linux/arch/powerpc/platforms/pseries/setup.c
Gavin Shan eb740b5f3e powerpc/eeh: Introduce EEH device
Original EEH implementation depends on struct pci_dn heavily. However,
EEH shouldn't depend on that actually because EEH needn't share much
information with other PCI components. That's to say, EEH should have
worked independently.

The patch introduces struct eeh_dev so that EEH core components needn't
be working based on struct pci_dn in future. Also, struct pci_dn, struct
eeh_dev instances are created in dynamic fasion and the binding with EEH
device, OF node, PCI device is implemented as well.

The EEH devices are created after PHBs are detected and initialized, but
PCI emunation hasn't started yet. Apart from that, PHB might be created
dynamically through DLPAR component and the EEH devices should be creatd
as well. Another case might be OF node is created dynamically by DR
(Dynamic Reconfiguration), which has been defined by PAPR. For those OF
nodes created by DR, EEH devices should be also created accordingly. The
binding between EEH device and OF node is done while the EEH device is
initially created.

The binding between EEH device and PCI device should be done after PCI
emunation is done. Besides, PCI hotplug also needs the binding so that
the EEH devices could be traced from the newly coming PCI buses or PCI
devices.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-03-09 11:39:29 +11:00

658 lines
17 KiB
C

/*
* 64-bit pSeries and RS/6000 setup code.
*
* Copyright (C) 1995 Linus Torvalds
* Adapted from 'alpha' version by Gary Thomas
* Modified by Cort Dougan (cort@cs.nmt.edu)
* Modified by PPC64 Team, IBM Corp
*
* 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.
*/
/*
* bootup setup stuff..
*/
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/user.h>
#include <linux/tty.h>
#include <linux/major.h>
#include <linux/interrupt.h>
#include <linux/reboot.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/console.h>
#include <linux/pci.h>
#include <linux/utsname.h>
#include <linux/adb.h>
#include <linux/export.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
#include <linux/root_dev.h>
#include <linux/cpuidle.h>
#include <asm/mmu.h>
#include <asm/processor.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/prom.h>
#include <asm/rtas.h>
#include <asm/pci-bridge.h>
#include <asm/iommu.h>
#include <asm/dma.h>
#include <asm/machdep.h>
#include <asm/irq.h>
#include <asm/time.h>
#include <asm/nvram.h>
#include <asm/pmc.h>
#include <asm/mpic.h>
#include <asm/xics.h>
#include <asm/ppc-pci.h>
#include <asm/i8259.h>
#include <asm/udbg.h>
#include <asm/smp.h>
#include <asm/firmware.h>
#include <asm/eeh.h>
#include <asm/pSeries_reconfig.h>
#include "plpar_wrappers.h"
#include "pseries.h"
int CMO_PrPSP = -1;
int CMO_SecPSP = -1;
unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT);
EXPORT_SYMBOL(CMO_PageSize);
int fwnmi_active; /* TRUE if an FWNMI handler is present */
static struct device_node *pSeries_mpic_node;
static void pSeries_show_cpuinfo(struct seq_file *m)
{
struct device_node *root;
const char *model = "";
root = of_find_node_by_path("/");
if (root)
model = of_get_property(root, "model", NULL);
seq_printf(m, "machine\t\t: CHRP %s\n", model);
of_node_put(root);
}
/* Initialize firmware assisted non-maskable interrupts if
* the firmware supports this feature.
