* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (50 commits)
x86, mm: Allow ZONE_DMA to be configurable
x86, NUMA: Trim numa meminfo with max_pfn in a separate loop
x86, NUMA: Rename setup_node_bootmem() to setup_node_data()
x86, NUMA: Enable emulation on 32bit too
x86, NUMA: Enable CONFIG_AMD_NUMA on 32bit too
x86, NUMA: Rename amdtopology_64.c to amdtopology.c
x86, NUMA: Make numa_init_array() static
x86, NUMA: Make 32bit use common NUMA init path
x86, NUMA: Initialize and use remap allocator from setup_node_bootmem()
x86-32, NUMA: Add @start and @end to init_alloc_remap()
x86, NUMA: Remove long 64bit assumption from numa.c
x86, NUMA: Enable build of generic NUMA init code on 32bit
x86, NUMA: Move NUMA init logic from numa_64.c to numa.c
x86-32, NUMA: Update numaq to use new NUMA init protocol
x86-32, NUMA: Replace srat_32.c with srat.c
x86-32, NUMA: implement temporary NUMA init shims
x86, NUMA: Move numa_nodes_parsed to numa.[hc]
x86-32, NUMA: Move get_memcfg_numa() into numa_32.c
x86, NUMA: make srat.c 32bit safe
x86, NUMA: rename srat_64.c to srat.c
...
config X86_32
def_bool !64BIT
+ select CLKSRC_I8253
config X86_64
def_bool 64BIT
select GENERIC_IRQ_SHOW
select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
- select ARCH_NO_SYSDEV_OPS
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
def_bool y
config ZONE_DMA
- def_bool y
+ bool "DMA memory allocation support" if EXPERT
+ default y
+ help
+ DMA memory allocation support allows devices with less than 32-bit
+ addressing to allocate within the first 16MB of address space.
+ Disable if no such devices will be used.
+
+ If unsure, say Y.
config SBUS
bool
# Following is an alphabetically sorted list of 32 bit extended platforms
# Please maintain the alphabetic order if and when there are additions
-config X86_ELAN
- bool "AMD Elan"
- depends on X86_32
- depends on X86_EXTENDED_PLATFORM
- ---help---
- Select this for an AMD Elan processor.
-
- Do not use this option for K6/Athlon/Opteron processors!
-
- If unsure, choose "PC-compatible" instead.
-
config X86_INTEL_CE
bool "CE4100 TV platform"
depends on PCI
bool "AMD IOMMU support"
select SWIOTLB
select PCI_MSI
+ select PCI_IOV
depends on X86_64 && PCI && ACPI
---help---
With this option you can enable support for AMD IOMMU hardware in
config AMD_NUMA
def_bool y
prompt "Old style AMD Opteron NUMA detection"
- depends on X86_64 && NUMA && PCI
+ depends on NUMA && PCI
---help---
Enable AMD NUMA node topology detection. You should say Y here if
you have a multi processor AMD system. This uses an old method to
config NUMA_EMU
bool "NUMA emulation"
- depends on X86_64 && NUMA
+ depends on NUMA
---help---
Enable NUMA emulation. A flat machine will be split
into virtual nodes when booted with "numa=fake=N", where N is the
def_bool y
depends on X86_32 && NUMA
+ config HAVE_ARCH_ALLOC_REMAP
+ def_bool y
+ depends on X86_32 && NUMA
+
config ARCH_HAVE_MEMORY_PRESENT
def_bool y
depends on X86_32 && DISCONTIGMEM
def_bool y
depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
- config HAVE_ARCH_ALLOC_REMAP
- def_bool y
- depends on X86_32 && NUMA
-
config ARCH_FLATMEM_ENABLE
def_bool y
- depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
+ depends on X86_32 && !NUMA
config ARCH_DISCONTIGMEM_ENABLE
def_bool y
def_bool y
depends on NUMA && X86_32
- config ARCH_PROC_KCORE_TEXT
- def_bool y
- depends on X86_64 && PROC_KCORE
-
- config ARCH_SPARSEMEM_DEFAULT
- def_bool y
- depends on X86_64
-
config ARCH_SPARSEMEM_ENABLE
def_bool y
depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
