OpenCloudOS-Kernel/drivers/net/declance.c

1313 lines
32 KiB
C
Raw Normal View History

/*
* Lance ethernet driver for the MIPS processor based
* DECstation family
*
*
* adopted from sunlance.c by Richard van den Berg
*
* Copyright (C) 2002, 2003, 2005 Maciej W. Rozycki
*
* additional sources:
* - PMAD-AA TURBOchannel Ethernet Module Functional Specification,
* Revision 1.2
*
* History:
*
* v0.001: The kernel accepts the code and it shows the hardware address.
*
* v0.002: Removed most sparc stuff, left only some module and dma stuff.
*
* v0.003: Enhanced base address calculation from proposals by
* Harald Koerfgen and Thomas Riemer.
*
* v0.004: lance-regs is pointing at the right addresses, added prom
* check. First start of address mapping and DMA.
*
* v0.005: started to play around with LANCE-DMA. This driver will not
* work for non IOASIC lances. HK
*
* v0.006: added pointer arrays to lance_private and setup routine for
* them in dec_lance_init. HK
*
* v0.007: Big shit. The LANCE seems to use a different DMA mechanism to
* access the init block. This looks like one (short) word at a
* time, but the smallest amount the IOASIC can transfer is a
* (long) word. So we have a 2-2 padding here. Changed
* lance_init_block accordingly. The 16-16 padding for the buffers
* seems to be correct. HK
*
* v0.008: mods to make PMAX_LANCE work. 01/09/1999 triemer
*
* v0.009: Module support fixes, multiple interfaces support, various
* bits. macro
*/
#include <linux/crc32.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/if_ether.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/spinlock.h>
#include <linux/stddef.h>
#include <linux/string.h>
#include <asm/addrspace.h>
#include <asm/system.h>
#include <asm/dec/interrupts.h>
#include <asm/dec/ioasic.h>
#include <asm/dec/ioasic_addrs.h>
#include <asm/dec/kn01.h>
#include <asm/dec/machtype.h>
#include <asm/dec/system.h>
#include <asm/dec/tc.h>
static char version[] __devinitdata =
"declance.c: v0.009 by Linux MIPS DECstation task force\n";
MODULE_AUTHOR("Linux MIPS DECstation task force");
MODULE_DESCRIPTION("DEC LANCE (DECstation onboard, PMAD-xx) driver");
MODULE_LICENSE("GPL");
/*
* card types
*/
#define ASIC_LANCE 1
#define PMAD_LANCE 2
#define PMAX_LANCE 3
#define LE_CSR0 0
#define LE_CSR1 1
#define LE_CSR2 2
#define LE_CSR3 3
#define LE_MO_PROM 0x8000 /* Enable promiscuous mode */
#define LE_C0_ERR 0x8000 /* Error: set if BAB, SQE, MISS or ME is set */
#define LE_C0_BABL 0x4000 /* BAB: Babble: tx timeout. */
#define LE_C0_CERR 0x2000 /* SQE: Signal quality error */
#define LE_C0_MISS 0x1000 /* MISS: Missed a packet */
#define LE_C0_MERR 0x0800 /* ME: Memory error */
#define LE_C0_RINT 0x0400 /* Received interrupt */
#define LE_C0_TINT 0x0200 /* Transmitter Interrupt */
#define LE_C0_IDON 0x0100 /* IFIN: Init finished. */
#define LE_C0_INTR 0x0080 /* Interrupt or error */
#define LE_C0_INEA 0x0040 /* Interrupt enable */
#define LE_C0_RXON 0x0020 /* Receiver on */
#define LE_C0_TXON 0x0010 /* Transmitter on */
#define LE_C0_TDMD 0x0008 /* Transmitter demand */
#define LE_C0_STOP 0x0004 /* Stop the card */
#define LE_C0_STRT 0x0002 /* Start the card */
#define LE_C0_INIT 0x0001 /* Init the card */
#define LE_C3_BSWP 0x4 /* SWAP */
#define LE_C3_ACON 0x2 /* ALE Control */
#define LE_C3_BCON 0x1 /* Byte control */
/* Receive message descriptor 1 */
#define LE_R1_OWN 0x80 /* Who owns the entry */
#define LE_R1_ERR 0x40 /* Error: if FRA, OFL, CRC or BUF is set */
#define LE_R1_FRA 0x20 /* FRA: Frame error */
#define LE_R1_OFL 0x10 /* OFL: Frame overflow */
#define LE_R1_CRC 0x08 /* CRC error */
#define LE_R1_BUF 0x04 /* BUF: Buffer error */
#define LE_R1_SOP 0x02 /* Start of packet */
#define LE_R1_EOP 0x01 /* End of packet */
#define LE_R1_POK 0x03 /* Packet is complete: SOP + EOP */
#define LE_T1_OWN 0x80 /* Lance owns the packet */
#define LE_T1_ERR 0x40 /* Error summary */
#define LE_T1_EMORE 0x10 /* Error: more than one retry needed */
#define LE_T1_EONE 0x08 /* Error: one retry needed */
#define LE_T1_EDEF 0x04 /* Error: deferred */
#define LE_T1_SOP 0x02 /* Start of packet */
#define LE_T1_EOP 0x01 /* End of packet */
#define LE_T1_POK 0x03 /* Packet is complete: SOP + EOP */
#define LE_T3_BUF 0x8000 /* Buffer error */
#define LE_T3_UFL 0x4000 /* Error underflow */
#define LE_T3_LCOL 0x1000 /* Error late collision */
#define LE_T3_CLOS 0x0800 /* Error carrier loss */
#define LE_T3_RTY 0x0400 /* Error retry */
#define LE_T3_TDR 0x03ff /* Time Domain Reflectometry counter */
/* Define: 2^4 Tx buffers and 2^4 Rx buffers */
#ifndef LANCE_LOG_TX_BUFFERS
#define LANCE_LOG_TX_BUFFERS 4
#define LANCE_LOG_RX_BUFFERS 4
#endif
#define TX_RING_SIZE (1 << (LANCE_LOG_TX_BUFFERS))
#define TX_RING_MOD_MASK (TX_RING_SIZE - 1)
#define RX_RING_SIZE (1 << (LANCE_LOG_RX_BUFFERS))
#define RX_RING_MOD_MASK (RX_RING_SIZE - 1)
#define PKT_BUF_SZ 1536
#define RX_BUFF_SIZE PKT_BUF_SZ
#define TX_BUFF_SIZE PKT_BUF_SZ
#undef TEST_HITS
#define ZERO 0
/* The DS2000/3000 have a linear 64 KB buffer.
