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/znet.c

925 lines
29 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
/* znet.c: An Zenith Z-Note ethernet driver for linux. */
/*
Written by Donald Becker.
The author may be reached as becker@scyld.com.
This driver is based on the Linux skeleton driver. The copyright of the
skeleton driver is held by the United States Government, as represented
by DIRNSA, and it is released under the GPL.
Thanks to Mike Hollick for alpha testing and suggestions.
References:
The Crynwr packet driver.
"82593 CSMA/CD Core LAN Controller" Intel datasheet, 1992
Intel Microcommunications Databook, Vol. 1, 1990.
As usual with Intel, the documentation is incomplete and inaccurate.
I had to read the Crynwr packet driver to figure out how to actually
use the i82593, and guess at what register bits matched the loosely
related i82586.
Theory of Operation
The i82593 used in the Zenith Z-Note series operates using two(!) slave
DMA channels, one interrupt, and one 8-bit I/O port.
While there several ways to configure '593 DMA system, I chose the one
that seemed commensurate with the highest system performance in the face
of moderate interrupt latency: Both DMA channels are configured as
recirculating ring buffers, with one channel (#0) dedicated to Rx and
the other channel (#1) to Tx and configuration. (Note that this is
different than the Crynwr driver, where the Tx DMA channel is initialized
before each operation. That approach simplifies operation and Tx error
recovery, but requires additional I/O in normal operation and precludes
transmit buffer chaining.)
Both rings are set to 8192 bytes using {TX,RX}_RING_SIZE. This provides
a reasonable ring size for Rx, while simplifying DMA buffer allocation --
DMA buffers must not cross a 128K boundary. (In truth the size selection
was influenced by my lack of '593 documentation. I thus was constrained
to use the Crynwr '593 initialization table, which sets the Rx ring size
to 8K.)
Despite my usual low opinion about Intel-designed parts, I must admit
that the bulk data handling of the i82593 is a good design for
an integrated system, like a laptop, where using two slave DMA channels
doesn't pose a problem. I still take issue with using only a single I/O
port. In the same controlled environment there are essentially no
limitations on I/O space, and using multiple locations would eliminate
the need for multiple operations when looking at status registers,
setting the Rx ring boundary, or switching to promiscuous mode.
I also question Zenith's selection of the '593: one of the advertised
advantages of earlier Intel parts was that if you figured out the magic
initialization incantation you could use the same part on many different
network types. Zenith's use of the "FriendlyNet" (sic) connector rather
than an on-board transceiver leads me to believe that they were planning
to take advantage of this. But, uhmmm, the '593 omits all but ethernet
functionality from the serial subsystem.
*/
/* 10/2002
o Resurected for Linux 2.5+ by Marc Zyngier <maz@wild-wind.fr.eu.org> :
- Removed strange DMA snooping in znet_sent_packet, which lead to
TX buffer corruption on my laptop.
- Use init_etherdev stuff.
- Use kmalloc-ed DMA buffers.
- Use as few global variables as possible.
- Use proper resources management.
- Use wireless/i82593.h as much as possible (structure, constants)
- Compiles as module or build-in.
- Now survives unplugging/replugging cable.
Some code was taken from wavelan_cs.
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
Tested on a vintage Zenith Z-Note 433Lnp+. Probably broken on
anything else. Testers (and detailed bug reports) are welcome :-).
o TODO :
- Properly handle multicast
- Understand why some traffic patterns add a 1s latency...
