summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile12
-rw-r--r--arch/x86/kernel/acpi/boot.c22
-rw-r--r--arch/x86/kernel/acpi/realmode/wakeup.S21
-rw-r--r--arch/x86/kernel/acpi/realmode/wakeup.h5
-rw-r--r--arch/x86/kernel/acpi/realmode/wakeup.lds.S28
-rw-r--r--arch/x86/kernel/acpi/sleep.c77
-rw-r--r--arch/x86/kernel/acpi/sleep.h5
-rw-r--r--arch/x86/kernel/acpi/wakeup_rm.S12
-rw-r--r--arch/x86/kernel/alternative.c11
-rw-r--r--arch/x86/kernel/amd_iommu_init.c26
-rw-r--r--arch/x86/kernel/amd_nb.c102
-rw-r--r--arch/x86/kernel/apb_timer.c64
-rw-r--r--arch/x86/kernel/aperture_64.c37
-rw-r--r--arch/x86/kernel/apic/apic.c192
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c4
-rw-r--r--arch/x86/kernel/apic/apic_noop.c26
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c34
-rw-r--r--arch/x86/kernel/apic/es7000_32.c35
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c494
-rw-r--r--arch/x86/kernel/apic/ipi.c12
-rw-r--r--arch/x86/kernel/apic/numaq_32.c21
-rw-r--r--arch/x86/kernel/apic/probe_32.c10
-rw-r--r--arch/x86/kernel/apic/summit_32.c47
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c60
-rw-r--r--arch/x86/kernel/apm_32.c24
-rw-r--r--arch/x86/kernel/asm-offsets.c65
-rw-r--r--arch/x86/kernel/asm-offsets_32.c69
-rw-r--r--arch/x86/kernel/asm-offsets_64.c90
-rw-r--r--arch/x86/kernel/check.c8
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/amd.c84
-rw-r--r--arch/x86/kernel/cpu/common.c6
-rw-r--r--arch/x86/kernel/cpu/cpufreq/Kconfig266
-rw-r--r--arch/x86/kernel/cpu/cpufreq/Makefile21
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c776
-rw-r--r--arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c446
-rw-r--r--arch/x86/kernel/cpu/cpufreq/e_powersaver.c367
-rw-r--r--arch/x86/kernel/cpu/cpufreq/elanfreq.c309
-rw-r--r--arch/x86/kernel/cpu/cpufreq/gx-suspmod.c517
-rw-r--r--arch/x86/kernel/cpu/cpufreq/longhaul.c1029
-rw-r--r--arch/x86/kernel/cpu/cpufreq/longhaul.h353
-rw-r--r--arch/x86/kernel/cpu/cpufreq/longrun.c327
-rw-r--r--arch/x86/kernel/cpu/cpufreq/mperf.c51
-rw-r--r--arch/x86/kernel/cpu/cpufreq/mperf.h9
-rw-r--r--arch/x86/kernel/cpu/cpufreq/p4-clockmod.c331
-rw-r--r--arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c626
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k6.c261
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k7.c752
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k7.h43
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c1601
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.h224
-rw-r--r--arch/x86/kernel/cpu/cpufreq/sc520_freq.c194
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c636
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-ich.c452
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-lib.c481
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-lib.h49
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-smi.c467
-rw-r--r--arch/x86/kernel/cpu/intel.c5
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c80
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c42
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c25
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c8
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c12
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c30
-rw-r--r--arch/x86/kernel/cpu/perf_event.c199
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c191
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c472
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c83
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c47
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c4
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c4
-rw-r--r--arch/x86/kernel/cpu/vmware.c2
-rw-r--r--arch/x86/kernel/crash_dump_32.c3
-rw-r--r--arch/x86/kernel/crash_dump_64.c3
-rw-r--r--arch/x86/kernel/devicetree.c439
-rw-r--r--arch/x86/kernel/dumpstack.c51
-rw-r--r--arch/x86/kernel/dumpstack_32.c15
-rw-r--r--arch/x86/kernel/dumpstack_64.c14
-rw-r--r--arch/x86/kernel/e820.c19
-rw-r--r--arch/x86/kernel/early-quirks.c21
-rw-r--r--arch/x86/kernel/entry_32.S13
-rw-r--r--arch/x86/kernel/entry_64.S17
-rw-r--r--arch/x86/kernel/ftrace.c15
-rw-r--r--arch/x86/kernel/head32.c9
-rw-r--r--arch/x86/kernel/head64.c3
-rw-r--r--arch/x86/kernel/head_32.S10
-rw-r--r--arch/x86/kernel/head_64.S3
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/i387.c2
-rw-r--r--arch/x86/kernel/i8237.c30
-rw-r--r--arch/x86/kernel/i8259.c35
-rw-r--r--arch/x86/kernel/ioport.c20
-rw-r--r--arch/x86/kernel/irq.c93
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/irqinit.c92
-rw-r--r--arch/x86/kernel/kgdb.c15
-rw-r--r--arch/x86/kernel/kprobes.c13
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kernel/mca_32.c2
-rw-r--r--arch/x86/kernel/microcode_amd.c188
-rw-r--r--arch/x86/kernel/microcode_core.c41
-rw-r--r--arch/x86/kernel/mpparse.c12
-rw-r--r--arch/x86/kernel/pci-calgary_64.c4
-rw-r--r--arch/x86/kernel/pci-gart_64.c41
-rw-r--r--arch/x86/kernel/process.c23
-rw-r--r--arch/x86/kernel/process_64.c8
-rw-r--r--arch/x86/kernel/ptrace.c36
-rw-r--r--arch/x86/kernel/reboot.c129
-rw-r--r--arch/x86/kernel/reboot_32.S135
-rw-r--r--arch/x86/kernel/rtc.c3
-rw-r--r--arch/x86/kernel/setup.c93
-rw-r--r--arch/x86/kernel/setup_percpu.c11
-rw-r--r--arch/x86/kernel/smpboot.c138
-rw-r--r--arch/x86/kernel/stacktrace.c6
-rw-r--r--arch/x86/kernel/step.c2
-rw-r--r--arch/x86/kernel/syscall_table_32.S4
-rw-r--r--arch/x86/kernel/topology.c2
-rw-r--r--arch/x86/kernel/trampoline.c42
-rw-r--r--arch/x86/kernel/trampoline_32.S15
-rw-r--r--arch/x86/kernel/trampoline_64.S28
-rw-r--r--arch/x86/kernel/tsc.c4
-rw-r--r--arch/x86/kernel/verify_cpu.S2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S18
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c1
-rw-r--r--arch/x86/kernel/x86_init.c5
-rw-r--r--arch/x86/kernel/xsave.c2
131 files changed, 3019 insertions, 12423 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 34244b2cd88..7338ef2218b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -41,13 +41,13 @@ obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
obj-y += bootflag.o e820.o
-obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
+obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
obj-y += tsc.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
-obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o
+obj-y += trampoline.o trampoline_$(BITS).o
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
@@ -55,10 +55,12 @@ obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
obj-y += step.o
obj-$(CONFIG_INTEL_TXT) += tboot.o
+obj-$(CONFIG_ISA_DMA_API) += i8237.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += cpu/
obj-y += acpi/
obj-y += reboot.o
+obj-$(CONFIG_X86_32) += reboot_32.o
obj-$(CONFIG_MCA) += mca_32.o
obj-$(CONFIG_X86_MSR) += msr.o
obj-$(CONFIG_X86_CPUID) += cpuid.o
@@ -66,10 +68,9 @@ obj-$(CONFIG_PCI) += early-quirks.o
apm-y := apm_32.o
obj-$(CONFIG_APM) += apm.o
obj-$(CONFIG_SMP) += smp.o
