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/mace.c

1022 lines
27 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
/*
* Network device driver for the MACE ethernet controller on
* Apple Powermacs. Assumes it's under a DBDMA controller.
*
* Copyright (C) 1996 Paul Mackerras.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/delay.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/init.h>
#include <linux/crc32.h>
#include <linux/spinlock.h>
net: use bitrev8 Use bitrev8 for bmac, mace, macmace, macsonic, and skfp drivers. [akpm@osdl.org: use the API, not the array] Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Mirko Lindner <mlindner@syskonnect.de> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-12-20 05:09:08 +08:00
#include <linux/bitrev.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <asm/prom.h>
#include <asm/dbdma.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/macio.h>
#include "mace.h"
static int port_aaui = -1;
#define N_RX_RING 8
#define N_TX_RING 6
#define MAX_TX_ACTIVE 1
#define NCMDS_TX 1 /* dma commands per element in tx ring */
#define RX_BUFLEN (ETH_FRAME_LEN + 8)
#define TX_TIMEOUT HZ /* 1 second */
/* Chip rev needs workaround on HW & multicast addr change */
#define BROKEN_ADDRCHG_REV 0x0941
/* Bits in transmit DMA status */
#define TX_DMA_ERR 0x80
struct mace_data {
volatile struct mace __iomem *mace;
volatile struct dbdma_regs __iomem *tx_dma;
int tx_dma_intr;
volatile struct dbdma_regs __iomem *rx_dma;
int rx_dma_intr;
volatile struct dbdma_cmd *tx_cmds; /* xmit dma command list */
volatile struct dbdma_cmd *rx_cmds; /* recv dma command list */
struct sk_buff *rx_bufs[N_RX_RING];
int rx_fill;
int rx_empty;
struct sk_buff *tx_bufs[N_TX_RING];
int tx_fill;
int tx_empty;
unsigned char maccc;
unsigned char tx_fullup;
unsigned char tx_active;
unsigned char tx_bad_runt;
struct timer_list tx_timeout;
int timeout_active;
int port_aaui;
int chipid;
struct macio_dev *mdev;
spinlock_t lock;
};
/*
* Number of bytes of private data per MACE: allow enough for
* the rx and tx dma commands plus a branch dma command each,
* and another 16 bytes to allow us to align the dma command
* buffers on a 16 byte boundary.
*/
#define PRIV_BYTES (sizeof(struct mace_data) \
+ (N_RX_RING + NCMDS_TX * N_TX_RING + 3) * sizeof(struct dbdma_cmd))
static int mace_open(struct net_device *dev);
static int mace_close(struct net_device *dev);
static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev);
static void mace_set_multicast(struct net_device *dev);
static void mace_reset(struct net_device *dev);
static int mace_set_address(struct net_device *dev, void *addr);
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 mace_interrupt(int irq, void *dev_id);
static irqreturn_t mace_txdma_intr(int irq, void *dev_id);
static irqreturn_t mace_rxdma_intr(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 mace_set_timeout(struct net_device *dev);
static void mace_tx_timeout(unsigned long data);
static inline void dbdma_reset(volatile struct dbdma_regs __iomem *dma);
static inline void mace_clean_rings(struct mace_data *mp);
static void __mace_set_address(struct net_device *dev, void *addr);
/*
* If we can't get a skbuff when we need it, we use this area for DMA.
*/
static unsigned char *dummy_buf;
[PATCH] openfirmware: generate device table for userspace This converts the usage of struct of_match to struct of_device_id, similar to pci_device_id. This allows a device table to be generated, which can be parsed by depmod(8) to generate a map file for module loading. In order for hotplug to work with macio devices, patches to module-init-tools and hotplug must be applied. Those patches are available at: ftp://ftp.suse.com/pub/people/jeffm/linux/macio-hotplug/ Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-07 03:44:41 +08:00
static int __devinit mace_probe(struct macio_dev *mdev, const struct of_device_id *match)
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 device_node *mace = macio_get_of_node(mdev);
struct net_device *dev;
struct mace_data *mp;
[POWERPC] netdevices: Constify & voidify get_property() Now that get_property() returns a void *, there's no need to cast its return value. Also, treat the return value as const, so we can constify get_property later. powerpc-specific network device driver changes. Signed-off-by: Jeremy Kerr <jk@ozlabs.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-12 13:41:03 +08:00
const unsigned char *addr;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
int j, rev, rc = -EBUSY;
if (macio_resource_count(mdev) != 3 || macio_irq_count(mdev) != 3) {
printk(KERN_ERR "can't use MACE %s: need 3 addrs and 3 irqs\n",
