */
outw(packet_no, ioaddr + PNR_ARR);
/* read the first word from this packet */
outw(PTR_AUTOINC | PTR_READ | 0, ioaddr + POINTER);
tx_status = inw(ioaddr + DATA_1);
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_errors++;
if (tx_status & TS_LOSTCAR) dev->stats.tx_carrier_errors++;
if (tx_status & TS_LATCOL) dev->stats.tx_window_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (tx_status & TS_16COL) {
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_aborted_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc->tx_err++;
}
if (tx_status & TS_SUCCESS) {
printk(KERN_NOTICE "%s: Successful packet caused error "
"interrupt?\n", dev->name);
}
/* re-enable transmit */
SMC_SELECT_BANK(0);
outw(inw(ioaddr + TCR) | TCR_ENABLE | smc->duplex, ioaddr + TCR);
SMC_SELECT_BANK(2);
outw(MC_FREEPKT, ioaddr + MMU_CMD); /* Free the packet memory. */
/* one less packet waiting for me */
smc->packets_waiting--;
outw(saved_packet, ioaddr + PNR_ARR);
return;
}
/*====================================================================*/
static void smc_eph_irq(struct net_device *dev)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_short card_stats, ephs;
SMC_SELECT_BANK(0);
ephs = inw(ioaddr + EPH);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: Ethernet protocol handler interrupt, status"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
" %4.4x.\n", dev->name, ephs);
/* Could be a counter roll-over warning: update stats. */
card_stats = inw(ioaddr + COUNTER);
/* single collisions */
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.collisions += card_stats & 0xF;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
card_stats >>= 4;
/* multiple collisions */
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.collisions += card_stats & 0xF;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#if 0 /* These are for when linux supports these statistics */
card_stats >>= 4; /* deferred */
card_stats >>= 4; /* excess deferred */
#endif
/* If we had a transmit error we must re-enable the transmitter. */
outw(inw(ioaddr + TCR) | TCR_ENABLE | smc->duplex, ioaddr + TCR);
/* Clear a link error interrupt. */
SMC_SELECT_BANK(1);
outw(CTL_AUTO_RELEASE | 0x0000, ioaddr + CONTROL);
outw(CTL_AUTO_RELEASE | CTL_TE_ENABLE | CTL_CR_ENABLE,
ioaddr + CONTROL);
SMC_SELECT_BANK(2);
}
/*====================================================================*/
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
static irqreturn_t smc_interrupt(int irq, void *dev_id)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct net_device *dev = dev_id;
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_short saved_bank, saved_pointer, mask, status;
unsigned int handled = 1;
char bogus_cnt = INTR_WORK; /* Work we are willing to do. */
if (!netif_device_present(dev))
return IRQ_NONE;
ioaddr = dev->base_addr;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: SMC91c92 interrupt %d at %#x.\n", dev->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
irq, ioaddr);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_lock(&smc->lock);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc->watchdog = 0;
saved_bank = inw(ioaddr + BANK_SELECT);
if ((saved_bank & 0xff00) != 0x3300) {
/* The device does not exist -- the card could be off-line, or
maybe it has been ejected. */
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: SMC91c92 interrupt %d for non-existent"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
"/ejected device.\n", dev->name, irq);
handled = 0;
goto irq_done;
}
SMC_SELECT_BANK(2);
saved_pointer = inw(ioaddr + POINTER);
mask = inw(ioaddr + INTERRUPT) >> 8;
/* clear all interrupts */
outw(0, ioaddr + INTERRUPT);
do { /* read the status flag, and mask it */
status = inw(ioaddr + INTERRUPT) & 0xff;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: Status is %#2.2x (mask %#2.2x).\n", dev->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
status, mask);
if ((status & mask) == 0) {
if (bogus_cnt == INTR_WORK)
handled = 0;
break;
}
if (status & IM_RCV_INT) {
/* Got a packet(s). */
smc_rx(dev);
}
if (status & IM_TX_INT) {
smc_tx_err(dev);
outw(IM_TX_INT, ioaddr + INTERRUPT);
}
status &= mask;
if (status & IM_TX_EMPTY_INT) {
outw(IM_TX_EMPTY_INT, ioaddr + INTERRUPT);
mask &= ~IM_TX_EMPTY_INT;
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.tx_packets += smc->packets_waiting;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc->packets_waiting = 0;
}
if (status & IM_ALLOC_INT) {
/* Clear this interrupt so it doesn't happen again */
