linux_dsm_epyc7002/drivers/net/ibmveth.c

1627 lines
47 KiB
C
Raw Normal View History

/**************************************************************************/
/* */
/* IBM eServer i/pSeries Virtual Ethernet Device Driver */
/* Copyright (C) 2003 IBM Corp. */
/* Originally written by Dave Larson (larson1@us.ibm.com) */
/* Maintained by Santiago Leon (santil@us.ibm.com) */
/* */
/* This program is free software; you can redistribute it and/or modify */
/* it under the terms of the GNU General Public License as published by */
/* the Free Software Foundation; either version 2 of the License, or */
/* (at your option) any later version. */
/* */
/* This program is distributed in the hope that it will be useful, */
/* but WITHOUT ANY WARRANTY; without even the implied warranty of */
/* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the */
/* GNU General Public License for more details. */
/* */
/* You should have received a copy of the GNU General Public License */
/* along with this program; if not, write to the Free Software */
/* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 */
/* USA */
/* */
/* This module contains the implementation of a virtual ethernet device */
/* for use with IBM i/pSeries LPAR Linux. It utilizes the logical LAN */
/* option of the RS/6000 Platform Architechture to interface with virtual */
/* ethernet NICs that are presented to the partition by the hypervisor. */
/* */
/**************************************************************************/
/*
TODO:
- add support for sysfs
- possibly remove procfs support
*/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/ethtool.h>
#include <linux/proc_fs.h>
#include <linux/in.h>
#include <linux/ip.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <asm/hvcall.h>
#include <asm/atomic.h>
#include <asm/vio.h>
#include <asm/iommu.h>
#include <asm/uaccess.h>
#include <asm/firmware.h>
#include <linux/seq_file.h>
#include "ibmveth.h"
#undef DEBUG
#define ibmveth_printk(fmt, args...) \
printk(KERN_DEBUG "%s: " fmt, __FILE__, ## args)
#define ibmveth_error_printk(fmt, args...) \
printk(KERN_ERR "(%s:%3.3d ua:%x) ERROR: " fmt, __FILE__, __LINE__ , adapter->vdev->unit_address, ## args)
#ifdef DEBUG
#define ibmveth_debug_printk_no_adapter(fmt, args...) \
printk(KERN_DEBUG "(%s:%3.3d): " fmt, __FILE__, __LINE__ , ## args)
#define ibmveth_debug_printk(fmt, args...) \
printk(KERN_DEBUG "(%s:%3.3d ua:%x): " fmt, __FILE__, __LINE__ , adapter->vdev->unit_address, ## args)
#define ibmveth_assert(expr) \
if(!(expr)) { \
printk(KERN_DEBUG "assertion failed (%s:%3.3d ua:%x): %s\n", __FILE__, __LINE__, adapter->vdev->unit_address, #expr); \
BUG(); \
}
#else
#define ibmveth_debug_printk_no_adapter(fmt, args...)
#define ibmveth_debug_printk(fmt, args...)
#define ibmveth_assert(expr)
#endif
static int ibmveth_open(struct net_device *dev);
static int ibmveth_close(struct net_device *dev);
static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
static int ibmveth_poll(struct napi_struct *napi, int budget);
static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *dev);
static void ibmveth_set_multicast_list(struct net_device *dev);
static int ibmveth_change_mtu(struct net_device *dev, int new_mtu);
static void ibmveth_proc_register_driver(void);
static void ibmveth_proc_unregister_driver(void);
static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter);
static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter);
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 20:55:46 +07:00
static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter);
static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev);
static struct kobj_type ktype_veth_pool;
#ifdef CONFIG_PROC_FS
#define IBMVETH_PROC_DIR "ibmveth"
static struct proc_dir_entry *ibmveth_proc_dir;
#endif
static const char ibmveth_driver_name[] = "ibmveth";
static const char ibmveth_driver_string[] = "IBM i/pSeries Virtual Ethernet Driver";
#define ibmveth_driver_version "1.03"
MODULE_AUTHOR("Santiago Leon <santil@us.ibm.com>");
MODULE_DESCRIPTION("IBM i/pSeries Virtual Ethernet Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(ibmveth_driver_version);
struct ibmveth_stat {
char name[ETH_GSTRING_LEN];
int offset;
};
#define IBMVETH_STAT_OFF(stat) offsetof(struct ibmveth_adapter, stat)
#define IBMVETH_GET_STAT(a, off) *((u64 *)(((unsigned long)(a)) + off))
struct ibmveth_stat ibmveth_stats[] = {
{ "replenish_task_cycles", IBMVETH_STAT_OFF(replenish_task_cycles) },
{ "replenish_no_mem", IBMVETH_STAT_OFF(replenish_no_mem) },
{ "replenish_add_buff_failure", IBMVETH_STAT_OFF(replenish_add_buff_failure) },
{ "replenish_add_buff_success", IBMVETH_STAT_OFF(replenish_add_buff_success) },
{ "rx_invalid_buffer", IBMVETH_STAT_OFF(rx_invalid_buffer) },
{ "rx_no_buffer", IBMVETH_STAT_OFF(rx_no_buffer) },
{ "tx_map_failed", IBMVETH_STAT_OFF(tx_map_failed) },
{ "tx_send_failed", IBMVETH_STAT_OFF(tx_send_failed) },
};
/* simple methods of getting data from the current rxq entry */
static inline u32 ibmveth_rxq_flags(struct ibmveth_adapter *adapter)
{
return adapter->rx_queue.queue_addr[adapter->rx_queue.index].flags_off;
}
static inline int ibmveth_rxq_toggle(struct ibmveth_adapter *adapter)
{
return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_TOGGLE) >> IBMVETH_RXQ_TOGGLE_SHIFT;
}
static inline int ibmveth_rxq_pending_buffer(struct ibmveth_adapter *adapter)
{
return (ibmveth_rxq_toggle(adapter) == adapter->rx_queue.toggle);
}
static inline int ibmveth_rxq_buffer_valid(struct ibmveth_adapter *adapter)
{
return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_VALID);
}
static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter)
{
return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK);
}
static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter)
{
return (adapter->rx_queue.queue_addr[adapter->rx_queue.index].length);
}
static inline int ibmveth_rxq_csum_good(struct ibmveth_adapter *adapter)
{
return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_CSUM_GOOD);
}
/* setup the initial settings for a buffer pool */
static void ibmveth_init_buffer_pool(struct ibmveth_buff_pool *pool, u32 pool_index, u32 pool_size, u32 buff_size, u32 pool_active)
{
pool->size = pool_size;
pool->index = pool_index;
pool->buff_size = buff_size;
pool->threshold = pool_size / 2;
pool->active = pool_active;
}
/* allocate and setup an buffer pool - called during open */
static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool)
{
int i;
pool->free_map = kmalloc(sizeof(u16) * pool->size, GFP_KERNEL);
if(!pool->free_map) {
return -1;
}
pool->dma_addr = kmalloc(sizeof(dma_addr_t) * pool->size, GFP_KERNEL);
if(!pool->dma_addr) {
kfree(pool->free_map);
pool->free_map = NULL;
return -1;
}
pool->skbuff = kmalloc(sizeof(void*) * pool->size, GFP_KERNEL);
if(!pool->skbuff) {
kfree(pool->dma_addr);
pool->dma_addr = NULL;
kfree(pool->free_map);
pool->free_map = NULL;
return -1;
}
memset(pool->skbuff, 0, sizeof(void*) * pool->size);
memset(pool->dma_addr, 0, sizeof(dma_addr_t) * pool->size);
for(i = 0; i < pool->size; ++i) {
pool->free_map[i] = i;
}
atomic_set(&pool->available, 0);
pool->producer_index = 0;
pool->consumer_index = 0;
return 0;
}
/* replenish the buffers for a pool. note that we don't need to
* skb_reserve these since they are used for incoming...