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.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 <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/bitops.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/dma.h>
znet: fix build failure from i82593.h relocation znet was including "wireless/i82593.h" (which is a bit wierd), and I missed that when I relocated i82593.h to drivers/staging/wavelan. Since I don't have ISA turned-on in my normal .config, I didn't see the build failures -- mea culpa! Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-11-17 23:16:32 +08:00
#include <linux/i82593.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
static char version[] __initdata = "znet.c:v1.02 9/23/94 becker@scyld.com\n";
#ifndef ZNET_DEBUG
#define ZNET_DEBUG 1
#endif
static unsigned int znet_debug = ZNET_DEBUG;
module_param (znet_debug, int, 0);
MODULE_PARM_DESC (znet_debug, "ZNet debug level");
MODULE_LICENSE("GPL");
/* The DMA modes we need aren't in <dma.h>. */
#define DMA_RX_MODE 0x14 /* Auto init, I/O to mem, ++, demand. */
#define DMA_TX_MODE 0x18 /* Auto init, Mem to I/O, ++, demand. */
#define dma_page_eq(ptr1, ptr2) ((long)(ptr1)>>17 == (long)(ptr2)>>17)
#define RX_BUF_SIZE 8192
#define TX_BUF_SIZE 8192
#define DMA_BUF_SIZE (RX_BUF_SIZE + 16) /* 8k + 16 bytes for trailers */
#define TX_TIMEOUT 10
struct znet_private {
int rx_dma, tx_dma;
spinlock_t lock;
short sia_base, sia_size, io_size;
struct i82593_conf_block i593_init;
/* The starting, current, and end pointers for the packet buffers. */
ushort *rx_start, *rx_cur, *rx_end;
ushort *tx_start, *tx_cur, *tx_end;
ushort tx_buf_len; /* Tx buffer length, in words. */
};
/* Only one can be built-in;-> */
static struct net_device *znet_dev;
struct netidblk {
char magic[8]; /* The magic number (string) "NETIDBLK" */
unsigned char netid[8]; /* The physical station address */
char nettype, globalopt;
char vendor[8]; /* The machine vendor and product name. */
char product[8];
char irq1, irq2; /* Interrupts, only one is currently used. */
char dma1, dma2;
short dma_mem_misc[8]; /* DMA buffer locations (unused in Linux). */
short iobase1, iosize1;
short iobase2, iosize2; /* Second iobase unused. */
char driver_options; /* Misc. bits */
char pad;
};
static int znet_open(struct net_device *dev);
netdev: convert bulk of drivers to netdev_tx_t In a couple of cases collapse some extra code like: int retval = NETDEV_TX_OK; ... return retval; into return NETDEV_TX_OK; Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-01 03:50:58 +08:00
static netdev_tx_t znet_send_packet(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 znet_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 znet_rx(struct net_device *dev);
static int znet_close(struct net_device *dev);
static void hardware_init(struct net_device *dev);
static void update_stop_hit(short ioaddr, unsigned short rx_stop_offset);
static void znet_tx_timeout (struct net_device *dev);
/* Request needed resources */
static int znet_request_resources (struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(dev);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
drivers/net: request_irq - Remove unnecessary leading & from second arg Not as fancy as coccinelle. Checkpatch errors ignored. Compile tested allyesconfig x86, not all files compiled. grep -rPl --include=*.[ch] "\brequest_irq\s*\([^,\)]+,\s*\&" drivers/net | while read file ; do \ perl -i -e 'local $/; while (<>) { s@(\brequest_irq\s*\([^,\)]+,\s*)\&@\1@g ; print ; }' $file ;\ done Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-19 15:29:17 +08:00
if (request_irq (dev->irq, znet_interrupt, 0, "ZNet", 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
goto failed;
if (request_dma (znet->rx_dma, "ZNet rx"))
goto free_irq;
if (request_dma (znet->tx_dma, "ZNet tx"))
goto free_rx_dma;
if (!request_region (znet->sia_base, znet->sia_size, "ZNet SIA"))
goto free_tx_dma;
if (!request_region (dev->base_addr, znet->io_size, "ZNet I/O"))
goto free_sia;
return 0; /* Happy ! */
free_sia:
release_region (znet->sia_base, znet->sia_size);
free_tx_dma:
free_dma (znet->tx_dma);
free_rx_dma:
free_dma (znet->rx_dma);
free_irq:
free_irq (dev->irq, dev);
failed:
return -1;
}
static void znet_release_resources (struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(dev);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
release_region (znet->sia_base, znet->sia_size);
release_region (dev->base_addr, znet->io_size);
free_dma (znet->tx_dma);
free_dma (znet->rx_dma);
free_irq (dev->irq, dev);
}
/* Keep the magical SIA stuff in a single function... */
static void znet_transceiver_power (struct net_device *dev, int on)
{
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
unsigned char v;
/* Turn on/off the 82501 SIA, using zenith-specific magic. */
/* Select LAN control register */
outb(0x10, znet->sia_base);
if (on)
v = inb(znet->sia_base + 1) | 0x84;
else
v = inb(znet->sia_base + 1) & ~0x84;
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
outb(v, znet->sia_base+1); /* Turn on/off LAN power (bit 2). */
}
/* Init the i82593, with current promisc/mcast configuration.
Also used from hardware_init. */
static void znet_set_multicast_list (struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
short ioaddr = dev->base_addr;
struct i82593_conf_block *cfblk = &znet->i593_init;
memset(cfblk, 0x00, sizeof(struct i82593_conf_block));
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* The configuration block. What an undocumented nightmare.
The first set of values are those suggested (without explanation)
for ethernet in the Intel 82586 databook. The rest appear to be
completely undocumented, except for cryptic notes in the Crynwr
packet driver. This driver uses the Crynwr values verbatim. */
/* maz : Rewritten to take advantage of the wanvelan includes.
