Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-02 00:51:44 +00:00
Code Issues Packages Projects Releases Wiki Activity
3603a6a37c
linux/drivers/pci/pcie/aer/aerdrv.c

346 lines
9.1 KiB
C
Raw Normal View History

PCI-Express AER implemetation: AER core and aerdriver Patch 3 implements the core part of PCI-Express AER and aerdrv port service driver. When a root port service device is probed, the aerdrv will call request_irq to register irq handler for AER error interrupt. When a device sends an PCI-Express error message to the root port, the root port will trigger an interrupt, by either MSI or IO-APIC, then kernel would run the irq handler. The handler collects root error status register and schedules a work. The work will call the core part to process the error based on its type (Correctable/non-fatal/fatal). As for Correctable errors, the patch chooses to just clear the correctable error status register of the device. As for the non-fatal error, the patch follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. As for the fatal error, the patch resets the pci-express link and follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-07-31 07:21:33 +00:00
/*
* drivers/pci/pcie/aer/aerdrv.c
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* This file implements the AER root port service driver. The driver will
* register an irq handler. When root port triggers an AER interrupt, the irq
* handler will collect root port status and schedule a work.
*
* Copyright (C) 2006 Intel Corp.
* Tom Long Nguyen (tom.l.nguyen@intel.com)
* Zhang Yanmin (yanmin.zhang@intel.com)
*
*/
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/pcieport_if.h>
#include "aerdrv.h"
/*
* Version Information
*/
#define DRIVER_VERSION "v1.0"
#define DRIVER_AUTHOR "tom.l.nguyen@intel.com"
#define DRIVER_DESC "Root Port Advanced Error Reporting Driver"
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_LICENSE("GPL");
static int __devinit aer_probe (struct pcie_device *dev,
const struct pcie_port_service_id *id );
static void aer_remove(struct pcie_device *dev);
static int aer_suspend(struct pcie_device *dev, pm_message_t state)
{return 0;}
static int aer_resume(struct pcie_device *dev) {return 0;}
static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
enum pci_channel_state error);
static void aer_error_resume(struct pci_dev *dev);
static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
/*
* PCI Express bus's AER Root service driver data structure
*/
static struct pcie_port_service_id aer_id[] = {
{
.vendor = PCI_ANY_ID,
.device = PCI_ANY_ID,
.port_type = PCIE_RC_PORT,
.service_type = PCIE_PORT_SERVICE_AER,
},
{ /* end: all zeroes */ }
};
static struct pci_error_handlers aer_error_handlers = {
.error_detected = aer_error_detected,
.resume = aer_error_resume,
};
static struct pcie_port_service_driver aerdrv = {
.name = "aer",
.id_table = &aer_id[0],
.probe = aer_probe,
.remove = aer_remove,
.suspend = aer_suspend,
.resume = aer_resume,
.err_handler = &aer_error_handlers,
.reset_link = aer_root_reset,
};
/**
* aer_irq - Root Port's ISR
* @irq: IRQ assigned to Root Port
* @context: pointer to Root Port data structure
*
* Invoked when Root Port detects AER messages.