*/
static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool)
{
u32 i;
u32 count = pool->size - atomic_read(&pool->available);
u32 buffers_added = 0;
struct sk_buff *skb;
unsigned int free_index, index;
u64 correlator;
unsigned long lpar_rc;
dma_addr_t dma_addr;
mb();
for(i = 0; i < count; ++i) {
union ibmveth_buf_desc desc;
skb = alloc_skb(pool->buff_size, GFP_ATOMIC);
if(!skb) {
ibmveth_debug_printk("replenish: unable to allocate skb\n");
adapter->replenish_no_mem++;
break;
}
free_index = pool->consumer_index;
pool->consumer_index = (pool->consumer_index + 1) % pool->size;
index = pool->free_map[free_index];
ibmveth_assert(index != IBM_VETH_INVALID_MAP);
ibmveth_assert(pool->skbuff[index] == NULL);
dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
pool->buff_size, DMA_FROM_DEVICE);
if (dma_mapping_error(&adapter->vdev->dev, dma_addr))
goto failure;
pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
pool->dma_addr[index] = dma_addr;
pool->skbuff[index] = skb;
correlator = ((u64)pool->index << 32) | index;
*(u64*)skb->data = correlator;
desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size;
desc.fields.address = dma_addr;
lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);
if (lpar_rc != H_SUCCESS)
goto failure;
else {
buffers_added++;
adapter->replenish_add_buff_success++;
}
}
mb();
atomic_add(buffers_added, &(pool->available));
return;
failure:
pool->free_map[free_index] = index;
pool->skbuff[index] = NULL;
if (pool->consumer_index == 0)
pool->consumer_index = pool->size - 1;
else
pool->consumer_index--;
if (!dma_mapping_error(&adapter->vdev->dev, dma_addr))
dma_unmap_single(&adapter->vdev->dev,
pool->dma_addr[index], pool->buff_size,
DMA_FROM_DEVICE);
dev_kfree_skb_any(skb);
adapter->replenish_add_buff_failure++;
mb();
atomic_add(buffers_added, &(pool->available));
}
/* replenish routine */
static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
{
int i;
adapter->replenish_task_cycles++;
for (i = (IbmVethNumBufferPools - 1); i >= 0; i--)
if(adapter->rx_buff_pool[i].active)
ibmveth_replenish_buffer_pool(adapter,
&adapter->rx_buff_pool[i]);
adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);
}
/* empty and free ana buffer pool - also used to do cleanup in error paths */
static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool)
{
int i;
kfree(pool->free_map);
pool->free_map = NULL;
if(pool->skbuff && pool->dma_addr) {
for(i = 0; i < pool->size; ++i) {
struct sk_buff *skb = pool->skbuff[i];
if(skb) {
dma_unmap_single(&adapter->vdev->dev,
pool->dma_addr[i],
pool->buff_size,
DMA_FROM_DEVICE);
dev_kfree_skb_any(skb);
pool->skbuff[i] = NULL;
}
}
}
if(pool->dma_addr) {
kfree(pool->dma_addr);
pool->dma_addr = NULL;
}
if(pool->skbuff) {
kfree(pool->skbuff);
pool->skbuff = NULL;
}
}
/* remove a buffer from a pool */
static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, u64 correlator)
{
unsigned int pool = correlator >> 32;
unsigned int index = correlator & 0xffffffffUL;
unsigned int free_index;
struct sk_buff *skb;
ibmveth_assert(pool < IbmVethNumBufferPools);
ibmveth_assert(index < adapter->rx_buff_pool[pool].size);
skb = adapter->rx_buff_pool[pool].skbuff[index];
ibmveth_assert(skb != NULL);
adapter->rx_buff_pool[pool].skbuff[index] = NULL;
dma_unmap_single(&adapter->vdev->dev,
adapter->rx_buff_pool[pool].dma_addr[index],
adapter->rx_buff_pool[pool].buff_size,
DMA_FROM_DEVICE);
free_index = adapter->rx_buff_pool[pool].producer_index;
adapter->rx_buff_pool[pool].producer_index
= (adapter->rx_buff_pool[pool].producer_index + 1)
% adapter->rx_buff_pool[pool].size;
adapter->rx_buff_pool[pool].free_map[free_index] = index;
mb();
atomic_dec(&(adapter->rx_buff_pool[pool].available));
}
/* get the current buffer on the rx queue */
static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *adapter)
{
u64 correlator = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
unsigned int pool = correlator >> 32;
unsigned int index = correlator & 0xffffffffUL;
ibmveth_assert(pool < IbmVethNumBufferPools);
ibmveth_assert(index < adapter->rx_buff_pool[pool].size);
return adapter->rx_buff_pool[pool].skbuff[index];
}
/* recycle the current buffer on the rx queue */
static void ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter)
{
u32 q_index = adapter->rx_queue.index;
u64 correlator = adapter->rx_queue.queue_addr[q_index].correlator;
unsigned int pool = correlator >> 32;
unsigned int index = correlator & 0xffffffffUL;
union ibmveth_buf_desc desc;
unsigned long lpar_rc;
ibmveth_assert(pool < IbmVethNumBufferPools);
ibmveth_assert(index < adapter->rx_buff_pool[pool].size);
if(!adapter->rx_buff_pool[pool].active) {
ibmveth_rxq_harvest_buffer(adapter);
ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]);
return;
}
desc.fields.flags_len = IBMVETH_BUF_VALID |
adapter->rx_buff_pool[pool].buff_size;
desc.fields.address = adapter->rx_buff_pool[pool].dma_addr[index];
lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);
if(lpar_rc != H_SUCCESS) {
ibmveth_debug_printk("h_add_logical_lan_buffer failed during recycle rc=%ld", lpar_rc);
ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);
}
if(++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
adapter->rx_queue.index = 0;
adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
}
}
static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter)
{
ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);
if(++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
adapter->rx_queue.index = 0;
adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
}
}
static void ibmveth_cleanup(struct ibmveth_adapter *adapter)
{
int i;
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
struct device *dev = &adapter->vdev->dev;
if(adapter->buffer_list_addr != NULL) {
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
if (!dma_mapping_error(dev, adapter->buffer_list_dma)) {
dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
DMA_BIDIRECTIONAL);
adapter->buffer_list_dma = DMA_ERROR_CODE;
}
free_page((unsigned long)adapter->buffer_list_addr);
adapter->buffer_list_addr = NULL;
}
if(adapter->filter_list_addr != NULL) {
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
if (!dma_mapping_error(dev, adapter->filter_list_dma)) {
dma_unmap_single(dev, adapter->filter_list_dma, 4096,
DMA_BIDIRECTIONAL);
adapter->filter_list_dma = DMA_ERROR_CODE;
}
free_page((unsigned long)adapter->filter_list_addr);
adapter->filter_list_addr = NULL;
}
if(adapter->rx_queue.queue_addr != NULL) {
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
if (!dma_mapping_error(dev, adapter->rx_queue.queue_dma)) {
dma_unmap_single(dev,
adapter->rx_queue.queue_dma,
adapter->rx_queue.queue_len,
DMA_BIDIRECTIONAL);
adapter->rx_queue.queue_dma = DMA_ERROR_CODE;
}
kfree(adapter->rx_queue.queue_addr);
adapter->rx_queue.queue_addr = NULL;
}
for(i = 0; i<IbmVethNumBufferPools; i++)
if (adapter->rx_buff_pool[i].active)
ibmveth_free_buffer_pool(adapter,
&adapter->rx_buff_pool[i]);
if (adapter->bounce_buffer != NULL) {
if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
dma_unmap_single(&adapter->vdev->dev,
adapter->bounce_buffer_dma,
adapter->netdev->mtu + IBMVETH_BUFF_OH,
DMA_BIDIRECTIONAL);
adapter->bounce_buffer_dma = DMA_ERROR_CODE;
}
kfree(adapter->bounce_buffer);
adapter->bounce_buffer = NULL;
}
}
static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
union ibmveth_buf_desc rxq_desc, u64 mac_address)
{
int rc, try_again = 1;
/* After a kexec the adapter will still be open, so our attempt to
* open it will fail. So if we get a failure we free the adapter and
* try again, but only once. */
retry:
rc = h_register_logical_lan(adapter->vdev->unit_address,
adapter->buffer_list_dma, rxq_desc.desc,
adapter->filter_list_dma, mac_address);
if (rc != H_SUCCESS && try_again) {
do {
rc = h_free_logical_lan(adapter->vdev->unit_address);
} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));
try_again = 0;
goto retry;
}
return rc;
}
static int ibmveth_open(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
u64 mac_address = 0;
int rxq_entries = 1;
unsigned long lpar_rc;
int rc;
union ibmveth_buf_desc rxq_desc;
int i;
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
struct device *dev;
ibmveth_debug_printk("open starting\n");
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_enable(&adapter->napi);
for(i = 0; i<IbmVethNumBufferPools; i++)
rxq_entries += adapter->rx_buff_pool[i].size;
adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
if(!adapter->buffer_list_addr || !adapter->filter_list_addr) {
ibmveth_error_printk("unable to allocate filter or buffer list pages\n");
ibmveth_cleanup(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
return -ENOMEM;
}
adapter->rx_queue.queue_len = sizeof(struct ibmveth_rx_q_entry) * rxq_entries;
adapter->rx_queue.queue_addr = kmalloc(adapter->rx_queue.queue_len, GFP_KERNEL);
if(!adapter->rx_queue.queue_addr) {
ibmveth_error_printk("unable to allocate rx queue pages\n");
ibmveth_cleanup(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
return -ENOMEM;
}
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
dev = &adapter->vdev->dev;
adapter->buffer_list_dma = dma_map_single(dev,
adapter->buffer_list_addr, 4096, DMA_BIDIRECTIONAL);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
adapter->filter_list_dma = dma_map_single(dev,
adapter->filter_list_addr, 4096, DMA_BIDIRECTIONAL);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
adapter->rx_queue.queue_dma = dma_map_single(dev,
adapter->rx_queue.queue_addr,
adapter->rx_queue.queue_len, DMA_BIDIRECTIONAL);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
if ((dma_mapping_error(dev, adapter->buffer_list_dma)) ||