mace->full_name);
return -ENODEV;
}
[POWERPC] Rename get_property to of_get_property: drivers These are all the remaining instances of get_property. Simple rename of get_property to of_get_property. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-05-01 11:54:02 +08:00
addr = of_get_property(mace, "mac-address", NULL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (addr == NULL) {
[POWERPC] Rename get_property to of_get_property: drivers These are all the remaining instances of get_property. Simple rename of get_property to of_get_property. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-05-01 11:54:02 +08:00
addr = of_get_property(mace, "local-mac-address", NULL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (addr == NULL) {
printk(KERN_ERR "Can't get mac-address for MACE %s\n",
mace->full_name);
return -ENODEV;
}
}
/*
* lazy allocate the driver-wide dummy buffer. (Note that we
* never have more than one MACE in the system anyway)
*/
if (dummy_buf == NULL) {
dummy_buf = kmalloc(RX_BUFLEN+2, GFP_KERNEL);
if (dummy_buf == NULL) {
printk(KERN_ERR "MACE: couldn't allocate dummy buffer\n");
return -ENOMEM;
}
}
if (macio_request_resources(mdev, "mace")) {
printk(KERN_ERR "MACE: can't request IO resources !\n");
return -EBUSY;
}
dev = alloc_etherdev(PRIV_BYTES);
if (!dev) {
printk(KERN_ERR "MACE: can't allocate ethernet device !\n");
rc = -ENOMEM;
goto err_release;
}
SET_NETDEV_DEV(dev, &mdev->ofdev.dev);
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
mp = 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
mp->mdev = mdev;
macio_set_drvdata(mdev, dev);
dev->base_addr = macio_resource_start(mdev, 0);
mp->mace = ioremap(dev->base_addr, 0x1000);
if (mp->mace == NULL) {
printk(KERN_ERR "MACE: can't map IO resources !\n");
rc = -ENOMEM;
goto err_free;
}
dev->irq = macio_irq(mdev, 0);
rev = addr[0] == 0 && addr[1] == 0xA0;
for (j = 0; j < 6; ++j) {
net: use bitrev8 Use bitrev8 for bmac, mace, macmace, macsonic, and skfp drivers. [akpm@osdl.org: use the API, not the array] Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Mirko Lindner <mlindner@syskonnect.de> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-12-20 05:09:08 +08:00
dev->dev_addr[j] = rev ? bitrev8(addr[j]): addr[j];
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
}
mp->chipid = (in_8(&mp->mace->chipid_hi) << 8) |
in_8(&mp->mace->chipid_lo);
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
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
mp = 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
mp->maccc = ENXMT | ENRCV;
mp->tx_dma = ioremap(macio_resource_start(mdev, 1), 0x1000);
if (mp->tx_dma == NULL) {
printk(KERN_ERR "MACE: can't map TX DMA resources !\n");
rc = -ENOMEM;
goto err_unmap_io;
}
mp->tx_dma_intr = macio_irq(mdev, 1);
mp->rx_dma = ioremap(macio_resource_start(mdev, 2), 0x1000);
if (mp->rx_dma == NULL) {
printk(KERN_ERR "MACE: can't map RX DMA resources !\n");
rc = -ENOMEM;
goto err_unmap_tx_dma;
}
mp->rx_dma_intr = macio_irq(mdev, 2);
mp->tx_cmds = (volatile struct dbdma_cmd *) DBDMA_ALIGN(mp + 1);
mp->rx_cmds = mp->tx_cmds + NCMDS_TX * N_TX_RING + 1;
memset((char *) mp->tx_cmds, 0,
(NCMDS_TX*N_TX_RING + N_RX_RING + 2) * sizeof(struct dbdma_cmd));
init_timer(&mp->tx_timeout);
spin_lock_init(&mp->lock);
mp->timeout_active = 0;
if (port_aaui >= 0)
mp->port_aaui = port_aaui;
else {
/* Apple Network Server uses the AAUI port */
if (machine_is_compatible("AAPL,ShinerESB"))
mp->port_aaui = 1;
else {
#ifdef CONFIG_MACE_AAUI_PORT
mp->port_aaui = 1;
#else
mp->port_aaui = 0;
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
#endif
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->open = mace_open;
dev->stop = mace_close;
dev->hard_start_xmit = mace_xmit_start;
dev->set_multicast_list = mace_set_multicast;
dev->set_mac_address = mace_set_address;
/*
* Most of what is below could be moved to mace_open()
*/
mace_reset(dev);
rc = request_irq(dev->irq, mace_interrupt, 0, "MACE", dev);
if (rc) {
printk(KERN_ERR "MACE: can't get irq %d\n", dev->irq);
goto err_unmap_rx_dma;
}
rc = request_irq(mp->tx_dma_intr, mace_txdma_intr, 0, "MACE-txdma", dev);
if (rc) {