select SPARSEMEM_STATIC if X86_32
select SPARSEMEM_VMEMMAP_ENABLE if X86_64
+ config ARCH_SPARSEMEM_DEFAULT
+ def_bool y
+ depends on X86_64
+
config ARCH_SELECT_MEMORY_MODEL
def_bool y
depends on ARCH_SPARSEMEM_ENABLE
def_bool X86_64
depends on MEMORY_HOTPLUG
+ config ARCH_PROC_KCORE_TEXT
+ def_bool y
+ depends on X86_64 && PROC_KCORE
+
config ILLEGAL_POINTER_VALUE
hex
default 0 if X86_32
def_bool y
depends on MEMORY_HOTPLUG
- config HAVE_ARCH_EARLY_PFN_TO_NID
- def_bool X86_64
- depends on NUMA
-
config USE_PERCPU_NUMA_NODE_ID
def_bool y
depends on NUMA
endif # APM
-source "arch/x86/kernel/cpu/cpufreq/Kconfig"
+source "drivers/cpufreq/Kconfig"
source "drivers/cpuidle/Kconfig"
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
#define test_cpu_cap(c, bit) \
test_bit(bit, (unsigned long *)((c)->x86_capability))
- #define cpu_has(c, bit) \
- (__builtin_constant_p(bit) && \
+ #define REQUIRED_MASK_BIT_SET(bit) \
( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) || \
(((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) || \
(((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) || \
(((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \
(((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \
(((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \
- (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \
- ? 1 : \
+ (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+ #define cpu_has(c, bit) \
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
test_cpu_cap(c, bit))
+ #define this_cpu_has(bit) \
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
+ x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit)
#define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability))
typeof(o2) __o2 = o2; \
typeof(o2) __n2 = n2; \
typeof(o2) __dummy; \
- alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4, \
+ alternative_io("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4, \
"cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \
X86_FEATURE_CX16, \
ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \
old__; \
})
+ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+ const unsigned long __percpu *addr)
+ {
+ unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+
+ return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0;
+ }
+
+ static inline int x86_this_cpu_variable_test_bit(int nr,
+ const unsigned long __percpu *addr)
+ {
+ int oldbit;
+
+ asm volatile("bt "__percpu_arg(2)",%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit)
+ : "m" (*(unsigned long *)addr), "Ir" (nr));
+
+ return oldbit;
+ }
+
+ #define x86_this_cpu_test_bit(nr, addr) \
+ (__builtin_constant_p((nr)) \
+ ? x86_this_cpu_constant_test_bit((nr), (addr)) \
+ : x86_this_cpu_variable_test_bit((nr), (addr)))
+
+
#include <asm-generic/percpu.h>
/* We can use this directly for local CPU (faster). */
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
- if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_ARAT)) {
+ if (this_cpu_has(X86_FEATURE_ARAT)) {
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
/* Make LAPIC timer preferrable over percpu HPET */
lapic_clockevent.rating = 150;
/* always use the value from LDR */
early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
logical_smp_processor_id();
+
+ /*
+ * Some NUMA implementations (NUMAQ) don't initialize apicid to
+ * node mapping during NUMA init. Now that logical apicid is
+ * guaranteed to be known, give it another chance. This is already
+ * a bit too late - percpu allocation has already happened without
+ * proper NUMA affinity.