**/
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 13:55:46 +00:00
static irqreturn_t aer_irq(int irq, void *context)
PCI-Express AER implemetation: AER core and aerdriver Patch 3 implements the core part of PCI-Express AER and aerdrv port service driver. When a root port service device is probed, the aerdrv will call request_irq to register irq handler for AER error interrupt. When a device sends an PCI-Express error message to the root port, the root port will trigger an interrupt, by either MSI or IO-APIC, then kernel would run the irq handler. The handler collects root error status register and schedules a work. The work will call the core part to process the error based on its type (Correctable/non-fatal/fatal). As for Correctable errors, the patch chooses to just clear the correctable error status register of the device. As for the non-fatal error, the patch follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. As for the fatal error, the patch resets the pci-express link and follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-07-31 07:21:33 +00:00
{
unsigned int status, id;
struct pcie_device *pdev = (struct pcie_device *)context;
struct aer_rpc *rpc = get_service_data(pdev);
int next_prod_idx;
unsigned long flags;
int pos;
pos = pci_find_aer_capability(pdev->port);
/*
* Must lock access to Root Error Status Reg, Root Error ID Reg,
* and Root error producer/consumer index
*/
spin_lock_irqsave(&rpc->e_lock, flags);
/* Read error status */
pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
if (!(status & ROOT_ERR_STATUS_MASKS)) {
spin_unlock_irqrestore(&rpc->e_lock, flags);
return IRQ_NONE;
}
/* Read error source and clear error status */
pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_COR_SRC, &id);
pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);
/* Store error source for later DPC handler */
next_prod_idx = rpc->prod_idx + 1;
if (next_prod_idx == AER_ERROR_SOURCES_MAX)
next_prod_idx = 0;
if (next_prod_idx == rpc->cons_idx) {
/*
* Error Storm Condition - possibly the same error occurred.
* Drop the error.
*/
spin_unlock_irqrestore(&rpc->e_lock, flags);
return IRQ_HANDLED;
}
rpc->e_sources[rpc->prod_idx].status = status;
rpc->e_sources[rpc->prod_idx].id = id;
rpc->prod_idx = next_prod_idx;
spin_unlock_irqrestore(&rpc->e_lock, flags);
/* Invoke DPC handler */
schedule_work(&rpc->dpc_handler);
return IRQ_HANDLED;
}
/**
* aer_alloc_rpc - allocate Root Port data structure
* @dev: pointer to the pcie_dev data structure
*
* Invoked when Root Port's AER service is loaded.
**/
static struct aer_rpc* aer_alloc_rpc(struct pcie_device *dev)
{
struct aer_rpc *rpc;
[PATCH] getting rid of all casts of k[cmz]alloc() calls Run this: #!/bin/sh for f in $(grep -Erl "\([^\)]*\) *k[cmz]alloc" *) ; do echo "De-casting $f..." perl -pi -e "s/ ?= ?\([^\)]*\) *(k[cmz]alloc) *\(/ = \1\(/" $f done And then go through and reinstate those cases where code is casting pointers to non-pointers. And then drop a few hunks which conflicted with outstanding work. Cc: Russell King <rmk@arm.linux.org.uk>, Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Greg KH <greg@kroah.com> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Paul Fulghum <paulkf@microgate.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Karsten Keil <kkeil@suse.de> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Jeff Garzik <jeff@garzik.org> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Ian Kent <raven@themaw.net> Cc: Steven French <sfrench@us.ibm.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: Jaroslav Kysela <perex@suse.cz> Cc: Takashi Iwai <tiwai@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-13 08:35:56 +00:00
if (!(rpc = kmalloc(sizeof(struct aer_rpc),
PCI-Express AER implemetation: AER core and aerdriver Patch 3 implements the core part of PCI-Express AER and aerdrv port service driver. When a root port service device is probed, the aerdrv will call request_irq to register irq handler for AER error interrupt. When a device sends an PCI-Express error message to the root port, the root port will trigger an interrupt, by either MSI or IO-APIC, then kernel would run the irq handler. The handler collects root error status register and schedules a work. The work will call the core part to process the error based on its type (Correctable/non-fatal/fatal). As for Correctable errors, the patch chooses to just clear the correctable error status register of the device. As for the non-fatal error, the patch follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. As for the fatal error, the patch resets the pci-express link and follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-07-31 07:21:33 +00:00
GFP_KERNEL)))
return NULL;
memset(rpc, 0, sizeof(struct aer_rpc));
/*
* Initialize Root lock access, e_lock, to Root Error Status Reg,
* Root Error ID Reg, and Root error producer/consumer index.