mask &= ~IM_ALLOC_INT;
smc_hardware_send_packet(dev);
/* enable xmit interrupts based on this */
mask |= (IM_TX_EMPTY_INT | IM_TX_INT);
/* and let the card send more packets to me */
netif_wake_queue(dev);
}
if (status & IM_RX_OVRN_INT) {
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.rx_errors++;
dev->stats.rx_fifo_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (smc->duplex)
smc->rx_ovrn = 1; /* need MC_RESET outside smc_interrupt */
outw(IM_RX_OVRN_INT, ioaddr + INTERRUPT);
}
if (status & IM_EPH_INT)
smc_eph_irq(dev);
} while (--bogus_cnt);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug(" Restoring saved registers mask %2.2x bank %4.4x"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
" pointer %4.4x.\n", mask, saved_bank, saved_pointer);
/* restore state register */
outw((mask<<8), ioaddr + INTERRUPT);
outw(saved_pointer, ioaddr + POINTER);
SMC_SELECT_BANK(saved_bank);
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: Exiting interrupt IRQ%d.\n", dev->name, irq);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
irq_done:
if ((smc->manfid == MANFID_OSITECH) &&
(smc->cardid != PRODID_OSITECH_SEVEN)) {
/* Retrigger interrupt if needed */
mask_bits(0x00ff, ioaddr-0x10+OSITECH_RESET_ISR);
set_bits(0x0300, ioaddr-0x10+OSITECH_RESET_ISR);
}
if (smc->manfid == MANFID_MOTOROLA) {
u_char cor;
cor = readb(smc->base + MOT_UART + CISREG_COR);
writeb(cor & ~COR_IREQ_ENA, smc->base + MOT_UART + CISREG_COR);
writeb(cor, smc->base + MOT_UART + CISREG_COR);
cor = readb(smc->base + MOT_LAN + CISREG_COR);
writeb(cor & ~COR_IREQ_ENA, smc->base + MOT_LAN + CISREG_COR);
writeb(cor, smc->base + MOT_LAN + CISREG_COR);
}
#ifdef DOES_NOT_WORK
if (smc->base != NULL) { /* Megahertz MFC's */
readb(smc->base+MEGAHERTZ_ISR);
readb(smc->base+MEGAHERTZ_ISR);
}
#endif
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock(&smc->lock);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return IRQ_RETVAL(handled);
}
/*====================================================================*/
static void smc_rx(struct net_device *dev)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
int rx_status;
int packet_length; /* Caution: not frame length, rather words
to transfer from the chip. */
/* Assertion: we are in Window 2. */
if (inw(ioaddr + FIFO_PORTS) & FP_RXEMPTY) {
printk(KERN_ERR "%s: smc_rx() with nothing on Rx FIFO.\n",
dev->name);
return;
}
/* Reset the read pointer, and read the status and packet length. */
outw(PTR_READ | PTR_RCV | PTR_AUTOINC, ioaddr + POINTER);
rx_status = inw(ioaddr + DATA_1);
packet_length = inw(ioaddr + DATA_1) & 0x07ff;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: Receive status %4.4x length %d.\n",
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev->name, rx_status, packet_length);
if (!(rx_status & RS_ERRORS)) {
/* do stuff to make a new packet */
struct sk_buff *skb;
/* Note: packet_length adds 5 or 6 extra bytes here! */
skb = dev_alloc_skb(packet_length+2);
if (skb == NULL) {
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: Low memory, packet dropped.\n", dev->name);
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.rx_dropped++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
outw(MC_RELEASE, ioaddr + MMU_CMD);
return;
}
packet_length -= (rx_status & RS_ODDFRAME ? 5 : 6);
skb_reserve(skb, 2);
insw(ioaddr+DATA_1, skb_put(skb, packet_length),
(packet_length+1)>>1);
skb->protocol = eth_type_trans(skb, dev);
netif_rx(skb);
dev->last_rx = jiffies;
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.rx_packets++;
dev->stats.rx_bytes += packet_length;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (rx_status & RS_MULTICAST)
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.multicast++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} else {
/* error ... */
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.rx_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
if (rx_status & RS_ALGNERR) dev->stats.rx_frame_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (rx_status & (RS_TOOSHORT | RS_TOOLONG))
smc91c92: convert to internal net_device_stats Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-21 03:36:09 +08:00
dev->stats.rx_length_errors++;
if (rx_status & RS_BADCRC) dev->stats.rx_crc_errors++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/* Let the MMU free the memory of this packet. */
outw(MC_RELEASE, ioaddr + MMU_CMD);
return;
}
/*======================================================================
Set the receive mode.