-obj-$(CONFIG_SMP) += smpboot.o tsc_sync.o
+obj-$(CONFIG_SMP) += smpboot.o
+obj-$(CONFIG_SMP) += tsc_sync.o
obj-$(CONFIG_SMP) += setup_percpu.o
-obj-$(CONFIG_X86_64_SMP) += tsc_sync.o
-obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o
obj-$(CONFIG_X86_MPPARSE) += mpparse.o
obj-y += apic/
obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
@@ -109,6 +110,7 @@ obj-$(CONFIG_MICROCODE) += microcode.o
obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
+obj-$(CONFIG_OF) += devicetree.o
###
# 64 bit specific files
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b3a71137983..9a966c579af 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -72,6 +72,7 @@ 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;
@@ -415,10 +416,15 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
return 0;
}
- if (acpi_skip_timer_override &&
- intsrc->source_irq == 0 && intsrc->global_irq == 2) {
- printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n");
- return 0;
+ if (intsrc->source_irq == 0 && intsrc->global_irq == 2) {
+ if (acpi_skip_timer_override) {
+ printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n");
+ return 0;
+ }
+ if (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,
@@ -589,14 +595,8 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
nid = acpi_get_node(handle);
if (nid == -1 || !node_online(nid))
return;
-#ifdef CONFIG_X86_64
- apicid_to_node[physid] = nid;
+ set_apicid_to_node(physid, nid);
numa_set_node(cpu, nid);
-#else /* CONFIG_X86_32 */
- apicid_2_node[physid] = nid;
- cpu_to_node_map[cpu] = nid;
-#endif
-
#endif
}
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index 28595d6df47..ead21b66311 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -6,11 +6,17 @@
#include <asm/page_types.h>
#include <asm/pgtable_types.h>
#include <asm/processor-flags.h>
+#include "wakeup.h"
.code16
- .section ".header", "a"
+ .section ".jump", "ax"
+ .globl _start
+_start:
+ cli
+ jmp wakeup_code
/* This should match the structure in wakeup.h */
+ .section ".header", "a"
.globl wakeup_header
wakeup_header:
video_mode: .short 0 /* Video mode number */
@@ -30,14 +36,11 @@ wakeup_jmp: .byte 0xea /* ljmpw */
wakeup_jmp_off: .word 3f
wakeup_jmp_seg: .word 0
wakeup_gdt: .quad 0, 0, 0
-signature: .long 0x51ee1111
+signature: .long WAKEUP_HEADER_SIGNATURE
.text
- .globl _start
.code16
wakeup_code:
-_start:
- cli
cld
/* Apparently some dimwit BIOS programmers don't know how to
@@ -77,12 +80,12 @@ _start:
/* Check header signature... */
movl signature, %eax
- cmpl $0x51ee1111, %eax
+ cmpl $WAKEUP_HEADER_SIGNATURE, %eax
jne bogus_real_magic
/* Check we really have everything... */
movl end_signature, %eax
- cmpl $0x65a22c82, %eax
+ cmpl $WAKEUP_END_SIGNATURE, %eax
jne bogus_real_magic
/* Call the C code */
@@ -147,3 +150,7 @@ wakeup_heap:
wakeup_stack:
.space 2048
wakeup_stack_end:
+
+ .section ".signature","a"
+end_signature:
+ .long WAKEUP_END_SIGNATURE
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h
index 69d38d0b2b6..e1828c07e79 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.h
+++ b/arch/x86/kernel/acpi/realmode/wakeup.h
@@ -35,7 +35,8 @@ struct wakeup_header {
extern struct wakeup_header wakeup_header;
#endif
-#define HEADER_OFFSET 0x3f00
-#define WAKEUP_SIZE 0x4000
+#define WAKEUP_HEADER_OFFSET 8
+#define WAKEUP_HEADER_SIGNATURE 0x51ee1111
+#define WAKEUP_END_SIGNATURE 0x65a22c82
#endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 060fff8f5c5..d4f8010a5b1 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -13,9 +13,19 @@ ENTRY(_start)
SECTIONS
{
. = 0;
+ .jump : {
+ *(.jump)
+ } = 0x90909090
+
+ . = WAKEUP_HEADER_OFFSET;
+ .header : {
+ *(.header)
+ }
+
+ . = ALIGN(16);
.text : {
*(.text*)
- }
+ } = 0x90909090
. = ALIGN(16);
.rodata : {
@@ -33,11 +43,6 @@ SECTIONS
*(.data*)
}
- .signature : {
- end_signature = .;
- LONG(0x65a22c82)
- }
-
. = ALIGN(16);
.bss : {
__bss_start = .;
@@ -45,20 +50,13 @@ SECTIONS
__bss_end = .;
}
- . = HEADER_OFFSET;
- .header : {
- *(.header)
+ .signature : {
+ *(.signature)
}
- . = ALIGN(16);
_end = .;
/DISCARD/ : {
*(.note*)
}
-
- /*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
- */
- . = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!");
}
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 68d1537b8c8..ff93bc1b09c 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -18,37 +18,28 @@
#include "realmode/wakeup.h"
#include "sleep.h"
-unsigned long acpi_wakeup_address;
unsigned long acpi_realmode_flags;
-/* address in low memory of the wakeup routine. */
-static unsigned long acpi_realmode;
-
#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
static char temp_stack[4096];
#endif
/**
- * acpi_save_state_mem - save kernel state
+ * acpi_suspend_lowlevel - save kernel state
*
* Create an identity mapped page table and copy the wakeup routine to
* low memory.
- *
- * Note that this is too late to change acpi_wakeup_address.
*/
-int acpi_save_state_mem(void)
+int acpi_suspend_lowlevel(void)
{
struct wakeup_header *header;
+ /* address in low memory of the wakeup routine. */
+ char *acpi_realmode;
- if (!acpi_realmode) {
- printk(KERN_ERR "Could not allocate memory during boot, "
- "S3 disabled\n");
- return -ENOMEM;
- }
- memcpy((void *)acpi_realmode, &wakeup_code_start, WAKEUP_SIZE);
+ acpi_realmode = TRAMPOLINE_SYM(acpi_wakeup_code);
- header = (struct wakeup_header *)(acpi_realmode + HEADER_OFFSET);
- if (header->signature != 0x51ee1111) {
+ header = (struct wakeup_header *)(acpi_realmode + WAKEUP_HEADER_OFFSET);
+ if (header->signature != WAKEUP_HEADER_SIGNATURE) {
printk(KERN_ERR "wakeup header does not match\n");
return -EINVAL;
}
@@ -68,9 +59,7 @@ int acpi_save_state_mem(void)
/* GDT[0]: GDT self-pointer */
header->wakeup_gdt[0] =
(u64)(sizeof(header->wakeup_gdt) - 1) +
- ((u64)(acpi_wakeup_address +
- ((char *)&header->wakeup_gdt - (char *)acpi_realmode))
- << 16);
+ ((u64)__pa(&header->wakeup_gdt) << 16);
/* GDT[1]: big real mode-like code segment */
header->wakeup_gdt[1] =
GDT_ENTRY(0x809b, acpi_wakeup_address, 0xfffff);
@@ -96,7 +85,7 @@ int acpi_save_state_mem(void)
header->pmode_cr3 = (u32)__pa(&initial_page_table);
saved_magic = 0x12345678;
#else /* CONFIG_64BIT */
- header->trampoline_segment = setup_trampoline() >> 4;
+ header->trampoline_segment = trampoline_address() >> 4;
#ifdef CONFIG_SMP
stack_start = (unsigned long)temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
@@ -107,56 +96,10 @@ int acpi_save_state_mem(void)
saved_magic = 0x123456789abcdef0L;
#endif /* CONFIG_64BIT */
+ do_suspend_lowlevel();
return 0;
}
-/*
- * acpi_restore_state - undo effects of acpi_save_state_mem
- */
-void acpi_restore_state_mem(void)
-{
-}
-
-
-/**
- * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation
- *
- * We allocate a page from the first 1MB of memory for the wakeup
- * routine for when we come back from a sleep state. The
- * runtime allocator allows specification of <16MB pages, but not
- * <1MB pages.