At least we have names, not just blind values */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 0 */
cfblk->fifo_limit = 10; /* = 16 B rx and 80 B tx fifo thresholds */
cfblk->forgnesi = 0; /* 0=82C501, 1=AMD7992B compatibility */
cfblk->fifo_32 = 1;
cfblk->d6mod = 0; /* Run in i82593 advanced mode */
cfblk->throttle_enb = 1;
/* Byte 1 */
cfblk->throttle = 8; /* Continuous w/interrupts, 128-clock DMA. */
cfblk->cntrxint = 0; /* enable continuous mode receive interrupts */
cfblk->contin = 1; /* enable continuous mode */
/* Byte 2 */
cfblk->addr_len = ETH_ALEN;
cfblk->acloc = 1; /* Disable source addr insertion by i82593 */
cfblk->preamb_len = 2; /* 8 bytes preamble */
cfblk->loopback = 0; /* Loopback off */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 3 */
cfblk->lin_prio = 0; /* Default priorities & backoff methods. */
cfblk->tbofstop = 0;
cfblk->exp_prio = 0;
cfblk->bof_met = 0;
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 4 */
cfblk->ifrm_spc = 6; /* 96 bit times interframe spacing */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 5 */
cfblk->slottim_low = 0; /* 512 bit times slot time (low) */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 6 */
cfblk->slottim_hi = 2; /* 512 bit times slot time (high) */
cfblk->max_retr = 15; /* 15 collisions retries */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 7 */
cfblk->prmisc = ((dev->flags & IFF_PROMISC) ? 1 : 0); /* Promiscuous mode */
cfblk->bc_dis = 0; /* Enable broadcast reception */
cfblk->crs_1 = 0; /* Don't transmit without carrier sense */
cfblk->nocrc_ins = 0; /* i82593 generates CRC */
cfblk->crc_1632 = 0; /* 32-bit Autodin-II CRC */
cfblk->crs_cdt = 0; /* CD not to be interpreted as CS */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 8 */
cfblk->cs_filter = 0; /* CS is recognized immediately */
cfblk->crs_src = 0; /* External carrier sense */
cfblk->cd_filter = 0; /* CD is recognized immediately */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte 9 */
cfblk->min_fr_len = ETH_ZLEN >> 2; /* Minimum frame length */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte A */
cfblk->lng_typ = 1; /* Type/length checks OFF */
cfblk->lng_fld = 1; /* Disable 802.3 length field check */
cfblk->rxcrc_xf = 1; /* Don't transfer CRC to memory */
cfblk->artx = 1; /* Disable automatic retransmission */
cfblk->sarec = 1; /* Disable source addr trig of CD */
cfblk->tx_jabber = 0; /* Disable jabber jam sequence */
cfblk->hash_1 = 1; /* Use bits 0-5 in mc address hash */
cfblk->lbpkpol = 0; /* Loopback pin active high */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte B */
cfblk->fdx = 0; /* Disable full duplex operation */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte C */
cfblk->dummy_6 = 0x3f; /* all ones, Default multicast addresses & backoff. */
cfblk->mult_ia = 0; /* No multiple individual addresses */
cfblk->dis_bof = 0; /* Disable the backoff algorithm ?! */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte D */
cfblk->dummy_1 = 1; /* set to 1 */
cfblk->tx_ifs_retrig = 3; /* Hmm... Disabled */
net: convert multiple drivers to use netdev_for_each_mc_addr, part6 Signed-off-by: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-24 07:17:07 +08:00
cfblk->mc_all = (!netdev_mc_empty(dev) ||
(dev->flags & IFF_ALLMULTI)); /* multicast all mode */
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
cfblk->rcv_mon = 0; /* Monitor mode disabled */
cfblk->frag_acpt = 0; /* Do not accept fragments */
cfblk->tstrttrs = 0; /* No start transmission threshold */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Byte E */
cfblk->fretx = 1; /* FIFO automatic retransmission */
cfblk->runt_eop = 0; /* drop "runt" packets */
cfblk->hw_sw_pin = 0; /* ?? */
cfblk->big_endn = 0; /* Big Endian ? no... */
cfblk->syncrqs = 1; /* Synchronous DRQ deassertion... */
cfblk->sttlen = 1; /* 6 byte status registers */
cfblk->rx_eop = 0; /* Signal EOP on packet reception */
cfblk->tx_eop = 0; /* Signal EOP on packet transmission */
/* Byte F */
cfblk->rbuf_size = RX_BUF_SIZE >> 12; /* Set receive buffer size */
cfblk->rcvstop = 1; /* Enable Receive Stop Register */
if (znet_debug > 2) {
int i;
unsigned char *c;
for (i = 0, c = (char *) cfblk; i < sizeof (*cfblk); i++)
printk ("%02X ", c[i]);
printk ("\n");
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
*znet->tx_cur++ = sizeof(struct i82593_conf_block);
memcpy(znet->tx_cur, cfblk, sizeof(struct i82593_conf_block));
znet->tx_cur += sizeof(struct i82593_conf_block)/2;
outb(OP0_CONFIGURE | CR0_CHNL, ioaddr);
/* XXX FIXME maz : Add multicast addresses here, so having a
* multicast address configured isn't equal to IFF_ALLMULTI */