[POWERPC] Add new interrupt mapping core and change platforms to use it This adds the new irq remapper core and removes the old one. Because there are some fundamental conflicts with the old code, like the value of NO_IRQ which I'm now setting to 0 (as per discussions with Linus), etc..., this commit also changes the relevant platform and driver code over to use the new remapper (so as not to cause difficulties later in bisecting). This patch removes the old pre-parsing of the open firmware interrupt tree along with all the bogus assumptions it made to try to renumber interrupts according to the platform. This is all to be handled by the new code now. For the pSeries XICS interrupt controller, a single remapper host is created for the whole machine regardless of how many interrupt presentation and source controllers are found, and it's set to match any device node that isn't a 8259. That works fine on pSeries and avoids having to deal with some of the complexities of split source controllers vs. presentation controllers in the pSeries device trees. The powerpc i8259 PIC driver now always requests the legacy interrupt range. It also has the feature of being able to match any device node (including NULL) if passed no device node as an input. That will help porting over platforms with broken device-trees like Pegasos who don't have a proper interrupt tree. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-03 19:36:01 +08:00
printk(KERN_ERR "MACE: can't get irq %d\n", mp->tx_dma_intr);
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 err_free_irq;
}
rc = request_irq(mp->rx_dma_intr, mace_rxdma_intr, 0, "MACE-rxdma", dev);
if (rc) {
[POWERPC] Add new interrupt mapping core and change platforms to use it This adds the new irq remapper core and removes the old one. Because there are some fundamental conflicts with the old code, like the value of NO_IRQ which I'm now setting to 0 (as per discussions with Linus), etc..., this commit also changes the relevant platform and driver code over to use the new remapper (so as not to cause difficulties later in bisecting). This patch removes the old pre-parsing of the open firmware interrupt tree along with all the bogus assumptions it made to try to renumber interrupts according to the platform. This is all to be handled by the new code now. For the pSeries XICS interrupt controller, a single remapper host is created for the whole machine regardless of how many interrupt presentation and source controllers are found, and it's set to match any device node that isn't a 8259. That works fine on pSeries and avoids having to deal with some of the complexities of split source controllers vs. presentation controllers in the pSeries device trees. The powerpc i8259 PIC driver now always requests the legacy interrupt range. It also has the feature of being able to match any device node (including NULL) if passed no device node as an input. That will help porting over platforms with broken device-trees like Pegasos who don't have a proper interrupt tree. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-03 19:36:01 +08:00
printk(KERN_ERR "MACE: can't get irq %d\n", mp->rx_dma_intr);
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 err_free_tx_irq;
}
rc = register_netdev(dev);
if (rc) {
printk(KERN_ERR "MACE: Cannot register net device, aborting.\n");
goto err_free_rx_irq;
}
net: convert print_mac to %pM This converts pretty much everything to print_mac. There were a few things that had conflicts which I have just dropped for now, no harm done. I've built an allyesconfig with this and looked at the files that weren't built very carefully, but it's a huge patch. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-28 06:59:26 +08:00
printk(KERN_INFO "%s: MACE at %pM, chip revision %d.%d\n",
dev->name, 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
mp->chipid >> 8, mp->chipid & 0xff);
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;
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
err_free_rx_irq:
free_irq(macio_irq(mdev, 2), dev);
err_free_tx_irq:
free_irq(macio_irq(mdev, 1), dev);
err_free_irq:
free_irq(macio_irq(mdev, 0), dev);
err_unmap_rx_dma:
iounmap(mp->rx_dma);
err_unmap_tx_dma:
iounmap(mp->tx_dma);
err_unmap_io:
iounmap(mp->mace);
err_free:
free_netdev(dev);
err_release:
macio_release_resources(mdev);
return rc;
}
static int __devexit mace_remove(struct macio_dev *mdev)
{
struct net_device *dev = macio_get_drvdata(mdev);
struct mace_data *mp;
BUG_ON(dev == NULL);
macio_set_drvdata(mdev, NULL);
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
mp = 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
unregister_netdev(dev);
free_irq(dev->irq, dev);
free_irq(mp->tx_dma_intr, dev);
free_irq(mp->rx_dma_intr, dev);
iounmap(mp->rx_dma);
iounmap(mp->tx_dma);
iounmap(mp->mace);
free_netdev(dev);
macio_release_resources(mdev);
return 0;
}
static void dbdma_reset(volatile struct dbdma_regs __iomem *dma)
{
int i;
out_le32(&dma->control, (WAKE|FLUSH|PAUSE|RUN) << 16);
/*
* Yes this looks peculiar, but apparently it needs to be this
* way on some machines.