This routine is used by both the protocol level to notify us of
promiscuous/multicast mode changes, and by the open/reset code to
initialize the Rx registers. We always set the multicast list and
leave the receiver running.
======================================================================*/
static void set_rx_mode(struct net_device *dev)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
struct smc_private *smc = netdev_priv(dev);
u_int multicast_table[ 2 ] = { 0, };
unsigned long flags;
u_short rx_cfg_setting;
if (dev->flags & IFF_PROMISC) {
rx_cfg_setting = RxStripCRC | RxEnable | RxPromisc | RxAllMulti;
} else if (dev->flags & IFF_ALLMULTI)
rx_cfg_setting = RxStripCRC | RxEnable | RxAllMulti;
else {
net: use netdev_mc_count and netdev_mc_empty when appropriate This patch replaces dev->mc_count in all drivers (hopefully I didn't miss anything). Used spatch and did small tweaks and conding style changes when it was suitable. Jirka Signed-off-by: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 12:30:35 +08:00
if (!netdev_mc_empty(dev)) {
net/pcmcia: convert to use netdev_for_each_mc_addr removed fill_multicast_tbl function in smc91c92_cs and do the work inline rewritten set_addresses function in xirc2ps_cs. This was kinda headache. Simulated the original and new functions and they bahave the same. Signed-off-by: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-19 16:48:47 +08:00
struct dev_mc_list *mc_addr;
netdev_for_each_mc_addr(mc_addr, dev) {
u_int position = ether_crc(6, mc_addr->dmi_addr);
#ifndef final_version /* Verify multicast address. */
if ((mc_addr->dmi_addr[0] & 1) == 0)
continue;
#endif
multicast_table[position >> 29] |= 1 << ((position >> 26) & 7);
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
rx_cfg_setting = RxStripCRC | RxEnable;
}
/* Load MC table and Rx setting into the chip without interrupts. */
spin_lock_irqsave(&smc->lock, flags);
SMC_SELECT_BANK(3);
outl(multicast_table[0], ioaddr + MULTICAST0);
outl(multicast_table[1], ioaddr + MULTICAST4);
SMC_SELECT_BANK(0);
outw(rx_cfg_setting, ioaddr + RCR);
SMC_SELECT_BANK(2);
spin_unlock_irqrestore(&smc->lock, flags);
return;
}
/*======================================================================
Senses when a card's config changes. Here, it's coax or TP.
======================================================================*/
static int s9k_config(struct net_device *dev, struct ifmap *map)
{
struct smc_private *smc = netdev_priv(dev);
if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) {
if (smc->cfg & CFG_MII_SELECT)
return -EOPNOTSUPP;
else if (map->port > 2)
return -EINVAL;
dev->if_port = map->port;
printk(KERN_INFO "%s: switched to %s port\n",
dev->name, if_names[dev->if_port]);
smc_reset(dev);
}
return 0;
}
/*======================================================================
Reset the chip, reloading every register that might be corrupted.
======================================================================*/
/*
Set transceiver type, perhaps to something other than what the user
specified in dev->if_port.