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
znet: convert to net_device_ops Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-09 21:01:27 +08:00
static const struct net_device_ops znet_netdev_ops = {
.ndo_open = znet_open,
.ndo_stop = znet_close,
.ndo_start_xmit = znet_send_packet,
.ndo_set_multicast_list = znet_set_multicast_list,
.ndo_tx_timeout = znet_tx_timeout,
.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
/* The Z-Note probe is pretty easy. The NETIDBLK exists in the safe-to-probe
BIOS area. We just scan for the signature, and pull the vital parameters
out of the structure. */
static int __init znet_probe (void)
{
int i;
struct netidblk *netinfo;
struct znet_private *znet;
struct net_device *dev;
char *p;
int err = -ENOMEM;
/* This code scans the region 0xf0000 to 0xfffff for a "NETIDBLK". */
for(p = (char *)phys_to_virt(0xf0000); p < (char *)phys_to_virt(0x100000); p++)
if (*p == 'N' && strncmp(p, "NETIDBLK", 8) == 0)
break;
if (p >= (char *)phys_to_virt(0x100000)) {
if (znet_debug > 1)
printk(KERN_INFO "No Z-Note ethernet adaptor found.\n");
return -ENODEV;
}
dev = alloc_etherdev(sizeof(struct znet_private));
if (!dev)
return -ENOMEM;
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
znet = netdev_priv(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
netinfo = (struct netidblk *)p;
dev->base_addr = netinfo->iobase1;
dev->irq = netinfo->irq1;
/* The station address is in the "netidblk" at 0x0f0000. */
for (i = 0; i < 6; i++)
[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->dev_addr[i] = netinfo->netid[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
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
printk(KERN_INFO "%s: ZNET at %#3lx, %pM"
[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
", using IRQ %d DMA %d and %d.\n",
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->name, dev->base_addr, dev->dev_addr,
[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->irq, netinfo->dma1, netinfo->dma2);
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 (znet_debug > 1) {
printk(KERN_INFO "%s: vendor '%16.16s' IRQ1 %d IRQ2 %d DMA1 %d DMA2 %d.\n",
dev->name, netinfo->vendor,
netinfo->irq1, netinfo->irq2,
netinfo->dma1, netinfo->dma2);
printk(KERN_INFO "%s: iobase1 %#x size %d iobase2 %#x size %d net type %2.2x.\n",
dev->name, netinfo->iobase1, netinfo->iosize1,
netinfo->iobase2, netinfo->iosize2, netinfo->nettype);
}
if (znet_debug > 0)
printk(KERN_INFO "%s", version);
znet->rx_dma = netinfo->dma1;
znet->tx_dma = netinfo->dma2;
spin_lock_init(&znet->lock);
znet->sia_base = 0xe6; /* Magic address for the 82501 SIA */
znet->sia_size = 2;
/* maz: Despite the '593 being advertised above as using a
* single 8bits I/O port, this driver does many 16bits
* access. So set io_size accordingly */
znet->io_size = 2;
if (!(znet->rx_start = kmalloc (DMA_BUF_SIZE, GFP_KERNEL | GFP_DMA)))
goto free_dev;
if (!(znet->tx_start = kmalloc (DMA_BUF_SIZE, GFP_KERNEL | GFP_DMA)))
goto free_rx;
if (!dma_page_eq (znet->rx_start, znet->rx_start + (RX_BUF_SIZE/2-1)) ||
!dma_page_eq (znet->tx_start, znet->tx_start + (TX_BUF_SIZE/2-1))) {
printk (KERN_WARNING "tx/rx crossing DMA frontiers, giving up\n");
goto free_tx;
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
znet->rx_end = znet->rx_start + RX_BUF_SIZE/2;
znet->tx_buf_len = TX_BUF_SIZE/2;
znet->tx_end = znet->tx_start + znet->tx_buf_len;
/* The ZNET-specific entries in the device structure. */
znet: convert to net_device_ops Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-09 21:01:27 +08:00
dev->netdev_ops = &znet_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
dev->watchdog_timeo = TX_TIMEOUT;
err = register_netdev(dev);
if (err)
goto free_tx;
znet_dev = dev;
return 0;
free_tx:
kfree(znet->tx_start);
free_rx:
kfree(znet->rx_start);
free_dev:
free_netdev(dev);
return err;
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
static int znet_open(struct net_device *dev)
{
int ioaddr = dev->base_addr;
if (znet_debug > 2)
printk(KERN_DEBUG "%s: znet_open() called.\n", dev->name);
/* These should never fail. You can't add devices to a sealed box! */
if (znet_request_resources (dev)) {
printk(KERN_WARNING "%s: Not opened -- resource busy?!?\n", dev->name);
return -EBUSY;
}
znet_transceiver_power (dev, 1);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* According to the Crynwr driver we should wait 50 msec. for the
LAN clock to stabilize. My experiments indicates that the '593 can
be initialized immediately. The delay is probably needed for the
DC-to-DC converter to come up to full voltage, and for the oscillator
to be spot-on at 20Mhz before transmitting.
