![David Rientjes](/assets/img/avatar_default.png)
NUMA boot code assumes that physical node ids start at 0, but the DIMMs that the apic id represents may not be reachable. If this is the case, node 0 is never online and cpus never end up getting appropriately assigned to a node. This causes the cpumask of all online nodes to be empty and machines crash with kernel code assuming online nodes have valid cpus. The fix is to appropriately map all the address ranges for physical nodes and ensure the cpu to node mapping function checks all possible nodes (up to MAX_NUMNODES) instead of simply checking nodes 0-N, where N is the number of physical nodes, for valid address ranges. This requires no longer "compressing" the address ranges of nodes in the physical node map from 0-N, but rather leave indices in physnodes[] to represent the actual node id of the physical node. Accordingly, the topology exported by both amd_get_nodes() and acpi_get_nodes() no longer must return the number of nodes to iterate through; all such iterations will now be to MAX_NUMNODES. This change also passes the end address of system RAM (which may be different from normal operation if mem= is specified on the command line) before the physnodes[] array is populated. ACPI parsed nodes are truncated to fit within the address range that respect the mem= boundaries and even some physical nodes may become unreachable in such cases. When NUMA emulation does succeed, any apicid to node mapping that exists for unreachable nodes are given default values so that proximity domains can still be assigned. This is important for node_distance() to function as desired. Signed-off-by: David Rientjes <rientjes@google.com> LKML-Reference: <alpine.DEB.2.00.1012221702090.3701@chino.kir.corp.google.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
202 lines
5.3 KiB
C
202 lines
5.3 KiB
C
#ifndef _ASM_X86_ACPI_H
|
|
#define _ASM_X86_ACPI_H
|
|
|
|
/*
|
|
* Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
|
|
* Copyright (C) 2001 Patrick Mochel <mochel@osdl.org>
|
|
*
|
|
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
*
|
|
* 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 <acpi/pdc_intel.h>
|
|
|
|
#include <asm/numa.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/mmu.h>
|
|
#include <asm/mpspec.h>
|
|
|
|
#define COMPILER_DEPENDENT_INT64 long long
|
|
#define COMPILER_DEPENDENT_UINT64 unsigned long long
|
|
|
|
/*
|
|
* Calling conventions:
|
|
*
|
|
* ACPI_SYSTEM_XFACE - Interfaces to host OS (handlers, threads)
|
|
* ACPI_EXTERNAL_XFACE - External ACPI interfaces
|
|
* ACPI_INTERNAL_XFACE - Internal ACPI interfaces
|
|
* ACPI_INTERNAL_VAR_XFACE - Internal variable-parameter list interfaces
|
|
*/
|
|
#define ACPI_SYSTEM_XFACE
|
|
#define ACPI_EXTERNAL_XFACE
|
|
#define ACPI_INTERNAL_XFACE
|
|
#define ACPI_INTERNAL_VAR_XFACE
|
|
|
|
/* Asm macros */
|
|
|
|
#define ACPI_ASM_MACROS
|
|
#define BREAKPOINT3
|
|
#define ACPI_DISABLE_IRQS() local_irq_disable()
|
|
#define ACPI_ENABLE_IRQS() local_irq_enable()
|
|
#define ACPI_FLUSH_CPU_CACHE() wbinvd()
|
|
|
|
int __acpi_acquire_global_lock(unsigned int *lock);
|
|
int __acpi_release_global_lock(unsigned int *lock);
|
|
|
|
#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
|
|
((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
|
|
|
|
#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
|
|
((Acq) = __acpi_release_global_lock(&facs->global_lock))
|
|
|
|
/*
|
|
* Math helper asm macros
|
|
*/
|
|
#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