*/
for (i = 200; i > 0; --i)
if (ld_le32(&dma->control) & RUN)
udelay(1);
}
static void mace_reset(struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
int i;
/* soft-reset the chip */
i = 200;
while (--i) {
out_8(&mb->biucc, SWRST);
if (in_8(&mb->biucc) & SWRST) {
udelay(10);
continue;
}
break;
}
if (!i) {
printk(KERN_ERR "mace: cannot reset chip!\n");
return;
}
out_8(&mb->imr, 0xff); /* disable all intrs for now */
i = in_8(&mb->ir);
out_8(&mb->maccc, 0); /* turn off tx, rx */
out_8(&mb->biucc, XMTSP_64);
out_8(&mb->utr, RTRD);
out_8(&mb->fifocc, RCVFW_32 | XMTFW_16 | XMTFWU | RCVFWU | XMTBRST);
out_8(&mb->xmtfc, AUTO_PAD_XMIT); /* auto-pad short frames */
out_8(&mb->rcvfc, 0);
/* load up the hardware address */
__mace_set_address(dev, dev->dev_addr);
/* clear the multicast filter */
if (mp->chipid == BROKEN_ADDRCHG_REV)
out_8(&mb->iac, LOGADDR);
else {
out_8(&mb->iac, ADDRCHG | LOGADDR);
while ((in_8(&mb->iac) & ADDRCHG) != 0)
;
}
for (i = 0; i < 8; ++i)
out_8(&mb->ladrf, 0);
/* done changing address */
if (mp->chipid != BROKEN_ADDRCHG_REV)
out_8(&mb->iac, 0);
if (mp->port_aaui)
out_8(&mb->plscc, PORTSEL_AUI + ENPLSIO);
else
out_8(&mb->plscc, PORTSEL_GPSI + ENPLSIO);
}
static void __mace_set_address(struct net_device *dev, void *addr)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
unsigned char *p = addr;
int i;
/* load up the hardware address */
if (mp->chipid == BROKEN_ADDRCHG_REV)
out_8(&mb->iac, PHYADDR);
else {
out_8(&mb->iac, ADDRCHG | PHYADDR);
while ((in_8(&mb->iac) & ADDRCHG) != 0)
;
}
for (i = 0; i < 6; ++i)
out_8(&mb->padr, dev->dev_addr[i] = p[i]);
if (mp->chipid != BROKEN_ADDRCHG_REV)
out_8(&mb->iac, 0);
}
static int mace_set_address(struct net_device *dev, void *addr)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
unsigned long flags;
spin_lock_irqsave(&mp->lock, flags);
__mace_set_address(dev, addr);
/* note: setting ADDRCHG clears ENRCV */
out_8(&mb->maccc, mp->maccc);
spin_unlock_irqrestore(&mp->lock, flags);
return 0;
}
static inline void mace_clean_rings(struct mace_data *mp)
{
int i;
/* free some skb's */
for (i = 0; i < N_RX_RING; ++i) {
NULL noise in drivers/net Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 18:06:46 +08:00
if (mp->rx_bufs[i] != NULL) {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev_kfree_skb(mp->rx_bufs[i]);
mp->rx_bufs[i] = NULL;
}
}
for (i = mp->tx_empty; i != mp->tx_fill; ) {
dev_kfree_skb(mp->tx_bufs[i]);
if (++i >= N_TX_RING)
i = 0;
}
}
static int mace_open(struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
volatile struct dbdma_regs __iomem *rd = mp->rx_dma;
volatile struct dbdma_regs __iomem *td = mp->tx_dma;
volatile struct dbdma_cmd *cp;
int i;
struct sk_buff *skb;
unsigned char *data;
/* reset the chip */
mace_reset(dev);
/* initialize list of sk_buffs for receiving and set up recv dma */
mace_clean_rings(mp);
memset((char *)mp->rx_cmds, 0, N_RX_RING * sizeof(struct dbdma_cmd));
cp = mp->rx_cmds;
for (i = 0; i < N_RX_RING - 1; ++i) {
skb = dev_alloc_skb(RX_BUFLEN + 2);
NULL noise in drivers/net Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 18:06:46 +08:00
if (!skb) {
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
data = dummy_buf;
} else {
skb_reserve(skb, 2); /* so IP header lands on 4-byte bdry */
data = skb->data;
}
mp->rx_bufs[i] = skb;
st_le16(&cp->req_count, RX_BUFLEN);
st_le16(&cp->command, INPUT_LAST + INTR_ALWAYS);
st_le32(&cp->phy_addr, virt_to_bus(data));
cp->xfer_status = 0;
++cp;
}
mp->rx_bufs[i] = NULL;
st_le16(&cp->command, DBDMA_STOP);
mp->rx_fill = i;
mp->rx_empty = 0;
/* Put a branch back to the beginning of the receive command list */
++cp;
st_le16(&cp->command, DBDMA_NOP + BR_ALWAYS);
st_le32(&cp->cmd_dep, virt_to_bus(mp->rx_cmds));
/* start rx dma */
out_le32(&rd->control, (RUN|PAUSE|FLUSH|WAKE) << 16); /* clear run bit */
out_le32(&rd->cmdptr, virt_to_bus(mp->rx_cmds));