*/
static void __init fwnmi_init(void)
{
unsigned long system_reset_addr, machine_check_addr;
int ibm_nmi_register = rtas_token("ibm,nmi-register");
if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE)
return;
/* If the kernel's not linked at zero we point the firmware at low
* addresses anyway, and use a trampoline to get to the real code. */
system_reset_addr = __pa(system_reset_fwnmi) - PHYSICAL_START;
machine_check_addr = __pa(machine_check_fwnmi) - PHYSICAL_START;
if (0 == rtas_call(ibm_nmi_register, 2, 1, NULL, system_reset_addr,
machine_check_addr))
fwnmi_active = 1;
}
static void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
unsigned int cascade_irq = i8259_irq();
if (cascade_irq != NO_IRQ)
generic_handle_irq(cascade_irq);
chip->irq_eoi(&desc->irq_data);
}
static void __init pseries_setup_i8259_cascade(void)
{
struct device_node *np, *old, *found = NULL;
unsigned int cascade;
const u32 *addrp;
unsigned long intack = 0;
int naddr;
for_each_node_by_type(np, "interrupt-controller") {
if (of_device_is_compatible(np, "chrp,iic")) {
found = np;
break;
}
}
if (found == NULL) {
printk(KERN_DEBUG "pic: no ISA interrupt controller\n");
return;
}
cascade = irq_of_parse_and_map(found, 0);
if (cascade == NO_IRQ) {
printk(KERN_ERR "pic: failed to map cascade interrupt");
return;
}
pr_debug("pic: cascade mapped to irq %d\n", cascade);
for (old = of_node_get(found); old != NULL ; old = np) {
np = of_get_parent(old);
of_node_put(old);
if (np == NULL)
break;
if (strcmp(np->name, "pci") != 0)
continue;
addrp = of_get_property(np, "8259-interrupt-acknowledge", NULL);
if (addrp == NULL)
continue;
naddr = of_n_addr_cells(np);
intack = addrp[naddr-1];
if (naddr > 1)
intack |= ((unsigned long)addrp[naddr-2]) << 32;
}
if (intack)
printk(KERN_DEBUG "pic: PCI 8259 intack at 0x%016lx\n", intack);
i8259_init(found, intack);
of_node_put(found);
irq_set_chained_handler(cascade, pseries_8259_cascade);
}
static void __init pseries_mpic_init_IRQ(void)
{
struct device_node *np;
const unsigned int *opprop;
unsigned long openpic_addr = 0;
int naddr, n, i, opplen;
struct mpic *mpic;
np = of_find_node_by_path("/");
naddr = of_n_addr_cells(np);
opprop = of_get_property(np, "platform-open-pic", &opplen);
if (opprop != 0) {
openpic_addr = of_read_number(opprop, naddr);
printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
}
of_node_put(np);
BUG_ON(openpic_addr == 0);
/* Setup the openpic driver */
mpic = mpic_alloc(pSeries_mpic_node, openpic_addr,
MPIC_NO_RESET, 16, 0, " MPIC ");
BUG_ON(mpic == NULL);
/* Add ISUs */
opplen /= sizeof(u32);
for (n = 0, i = naddr; i < opplen; i += naddr, n++) {
unsigned long isuaddr = of_read_number(opprop + i, naddr);
mpic_assign_isu(mpic, n, isuaddr);
}
/* Setup top-level get_irq */
ppc_md.get_irq = mpic_get_irq;
/* All ISUs are setup, complete initialization */
mpic_init(mpic);
/* Look for cascade */
pseries_setup_i8259_cascade();
}
static void __init pseries_xics_init_IRQ(void)
{
xics_init();
pseries_setup_i8259_cascade();
}
static void pseries_lpar_enable_pmcs(void)
{
unsigned long set, reset;
set = 1UL << 63;
reset = 0;
plpar_hcall_norets(H_PERFMON, set, reset);
}
static void __init pseries_discover_pic(void)
{
struct device_node *np;
const char *typep;
for (np = NULL; (np = of_find_node_by_name(np,
"interrupt-controller"));) {
typep = of_get_property(np, "compatible", NULL);
if (strstr(typep, "open-pic")) {
pSeries_mpic_node = of_node_get(np);
ppc_md.init_IRQ = pseries_mpic_init_IRQ;
setup_kexec_cpu_down_mpic();
smp_init_pseries_mpic();
return;
} else if (strstr(typep, "ppc-xicp")) {
ppc_md.init_IRQ = pseries_xics_init_IRQ;
setup_kexec_cpu_down_xics();
smp_init_pseries_xics();
return;
}
}
printk(KERN_ERR "pSeries_discover_pic: failed to recognize"
" interrupt-controller\n");
}
static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
{
struct device_node *np = node;
struct pci_dn *pci = NULL;
int err = NOTIFY_OK;
switch (action) {
case PSERIES_RECONFIG_ADD:
pci = np->parent->data;
if (pci) {
update_dn_pci_info(np, pci->phb);
/* Create EEH device for the OF node */
eeh_dev_init(np, pci->phb);
}
break;
default:
err = NOTIFY_DONE;
break;
}
return err;
}
static struct notifier_block pci_dn_reconfig_nb = {
.notifier_call = pci_dn_reconfig_notifier,
};
struct kmem_cache *dtl_cache;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
/*
* Allocate space for the dispatch trace log for all possible cpus
* and register the buffers with the hypervisor. This is used for
* computing time stolen by the hypervisor.
