linux-sg2042/arch/x86/kernel/acpi/boot.c

1703 lines
40 KiB
C
Raw Normal View History

/*
* boot.c - Architecture-Specific Low-Level ACPI Boot Support
*
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
* Copyright (C) 2001 Jun Nakajima <jun.nakajima@intel.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
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
#include <linux/init.h>
#include <linux/acpi.h>
#include <linux/acpi_pmtmr.h>
#include <linux/efi.h>
#include <linux/cpumask.h>
#include <linux/module.h>
#include <linux/dmi.h>
#include <linux/irq.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/pci.h>
#include <asm/pci_x86.h>
#include <asm/pgtable.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
#include <asm/io.h>
#include <asm/mpspec.h>
#include <asm/smp.h>
static int __initdata acpi_force = 0;
u32 acpi_rsdt_forced;
int acpi_disabled;
EXPORT_SYMBOL(acpi_disabled);
#ifdef CONFIG_X86_64
# include <asm/proto.h>
# include <asm/numa_64.h>
#endif /* X86 */
#define BAD_MADT_ENTRY(entry, end) ( \
(!entry) || (unsigned long)entry + sizeof(*entry) > end || \
((struct acpi_subtable_header *)entry)->length < sizeof(*entry))
#define PREFIX "ACPI: "
int acpi_noirq; /* skip ACPI IRQ initialization */
int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */
EXPORT_SYMBOL(acpi_pci_disabled);
int acpi_lapic;
int acpi_ioapic;
int acpi_strict;
u8 acpi_sci_flags __initdata;
int acpi_sci_override_gsi __initdata;
int acpi_skip_timer_override __initdata;
int acpi_use_timer_override __initdata;
int acpi_fix_pin2_polarity __initdata;
#ifdef CONFIG_X86_LOCAL_APIC
static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
#endif
#ifndef __HAVE_ARCH_CMPXCHG
#warning ACPI uses CMPXCHG, i486 and later hardware
#endif
/* --------------------------------------------------------------------------
Boot-time Configuration
-------------------------------------------------------------------------- */
/*
* The default interrupt routing model is PIC (8259). This gets
* overridden if IOAPICs are enumerated (below).
*/
enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC;
/*
* ISA irqs by default are the first 16 gsis but can be
* any gsi as specified by an interrupt source override.
*/
static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = {
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
};
static unsigned int gsi_to_irq(unsigned int gsi)
{
unsigned int irq = gsi + NR_IRQS_LEGACY;
unsigned int i;
for (i = 0; i < NR_IRQS_LEGACY; i++) {
if (isa_irq_to_gsi[i] == gsi) {
return i;
}
}
/* Provide an identity mapping of gsi == irq
* except on truly weird platforms that have
* non isa irqs in the first 16 gsis.
*/
if (gsi >= NR_IRQS_LEGACY)
irq = gsi;
else
irq = gsi_top + gsi;
return irq;
}
static u32 irq_to_gsi(int irq)
{
unsigned int gsi;
if (irq < NR_IRQS_LEGACY)
gsi = isa_irq_to_gsi[irq];
else if (irq < gsi_top)
gsi = irq;
else if (irq < (gsi_top + NR_IRQS_LEGACY))
gsi = irq - gsi_top;
else
gsi = 0xffffffff;
return gsi;
}
/*
* Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END,
* to map the target physical address. The problem is that set_fixmap()
* provides a single page, and it is possible that the page is not
* sufficient.
* By using this area, we can map up to MAX_IO_APICS pages temporarily,
* i.e. until the next __va_range() call.
*
* Important Safety Note: The fixed I/O APIC page numbers are *subtracted*
* from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and
* count idx down while incrementing the phys address.
*/
char *__init __acpi_map_table(unsigned long phys, unsigned long size)
{
if (!phys || !size)
return NULL;
return early_ioremap(phys, size);
}
void __init __acpi_unmap_table(char *map, unsigned long size)
{
if (!map || !size)
return;
early_iounmap(map, size);
}
#ifdef CONFIG_X86_LOCAL_APIC
static int __init acpi_parse_madt(struct acpi_table_header *table)
{
struct acpi_table_madt *madt = NULL;
if (!cpu_has_apic)
return -EINVAL;
madt = (struct acpi_table_madt *)table;
if (!madt) {
printk(KERN_WARNING PREFIX "Unable to map MADT\n");
return -ENODEV;
}
if (madt->address) {
acpi_lapic_addr = (u64) madt->address;
printk(KERN_DEBUG PREFIX "Local APIC address 0x%08x\n",
madt->address);
}
default_acpi_madt_oem_check(madt->header.oem_id,
madt->header.oem_table_id);
return 0;
}
static void __cpuinit acpi_register_lapic(int id, u8 enabled)
{
unsigned int ver = 0;
x86, acpi: Parse all SRAT cpu entries even above the cpu number limitation Recent Intel new system have different order in MADT, aka will list all thread0 at first, then all thread1. But SRAT table still old order, it will list cpus in one socket all together. If the user have compiled limited NR_CPUS or boot with nr_cpus=, could have missed to put some cpus apic id to node mapping into apicid_to_node[]. for example for 4 sockets system with 64 cpus with nr_cpus=32 will get crash... [ 9.106288] Total of 32 processors activated (136190.88 BogoMIPS). [ 9.235021] divide error: 0000 [#1] SMP [ 9.235315] last sysfs file: [ 9.235481] CPU 1 [ 9.235592] Modules linked in: [ 9.245398] [ 9.245478] Pid: 2, comm: kthreadd Not tainted 2.6.37-rc1-tip-yh-01782-ge92ef79-dirty #274 /Sun Fire x4800 [ 9.265415] RIP: 0010:[<ffffffff81075a8f>] [<ffffffff81075a8f>] select_task_rq_fair+0x4f0/0x623 ... [ 9.645938] RIP [<ffffffff81075a8f>] select_task_rq_fair+0x4f0/0x623 [ 9.665356] RSP <ffff88103f8d1c40> [ 9.665568] ---[ end trace 2296156d35fdfc87 ]--- So let just parse all cpu entries in SRAT. Also add apicid checking with MAX_LOCAL_APIC, in case We could out of boundaries of apicid_to_node[]. it fixes following bug too. https://bugzilla.kernel.org/show_bug.cgi?id=22662 -v2: expand to 32bit according to hpa need to add MAX_LOCAL_APIC for 32bit Reported-and-Tested-by: Wu Fengguang <fengguang.wu@intel.com> Reported-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Tested-by: Myron Stowe <myron.stowe@hp.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0AD486.9020704@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-17 11:09:58 +08:00
if (id >= (MAX_LOCAL_APIC-1)) {
printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
return;
}
if (!enabled) {
++disabled_cpus;
return;
}
if (boot_cpu_physical_apicid != -1U)
ver = apic_version[boot_cpu_physical_apicid];
generic_processor_info(id, ver);
}
static int __init
acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
{
struct acpi_madt_local_x2apic *processor = NULL;
int apic_id;
u8 enabled;
processor = (struct acpi_madt_local_x2apic *)header;
if (BAD_MADT_ENTRY(processor, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
apic_id = processor->local_apic_id;
enabled = processor->lapic_flags & ACPI_MADT_ENABLED;
#ifdef CONFIG_X86_X2APIC
/*
* We need to register disabled CPU as well to permit
* counting disabled CPUs. This allows us to size
* cpus_possible_map more accurately, to permit
* to not preallocating memory for all NR_CPUS
* when we use CPU hotplug.
*/
if (!apic->apic_id_valid(apic_id) && enabled)
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
else
acpi_register_lapic(apic_id, enabled);
#else
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
#endif
return 0;
}
static int __init
acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_local_apic *processor = NULL;
processor = (struct acpi_madt_local_apic *)header;
if (BAD_MADT_ENTRY(processor, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
/*
* We need to register disabled CPU as well to permit
* counting disabled CPUs. This allows us to size
* cpus_possible_map more accurately, to permit
* to not preallocating memory for all NR_CPUS
* when we use CPU hotplug.