out_le32(&rd->control, (RUN << 16) | RUN);
/* put a branch at the end of the tx command list */
cp = mp->tx_cmds + NCMDS_TX * N_TX_RING;
st_le16(&cp->command, DBDMA_NOP + BR_ALWAYS);
st_le32(&cp->cmd_dep, virt_to_bus(mp->tx_cmds));
/* reset tx dma */
out_le32(&td->control, (RUN|PAUSE|FLUSH|WAKE) << 16);
out_le32(&td->cmdptr, virt_to_bus(mp->tx_cmds));
mp->tx_fill = 0;
mp->tx_empty = 0;
mp->tx_fullup = 0;
mp->tx_active = 0;
mp->tx_bad_runt = 0;
/* turn it on! */
out_8(&mb->maccc, mp->maccc);
/* enable all interrupts except receive interrupts */
out_8(&mb->imr, RCVINT);
return 0;
}
static int mace_close(struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
volatile struct dbdma_regs __iomem *rd = mp->rx_dma;
volatile struct dbdma_regs __iomem *td = mp->tx_dma;
/* disable rx and tx */
out_8(&mb->maccc, 0);
out_8(&mb->imr, 0xff); /* disable all intrs */
/* disable rx and tx dma */
st_le32(&rd->control, (RUN|PAUSE|FLUSH|WAKE) << 16); /* clear run bit */
st_le32(&td->control, (RUN|PAUSE|FLUSH|WAKE) << 16); /* clear run bit */
mace_clean_rings(mp);
return 0;
}
static inline void mace_set_timeout(struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
if (mp->timeout_active)
del_timer(&mp->tx_timeout);
mp->tx_timeout.expires = jiffies + TX_TIMEOUT;
mp->tx_timeout.function = mace_tx_timeout;
mp->tx_timeout.data = (unsigned long) dev;
add_timer(&mp->tx_timeout);
mp->timeout_active = 1;
}
static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct dbdma_regs __iomem *td = mp->tx_dma;
volatile struct dbdma_cmd *cp, *np;
unsigned long flags;
int fill, next, len;
/* see if there's a free slot in the tx ring */
spin_lock_irqsave(&mp->lock, flags);
fill = mp->tx_fill;
next = fill + 1;
if (next >= N_TX_RING)
next = 0;
if (next == mp->tx_empty) {
netif_stop_queue(dev);
mp->tx_fullup = 1;
spin_unlock_irqrestore(&mp->lock, flags);
return 1; /* can't take it at the moment */
}
spin_unlock_irqrestore(&mp->lock, flags);
/* partially fill in the dma command block */
len = skb->len;
if (len > ETH_FRAME_LEN) {
printk(KERN_DEBUG "mace: xmit frame too long (%d)\n", len);
len = ETH_FRAME_LEN;
}
mp->tx_bufs[fill] = skb;
cp = mp->tx_cmds + NCMDS_TX * fill;
st_le16(&cp->req_count, len);
st_le32(&cp->phy_addr, virt_to_bus(skb->data));
np = mp->tx_cmds + NCMDS_TX * next;
out_le16(&np->command, DBDMA_STOP);
/* poke the tx dma channel */
spin_lock_irqsave(&mp->lock, flags);
mp->tx_fill = next;
if (!mp->tx_bad_runt && mp->tx_active < MAX_TX_ACTIVE) {
out_le16(&cp->xfer_status, 0);
out_le16(&cp->command, OUTPUT_LAST);
out_le32(&td->control, ((RUN|WAKE) << 16) + (RUN|WAKE));
++mp->tx_active;
mace_set_timeout(dev);
}
if (++next >= N_TX_RING)
next = 0;
if (next == mp->tx_empty)
netif_stop_queue(dev);
spin_unlock_irqrestore(&mp->lock, flags);
return 0;
}
static void mace_set_multicast(struct net_device *dev)
{
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
int i, j;
u32 crc;
unsigned long flags;
spin_lock_irqsave(&mp->lock, flags);
mp->maccc &= ~PROM;
if (dev->flags & IFF_PROMISC) {
mp->maccc |= PROM;
} else {
unsigned char multicast_filter[8];
struct dev_mc_list *dmi = dev->mc_list;
if (dev->flags & IFF_ALLMULTI) {
for (i = 0; i < 8; i++)
multicast_filter[i] = 0xff;
} else {
for (i = 0; i < 8; i++)
multicast_filter[i] = 0;
for (i = 0; i < dev->mc_count; i++) {
crc = ether_crc_le(6, dmi->dmi_addr);
j = crc >> 26; /* bit number in multicast_filter */
multicast_filter[j >> 3] |= 1 << (j & 7);
dmi = dmi->next;
}
}
#if 0
printk("Multicast filter :");
for (i = 0; i < 8; i++)
printk("%02x ", multicast_filter[i]);
printk("\n");
#endif
if (mp->chipid == BROKEN_ADDRCHG_REV)
out_8(&mb->iac, LOGADDR);
else {
out_8(&mb->iac, ADDRCHG | LOGADDR);
while ((in_8(&mb->iac) & ADDRCHG) != 0)
;
}
for (i = 0; i < 8; ++i)
out_8(&mb->ladrf, multicast_filter[i]);
if (mp->chipid != BROKEN_ADDRCHG_REV)
out_8(&mb->iac, 0);
}
/* reset maccc */
out_8(&mb->maccc, mp->maccc);