(dma_mapping_error(dev, adapter->filter_list_dma)) ||
(dma_mapping_error(dev, adapter->rx_queue.queue_dma))) {
ibmveth_error_printk("unable to map filter or buffer list pages\n");
ibmveth_cleanup(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
return -ENOMEM;
}
adapter->rx_queue.index = 0;
adapter->rx_queue.num_slots = rxq_entries;
adapter->rx_queue.toggle = 1;
memcpy(&mac_address, netdev->dev_addr, netdev->addr_len);
mac_address = mac_address >> 16;
rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len;
rxq_desc.fields.address = adapter->rx_queue.queue_dma;
ibmveth_debug_printk("buffer list @ 0x%p\n", adapter->buffer_list_addr);
ibmveth_debug_printk("filter list @ 0x%p\n", adapter->filter_list_addr);
ibmveth_debug_printk("receive q @ 0x%p\n", adapter->rx_queue.queue_addr);
h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);
lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);
if(lpar_rc != H_SUCCESS) {
ibmveth_error_printk("h_register_logical_lan failed with %ld\n", lpar_rc);
ibmveth_error_printk("buffer TCE:0x%llx filter TCE:0x%llx rxq desc:0x%llx MAC:0x%llx\n",
adapter->buffer_list_dma,
adapter->filter_list_dma,
rxq_desc.desc,
mac_address);
ibmveth_cleanup(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
return -ENONET;
}
for(i = 0; i<IbmVethNumBufferPools; i++) {
if(!adapter->rx_buff_pool[i].active)
continue;
if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[i])) {
ibmveth_error_printk("unable to alloc pool\n");
adapter->rx_buff_pool[i].active = 0;
ibmveth_cleanup(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
return -ENOMEM ;
}
}
ibmveth_debug_printk("registering irq 0x%x\n", netdev->irq);
if((rc = request_irq(netdev->irq, ibmveth_interrupt, 0, netdev->name, netdev)) != 0) {
ibmveth_error_printk("unable to request irq 0x%x, rc %d\n", netdev->irq, rc);
do {
rc = h_free_logical_lan(adapter->vdev->unit_address);
} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));
ibmveth_cleanup(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
return rc;
}
adapter->bounce_buffer =
kmalloc(netdev->mtu + IBMVETH_BUFF_OH, GFP_KERNEL);
if (!adapter->bounce_buffer) {
ibmveth_error_printk("unable to allocate bounce buffer\n");
ibmveth_cleanup(adapter);
napi_disable(&adapter->napi);
return -ENOMEM;
}
adapter->bounce_buffer_dma =
dma_map_single(&adapter->vdev->dev, adapter->bounce_buffer,
netdev->mtu + IBMVETH_BUFF_OH, DMA_BIDIRECTIONAL);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
ibmveth_error_printk("unable to map bounce buffer\n");
ibmveth_cleanup(adapter);
napi_disable(&adapter->napi);
return -ENOMEM;
}
ibmveth_debug_printk("initial replenish cycle\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 20:55:46 +07:00
ibmveth_interrupt(netdev->irq, netdev);
netif_start_queue(netdev);
ibmveth_debug_printk("open complete\n");
return 0;
}
static int ibmveth_close(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
long lpar_rc;
ibmveth_debug_printk("close starting\n");
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
napi_disable(&adapter->napi);
if (!adapter->pool_config)
netif_stop_queue(netdev);
free_irq(netdev->irq, netdev);
do {
lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
if(lpar_rc != H_SUCCESS)
{
ibmveth_error_printk("h_free_logical_lan failed with %lx, continuing with close\n",
lpar_rc);
}
adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);
ibmveth_cleanup(adapter);
ibmveth_debug_printk("close complete\n");
return 0;
}
static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) {
cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE);
cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | ADVERTISED_FIBRE);
cmd->speed = SPEED_1000;
cmd->duplex = DUPLEX_FULL;
cmd->port = PORT_FIBRE;
cmd->phy_address = 0;
cmd->transceiver = XCVR_INTERNAL;
cmd->autoneg = AUTONEG_ENABLE;
cmd->maxtxpkt = 0;
cmd->maxrxpkt = 1;
return 0;
}
static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *info) {
strncpy(info->driver, ibmveth_driver_name, sizeof(info->driver) - 1);
strncpy(info->version, ibmveth_driver_version, sizeof(info->version) - 1);
}
static u32 netdev_get_link(struct net_device *dev) {
return 1;
}
static void ibmveth_set_rx_csum_flags(struct net_device *dev, u32 data)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
if (data)
adapter->rx_csum = 1;
else {
/*
* Since the ibmveth firmware interface does not have the concept of
* separate tx/rx checksum offload enable, if rx checksum is disabled
* we also have to disable tx checksum offload. Once we disable rx
* checksum offload, we are no longer allowed to send tx buffers that
* are not properly checksummed.
*/
adapter->rx_csum = 0;
dev->features &= ~NETIF_F_IP_CSUM;
}
}
static void ibmveth_set_tx_csum_flags(struct net_device *dev, u32 data)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
if (data) {
dev->features |= NETIF_F_IP_CSUM;
adapter->rx_csum = 1;
} else
dev->features &= ~NETIF_F_IP_CSUM;
}
static int ibmveth_set_csum_offload(struct net_device *dev, u32 data,
void (*done) (struct net_device *, u32))
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
unsigned long set_attr, clr_attr, ret_attr;
long ret;
int rc1 = 0, rc2 = 0;
int restart = 0;
if (netif_running(dev)) {
restart = 1;
adapter->pool_config = 1;
ibmveth_close(dev);
adapter->pool_config = 0;
}
set_attr = 0;
clr_attr = 0;
if (data)
set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;
else
clr_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;
ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr);
if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
!(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
(ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
ret = h_illan_attributes(adapter->vdev->unit_address, clr_attr,
set_attr, &ret_attr);
if (ret != H_SUCCESS) {
rc1 = -EIO;
ibmveth_error_printk("unable to change checksum offload settings."
" %d rc=%ld\n", data, ret);
ret = h_illan_attributes(adapter->vdev->unit_address,
set_attr, clr_attr, &ret_attr);
} else
done(dev, data);
} else {
rc1 = -EIO;
ibmveth_error_printk("unable to change checksum offload settings."
" %d rc=%ld ret_attr=%lx\n", data, ret, ret_attr);
}
if (restart)
rc2 = ibmveth_open(dev);
return rc1 ? rc1 : rc2;
}
static int ibmveth_set_rx_csum(struct net_device *dev, u32 data)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
if ((data && adapter->rx_csum) || (!data && !adapter->rx_csum))
return 0;
return ibmveth_set_csum_offload(dev, data, ibmveth_set_rx_csum_flags);
}
static int ibmveth_set_tx_csum(struct net_device *dev, u32 data)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
int rc = 0;
if (data && (dev->features & NETIF_F_IP_CSUM))
return 0;
if (!data && !(dev->features & NETIF_F_IP_CSUM))
return 0;
if (data && !adapter->rx_csum)
rc = ibmveth_set_csum_offload(dev, data, ibmveth_set_tx_csum_flags);
else
ibmveth_set_tx_csum_flags(dev, data);
return rc;
}
static u32 ibmveth_get_rx_csum(struct net_device *dev)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
return adapter->rx_csum;
}
static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
int i;
if (stringset != ETH_SS_STATS)
return;
for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++, data += ETH_GSTRING_LEN)
memcpy(data, ibmveth_stats[i].name, ETH_GSTRING_LEN);
}
static int ibmveth_get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(ibmveth_stats);
default:
return -EOPNOTSUPP;
}
}
static void ibmveth_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
int i;
struct ibmveth_adapter *adapter = netdev_priv(dev);
for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++)
data[i] = IBMVETH_GET_STAT(adapter, ibmveth_stats[i].offset);
}
static const struct ethtool_ops netdev_ethtool_ops = {
.get_drvinfo = netdev_get_drvinfo,
.get_settings = netdev_get_settings,
.get_link = netdev_get_link,
.set_tx_csum = ibmveth_set_tx_csum,
.get_rx_csum = ibmveth_get_rx_csum,
.set_rx_csum = ibmveth_set_rx_csum,
.get_strings = ibmveth_get_strings,
.get_sset_count = ibmveth_get_sset_count,
.get_ethtool_stats = ibmveth_get_ethtool_stats,
};
static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
return -EOPNOTSUPP;
}
#define page_offset(v) ((unsigned long)(v) & ((1 << 12) - 1))
static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
union ibmveth_buf_desc desc;
unsigned long lpar_rc;
unsigned long correlator;
unsigned long flags;
unsigned int retry_count;
unsigned int tx_dropped = 0;
unsigned int tx_bytes = 0;
unsigned int tx_packets = 0;
unsigned int tx_send_failed = 0;
unsigned int tx_map_failed = 0;
int used_bounce = 0;
unsigned long data_dma_addr;
desc.fields.flags_len = IBMVETH_BUF_VALID | skb->len;
if (skb->ip_summed == CHECKSUM_PARTIAL &&
ip_hdr(skb)->protocol != IPPROTO_TCP && skb_checksum_help(skb)) {
ibmveth_error_printk("tx: failed to checksum packet\n");
tx_dropped++;
goto out;
}
if (skb->ip_summed == CHECKSUM_PARTIAL) {
unsigned char *buf = skb_transport_header(skb) + skb->csum_offset;
desc.fields.flags_len |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD);
/* Need to zero out the checksum */
buf[0] = 0;
buf[1] = 0;
}
data_dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
skb->len, DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->vdev->dev, data_dma_addr)) {
if (!firmware_has_feature(FW_FEATURE_CMO))
ibmveth_error_printk("tx: unable to map xmit buffer\n");
skb_copy_from_linear_data(skb, adapter->bounce_buffer,
skb->len);
desc.fields.address = adapter->bounce_buffer_dma;
tx_map_failed++;
used_bounce = 1;
wmb();
} else
desc.fields.address = data_dma_addr;
/* send the frame. Arbitrarily set retrycount to 1024 */
correlator = 0;
retry_count = 1024;
do {
lpar_rc = h_send_logical_lan(adapter->vdev->unit_address,