Until this proves to be a problem we rely on the higher layers for the
delay and save allocating a timer entry. */
/* maz : Well, I'm getting every time the following message
* without the delay on a 486@33. This machine is much too
* fast... :-) So maybe the Crynwr driver wasn't wrong after
* all, even if the message is completly harmless on my
* setup. */
mdelay (50);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* This follows the packet driver's lead, and checks for success. */
if (inb(ioaddr) != 0x10 && inb(ioaddr) != 0x00)
printk(KERN_WARNING "%s: Problem turning on the transceiver power.\n",
dev->name);
hardware_init(dev);
netif_start_queue (dev);
return 0;
}
static void znet_tx_timeout (struct net_device *dev)
{
int ioaddr = dev->base_addr;
ushort event, tx_status, rx_offset, state;
outb (CR0_STATUS_0, ioaddr);
event = inb (ioaddr);
outb (CR0_STATUS_1, ioaddr);
tx_status = inw (ioaddr);
outb (CR0_STATUS_2, ioaddr);
rx_offset = inw (ioaddr);
outb (CR0_STATUS_3, ioaddr);
state = inb (ioaddr);
printk (KERN_WARNING "%s: transmit timed out, status %02x %04x %04x %02x,"
" resetting.\n", dev->name, event, tx_status, rx_offset, state);
if (tx_status == TX_LOST_CRS)
printk (KERN_WARNING "%s: Tx carrier error, check transceiver cable.\n",
dev->name);
outb (OP0_RESET, ioaddr);
hardware_init (dev);
netif_wake_queue (dev);
}
netdev: convert bulk of drivers to netdev_tx_t In a couple of cases collapse some extra code like: int retval = NETDEV_TX_OK; ... return retval; into return NETDEV_TX_OK; Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-01 03:50:58 +08:00
static netdev_tx_t znet_send_packet(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
{
int ioaddr = dev->base_addr;
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
unsigned long flags;
short length = skb->len;
if (znet_debug > 4)
printk(KERN_DEBUG "%s: ZNet_send_packet.\n", dev->name);
if (length < ETH_ZLEN) {
[NET]: Avoid allocating skb in skb_pad First of all it is unnecessary to allocate a new skb in skb_pad since the existing one is not shared. More importantly, our hard_start_xmit interface does not allow a new skb to be allocated since that breaks requeueing. This patch uses pskb_expand_head to expand the existing skb and linearize it if needed. Actually, someone should sift through every instance of skb_pad on a non-linear skb as they do not fit the reasons why this was originally created. Incidentally, this fixes a minor bug when the skb is cloned (tcpdump, TCP, etc.). As it is skb_pad will simply write over a cloned skb. Because of the position of the write it is unlikely to cause problems but still it's best if we don't do it. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-23 17:06:41 +08:00
if (skb_padto(skb, ETH_ZLEN))
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
length = ETH_ZLEN;
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
netif_stop_queue (dev);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
/* Check that the part hasn't reset itself, probably from suspend. */
outb(CR0_STATUS_0, ioaddr);
if (inw(ioaddr) == 0x0010 &&
inw(ioaddr) == 0x0000 &&
inw(ioaddr) == 0x0010) {
if (znet_debug > 1)
printk (KERN_WARNING "%s : waking up\n", dev->name);
hardware_init(dev);
znet_transceiver_power (dev, 1);
}
if (1) {
unsigned char *buf = (void *)skb->data;
ushort *tx_link = znet->tx_cur - 1;
ushort rnd_len = (length + 1)>>1;
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.tx_bytes+=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 (znet->tx_cur >= znet->tx_end)
znet->tx_cur = znet->tx_start;
*znet->tx_cur++ = length;
if (znet->tx_cur + rnd_len + 1 > znet->tx_end) {
int semi_cnt = (znet->tx_end - znet->tx_cur)<<1; /* Cvrt to byte cnt. */
memcpy(znet->tx_cur, buf, semi_cnt);
rnd_len -= semi_cnt>>1;
memcpy(znet->tx_start, buf + semi_cnt, length - semi_cnt);
znet->tx_cur = znet->tx_start + rnd_len;
} else {
memcpy(znet->tx_cur, buf, skb->len);
znet->tx_cur += rnd_len;
}
*znet->tx_cur++ = 0;
spin_lock_irqsave(&znet->lock, flags);
{
*tx_link = OP0_TRANSMIT | CR0_CHNL;
/* Is this always safe to do? */
outb(OP0_TRANSMIT | CR0_CHNL, ioaddr);
}
spin_unlock_irqrestore (&znet->lock, flags);
netif_start_queue (dev);
if (znet_debug > 4)