- */
-void __init acpi_reserve_wakeup_memory(void)
-{
- phys_addr_t mem;
-
- if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
- printk(KERN_ERR
- "ACPI: Wakeup code way too big, S3 disabled.\n");
- return;
- }
-
- mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
-
- if (mem == MEMBLOCK_ERROR) {
- printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
- return;
- }
- acpi_realmode = (unsigned long) phys_to_virt(mem);
- acpi_wakeup_address = mem;
- memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
-}
-
-int __init acpi_configure_wakeup_memory(void)
-{
- if (acpi_realmode)
- set_memory_x(acpi_realmode, WAKEUP_SIZE >> PAGE_SHIFT);
-
- return 0;
-}
-arch_initcall(acpi_configure_wakeup_memory);
-
-
static int __init acpi_sleep_setup(char *str)
{
while ((str != NULL) && (*str != '\0')) {
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index adbcbaa6f1d..416d4be13fe 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -4,13 +4,12 @@
#include <asm/trampoline.h>
-extern char wakeup_code_start, wakeup_code_end;
-
extern unsigned long saved_video_mode;
extern long saved_magic;
extern int wakeup_pmode_return;
-extern char swsusp_pg_dir[PAGE_SIZE];
extern unsigned long acpi_copy_wakeup_routine(unsigned long);
extern void wakeup_long64(void);
+
+extern void do_suspend_lowlevel(void);
diff --git a/arch/x86/kernel/acpi/wakeup_rm.S b/arch/x86/kernel/acpi/wakeup_rm.S
index 6ff3b573057..63b8ab524f2 100644
--- a/arch/x86/kernel/acpi/wakeup_rm.S
+++ b/arch/x86/kernel/acpi/wakeup_rm.S
@@ -2,9 +2,11 @@
* Wrapper script for the realmode binary as a transport object
* before copying to low memory.
*/
- .section ".rodata","a"
- .globl wakeup_code_start, wakeup_code_end
-wakeup_code_start:
+#include <asm/page_types.h>
+
+ .section ".x86_trampoline","a"
+ .balign PAGE_SIZE
+ .globl acpi_wakeup_code
+acpi_wakeup_code:
.incbin "arch/x86/kernel/acpi/realmode/wakeup.bin"
-wakeup_code_end:
- .size wakeup_code_start, .-wakeup_code_start
+ .size acpi_wakeup_code, .-acpi_wakeup_code
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 123608531c8..4a234677e21 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -199,7 +199,7 @@ void *text_poke_early(void *addr, const void *opcode, size_t len);
/* Replace instructions with better alternatives for this CPU type.
This runs before SMP is initialized to avoid SMP problems with
- self modifying code. This implies that assymetric systems where
+ self modifying code. This implies that asymmetric systems where
APs have less capabilities than the boot processor are not handled.
Tough. Make sure you disable such features by hand. */
@@ -620,7 +620,12 @@ static int __kprobes stop_machine_text_poke(void *data)
flush_icache_range((unsigned long)p->addr,
(unsigned long)p->addr + p->len);
}
-
+ /*
+ * Intel Archiecture Software Developer's Manual section 7.1.3 specifies
+ * that a core serializing instruction such as "cpuid" should be
+ * executed on _each_ core before the new instruction is made visible.
+ */
+ sync_core();
return 0;
}
@@ -671,7 +676,7 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
atomic_set(&stop_machine_first, 1);
wrote_text = 0;
- stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+ __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
}
#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 6e11c813415..246d727b65b 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -21,7 +21,7 @@
#include <linux/acpi.h>
#include <linux/list.h>
#include <linux/slab.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/interrupt.h>
#include <linux/msi.h>
#include <asm/pci-direct.h>
@@ -1260,7 +1260,7 @@ static void disable_iommus(void)
* disable suspend until real resume implemented
*/
-static int amd_iommu_resume(struct sys_device *dev)
+static void amd_iommu_resume(void)
{
struct amd_iommu *iommu;
@@ -1276,11 +1276,9 @@ static int amd_iommu_resume(struct sys_device *dev)
*/
amd_iommu_flush_all_devices();
amd_iommu_flush_all_domains();
-
- return 0;
}
-static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
+static int amd_iommu_suspend(void)
{
/* disable IOMMUs to go out of the way for BIOS */
disable_iommus();
@@ -1288,17 +1286,11 @@ static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
return 0;
}
-static struct sysdev_class amd_iommu_sysdev_class = {
- .name = "amd_iommu",
+static struct syscore_ops amd_iommu_syscore_ops = {
.suspend = amd_iommu_suspend,
.resume = amd_iommu_resume,
};
-static struct sys_device device_amd_iommu = {
- .id = 0,
- .cls = &amd_iommu_sysdev_class,
-};
-
/*
* This is the core init function for AMD IOMMU hardware in the system.