desc.desc, 0, 0, 0, 0, 0,
correlator, &correlator);
} while ((lpar_rc == H_BUSY) && (retry_count--));
if(lpar_rc != H_SUCCESS && lpar_rc != H_DROPPED) {
ibmveth_error_printk("tx: h_send_logical_lan failed with rc=%ld\n", lpar_rc);
ibmveth_error_printk("tx: valid=%d, len=%d, address=0x%08x\n",
(desc.fields.flags_len & IBMVETH_BUF_VALID) ? 1 : 0,
skb->len, desc.fields.address);
tx_send_failed++;
tx_dropped++;
} else {
tx_packets++;
tx_bytes += skb->len;
netdev->trans_start = jiffies;
}
if (!used_bounce)
dma_unmap_single(&adapter->vdev->dev, data_dma_addr,
skb->len, DMA_TO_DEVICE);
out: spin_lock_irqsave(&adapter->stats_lock, flags);
netdev->stats.tx_dropped += tx_dropped;
netdev->stats.tx_bytes += tx_bytes;
netdev->stats.tx_packets += tx_packets;
adapter->tx_send_failed += tx_send_failed;
adapter->tx_map_failed += tx_map_failed;
spin_unlock_irqrestore(&adapter->stats_lock, flags);
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
static int ibmveth_poll(struct napi_struct *napi, int budget)
{
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
struct ibmveth_adapter *adapter = container_of(napi, struct ibmveth_adapter, napi);
struct net_device *netdev = adapter->netdev;
int frames_processed = 0;
unsigned long lpar_rc;
restart_poll:
do {
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
struct sk_buff *skb;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
if (!ibmveth_rxq_pending_buffer(adapter))
break;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
rmb();
if (!ibmveth_rxq_buffer_valid(adapter)) {
wmb(); /* suggested by larson1 */
adapter->rx_invalid_buffer++;
ibmveth_debug_printk("recycling invalid buffer\n");
ibmveth_rxq_recycle_buffer(adapter);
} else {
int length = ibmveth_rxq_frame_length(adapter);
int offset = ibmveth_rxq_frame_offset(adapter);
int csum_good = ibmveth_rxq_csum_good(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
skb = ibmveth_rxq_get_buffer(adapter);
if (csum_good)
skb->ip_summed = CHECKSUM_UNNECESSARY;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
ibmveth_rxq_harvest_buffer(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
skb_reserve(skb, offset);
skb_put(skb, length);
skb->protocol = eth_type_trans(skb, netdev);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
netif_receive_skb(skb); /* send it up */
netdev->stats.rx_packets++;
netdev->stats.rx_bytes += length;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
frames_processed++;
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
} while (frames_processed < budget);
ibmveth_replenish_task(adapter);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
if (frames_processed < budget) {
/* We think we are done - reenable interrupts,
* then check once more to make sure we are done.
*/
lpar_rc = h_vio_signal(adapter->vdev->unit_address,
VIO_IRQ_ENABLE);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
ibmveth_assert(lpar_rc == H_SUCCESS);
napi_complete(napi);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
if (ibmveth_rxq_pending_buffer(adapter) &&
napi_reschedule(napi)) {
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
lpar_rc = h_vio_signal(adapter->vdev->unit_address,
VIO_IRQ_DISABLE);
goto restart_poll;
}
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
return frames_processed;
}
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 20:55:46 +07:00
static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
{
struct net_device *netdev = dev_instance;
struct ibmveth_adapter *adapter = netdev_priv(netdev);
unsigned long lpar_rc;
if (napi_schedule_prep(&adapter->napi)) {
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
lpar_rc = h_vio_signal(adapter->vdev->unit_address,
VIO_IRQ_DISABLE);
ibmveth_assert(lpar_rc == H_SUCCESS);
__napi_schedule(&adapter->napi);
}
return IRQ_HANDLED;
}
static void ibmveth_set_multicast_list(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
unsigned long lpar_rc;
if ((netdev->flags & IFF_PROMISC) ||
(netdev_mc_count(netdev) > adapter->mcastFilterSize)) {
lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
IbmVethMcastEnableRecv |
IbmVethMcastDisableFiltering,
0);
if(lpar_rc != H_SUCCESS) {
ibmveth_error_printk("h_multicast_ctrl rc=%ld when entering promisc mode\n", lpar_rc);
}
} else {
struct dev_mc_list *mclist;
/* clear the filter table & disable filtering */
lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
IbmVethMcastEnableRecv |
IbmVethMcastDisableFiltering |
IbmVethMcastClearFilterTable,
0);
if(lpar_rc != H_SUCCESS) {
ibmveth_error_printk("h_multicast_ctrl rc=%ld when attempting to clear filter table\n", lpar_rc);
}
/* add the addresses to the filter table */
netdev_for_each_mc_addr(mclist, netdev) {
// add the multicast address to the filter table
unsigned long mcast_addr = 0;
memcpy(((char *)&mcast_addr)+2, mclist->dmi_addr, 6);
lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
IbmVethMcastAddFilter,
mcast_addr);
if(lpar_rc != H_SUCCESS) {
ibmveth_error_printk("h_multicast_ctrl rc=%ld when adding an entry to the filter table\n", lpar_rc);
}
}
/* re-enable filtering */
lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
IbmVethMcastEnableFiltering,
0);
if(lpar_rc != H_SUCCESS) {
ibmveth_error_printk("h_multicast_ctrl rc=%ld when enabling filtering\n", lpar_rc);
}
}
}
static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
struct vio_dev *viodev = adapter->vdev;
int new_mtu_oh = new_mtu + IBMVETH_BUFF_OH;
int i;
if (new_mtu < IBMVETH_MAX_MTU)
return -EINVAL;
for (i = 0; i < IbmVethNumBufferPools; i++)
if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size)
break;
if (i == IbmVethNumBufferPools)
return -EINVAL;
/* Deactivate all the buffer pools so that the next loop can activate
only the buffer pools necessary to hold the new MTU */
for (i = 0; i < IbmVethNumBufferPools; i++)
if (adapter->rx_buff_pool[i].active) {
ibmveth_free_buffer_pool(adapter,
&adapter->rx_buff_pool[i]);
adapter->rx_buff_pool[i].active = 0;
}
/* Look for an active buffer pool that can hold the new MTU */
for(i = 0; i<IbmVethNumBufferPools; i++) {
adapter->rx_buff_pool[i].active = 1;
if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) {
if (netif_running(adapter->netdev)) {
adapter->pool_config = 1;
ibmveth_close(adapter->netdev);
adapter->pool_config = 0;
dev->mtu = new_mtu;
vio_cmo_set_dev_desired(viodev,
ibmveth_get_desired_dma
(viodev));
return ibmveth_open(adapter->netdev);
}
dev->mtu = new_mtu;
vio_cmo_set_dev_desired(viodev,
ibmveth_get_desired_dma
(viodev));
return 0;
}
}
return -EINVAL;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void ibmveth_poll_controller(struct net_device *dev)
{
ibmveth_replenish_task(netdev_priv(dev));
ibmveth_interrupt(dev->irq, dev);
}
#endif
/**
* ibmveth_get_desired_dma - Calculate IO memory desired by the driver
*
* @vdev: struct vio_dev for the device whose desired IO mem is to be returned
*
* Return value:
* Number of bytes of IO data the driver will need to perform well.
*/
static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev)
{
struct net_device *netdev = dev_get_drvdata(&vdev->dev);
struct ibmveth_adapter *adapter;
unsigned long ret;
int i;
int rxqentries = 1;
/* netdev inits at probe time along with the structures we need below*/
if (netdev == NULL)
return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT);
adapter = netdev_priv(netdev);
ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE;
ret += IOMMU_PAGE_ALIGN(netdev->mtu);
for (i = 0; i < IbmVethNumBufferPools; i++) {
/* add the size of the active receive buffers */
if (adapter->rx_buff_pool[i].active)
ret +=
adapter->rx_buff_pool[i].size *
IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i].
buff_size);
rxqentries += adapter->rx_buff_pool[i].size;
}
/* add the size of the receive queue entries */
ret += IOMMU_PAGE_ALIGN(rxqentries * sizeof(struct ibmveth_rx_q_entry));
return ret;
}
static const struct net_device_ops ibmveth_netdev_ops = {
.ndo_open = ibmveth_open,
.ndo_stop = ibmveth_close,
.ndo_start_xmit = ibmveth_start_xmit,
.ndo_set_multicast_list = ibmveth_set_multicast_list,
.ndo_do_ioctl = ibmveth_ioctl,
.ndo_change_mtu = ibmveth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = ibmveth_poll_controller,
#endif
};
static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
{
int rc, i;
long ret;
struct net_device *netdev;
struct ibmveth_adapter *adapter;
unsigned long set_attr, ret_attr;
unsigned char *mac_addr_p;
unsigned int *mcastFilterSize_p;
ibmveth_debug_printk_no_adapter("entering ibmveth_probe for UA 0x%x\n",
dev->unit_address);
mac_addr_p = (unsigned char *) vio_get_attribute(dev,
VETH_MAC_ADDR, NULL);
if(!mac_addr_p) {
printk(KERN_ERR "(%s:%3.3d) ERROR: Can't find VETH_MAC_ADDR "
"attribute\n", __FILE__, __LINE__);
return 0;
}
mcastFilterSize_p = (unsigned int *) vio_get_attribute(dev,
VETH_MCAST_FILTER_SIZE, NULL);
if(!mcastFilterSize_p) {
printk(KERN_ERR "(%s:%3.3d) ERROR: Can't find "
"VETH_MCAST_FILTER_SIZE attribute\n",
__FILE__, __LINE__);
return 0;
}
netdev = alloc_etherdev(sizeof(struct ibmveth_adapter));
if(!netdev)
return -ENOMEM;
adapter = netdev_priv(netdev);
dev_set_drvdata(&dev->dev, netdev);
adapter->vdev = dev;
adapter->netdev = netdev;
adapter->mcastFilterSize= *mcastFilterSize_p;
adapter->pool_config = 0;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 06:41:36 +07:00
netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
/* Some older boxes running PHYP non-natively have an OF that
returns a 8-byte local-mac-address field (and the first
2 bytes have to be ignored) while newer boxes' OF return
a 6-byte field. Note that IEEE 1275 specifies that
local-mac-address must be a 6-byte field.