printk(KERN_DEBUG "%s: Transmitter queued, length %d.\n", dev->name, length);
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
dev_kfree_skb(skb);
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
}
/* The ZNET interrupt handler. */
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 znet_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;
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
int ioaddr;
int boguscnt = 20;
int handled = 0;
spin_lock (&znet->lock);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
ioaddr = dev->base_addr;
outb(CR0_STATUS_0, ioaddr);
do {
ushort status = inb(ioaddr);
if (znet_debug > 5) {
ushort result, rx_ptr, running;
outb(CR0_STATUS_1, ioaddr);
result = inw(ioaddr);
outb(CR0_STATUS_2, ioaddr);
rx_ptr = inw(ioaddr);
outb(CR0_STATUS_3, ioaddr);
running = inb(ioaddr);
printk(KERN_DEBUG "%s: interrupt, status %02x, %04x %04x %02x serial %d.\n",
dev->name, status, result, rx_ptr, running, boguscnt);
}
if ((status & SR0_INTERRUPT) == 0)
break;
handled = 1;
if ((status & SR0_EVENT_MASK) == SR0_TRANSMIT_DONE ||
(status & SR0_EVENT_MASK) == SR0_RETRANSMIT_DONE ||
(status & SR0_EVENT_MASK) == SR0_TRANSMIT_NO_CRC_DONE) {
int tx_status;
outb(CR0_STATUS_1, ioaddr);
tx_status = inw(ioaddr);
/* It's undocumented, but tx_status seems to match the i82586. */
if (tx_status & TX_OK) {
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.tx_packets++;
dev->stats.collisions += tx_status & TX_NCOL_MASK;
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 (tx_status & (TX_LOST_CTS | TX_LOST_CRS))
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.tx_carrier_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 & TX_UND_RUN)
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.tx_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 (!(tx_status & TX_HRT_BEAT))
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.tx_heartbeat_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 & TX_MAX_COL)
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +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
/* ...and the catch-all. */
if ((tx_status | (TX_LOST_CRS | TX_LOST_CTS | TX_UND_RUN | TX_HRT_BEAT | TX_MAX_COL)) != (TX_LOST_CRS | TX_LOST_CTS | TX_UND_RUN | TX_HRT_BEAT | TX_MAX_COL))
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +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
/* Transceiver may be stuck if cable
* was removed while emiting a
* packet. Flip it off, then on to
* reset it. This is very empirical,
* but it seems to work. */
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
znet_transceiver_power (dev, 0);
znet_transceiver_power (dev, 1);
}
netif_wake_queue (dev);
}
if ((status & SR0_RECEPTION) ||
(status & SR0_EVENT_MASK) == SR0_STOP_REG_HIT) {
znet_rx(dev);
}
/* Clear the interrupts we've handled. */
outb(CR0_INT_ACK, ioaddr);
} while (boguscnt--);
spin_unlock (&znet->lock);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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 IRQ_RETVAL(handled);
}
static void znet_rx(struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
int ioaddr = dev->base_addr;
int boguscount = 1;
short next_frame_end_offset = 0; /* Offset of next frame start. */
short *cur_frame_end;
short cur_frame_end_offset;
outb(CR0_STATUS_2, ioaddr);
cur_frame_end_offset = inw(ioaddr);
if (cur_frame_end_offset == znet->rx_cur - znet->rx_start) {
printk(KERN_WARNING "%s: Interrupted, but nothing to receive, offset %03x.\n",
dev->name, cur_frame_end_offset);
return;
}
/* Use same method as the Crynwr driver: construct a forward list in
the same area of the backwards links we now have. This allows us to
pass packets to the upper layers in the order they were received --
important for fast-path sequential operations. */
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
while (znet->rx_start + cur_frame_end_offset != znet->rx_cur &&
++boguscount < 5) {
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
unsigned short hi_cnt, lo_cnt, hi_status, lo_status;
int count, status;
if (cur_frame_end_offset < 4) {
/* Oh no, we have a special case: the frame trailer wraps around
the end of the ring buffer. We've saved space at the end of
the ring buffer for just this problem. */
memcpy(znet->rx_end, znet->rx_start, 8);