*/
static void smc_set_xcvr(struct net_device *dev, int if_port)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_short saved_bank;
saved_bank = inw(ioaddr + BANK_SELECT);
SMC_SELECT_BANK(1);
if (if_port == 2) {
outw(smc->cfg | CFG_AUI_SELECT, ioaddr + CONFIG);
if ((smc->manfid == MANFID_OSITECH) &&
(smc->cardid != PRODID_OSITECH_SEVEN))
set_bits(OSI_AUI_PWR, ioaddr - 0x10 + OSITECH_AUI_PWR);
smc->media_status = ((dev->if_port == 0) ? 0x0001 : 0x0002);
} else {
outw(smc->cfg, ioaddr + CONFIG);
if ((smc->manfid == MANFID_OSITECH) &&
(smc->cardid != PRODID_OSITECH_SEVEN))
mask_bits(~OSI_AUI_PWR, ioaddr - 0x10 + OSITECH_AUI_PWR);
smc->media_status = ((dev->if_port == 0) ? 0x0012 : 0x4001);
}
SMC_SELECT_BANK(saved_bank);
}
static void smc_reset(struct net_device *dev)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
struct smc_private *smc = netdev_priv(dev);
int i;
pcmcia: use dynamic debug infrastructure, deprecate CS_CHECK (net) Convert PCMCIA drivers to use the dynamic debug infrastructure, instead of requiring manual settings of PCMCIA_DEBUG. Only some rare debug checks are now hidden behind "#ifdef DEBUG" or "#if 0". Also, remove all usages of the CS_CHECK macro and replace them with proper Linux style calling and return value checking. The extra error reporting may be dropped, as the PCMCIA core already complains about any (non-driver-author) errors. CC: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2009-10-24 21:51:05 +08:00
pr_debug("%s: smc91c92 reset called.\n", dev->name);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* The first interaction must be a write to bring the chip out
of sleep mode. */
SMC_SELECT_BANK(0);
/* Reset the chip. */
outw(RCR_SOFTRESET, ioaddr + RCR);
udelay(10);
/* Clear the transmit and receive configuration registers. */
outw(RCR_CLEAR, ioaddr + RCR);
outw(TCR_CLEAR, ioaddr + TCR);
/* Set the Window 1 control, configuration and station addr registers.
No point in writing the I/O base register ;-> */
SMC_SELECT_BANK(1);
spelling fixes acquired (aquired) contiguous (contigious) successful (succesful, succesfull) surprise (suprise) whether (weather) some other misspellings Signed-off-by: Andreas Mohr <andi@lisas.de> Signed-off-by: Adrian Bunk <bunk@stusta.de>
2006-06-27 00:35:02 +08:00
/* Automatically release successfully transmitted packets,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
Accept link errors, counter and Tx error interrupts. */
outw(CTL_AUTO_RELEASE | CTL_TE_ENABLE | CTL_CR_ENABLE,
ioaddr + CONTROL);
smc_set_xcvr(dev, dev->if_port);
if ((smc->manfid == MANFID_OSITECH) &&
(smc->cardid != PRODID_OSITECH_SEVEN))
outw((dev->if_port == 2 ? OSI_AUI_PWR : 0) |
(inw(ioaddr-0x10+OSITECH_AUI_PWR) & 0xff00),
ioaddr - 0x10 + OSITECH_AUI_PWR);
/* Fill in the physical address. The databook is wrong about the order! */
for (i = 0; i < 6; i += 2)
outw((dev->dev_addr[i+1]<<8)+dev->dev_addr[i],
ioaddr + ADDR0 + i);
/* Reset the MMU */
SMC_SELECT_BANK(2);
outw(MC_RESET, ioaddr + MMU_CMD);
outw(0, ioaddr + INTERRUPT);
/* Re-enable the chip. */
SMC_SELECT_BANK(0);
outw(((smc->cfg & CFG_MII_SELECT) ? 0 : TCR_MONCSN) |
TCR_ENABLE | TCR_PAD_EN | smc->duplex, ioaddr + TCR);
set_rx_mode(dev);
if (smc->cfg & CFG_MII_SELECT) {
SMC_SELECT_BANK(3);
/* Reset MII */
mdio_write(dev, smc->mii_if.phy_id, 0, 0x8000);
/* Advertise 100F, 100H, 10F, 10H */
mdio_write(dev, smc->mii_if.phy_id, 4, 0x01e1);
/* Restart MII autonegotiation */
mdio_write(dev, smc->mii_if.phy_id, 0, 0x0000);
mdio_write(dev, smc->mii_if.phy_id, 0, 0x1200);
}
/* Enable interrupts. */
SMC_SELECT_BANK(2);