* This function is called from the generic x86 DMA layer initialization
@@ -1415,14 +1407,6 @@ static int __init amd_iommu_init(void)
goto free;
}
- ret = sysdev_class_register(&amd_iommu_sysdev_class);
- if (ret)
- goto free;
-
- ret = sysdev_register(&device_amd_iommu);
- if (ret)
- goto free;
-
ret = amd_iommu_init_devices();
if (ret)
goto free;
@@ -1441,6 +1425,8 @@ static int __init amd_iommu_init(void)
amd_iommu_init_notifier();
+ register_syscore_ops(&amd_iommu_syscore_ops);
+
if (iommu_pass_through)
goto out;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 0a99f7198bc..4c39baa8fac 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -12,14 +12,19 @@
static u32 *flush_words;
-struct pci_device_id amd_nb_misc_ids[] = {
+const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
{}
};
EXPORT_SYMBOL(amd_nb_misc_ids);
+static struct pci_device_id amd_nb_link_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+ {}
+};
+
const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
{ 0x00, 0x18, 0x20 },
{ 0xff, 0x00, 0x20 },
@@ -31,7 +36,7 @@ struct amd_northbridge_info amd_northbridges;
EXPORT_SYMBOL(amd_northbridges);
static struct pci_dev *next_northbridge(struct pci_dev *dev,
- struct pci_device_id *ids)
+ const struct pci_device_id *ids)
{
do {
dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
@@ -43,9 +48,9 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev,
int amd_cache_northbridges(void)
{
- int i = 0;
+ u16 i = 0;
struct amd_northbridge *nb;
- struct pci_dev *misc;
+ struct pci_dev *misc, *link;
if (amd_nb_num())
return 0;
@@ -64,10 +69,12 @@ int amd_cache_northbridges(void)
amd_northbridges.nb = nb;
amd_northbridges.num = i;
- misc = NULL;
+ link = misc = NULL;
for (i = 0; i != amd_nb_num(); i++) {
node_to_amd_nb(i)->misc = misc =
next_northbridge(misc, amd_nb_misc_ids);
+ node_to_amd_nb(i)->link = link =
+ next_northbridge(link, amd_nb_link_ids);
}
/* some CPU families (e.g. family 0x11) do not support GART */
@@ -85,26 +92,95 @@ int amd_cache_northbridges(void)
boot_cpu_data.x86_mask >= 0x1))
amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
+ if (boot_cpu_data.x86 == 0x15)
+ amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
+
+ /* L3 cache partitioning is supported on family 0x15 */
+ if (boot_cpu_data.x86 == 0x15)
+ amd_northbridges.flags |= AMD_NB_L3_PARTITIONING;
+
return 0;
}
EXPORT_SYMBOL_GPL(amd_cache_northbridges);
-/* Ignores subdevice/subvendor but as far as I can figure out
- they're useless anyways */
-int __init early_is_amd_nb(u32 device)
+/*
+ * Ignores subdevice/subvendor but as far as I can figure out
+ * they're useless anyways
+ */
+bool __init early_is_amd_nb(u32 device)
{
- struct pci_device_id *id;
+ const struct pci_device_id *id;
u32 vendor = device & 0xffff;
+
device >>= 16;
for (id = amd_nb_misc_ids; id->vendor; id++)
if (vendor == id->vendor && device == id->device)
- return 1;
+ return true;
+ return false;
+}
+
+int amd_get_subcaches(int cpu)
+{
+ struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
+ unsigned int mask;
+ int cuid = 0;
+
+ if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return 0;
+
+ pci_read_config_dword(link, 0x1d4, &mask);
+
+#ifdef CONFIG_SMP
+ cuid = cpu_data(cpu).compute_unit_id;
+#endif
+ return (mask >> (4 * cuid)) & 0xf;
+}
+
+int amd_set_subcaches(int cpu, int mask)
+{
+ static unsigned int reset, ban;
+ struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
+ unsigned int reg;
+ int cuid = 0;
+
+ if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf)
+ return -EINVAL;
+
+ /* if necessary, collect reset state of L3 partitioning and BAN mode */
+ if (reset == 0) {
+ pci_read_config_dword(nb->link, 0x1d4, &reset);
+ pci_read_config_dword(nb->misc, 0x1b8, &ban);
+ ban &= 0x180000;
+ }
+
+ /* deactivate BAN mode if any subcaches are to be disabled */
+ if (mask != 0xf) {
+ pci_read_config_dword(nb->misc, 0x1b8, &reg);
+ pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
+ }
+
+#ifdef CONFIG_SMP
+ cuid = cpu_data(cpu).compute_unit_id;
+#endif
+ mask <<= 4 * cuid;
+ mask |= (0xf ^ (1 << cuid)) << 26;
+
+ pci_write_config_dword(nb->link, 0x1d4, mask);
+
+ /* reset BAN mode if L3 partitioning returned to reset state */
+ pci_read_config_dword(nb->link, 0x1d4, &reg);
+ if (reg == reset) {
+ pci_read_config_dword(nb->misc, 0x1b8, &reg);
+ reg &= ~0x180000;
+ pci_write_config_dword(nb->misc, 0x1b8, reg | ban);
+ }
+
return 0;
}
-int amd_cache_gart(void)
+static int amd_cache_gart(void)
{
- int i;
+ u16 i;
if (!amd_nb_has_feature(AMD_NB_GART))
return 0;
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 51ef31a89be..cd1ffed4ee2 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -284,7 +284,7 @@ static int __init apbt_clockevent_register(void)
memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device));
if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
- apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100;
+ adev->evt.rating = APBT_CLOCKEVENT_RATING - 100;
global_clock_event = &adev->evt;
printk(KERN_DEBUG "%s clockevent registered as global\n",
global_clock_event->name);
@@ -316,7 +316,7 @@ static void apbt_setup_irq(struct apbt_dev *adev)
irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
/* APB timer irqs are set up as mp_irqs, timer is edge type */
- __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+ __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge");
if (system_state == SYSTEM_BOOTING) {
if (request_irq(adev->irq, apbt_interrupt_handler,
@@ -508,64 +508,12 @@ static int apbt_next_event(unsigned long delta,
return 0;
}
-/*
- * APB timer clock is not in sync with pclk on Langwell, which translates to
- * unreliable read value caused by sampling error. the error does not add up
- * overtime and only happens when sampling a 0 as a 1 by mistake. so the time
- * would go backwards. the following code is trying to prevent time traveling
- * backwards. little bit paranoid.
- */
static cycle_t apbt_read_clocksource(struct clocksource *cs)
{
- unsigned long t0, t1, t2;
- static unsigned long last_read;
-
-bad_count:
- t1 = apbt_readl(phy_cs_timer_id,
- APBTMR_N_CURRENT_VALUE);
- t2 = apbt_readl(phy_cs_timer_id,
- APBTMR_N_CURRENT_VALUE);
- if (unlikely(t1 < t2)) {
- pr_debug("APBT: read current count error %lx:%lx:%lx\n",
- t1, t2, t2 - t1);
- goto bad_count;
- }
- /*
- * check against cached last read, makes sure time does not go back.
- * it could be a normal rollover but we will do tripple check anyway
- */
- if (unlikely(t2 > last_read)) {
- /* check if we have a normal rollover */
- unsigned long raw_intr_status =
- apbt_readl_reg(APBTMRS_RAW_INT_STATUS);
- /*
- * cs timer interrupt is masked but raw intr bit is set if
- * rollover occurs. then we read EOI reg to clear it.
- */
- if (raw_intr_status & (1 << phy_cs_timer_id)) {
- apbt_readl(phy_cs_timer_id, APBTMR_N_EOI);
- goto out;
- }
- pr_debug("APB CS going back %lx:%lx:%lx ",
- t2, last_read, t2 - last_read);
-bad_count_x3:
- pr_debug("triple check enforced\n");
- t0 = apbt_readl(phy_cs_timer_id,
- APBTMR_N_CURRENT_VALUE);
- udelay(1);
- t1 = apbt_readl(phy_cs_timer_id,
- APBTMR_N_CURRENT_VALUE);
- udelay(1);
- t2 = apbt_readl(phy_cs_timer_id,
- APBTMR_N_CURRENT_VALUE);
- if ((t2 > t1) || (t1 > t0)) {
- printk(KERN_ERR "Error: APB CS tripple check failed\n");
- goto bad_count_x3;
- }
- }
-out:
- last_read = t2;
- return (cycle_t)~t2;
+ unsigned long current_count;
+
+ current_count = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE);
+ return (cycle_t)~current_count;
}
static int apbt_clocksource_register(void)
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 5955a7800a9..73fb469908c 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -13,7 +13,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/pci_ids.h>
#include <linux/pci.h>
@@ -57,7 +57,7 @@ static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
static u32 __init allocate_aperture(void)
{
u32 aper_size;
- void *p;
+ unsigned long addr;
/* aper_size should <= 1G */
if (fallback_aper_order > 5)
@@ -73,7 +73,7 @@ static u32 __init allocate_aperture(void)
/*
* using 512M as goal, in case kexec will load kernel_big
* that will do the on position decompress, and could overlap with
- * that positon with gart that is used.
+ * that position with gart that is used.
* sequende:
* kernel_small
* ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
@@ -83,27 +83,26 @@ static u32 __init allocate_aperture(void)
* so don't use 512M below as gart iommu, leave the space for kernel
* code for safe
*/
- p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
+ addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20);
+ if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) {
+ printk(KERN_ERR
+ "Cannot allocate aperture memory hole (%lx,%uK)\n",
+ addr, aper_size>>10);
+ return 0;
+ }
+ memblock_x86_reserve_range(addr, addr + aper_size, "aperture64");
/*
* Kmemleak should not scan this block as it may not be mapped via the
* kernel direct mapping.