spin_unlock_irqrestore(&mp->lock, flags);
}
[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
static void mace_handle_misc_intrs(struct mace_data *mp, int intr, 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
{
volatile struct mace __iomem *mb = mp->mace;
static int mace_babbles, mace_jabbers;
if (intr & MPCO)
[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_missed_errors += 256;
dev->stats.rx_missed_errors += in_8(&mb->mpc); /* reading clears it */
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 (intr & RNTPCO)
[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 += 256;
dev->stats.rx_length_errors += in_8(&mb->rntpc); /* reading clears it */
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 (intr & CERR)
[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 (intr & BABBLE)
if (mace_babbles++ < 4)
printk(KERN_DEBUG "mace: babbling transmitter\n");
if (intr & JABBER)
if (mace_jabbers++ < 4)
printk(KERN_DEBUG "mace: jabbering transceiver\n");
}
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 mace_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 = (struct net_device *) dev_id;
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
volatile struct dbdma_regs __iomem *td = mp->tx_dma;
volatile struct dbdma_cmd *cp;
int intr, fs, i, stat, x;
int xcount, dstat;
unsigned long flags;
/* static int mace_last_fs, mace_last_xcount; */
spin_lock_irqsave(&mp->lock, flags);
intr = in_8(&mb->ir); /* read interrupt register */
in_8(&mb->xmtrc); /* get retries */
[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
mace_handle_misc_intrs(mp, intr, 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
i = mp->tx_empty;
while (in_8(&mb->pr) & XMTSV) {
del_timer(&mp->tx_timeout);
mp->timeout_active = 0;
/*
* Clear any interrupt indication associated with this status
* word. This appears to unlatch any error indication from
* the DMA controller.
*/
intr = in_8(&mb->ir);
if (intr != 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
mace_handle_misc_intrs(mp, intr, dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (mp->tx_bad_runt) {
fs = in_8(&mb->xmtfs);
mp->tx_bad_runt = 0;
out_8(&mb->xmtfc, AUTO_PAD_XMIT);
continue;
}
dstat = ld_le32(&td->status);
/* stop DMA controller */
out_le32(&td->control, RUN << 16);
/*
* xcount is the number of complete frames which have been
* written to the fifo but for which status has not been read.
*/
xcount = (in_8(&mb->fifofc) >> XMTFC_SH) & XMTFC_MASK;
if (xcount == 0 || (dstat & DEAD)) {
/*
* If a packet was aborted before the DMA controller has
* finished transferring it, it seems that there are 2 bytes
* which are stuck in some buffer somewhere. These will get
* transmitted as soon as we read the frame status (which
* reenables the transmit data transfer request). Turning
* off the DMA controller and/or resetting the MACE doesn't
* help. So we disable auto-padding and FCS transmission
* so the two bytes will only be a runt packet which should
* be ignored by other stations.
*/
out_8(&mb->xmtfc, DXMTFCS);
}
fs = in_8(&mb->xmtfs);
if ((fs & XMTSV) == 0) {
printk(KERN_ERR "mace: xmtfs not valid! (fs=%x xc=%d ds=%x)\n",
fs, xcount, dstat);
mace_reset(dev);
/*
* XXX mace likes to hang the machine after a xmtfs error.
* This is hard to reproduce, reseting *may* help
*/
}
cp = mp->tx_cmds + NCMDS_TX * i;
stat = ld_le16(&cp->xfer_status);
if ((fs & (UFLO|LCOL|LCAR|RTRY)) || (dstat & DEAD) || xcount == 0) {
/*
* Check whether there were in fact 2 bytes written to
* the transmit FIFO.
*/
udelay(1);
x = (in_8(&mb->fifofc) >> XMTFC_SH) & XMTFC_MASK;
if (x != 0) {
/* there were two bytes with an end-of-packet indication */
mp->tx_bad_runt = 1;
mace_set_timeout(dev);
} else {
/*
* Either there weren't the two bytes buffered up, or they
* didn't have an end-of-packet indication.
* We flush the transmit FIFO just in case (by setting the
* XMTFWU bit with the transmitter disabled).