outw((IM_EPH_INT | IM_RX_OVRN_INT | IM_RCV_INT) << 8,
ioaddr + INTERRUPT);
}
/*======================================================================
Media selection timer routine
======================================================================*/
static void media_check(u_long arg)
{
struct net_device *dev = (struct net_device *) arg;
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u_short i, media, saved_bank;
u_short link;
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
unsigned long flags;
spin_lock_irqsave(&smc->lock, flags);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
saved_bank = inw(ioaddr + BANK_SELECT);
if (!netif_device_present(dev))
goto reschedule;
SMC_SELECT_BANK(2);
/* need MC_RESET to keep the memory consistent. errata? */
if (smc->rx_ovrn) {
outw(MC_RESET, ioaddr + MMU_CMD);
smc->rx_ovrn = 0;
}
i = inw(ioaddr + INTERRUPT);
SMC_SELECT_BANK(0);
media = inw(ioaddr + EPH) & EPH_LINK_OK;
SMC_SELECT_BANK(1);
media |= (inw(ioaddr + CONFIG) & CFG_AUI_SELECT) ? 2 : 1;
/* Check for pending interrupt with watchdog flag set: with
this, we can limp along even if the interrupt is blocked */
if (smc->watchdog++ && ((i>>8) & i)) {
if (!smc->fast_poll)
printk(KERN_INFO "%s: interrupt(s) dropped!\n", dev->name);
PCMCIA-NETDEV : the 2nd argument of el3_interrrupt and smc_interrupt is struct net_device* Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-02-10 10:57:35 +08:00
smc_interrupt(dev->irq, dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
smc->fast_poll = HZ;
}
if (smc->fast_poll) {
smc->fast_poll--;
smc->media.expires = jiffies + HZ/100;
add_timer(&smc->media);
SMC_SELECT_BANK(saved_bank);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irqrestore(&smc->lock, flags);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return;
}
if (smc->cfg & CFG_MII_SELECT) {
if (smc->mii_if.phy_id < 0)
goto reschedule;
SMC_SELECT_BANK(3);
link = mdio_read(dev, smc->mii_if.phy_id, 1);
if (!link || (link == 0xffff)) {
printk(KERN_INFO "%s: MII is missing!\n", dev->name);
smc->mii_if.phy_id = -1;
goto reschedule;
}
link &= 0x0004;
if (link != smc->link_status) {
u_short p = mdio_read(dev, smc->mii_if.phy_id, 5);
printk(KERN_INFO "%s: %s link beat\n", dev->name,
(link) ? "found" : "lost");
smc->duplex = (((p & 0x0100) || ((p & 0x1c0) == 0x40))
? TCR_FDUPLX : 0);
if (link) {
printk(KERN_INFO "%s: autonegotiation complete: "
"%sbaseT-%cD selected\n", dev->name,
((p & 0x0180) ? "100" : "10"),
(smc->duplex ? 'F' : 'H'));
}
SMC_SELECT_BANK(0);
outw(inw(ioaddr + TCR) | smc->duplex, ioaddr + TCR);
smc->link_status = link;
}
goto reschedule;
}
/* Ignore collisions unless we've had no rx's recently */
[NET PCMCIA]: drivers/net/pcmcia/smc91c92_cs.c : Use of time_after macro From: Marcelo Feitoza Parisi <marcelo@feitoza.com.br> Use of the time_after() macro, defined at linux/jiffies.h, which deal with wrapping correctly and are nicer to read. Signed-off-by: Marcelo Feitoza Parisi <marcelo@feitoza.com.br> Signed-off-by: Domen Puncer <domen@coderock.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-16 01:00:41 +08:00
if (time_after(jiffies, dev->last_rx + HZ)) {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (smc->tx_err || (smc->media_status & EPH_16COL))
media |= EPH_16COL;
}
smc->tx_err = 0;
if (media != smc->media_status) {
if ((media & smc->media_status & 1) &&
((smc->media_status ^ media) & EPH_LINK_OK))
printk(KERN_INFO "%s: %s link beat\n", dev->name,
(smc->media_status & EPH_LINK_OK ? "lost" : "found"));
else if ((media & smc->media_status & 2) &&
((smc->media_status ^ media) & EPH_16COL))
printk(KERN_INFO "%s: coax cable %s\n", dev->name,