*/
static int alloc_dispatch_logs(void)
{
int cpu, ret;
struct paca_struct *pp;
struct dtl_entry *dtl;
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return 0;
if (!dtl_cache)
return 0;
for_each_possible_cpu(cpu) {
pp = &paca[cpu];
dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
if (!dtl) {
pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
cpu);
pr_warn("Stolen time statistics will be unreliable\n");
break;
}
pp->dtl_ridx = 0;
pp->dispatch_log = dtl;
pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
pp->dtl_curr = dtl;
}
/* Register the DTL for the current (boot) cpu */
dtl = get_paca()->dispatch_log;
get_paca()->dtl_ridx = 0;
get_paca()->dtl_curr = dtl;
get_paca()->lppaca_ptr->dtl_idx = 0;
/* hypervisor reads buffer length from this field */
dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
if (ret)
pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
"with %d\n", smp_processor_id(),
hard_smp_processor_id(), ret);
get_paca()->lppaca_ptr->dtl_enable_mask = 2;
return 0;
}
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
static inline int alloc_dispatch_logs(void)
{
return 0;
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
static int alloc_dispatch_log_kmem_cache(void)
{
dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
DISPATCH_LOG_BYTES, 0, NULL);
if (!dtl_cache) {
pr_warn("Failed to create dispatch trace log buffer cache\n");
pr_warn("Stolen time statistics will be unreliable\n");
return 0;
}
return alloc_dispatch_logs();
}
early_initcall(alloc_dispatch_log_kmem_cache);
static void pSeries_idle(void)
{
/* This would call on the cpuidle framework, and the back-end pseries
* driver to go to idle states
*/
if (cpuidle_idle_call()) {
/* On error, execute default handler
* to go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
}
}
static void __init pSeries_setup_arch(void)
{
panic_timeout = 10;
/* Discover PIC type and setup ppc_md accordingly */
pseries_discover_pic();
/* openpic global configuration register (64-bit format). */
/* openpic Interrupt Source Unit pointer (64-bit format). */
/* python0 facility area (mmio) (64-bit format) REAL address. */
/* init to some ~sane value until calibrate_delay() runs */
loops_per_jiffy = 50000000;
fwnmi_init();
/* Find and initialize PCI host bridges */
init_pci_config_tokens();
eeh_pseries_init();
find_and_init_phbs();
pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb);
eeh_init();
pSeries_nvram_init();
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
vpa_init(boot_cpuid);
ppc_md.power_save = pSeries_idle;
}
if (firmware_has_feature(FW_FEATURE_LPAR))
ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
else
ppc_md.enable_pmcs = power4_enable_pmcs;
}
static int __init pSeries_init_panel(void)
{
/* Manually leave the kernel version on the panel. */
ppc_md.progress("Linux ppc64\n", 0);
ppc_md.progress(init_utsname()->version, 0);
return 0;
}
machine_arch_initcall(pseries, pSeries_init_panel);
static int pseries_set_dabr(unsigned long dabr)
{
return plpar_hcall_norets(H_SET_DABR, dabr);
}
static int pseries_set_xdabr(unsigned long dabr)
{
/* We want to catch accesses from kernel and userspace */
return plpar_hcall_norets(H_SET_XDABR, dabr,
H_DABRX_KERNEL | H_DABRX_USER);
}
#define CMO_CHARACTERISTICS_TOKEN 44
#define CMO_MAXLENGTH 1026
void pSeries_coalesce_init(void)
{
struct hvcall_mpp_x_data mpp_x_data;
if (firmware_has_feature(FW_FEATURE_CMO) && !h_get_mpp_x(&mpp_x_data))
powerpc_firmware_features |= FW_FEATURE_XCMO;
else
powerpc_firmware_features &= ~FW_FEATURE_XCMO;
}
/**
* fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions,
* handle that here. (Stolen from parse_system_parameter_string)
*/
void pSeries_cmo_feature_init(void)
{
char *ptr, *key, *value, *end;
int call_status;
int page_order = IOMMU_PAGE_SHIFT;
pr_debug(" -> fw_cmo_feature_init()\n");
spin_lock(&rtas_data_buf_lock);
memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
NULL,
CMO_CHARACTERISTICS_TOKEN,
__pa(rtas_data_buf),
RTAS_DATA_BUF_SIZE);
if (call_status != 0) {
spin_unlock(&rtas_data_buf_lock);
pr_debug("CMO not available\n");
pr_debug(" <- fw_cmo_feature_init()\n");
return;
}
end = rtas_data_buf + CMO_MAXLENGTH - 2;
ptr = rtas_data_buf + 2; /* step over strlen value */
key = value = ptr;
while (*ptr && (ptr <= end)) {
/* Separate the key and value by replacing '=' with '\0' and
* point the value at the string after the '='
*/
if (ptr[0] == '=') {
ptr[0] = '\0';
value = ptr + 1;
} else if (ptr[0] == '\0' || ptr[0] == ',') {
/* Terminate the string containing the key/value pair */
ptr[0] = '\0';