The RPA doc specifies that the first byte must be 10b, so
we'll just look for it to solve this 8 vs. 6 byte field issue */
if ((*mac_addr_p & 0x3) != 0x02)
mac_addr_p += 2;
adapter->mac_addr = 0;
memcpy(&adapter->mac_addr, mac_addr_p, 6);
netdev->irq = dev->irq;
netdev->netdev_ops = &ibmveth_netdev_ops;
netdev->ethtool_ops = &netdev_ethtool_ops;
SET_NETDEV_DEV(netdev, &dev->dev);
netdev->features |= NETIF_F_LLTX;
spin_lock_init(&adapter->stats_lock);
memcpy(netdev->dev_addr, &adapter->mac_addr, netdev->addr_len);
for(i = 0; i<IbmVethNumBufferPools; i++) {
struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
int error;
ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
pool_count[i], pool_size[i],
pool_active[i]);
error = kobject_init_and_add(kobj, &ktype_veth_pool,
&dev->dev.kobj, "pool%d", i);
if (!error)
kobject_uevent(kobj, KOBJ_ADD);
}
ibmveth_debug_printk("adapter @ 0x%p\n", adapter);
adapter->buffer_list_dma = DMA_ERROR_CODE;
adapter->filter_list_dma = DMA_ERROR_CODE;
adapter->rx_queue.queue_dma = DMA_ERROR_CODE;
ibmveth_debug_printk("registering netdev...\n");
ret = h_illan_attributes(dev->unit_address, 0, 0, &ret_attr);
if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
!(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
(ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;
ret = h_illan_attributes(dev->unit_address, 0, set_attr, &ret_attr);
if (ret == H_SUCCESS) {
adapter->rx_csum = 1;
netdev->features |= NETIF_F_IP_CSUM;
} else
ret = h_illan_attributes(dev->unit_address, set_attr, 0, &ret_attr);
}
rc = register_netdev(netdev);
if(rc) {
ibmveth_debug_printk("failed to register netdev rc=%d\n", rc);
free_netdev(netdev);
return rc;
}
ibmveth_debug_printk("registered\n");
ibmveth_proc_register_adapter(adapter);
return 0;
}
static int __devexit ibmveth_remove(struct vio_dev *dev)
{
struct net_device *netdev = dev_get_drvdata(&dev->dev);
struct ibmveth_adapter *adapter = netdev_priv(netdev);
int i;
for(i = 0; i<IbmVethNumBufferPools; i++)
kobject_put(&adapter->rx_buff_pool[i].kobj);
unregister_netdev(netdev);
ibmveth_proc_unregister_adapter(adapter);
free_netdev(netdev);
dev_set_drvdata(&dev->dev, NULL);
return 0;
}
#ifdef CONFIG_PROC_FS
static void ibmveth_proc_register_driver(void)
{
ibmveth_proc_dir = proc_mkdir(IBMVETH_PROC_DIR, init_net.proc_net);
if (ibmveth_proc_dir) {
}
}
static void ibmveth_proc_unregister_driver(void)
{
remove_proc_entry(IBMVETH_PROC_DIR, init_net.proc_net);
}
static int ibmveth_show(struct seq_file *seq, void *v)
{
struct ibmveth_adapter *adapter = seq->private;
char *current_mac = (char *) adapter->netdev->dev_addr;
char *firmware_mac = (char *) &adapter->mac_addr;
seq_printf(seq, "%s %s\n\n", ibmveth_driver_string, ibmveth_driver_version);
seq_printf(seq, "Unit Address: 0x%x\n", adapter->vdev->unit_address);
seq_printf(seq, "Current MAC: %pM\n", current_mac);
seq_printf(seq, "Firmware MAC: %pM\n", firmware_mac);
seq_printf(seq, "\nAdapter Statistics:\n");
seq_printf(seq, " TX: vio_map_single failres: %lld\n", adapter->tx_map_failed);
seq_printf(seq, " send failures: %lld\n", adapter->tx_send_failed);
seq_printf(seq, " RX: replenish task cycles: %lld\n", adapter->replenish_task_cycles);
seq_printf(seq, " alloc_skb_failures: %lld\n", adapter->replenish_no_mem);
seq_printf(seq, " add buffer failures: %lld\n", adapter->replenish_add_buff_failure);
seq_printf(seq, " invalid buffers: %lld\n", adapter->rx_invalid_buffer);
seq_printf(seq, " no buffers: %lld\n", adapter->rx_no_buffer);
return 0;
}
static int ibmveth_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, ibmveth_show, PDE(inode)->data);
}
static const struct file_operations ibmveth_proc_fops = {
.owner = THIS_MODULE,
.open = ibmveth_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter)
{
struct proc_dir_entry *entry;
if (ibmveth_proc_dir) {
char u_addr[10];
sprintf(u_addr, "%x", adapter->vdev->unit_address);
entry = proc_create_data(u_addr, S_IFREG, ibmveth_proc_dir,
&ibmveth_proc_fops, adapter);
if (!entry)
ibmveth_error_printk("Cannot create adapter proc entry");
}
return;
}
static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter)
{
if (ibmveth_proc_dir) {
char u_addr[10];
sprintf(u_addr, "%x", adapter->vdev->unit_address);
remove_proc_entry(u_addr, ibmveth_proc_dir);
}
}
#else /* CONFIG_PROC_FS */
static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter)
{
}
static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter)
{
}
static void ibmveth_proc_register_driver(void)
{
}
static void ibmveth_proc_unregister_driver(void)
{
}
#endif /* CONFIG_PROC_FS */
static struct attribute veth_active_attr;
static struct attribute veth_num_attr;
static struct attribute veth_size_attr;
static ssize_t veth_pool_show(struct kobject * kobj,
struct attribute * attr, char * buf)
{
struct ibmveth_buff_pool *pool = container_of(kobj,
struct ibmveth_buff_pool,
kobj);
if (attr == &veth_active_attr)
return sprintf(buf, "%d\n", pool->active);
else if (attr == &veth_num_attr)
return sprintf(buf, "%d\n", pool->size);
else if (attr == &veth_size_attr)
return sprintf(buf, "%d\n", pool->buff_size);
return 0;
}
static ssize_t veth_pool_store(struct kobject * kobj, struct attribute * attr,
const char * buf, size_t count)
{
struct ibmveth_buff_pool *pool = container_of(kobj,
struct ibmveth_buff_pool,
kobj);
struct net_device *netdev = dev_get_drvdata(
container_of(kobj->parent, struct device, kobj));
struct ibmveth_adapter *adapter = netdev_priv(netdev);
long value = simple_strtol(buf, NULL, 10);
long rc;
if (attr == &veth_active_attr) {
if (value && !pool->active) {
ibmveth: Fix h_free_logical_lan error on pool resize When attempting to activate additional rx buffer pools on an ibmveth interface that was not yet up, the error below was seen. The patch fixes this by only closing and opening the interface to activate the resize if the interface is already opened. (drivers/net/ibmveth.c:597 ua:30000004) ERROR: h_free_logical_lan failed with fffffffffffffffc, continuing with close Unable to handle kernel paging request for data at address 0x00000ff8 Faulting instruction address: 0xd0000000002540e0 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=128 NUMA PSERIES LPAR Modules linked in: ip6t_REJECT xt_tcpudp ipt_REJECT xt_state iptable_mangle ipta ble_nat ip_nat iptable_filter ip6table_mangle ip_conntrack nfnetlink ip_tables i p6table_filter ip6_tables x_tables ipv6 apparmor aamatch_pcre loop dm_mod ibmvet h sg ibmvscsic sd_mod scsi_mod NIP: D0000000002540E0 LR: D0000000002540D4 CTR: 80000000001AF404 REGS: c00000001cd27870 TRAP: 0300 Not tainted (2.6.16.46-0.4-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242422 XER: 00000007 DAR: 0000000000000FF8, DSISR: 0000000040000000 TASK = c00000001ca7b4e0[1636] 'sh' THREAD: c00000001cd24000 CPU: 0 GPR00: D0000000002540D4 C00000001CD27AF0 D000000000265650 C00000001C936500 GPR04: 8000000000009032 FFFFFFFFFFFFFFFF 0000000000000007 000000000002C2EF GPR08: FFFFFFFFFFFFFFFF 0000000000000000 C000000000652A10 C000000000652AE0 GPR12: 0000000000004000 C0000000004A3300 00000000100A0000 0000000000000000 GPR16: 00000000100B8808 00000000100C0F60 0000000000000000 0000000010084878 GPR20: 0000000000000000 00000000100C0CB0 00000000100AF498 0000000000000002 GPR24: 00000000100BA488 C00000001C936760 D000000000258DD0 C00000001C936000 GPR28: 0000000000000000 C00000001C936500 D000000000265180 C00000001C936000 NIP [D0000000002540E0] .ibmveth_close+0xc8/0xf4 [ibmveth] LR [D0000000002540D4] .ibmveth_close+0xbc/0xf4 [ibmveth] Call Trace: [C00000001CD27AF0] [D0000000002540D4] .ibmveth_close+0xbc/0xf4 [ibmveth] (unreliable) [C00000001CD27B80] [D0000000002545FC] .veth_pool_store+0xd0/0x260 [ibmveth] [C00000001CD27C40] [C00000000012E0E8] .sysfs_write_file+0x118/0x198 [C00000001CD27CF0] [C0000000000CDAF0] .vfs_write+0x130/0x218 [C00000001CD27D90] [C0000000000CE52C] .sys_write+0x4c/0x8c [C00000001CD27E30] [C00000000000871C] syscall_exit+0x0/0x40 Instruction dump: 419affd8 2fa30000 419e0020 e93d0000 e89e8040 38a00255 e87e81b0 80c90018 48001531 e8410028 e93d00e0 7fa3eb78 <e8090ff8> f81d0430 4bfffdc9 38210090 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-06-09 02:05:16 +07:00