*/
rpc->e_lock = SPIN_LOCK_UNLOCKED;
rpc->rpd = dev;
WorkStruct: Pass the work_struct pointer instead of context data Pass the work_struct pointer to the work function rather than context data. The work function can use container_of() to work out the data. For the cases where the container of the work_struct may go away the moment the pending bit is cleared, it is made possible to defer the release of the structure by deferring the clearing of the pending bit. To make this work, an extra flag is introduced into the management side of the work_struct. This governs auto-release of the structure upon execution. Ordinarily, the work queue executor would release the work_struct for further scheduling or deallocation by clearing the pending bit prior to jumping to the work function. This means that, unless the driver makes some guarantee itself that the work_struct won't go away, the work function may not access anything else in the work_struct or its container lest they be deallocated.. This is a problem if the auxiliary data is taken away (as done by the last patch). However, if the pending bit is *not* cleared before jumping to the work function, then the work function *may* access the work_struct and its container with no problems. But then the work function must itself release the work_struct by calling work_release(). In most cases, automatic release is fine, so this is the default. Special initiators exist for the non-auto-release case (ending in _NAR). Signed-Off-By: David Howells <dhowells@redhat.com>
2006-11-22 14:55:48 +00:00
INIT_WORK(&rpc->dpc_handler, aer_isr);
PCI-Express AER implemetation: AER core and aerdriver Patch 3 implements the core part of PCI-Express AER and aerdrv port service driver. When a root port service device is probed, the aerdrv will call request_irq to register irq handler for AER error interrupt. When a device sends an PCI-Express error message to the root port, the root port will trigger an interrupt, by either MSI or IO-APIC, then kernel would run the irq handler. The handler collects root error status register and schedules a work. The work will call the core part to process the error based on its type (Correctable/non-fatal/fatal). As for Correctable errors, the patch chooses to just clear the correctable error status register of the device. As for the non-fatal error, the patch follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. As for the fatal error, the patch resets the pci-express link and follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-07-31 07:21:33 +00:00
rpc->prod_idx = rpc->cons_idx = 0;
mutex_init(&rpc->rpc_mutex);
init_waitqueue_head(&rpc->wait_release);
/* Use PCIE bus function to store rpc into PCIE device */
set_service_data(dev, rpc);
return rpc;
}
/**
* aer_remove - clean up resources
* @dev: pointer to the pcie_dev data structure
*
* Invoked when PCI Express bus unloads or AER probe fails.
**/
static void aer_remove(struct pcie_device *dev)
{
struct aer_rpc *rpc = get_service_data(dev);
if (rpc) {
/* If register interrupt service, it must be free. */
if (rpc->isr)
free_irq(dev->irq, dev);
wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
aer_delete_rootport(rpc);
set_service_data(dev, NULL);
}
}
/**
* aer_probe - initialize resources
* @dev: pointer to the pcie_dev data structure
* @id: pointer to the service id data structure
*
* Invoked when PCI Express bus loads AER service driver.