*/
- kmemleak_ignore(p);
- if (!p || __pa(p)+aper_size > 0xffffffff) {
- printk(KERN_ERR
- "Cannot allocate aperture memory hole (%p,%uK)\n",
- p, aper_size>>10);
- if (p)
- free_bootmem(__pa(p), aper_size);
- return 0;
- }
+ kmemleak_ignore(phys_to_virt(addr));
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
- aper_size >> 10, __pa(p));
- insert_aperture_resource((u32)__pa(p), aper_size);
- register_nosave_region((u32)__pa(p) >> PAGE_SHIFT,
- (u32)__pa(p+aper_size) >> PAGE_SHIFT);
+ aper_size >> 10, addr);
+ insert_aperture_resource((u32)addr, aper_size);
+ register_nosave_region(addr >> PAGE_SHIFT,
+ (addr+aper_size) >> PAGE_SHIFT);
- return (u32)__pa(p);
+ return (u32)addr;
}
@@ -500,7 +499,7 @@ out:
* Don't enable translation yet but enable GART IO and CPU
* accesses and set DISTLBWALKPRB since GART table memory is UC.
*/
- u32 ctl = DISTLBWALKPRB | aper_order << 1;
+ u32 ctl = aper_order << 1;
bus = amd_nb_bus_dev_ranges[i].bus;
dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 06c196d7e59..fabf01eff77 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -24,7 +24,7 @@
#include <linux/ftrace.h>
#include <linux/ioport.h>
#include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/timex.h>
#include <linux/dmar.h>
@@ -43,6 +43,7 @@
#include <asm/i8259.h>
#include <asm/proto.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/idle.h>
@@ -78,12 +79,21 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
#ifdef CONFIG_X86_32
+
+/*
+ * On x86_32, the mapping between cpu and logical apicid may vary
+ * depending on apic in use. The following early percpu variable is
+ * used for the mapping. This is where the behaviors of x86_64 and 32
+ * actually diverge. Let's keep it ugly for now.
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid, BAD_APICID);
+
/*
* Knob to control our willingness to enable the local APIC.
*
* +1=force-enable
*/
-static int force_enable_local_apic;
+static int force_enable_local_apic __initdata;
/*
* APIC command line parameters
*/
@@ -153,7 +163,7 @@ early_param("nox2apic", setup_nox2apic);
unsigned long mp_lapic_addr;
int disable_apic;
/* Disable local APIC timer from the kernel commandline or via dmi quirk */
-static int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __initdata;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -177,29 +187,8 @@ static struct resource lapic_resource = {
static unsigned int calibration_result;
-static int lapic_next_event(unsigned long delta,
- struct clock_event_device *evt);
-static void lapic_timer_setup(enum clock_event_mode mode,
- struct clock_event_device *evt);
-static void lapic_timer_broadcast(const struct cpumask *mask);
static void apic_pm_activate(void);
-/*
- * The local apic timer can be used for any function which is CPU local.
- */
-static struct clock_event_device lapic_clockevent = {
- .name = "lapic",
- .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
- | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
- .shift = 32,
- .set_mode = lapic_timer_setup,
- .set_next_event = lapic_next_event,
- .broadcast = lapic_timer_broadcast,
- .rating = 100,
- .irq = -1,
-};
-static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
-
static unsigned long apic_phys;
/*
@@ -238,7 +227,7 @@ static int modern_apic(void)
* right after this call apic become NOOP driven
* so apic->write/read doesn't do anything
*/
-void apic_disable(void)
+static void __init apic_disable(void)
{
pr_info("APIC: switched to apic NOOP\n");
apic = &apic_noop;
@@ -282,23 +271,6 @@ u64 native_apic_icr_read(void)
return icr1 | ((u64)icr2 << 32);
}
-/**
- * enable_NMI_through_LVT0 - enable NMI through local vector table 0
- */
-void __cpuinit enable_NMI_through_LVT0(void)
-{
- unsigned int v;
-
- /* unmask and set to NMI */
- v = APIC_DM_NMI;
-
- /* Level triggered for 82489DX (32bit mode) */
- if (!lapic_is_integrated())
- v |= APIC_LVT_LEVEL_TRIGGER;
-
- apic_write(APIC_LVT0, v);
-}
-
#ifdef CONFIG_X86_32
/**
* get_physical_broadcast - Get number of physical broadcast IDs
@@ -508,6 +480,23 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
#endif
}
+
+/*
+ * The local apic timer can be used for any function which is CPU local.
+ */
+static struct clock_event_device lapic_clockevent = {
+ .name = "lapic",
+ .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
+ | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
+ .shift = 32,
+ .set_mode = lapic_timer_setup,
+ .set_next_event = lapic_next_event,
+ .broadcast = lapic_timer_broadcast,
+ .rating = 100,
+ .irq = -1,
+};
+static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
+
/*
* Setup the local APIC timer for this CPU. Copy the initialized values
* of the boot CPU and register the clock event in the framework.
@@ -1209,7 +1198,7 @@ void __cpuinit setup_local_APIC(void)
rdtscll(tsc);
if (disable_apic) {
- arch_disable_smp_support();
+ disable_ioapic_support();
return;
}
@@ -1237,6 +1226,19 @@ void __cpuinit setup_local_APIC(void)
*/
apic->init_apic_ldr();
+#ifdef CONFIG_X86_32
+ /*
+ * APIC LDR is initialized. If logical_apicid mapping was
+ * initialized during get_smp_config(), make sure it matches the
+ * actual value.
+ */
+ i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+ WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
+ /* always use the value from LDR */
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+ logical_smp_processor_id();
+#endif
+
/*
* Set Task Priority to 'accept all'. We never change this
* later on.
@@ -1381,12 +1383,17 @@ void __cpuinit end_local_APIC_setup(void)
#endif
apic_pm_activate();
+}
+
+void __init bsp_end_local_APIC_setup(void)
+{
+ end_local_APIC_setup();
/*
* Now that local APIC setup is completed for BP, configure the fault
* handling for interrupt remapping.
*/
- if (!smp_processor_id() && intr_remapping_enabled)
+ if (intr_remapping_enabled)
enable_drhd_fault_handling();
}
@@ -1443,7 +1450,7 @@ int __init enable_IR(void)
void __init enable_IR_x2apic(void)
{
unsigned long flags;
- struct IO_APIC_route_entry **ioapic_entries = NULL;
+ struct IO_APIC_route_entry **ioapic_entries;
int ret, x2apic_enabled = 0;
int dmar_table_init_ret;
@@ -1532,7 +1539,7 @@ static int __init detect_init_APIC(void)
}
#else
-static int apic_verify(void)
+static int __init apic_verify(void)
{
u32 features, h, l;
@@ -1557,7 +1564,7 @@ static int apic_verify(void)
return 0;
}
-int apic_force_enable(void)
+int __init apic_force_enable(unsigned long addr)
{
u32 h, l;
@@ -1573,7 +1580,7 @@ int apic_force_enable(void)
if (!(l & MSR_IA32_APICBASE_ENABLE)) {
pr_info("Local APIC disabled by BIOS -- reenabling.\n");
l &= ~MSR_IA32_APICBASE_BASE;
- l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
+ l |= MSR_IA32_APICBASE_ENABLE | addr;
wrmsr(MSR_IA32_APICBASE, l, h);
enabled_via_apicbase = 1;
}
@@ -1614,7 +1621,7 @@ static int __init detect_init_APIC(void)
"you can enable it with \"lapic\"\n");
return -1;
}
- if (apic_force_enable())
+ if (apic_force_enable(APIC_DEFAULT_PHYS_BASE))
return -1;
} else {
if (apic_verify())
@@ -1756,7 +1763,7 @@ int __init APIC_init_uniprocessor(void)
enable_IO_APIC();
#endif
- end_local_APIC_setup();
+ bsp_end_local_APIC_setup();
#ifdef CONFIG_X86_IO_APIC
if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
@@ -1925,17 +1932,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
{
int cpu;
- /*
- * Validate version
- */
- if (version == 0x0) {
- pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
- "fixing up to 0x10. (tell your hw vendor)\n",
- version);
- version = 0x10;
- }
- apic_version[apicid] = version;
-
if (num_processors >= nr_cpu_ids) {
int max = nr_cpu_ids;
int thiscpu = max + disabled_cpus;
@@ -1949,22 +1945,34 @@ void __cpuinit generic_processor_info(int apicid, int version)
}
num_processors++;
- cpu = cpumask_next_zero(-1, cpu_present_mask);
-
- if (version != apic_version[boot_cpu_physical_apicid])
- WARN_ONCE(1,
- "ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
- apic_version[boot_cpu_physical_apicid], cpu, version);
-
- physid_set(apicid, phys_cpu_present_map);
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
* in same order as logical cpu numbers. Hence the first
* entry is BSP, and so on.