* The PMAD-AA has 128 kb buffer on-board.
*
* The IOASIC LANCE devices use a shared memory region. This region as seen
* from the CPU is (max) 128 KB long and has to be on an 128 KB boundary.
* The LANCE sees this as a 64 KB long continuous memory region.
*
* The LANCE's DMA address is used as an index in this buffer and DMA takes
* place in bursts of eight 16-Bit words which are packed into four 32-Bit words
* by the IOASIC. This leads to a strange padding: 16 bytes of valid data followed
* by a 16 byte gap :-(.
*/
struct lance_rx_desc {
unsigned short rmd0; /* low address of packet */
short gap0;
unsigned char rmd1_hadr; /* high address of packet */
unsigned char rmd1_bits; /* descriptor bits */
short gap1;
short length; /* 2s complement (negative!)
of buffer length */
short gap2;
unsigned short mblength; /* actual number of bytes received */
short gap3;
};
struct lance_tx_desc {
unsigned short tmd0; /* low address of packet */
short gap0;
unsigned char tmd1_hadr; /* high address of packet */
unsigned char tmd1_bits; /* descriptor bits */
short gap1;
short length; /* 2s complement (negative!)
of buffer length */
short gap2;
unsigned short misc;
short gap3;
};
/* First part of the LANCE initialization block, described in databook. */
struct lance_init_block {
unsigned short mode; /* pre-set mode (reg. 15) */
short gap0;
unsigned char phys_addr[12]; /* physical ethernet address
only 0, 1, 4, 5, 8, 9 are valid
2, 3, 6, 7, 10, 11 are gaps */
unsigned short filter[8]; /* multicast filter
only 0, 2, 4, 6 are valid
1, 3, 5, 7 are gaps */
/* Receive and transmit ring base, along with extra bits. */
unsigned short rx_ptr; /* receive descriptor addr */
short gap1;
unsigned short rx_len; /* receive len and high addr */
short gap2;
unsigned short tx_ptr; /* transmit descriptor addr */
short gap3;
unsigned short tx_len; /* transmit len and high addr */
short gap4;
short gap5[8];
/* The buffer descriptors */
struct lance_rx_desc brx_ring[RX_RING_SIZE];
struct lance_tx_desc btx_ring[TX_RING_SIZE];
};
#define BUF_OFFSET_CPU sizeof(struct lance_init_block)
#define BUF_OFFSET_LNC (sizeof(struct lance_init_block)>>1)
#define libdesc_offset(rt, elem) \
((__u32)(((unsigned long)(&(((struct lance_init_block *)0)->rt[elem])))))
/*
* This works *only* for the ring descriptors
*/
#define LANCE_ADDR(x) (CPHYSADDR(x) >> 1)
struct lance_private {
struct net_device *next;
int type;
int slot;
int dma_irq;
volatile struct lance_regs *ll;
volatile struct lance_init_block *init_block;
spinlock_t lock;
int rx_new, tx_new;
int rx_old, tx_old;
struct net_device_stats stats;
unsigned short busmaster_regval;
struct timer_list multicast_timer;
/* Pointers to the ring buffers as seen from the CPU */
char *rx_buf_ptr_cpu[RX_RING_SIZE];
char *tx_buf_ptr_cpu[TX_RING_SIZE];
/* Pointers to the ring buffers as seen from the LANCE */
char *rx_buf_ptr_lnc[RX_RING_SIZE];
char *tx_buf_ptr_lnc[TX_RING_SIZE];
};
#define TX_BUFFS_AVAIL ((lp->tx_old<=lp->tx_new)?\
lp->tx_old+TX_RING_MOD_MASK-lp->tx_new:\
lp->tx_old - lp->tx_new-1)
/* The lance control ports are at an absolute address, machine and tc-slot
* dependent.