cur_frame_end_offset += (RX_BUF_SIZE/2);
}
cur_frame_end = znet->rx_start + cur_frame_end_offset - 4;
lo_status = *cur_frame_end++;
hi_status = *cur_frame_end++;
status = ((hi_status & 0xff) << 8) + (lo_status & 0xff);
lo_cnt = *cur_frame_end++;
hi_cnt = *cur_frame_end++;
count = ((hi_cnt & 0xff) << 8) + (lo_cnt & 0xff);
if (znet_debug > 5)
printk(KERN_DEBUG "Constructing trailer at location %03x, %04x %04x %04x %04x"
" count %#x status %04x.\n",
cur_frame_end_offset<<1, lo_status, hi_status, lo_cnt, hi_cnt,
count, status);
cur_frame_end[-4] = status;
cur_frame_end[-3] = next_frame_end_offset;
cur_frame_end[-2] = count;
next_frame_end_offset = cur_frame_end_offset;
cur_frame_end_offset -= ((count + 1)>>1) + 3;
if (cur_frame_end_offset < 0)
cur_frame_end_offset += RX_BUF_SIZE/2;
};
/* Now step forward through the list. */
do {
ushort *this_rfp_ptr = znet->rx_start + next_frame_end_offset;
int status = this_rfp_ptr[-4];
int pkt_len = this_rfp_ptr[-2];
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
if (znet_debug > 5)
printk(KERN_DEBUG "Looking at trailer ending at %04x status %04x length %03x"
" next %04x.\n", next_frame_end_offset<<1, status, pkt_len,
this_rfp_ptr[-3]<<1);
/* Once again we must assume that the i82586 docs apply. */
if ( ! (status & RX_RCV_OK)) { /* There was an error. */
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.rx_errors++;
if (status & RX_CRC_ERR) dev->stats.rx_crc_errors++;
if (status & RX_ALG_ERR) 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 0
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
if (status & 0x0200) dev->stats.rx_over_errors++; /* Wrong. */
if (status & 0x0100) 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
#else
/* maz : Wild guess... */
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
if (status & RX_OVRRUN) dev->stats.rx_over_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
#endif
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
if (status & RX_SRT_FRM) dev->stats.rx_length_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
} else if (pkt_len > 1536) {
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.rx_length_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
} else {
/* Malloc up new buffer. */
struct sk_buff *skb;
skb = dev_alloc_skb(pkt_len);
if (skb == NULL) {
if (znet_debug)
printk(KERN_WARNING "%s: Memory squeeze, dropping packet.\n", dev->name);
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +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
break;
}
if (&znet->rx_cur[(pkt_len+1)>>1] > znet->rx_end) {
int semi_cnt = (znet->rx_end - znet->rx_cur)<<1;
memcpy(skb_put(skb,semi_cnt), znet->rx_cur, semi_cnt);
memcpy(skb_put(skb,pkt_len-semi_cnt), znet->rx_start,
pkt_len - semi_cnt);
} else {
memcpy(skb_put(skb,pkt_len), znet->rx_cur, pkt_len);
if (znet_debug > 6) {
unsigned int *packet = (unsigned int *) skb->data;
printk(KERN_DEBUG "Packet data is %08x %08x %08x %08x.\n", packet[0],
packet[1], packet[2], packet[3]);
}
}
skb->protocol=eth_type_trans(skb,dev);
netif_rx(skb);
[NET] drivers/net: statistics cleanup #1 -- save memory and shrink code We now have struct net_device_stats embedded in struct net_device, and the default ->get_stats() hook does the obvious thing for us. Run through drivers/net/* and remove the driver-local storage of statistics, and driver-local ->get_stats() hook where applicable. This was just the low-hanging fruit in drivers/net; plenty more drivers remain to be updated. [ Resolved conflicts with napi_struct changes and fix sunqe build regression... -DaveM ] Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 08:41:50 +08:00
dev->stats.rx_packets++;
dev->stats.rx_bytes += pkt_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
}
znet->rx_cur = this_rfp_ptr;
if (znet->rx_cur >= znet->rx_end)
znet->rx_cur -= RX_BUF_SIZE/2;
update_stop_hit(ioaddr, (znet->rx_cur - znet->rx_start)<<1);
next_frame_end_offset = this_rfp_ptr[-3];
if (next_frame_end_offset == 0) /* Read all the frames? */
break; /* Done for now */
this_rfp_ptr = znet->rx_start + next_frame_end_offset;
} while (--boguscount);
/* If any worth-while packets have been received, dev_rint()
has done a mark_bh(INET_BH) for us and will work on them