+ * boot_cpu_init() already hold bit 0 in cpu_present_mask
+ * for BSP.
*/
cpu = 0;
+ } else
+ cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+ /*
+ * Validate version
+ */
+ if (version == 0x0) {
+ pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
+ cpu, apicid);
+ version = 0x10;
}
+ apic_version[apicid] = version;
+
+ if (version != apic_version[boot_cpu_physical_apicid]) {
+ pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
+ apic_version[boot_cpu_physical_apicid], cpu, version);
+ }
+
+ physid_set(apicid, phys_cpu_present_map);
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
@@ -1972,7 +1980,10 @@ void __cpuinit generic_processor_info(int apicid, int version)
early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
-
+#ifdef CONFIG_X86_32
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+ apic->x86_32_early_logical_apicid(cpu);
+#endif
set_cpu_possible(cpu, true);
set_cpu_present(cpu, true);
}
@@ -1993,10 +2004,14 @@ void default_init_apic_ldr(void)
}
#ifdef CONFIG_X86_32
-int default_apicid_to_node(int logical_apicid)
+int default_x86_32_numa_cpu_node(int cpu)
{
-#ifdef CONFIG_SMP
- return apicid_2_node[hard_smp_processor_id()];
+#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
@@ -2031,7 +2046,7 @@ static struct {
unsigned int apic_thmr;
} apic_pm_state;
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
+static int lapic_suspend(void)
{
unsigned long flags;
int maxlvt;
@@ -2069,23 +2084,21 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
return 0;
}
-static int lapic_resume(struct sys_device *dev)
+static void lapic_resume(void)
{
unsigned int l, h;
unsigned long flags;
- int maxlvt;
- int ret = 0;
+ int maxlvt, ret;
struct IO_APIC_route_entry **ioapic_entries = NULL;
if (!apic_pm_state.active)
- return 0;
+ return;
local_irq_save(flags);
if (intr_remapping_enabled) {
ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
WARN(1, "Alloc ioapic_entries in lapic resume failed.");
- ret = -ENOMEM;
goto restore;
}
@@ -2147,8 +2160,6 @@ static int lapic_resume(struct sys_device *dev)
}
restore:
local_irq_restore(flags);
-
- return ret;
}
/*
@@ -2156,17 +2167,11 @@ restore:
* are needed on every CPU up until machine_halt/restart/poweroff.
*/
-static struct sysdev_class lapic_sysclass = {
- .name = "lapic",
+static struct syscore_ops lapic_syscore_ops = {
.resume = lapic_resume,
.suspend = lapic_suspend,
};
-static struct sys_device device_lapic = {
- .id = 0,
- .cls = &lapic_sysclass,
-};
-
static void __cpuinit apic_pm_activate(void)
{
apic_pm_state.active = 1;
@@ -2174,16 +2179,11 @@ static void __cpuinit apic_pm_activate(void)
static int __init init_lapic_sysfs(void)
{
- int error;
-
- if (!cpu_has_apic)
- return 0;
/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+ if (cpu_has_apic)
+ register_syscore_ops(&lapic_syscore_ops);
- error = sysdev_class_register(&lapic_sysclass);
- if (!error)
- error = sysdev_register(&device_lapic);
- return error;
+ return 0;
}
/* local apic needs to resume before other devices access its registers. */
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 09d3b17ce0c..5652d31fe10 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -185,8 +185,6 @@ struct apic apic_flat = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
- .apicid_to_node = NULL,
- .cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
@@ -337,8 +335,6 @@ struct apic apic_physflat = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
- .apicid_to_node = NULL,
- .cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index e31b9ffe25f..f1baa2dc087 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -54,11 +54,6 @@ static u64 noop_apic_icr_read(void)
return 0;
}
-static int noop_cpu_to_logical_apicid(int cpu)
-{
- return 0;
-}
-
static int noop_phys_pkg_id(int cpuid_apic, int index_msb)
{
return 0;
@@ -113,12 +108,6 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask)
cpumask_set_cpu(cpu, retmask);
}
-int noop_apicid_to_node(int logical_apicid)
-{
- /* we're always on node 0 */
- return 0;
-}
-
static u32 noop_apic_read(u32 reg)
{
WARN_ON_ONCE((cpu_has_apic && !disable_apic));
@@ -130,6 +119,14 @@ static void noop_apic_write(u32 reg, u32 v)
WARN_ON_ONCE(cpu_has_apic && !disable_apic);
}
+#ifdef CONFIG_X86_32
+static int noop_x86_32_numa_cpu_node(int cpu)
+{
+ /* we're always on node 0 */
+ return 0;
+}
+#endif
+
struct apic apic_noop = {
.name = "noop",
.probe = noop_probe,
@@ -153,9 +150,7 @@ struct apic apic_noop = {
.ioapic_phys_id_map = default_ioapic_phys_id_map,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
- .apicid_to_node = noop_apicid_to_node,
- .cpu_to_logical_apicid = noop_cpu_to_logical_apicid,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = physid_set_mask_of_physid,
@@ -197,4 +192,9 @@ struct apic apic_noop = {
.icr_write = noop_apic_icr_write,
.wait_icr_idle = noop_apic_wait_icr_idle,
.safe_wait_icr_idle = noop_safe_apic_wait_icr_idle,
+
+#ifdef CONFIG_X86_32
+ .x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid,
+ .x86_32_numa_cpu_node = noop_x86_32_numa_cpu_node,
+#endif
};
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index cb804c5091b..541a2e43165 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -45,6 +45,12 @@ static unsigned long bigsmp_check_apicid_present(int bit)
return 1;
}
+static int bigsmp_early_logical_apicid(int cpu)
+{
+ /* on bigsmp, logical apicid is the same as physical */
+ return early_per_cpu(x86_cpu_to_apicid, cpu);
+}
+
static inline unsigned long calculate_ldr(int cpu)
{
unsigned long val, id;
@@ -80,11 +86,6 @@ static void bigsmp_setup_apic_routing(void)
nr_ioapics);
}
-static int bigsmp_apicid_to_node(int logical_apicid)
-{
- return apicid_2_node[hard_smp_processor_id()];
-}
-
static int bigsmp_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids)
@@ -93,14 +94,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu)
return BAD_APICID;
}
-/* Mapping from cpu number to logical apicid */
-static inline int bigsmp_cpu_to_logical_apicid(int cpu)
-{
- if (cpu >= nr_cpu_ids)
- return BAD_APICID;
- return cpu_physical_id(cpu);
-}
-
static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
{
/* For clustered we don't have a good way to do this yet - hack */
@@ -115,7 +108,11 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid)
/* As we are using single CPU as destination, pick only one CPU here */
static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
{
- return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
+ int cpu = cpumask_first(cpumask);
+
+ if (cpu < nr_cpu_ids)
+ return cpu_physical_id(cpu);
+ return BAD_APICID;
}
static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -129,9 +126,9 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
*/
for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
- break;
+ return cpu_physical_id(cpu);
}
- return bigsmp_cpu_to_logical_apicid(cpu);
+ return BAD_APICID;
}
static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