*/
acpi_register_lapic(processor->id, /* APIC ID */
processor->lapic_flags & ACPI_MADT_ENABLED);
return 0;
}
static int __init
acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
{
struct acpi_madt_local_sapic *processor = NULL;
processor = (struct acpi_madt_local_sapic *)header;
if (BAD_MADT_ENTRY(processor, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */
processor->lapic_flags & ACPI_MADT_ENABLED);
return 0;
}
static int __init
acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
const unsigned long end)
{
struct acpi_madt_local_apic_override *lapic_addr_ovr = NULL;
lapic_addr_ovr = (struct acpi_madt_local_apic_override *)header;
if (BAD_MADT_ENTRY(lapic_addr_ovr, end))
return -EINVAL;
acpi_lapic_addr = lapic_addr_ovr->address;
return 0;
}
static int __init
acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
const unsigned long end)
{
struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL;
x2apic_nmi = (struct acpi_madt_local_x2apic_nmi *)header;
if (BAD_MADT_ENTRY(x2apic_nmi, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
if (x2apic_nmi->lint != 1)
printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
return 0;
}
static int __init
acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_local_apic_nmi *lapic_nmi = NULL;
lapic_nmi = (struct acpi_madt_local_apic_nmi *)header;
if (BAD_MADT_ENTRY(lapic_nmi, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
if (lapic_nmi->lint != 1)
printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
return 0;
}
#endif /*CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_io_apic *ioapic = NULL;
ioapic = (struct acpi_madt_io_apic *)header;
if (BAD_MADT_ENTRY(ioapic, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
mp_register_ioapic(ioapic->id,
ioapic->address, ioapic->global_irq_base);
return 0;
}
/*
* Parse Interrupt Source Override for the ACPI SCI
*/
static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, u32 gsi)
{
if (trigger == 0) /* compatible SCI trigger is level */
trigger = 3;
if (polarity == 0) /* compatible SCI polarity is low */
polarity = 3;
/* Command-line over-ride via acpi_sci= */
if (acpi_sci_flags & ACPI_MADT_TRIGGER_MASK)
trigger = (acpi_sci_flags & ACPI_MADT_TRIGGER_MASK) >> 2;
if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK)
polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
/*
* mp_config_acpi_legacy_irqs() already setup IRQs < 16
* If GSI is < 16, this will update its flags,
* else it will create a new mp_irqs[] entry.
*/
mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
/*
* stash over-ride to indicate we've been here
* and for later update of acpi_gbl_FADT
*/
acpi_sci_override_gsi = gsi;
return;
}
static int __init
acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
const unsigned long end)
{
struct acpi_madt_interrupt_override *intsrc = NULL;
intsrc = (struct acpi_madt_interrupt_override *)header;
if (BAD_MADT_ENTRY(intsrc, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
if (intsrc->source_irq == acpi_gbl_FADT.sci_interrupt) {
acpi_sci_ioapic_setup(intsrc->source_irq,
intsrc->inti_flags & ACPI_MADT_POLARITY_MASK,
(intsrc->inti_flags & ACPI_MADT_TRIGGER_MASK) >> 2,
intsrc->global_irq);
return 0;
}
if (intsrc->source_irq == 0) {
if (acpi_skip_timer_override) {
printk(PREFIX "BIOS IRQ0 override ignored.\n");
return 0;
}
if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity
&& (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) {
intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK;
printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n");
}
}
mp_override_legacy_irq(intsrc->source_irq,
intsrc->inti_flags & ACPI_MADT_POLARITY_MASK,
(intsrc->inti_flags & ACPI_MADT_TRIGGER_MASK) >> 2,
intsrc->global_irq);
return 0;
}
static int __init
acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_nmi_source *nmi_src = NULL;
nmi_src = (struct acpi_madt_nmi_source *)header;
if (BAD_MADT_ENTRY(nmi_src, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
/* TBD: Support nimsrc entries? */
return 0;
}
#endif /* CONFIG_X86_IO_APIC */
/*
* acpi_pic_sci_set_trigger()
*
* use ELCR to set PIC-mode trigger type for SCI
*
* If a PIC-mode SCI is not recognized or gives spurious IRQ7's
* it may require Edge Trigger -- use "acpi_sci=edge"
*
* Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers
* for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge.
* ECLR1 is IRQs 0-7 (IRQ 0, 1, 2 must be 0)
* ECLR2 is IRQs 8-15 (IRQ 8, 13 must be 0)
*/
void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
{
unsigned int mask = 1 << irq;
unsigned int old, new;
/* Real old ELCR mask */
old = inb(0x4d0) | (inb(0x4d1) << 8);
/*
* If we use ACPI to set PCI IRQs, then we should clear ELCR
* since we will set it correctly as we enable the PCI irq
* routing.
*/
new = acpi_noirq ? old : 0;
/*
* Update SCI information in the ELCR, it isn't in the PCI
* routing tables..
*/
switch (trigger) {
case 1: /* Edge - clear */
new &= ~mask;
break;
case 3: /* Level - set */
new |= mask;
break;
}
if (old == new)
return;
printk(PREFIX "setting ELCR to %04x (from %04x)\n", new, old);
outb(new, 0x4d0);
outb(new >> 8, 0x4d1);
}
int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
{
*irq = gsi_to_irq(gsi);
#ifdef CONFIG_X86_IO_APIC
if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC)
setup_IO_APIC_irq_extra(gsi);
#endif
return 0;
}
EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi)
{
if (isa_irq >= 16)
return -1;
*gsi = irq_to_gsi(isa_irq);
return 0;
}
static int acpi_register_gsi_pic(struct device *dev, u32 gsi,
int trigger, int polarity)
{
#ifdef CONFIG_PCI
/*
* Make sure all (legacy) PCI IRQs are set as level-triggered.
*/
if (trigger == ACPI_LEVEL_SENSITIVE)
eisa_set_level_irq(gsi);
#endif
return gsi;
}
static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
int trigger, int polarity)
{
#ifdef CONFIG_X86_IO_APIC
gsi = mp_register_gsi(dev, gsi, trigger, polarity);
#endif
return gsi;
}
int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
int trigger, int polarity) = acpi_register_gsi_pic;
/*
* success: return IRQ number (>=0)
* failure: return < 0
*/
int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
{
unsigned int irq;
unsigned int plat_gsi = gsi;
plat_gsi = (*__acpi_register_gsi)(dev, gsi, trigger, polarity);
irq = gsi_to_irq(plat_gsi);
return irq;
}
void __init acpi_set_irq_model_pic(void)
{
acpi_irq_model = ACPI_IRQ_MODEL_PIC;
__acpi_register_gsi = acpi_register_gsi_pic;
acpi_ioapic = 0;
}
void __init acpi_set_irq_model_ioapic(void)
{
acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
__acpi_register_gsi = acpi_register_gsi_ioapic;
acpi_ioapic = 1;
}
/*
* ACPI based hotplug support for CPU
*/
#ifdef CONFIG_ACPI_HOTPLUG_CPU
#include <acpi/processor.h>
static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
int nid;
nid = acpi_get_node(handle);
if (nid == -1 || !node_online(nid))
return;
set_apicid_to_node(physid, nid);
numa_set_node(cpu, nid);
#endif
}
static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
{
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *obj;
struct acpi_madt_local_apic *lapic;
cpumask_var_t tmp_map, new_map;
u8 physid;
int cpu;
int retval = -ENOMEM;
if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
return -EINVAL;
if (!buffer.length || !buffer.pointer)
return -EINVAL;
obj = buffer.pointer;
if (obj->type != ACPI_TYPE_BUFFER ||
obj->buffer.length < sizeof(*lapic)) {
kfree(buffer.pointer);
return -EINVAL;
}
lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer;
if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC ||
!(lapic->lapic_flags & ACPI_MADT_ENABLED)) {
kfree(buffer.pointer);
return -EINVAL;
}
physid = lapic->id;
kfree(buffer.pointer);
buffer.length = ACPI_ALLOCATE_BUFFER;
buffer.pointer = NULL;
lapic = NULL;
if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL))
goto out;
if (!alloc_cpumask_var(&new_map, GFP_KERNEL))
goto free_tmp_map;
cpumask_copy(tmp_map, cpu_present_mask);
acpi_register_lapic(physid, ACPI_MADT_ENABLED);
/*
* If mp_register_lapic successfully generates a new logical cpu
* number, then the following will get us exactly what was mapped
*/
cpumask_andnot(new_map, cpu_present_mask, tmp_map);
if (cpumask_empty(new_map)) {
printk ("Unable to map lapic to logical cpu number\n");
retval = -EINVAL;
goto free_new_map;
}
acpi_processor_set_pdc(handle);
cpu = cpumask_first(new_map);
acpi_map_cpu2node(handle, cpu, physid);
*pcpu = cpu;
retval = 0;
free_new_map:
free_cpumask_var(new_map);
free_tmp_map:
free_cpumask_var(tmp_map);
out:
return retval;
}
/* wrapper to silence section mismatch warning */
int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu)
{
return _acpi_map_lsapic(handle, pcpu);
}
EXPORT_SYMBOL(acpi_map_lsapic);
int acpi_unmap_lsapic(int cpu)
{
per_cpu(x86_cpu_to_apicid, cpu) = -1;
set_cpu_present(cpu, false);
num_processors--;
return (0);
}
EXPORT_SYMBOL(acpi_unmap_lsapic);
#endif /* CONFIG_ACPI_HOTPLUG_CPU */
int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
{
/* TBD */
return -EINVAL;
}
EXPORT_SYMBOL(acpi_register_ioapic);
int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
{
/* TBD */
return -EINVAL;
}
EXPORT_SYMBOL(acpi_unregister_ioapic);
static int __init acpi_parse_sbf(struct acpi_table_header *table)
{
struct acpi_table_boot *sb;
sb = (struct acpi_table_boot *)table;
if (!sb) {
printk(KERN_WARNING PREFIX "Unable to map SBF\n");
return -ENODEV;
}
sbf_port = sb->cmos_index; /* Save CMOS port */
return 0;
}
#ifdef CONFIG_HPET_TIMER
#include <asm/hpet.h>
static struct __initdata resource *hpet_res;
static int __init acpi_parse_hpet(struct acpi_table_header *table)
{
struct acpi_table_hpet *hpet_tbl;
hpet_tbl = (struct acpi_table_hpet *)table;
if (!hpet_tbl) {
printk(KERN_WARNING PREFIX "Unable to map HPET\n");
return -ENODEV;
}
if (hpet_tbl->address.space_id != ACPI_SPACE_MEM) {
printk(KERN_WARNING PREFIX "HPET timers must be located in "
"memory.\n");
return -1;
}
hpet_address = hpet_tbl->address.address;
hpet_blockid = hpet_tbl->sequence;
/*
* Some broken BIOSes advertise HPET at 0x0. We really do not
* want to allocate a resource there.