* DECstations do only 32-bit access and the LANCE uses 16 bit addresses,
* so we have to give the structure an extra member making rap pointing
* at the right address
*/
struct lance_regs {
volatile unsigned short rdp; /* register data port */
unsigned short pad;
volatile unsigned short rap; /* register address port */
};
int dec_lance_debug = 2;
static struct net_device *root_lance_dev;
static inline void writereg(volatile unsigned short *regptr, short value)
{
*regptr = value;
iob();
}
/* Load the CSR registers */
static void load_csrs(struct lance_private *lp)
{
volatile struct lance_regs *ll = lp->ll;
int leptr;
/* The address space as seen from the LANCE
* begins at address 0. HK
*/
leptr = 0;
writereg(&ll->rap, LE_CSR1);
writereg(&ll->rdp, (leptr & 0xFFFF));
writereg(&ll->rap, LE_CSR2);
writereg(&ll->rdp, leptr >> 16);
writereg(&ll->rap, LE_CSR3);
writereg(&ll->rdp, lp->busmaster_regval);
/* Point back to csr0 */
writereg(&ll->rap, LE_CSR0);
}
/*
* Our specialized copy routines
*
*/
void cp_to_buf(const int type, void *to, const void *from, int len)
{
unsigned short *tp, *fp, clen;
unsigned char *rtp, *rfp;
if (type == PMAX_LANCE) {
clen = len >> 1;
tp = (unsigned short *) to;
fp = (unsigned short *) from;
while (clen--) {
*tp++ = *fp++;
tp++;
}
clen = len & 1;
rtp = (unsigned char *) tp;
rfp = (unsigned char *) fp;
while (clen--) {
*rtp++ = *rfp++;
}
} else {
/*
* copy 16 Byte chunks
*/
clen = len >> 4;
tp = (unsigned short *) to;
fp = (unsigned short *) from;
while (clen--) {
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
tp += 8;
}
/*
* do the rest, if any.
*/
clen = len & 15;
rtp = (unsigned char *) tp;
rfp = (unsigned char *) fp;
while (clen--) {
*rtp++ = *rfp++;
}
}
iob();
}
void cp_from_buf(const int type, void *to, const void *from, int len)
{
unsigned short *tp, *fp, clen;
unsigned char *rtp, *rfp;
if (type == PMAX_LANCE) {
clen = len >> 1;
tp = (unsigned short *) to;
fp = (unsigned short *) from;
while (clen--) {
*tp++ = *fp++;
fp++;
}
clen = len & 1;
rtp = (unsigned char *) tp;
rfp = (unsigned char *) fp;
while (clen--) {
*rtp++ = *rfp++;
}
} else {
/*
* copy 16 Byte chunks
*/
clen = len >> 4;
tp = (unsigned short *) to;
fp = (unsigned short *) from;
while (clen--) {
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
*tp++ = *fp++;
fp += 8;
}
/*
* do the rest, if any.
*/
clen = len & 15;
rtp = (unsigned char *) tp;
rfp = (unsigned char *) fp;
while (clen--) {
*rtp++ = *rfp++;
}
}
}
/* Setup the Lance Rx and Tx rings */
static void lance_init_ring(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_init_block *ib;
int leptr;
int i;
ib = (struct lance_init_block *) (dev->mem_start);
/* Lock out other processes while setting up hardware */
netif_stop_queue(dev);
lp->rx_new = lp->tx_new = 0;
lp->rx_old = lp->tx_old = 0;
/* Copy the ethernet address to the lance init block.