if (netif_running(netdev)) {
if(ibmveth_alloc_buffer_pool(pool)) {
ibmveth_error_printk("unable to alloc pool\n");
return -ENOMEM;
}
pool->active = 1;
adapter->pool_config = 1;
ibmveth_close(netdev);
adapter->pool_config = 0;
if ((rc = ibmveth_open(netdev)))
return rc;
} else
pool->active = 1;
} else if (!value && pool->active) {
int mtu = netdev->mtu + IBMVETH_BUFF_OH;
int i;
/* Make sure there is a buffer pool with buffers that
can hold a packet of the size of the MTU */
ibmveth: Fix rx pool deactivate oops This fixes the following oops which can occur when trying to deallocate receive buffer pools using sysfs with the ibmveth driver. NIP: d00000000024f954 LR: d00000000024fa58 CTR: c0000000000d7478 REGS: c00000000ffef9f0 TRAP: 0300 Not tainted (2.6.22-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242442 XER: 00000010 DAR: 00000000000007f0, DSISR: 0000000042000000 TASK = c000000002f91360[2967] 'bash' THREAD: c00000001398c000 CPU: 2 GPR00: 0000000000000000 c00000000ffefc70 d000000000262d30 c00000001c4087a0 GPR04: 00000003000000fe 0000000000000000 000000000000000f c000000000579d80 GPR08: 0000000000365688 c00000001c408998 00000000000007f0 0000000000000000 GPR12: d000000000251e88 c000000000579d80 00000000200957ec 0000000000000000 GPR16: 00000000100b8808 00000000100feb30 0000000000000000 0000000010084828 GPR20: 0000000000000000 000000001014d4d0 0000000000000010 c00000000ffefeb0 GPR24: c00000001c408000 0000000000000000 c00000001c408000 00000000ffffb054 GPR28: 00000000000000fe 0000000000000003 d000000000262700 c00000001c4087a0 NIP [d00000000024f954] .ibmveth_remove_buffer_from_pool+0x38/0x108 [ibmveth] LR [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] Call Trace: [c00000000ffefc70] [c0000000000280a8] .dma_iommu_unmap_single+0x14/0x28 (unreliable) [c00000000ffefd00] [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] [c00000000ffefd80] [d000000000250e40] .ibmveth_poll+0xd8/0x434 [ibmveth] [c00000000ffefe40] [c00000000032da8c] .net_rx_action+0xdc/0x248 [c00000000ffefef0] [c000000000068b4c] .__do_softirq+0xa8/0x164 [c00000000ffeff90] [c00000000002789c] .call_do_softirq+0x14/0x24 [c00000001398f6f0] [c00000000000c04c] .do_softirq+0x68/0xac [c00000001398f780] [c000000000068ca0] .irq_exit+0x54/0x6c [c00000001398f800] [c00000000000c8e4] .do_IRQ+0x170/0x1ac [c00000001398f890] [c000000000004790] hardware_interrupt_entry+0x18/0x1c Exception: 501 at .plpar_hcall_norets+0x24/0x94 LR = .veth_pool_store+0x15c/0x298 [ibmveth] [c00000001398fb80] [d000000000250b2c] .veth_pool_store+0x5c/0x298 [ibmveth] (unreliable) [c00000001398fc30] [c000000000145530] .sysfs_write_file+0x140/0x1d8 [c00000001398fcf0] [c0000000000de89c] .vfs_write+0x120/0x208 [c00000001398fd90] [c0000000000df2c8] .sys_write+0x4c/0x8c [c00000001398fe30] [c0000000000086ac] syscall_exit+0x0/0x40 Instruction dump: fba1ffe8 fbe1fff8 789d0022 f8010010 f821ff71 789c0020 1d3d00a8 7b8a1f24 38000000 7c7f1b78 7d291a14 e9690128 <7c0a592a> e8030000 e9690120 80a90100 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-08-03 10:55:19 +07:00
for (i = 0; i < IbmVethNumBufferPools; i++) {
if (pool == &adapter->rx_buff_pool[i])
continue;
if (!adapter->rx_buff_pool[i].active)
continue;
ibmveth: Fix rx pool deactivate oops This fixes the following oops which can occur when trying to deallocate receive buffer pools using sysfs with the ibmveth driver. NIP: d00000000024f954 LR: d00000000024fa58 CTR: c0000000000d7478 REGS: c00000000ffef9f0 TRAP: 0300 Not tainted (2.6.22-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242442 XER: 00000010 DAR: 00000000000007f0, DSISR: 0000000042000000 TASK = c000000002f91360[2967] 'bash' THREAD: c00000001398c000 CPU: 2 GPR00: 0000000000000000 c00000000ffefc70 d000000000262d30 c00000001c4087a0 GPR04: 00000003000000fe 0000000000000000 000000000000000f c000000000579d80 GPR08: 0000000000365688 c00000001c408998 00000000000007f0 0000000000000000 GPR12: d000000000251e88 c000000000579d80 00000000200957ec 0000000000000000 GPR16: 00000000100b8808 00000000100feb30 0000000000000000 0000000010084828 GPR20: 0000000000000000 000000001014d4d0 0000000000000010 c00000000ffefeb0 GPR24: c00000001c408000 0000000000000000 c00000001c408000 00000000ffffb054 GPR28: 00000000000000fe 0000000000000003 d000000000262700 c00000001c4087a0 NIP [d00000000024f954] .ibmveth_remove_buffer_from_pool+0x38/0x108 [ibmveth] LR [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] Call Trace: [c00000000ffefc70] [c0000000000280a8] .dma_iommu_unmap_single+0x14/0x28 (unreliable) [c00000000ffefd00] [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] [c00000000ffefd80] [d000000000250e40] .ibmveth_poll+0xd8/0x434 [ibmveth] [c00000000ffefe40] [c00000000032da8c] .net_rx_action+0xdc/0x248 [c00000000ffefef0] [c000000000068b4c] .__do_softirq+0xa8/0x164 [c00000000ffeff90] [c00000000002789c] .call_do_softirq+0x14/0x24 [c00000001398f6f0] [c00000000000c04c] .do_softirq+0x68/0xac [c00000001398f780] [c000000000068ca0] .irq_exit+0x54/0x6c [c00000001398f800] [c00000000000c8e4] .do_IRQ+0x170/0x1ac [c00000001398f890] [c000000000004790] hardware_interrupt_entry+0x18/0x1c Exception: 501 at .plpar_hcall_norets+0x24/0x94 LR = .veth_pool_store+0x15c/0x298 [ibmveth] [c00000001398fb80] [d000000000250b2c] .veth_pool_store+0x5c/0x298 [ibmveth] (unreliable) [c00000001398fc30] [c000000000145530] .sysfs_write_file+0x140/0x1d8 [c00000001398fcf0] [c0000000000de89c] .vfs_write+0x120/0x208 [c00000001398fd90] [c0000000000df2c8] .sys_write+0x4c/0x8c [c00000001398fe30] [c0000000000086ac] syscall_exit+0x0/0x40 Instruction dump: fba1ffe8 fbe1fff8 789d0022 f8010010 f821ff71 789c0020 1d3d00a8 7b8a1f24 38000000 7c7f1b78 7d291a14 e9690128 <7c0a592a> e8030000 e9690120 80a90100 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-08-03 10:55:19 +07:00
if (mtu <= adapter->rx_buff_pool[i].buff_size)
break;
}