*/
if (!hpet_address) {
printk(KERN_WARNING PREFIX
"HPET id: %#x base: %#lx is invalid\n",
hpet_tbl->id, hpet_address);
return 0;
}
#ifdef CONFIG_X86_64
/*
* Some even more broken BIOSes advertise HPET at
* 0xfed0000000000000 instead of 0xfed00000. Fix it up and add
* some noise:
*/
if (hpet_address == 0xfed0000000000000UL) {
if (!hpet_force_user) {
printk(KERN_WARNING PREFIX "HPET id: %#x "
"base: 0xfed0000000000000 is bogus\n "
"try hpet=force on the kernel command line to "
"fix it up to 0xfed00000.\n", hpet_tbl->id);
hpet_address = 0;
return 0;
}
printk(KERN_WARNING PREFIX
"HPET id: %#x base: 0xfed0000000000000 fixed up "
"to 0xfed00000.\n", hpet_tbl->id);
hpet_address >>= 32;
}
#endif
printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n",
hpet_tbl->id, hpet_address);
/*
* Allocate and initialize the HPET firmware resource for adding into
* the resource tree during the lateinit timeframe.
*/
#define HPET_RESOURCE_NAME_SIZE 9
hpet_res = alloc_bootmem(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE);
hpet_res->name = (void *)&hpet_res[1];
hpet_res->flags = IORESOURCE_MEM;
snprintf((char *)hpet_res->name, HPET_RESOURCE_NAME_SIZE, "HPET %u",
hpet_tbl->sequence);
hpet_res->start = hpet_address;
hpet_res->end = hpet_address + (1 * 1024) - 1;
return 0;
}
/*
* hpet_insert_resource inserts the HPET resources used into the resource
* tree.
*/
static __init int hpet_insert_resource(void)
{
if (!hpet_res)
return 1;
return insert_resource(&iomem_resource, hpet_res);
}
late_initcall(hpet_insert_resource);
#else
#define acpi_parse_hpet NULL
#endif
static int __init acpi_parse_fadt(struct acpi_table_header *table)
{
#ifdef CONFIG_X86_PM_TIMER
/* detect the location of the ACPI PM Timer */
if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) {
/* FADT rev. 2 */
if (acpi_gbl_FADT.xpm_timer_block.space_id !=
ACPI_ADR_SPACE_SYSTEM_IO)
return 0;
pmtmr_ioport = acpi_gbl_FADT.xpm_timer_block.address;
/*
* "X" fields are optional extensions to the original V1.0
* fields, so we must selectively expand V1.0 fields if the
* corresponding X field is zero.
*/
if (!pmtmr_ioport)
pmtmr_ioport = acpi_gbl_FADT.pm_timer_block;
} else {
/* FADT rev. 1 */
pmtmr_ioport = acpi_gbl_FADT.pm_timer_block;
}
if (pmtmr_ioport)
printk(KERN_INFO PREFIX "PM-Timer IO Port: %#x\n",
pmtmr_ioport);
#endif
return 0;
}
#ifdef CONFIG_X86_LOCAL_APIC
/*
* Parse LAPIC entries in MADT
* returns 0 on success, < 0 on error
*/
static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
{
int count;
if (!cpu_has_apic)
return -ENODEV;
/*
* Note that the LAPIC address is obtained from the MADT (32-bit value)
* and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value).
*/
count =
acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
acpi_parse_lapic_addr_ovr, 0);
if (count < 0) {
printk(KERN_ERR PREFIX
"Error parsing LAPIC address override entry\n");
return count;
}
register_lapic_address(acpi_lapic_addr);
return count;
}
static int __init acpi_parse_madt_lapic_entries(void)
{
int count;
int x2count = 0;
if (!cpu_has_apic)
return -ENODEV;
/*
* Note that the LAPIC address is obtained from the MADT (32-bit value)
* and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value).
*/
count =
acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
acpi_parse_lapic_addr_ovr, 0);
if (count < 0) {
printk(KERN_ERR PREFIX
"Error parsing LAPIC address override entry\n");
return count;
}
register_lapic_address(acpi_lapic_addr);
count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
acpi_parse_sapic, MAX_LOCAL_APIC);
if (!count) {
x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
acpi_parse_x2apic, MAX_LOCAL_APIC);
count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
acpi_parse_lapic, MAX_LOCAL_APIC);
}
if (!count && !x2count) {
printk(KERN_ERR PREFIX "No LAPIC entries present\n");
/* TBD: Cleanup to allow fallback to MPS */
return -ENODEV;
} else if (count < 0 || x2count < 0) {
printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n");
/* TBD: Cleanup to allow fallback to MPS */
return count;
}
x2count =
acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI,
acpi_parse_x2apic_nmi, 0);
count =
acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0);
if (count < 0 || x2count < 0) {
printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n");
/* TBD: Cleanup to allow fallback to MPS */
return count;
}
return 0;
}
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
#define MP_ISA_BUS 0
#ifdef CONFIG_X86_ES7000
extern int es7000_plat;
#endif
void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
{
int ioapic;
int pin;
struct mpc_intsrc mp_irq;
/*
* Convert 'gsi' to 'ioapic.pin'.
*/
ioapic = mp_find_ioapic(gsi);
if (ioapic < 0)
return;
pin = mp_find_ioapic_pin(ioapic, gsi);
/*
* TBD: This check is for faulty timer entries, where the override
* erroneously sets the trigger to level, resulting in a HUGE
* increase of timer interrupts!
*/
if ((bus_irq == 0) && (trigger == 3))
trigger = 1;
mp_irq.type = MP_INTSRC;
mp_irq.irqtype = mp_INT;
mp_irq.irqflag = (trigger << 2) | polarity;
mp_irq.srcbus = MP_ISA_BUS;
mp_irq.srcbusirq = bus_irq; /* IRQ */
mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */
mp_irq.dstirq = pin; /* INTIN# */
mp_save_irq(&mp_irq);
isa_irq_to_gsi[bus_irq] = gsi;
}
void __init mp_config_acpi_legacy_irqs(void)
{
int i;
struct mpc_intsrc mp_irq;
#ifdef CONFIG_EISA
/*
* Fabricate the legacy ISA bus (bus #31).
*/
mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA;
#endif
set_bit(MP_ISA_BUS, mp_bus_not_pci);
pr_debug("Bus #%d is ISA\n", MP_ISA_BUS);
#ifdef CONFIG_X86_ES7000
/*
* Older generations of ES7000 have no legacy identity mappings
*/
if (es7000_plat == 1)
return;
#endif
/*
* Use the default configuration for the IRQs 0-15. Unless
* overridden by (MADT) interrupt source override entries.
*/
for (i = 0; i < 16; i++) {
int ioapic, pin;
unsigned int dstapic;
int idx;
u32 gsi;
/* Locate the gsi that irq i maps to. */
if (acpi_isa_irq_to_gsi(i, &gsi))
continue;
/*
* Locate the IOAPIC that manages the ISA IRQ.