@@ -219,8 +216,6 @@ struct apic apic_bigsmp = {
.ioapic_phys_id_map = bigsmp_ioapic_phys_id_map,
.setup_apic_routing = bigsmp_setup_apic_routing,
.multi_timer_check = NULL,
- .apicid_to_node = bigsmp_apicid_to_node,
- .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid,
.cpu_present_to_apicid = bigsmp_cpu_present_to_apicid,
.apicid_to_cpu_present = physid_set_mask_of_physid,
.setup_portio_remap = NULL,
@@ -256,4 +251,7 @@ struct apic apic_bigsmp = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+
+ .x86_32_early_logical_apicid = bigsmp_early_logical_apicid,
+ .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node,
};
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 8593582d802..3e9de4854c5 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -460,6 +460,12 @@ static unsigned long es7000_check_apicid_present(int bit)
return physid_isset(bit, phys_cpu_present_map);
}
+static int es7000_early_logical_apicid(int cpu)
+{
+ /* on es7000, logical apicid is the same as physical */
+ return early_per_cpu(x86_bios_cpu_apicid, cpu);
+}
+
static unsigned long calculate_ldr(int cpu)
{
unsigned long id = per_cpu(x86_bios_cpu_apicid, cpu);
@@ -504,12 +510,11 @@ static void es7000_setup_apic_routing(void)
nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
}
-static int es7000_apicid_to_node(int logical_apicid)
+static int es7000_numa_cpu_node(int cpu)
{
return 0;
}
-
static int es7000_cpu_present_to_apicid(int mps_cpu)
{
if (!mps_cpu)
@@ -528,18 +533,6 @@ static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap)
++cpu_id;
}
-/* Mapping from cpu number to logical apicid */
-static int es7000_cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
- if (cpu >= nr_cpu_ids)
- return BAD_APICID;
- return cpu_2_logical_apicid[cpu];
-#else
- return logical_smp_processor_id();
-#endif
-}
-
static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
{
/* For clustered we don't have a good way to do this yet - hack */
@@ -561,7 +554,7 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
* The cpus in the mask must all be on the apic cluster.
*/
for_each_cpu(cpu, cpumask) {
- int new_apicid = es7000_cpu_to_logical_apicid(cpu);
+ int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
WARN(1, "Not a valid mask!");
@@ -578,7 +571,7 @@ static unsigned int
es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask,
const struct cpumask *andmask)
{
- int apicid = es7000_cpu_to_logical_apicid(0);
+ int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
cpumask_var_t cpumask;
if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -655,8 +648,6 @@ struct apic __refdata apic_es7000_cluster = {
.ioapic_phys_id_map = es7000_ioapic_phys_id_map,
.setup_apic_routing = es7000_setup_apic_routing,
.multi_timer_check = NULL,
- .apicid_to_node = es7000_apicid_to_node,
- .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid,
.cpu_present_to_apicid = es7000_cpu_present_to_apicid,
.apicid_to_cpu_present = es7000_apicid_to_cpu_present,
.setup_portio_remap = NULL,
@@ -695,6 +686,9 @@ struct apic __refdata apic_es7000_cluster = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+
+ .x86_32_early_logical_apicid = es7000_early_logical_apicid,
+ .x86_32_numa_cpu_node = es7000_numa_cpu_node,
};
struct apic __refdata apic_es7000 = {
@@ -720,8 +714,6 @@ struct apic __refdata apic_es7000 = {
.ioapic_phys_id_map = es7000_ioapic_phys_id_map,
.setup_apic_routing = es7000_setup_apic_routing,
.multi_timer_check = NULL,
- .apicid_to_node = es7000_apicid_to_node,
- .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid,
.cpu_present_to_apicid = es7000_cpu_present_to_apicid,
.apicid_to_cpu_present = es7000_apicid_to_cpu_present,
.setup_portio_remap = NULL,
@@ -758,4 +750,7 @@ struct apic __refdata apic_es7000 = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+
+ .x86_32_early_logical_apicid = es7000_early_logical_apicid,
+ .x86_32_numa_cpu_node = es7000_numa_cpu_node,
};
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 79fd43ca6f9..5260fe91bcb 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -16,6 +16,7 @@
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/module.h>
+#include <linux/delay.h>
#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(void)
@@ -83,7 +84,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
arch_spin_lock(&lock);
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
show_regs(regs);
- dump_stack();
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return NOTIFY_STOP;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 697dc34b7b8..45fd33d1fd3 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -30,7 +30,7 @@
#include <linux/compiler.h>
#include <linux/acpi.h>
#include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/msi.h>
#include <linux/htirq.h>
#include <linux/freezer.h>
@@ -108,7 +108,10 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
int skip_ioapic_setup;
-void arch_disable_smp_support(void)
+/**
+ * disable_ioapic_support() - disables ioapic support at runtime
+ */
+void disable_ioapic_support(void)
{
#ifdef CONFIG_PCI
noioapicquirk = 1;
@@ -120,11 +123,14 @@ void arch_disable_smp_support(void)
static int __init parse_noapic(char *str)
{
/* disable IO-APIC */
- arch_disable_smp_support();
+ disable_ioapic_support();
return 0;
}
early_param("noapic", parse_noapic);
+static int io_apic_setup_irq_pin(unsigned int irq, int node,
+ struct io_apic_irq_attr *attr);
+
/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
void mp_save_irq(struct mpc_intsrc *m)
{
@@ -181,7 +187,7 @@ int __init arch_early_irq_init(void)
irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
for (i = 0; i < count; i++) {
- set_irq_chip_data(i, &cfg[i]);
+ irq_set_chip_data(i, &cfg[i]);
zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
/*
@@ -200,7 +206,7 @@ int __init arch_early_irq_init(void)
#ifdef CONFIG_SPARSE_IRQ
static struct irq_cfg *irq_cfg(unsigned int irq)
{
- return get_irq_chip_data(irq);
+ return irq_get_chip_data(irq);
}
static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
@@ -226,7 +232,7 @@ static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
{
if (!cfg)
return;
- set_irq_chip_data(at, NULL);
+ irq_set_chip_data(at, NULL);
free_cpumask_var(cfg->domain);
free_cpumask_var(cfg->old_domain);
kfree(cfg);
@@ -256,14 +262,14 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
if (res < 0) {
if (res != -EEXIST)
return NULL;
- cfg = get_irq_chip_data(at);
+ cfg = irq_get_chip_data(at);
if (cfg)
return cfg;
}
cfg = alloc_irq_cfg(at, node);
if (cfg)
- set_irq_chip_data(at, cfg);
+ irq_set_chip_data(at, cfg);
else
irq_free_desc(at);
return cfg;
@@ -818,7 +824,7 @@ static int EISA_ELCR(unsigned int irq)
#define default_MCA_trigger(idx) (1)
#define default_MCA_polarity(idx) default_ISA_polarity(idx)
-static int MPBIOS_polarity(int idx)
+static int irq_polarity(int idx)
{
int bus = mp_irqs[idx].srcbus;
int polarity;
@@ -860,7 +866,7 @@ static int MPBIOS_polarity(int idx)
return polarity;
}
-static int MPBIOS_trigger(int idx)