* XXX bit 0 of the physical address registers has to be zero
*/
ib->phys_addr[0] = dev->dev_addr[0];
ib->phys_addr[1] = dev->dev_addr[1];
ib->phys_addr[4] = dev->dev_addr[2];
ib->phys_addr[5] = dev->dev_addr[3];
ib->phys_addr[8] = dev->dev_addr[4];
ib->phys_addr[9] = dev->dev_addr[5];
/* Setup the initialization block */
/* Setup rx descriptor pointer */
leptr = LANCE_ADDR(libdesc_offset(brx_ring, 0));
ib->rx_len = (LANCE_LOG_RX_BUFFERS << 13) | (leptr >> 16);
ib->rx_ptr = leptr;
if (ZERO)
printk("RX ptr: %8.8x(%8.8x)\n", leptr, libdesc_offset(brx_ring, 0));
/* Setup tx descriptor pointer */
leptr = LANCE_ADDR(libdesc_offset(btx_ring, 0));
ib->tx_len = (LANCE_LOG_TX_BUFFERS << 13) | (leptr >> 16);
ib->tx_ptr = leptr;
if (ZERO)
printk("TX ptr: %8.8x(%8.8x)\n", leptr, libdesc_offset(btx_ring, 0));
if (ZERO)
printk("TX rings:\n");
/* Setup the Tx ring entries */
for (i = 0; i < TX_RING_SIZE; i++) {
leptr = (int) lp->tx_buf_ptr_lnc[i];
ib->btx_ring[i].tmd0 = leptr;
ib->btx_ring[i].tmd1_hadr = leptr >> 16;
ib->btx_ring[i].tmd1_bits = 0;
ib->btx_ring[i].length = 0xf000; /* The ones required by tmd2 */
ib->btx_ring[i].misc = 0;
if (i < 3 && ZERO)
printk("%d: 0x%8.8x(0x%8.8x)\n", i, leptr, (int) lp->tx_buf_ptr_cpu[i]);
}
/* Setup the Rx ring entries */
if (ZERO)
printk("RX rings:\n");
for (i = 0; i < RX_RING_SIZE; i++) {
leptr = (int) lp->rx_buf_ptr_lnc[i];
ib->brx_ring[i].rmd0 = leptr;
ib->brx_ring[i].rmd1_hadr = leptr >> 16;
ib->brx_ring[i].rmd1_bits = LE_R1_OWN;
ib->brx_ring[i].length = -RX_BUFF_SIZE | 0xf000;
ib->brx_ring[i].mblength = 0;
if (i < 3 && ZERO)
printk("%d: 0x%8.8x(0x%8.8x)\n", i, leptr, (int) lp->rx_buf_ptr_cpu[i]);
}
iob();
}
static int init_restart_lance(struct lance_private *lp)
{
volatile struct lance_regs *ll = lp->ll;
int i;
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_INIT);
/* Wait for the lance to complete initialization */
for (i = 0; (i < 100) && !(ll->rdp & LE_C0_IDON); i++) {
udelay(10);
}
if ((i == 100) || (ll->rdp & LE_C0_ERR)) {
printk("LANCE unopened after %d ticks, csr0=%4.4x.\n", i, ll->rdp);
return -1;
}
if ((ll->rdp & LE_C0_ERR)) {
printk("LANCE unopened after %d ticks, csr0=%4.4x.\n", i, ll->rdp);
return -1;
}
writereg(&ll->rdp, LE_C0_IDON);
writereg(&ll->rdp, LE_C0_STRT);
writereg(&ll->rdp, LE_C0_INEA);
return 0;
}
static int lance_rx(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_init_block *ib;
volatile struct lance_rx_desc *rd = 0;
unsigned char bits;
int len = 0;
struct sk_buff *skb = 0;
ib = (struct lance_init_block *) (dev->mem_start);
#ifdef TEST_HITS
{
int i;
printk("[");
for (i = 0; i < RX_RING_SIZE; i++) {
if (i == lp->rx_new)
printk("%s", ib->brx_ring[i].rmd1_bits &
LE_R1_OWN ? "_" : "X");
else
printk("%s", ib->brx_ring[i].rmd1_bits &
LE_R1_OWN ? "." : "1");
}
printk("]");
}
#endif
for (rd = &ib->brx_ring[lp->rx_new];
!((bits = rd->rmd1_bits) & LE_R1_OWN);
rd = &ib->brx_ring[lp->rx_new]) {
/* We got an incomplete frame? */
if ((bits & LE_R1_POK) != LE_R1_POK) {
lp->stats.rx_over_errors++;
lp->stats.rx_errors++;
} else if (bits & LE_R1_ERR) {
/* Count only the end frame as a rx error,
* not the beginning
*/
if (bits & LE_R1_BUF)
lp->stats.rx_fifo_errors++;
if (bits & LE_R1_CRC)
lp->stats.rx_crc_errors++;
if (bits & LE_R1_OFL)
lp->stats.rx_over_errors++;
if (bits & LE_R1_FRA)
lp->stats.rx_frame_errors++;
if (bits & LE_R1_EOP)
lp->stats.rx_errors++;
} else {
len = (rd->mblength & 0xfff) - 4;
skb = dev_alloc_skb(len + 2);
if (skb == 0) {
printk("%s: Memory squeeze, deferring packet.\n",
dev->name);
lp->stats.rx_dropped++;
rd->mblength = 0;
rd->rmd1_bits = LE_R1_OWN;
lp->rx_new = (lp->rx_new + 1) & RX_RING_MOD_MASK;
return 0;
}
lp->stats.rx_bytes += len;
skb->dev = dev;
skb_reserve(skb, 2); /* 16 byte align */
skb_put(skb, len); /* make room */
cp_from_buf(lp->type, skb->data,
(char *)lp->rx_buf_ptr_cpu[lp->rx_new],
len);
skb->protocol = eth_type_trans(skb, dev);
netif_rx(skb);
dev->last_rx = jiffies;
lp->stats.rx_packets++;
}
/* Return the packet to the pool */
rd->mblength = 0;
rd->length = -RX_BUFF_SIZE | 0xf000;
rd->rmd1_bits = LE_R1_OWN;
lp->rx_new = (lp->rx_new + 1) & RX_RING_MOD_MASK;
}
return 0;
}
static void lance_tx(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_init_block *ib;
volatile struct lance_regs *ll = lp->ll;
volatile struct lance_tx_desc *td;
int i, j;
int status;
ib = (struct lance_init_block *) (dev->mem_start);
j = lp->tx_old;
spin_lock(&lp->lock);
for (i = j; i != lp->tx_new; i = j) {
td = &ib->btx_ring[i];
/* If we hit a packet not owned by us, stop */
if (td->tmd1_bits & LE_T1_OWN)
break;
if (td->tmd1_bits & LE_T1_ERR) {
status = td->misc;
lp->stats.tx_errors++;
if (status & LE_T3_RTY)
lp->stats.tx_aborted_errors++;
if (status & LE_T3_LCOL)
lp->stats.tx_window_errors++;
if (status & LE_T3_CLOS) {
lp->stats.tx_carrier_errors++;
printk("%s: Carrier Lost\n", dev->name);
/* Stop the lance */
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_STOP);
lance_init_ring(dev);
load_csrs(lp);
init_restart_lance(lp);
goto out;
}
/* Buffer errors and underflows turn off the
* transmitter, restart the adapter.