*/
ioapic = mp_find_ioapic(gsi);
if (ioapic < 0)
continue;
pin = mp_find_ioapic_pin(ioapic, gsi);
dstapic = mpc_ioapic_id(ioapic);
for (idx = 0; idx < mp_irq_entries; idx++) {
struct mpc_intsrc *irq = mp_irqs + idx;
/* Do we already have a mapping for this ISA IRQ? */
if (irq->srcbus == MP_ISA_BUS && irq->srcbusirq == i)
break;
/* Do we already have a mapping for this IOAPIC pin */
if (irq->dstapic == dstapic && irq->dstirq == pin)
break;
}
if (idx != mp_irq_entries) {
printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i);
continue; /* IRQ already used */
}
mp_irq.type = MP_INTSRC;
mp_irq.irqflag = 0; /* Conforming */
mp_irq.srcbus = MP_ISA_BUS;
mp_irq.dstapic = dstapic;
mp_irq.irqtype = mp_INT;
mp_irq.srcbusirq = i; /* Identity mapped */
mp_irq.dstirq = pin;
mp_save_irq(&mp_irq);
}
}
static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
int polarity)
{
#ifdef CONFIG_X86_MPPARSE
struct mpc_intsrc mp_irq;
struct pci_dev *pdev;
unsigned char number;
unsigned int devfn;
int ioapic;
u8 pin;
if (!acpi_ioapic)
return 0;
if (!dev)
return 0;
if (dev->bus != &pci_bus_type)
return 0;
pdev = to_pci_dev(dev);
number = pdev->bus->number;
devfn = pdev->devfn;
pin = pdev->pin;
/* print the entry should happen on mptable identically */
mp_irq.type = MP_INTSRC;
mp_irq.irqtype = mp_INT;
mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
mp_irq.srcbus = number;
mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
ioapic = mp_find_ioapic(gsi);
mp_irq.dstapic = mpc_ioapic_id(ioapic);
mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
mp_save_irq(&mp_irq);
#endif
return 0;
}
int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
{
int ioapic;
int ioapic_pin;
struct io_apic_irq_attr irq_attr;
if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
return gsi;
/* Don't set up the ACPI SCI because it's already set up */
if (acpi_gbl_FADT.sci_interrupt == gsi)
return gsi;
ioapic = mp_find_ioapic(gsi);
if (ioapic < 0) {
printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
return gsi;
}
ioapic_pin = mp_find_ioapic_pin(ioapic, gsi);
if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
printk(KERN_ERR "Invalid reference to IOAPIC pin "
"%d-%d\n", mpc_ioapic_id(ioapic),
ioapic_pin);
return gsi;
}
if (enable_update_mptable)
mp_config_acpi_gsi(dev, gsi, trigger, polarity);
x86/acpi: remove irq-compression trick on 32-bit We already have a per cpu vector on 32-bit via recent changes, and don't need this trick any more (which trick obfuscates the real GSI mappings and which only triggers on larger systems to begin with): On 3 ioapic system (24 per ioapic) before patch I got: ACPI: PCI Interrupt Link [ILSB] enabled at IRQ 71 IOAPIC[2]: Set routing entry (10-23 -> 0xa9 -> IRQ 64 Mode:1 Active:1) pci 0000:80:01.1: PCI INT A -> Link[ILSB] -> GSI 71 (level, low) -> IRQ 64 ACPI: PCI Interrupt Link [LE5B] enabled at IRQ 67 IOAPIC[2]: Set routing entry (10-19 -> 0xb1 -> IRQ 65 Mode:1 Active:1) pci 0000:83:00.0: PCI INT B -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 65 ACPI: PCI Interrupt Link [LE5A] enabled at IRQ 66 IOAPIC[2]: Set routing entry (10-18 -> 0xb9 -> IRQ 66 Mode:1 Active:1) pci 0000:83:00.1: PCI INT A -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 ACPI: PCI Interrupt Link [LE5D] enabled at IRQ 65 IOAPIC[2]: Set routing entry (10-17 -> 0xc1 -> IRQ 67 Mode:1 Active:1) pci 0000:84:00.0: PCI INT B -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 67 ACPI: PCI Interrupt Link [LE5C] enabled at IRQ 64 IOAPIC[2]: Set routing entry (10-16 -> 0xc9 -> IRQ 68 Mode:1 Active:1) pci 0000:84:00.1: PCI INT A -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 68 pci 0000:87:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:87:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 67 pci 0000:88:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 68 pci 0000:88:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 65 pci 0000:8b:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:8b:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 67 pci 0000:8c:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 68 pci 0000:8c:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 65 after the patch we get: ACPI: PCI Interrupt Link [ILSB] enabled at IRQ 71 IOAPIC[2]: Set routing entry (10-23 -> 0xa9 -> IRQ 71 Mode:1 Active:1) pci 0000:80:01.1: PCI INT A -> Link[ILSB] -> GSI 71 (level, low) -> IRQ 71 ACPI: PCI Interrupt Link [LE5B] enabled at IRQ 67 IOAPIC[2]: Set routing entry (10-19 -> 0xb1 -> IRQ 67 Mode:1 Active:1) pci 0000:83:00.0: PCI INT B -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 67 ACPI: PCI Interrupt Link [LE5A] enabled at IRQ 66 IOAPIC[2]: Set routing entry (10-18 -> 0xb9 -> IRQ 66 Mode:1 Active:1) pci 0000:83:00.1: PCI INT A -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 ACPI: PCI Interrupt Link [LE5D] enabled at IRQ 65 IOAPIC[2]: Set routing entry (10-17 -> 0xc1 -> IRQ 65 Mode:1 Active:1) pci 0000:84:00.0: PCI INT B -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 65 ACPI: PCI Interrupt Link [LE5C] enabled at IRQ 64 IOAPIC[2]: Set routing entry (10-16 -> 0xc9 -> IRQ 64 Mode:1 Active:1) pci 0000:84:00.1: PCI INT A -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 64 pci 0000:87:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:87:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 65 pci 0000:88:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 64 pci 0000:88:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 67 pci 0000:8b:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:8b:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 65 pci 0000:8c:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 64 pci 0000:8c:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 67 As it can be seen that GSIs now get mapped lineary. [ Impact: simplify irq number mapping on bigger 32-bit systems ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: Len Brown <lenb@kernel.org> LKML-Reference: <4A01C35C.7060207@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-07 01:05:32 +08:00
set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
x86/acpi: remove irq-compression trick on 32-bit We already have a per cpu vector on 32-bit via recent changes, and don't need this trick any more (which trick obfuscates the real GSI mappings and which only triggers on larger systems to begin with): On 3 ioapic system (24 per ioapic) before patch I got: ACPI: PCI Interrupt Link [ILSB] enabled at IRQ 71 IOAPIC[2]: Set routing entry (10-23 -> 0xa9 -> IRQ 64 Mode:1 Active:1) pci 0000:80:01.1: PCI INT A -> Link[ILSB] -> GSI 71 (level, low) -> IRQ 64 ACPI: PCI Interrupt Link [LE5B] enabled at IRQ 67 IOAPIC[2]: Set routing entry (10-19 -> 0xb1 -> IRQ 65 Mode:1 Active:1) pci 0000:83:00.0: PCI INT B -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 65 ACPI: PCI Interrupt Link [LE5A] enabled at IRQ 66 IOAPIC[2]: Set routing entry (10-18 -> 0xb9 -> IRQ 66 Mode:1 Active:1) pci 0000:83:00.1: PCI INT A -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 ACPI: PCI Interrupt Link [LE5D] enabled at IRQ 65 IOAPIC[2]: Set routing entry (10-17 -> 0xc1 -> IRQ 67 Mode:1 Active:1) pci 0000:84:00.0: PCI INT B -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 67 ACPI: PCI Interrupt Link [LE5C] enabled at IRQ 64 IOAPIC[2]: Set routing entry (10-16 -> 0xc9 -> IRQ 68 Mode:1 Active:1) pci 0000:84:00.1: PCI INT A -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 68 pci 0000:87:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:87:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 67 pci 0000:88:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 68 pci 0000:88:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 65 pci 0000:8b:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:8b:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 67 pci 0000:8c:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 68 pci 0000:8c:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 65 after the patch we get: ACPI: PCI Interrupt Link [ILSB] enabled at IRQ 71 IOAPIC[2]: Set routing entry (10-23 -> 0xa9 -> IRQ 71 Mode:1 Active:1) pci 0000:80:01.1: PCI INT A -> Link[ILSB] -> GSI 71 (level, low) -> IRQ 71 ACPI: PCI Interrupt Link [LE5B] enabled at IRQ 67 IOAPIC[2]: Set routing entry (10-19 -> 0xb1 -> IRQ 67 Mode:1 Active:1) pci 0000:83:00.0: PCI INT B -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 67 ACPI: PCI Interrupt Link [LE5A] enabled at IRQ 66 IOAPIC[2]: Set routing entry (10-18 -> 0xb9 -> IRQ 66 Mode:1 Active:1) pci 0000:83:00.1: PCI INT A -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 ACPI: PCI Interrupt Link [LE5D] enabled at IRQ 65 IOAPIC[2]: Set routing entry (10-17 -> 0xc1 -> IRQ 65 Mode:1 Active:1) pci 0000:84:00.0: PCI INT B -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 65 ACPI: PCI Interrupt Link [LE5C] enabled at IRQ 64 IOAPIC[2]: Set routing entry (10-16 -> 0xc9 -> IRQ 64 Mode:1 Active:1) pci 0000:84:00.1: PCI INT A -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 64 pci 0000:87:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:87:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 65 pci 0000:88:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 64 pci 0000:88:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 67 pci 0000:8b:00.0: PCI INT B -> Link[LE5A] -> GSI 66 (level, low) -> IRQ 66 pci 0000:8b:00.1: PCI INT A -> Link[LE5D] -> GSI 65 (level, low) -> IRQ 65 pci 0000:8c:00.0: PCI INT B -> Link[LE5C] -> GSI 64 (level, low) -> IRQ 64 pci 0000:8c:00.1: PCI INT A -> Link[LE5B] -> GSI 67 (level, low) -> IRQ 67 As it can be seen that GSIs now get mapped lineary. [ Impact: simplify irq number mapping on bigger 32-bit systems ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: Len Brown <lenb@kernel.org> LKML-Reference: <4A01C35C.7060207@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-07 01:05:32 +08:00
return gsi;
}
/*
* Parse IOAPIC related entries in MADT
* returns 0 on success, < 0 on error
*/
static int __init acpi_parse_madt_ioapic_entries(void)
{
int count;
/*
* ACPI interpreter is required to complete interrupt setup,
* so if it is off, don't enumerate the io-apics with ACPI.