(media & EPH_16COL ? "problem" : "ok"));
if (dev->if_port == 0) {
if (media & 1) {
if (media & EPH_LINK_OK)
printk(KERN_INFO "%s: flipped to 10baseT\n",
dev->name);
else
smc_set_xcvr(dev, 2);
} else {
if (media & EPH_16COL)
smc_set_xcvr(dev, 1);
else
printk(KERN_INFO "%s: flipped to 10base2\n",
dev->name);
}
}
smc->media_status = media;
}
reschedule:
smc->media.expires = jiffies + HZ;
add_timer(&smc->media);
SMC_SELECT_BANK(saved_bank);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irqrestore(&smc->lock, flags);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
static int smc_link_ok(struct net_device *dev)
{
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
struct smc_private *smc = netdev_priv(dev);
if (smc->cfg & CFG_MII_SELECT) {
return mii_link_ok(&smc->mii_if);
} else {
SMC_SELECT_BANK(0);
return inw(ioaddr + EPH) & EPH_LINK_OK;
}
}
static int smc_netdev_get_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
{
u16 tmp;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
ecmd->supported = (SUPPORTED_TP | SUPPORTED_AUI |
SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full);
SMC_SELECT_BANK(1);
tmp = inw(ioaddr + CONFIG);
ecmd->port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP;
ecmd->transceiver = XCVR_INTERNAL;
ecmd->speed = SPEED_10;
ecmd->phy_address = ioaddr + MGMT;
SMC_SELECT_BANK(0);
tmp = inw(ioaddr + TCR);
ecmd->duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF;
return 0;
}
static int smc_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
{
u16 tmp;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (ecmd->speed != SPEED_10)
return -EINVAL;
if (ecmd->duplex != DUPLEX_HALF && ecmd->duplex != DUPLEX_FULL)
return -EINVAL;
if (ecmd->port != PORT_TP && ecmd->port != PORT_AUI)
return -EINVAL;
if (ecmd->transceiver != XCVR_INTERNAL)
return -EINVAL;
if (ecmd->port == PORT_AUI)
smc_set_xcvr(dev, 1);
else
smc_set_xcvr(dev, 0);
SMC_SELECT_BANK(0);
tmp = inw(ioaddr + TCR);
if (ecmd->duplex == DUPLEX_FULL)
tmp |= TCR_FDUPLX;
else
tmp &= ~TCR_FDUPLX;
outw(tmp, ioaddr + TCR);
return 0;
}
static int check_if_running(struct net_device *dev)
{
if (!netif_running(dev))
return -EINVAL;
return 0;
}
static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
strcpy(info->driver, DRV_NAME);
strcpy(info->version, DRV_VERSION);
}
static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u16 saved_bank = inw(ioaddr + BANK_SELECT);
int ret;
spin_lock_irq(&smc->lock);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
SMC_SELECT_BANK(3);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (smc->cfg & CFG_MII_SELECT)
ret = mii_ethtool_gset(&smc->mii_if, ecmd);
else
ret = smc_netdev_get_ecmd(dev, ecmd);
SMC_SELECT_BANK(saved_bank);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irq(&smc->lock);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return ret;
}
static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u16 saved_bank = inw(ioaddr + BANK_SELECT);
int ret;
spin_lock_irq(&smc->lock);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
SMC_SELECT_BANK(3);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (smc->cfg & CFG_MII_SELECT)
ret = mii_ethtool_sset(&smc->mii_if, ecmd);
else
ret = smc_netdev_set_ecmd(dev, ecmd);
SMC_SELECT_BANK(saved_bank);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irq(&smc->lock);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return ret;
}
static u32 smc_get_link(struct net_device *dev)
{
struct smc_private *smc = netdev_priv(dev);
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u16 saved_bank = inw(ioaddr + BANK_SELECT);
u32 ret;