**/
static int __devinit aer_probe (struct pcie_device *dev,
const struct pcie_port_service_id *id )
{
int status;
struct aer_rpc *rpc;
struct device *device = &dev->device;
/* Init */
if ((status = aer_init(dev)))
return status;
/* Alloc rpc data structure */
if (!(rpc = aer_alloc_rpc(dev))) {
printk(KERN_DEBUG "%s: Alloc rpc fails on PCIE device[%s]\n",
__FUNCTION__, device->bus_id);
aer_remove(dev);
return -ENOMEM;
}
/* Request IRQ ISR */
[PATCH] Scheduled removal of SA_xxx interrupt flags fixups The obsolete SA_xxx interrupt flags have been used despite the scheduled removal. Fixup the remaining users. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Jeff Garzik <jeff@garzik.org> Cc: Wim Van Sebroeck <wim@iguana.be> Cc: Roland Dreier <rolandd@cisco.com> Cc: Alessandro Zummo <a.zummo@towertech.it> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Greg KH <greg@kroah.com> Cc: Dave Airlie <airlied@linux.ie> Cc: James Simmons <jsimmons@infradead.org> Cc: "Antonino A. Daplas" <adaplas@pol.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-14 08:33:16 +00:00
if ((status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv",
PCI-Express AER implemetation: AER core and aerdriver Patch 3 implements the core part of PCI-Express AER and aerdrv port service driver. When a root port service device is probed, the aerdrv will call request_irq to register irq handler for AER error interrupt. When a device sends an PCI-Express error message to the root port, the root port will trigger an interrupt, by either MSI or IO-APIC, then kernel would run the irq handler. The handler collects root error status register and schedules a work. The work will call the core part to process the error based on its type (Correctable/non-fatal/fatal). As for Correctable errors, the patch chooses to just clear the correctable error status register of the device. As for the non-fatal error, the patch follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. As for the fatal error, the patch resets the pci-express link and follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-07-31 07:21:33 +00:00
dev))) {
printk(KERN_DEBUG "%s: Request ISR fails on PCIE device[%s]\n",
__FUNCTION__, device->bus_id);
aer_remove(dev);
return status;
}
rpc->isr = 1;
aer_enable_rootport(rpc);
return status;
}
/**
* aer_root_reset - reset link on Root Port
* @dev: pointer to Root Port's pci_dev data structure
*
* Invoked by Port Bus driver when performing link reset at Root Port.
**/
static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
{
u16 p2p_ctrl;
u32 status;
int pos;
pos = pci_find_aer_capability(dev);
/* Disable Root's interrupt in response to error messages */
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, 0);
/* Assert Secondary Bus Reset */
pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &p2p_ctrl);
p2p_ctrl |= PCI_CB_BRIDGE_CTL_CB_RESET;
pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
/* De-assert Secondary Bus Reset */
p2p_ctrl &= ~PCI_CB_BRIDGE_CTL_CB_RESET;
pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
/*
* System software must wait for at least 100ms from the end
* of a reset of one or more device before it is permitted
* to issue Configuration Requests to those devices.
*/
msleep(200);
printk(KERN_DEBUG "Complete link reset at Root[%s]\n", dev->dev.bus_id);
/* Enable Root Port's interrupt in response to error messages */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status);
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status);
pci_write_config_dword(dev,
pos + PCI_ERR_ROOT_COMMAND,
ROOT_PORT_INTR_ON_MESG_MASK);
return PCI_ERS_RESULT_RECOVERED;
}
/**
* aer_error_detected - update severity status
* @dev: pointer to Root Port's pci_dev data structure
* @error: error severity being notified by port bus
*
* Invoked by Port Bus driver during error recovery.
**/
static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
enum pci_channel_state error)
{
/* Root Port has no impact. Always recovers. */
return PCI_ERS_RESULT_CAN_RECOVER;
}
/**
* aer_error_resume - clean up corresponding error status bits
* @dev: pointer to Root Port's pci_dev data structure
*
* Invoked by Port Bus driver during nonfatal recovery.
**/
static void aer_error_resume(struct pci_dev *dev)
{
int pos;
u32 status, mask;
u16 reg16;
/* Clean up Root device status */
pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, &reg16);
pci_write_config_word(dev, pos + PCI_EXP_DEVSTA, reg16);
/* Clean AER Root Error Status */
pos = pci_find_aer_capability(dev);
pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
if (dev->error_state == pci_channel_io_normal)
status &= ~mask; /* Clear corresponding nonfatal bits */
else
status &= mask; /* Clear corresponding fatal bits */
pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
}
/**
* aer_service_init - register AER root service driver
*
* Invoked when AER root service driver is loaded.
**/
static int __init aer_service_init(void)
{
return pcie_port_service_register(&aerdrv);
}
/**
* aer_service_exit - unregister AER root service driver
*
* Invoked when AER root service driver is unloaded.
**/
static void __exit aer_service_exit(void)
{
pcie_port_service_unregister(&aerdrv);
}
module_init(aer_service_init);
module_exit(aer_service_exit);
Reference in New Issue Copy Permalink