if (key == value) {
pr_debug("Malformed key/value pair\n");
/* Never found a '=', end processing */
break;
}
if (0 == strcmp(key, "CMOPageSize"))
page_order = simple_strtol(value, NULL, 10);
else if (0 == strcmp(key, "PrPSP"))
CMO_PrPSP = simple_strtol(value, NULL, 10);
else if (0 == strcmp(key, "SecPSP"))
CMO_SecPSP = simple_strtol(value, NULL, 10);
value = key = ptr + 1;
}
ptr++;
}
/* Page size is returned as the power of 2 of the page size,
* convert to the page size in bytes before returning
*/
CMO_PageSize = 1 << page_order;
pr_debug("CMO_PageSize = %lu\n", CMO_PageSize);
if (CMO_PrPSP != -1 || CMO_SecPSP != -1) {
pr_info("CMO enabled\n");
pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP,
CMO_SecPSP);
powerpc_firmware_features |= FW_FEATURE_CMO;
pSeries_coalesce_init();
} else
pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP,
CMO_SecPSP);
spin_unlock(&rtas_data_buf_lock);
pr_debug(" <- fw_cmo_feature_init()\n");
}
/*
* Early initialization. Relocation is on but do not reference unbolted pages
*/
static void __init pSeries_init_early(void)
{
pr_debug(" -> pSeries_init_early()\n");
#ifdef CONFIG_HVC_CONSOLE
if (firmware_has_feature(FW_FEATURE_LPAR))
hvc_vio_init_early();
#endif
if (firmware_has_feature(FW_FEATURE_DABR))
ppc_md.set_dabr = pseries_set_dabr;
else if (firmware_has_feature(FW_FEATURE_XDABR))
ppc_md.set_dabr = pseries_set_xdabr;
pSeries_cmo_feature_init();
iommu_init_early_pSeries();
pr_debug(" <- pSeries_init_early()\n");
}
/*
* Called very early, MMU is off, device-tree isn't unflattened
*/
static int __init pSeries_probe_hypertas(unsigned long node,
const char *uname, int depth,
void *data)
{
const char *hypertas;
unsigned long len;
if (depth != 1 ||
(strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
return 0;
hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len);
if (!hypertas)
return 1;
powerpc_firmware_features |= FW_FEATURE_LPAR;
fw_feature_init(hypertas, len);
return 1;
}
static int __init pSeries_probe(void)
{
unsigned long root = of_get_flat_dt_root();
char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
if (dtype == NULL)
return 0;
if (strcmp(dtype, "chrp"))
return 0;
/* Cell blades firmware claims to be chrp while it's not. Until this
* is fixed, we need to avoid those here.
*/
if (of_flat_dt_is_compatible(root, "IBM,CPBW-1.0") ||
of_flat_dt_is_compatible(root, "IBM,CBEA"))
return 0;
pr_debug("pSeries detected, looking for LPAR capability...\n");
/* Now try to figure out if we are running on LPAR */
of_scan_flat_dt(pSeries_probe_hypertas, NULL);
if (firmware_has_feature(FW_FEATURE_LPAR))
hpte_init_lpar();
else
hpte_init_native();
pr_debug("Machine is%s LPAR !\n",
(powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
return 1;
}
static int pSeries_pci_probe_mode(struct pci_bus *bus)
{
if (firmware_has_feature(FW_FEATURE_LPAR))
return PCI_PROBE_DEVTREE;
return PCI_PROBE_NORMAL;
}
/**
* pSeries_power_off - tell firmware about how to power off the system.
*
* This function calls either the power-off rtas token in normal cases
* or the ibm,power-off-ups token (if present & requested) in case of
* a power failure. If power-off token is used, power on will only be
* possible with power button press. If ibm,power-off-ups token is used
* it will allow auto poweron after power is restored.
*/
static void pSeries_power_off(void)
{
int rc;
int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
if (rtas_flash_term_hook)
rtas_flash_term_hook(SYS_POWER_OFF);
if (rtas_poweron_auto == 0 ||
rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) {
rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1);
printk(KERN_INFO "RTAS power-off returned %d\n", rc);
} else {
rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL);
printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc);
}
for (;;);
}
#ifndef CONFIG_PCI
void pSeries_final_fixup(void) { }
#endif
define_machine(pseries) {
.name = "pSeries",
.probe = pSeries_probe,
.setup_arch = pSeries_setup_arch,
.init_early = pSeries_init_early,
.show_cpuinfo = pSeries_show_cpuinfo,
.log_error = pSeries_log_error,
.pcibios_fixup = pSeries_final_fixup,
.pci_probe_mode = pSeries_pci_probe_mode,
.restart = rtas_restart,
.power_off = pSeries_power_off,
.halt = rtas_halt,
.panic = rtas_os_term,
.get_boot_time = rtas_get_boot_time,
.get_rtc_time = rtas_get_rtc_time,
.set_rtc_time = rtas_set_rtc_time,
.calibrate_decr = generic_calibrate_decr,
.progress = rtas_progress,
.system_reset_exception = pSeries_system_reset_exception,
.machine_check_exception = pSeries_machine_check_exception,
};