spin_lock_irq(&smc->lock);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
SMC_SELECT_BANK(3);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
ret = smc_link_ok(dev);
SMC_SELECT_BANK(saved_bank);
PATCH kernel 2.6.22] PCMCIA-NETDEV : modify smc91c92_cs.c to become SMP safe protect smc_start_xmit, smc_interrupt and media_check by spin_lock. Signed-off-by: Komuro <komurojun-mbn@nifty.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-23 20:36:06 +08:00
spin_unlock_irq(&smc->lock);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return ret;
}
static int smc_nway_reset(struct net_device *dev)
{
struct smc_private *smc = netdev_priv(dev);
if (smc->cfg & CFG_MII_SELECT) {
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u16 saved_bank = inw(ioaddr + BANK_SELECT);
int res;
SMC_SELECT_BANK(3);
res = mii_nway_restart(&smc->mii_if);
SMC_SELECT_BANK(saved_bank);
return res;
} else
return -EOPNOTSUPP;
}
drivers/net: const-ify ethtool_ops declarations Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 02:30:00 +08:00
static const struct ethtool_ops ethtool_ops = {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.begin = check_if_running,
.get_drvinfo = smc_get_drvinfo,
.get_settings = smc_get_settings,
.set_settings = smc_set_settings,
.get_link = smc_get_link,
.nway_reset = smc_nway_reset,
};
static int smc_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
{
struct smc_private *smc = netdev_priv(dev);
struct mii_ioctl_data *mii = if_mii(rq);
int rc = 0;
u16 saved_bank;
pcmcia: replace kio_addr_t with unsigned int everywhere Remove kio_addr_t, and replace it with unsigned int. No known architecture needs more than 32 bits for IO addresses and ports and having a separate type for it is just messy. Signed-off-by: Olof Johansson <olof@lixom.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:35 +08:00
unsigned int ioaddr = dev->base_addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (!netif_running(dev))
return -EINVAL;
spin_lock_irq(&smc->lock);
saved_bank = inw(ioaddr + BANK_SELECT);
SMC_SELECT_BANK(3);
rc = generic_mii_ioctl(&smc->mii_if, mii, cmd, NULL);
SMC_SELECT_BANK(saved_bank);
spin_unlock_irq(&smc->lock);
return rc;
}
[PATCH] pcmcia: id_table for smc91c92_cs.c Add pcmcia_device_id table. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-28 07:28:27 +08:00
static struct pcmcia_device_id smc91c92_ids[] = {
PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0109, 0x0501),
PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0140, 0x000a),
PCMCIA_PFC_DEVICE_PROD_ID123(0, "MEGAHERTZ", "CC/XJEM3288", "DATA/FAX/CELL ETHERNET MODEM", 0xf510db04, 0x04cd2988, 0x46a52d63),
PCMCIA_PFC_DEVICE_PROD_ID123(0, "MEGAHERTZ", "CC/XJEM3336", "DATA/FAX/CELL ETHERNET MODEM", 0xf510db04, 0x0143b773, 0x46a52d63),
PCMCIA_PFC_DEVICE_PROD_ID123(0, "MEGAHERTZ", "EM1144T", "PCMCIA MODEM", 0xf510db04, 0x856d66c8, 0xbd6c43ef),
PCMCIA_PFC_DEVICE_PROD_ID123(0, "MEGAHERTZ", "XJEM1144/CCEM1144", "PCMCIA MODEM", 0xf510db04, 0x52d21e1e, 0xbd6c43ef),
PCMCIA_PFC_DEVICE_PROD_ID12(0, "Gateway 2000", "XJEM3336", 0xdd9989be, 0x662c394c),
PCMCIA_PFC_DEVICE_PROD_ID12(0, "MEGAHERTZ", "XJEM1144/CCEM1144", 0xf510db04, 0x52d21e1e),
[PATCH] pcmcia: fix many device IDs If the product-id-string contains the '+' , '&' ,'_', it was not converted properly from the /etc/pcmcia/config(pcmcia-cs config file). Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-28 16:07:24 +08:00
PCMCIA_PFC_DEVICE_PROD_ID12(0, "Ositech", "Trumpcard:Jack of Diamonds Modem+Ethernet", 0xc2f80cd, 0x656947b9),
PCMCIA_PFC_DEVICE_PROD_ID12(0, "Ositech", "Trumpcard:Jack of Hearts Modem+Ethernet", 0xc2f80cd, 0xdc9ba5ed),