ibmveth: Fix rx pool deactivate oops This fixes the following oops which can occur when trying to deallocate receive buffer pools using sysfs with the ibmveth driver. NIP: d00000000024f954 LR: d00000000024fa58 CTR: c0000000000d7478 REGS: c00000000ffef9f0 TRAP: 0300 Not tainted (2.6.22-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242442 XER: 00000010 DAR: 00000000000007f0, DSISR: 0000000042000000 TASK = c000000002f91360[2967] 'bash' THREAD: c00000001398c000 CPU: 2 GPR00: 0000000000000000 c00000000ffefc70 d000000000262d30 c00000001c4087a0 GPR04: 00000003000000fe 0000000000000000 000000000000000f c000000000579d80 GPR08: 0000000000365688 c00000001c408998 00000000000007f0 0000000000000000 GPR12: d000000000251e88 c000000000579d80 00000000200957ec 0000000000000000 GPR16: 00000000100b8808 00000000100feb30 0000000000000000 0000000010084828 GPR20: 0000000000000000 000000001014d4d0 0000000000000010 c00000000ffefeb0 GPR24: c00000001c408000 0000000000000000 c00000001c408000 00000000ffffb054 GPR28: 00000000000000fe 0000000000000003 d000000000262700 c00000001c4087a0 NIP [d00000000024f954] .ibmveth_remove_buffer_from_pool+0x38/0x108 [ibmveth] LR [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] Call Trace: [c00000000ffefc70] [c0000000000280a8] .dma_iommu_unmap_single+0x14/0x28 (unreliable) [c00000000ffefd00] [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] [c00000000ffefd80] [d000000000250e40] .ibmveth_poll+0xd8/0x434 [ibmveth] [c00000000ffefe40] [c00000000032da8c] .net_rx_action+0xdc/0x248 [c00000000ffefef0] [c000000000068b4c] .__do_softirq+0xa8/0x164 [c00000000ffeff90] [c00000000002789c] .call_do_softirq+0x14/0x24 [c00000001398f6f0] [c00000000000c04c] .do_softirq+0x68/0xac [c00000001398f780] [c000000000068ca0] .irq_exit+0x54/0x6c [c00000001398f800] [c00000000000c8e4] .do_IRQ+0x170/0x1ac [c00000001398f890] [c000000000004790] hardware_interrupt_entry+0x18/0x1c Exception: 501 at .plpar_hcall_norets+0x24/0x94 LR = .veth_pool_store+0x15c/0x298 [ibmveth] [c00000001398fb80] [d000000000250b2c] .veth_pool_store+0x5c/0x298 [ibmveth] (unreliable) [c00000001398fc30] [c000000000145530] .sysfs_write_file+0x140/0x1d8 [c00000001398fcf0] [c0000000000de89c] .vfs_write+0x120/0x208 [c00000001398fd90] [c0000000000df2c8] .sys_write+0x4c/0x8c [c00000001398fe30] [c0000000000086ac] syscall_exit+0x0/0x40 Instruction dump: fba1ffe8 fbe1fff8 789d0022 f8010010 f821ff71 789c0020 1d3d00a8 7b8a1f24 38000000 7c7f1b78 7d291a14 e9690128 <7c0a592a> e8030000 e9690120 80a90100 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-08-03 10:55:19 +07:00
if (i == IbmVethNumBufferPools) {
ibmveth_error_printk("no active pool >= MTU\n");
return -EPERM;
}
ibmveth: Fix rx pool deactivate oops This fixes the following oops which can occur when trying to deallocate receive buffer pools using sysfs with the ibmveth driver. NIP: d00000000024f954 LR: d00000000024fa58 CTR: c0000000000d7478 REGS: c00000000ffef9f0 TRAP: 0300 Not tainted (2.6.22-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242442 XER: 00000010 DAR: 00000000000007f0, DSISR: 0000000042000000 TASK = c000000002f91360[2967] 'bash' THREAD: c00000001398c000 CPU: 2 GPR00: 0000000000000000 c00000000ffefc70 d000000000262d30 c00000001c4087a0 GPR04: 00000003000000fe 0000000000000000 000000000000000f c000000000579d80 GPR08: 0000000000365688 c00000001c408998 00000000000007f0 0000000000000000 GPR12: d000000000251e88 c000000000579d80 00000000200957ec 0000000000000000 GPR16: 00000000100b8808 00000000100feb30 0000000000000000 0000000010084828 GPR20: 0000000000000000 000000001014d4d0 0000000000000010 c00000000ffefeb0 GPR24: c00000001c408000 0000000000000000 c00000001c408000 00000000ffffb054 GPR28: 00000000000000fe 0000000000000003 d000000000262700 c00000001c4087a0 NIP [d00000000024f954] .ibmveth_remove_buffer_from_pool+0x38/0x108 [ibmveth] LR [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] Call Trace: [c00000000ffefc70] [c0000000000280a8] .dma_iommu_unmap_single+0x14/0x28 (unreliable) [c00000000ffefd00] [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] [c00000000ffefd80] [d000000000250e40] .ibmveth_poll+0xd8/0x434 [ibmveth] [c00000000ffefe40] [c00000000032da8c] .net_rx_action+0xdc/0x248 [c00000000ffefef0] [c000000000068b4c] .__do_softirq+0xa8/0x164 [c00000000ffeff90] [c00000000002789c] .call_do_softirq+0x14/0x24 [c00000001398f6f0] [c00000000000c04c] .do_softirq+0x68/0xac [c00000001398f780] [c000000000068ca0] .irq_exit+0x54/0x6c [c00000001398f800] [c00000000000c8e4] .do_IRQ+0x170/0x1ac [c00000001398f890] [c000000000004790] hardware_interrupt_entry+0x18/0x1c Exception: 501 at .plpar_hcall_norets+0x24/0x94 LR = .veth_pool_store+0x15c/0x298 [ibmveth] [c00000001398fb80] [d000000000250b2c] .veth_pool_store+0x5c/0x298 [ibmveth] (unreliable) [c00000001398fc30] [c000000000145530] .sysfs_write_file+0x140/0x1d8 [c00000001398fcf0] [c0000000000de89c] .vfs_write+0x120/0x208 [c00000001398fd90] [c0000000000df2c8] .sys_write+0x4c/0x8c [c00000001398fe30] [c0000000000086ac] syscall_exit+0x0/0x40 Instruction dump: fba1ffe8 fbe1fff8 789d0022 f8010010 f821ff71 789c0020 1d3d00a8 7b8a1f24 38000000 7c7f1b78 7d291a14 e9690128 <7c0a592a> e8030000 e9690120 80a90100 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-08-03 10:55:19 +07:00
if (netif_running(netdev)) {
adapter->pool_config = 1;
ibmveth_close(netdev);
pool->active = 0;
ibmveth: Fix rx pool deactivate oops This fixes the following oops which can occur when trying to deallocate receive buffer pools using sysfs with the ibmveth driver. NIP: d00000000024f954 LR: d00000000024fa58 CTR: c0000000000d7478 REGS: c00000000ffef9f0 TRAP: 0300 Not tainted (2.6.22-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242442 XER: 00000010 DAR: 00000000000007f0, DSISR: 0000000042000000 TASK = c000000002f91360[2967] 'bash' THREAD: c00000001398c000 CPU: 2 GPR00: 0000000000000000 c00000000ffefc70 d000000000262d30 c00000001c4087a0 GPR04: 00000003000000fe 0000000000000000 000000000000000f c000000000579d80 GPR08: 0000000000365688 c00000001c408998 00000000000007f0 0000000000000000 GPR12: d000000000251e88 c000000000579d80 00000000200957ec 0000000000000000 GPR16: 00000000100b8808 00000000100feb30 0000000000000000 0000000010084828 GPR20: 0000000000000000 000000001014d4d0 0000000000000010 c00000000ffefeb0 GPR24: c00000001c408000 0000000000000000 c00000001c408000 00000000ffffb054 GPR28: 00000000000000fe 0000000000000003 d000000000262700 c00000001c4087a0 NIP [d00000000024f954] .ibmveth_remove_buffer_from_pool+0x38/0x108 [ibmveth] LR [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] Call Trace: [c00000000ffefc70] [c0000000000280a8] .dma_iommu_unmap_single+0x14/0x28 (unreliable) [c00000000ffefd00] [d00000000024fa58] .ibmveth_rxq_harvest_buffer+0x34/0x78 [ibmveth] [c00000000ffefd80] [d000000000250e40] .ibmveth_poll+0xd8/0x434 [ibmveth] [c00000000ffefe40] [c00000000032da8c] .net_rx_action+0xdc/0x248 [c00000000ffefef0] [c000000000068b4c] .__do_softirq+0xa8/0x164 [c00000000ffeff90] [c00000000002789c] .call_do_softirq+0x14/0x24 [c00000001398f6f0] [c00000000000c04c] .do_softirq+0x68/0xac [c00000001398f780] [c000000000068ca0] .irq_exit+0x54/0x6c [c00000001398f800] [c00000000000c8e4] .do_IRQ+0x170/0x1ac [c00000001398f890] [c000000000004790] hardware_interrupt_entry+0x18/0x1c Exception: 501 at .plpar_hcall_norets+0x24/0x94 LR = .veth_pool_store+0x15c/0x298 [ibmveth] [c00000001398fb80] [d000000000250b2c] .veth_pool_store+0x5c/0x298 [ibmveth] (unreliable) [c00000001398fc30] [c000000000145530] .sysfs_write_file+0x140/0x1d8 [c00000001398fcf0] [c0000000000de89c] .vfs_write+0x120/0x208 [c00000001398fd90] [c0000000000df2c8] .sys_write+0x4c/0x8c [c00000001398fe30] [c0000000000086ac] syscall_exit+0x0/0x40 Instruction dump: fba1ffe8 fbe1fff8 789d0022 f8010010 f821ff71 789c0020 1d3d00a8 7b8a1f24 38000000 7c7f1b78 7d291a14 e9690128 <7c0a592a> e8030000 e9690120 80a90100 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-08-03 10:55:19 +07:00
adapter->pool_config = 0;
if ((rc = ibmveth_open(netdev)))
return rc;
}
pool->active = 0;
}