*/
if (status & (LE_T3_BUF | LE_T3_UFL)) {
lp->stats.tx_fifo_errors++;
printk("%s: Tx: ERR_BUF|ERR_UFL, restarting\n",
dev->name);
/* Stop the lance */
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_STOP);
lance_init_ring(dev);
load_csrs(lp);
init_restart_lance(lp);
goto out;
}
} else if ((td->tmd1_bits & LE_T1_POK) == LE_T1_POK) {
/*
* So we don't count the packet more than once.
*/
td->tmd1_bits &= ~(LE_T1_POK);
/* One collision before packet was sent. */
if (td->tmd1_bits & LE_T1_EONE)
lp->stats.collisions++;
/* More than one collision, be optimistic. */
if (td->tmd1_bits & LE_T1_EMORE)
lp->stats.collisions += 2;
lp->stats.tx_packets++;
}
j = (j + 1) & TX_RING_MOD_MASK;
}
lp->tx_old = j;
out:
if (netif_queue_stopped(dev) &&
TX_BUFFS_AVAIL > 0)
netif_wake_queue(dev);
spin_unlock(&lp->lock);
}
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 lance_dma_merr_int(const int irq, void *dev_id)
{
struct net_device *dev = dev_id;
printk("%s: DMA error\n", dev->name);
return IRQ_HANDLED;
}
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 lance_interrupt(const int irq, void *dev_id)
{
struct net_device *dev = dev_id;
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_regs *ll = lp->ll;
int csr0;
writereg(&ll->rap, LE_CSR0);
csr0 = ll->rdp;
/* Acknowledge all the interrupt sources ASAP */
writereg(&ll->rdp, csr0 & (LE_C0_INTR | LE_C0_TINT | LE_C0_RINT));
if ((csr0 & LE_C0_ERR)) {
/* Clear the error condition */
writereg(&ll->rdp, LE_C0_BABL | LE_C0_ERR | LE_C0_MISS |
LE_C0_CERR | LE_C0_MERR);
}
if (csr0 & LE_C0_RINT)
lance_rx(dev);
if (csr0 & LE_C0_TINT)
lance_tx(dev);
if (csr0 & LE_C0_BABL)
lp->stats.tx_errors++;
if (csr0 & LE_C0_MISS)
lp->stats.rx_errors++;
if (csr0 & LE_C0_MERR) {
printk("%s: Memory error, status %04x\n", dev->name, csr0);
writereg(&ll->rdp, LE_C0_STOP);
lance_init_ring(dev);
load_csrs(lp);
init_restart_lance(lp);
netif_wake_queue(dev);
}
writereg(&ll->rdp, LE_C0_INEA);
writereg(&ll->rdp, LE_C0_INEA);
return IRQ_HANDLED;
}
struct net_device *last_dev = 0;
static int lance_open(struct net_device *dev)
{
volatile struct lance_init_block *ib = (struct lance_init_block *) (dev->mem_start);
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_regs *ll = lp->ll;
int status = 0;
last_dev = dev;
/* Stop the Lance */
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_STOP);
/* Set mode and clear multicast filter only at device open,
* so that lance_init_ring() called at any error will not
* forget multicast filters.