* If MPS is present, it will handle them,
* otherwise the system will stay in PIC mode
*/
if (acpi_disabled || acpi_noirq)
return -ENODEV;
if (!cpu_has_apic)
return -ENODEV;
/*
* if "noapic" boot option, don't look for IO-APICs
*/
if (skip_ioapic_setup) {
printk(KERN_INFO PREFIX "Skipping IOAPIC probe "
"due to 'noapic' option.\n");
return -ENODEV;
}
count =
acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic,
MAX_IO_APICS);
if (!count) {
printk(KERN_ERR PREFIX "No IOAPIC entries present\n");
return -ENODEV;
} else if (count < 0) {
printk(KERN_ERR PREFIX "Error parsing IOAPIC entry\n");
return count;
}
count =
acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
nr_irqs);
if (count < 0) {
printk(KERN_ERR PREFIX
"Error parsing interrupt source overrides entry\n");
/* TBD: Cleanup to allow fallback to MPS */
return count;
}
/*
* If BIOS did not supply an INT_SRC_OVR for the SCI
* pretend we got one so we can set the SCI flags.
*/
if (!acpi_sci_override_gsi)
acpi_sci_ioapic_setup(acpi_gbl_FADT.sci_interrupt, 0, 0,
acpi_gbl_FADT.sci_interrupt);
/* Fill in identity legacy mappings where no override */
mp_config_acpi_legacy_irqs();
count =
acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src,
nr_irqs);
if (count < 0) {
printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n");
/* TBD: Cleanup to allow fallback to MPS */
return count;
}
return 0;
}
#else
static inline int acpi_parse_madt_ioapic_entries(void)
{
return -1;
}
#endif /* !CONFIG_X86_IO_APIC */
static void __init early_acpi_process_madt(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
int error;
if (!acpi_table_parse(ACPI_SIG_MADT, acpi_parse_madt)) {
/*
* Parse MADT LAPIC entries
*/
error = early_acpi_parse_madt_lapic_addr_ovr();
if (!error) {
acpi_lapic = 1;
smp_found_config = 1;
}
if (error == -EINVAL) {
/*
* Dell Precision Workstation 410, 610 come here.
*/
printk(KERN_ERR PREFIX
"Invalid BIOS MADT, disabling ACPI\n");
disable_acpi();
}
}
#endif
}
static void __init acpi_process_madt(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
int error;
if (!acpi_table_parse(ACPI_SIG_MADT, acpi_parse_madt)) {
/*
* Parse MADT LAPIC entries
*/
error = acpi_parse_madt_lapic_entries();
if (!error) {
acpi_lapic = 1;
/*
* Parse MADT IO-APIC entries
*/
error = acpi_parse_madt_ioapic_entries();
if (!error) {
acpi_set_irq_model_ioapic();
smp_found_config = 1;
}
}
if (error == -EINVAL) {
/*
* Dell Precision Workstation 410, 610 come here.
*/
printk(KERN_ERR PREFIX
"Invalid BIOS MADT, disabling ACPI\n");
disable_acpi();
}
} else {
/*
* ACPI found no MADT, and so ACPI wants UP PIC mode.
* In the event an MPS table was found, forget it.
* Boot with "acpi=off" to use MPS on such a system.
*/
if (smp_found_config) {
printk(KERN_WARNING PREFIX
"No APIC-table, disabling MPS\n");
smp_found_config = 0;
}
}
/*
* ACPI supports both logical (e.g. Hyper-Threading) and physical
* processors, where MPS only supports physical.
*/
if (acpi_lapic && acpi_ioapic)
printk(KERN_INFO "Using ACPI (MADT) for SMP configuration "
"information\n");
else if (acpi_lapic)
printk(KERN_INFO "Using ACPI for processor (LAPIC) "
"configuration information\n");
#endif
return;
}
static int __init disable_acpi_irq(const struct dmi_system_id *d)
{
if (!acpi_force) {
printk(KERN_NOTICE "%s detected: force use of acpi=noirq\n",
d->ident);
acpi_noirq_set();
}
return 0;
}
static int __init disable_acpi_pci(const struct dmi_system_id *d)
{
if (!acpi_force) {
printk(KERN_NOTICE "%s detected: force use of pci=noacpi\n",
d->ident);
acpi_disable_pci();
}
return 0;
}
static int __init dmi_disable_acpi(const struct dmi_system_id *d)
{
if (!acpi_force) {
printk(KERN_NOTICE "%s detected: acpi off\n", d->ident);
disable_acpi();
} else {
printk(KERN_NOTICE
"Warning: DMI blacklist says broken, but acpi forced\n");
}
return 0;
}
x86: fix C1E && nx6325 stability problem The problems are that, with the ACPI vs timer overring issue _fixed_, after using the box for some time (between several seconds and 1 hour, at random) processes get very high CPU loads (once I've got X using 107% of the CPU, for example) and the system becomes unresponsive, as though there were interrupts lost or something similar. Andreas Herrman reproduced similar problems: > Ok, now I've reproduced the stability problem. > - Using tip/master, > - reverting e38502eb8aa82314d5ab0eba45f50e6790dadd88 and > - applying your patch from this posting > http://marc.info/?l=linux-kernel&m=121539354224562&w=4 > > Starting X, firefox, gimp, tuxpaint and doing some drawing in tuxpaint > results in a slow system. Drawing is almost not possible anymore -- > Selections of new colors, cursors etc. is performed with huge delay > if it's performed at all. > > BTW, the code sets up timer IRQ as Virtual Wire IRQ: > > Jul 8 14:57:58 kodscha IO-APIC (apicid-pin) 2-22, 2-23 not connected. > Jul 8 14:57:58 kodscha ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 > Jul 8 14:57:58 kodscha ...trying to set up timer as Virtual Wire IRQ... works. > > and both INT0 and INT2 of IOAPIC are masked: > > Jul 8 14:57:58 kodscha NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect: > Jul 8 14:57:58 kodscha 00 000 1 0 0 0 0 0 0 00 > Jul 8 14:57:58 kodscha 01 003 0 0 0 0 0 1 1 31 > Jul 8 14:57:58 kodscha 02 003 1 0 0 0 0 0 0 30 > > I've also seen strange CPU utilization -- with syslog-ng: > > top - 15:33:06 up 35 min, 4 users, load average: 1.70, 0.68, 0.37 > Tasks: 64 total, 4 running, 60 sleeping, 0 stopped, 0 zombie > Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st > Cpu1 : 6.4%us, 87.2%sy, 0.0%ni, 5.8%id, 0.0%wa, 0.6%hi, 0.0%si, 0.0%st > Mem: 895384k total, 283568k used, 611816k free, 35492k buffers > Swap: 1959920k total, 0k used, 1959920k free, 163044k cached > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > 4632 root 20 0 17216 800 580 S 104 0.1 0:34.22 syslog-ng > 28505 root 20 0 205m 11m 4024 S 6 1.3 0:21.16 X > 28518 root 20 0 56292 5652 4492 S 1 0.6 0:01.80 fluxbox > 1 root 20 0 3724 608 508 S 0 0.1 0:00.36 init > > So far I have no clue why C1E-idle in conjunction with virtual wire > mode causes this strange behaviour. > > ... and I start to think about the root cause of all this. > > I've performed similar tests under X with the IRQ0/INT0 configuration and > I did not see above symptoms. So lets fall back to the IRQ0/INT0 configuration on this box. This basically restores the dont-use-the-lapic-timer exception mechanism that was unconditional on this box prior commit 8750bf5 ("x86: add C1E aware idle function"). Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 22:12:26 +08:00
/*
* Force ignoring BIOS IRQ0 override