|
|
asm("divl %2;" \
|
|
: "=a"(q32), "=d"(r32) \
|
|
: "r"(d32), \
|
|
"0"(n_lo), "1"(n_hi))
|
|
|
|
|
|
#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
|
|
asm("shrl $1,%2 ;" \
|
|
"rcrl $1,%3;" \
|
|
: "=r"(n_hi), "=r"(n_lo) \
|
|
: "0"(n_hi), "1"(n_lo))
|
|
|
|
#ifdef CONFIG_ACPI
|
|
extern int acpi_lapic;
|
|
extern int acpi_ioapic;
|
|
extern int acpi_noirq;
|
|
extern int acpi_strict;
|
|
extern int acpi_disabled;
|
|
extern int acpi_pci_disabled;
|
|
extern int acpi_skip_timer_override;
|
|
extern int acpi_use_timer_override;
|
|
|
|
extern u8 acpi_sci_flags;
|
|
extern int acpi_sci_override_gsi;
|
|
void acpi_pic_sci_set_trigger(unsigned int, u16);
|
|
|
|
extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
|
|
int trigger, int polarity);
|
|
|
|
static inline void disable_acpi(void)
|
|
{
|
|
acpi_disabled = 1;
|
|
acpi_pci_disabled = 1;
|
|
acpi_noirq = 1;
|
|
}
|
|
|
|
extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
|
|
|
|
static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
|
|
static inline void acpi_disable_pci(void)
|
|
{
|
|
acpi_pci_disabled = 1;
|
|
acpi_noirq_set();
|
|
}
|
|
|
|
/* routines for saving/restoring kernel state */
|
|
extern int acpi_save_state_mem(void);
|
|
extern void acpi_restore_state_mem(void);
|
|
|
|
extern unsigned long acpi_wakeup_address;
|
|
|
|
/* early initialization routine */
|
|
extern void acpi_reserve_wakeup_memory(void);
|
|
|
|
/*
|
|
* Check if the CPU can handle C2 and deeper
|
|
*/
|
|
static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
|
|
{
|
|
/*
|
|
* Early models (<=5) of AMD Opterons are not supposed to go into
|
|
* C2 state.
|
|
*
|
|
* Steppings 0x0A and later are good
|
|
*/
|
|
if (boot_cpu_data.x86 == 0x0F &&
|
|
boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
|
|
boot_cpu_data.x86_model <= 0x05 &&
|
|
boot_cpu_data.x86_mask < 0x0A)
|
|
return 1;
|
|
else if (c1e_detected)
|
|
return 1;
|
|
else
|
|
return max_cstate;
|
|
}
|
|
|
|
static inline bool arch_has_acpi_pdc(void)
|
|
{
|
|
struct cpuinfo_x86 *c = &cpu_data(0);
|
|
return (c->x86_vendor == X86_VENDOR_INTEL ||
|
|
c->x86_vendor == X86_VENDOR_CENTAUR);
|
|
}
|
|
|
|
static inline void arch_acpi_set_pdc_bits(u32 *buf)
|
|
{
|
|
struct cpuinfo_x86 *c = &cpu_data(0);
|
|
|
|
buf[2] |= ACPI_PDC_C_CAPABILITY_SMP;
|
|
|
|
if (cpu_has(c, X86_FEATURE_EST))
|
|
buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
|
|
|
|
if (cpu_has(c, X86_FEATURE_ACPI))
|
|
buf[2] |= ACPI_PDC_T_FFH;
|
|
|
|
/*
|
|
* If mwait/monitor is unsupported, C2/C3_FFH will be disabled
|
|
*/
|
|
if (!cpu_has(c, X86_FEATURE_MWAIT))
|
|
buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
|
|
}
|
|
|
|
#else /* !CONFIG_ACPI */
|
|
|
|
#define acpi_lapic 0
|
|
#define acpi_ioapic 0
|
|
static inline void acpi_noirq_set(void) { }
|
|
static inline void acpi_disable_pci(void) { }
|
|
static inline void disable_acpi(void) { }
|
|
|
|
#endif /* !CONFIG_ACPI */
|
|
|
|
#define ARCH_HAS_POWER_INIT 1
|
|
|
|
struct bootnode;
|
|
|
|
#ifdef CONFIG_ACPI_NUMA
|
|
extern int acpi_numa;
|
|
extern void acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
|
|
unsigned long end);
|
|
extern int acpi_scan_nodes(unsigned long start, unsigned long end);
|
|
#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
|
|
|
|
#ifdef CONFIG_NUMA_EMU
|
|
extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
|
|
int num_nodes);
|
|
#endif
|
|
#endif /* CONFIG_ACPI_NUMA */
|
|
|
|
#define acpi_unlazy_tlb(x) leave_mm(x)
|
|
|
|
#endif /* _ASM_X86_ACPI_H */
|