+ */
+ if (apic->x86_32_numa_cpu_node)
+ set_apicid_to_node(early_per_cpu(x86_cpu_to_apicid, cpu),
+ apic->x86_32_numa_cpu_node(cpu));
#endif
/*
*/
void smp_error_interrupt(struct pt_regs *regs)
{
- u32 v, v1;
+ u32 v0, v1;
+ u32 i = 0;
+ static const char * const error_interrupt_reason[] = {
+ "Send CS error", /* APIC Error Bit 0 */
+ "Receive CS error", /* APIC Error Bit 1 */
+ "Send accept error", /* APIC Error Bit 2 */
+ "Receive accept error", /* APIC Error Bit 3 */
+ "Redirectable IPI", /* APIC Error Bit 4 */
+ "Send illegal vector", /* APIC Error Bit 5 */
+ "Received illegal vector", /* APIC Error Bit 6 */
+ "Illegal register address", /* APIC Error Bit 7 */
+ };
exit_idle();
irq_enter();
/* First tickle the hardware, only then report what went on. -- REW */
- v = apic_read(APIC_ESR);
+ v0 = apic_read(APIC_ESR);
apic_write(APIC_ESR, 0);
v1 = apic_read(APIC_ESR);
ack_APIC_irq();
atomic_inc(&irq_err_count);
- /*
- * Here is what the APIC error bits mean:
- * 0: Send CS error
- * 1: Receive CS error
- * 2: Send accept error
- * 3: Receive accept error
- * 4: Reserved
- * 5: Send illegal vector
- * 6: Received illegal vector
- * 7: Illegal register address
- */
- pr_debug("APIC error on CPU%d: %02x(%02x)\n",
- smp_processor_id(), v , v1);
+ apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)",
+ smp_processor_id(), v0 , v1);
+
+ v1 = v1 & 0xff;
+ while (v1) {
+ if (v1 & 0x1)
+ apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
+ i++;
+ v1 >>= 1;
+ };
+
+ apic_printk(APIC_DEBUG, KERN_CONT "\n");
+
irq_exit();
}
apic_write(APIC_LDR, val);
}
- #ifdef CONFIG_X86_32
- int default_x86_32_numa_cpu_node(int cpu)
- {
- #ifdef CONFIG_NUMA
- int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-
- if (apicid != BAD_APICID)
- return __apicid_to_node[apicid];
- return NUMA_NO_NODE;
- #else
- return 0;
- #endif
- }
- #endif
-
/*
* Power management
*/
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
-
- add_taint(TAINT_MACHINE_CHECK);
return 1;
}
if (old_event) {
static void intel_thermal_interrupt(void)
{
__u64 msr_val;
- struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
CORE_LEVEL) != 0)
mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
- if (cpu_has(c, X86_FEATURE_PLN))
+ if (this_cpu_has(X86_FEATURE_PLN))
if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
POWER_LIMIT_EVENT,
CORE_LEVEL) != 0)
mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
- if (cpu_has(c, X86_FEATURE_PTS)) {
+ if (this_cpu_has(X86_FEATURE_PTS)) {
rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
THERMAL_THROTTLING_EVENT,
PACKAGE_LEVEL) != 0)
mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
- if (cpu_has(c, X86_FEATURE_PLN))
+ if (this_cpu_has(X86_FEATURE_PLN))
if (therm_throt_process(msr_val &
PACKAGE_THERM_STATUS_POWER_LIMIT,
POWER_LIMIT_EVENT,
{
printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
smp_processor_id());
- add_taint(TAINT_MACHINE_CHECK);
}
static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+ h = lvtthmr_init;
/*
* The initial value of thermal LVT entries on all APs always reads
* 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
* sequence to them and LVT registers are reset to 0s except for
* the mask bits which are set to 1s when APs receive INIT IPI.
- * Always restore the value that BIOS has programmed on AP based on
- * BSP's info we saved since BIOS is always setting the same value
- * for all threads/cores
+ * If BIOS takes over the thermal interrupt and sets its interrupt
+ * delivery mode to SMI (not fixed), it restores the value that the
+ * BIOS has programmed on AP based on BSP's info we saved since BIOS
+ * is always setting the same value for all threads/cores.
*/
- apic_write(APIC_LVTTHMR, lvtthmr_init);
+ if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
+ apic_write(APIC_LVTTHMR, lvtthmr_init);
- h = lvtthmr_init;
if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG
}
}
- static int
+ static int __init
check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
{
- int ret = 0;
-
if (!mpc_new_phys || count <= mpc_new_length) {
WARN(1, "update_mptable: No spare slots (length: %x)\n", count);
return -1;
}
- return ret;
+ return 0;
}
#else /* CONFIG_X86_IO_APIC */
static