x86: fix C1E && nx6325 stability problem The problems are that, with the ACPI vs timer overring issue _fixed_, after using the box for some time (between several seconds and 1 hour, at random) processes get very high CPU loads (once I've got X using 107% of the CPU, for example) and the system becomes unresponsive, as though there were interrupts lost or something similar. Andreas Herrman reproduced similar problems: > Ok, now I've reproduced the stability problem. > - Using tip/master, > - reverting e38502eb8aa82314d5ab0eba45f50e6790dadd88 and > - applying your patch from this posting > http://marc.info/?l=linux-kernel&m=121539354224562&w=4 > > Starting X, firefox, gimp, tuxpaint and doing some drawing in tuxpaint > results in a slow system. Drawing is almost not possible anymore -- > Selections of new colors, cursors etc. is performed with huge delay > if it's performed at all. > > BTW, the code sets up timer IRQ as Virtual Wire IRQ: > > Jul 8 14:57:58 kodscha IO-APIC (apicid-pin) 2-22, 2-23 not connected. > Jul 8 14:57:58 kodscha ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 > Jul 8 14:57:58 kodscha ...trying to set up timer as Virtual Wire IRQ... works. > > and both INT0 and INT2 of IOAPIC are masked: > > Jul 8 14:57:58 kodscha NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect: > Jul 8 14:57:58 kodscha 00 000 1 0 0 0 0 0 0 00 > Jul 8 14:57:58 kodscha 01 003 0 0 0 0 0 1 1 31 > Jul 8 14:57:58 kodscha 02 003 1 0 0 0 0 0 0 30 > > I've also seen strange CPU utilization -- with syslog-ng: > > top - 15:33:06 up 35 min, 4 users, load average: 1.70, 0.68, 0.37 > Tasks: 64 total, 4 running, 60 sleeping, 0 stopped, 0 zombie > Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st > Cpu1 : 6.4%us, 87.2%sy, 0.0%ni, 5.8%id, 0.0%wa, 0.6%hi, 0.0%si, 0.0%st > Mem: 895384k total, 283568k used, 611816k free, 35492k buffers > Swap: 1959920k total, 0k used, 1959920k free, 163044k cached > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > 4632 root 20 0 17216 800 580 S 104 0.1 0:34.22 syslog-ng > 28505 root 20 0 205m 11m 4024 S 6 1.3 0:21.16 X > 28518 root 20 0 56292 5652 4492 S 1 0.6 0:01.80 fluxbox > 1 root 20 0 3724 608 508 S 0 0.1 0:00.36 init > > So far I have no clue why C1E-idle in conjunction with virtual wire > mode causes this strange behaviour. > > ... and I start to think about the root cause of all this. > > I've performed similar tests under X with the IRQ0/INT0 configuration and > I did not see above symptoms. So lets fall back to the IRQ0/INT0 configuration on this box. This basically restores the dont-use-the-lapic-timer exception mechanism that was unconditional on this box prior commit 8750bf5 ("x86: add C1E aware idle function"). Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 22:12:26 +08:00
*/
static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
{
if (!acpi_skip_timer_override) {
pr_notice("%s detected: Ignoring BIOS IRQ0 override\n",
d->ident);
acpi_skip_timer_override = 1;
}
x86: fix C1E && nx6325 stability problem The problems are that, with the ACPI vs timer overring issue _fixed_, after using the box for some time (between several seconds and 1 hour, at random) processes get very high CPU loads (once I've got X using 107% of the CPU, for example) and the system becomes unresponsive, as though there were interrupts lost or something similar. Andreas Herrman reproduced similar problems: > Ok, now I've reproduced the stability problem. > - Using tip/master, > - reverting e38502eb8aa82314d5ab0eba45f50e6790dadd88 and > - applying your patch from this posting > http://marc.info/?l=linux-kernel&m=121539354224562&w=4 > > Starting X, firefox, gimp, tuxpaint and doing some drawing in tuxpaint > results in a slow system. Drawing is almost not possible anymore -- > Selections of new colors, cursors etc. is performed with huge delay > if it's performed at all. > > BTW, the code sets up timer IRQ as Virtual Wire IRQ: > > Jul 8 14:57:58 kodscha IO-APIC (apicid-pin) 2-22, 2-23 not connected. > Jul 8 14:57:58 kodscha ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 > Jul 8 14:57:58 kodscha ...trying to set up timer as Virtual Wire IRQ... works. > > and both INT0 and INT2 of IOAPIC are masked: > > Jul 8 14:57:58 kodscha NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect: > Jul 8 14:57:58 kodscha 00 000 1 0 0 0 0 0 0 00 > Jul 8 14:57:58 kodscha 01 003 0 0 0 0 0 1 1 31 > Jul 8 14:57:58 kodscha 02 003 1 0 0 0 0 0 0 30 > > I've also seen strange CPU utilization -- with syslog-ng: > > top - 15:33:06 up 35 min, 4 users, load average: 1.70, 0.68, 0.37 > Tasks: 64 total, 4 running, 60 sleeping, 0 stopped, 0 zombie > Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st > Cpu1 : 6.4%us, 87.2%sy, 0.0%ni, 5.8%id, 0.0%wa, 0.6%hi, 0.0%si, 0.0%st > Mem: 895384k total, 283568k used, 611816k free, 35492k buffers > Swap: 1959920k total, 0k used, 1959920k free, 163044k cached > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > 4632 root 20 0 17216 800 580 S 104 0.1 0:34.22 syslog-ng > 28505 root 20 0 205m 11m 4024 S 6 1.3 0:21.16 X > 28518 root 20 0 56292 5652 4492 S 1 0.6 0:01.80 fluxbox > 1 root 20 0 3724 608 508 S 0 0.1 0:00.36 init > > So far I have no clue why C1E-idle in conjunction with virtual wire > mode causes this strange behaviour. > > ... and I start to think about the root cause of all this. > > I've performed similar tests under X with the IRQ0/INT0 configuration and > I did not see above symptoms. So lets fall back to the IRQ0/INT0 configuration on this box. This basically restores the dont-use-the-lapic-timer exception mechanism that was unconditional on this box prior commit 8750bf5 ("x86: add C1E aware idle function"). Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 22:12:26 +08:00
return 0;
}
/*
* If your system is blacklisted here, but you find that acpi=force
* works for you, please contact linux-acpi@vger.kernel.org
*/
static struct dmi_system_id __initdata acpi_dmi_table[] = {
/*
* Boxes that need ACPI disabled
*/
{
.callback = dmi_disable_acpi,
.ident = "IBM Thinkpad",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
DMI_MATCH(DMI_BOARD_NAME, "2629H1G"),
},
},
/*
* Boxes that need ACPI PCI IRQ routing disabled
*/
{
.callback = disable_acpi_irq,
.ident = "ASUS A7V",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC"),
DMI_MATCH(DMI_BOARD_NAME, "<A7V>"),
/* newer BIOS, Revision 1011, does work */
DMI_MATCH(DMI_BIOS_VERSION,
"ASUS A7V ACPI BIOS Revision 1007"),
},
},
{
/*
* Latest BIOS for IBM 600E (1.16) has bad pcinum
* for LPC bridge, which is needed for the PCI
* interrupt links to work. DSDT fix is in bug 5966.