*
* BTW it is common bug in all lance drivers! --ANK
*/
ib->mode = 0;
ib->filter [0] = 0;
ib->filter [2] = 0;
ib->filter [4] = 0;
ib->filter [6] = 0;
lance_init_ring(dev);
load_csrs(lp);
netif_start_queue(dev);
/* Associate IRQ with lance_interrupt */
if (request_irq(dev->irq, &lance_interrupt, 0, "lance", dev)) {
printk("%s: Can't get IRQ %d\n", dev->name, dev->irq);
return -EAGAIN;
}
if (lp->dma_irq >= 0) {
unsigned long flags;
if (request_irq(lp->dma_irq, &lance_dma_merr_int, 0,
"lance error", dev)) {
free_irq(dev->irq, dev);
printk("%s: Can't get DMA IRQ %d\n", dev->name,
lp->dma_irq);
return -EAGAIN;
}
spin_lock_irqsave(&ioasic_ssr_lock, flags);
fast_mb();
/* Enable I/O ASIC LANCE DMA. */
ioasic_write(IO_REG_SSR,
ioasic_read(IO_REG_SSR) | IO_SSR_LANCE_DMA_EN);
fast_mb();
spin_unlock_irqrestore(&ioasic_ssr_lock, flags);
}
status = init_restart_lance(lp);
return status;
}
static int lance_close(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_regs *ll = lp->ll;
netif_stop_queue(dev);
del_timer_sync(&lp->multicast_timer);
/* Stop the card */
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_STOP);
if (lp->dma_irq >= 0) {
unsigned long flags;
spin_lock_irqsave(&ioasic_ssr_lock, flags);
fast_mb();
/* Disable I/O ASIC LANCE DMA. */
ioasic_write(IO_REG_SSR,
ioasic_read(IO_REG_SSR) & ~IO_SSR_LANCE_DMA_EN);
fast_iob();
spin_unlock_irqrestore(&ioasic_ssr_lock, flags);
free_irq(lp->dma_irq, dev);
}
free_irq(dev->irq, dev);
return 0;
}
static inline int lance_reset(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_regs *ll = lp->ll;
int status;
/* Stop the lance */
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_STOP);
lance_init_ring(dev);
load_csrs(lp);
dev->trans_start = jiffies;
status = init_restart_lance(lp);
return status;
}
static void lance_tx_timeout(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_regs *ll = lp->ll;
printk(KERN_ERR "%s: transmit timed out, status %04x, reset\n",
dev->name, ll->rdp);
lance_reset(dev);
netif_wake_queue(dev);
}
static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_regs *ll = lp->ll;
volatile struct lance_init_block *ib = (struct lance_init_block *) (dev->mem_start);
int entry, skblen, len;
skblen = skb->len;
len = skblen;
if (len < ETH_ZLEN) {
if (skb_padto(skb, ETH_ZLEN))
return 0;
len = ETH_ZLEN;
}
lp->stats.tx_bytes += len;
entry = lp->tx_new & TX_RING_MOD_MASK;
ib->btx_ring[entry].length = (-len);
ib->btx_ring[entry].misc = 0;
cp_to_buf(lp->type, (char *)lp->tx_buf_ptr_cpu[entry], skb->data,
skblen);
/* Clear the slack of the packet, do I need this? */
/* For a firewall it's a good idea - AC */
/*
if (len != skblen)
memset ((char *) &ib->tx_buf [entry][skblen], 0, (len - skblen) << 1);
*/
/* Now, give the packet to the lance */
ib->btx_ring[entry].tmd1_bits = (LE_T1_POK | LE_T1_OWN);
lp->tx_new = (lp->tx_new + 1) & TX_RING_MOD_MASK;
if (TX_BUFFS_AVAIL <= 0)
netif_stop_queue(dev);
/* Kick the lance: transmit now */
writereg(&ll->rdp, LE_C0_INEA | LE_C0_TDMD);
spin_unlock_irq(&lp->lock);
dev->trans_start = jiffies;
dev_kfree_skb(skb);
return 0;
}
static struct net_device_stats *lance_get_stats(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
return &lp->stats;
}
static void lance_load_multicast(struct net_device *dev)
{
volatile struct lance_init_block *ib = (struct lance_init_block *) (dev->mem_start);
volatile u16 *mcast_table = (u16 *) & ib->filter;
struct dev_mc_list *dmi = dev->mc_list;
char *addrs;
int i;
u32 crc;
/* set all multicast bits */
if (dev->flags & IFF_ALLMULTI) {
ib->filter[0] = 0xffff;
ib->filter[2] = 0xffff;
ib->filter[4] = 0xffff;
ib->filter[6] = 0xffff;
return;
}
/* clear the multicast filter */
ib->filter[0] = 0;
ib->filter[2] = 0;
ib->filter[4] = 0;
ib->filter[6] = 0;
/* Add addresses */
for (i = 0; i < dev->mc_count; i++) {
addrs = dmi->dmi_addr;
dmi = dmi->next;
/* multicast address? */
if (!(*addrs & 1))
continue;
crc = ether_crc_le(ETH_ALEN, addrs);
crc = crc >> 26;
mcast_table[2 * (crc >> 4)] |= 1 << (crc & 0xf);
}
return;
}
static void lance_set_multicast(struct net_device *dev)
{
struct lance_private *lp = netdev_priv(dev);
volatile struct lance_init_block *ib;
volatile struct lance_regs *ll = lp->ll;
ib = (struct lance_init_block *) (dev->mem_start);
if (!netif_running(dev))
return;
if (lp->tx_old != lp->tx_new) {
mod_timer(&lp->multicast_timer, jiffies + 4 * HZ/100);
netif_wake_queue(dev);
return;
}
netif_stop_queue(dev);
writereg(&ll->rap, LE_CSR0);
writereg(&ll->rdp, LE_C0_STOP);
lance_init_ring(dev);
if (dev->flags & IFF_PROMISC) {
ib->mode |= LE_MO_PROM;
} else {
ib->mode &= ~LE_MO_PROM;
lance_load_multicast(dev);
}
load_csrs(lp);
init_restart_lance(lp);
netif_wake_queue(dev);
}
static void lance_set_multicast_retry(unsigned long _opaque)
{
struct net_device *dev = (struct net_device *) _opaque;
lance_set_multicast(dev);
}
static int __init dec_lance_init(const int type, const int slot)
{
static unsigned version_printed;
static const char fmt[] = "declance%d";
char name[10];
struct net_device *dev;
struct lance_private *lp;
volatile struct lance_regs *ll;
int i, ret;
unsigned long esar_base;
unsigned char *esar;
if (dec_lance_debug && version_printed++ == 0)
printk(version);
i = 0;
dev = root_lance_dev;
while (dev) {
i++;
lp = (struct lance_private *)dev->priv;
dev = lp->next;
}
snprintf(name, sizeof(name), fmt, i);
dev = alloc_etherdev(sizeof(struct lance_private));
if (!dev) {
printk(KERN_ERR "%s: Unable to allocate etherdev, aborting.\n",
name);
ret = -ENOMEM;
goto err_out;
}
/*
* alloc_etherdev ensures the data structures used by the LANCE
* are aligned.