*/
out_8(&mb->maccc, in_8(&mb->maccc) & ~ENXMT);
out_8(&mb->fifocc, in_8(&mb->fifocc) | XMTFWU);
udelay(1);
out_8(&mb->maccc, in_8(&mb->maccc) | ENXMT);
out_8(&mb->xmtfc, AUTO_PAD_XMIT);
}
}
/* dma should have finished */
if (i == mp->tx_fill) {
printk(KERN_DEBUG "mace: tx ring ran out? (fs=%x xc=%d ds=%x)\n",
fs, xcount, dstat);
continue;
}
/* Update stats */
if (fs & (UFLO|LCOL|LCAR|RTRY)) {
[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
if (fs & LCAR)
[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 (fs & (UFLO|LCOL|RTRY))
[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
} else {
[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 += mp->tx_bufs[i]->len;
++dev->stats.tx_packets;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
dev_kfree_skb_irq(mp->tx_bufs[i]);
--mp->tx_active;
if (++i >= N_TX_RING)
i = 0;
#if 0
mace_last_fs = fs;
mace_last_xcount = xcount;
#endif
}
if (i != mp->tx_empty) {
mp->tx_fullup = 0;
netif_wake_queue(dev);
}
mp->tx_empty = i;
i += mp->tx_active;
if (i >= N_TX_RING)
i -= N_TX_RING;
if (!mp->tx_bad_runt && i != mp->tx_fill && mp->tx_active < MAX_TX_ACTIVE) {
do {
/* set up the next one */
cp = mp->tx_cmds + NCMDS_TX * i;
out_le16(&cp->xfer_status, 0);
out_le16(&cp->command, OUTPUT_LAST);
++mp->tx_active;
if (++i >= N_TX_RING)
i = 0;
} while (i != mp->tx_fill && mp->tx_active < MAX_TX_ACTIVE);
out_le32(&td->control, ((RUN|WAKE) << 16) + (RUN|WAKE));
mace_set_timeout(dev);
}
spin_unlock_irqrestore(&mp->lock, flags);
return IRQ_HANDLED;
}
static void mace_tx_timeout(unsigned long data)
{
struct net_device *dev = (struct net_device *) data;
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct mace __iomem *mb = mp->mace;
volatile struct dbdma_regs __iomem *td = mp->tx_dma;
volatile struct dbdma_regs __iomem *rd = mp->rx_dma;
volatile struct dbdma_cmd *cp;
unsigned long flags;
int i;
spin_lock_irqsave(&mp->lock, flags);
mp->timeout_active = 0;
if (mp->tx_active == 0 && !mp->tx_bad_runt)
goto out;
/* update various counters */
[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
mace_handle_misc_intrs(mp, in_8(&mb->ir), 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
cp = mp->tx_cmds + NCMDS_TX * mp->tx_empty;
/* turn off both tx and rx and reset the chip */
out_8(&mb->maccc, 0);
printk(KERN_ERR "mace: transmit timeout - resetting\n");
dbdma_reset(td);
mace_reset(dev);
/* restart rx dma */
cp = bus_to_virt(ld_le32(&rd->cmdptr));
dbdma_reset(rd);
out_le16(&cp->xfer_status, 0);
out_le32(&rd->cmdptr, virt_to_bus(cp));
out_le32(&rd->control, (RUN << 16) | RUN);
/* fix up the transmit side */
i = mp->tx_empty;
mp->tx_active = 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
++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
if (mp->tx_bad_runt) {
mp->tx_bad_runt = 0;
} else if (i != mp->tx_fill) {
dev_kfree_skb(mp->tx_bufs[i]);
if (++i >= N_TX_RING)
i = 0;
mp->tx_empty = i;
}
mp->tx_fullup = 0;
netif_wake_queue(dev);
if (i != mp->tx_fill) {
cp = mp->tx_cmds + NCMDS_TX * i;
out_le16(&cp->xfer_status, 0);
out_le16(&cp->command, OUTPUT_LAST);
out_le32(&td->cmdptr, virt_to_bus(cp));
out_le32(&td->control, (RUN << 16) | RUN);
++mp->tx_active;
mace_set_timeout(dev);
}
/* turn it back on */
out_8(&mb->imr, RCVINT);
out_8(&mb->maccc, mp->maccc);
out:
spin_unlock_irqrestore(&mp->lock, flags);
}
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 mace_txdma_intr(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
{
return IRQ_HANDLED;
}
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
static irqreturn_t mace_rxdma_intr(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 = (struct net_device *) dev_id;
netdevice: safe convert to netdev_priv() #part-1 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 15:37:49 +08:00
struct mace_data *mp = 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
volatile struct dbdma_regs __iomem *rd = mp->rx_dma;
volatile struct dbdma_cmd *cp, *np;
int i, nb, stat, next;
struct sk_buff *skb;
unsigned frame_status;
static int mace_lost_status;
unsigned char *data;
unsigned long flags;
spin_lock_irqsave(&mp->lock, flags);
for (i = mp->rx_empty; i != mp->rx_fill; ) {
cp = mp->rx_cmds + i;
stat = ld_le16(&cp->xfer_status);
if ((stat & ACTIVE) == 0) {
next = i + 1;
if (next >= N_RX_RING)
next = 0;
np = mp->rx_cmds + next;
if (next != mp->rx_fill
&& (ld_le16(&np->xfer_status) & ACTIVE) != 0) {
printk(KERN_DEBUG "mace: lost a status word\n");
++mace_lost_status;
} else
break;
}
nb = ld_le16(&cp->req_count) - ld_le16(&cp->res_count);
out_le16(&cp->command, DBDMA_STOP);
/* got a packet, have a look at it */
skb = mp->rx_bufs[i];