} else if (attr == &veth_num_attr) {
if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT)
return -EINVAL;
else {
ibmveth: Fix h_free_logical_lan error on pool resize When attempting to activate additional rx buffer pools on an ibmveth interface that was not yet up, the error below was seen. The patch fixes this by only closing and opening the interface to activate the resize if the interface is already opened. (drivers/net/ibmveth.c:597 ua:30000004) ERROR: h_free_logical_lan failed with fffffffffffffffc, continuing with close Unable to handle kernel paging request for data at address 0x00000ff8 Faulting instruction address: 0xd0000000002540e0 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=128 NUMA PSERIES LPAR Modules linked in: ip6t_REJECT xt_tcpudp ipt_REJECT xt_state iptable_mangle ipta ble_nat ip_nat iptable_filter ip6table_mangle ip_conntrack nfnetlink ip_tables i p6table_filter ip6_tables x_tables ipv6 apparmor aamatch_pcre loop dm_mod ibmvet h sg ibmvscsic sd_mod scsi_mod NIP: D0000000002540E0 LR: D0000000002540D4 CTR: 80000000001AF404 REGS: c00000001cd27870 TRAP: 0300 Not tainted (2.6.16.46-0.4-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242422 XER: 00000007 DAR: 0000000000000FF8, DSISR: 0000000040000000 TASK = c00000001ca7b4e0[1636] 'sh' THREAD: c00000001cd24000 CPU: 0 GPR00: D0000000002540D4 C00000001CD27AF0 D000000000265650 C00000001C936500 GPR04: 8000000000009032 FFFFFFFFFFFFFFFF 0000000000000007 000000000002C2EF GPR08: FFFFFFFFFFFFFFFF 0000000000000000 C000000000652A10 C000000000652AE0 GPR12: 0000000000004000 C0000000004A3300 00000000100A0000 0000000000000000 GPR16: 00000000100B8808 00000000100C0F60 0000000000000000 0000000010084878 GPR20: 0000000000000000 00000000100C0CB0 00000000100AF498 0000000000000002 GPR24: 00000000100BA488 C00000001C936760 D000000000258DD0 C00000001C936000 GPR28: 0000000000000000 C00000001C936500 D000000000265180 C00000001C936000 NIP [D0000000002540E0] .ibmveth_close+0xc8/0xf4 [ibmveth] LR [D0000000002540D4] .ibmveth_close+0xbc/0xf4 [ibmveth] Call Trace: [C00000001CD27AF0] [D0000000002540D4] .ibmveth_close+0xbc/0xf4 [ibmveth] (unreliable) [C00000001CD27B80] [D0000000002545FC] .veth_pool_store+0xd0/0x260 [ibmveth] [C00000001CD27C40] [C00000000012E0E8] .sysfs_write_file+0x118/0x198 [C00000001CD27CF0] [C0000000000CDAF0] .vfs_write+0x130/0x218 [C00000001CD27D90] [C0000000000CE52C] .sys_write+0x4c/0x8c [C00000001CD27E30] [C00000000000871C] syscall_exit+0x0/0x40 Instruction dump: 419affd8 2fa30000 419e0020 e93d0000 e89e8040 38a00255 e87e81b0 80c90018 48001531 e8410028 e93d00e0 7fa3eb78 <e8090ff8> f81d0430 4bfffdc9 38210090 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-06-09 02:05:16 +07:00
if (netif_running(netdev)) {
adapter->pool_config = 1;
ibmveth_close(netdev);
adapter->pool_config = 0;
pool->size = value;
if ((rc = ibmveth_open(netdev)))
return rc;
} else
pool->size = value;
}
} else if (attr == &veth_size_attr) {
if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE)
return -EINVAL;
else {
ibmveth: Fix h_free_logical_lan error on pool resize When attempting to activate additional rx buffer pools on an ibmveth interface that was not yet up, the error below was seen. The patch fixes this by only closing and opening the interface to activate the resize if the interface is already opened. (drivers/net/ibmveth.c:597 ua:30000004) ERROR: h_free_logical_lan failed with fffffffffffffffc, continuing with close Unable to handle kernel paging request for data at address 0x00000ff8 Faulting instruction address: 0xd0000000002540e0 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=128 NUMA PSERIES LPAR Modules linked in: ip6t_REJECT xt_tcpudp ipt_REJECT xt_state iptable_mangle ipta ble_nat ip_nat iptable_filter ip6table_mangle ip_conntrack nfnetlink ip_tables i p6table_filter ip6_tables x_tables ipv6 apparmor aamatch_pcre loop dm_mod ibmvet h sg ibmvscsic sd_mod scsi_mod NIP: D0000000002540E0 LR: D0000000002540D4 CTR: 80000000001AF404 REGS: c00000001cd27870 TRAP: 0300 Not tainted (2.6.16.46-0.4-ppc64) MSR: 8000000000009032 <EE,ME,IR,DR> CR: 24242422 XER: 00000007 DAR: 0000000000000FF8, DSISR: 0000000040000000 TASK = c00000001ca7b4e0[1636] 'sh' THREAD: c00000001cd24000 CPU: 0 GPR00: D0000000002540D4 C00000001CD27AF0 D000000000265650 C00000001C936500 GPR04: 8000000000009032 FFFFFFFFFFFFFFFF 0000000000000007 000000000002C2EF GPR08: FFFFFFFFFFFFFFFF 0000000000000000 C000000000652A10 C000000000652AE0 GPR12: 0000000000004000 C0000000004A3300 00000000100A0000 0000000000000000 GPR16: 00000000100B8808 00000000100C0F60 0000000000000000 0000000010084878 GPR20: 0000000000000000 00000000100C0CB0 00000000100AF498 0000000000000002 GPR24: 00000000100BA488 C00000001C936760 D000000000258DD0 C00000001C936000 GPR28: 0000000000000000 C00000001C936500 D000000000265180 C00000001C936000 NIP [D0000000002540E0] .ibmveth_close+0xc8/0xf4 [ibmveth] LR [D0000000002540D4] .ibmveth_close+0xbc/0xf4 [ibmveth] Call Trace: [C00000001CD27AF0] [D0000000002540D4] .ibmveth_close+0xbc/0xf4 [ibmveth] (unreliable) [C00000001CD27B80] [D0000000002545FC] .veth_pool_store+0xd0/0x260 [ibmveth] [C00000001CD27C40] [C00000000012E0E8] .sysfs_write_file+0x118/0x198 [C00000001CD27CF0] [C0000000000CDAF0] .vfs_write+0x130/0x218 [C00000001CD27D90] [C0000000000CE52C] .sys_write+0x4c/0x8c [C00000001CD27E30] [C00000000000871C] syscall_exit+0x0/0x40 Instruction dump: 419affd8 2fa30000 419e0020 e93d0000 e89e8040 38a00255 e87e81b0 80c90018 48001531 e8410028 e93d00e0 7fa3eb78 <e8090ff8> f81d0430 4bfffdc9 38210090 Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-06-09 02:05:16 +07:00
if (netif_running(netdev)) {
adapter->pool_config = 1;
ibmveth_close(netdev);
adapter->pool_config = 0;
pool->buff_size = value;
if ((rc = ibmveth_open(netdev)))
return rc;
} else
pool->buff_size = value;
}
}
/* kick the interrupt handler to allocate/deallocate pools */
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 20:55:46 +07:00
ibmveth_interrupt(netdev->irq, netdev);
return count;
}
#define ATTR(_name, _mode) \
struct attribute veth_##_name##_attr = { \
.name = __stringify(_name), .mode = _mode, \
};
static ATTR(active, 0644);
static ATTR(num, 0644);
static ATTR(size, 0644);
static struct attribute * veth_pool_attrs[] = {
&veth_active_attr,
&veth_num_attr,
&veth_size_attr,
NULL,
};
static const struct sysfs_ops veth_pool_ops = {
.show = veth_pool_show,
.store = veth_pool_store,
};
static struct kobj_type ktype_veth_pool = {
.release = NULL,
.sysfs_ops = &veth_pool_ops,
.default_attrs = veth_pool_attrs,
};
static struct vio_device_id ibmveth_device_table[] __devinitdata= {
{ "network", "IBM,l-lan"},
{ "", "" }
};
MODULE_DEVICE_TABLE(vio, ibmveth_device_table);
static struct vio_driver ibmveth_driver = {
.id_table = ibmveth_device_table,
.probe = ibmveth_probe,
.remove = ibmveth_remove,
.get_desired_dma = ibmveth_get_desired_dma,
.driver = {
.name = ibmveth_driver_name,
.owner = THIS_MODULE,
}
};
static int __init ibmveth_module_init(void)
{
ibmveth_printk("%s: %s %s\n", ibmveth_driver_name, ibmveth_driver_string, ibmveth_driver_version);
ibmveth_proc_register_driver();
return vio_register_driver(&ibmveth_driver);
}
static void __exit ibmveth_module_exit(void)
{
vio_unregister_driver(&ibmveth_driver);
ibmveth_proc_unregister_driver();
}
module_init(ibmveth_module_init);
module_exit(ibmveth_module_exit);