*/
lp = netdev_priv(dev);
spin_lock_init(&lp->lock);
lp->type = type;
lp->slot = slot;
switch (type) {
#ifdef CONFIG_TC
case ASIC_LANCE:
dev->base_addr = CKSEG1ADDR(dec_kn_slot_base + IOASIC_LANCE);
/* buffer space for the on-board LANCE shared memory */
/*
* FIXME: ugly hack!
*/
dev->mem_start = CKSEG1ADDR(0x00020000);
dev->mem_end = dev->mem_start + 0x00020000;
dev->irq = dec_interrupt[DEC_IRQ_LANCE];
esar_base = CKSEG1ADDR(dec_kn_slot_base + IOASIC_ESAR);
/* Workaround crash with booting KN04 2.1k from Disk */
memset((void *)dev->mem_start, 0,
dev->mem_end - dev->mem_start);
/*
* setup the pointer arrays, this sucks [tm] :-(
*/
for (i = 0; i < RX_RING_SIZE; i++) {
lp->rx_buf_ptr_cpu[i] =
(char *)(dev->mem_start + BUF_OFFSET_CPU +
2 * i * RX_BUFF_SIZE);
lp->rx_buf_ptr_lnc[i] =
(char *)(BUF_OFFSET_LNC + i * RX_BUFF_SIZE);
}
for (i = 0; i < TX_RING_SIZE; i++) {
lp->tx_buf_ptr_cpu[i] =
(char *)(dev->mem_start + BUF_OFFSET_CPU +
2 * RX_RING_SIZE * RX_BUFF_SIZE +
2 * i * TX_BUFF_SIZE);
lp->tx_buf_ptr_lnc[i] =
(char *)(BUF_OFFSET_LNC +
RX_RING_SIZE * RX_BUFF_SIZE +
i * TX_BUFF_SIZE);
}
/* Setup I/O ASIC LANCE DMA. */
lp->dma_irq = dec_interrupt[DEC_IRQ_LANCE_MERR];
ioasic_write(IO_REG_LANCE_DMA_P,
CPHYSADDR(dev->mem_start) << 3);
break;
case PMAD_LANCE:
claim_tc_card(slot);
dev->mem_start = CKSEG1ADDR(get_tc_base_addr(slot));
dev->base_addr = dev->mem_start + 0x100000;
dev->irq = get_tc_irq_nr(slot);
esar_base = dev->mem_start + 0x1c0002;
lp->dma_irq = -1;
for (i = 0; i < RX_RING_SIZE; i++) {
lp->rx_buf_ptr_cpu[i] =
(char *)(dev->mem_start + BUF_OFFSET_CPU +
i * RX_BUFF_SIZE);
lp->rx_buf_ptr_lnc[i] =
(char *)(BUF_OFFSET_LNC + i * RX_BUFF_SIZE);
}
for (i = 0; i < TX_RING_SIZE; i++) {
lp->tx_buf_ptr_cpu[i] =
(char *)(dev->mem_start + BUF_OFFSET_CPU +
RX_RING_SIZE * RX_BUFF_SIZE +
i * TX_BUFF_SIZE);
lp->tx_buf_ptr_lnc[i] =
(char *)(BUF_OFFSET_LNC +
RX_RING_SIZE * RX_BUFF_SIZE +
i * TX_BUFF_SIZE);
}
break;
#endif
case PMAX_LANCE:
dev->irq = dec_interrupt[DEC_IRQ_LANCE];
dev->base_addr = CKSEG1ADDR(KN01_SLOT_BASE + KN01_LANCE);
dev->mem_start = CKSEG1ADDR(KN01_SLOT_BASE + KN01_LANCE_MEM);
esar_base = CKSEG1ADDR(KN01_SLOT_BASE + KN01_ESAR + 1);
lp->dma_irq = -1;
/*
* setup the pointer arrays, this sucks [tm] :-(
*/
for (i = 0; i < RX_RING_SIZE; i++) {
lp->rx_buf_ptr_cpu[i] =
(char *)(dev->mem_start + BUF_OFFSET_CPU +
2 * i * RX_BUFF_SIZE);
lp->rx_buf_ptr_lnc[i] =
(char *)(BUF_OFFSET_LNC + i * RX_BUFF_SIZE);
}
for (i = 0; i < TX_RING_SIZE; i++) {
lp->tx_buf_ptr_cpu[i] =
(char *)(dev->mem_start + BUF_OFFSET_CPU +
2 * RX_RING_SIZE * RX_BUFF_SIZE +
2 * i * TX_BUFF_SIZE);
lp->tx_buf_ptr_lnc[i] =
(char *)(BUF_OFFSET_LNC +
RX_RING_SIZE * RX_BUFF_SIZE +
i * TX_BUFF_SIZE);
}
break;
default:
printk(KERN_ERR "%s: declance_init called with unknown type\n",
name);
ret = -ENODEV;
goto err_out_free_dev;
}
ll = (struct lance_regs *) dev->base_addr;
esar = (unsigned char *) esar_base;
/* prom checks */
/* First, check for test pattern */
if (esar[0x60] != 0xff && esar[0x64] != 0x00 &&
esar[0x68] != 0x55 && esar[0x6c] != 0xaa) {