when we get to the bottom-half routine. */
}
/* The inverse routine to znet_open(). */
static int znet_close(struct net_device *dev)
{
int ioaddr = dev->base_addr;
netif_stop_queue (dev);
outb(OP0_RESET, ioaddr); /* CMD0_RESET */
if (znet_debug > 1)
printk(KERN_DEBUG "%s: Shutting down ethercard.\n", dev->name);
/* Turn off transceiver power. */
znet_transceiver_power (dev, 0);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
znet_release_resources (dev);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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 0;
}
static void show_dma(struct net_device *dev)
{
short ioaddr = dev->base_addr;
unsigned char stat = inb (ioaddr);
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
unsigned long flags;
short dma_port = ((znet->tx_dma&3)<<2) + IO_DMA2_BASE;
unsigned addr = inb(dma_port);
short residue;
addr |= inb(dma_port) << 8;
residue = get_dma_residue(znet->tx_dma);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
if (znet_debug > 1) {
flags=claim_dma_lock();
printk(KERN_DEBUG "Stat:%02x Addr: %04x cnt:%3x\n",
stat, addr<<1, residue);
release_dma_lock(flags);
}
}
/* Initialize the hardware. We have to do this when the board is open()ed
or when we come out of suspend mode. */
static void hardware_init(struct net_device *dev)
{
unsigned long flags;
short ioaddr = dev->base_addr;
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(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
znet->rx_cur = znet->rx_start;
znet->tx_cur = znet->tx_start;
/* Reset the chip, and start it up. */
outb(OP0_RESET, ioaddr);
flags=claim_dma_lock();
disable_dma(znet->rx_dma); /* reset by an interrupting task. */
clear_dma_ff(znet->rx_dma);
set_dma_mode(znet->rx_dma, DMA_RX_MODE);
set_dma_addr(znet->rx_dma, (unsigned int) znet->rx_start);
set_dma_count(znet->rx_dma, RX_BUF_SIZE);
enable_dma(znet->rx_dma);
/* Now set up the Tx channel. */
disable_dma(znet->tx_dma);
clear_dma_ff(znet->tx_dma);
set_dma_mode(znet->tx_dma, DMA_TX_MODE);
set_dma_addr(znet->tx_dma, (unsigned int) znet->tx_start);
set_dma_count(znet->tx_dma, znet->tx_buf_len<<1);
enable_dma(znet->tx_dma);
release_dma_lock(flags);
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +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
if (znet_debug > 1)
printk(KERN_DEBUG "%s: Initializing the i82593, rx buf %p tx buf %p\n",
dev->name, znet->rx_start,znet->tx_start);
/* Do an empty configure command, just like the Crynwr driver. This
resets to chip to its default values. */
*znet->tx_cur++ = 0;
*znet->tx_cur++ = 0;
show_dma(dev);
outb(OP0_CONFIGURE | CR0_CHNL, ioaddr);
znet_set_multicast_list (dev);
*znet->tx_cur++ = 6;
memcpy(znet->tx_cur, dev->dev_addr, 6);
znet->tx_cur += 3;
show_dma(dev);
outb(OP0_IA_SETUP | CR0_CHNL, ioaddr);
show_dma(dev);
update_stop_hit(ioaddr, 8192);
if (znet_debug > 1) printk(KERN_DEBUG "enabling Rx.\n");
outb(OP0_RCV_ENABLE, ioaddr);
netif_start_queue (dev);
}
static void update_stop_hit(short ioaddr, unsigned short rx_stop_offset)
{
outb(OP0_SWIT_TO_PORT_1 | CR0_CHNL, ioaddr);
if (znet_debug > 5)
printk(KERN_DEBUG "Updating stop hit with value %02x.\n",
(rx_stop_offset >> 6) | CR1_STOP_REG_UPDATE);
outb((rx_stop_offset >> 6) | CR1_STOP_REG_UPDATE, ioaddr);
outb(OP1_SWIT_TO_PORT_0, ioaddr);
}
static __exit void znet_cleanup (void)
{
if (znet_dev) {
netdevice: safe convert to netdev_priv() #part-4 We have some reasons to kill netdev->priv: 1. netdev->priv is equal to netdev_priv(). 2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously netdev_priv() is more flexible than netdev->priv. But we cann't kill netdev->priv, because so many drivers reference to it directly. This patch is a safe convert for netdev->priv to netdev_priv(netdev). Since all of the netdev->priv is only for read. But it is too big to be sent in one mail. I split it to 4 parts and make every part smaller than 100,000 bytes, which is max size allowed by vger. Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-13 15:39:10 +08:00
struct znet_private *znet = netdev_priv(znet_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
unregister_netdev (znet_dev);
kfree (znet->rx_start);
kfree (znet->tx_start);
free_netdev (znet_dev);
}
}
module_init (znet_probe);
module_exit (znet_cleanup);