* 2645, 2646 model numbers are shared with 600/600E/600X
*/
.callback = disable_acpi_irq,
.ident = "IBM Thinkpad 600 Series 2645",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
DMI_MATCH(DMI_BOARD_NAME, "2645"),
},
},
{
.callback = disable_acpi_irq,
.ident = "IBM Thinkpad 600 Series 2646",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
DMI_MATCH(DMI_BOARD_NAME, "2646"),
},
},
/*
* Boxes that need ACPI PCI IRQ routing and PCI scan disabled
*/
{ /* _BBN 0 bug */
.callback = disable_acpi_pci,
.ident = "ASUS PR-DLS",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
DMI_MATCH(DMI_BOARD_NAME, "PR-DLS"),
DMI_MATCH(DMI_BIOS_VERSION,
"ASUS PR-DLS ACPI BIOS Revision 1010"),
DMI_MATCH(DMI_BIOS_DATE, "03/21/2003")
},
},
{
.callback = disable_acpi_pci,
.ident = "Acer TravelMate 36x Laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"),
},
},
{}
};
/* second table for DMI checks that should run after early-quirks */
static struct dmi_system_id __initdata acpi_dmi_table_late[] = {
x86: fix C1E && nx6325 stability problem The problems are that, with the ACPI vs timer overring issue _fixed_, after using the box for some time (between several seconds and 1 hour, at random) processes get very high CPU loads (once I've got X using 107% of the CPU, for example) and the system becomes unresponsive, as though there were interrupts lost or something similar. Andreas Herrman reproduced similar problems: > Ok, now I've reproduced the stability problem. > - Using tip/master, > - reverting e38502eb8aa82314d5ab0eba45f50e6790dadd88 and > - applying your patch from this posting > http://marc.info/?l=linux-kernel&m=121539354224562&w=4 > > Starting X, firefox, gimp, tuxpaint and doing some drawing in tuxpaint > results in a slow system. Drawing is almost not possible anymore -- > Selections of new colors, cursors etc. is performed with huge delay > if it's performed at all. > > BTW, the code sets up timer IRQ as Virtual Wire IRQ: > > Jul 8 14:57:58 kodscha IO-APIC (apicid-pin) 2-22, 2-23 not connected. > Jul 8 14:57:58 kodscha ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 > Jul 8 14:57:58 kodscha ...trying to set up timer as Virtual Wire IRQ... works. > > and both INT0 and INT2 of IOAPIC are masked: > > Jul 8 14:57:58 kodscha NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect: > Jul 8 14:57:58 kodscha 00 000 1 0 0 0 0 0 0 00 > Jul 8 14:57:58 kodscha 01 003 0 0 0 0 0 1 1 31 > Jul 8 14:57:58 kodscha 02 003 1 0 0 0 0 0 0 30 > > I've also seen strange CPU utilization -- with syslog-ng: > > top - 15:33:06 up 35 min, 4 users, load average: 1.70, 0.68, 0.37 > Tasks: 64 total, 4 running, 60 sleeping, 0 stopped, 0 zombie > Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st > Cpu1 : 6.4%us, 87.2%sy, 0.0%ni, 5.8%id, 0.0%wa, 0.6%hi, 0.0%si, 0.0%st > Mem: 895384k total, 283568k used, 611816k free, 35492k buffers > Swap: 1959920k total, 0k used, 1959920k free, 163044k cached > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > 4632 root 20 0 17216 800 580 S 104 0.1 0:34.22 syslog-ng > 28505 root 20 0 205m 11m 4024 S 6 1.3 0:21.16 X > 28518 root 20 0 56292 5652 4492 S 1 0.6 0:01.80 fluxbox > 1 root 20 0 3724 608 508 S 0 0.1 0:00.36 init > > So far I have no clue why C1E-idle in conjunction with virtual wire > mode causes this strange behaviour. > > ... and I start to think about the root cause of all this. > > I've performed similar tests under X with the IRQ0/INT0 configuration and > I did not see above symptoms. So lets fall back to the IRQ0/INT0 configuration on this box. This basically restores the dont-use-the-lapic-timer exception mechanism that was unconditional on this box prior commit 8750bf5 ("x86: add C1E aware idle function"). Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 22:12:26 +08:00
/*
* HP laptops which use a DSDT reporting as HP/SB400/10000,
* which includes some code which overrides all temperature
* trip points to 16C if the INTIN2 input of the I/O APIC
* is enabled. This input is incorrectly designated the
* ISA IRQ 0 via an interrupt source override even though
* it is wired to the output of the master 8259A and INTIN0
* is not connected at all. Force ignoring BIOS IRQ0
x86: fix C1E && nx6325 stability problem The problems are that, with the ACPI vs timer overring issue _fixed_, after using the box for some time (between several seconds and 1 hour, at random) processes get very high CPU loads (once I've got X using 107% of the CPU, for example) and the system becomes unresponsive, as though there were interrupts lost or something similar. Andreas Herrman reproduced similar problems: > Ok, now I've reproduced the stability problem. > - Using tip/master, > - reverting e38502eb8aa82314d5ab0eba45f50e6790dadd88 and > - applying your patch from this posting > http://marc.info/?l=linux-kernel&m=121539354224562&w=4 > > Starting X, firefox, gimp, tuxpaint and doing some drawing in tuxpaint > results in a slow system. Drawing is almost not possible anymore -- > Selections of new colors, cursors etc. is performed with huge delay > if it's performed at all. > > BTW, the code sets up timer IRQ as Virtual Wire IRQ: > > Jul 8 14:57:58 kodscha IO-APIC (apicid-pin) 2-22, 2-23 not connected. > Jul 8 14:57:58 kodscha ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 > Jul 8 14:57:58 kodscha ...trying to set up timer as Virtual Wire IRQ... works. > > and both INT0 and INT2 of IOAPIC are masked: > > Jul 8 14:57:58 kodscha NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect: > Jul 8 14:57:58 kodscha 00 000 1 0 0 0 0 0 0 00 > Jul 8 14:57:58 kodscha 01 003 0 0 0 0 0 1 1 31 > Jul 8 14:57:58 kodscha 02 003 1 0 0 0 0 0 0 30 > > I've also seen strange CPU utilization -- with syslog-ng: > > top - 15:33:06 up 35 min, 4 users, load average: 1.70, 0.68, 0.37 > Tasks: 64 total, 4 running, 60 sleeping, 0 stopped, 0 zombie > Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st > Cpu1 : 6.4%us, 87.2%sy, 0.0%ni, 5.8%id, 0.0%wa, 0.6%hi, 0.0%si, 0.0%st > Mem: 895384k total, 283568k used, 611816k free, 35492k buffers > Swap: 1959920k total, 0k used, 1959920k free, 163044k cached > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > 4632 root 20 0 17216 800 580 S 104 0.1 0:34.22 syslog-ng > 28505 root 20 0 205m 11m 4024 S 6 1.3 0:21.16 X > 28518 root 20 0 56292 5652 4492 S 1 0.6 0:01.80 fluxbox > 1 root 20 0 3724 608 508 S 0 0.1 0:00.36 init > > So far I have no clue why C1E-idle in conjunction with virtual wire > mode causes this strange behaviour. > > ... and I start to think about the root cause of all this. > > I've performed similar tests under X with the IRQ0/INT0 configuration and > I did not see above symptoms. So lets fall back to the IRQ0/INT0 configuration on this box. This basically restores the dont-use-the-lapic-timer exception mechanism that was unconditional on this box prior commit 8750bf5 ("x86: add C1E aware idle function"). Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 22:12:26 +08:00
* override in that cases.
*/
x86 ACPI: Blacklist two HP machines with buggy BIOSes There is a bug in the BIOSes of some HP boxes with AMD Turions which connects IO-APIC pins with ACPI thermal trip points in such a way that if the state of the IO-APIC is not as expected by the (buggy) BIOS, the thermal trip points are set to insanely low values (usually all of them become 16 degrees Celsius). As a result, thermal throttling kicks in and knock the system down to its shoes. Unfortunately some of the recent IO-APIC changes made the bug show up. To prevent this from happening, blacklist machines that are known to be affected (nx6115 and 6715b in this particular case). This fixes http://bugzilla.kernel.org/show_bug.cgi?id=11516 listed as a regression from 2.6.26. On my box it was caused by: commit 691874fa96d6349a8b60f8ea9c2bae52ece79941 Author: Maciej W. Rozycki <macro@linux-mips.org> Date: Tue May 27 21:19:51 2008 +0100 x86: I/O APIC: timer through 8259A second-chance Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> and the whole story is described in this (huge) thread: http://marc.info/?l=linux-kernel&m=121358440508410&w=4 Matthew Garrett told us about that happening on the nx6125: http://marc.info/?l=linux-kernel&m=121396307411930&w=4 and then Maciej analysed the breakage on the basis of a DSDT from the nx6325: http://marc.info/?l=linux-kernel&m=121401068718826&w=4 As far as the Dmitry's and Jason's boxes are concerned, I recognized the symptoms and asked them to verify that the blacklisting helped. It appears that the buggy BIOS code has been copy-pasted to the entire range of machines, for no good reason. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Tested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Tested-by: Jason Vas Dias <jason.vas.dias@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-06 17:59:29 +08:00
{
.callback = dmi_ignore_irq0_timer_override,
.ident = "HP nx6115 laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6115"),
},
},