printk(KERN_ERR
"%s: Ethernet station address prom not found!\n",
name);
ret = -ENODEV;
goto err_out_free_dev;
}
/* Check the prom contents */
for (i = 0; i < 8; i++) {
if (esar[i * 4] != esar[0x3c - i * 4] &&
esar[i * 4] != esar[0x40 + i * 4] &&
esar[0x3c - i * 4] != esar[0x40 + i * 4]) {
printk(KERN_ERR "%s: Something is wrong with the "
"ethernet station address prom!\n", name);
ret = -ENODEV;
goto err_out_free_dev;
}
}
/* Copy the ethernet address to the device structure, later to the
* lance initialization block so the lance gets it every time it's
* (re)initialized.
*/
switch (type) {
case ASIC_LANCE:
printk("%s: IOASIC onboard LANCE, addr = ", name);
break;
case PMAD_LANCE:
printk("%s: PMAD-AA, addr = ", name);
break;
case PMAX_LANCE:
printk("%s: PMAX onboard LANCE, addr = ", name);
break;
}
for (i = 0; i < 6; i++) {
dev->dev_addr[i] = esar[i * 4];
printk("%2.2x%c", dev->dev_addr[i], i == 5 ? ',' : ':');
}
printk(" irq = %d\n", dev->irq);
dev->open = &lance_open;
dev->stop = &lance_close;
dev->hard_start_xmit = &lance_start_xmit;
dev->tx_timeout = &lance_tx_timeout;
dev->watchdog_timeo = 5*HZ;
dev->get_stats = &lance_get_stats;
dev->set_multicast_list = &lance_set_multicast;
/* lp->ll is the location of the registers for lance card */
lp->ll = ll;
/* busmaster_regval (CSR3) should be zero according to the PMAD-AA
* specification.
*/
lp->busmaster_regval = 0;
dev->dma = 0;
/* We cannot sleep if the chip is busy during a
* multicast list update event, because such events
* can occur from interrupts (ex. IPv6). So we
* use a timer to try again later when necessary. -DaveM
*/
init_timer(&lp->multicast_timer);
lp->multicast_timer.data = (unsigned long) dev;
lp->multicast_timer.function = &lance_set_multicast_retry;
ret = register_netdev(dev);
if (ret) {
printk(KERN_ERR
"%s: Unable to register netdev, aborting.\n", name);
goto err_out_free_dev;
}
lp->next = root_lance_dev;
root_lance_dev = dev;
printk("%s: registered as %s.\n", name, dev->name);
return 0;
err_out_free_dev:
free_netdev(dev);
err_out:
return ret;
}
/* Find all the lance cards on the system and initialize them */
static int __init dec_lance_probe(void)
{
int count = 0;
/* Scan slots for PMAD-AA cards first. */
#ifdef CONFIG_TC
if (TURBOCHANNEL) {
int slot;
while ((slot = search_tc_card("PMAD-AA")) >= 0) {
if (dec_lance_init(PMAD_LANCE, slot) < 0)
break;
count++;
}
}
#endif
/* Then handle onboard devices. */
if (dec_interrupt[DEC_IRQ_LANCE] >= 0) {
if (dec_interrupt[DEC_IRQ_LANCE_MERR] >= 0) {
#ifdef CONFIG_TC
if (dec_lance_init(ASIC_LANCE, -1) >= 0)
count++;
#endif
} else if (!TURBOCHANNEL) {
if (dec_lance_init(PMAX_LANCE, -1) >= 0)
count++;
}
}
return (count > 0) ? 0 : -ENODEV;
}
static void __exit dec_lance_cleanup(void)
{
while (root_lance_dev) {
struct net_device *dev = root_lance_dev;
struct lance_private *lp = netdev_priv(dev);
unregister_netdev(dev);
#ifdef CONFIG_TC
if (lp->slot >= 0)
release_tc_card(lp->slot);
#endif
root_lance_dev = lp->next;
free_netdev(dev);
}
}
module_init(dec_lance_probe);
module_exit(dec_lance_cleanup);