[PATCH] pcmcia: id_table for smc91c92_cs.c Add pcmcia_device_id table. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-28 07:28:27 +08:00
PCMCIA_MFC_DEVICE_MANF_CARD(0, 0x016c, 0x0020),
PCMCIA_DEVICE_MANF_CARD(0x016c, 0x0023),
PCMCIA_DEVICE_PROD_ID123("BASICS by New Media Corporation", "Ethernet", "SMC91C94", 0x23c78a9d, 0x00b2e941, 0xcef397fb),
PCMCIA_DEVICE_PROD_ID12("ARGOSY", "Fast Ethernet PCCard", 0x78f308dc, 0xdcea68bc),
PCMCIA_DEVICE_PROD_ID12("dit Co., Ltd.", "PC Card-10/100BTX", 0xe59365c8, 0x6a2161d1),
PCMCIA_DEVICE_PROD_ID12("DYNALINK", "L100C", 0x6a26d1cf, 0xc16ce9c5),
PCMCIA_DEVICE_PROD_ID12("Farallon", "Farallon Enet", 0x58d93fc4, 0x244734e9),
PCMCIA_DEVICE_PROD_ID12("Megahertz", "CC10BT/2", 0x33234748, 0x3c95b953),
PCMCIA_DEVICE_PROD_ID12("MELCO/SMC", "LPC-TX", 0xa2cd8e6d, 0x42da662a),
[PATCH] pcmcia: fix many device IDs If the product-id-string contains the '+' , '&' ,'_', it was not converted properly from the /etc/pcmcia/config(pcmcia-cs config file). Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-28 16:07:24 +08:00
PCMCIA_DEVICE_PROD_ID12("Ositech", "Trumpcard:Four of Diamonds Ethernet", 0xc2f80cd, 0xb3466314),
PCMCIA_DEVICE_PROD_ID12("Ositech", "Trumpcard:Seven of Diamonds Ethernet", 0xc2f80cd, 0x194b650a),
[PATCH] pcmcia: id_table for smc91c92_cs.c Add pcmcia_device_id table. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-28 07:28:27 +08:00
PCMCIA_DEVICE_PROD_ID12("PCMCIA", "Fast Ethernet PCCard", 0x281f1c5d, 0xdcea68bc),
PCMCIA_DEVICE_PROD_ID12("Psion", "10Mb Ethernet", 0x4ef00b21, 0x844be9e9),
PCMCIA_DEVICE_PROD_ID12("SMC", "EtherEZ Ethernet 8020", 0xc4f8b18b, 0x4a0eeb2d),
/* These conflict with other cards! */
/* PCMCIA_DEVICE_MANF_CARD(0x0186, 0x0100), */
/* PCMCIA_DEVICE_MANF_CARD(0x8a01, 0xc1ab), */
PCMCIA_DEVICE_NULL,
};
MODULE_DEVICE_TABLE(pcmcia, smc91c92_ids);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
static struct pcmcia_driver smc91c92_cs_driver = {
.owner = THIS_MODULE,
.drv = {
.name = "smc91c92_cs",
},
[PATCH] pcmcia: add return value to _config() functions Most of the driver initialization isn't done in the .probe function, but in the internal _config() functions. Make them return a value, so that .probe can properly report whether the probing of the device succeeded or not. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2006-03-31 23:26:06 +08:00
.probe = smc91c92_probe,
[PATCH] pcmcia: unify detach, REMOVAL_EVENT handlers into one remove callback Unify the "detach" and REMOVAL_EVENT handlers to one "remove" function. Old functionality is preserved, for the moment. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:23:14 +08:00
.remove = smc91c92_detach,
[PATCH] pcmcia: id_table for smc91c92_cs.c Add pcmcia_device_id table. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-28 07:28:27 +08:00
.id_table = smc91c92_ids,
[PATCH] pcmcia: new suspend core Move the suspend and resume methods out of the event handler, and into special functions. Also use these functions for pre- and post-reset, as almost all drivers already do, and the remaining ones can easily be converted. Bugfix to include/pcmcia/ds.c Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2005-11-15 04:21:18 +08:00
.suspend = smc91c92_suspend,
.resume = smc91c92_resume,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
};
static int __init init_smc91c92_cs(void)
{
return pcmcia_register_driver(&smc91c92_cs_driver);
}
static void __exit exit_smc91c92_cs(void)
{
pcmcia_unregister_driver(&smc91c92_cs_driver);
}
module_init(init_smc91c92_cs);
module_exit(exit_smc91c92_cs);