x86: fix C1E && nx6325 stability problem The problems are that, with the ACPI vs timer overring issue _fixed_, after using the box for some time (between several seconds and 1 hour, at random) processes get very high CPU loads (once I've got X using 107% of the CPU, for example) and the system becomes unresponsive, as though there were interrupts lost or something similar. Andreas Herrman reproduced similar problems: > Ok, now I've reproduced the stability problem. > - Using tip/master, > - reverting e38502eb8aa82314d5ab0eba45f50e6790dadd88 and > - applying your patch from this posting > http://marc.info/?l=linux-kernel&m=121539354224562&w=4 > > Starting X, firefox, gimp, tuxpaint and doing some drawing in tuxpaint > results in a slow system. Drawing is almost not possible anymore -- > Selections of new colors, cursors etc. is performed with huge delay > if it's performed at all. > > BTW, the code sets up timer IRQ as Virtual Wire IRQ: > > Jul 8 14:57:58 kodscha IO-APIC (apicid-pin) 2-22, 2-23 not connected. > Jul 8 14:57:58 kodscha ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 > Jul 8 14:57:58 kodscha ...trying to set up timer as Virtual Wire IRQ... works. > > and both INT0 and INT2 of IOAPIC are masked: > > Jul 8 14:57:58 kodscha NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect: > Jul 8 14:57:58 kodscha 00 000 1 0 0 0 0 0 0 00 > Jul 8 14:57:58 kodscha 01 003 0 0 0 0 0 1 1 31 > Jul 8 14:57:58 kodscha 02 003 1 0 0 0 0 0 0 30 > > I've also seen strange CPU utilization -- with syslog-ng: > > top - 15:33:06 up 35 min, 4 users, load average: 1.70, 0.68, 0.37 > Tasks: 64 total, 4 running, 60 sleeping, 0 stopped, 0 zombie > Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st > Cpu1 : 6.4%us, 87.2%sy, 0.0%ni, 5.8%id, 0.0%wa, 0.6%hi, 0.0%si, 0.0%st > Mem: 895384k total, 283568k used, 611816k free, 35492k buffers > Swap: 1959920k total, 0k used, 1959920k free, 163044k cached > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > 4632 root 20 0 17216 800 580 S 104 0.1 0:34.22 syslog-ng > 28505 root 20 0 205m 11m 4024 S 6 1.3 0:21.16 X > 28518 root 20 0 56292 5652 4492 S 1 0.6 0:01.80 fluxbox > 1 root 20 0 3724 608 508 S 0 0.1 0:00.36 init > > So far I have no clue why C1E-idle in conjunction with virtual wire > mode causes this strange behaviour. > > ... and I start to think about the root cause of all this. > > I've performed similar tests under X with the IRQ0/INT0 configuration and > I did not see above symptoms. So lets fall back to the IRQ0/INT0 configuration on this box. This basically restores the dont-use-the-lapic-timer exception mechanism that was unconditional on this box prior commit 8750bf5 ("x86: add C1E aware idle function"). Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 22:12:26 +08:00
{
.callback = dmi_ignore_irq0_timer_override,
.ident = "HP NX6125 laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6125"),
},
},
{
.callback = dmi_ignore_irq0_timer_override,
.ident = "HP NX6325 laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6325"),
},
},
x86 ACPI: Blacklist two HP machines with buggy BIOSes There is a bug in the BIOSes of some HP boxes with AMD Turions which connects IO-APIC pins with ACPI thermal trip points in such a way that if the state of the IO-APIC is not as expected by the (buggy) BIOS, the thermal trip points are set to insanely low values (usually all of them become 16 degrees Celsius). As a result, thermal throttling kicks in and knock the system down to its shoes. Unfortunately some of the recent IO-APIC changes made the bug show up. To prevent this from happening, blacklist machines that are known to be affected (nx6115 and 6715b in this particular case). This fixes http://bugzilla.kernel.org/show_bug.cgi?id=11516 listed as a regression from 2.6.26. On my box it was caused by: commit 691874fa96d6349a8b60f8ea9c2bae52ece79941 Author: Maciej W. Rozycki <macro@linux-mips.org> Date: Tue May 27 21:19:51 2008 +0100 x86: I/O APIC: timer through 8259A second-chance Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> and the whole story is described in this (huge) thread: http://marc.info/?l=linux-kernel&m=121358440508410&w=4 Matthew Garrett told us about that happening on the nx6125: http://marc.info/?l=linux-kernel&m=121396307411930&w=4 and then Maciej analysed the breakage on the basis of a DSDT from the nx6325: http://marc.info/?l=linux-kernel&m=121401068718826&w=4 As far as the Dmitry's and Jason's boxes are concerned, I recognized the symptoms and asked them to verify that the blacklisting helped. It appears that the buggy BIOS code has been copy-pasted to the entire range of machines, for no good reason. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Tested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Tested-by: Jason Vas Dias <jason.vas.dias@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-06 17:59:29 +08:00
{
.callback = dmi_ignore_irq0_timer_override,
.ident = "HP 6715b laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq 6715b"),
},
},
{
.callback = dmi_ignore_irq0_timer_override,
.ident = "FUJITSU SIEMENS",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"),
},
},
{}
};
/*
* acpi_boot_table_init() and acpi_boot_init()
* called from setup_arch(), always.
* 1. checksums all tables
* 2. enumerates lapics
* 3. enumerates io-apics
*
* acpi_table_init() is separate to allow reading SRAT without
* other side effects.
*
* side effects of acpi_boot_init:
* acpi_lapic = 1 if LAPIC found
* acpi_ioapic = 1 if IOAPIC found
* if (acpi_lapic && acpi_ioapic) smp_found_config = 1;
* if acpi_blacklisted() acpi_disabled = 1;
* acpi_irq_model=...
* ...
*/
void __init acpi_boot_table_init(void)
{
dmi_check_system(acpi_dmi_table);
/*
* If acpi_disabled, bail out
*/
if (acpi_disabled)
return;
/*
* Initialize the ACPI boot-time table parser.
*/
if (acpi_table_init()) {
disable_acpi();
return;
}
acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
/*
* blacklist may disable ACPI entirely
*/
if (acpi_blacklisted()) {
if (acpi_force) {
printk(KERN_WARNING PREFIX "acpi=force override\n");
} else {
printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
disable_acpi();
return;
}
}
}
int __init early_acpi_boot_init(void)
{
/*
* If acpi_disabled, bail out
*/
if (acpi_disabled)
return 1;
/*
* Process the Multiple APIC Description Table (MADT), if present
*/
early_acpi_process_madt();
return 0;
}
int __init acpi_boot_init(void)
{
/* those are executed after early-quirks are executed */
dmi_check_system(acpi_dmi_table_late);
/*
* If acpi_disabled, bail out
*/
if (acpi_disabled)
return 1;
acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
/*
* set sci_int and PM timer address
*/
acpi_table_parse(ACPI_SIG_FADT, acpi_parse_fadt);
/*
* Process the Multiple APIC Description Table (MADT), if present
*/
acpi_process_madt();
acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet);
if (!acpi_noirq)
x86_init.pci.init = pci_acpi_init;
return 0;
}
static int __init parse_acpi(char *arg)
{
if (!arg)
return -EINVAL;
/* "acpi=off" disables both ACPI table parsing and interpreter */
if (strcmp(arg, "off") == 0) {
disable_acpi();
}
/* acpi=force to over-ride black-list */
else if (strcmp(arg, "force") == 0) {
acpi_force = 1;
acpi_disabled = 0;
}
/* acpi=strict disables out-of-spec workarounds */
else if (strcmp(arg, "strict") == 0) {
acpi_strict = 1;
}
/* acpi=rsdt use RSDT instead of XSDT */
else if (strcmp(arg, "rsdt") == 0) {
acpi_rsdt_forced = 1;
}
/* "acpi=noirq" disables ACPI interrupt routing */
else if (strcmp(arg, "noirq") == 0) {
acpi_noirq_set();
}
/* "acpi=copy_dsdt" copys DSDT */
else if (strcmp(arg, "copy_dsdt") == 0) {
acpi_gbl_copy_dsdt_locally = 1;
} else {
/* Core will printk when we return error. */
return -EINVAL;
}
return 0;
}
early_param("acpi", parse_acpi);
/* FIXME: Using pci= for an ACPI parameter is a travesty. */
static int __init parse_pci(char *arg)
{
if (arg && strcmp(arg, "noacpi") == 0)
acpi_disable_pci();
return 0;
}
early_param("pci", parse_pci);
int __init acpi_mps_check(void)
{
#if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE)
/* mptable code is not built-in*/
if (acpi_disabled || acpi_noirq) {
printk(KERN_WARNING "MPS support code is not built-in.\n"
"Using acpi=off or acpi=noirq or pci=noacpi "
"may have problem\n");
return 1;
}
#endif
return 0;
}
#ifdef CONFIG_X86_IO_APIC
static int __init parse_acpi_skip_timer_override(char *arg)
{
acpi_skip_timer_override = 1;
return 0;
}
early_param("acpi_skip_timer_override", parse_acpi_skip_timer_override);
static int __init parse_acpi_use_timer_override(char *arg)
{
acpi_use_timer_override = 1;
return 0;
}
early_param("acpi_use_timer_override", parse_acpi_use_timer_override);
#endif /* CONFIG_X86_IO_APIC */
static int __init setup_acpi_sci(char *s)
{
if (!s)
return -EINVAL;
if (!strcmp(s, "edge"))
acpi_sci_flags = ACPI_MADT_TRIGGER_EDGE |
(acpi_sci_flags & ~ACPI_MADT_TRIGGER_MASK);
else if (!strcmp(s, "level"))
acpi_sci_flags = ACPI_MADT_TRIGGER_LEVEL |
(acpi_sci_flags & ~ACPI_MADT_TRIGGER_MASK);
else if (!strcmp(s, "high"))
acpi_sci_flags = ACPI_MADT_POLARITY_ACTIVE_HIGH |
(acpi_sci_flags & ~ACPI_MADT_POLARITY_MASK);
else if (!strcmp(s, "low"))
acpi_sci_flags = ACPI_MADT_POLARITY_ACTIVE_LOW |
(acpi_sci_flags & ~ACPI_MADT_POLARITY_MASK);
else
return -EINVAL;
return 0;
}
early_param("acpi_sci", setup_acpi_sci);
int __acpi_acquire_global_lock(unsigned int *lock)
{
unsigned int old, new, val;
do {
old = *lock;
new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1));
val = cmpxchg(lock, old, new);
} while (unlikely (val != old));
return (new < 3) ? -1 : 0;
}
int __acpi_release_global_lock(unsigned int *lock)
{
unsigned int old, new, val;
do {
old = *lock;
new = old & ~0x3;
val = cmpxchg(lock, old, new);
} while (unlikely (val != old));
return old & 0x1;
}