NULL noise in drivers/net Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 18:06:46 +08:00
if (!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_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
} else if (nb > 8) {
data = skb->data;
frame_status = (data[nb-3] << 8) + data[nb-4];
if (frame_status & (RS_OFLO|RS_CLSN|RS_FRAMERR|RS_FCSERR)) {
[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;
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 (frame_status & RS_OFLO)
[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_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
if (frame_status & RS_FRAMERR)
[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_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 (frame_status & RS_FCSERR)
[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_crc_errors;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} else {
/* Mace feature AUTO_STRIP_RCV is on by default, dropping the
* FCS on frames with 802.3 headers. This means that Ethernet
* frames have 8 extra octets at the end, while 802.3 frames
* have only 4. We need to correctly account for this. */
if (*(unsigned short *)(data+12) < 1536) /* 802.3 header */
nb -= 4;
else /* Ethernet header; mace includes FCS */
nb -= 8;
skb_put(skb, nb);
skb->protocol = eth_type_trans(skb, dev);
[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_bytes += skb->len;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
netif_rx(skb);
mp->rx_bufs[i] = NULL;
[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;
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 {
[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;
++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
}
/* advance to next */
if (++i >= N_RX_RING)
i = 0;
}
mp->rx_empty = i;
i = mp->rx_fill;
for (;;) {
next = i + 1;
if (next >= N_RX_RING)
next = 0;
if (next == mp->rx_empty)
break;
cp = mp->rx_cmds + i;
skb = mp->rx_bufs[i];
NULL noise in drivers/net Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 18:06:46 +08:00
if (!skb) {
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
skb = dev_alloc_skb(RX_BUFLEN + 2);
NULL noise in drivers/net Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 18:06:46 +08:00
if (skb) {
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
skb_reserve(skb, 2);
mp->rx_bufs[i] = skb;
}
}
st_le16(&cp->req_count, RX_BUFLEN);
data = skb? skb->data: dummy_buf;
st_le32(&cp->phy_addr, virt_to_bus(data));
out_le16(&cp->xfer_status, 0);
out_le16(&cp->command, INPUT_LAST + INTR_ALWAYS);
#if 0
if ((ld_le32(&rd->status) & ACTIVE) != 0) {
out_le32(&rd->control, (PAUSE << 16) | PAUSE);
while ((in_le32(&rd->status) & ACTIVE) != 0)
;
}
#endif
i = next;
}
if (i != mp->rx_fill) {
out_le32(&rd->control, ((RUN|WAKE) << 16) | (RUN|WAKE));
mp->rx_fill = i;
}
spin_unlock_irqrestore(&mp->lock, flags);
return IRQ_HANDLED;
}
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
static struct of_device_id mace_match[] =
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
{
{
.name = "mace",
},
{},
};
[PATCH] Add modalias for pmac network drivers mesh, mac53c94 and airport already have an entry. Add the network drivers for pmac. Signed-off-by: Olaf Hering <olh@suse.de> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-10-29 08:46:21 +08:00
MODULE_DEVICE_TABLE (of, mace_match);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
drivers/net: Trim trailing whitespace Signed-off-by: Jeff Garzik <jeff@garzik.org>
2006-09-14 01:24:59 +08:00
static struct macio_driver mace_driver =
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
{
.name = "mace",
.match_table = mace_match,
.probe = mace_probe,
.remove = mace_remove,
};
static int __init mace_init(void)
{
return macio_register_driver(&mace_driver);
}
static void __exit mace_cleanup(void)
{
macio_unregister_driver(&mace_driver);
drivers/net: Remove pointless checks for NULL prior to calling kfree()
2005-10-29 04:53:13 +08:00
kfree(dummy_buf);
dummy_buf = NULL;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
MODULE_AUTHOR("Paul Mackerras");
MODULE_DESCRIPTION("PowerMac MACE driver.");
[PATCH] Remove MODULE_PARM MODULE_PARM was actually breaking: recent gcc version optimize them out as unused. It's time to replace the last users, which are generally in the most unloved drivers anyway. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 19:07:05 +08:00
module_param(port_aaui, int, 0);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
MODULE_PARM_DESC(port_aaui, "MACE uses AAUI port (0-1)");
MODULE_LICENSE("GPL");
module_init(mace_init);
module_exit(mace_cleanup);