+static int irq_trigger(int idx)
{
int bus = mp_irqs[idx].srcbus;
int trigger;
@@ -932,16 +938,6 @@ static int MPBIOS_trigger(int idx)
return trigger;
}
-static inline int irq_polarity(int idx)
-{
- return MPBIOS_polarity(idx);
-}
-
-static inline int irq_trigger(int idx)
-{
- return MPBIOS_trigger(idx);
-}
-
static int pin_2_irq(int idx, int apic, int pin)
{
int irq;
@@ -1189,7 +1185,7 @@ void __setup_vector_irq(int cpu)
raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
- cfg = get_irq_chip_data(irq);
+ cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
/*
@@ -1220,10 +1216,6 @@ void __setup_vector_irq(int cpu)
static struct irq_chip ioapic_chip;
static struct irq_chip ir_ioapic_chip;
-#define IOAPIC_AUTO -1
-#define IOAPIC_EDGE 0
-#define IOAPIC_LEVEL 1
-
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
{
@@ -1248,35 +1240,31 @@ static inline int IO_APIC_irq_trigger(int irq)
}
#endif
-static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
+static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
+ unsigned long trigger)
{
+ struct irq_chip *chip = &ioapic_chip;
+ irq_flow_handler_t hdl;
+ bool fasteoi;
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL)
+ trigger == IOAPIC_LEVEL) {
irq_set_status_flags(irq, IRQ_LEVEL);
- else
+ fasteoi = true;
+ } else {
irq_clear_status_flags(irq, IRQ_LEVEL);
+ fasteoi = false;
+ }
- if (irq_remapped(get_irq_chip_data(irq))) {
+ if (irq_remapped(cfg)) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- if (trigger)
- set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
- handle_fasteoi_irq,
- "fasteoi");
- else
- set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
- handle_edge_irq, "edge");
- return;
+ chip = &ir_ioapic_chip;
+ fasteoi = trigger != 0;
}
- if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL)
- set_irq_chip_and_handler_name(irq, &ioapic_chip,
- handle_fasteoi_irq,
- "fasteoi");
- else
- set_irq_chip_and_handler_name(irq, &ioapic_chip,
- handle_edge_irq, "edge");
+ hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+ irq_set_chip_and_handler_name(irq, chip, hdl,
+ fasteoi ? "fasteoi" : "edge");
}
static int setup_ioapic_entry(int apic_id, int irq,
@@ -1374,7 +1362,7 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
return;
}
- ioapic_register_intr(irq, trigger);
+ ioapic_register_intr(irq, cfg, trigger);
if (irq < legacy_pic->nr_legacy_irqs)
legacy_pic->mask(irq);
@@ -1385,33 +1373,26 @@ static struct {
DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
} mp_ioapic_routing[MAX_IO_APICS];
-static void __init setup_IO_APIC_irqs(void)
+static bool __init io_apic_pin_not_connected(int idx, int apic_id, int pin)
{
- int apic_id, pin, idx, irq, notcon = 0;
- int node = cpu_to_node(0);
- struct irq_cfg *cfg;
+ if (idx != -1)
+ return false;
- apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+ apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n",
+ mp_ioapics[apic_id].apicid, pin);
+ return true;
+}
+
+static void __init __io_apic_setup_irqs(unsigned int apic_id)
+{
+ int idx, node = cpu_to_node(0);
+ struct io_apic_irq_attr attr;
+ unsigned int pin, irq;
- for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
idx = find_irq_entry(apic_id, pin, mp_INT);
- if (idx == -1) {
- if (!notcon) {
- notcon = 1;
- apic_printk(APIC_VERBOSE,
- KERN_DEBUG " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
- } else
- apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
+ if (io_apic_pin_not_connected(idx, apic_id, pin))
continue;
- }
- if (notcon) {
- apic_printk(APIC_VERBOSE,
- " (apicid-pin) not connected\n");
- notcon = 0;
- }
irq = pin_2_irq(idx, apic_id, pin);
@@ -1423,25 +1404,24 @@ static void __init setup_IO_APIC_irqs(void)
* installed and if it returns 1:
*/
if (apic->multi_timer_check &&
- apic->multi_timer_check(apic_id, irq))
+ apic->multi_timer_check(apic_id, irq))
continue;
- cfg = alloc_irq_and_cfg_at(irq, node);
- if (!cfg)
- continue;
+ set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
+ irq_polarity(idx));
- add_pin_to_irq_node(cfg, node, apic_id, pin);
- /*
- * don't mark it in pin_programmed, so later acpi could
- * set it correctly when irq < 16
- */
- setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
- irq_polarity(idx));
+ io_apic_setup_irq_pin(irq, node, &attr);
}
+}
- if (notcon)
- apic_printk(APIC_VERBOSE,
- " (apicid-pin) not connected\n");
+static void __init setup_IO_APIC_irqs(void)
+{
+ unsigned int apic_id;
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+
+ for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
+ __io_apic_setup_irqs(apic_id);
}
/*
@@ -1452,7 +1432,7 @@ static void __init setup_IO_APIC_irqs(void)
void setup_IO_APIC_irq_extra(u32 gsi)
{
int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
- struct irq_cfg *cfg;
+ struct io_apic_irq_attr attr;
/*
* Convert 'gsi' to 'ioapic.pin'.
@@ -1472,21 +1452,10 @@ void setup_IO_APIC_irq_extra(u32 gsi)
if (apic_id == 0 || irq < NR_IRQS_LEGACY)
return;
- cfg = alloc_irq_and_cfg_at(irq, node);
- if (!cfg)
- return;
-
- add_pin_to_irq_node(cfg, node, apic_id, pin);
+ set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
+ irq_polarity(idx));
- if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mp_ioapics[apic_id].apicid, pin);
- return;
- }
- set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
-
- setup_ioapic_irq(apic_id, pin, irq, cfg,
- irq_trigger(idx), irq_polarity(idx));
+ io_apic_setup_irq_pin_once(irq, node, &attr);
}
/*
@@ -1518,7 +1487,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin,
* The timer IRQ doesn't have to know that behind the
* scene we may have a 8259A-master in AEOI mode ...
*/
- set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
+ irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
+ "edge");
/*
* Add it to the IO-APIC irq-routing table:
@@ -1625,7 +1595,7 @@ __apicdebuginit(void) print_IO_APIC(void)
for_each_active_irq(irq) {
struct irq_pin_list *entry;
- cfg = get_irq_chip_data(irq);
+ cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
entry = cfg->irq_2_pin;
@@ -1916,7 +1886,7 @@ void disable_IO_APIC(void)
*
* With interrupt-remapping, for now we will use virtual wire A mode,
* as virtual wire B is little complex (need to configure both
- * IOAPIC RTE aswell as interrupt-remapping table entry).
+ * IOAPIC RTE as well as interrupt-remapping table entry).
* As this gets called during crash dump, keep this simple for now.
*/
if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) {
@@ -2391,7 +2361,7 @@ static void irq_complete_move(struct irq_cfg *cfg)
void irq_force_complete_move(int irq)
{
- struct irq_cfg *cfg = get_irq_chip_data(irq);
+ struct irq_cfg *cfg = irq_get_chip_data(irq);
if (!cfg)
return;
@@ -2405,7 +2375,7 @@ static inline void irq_complete_move(struct irq_cfg *cfg) { }
static void ack_apic_edge(struct irq_data *data)
{
irq_complete_move(data->chip_data);
- move_native_irq(data->irq);
+ irq_move_irq(data);
ack_APIC_irq();
}
@@ -2462,7 +2432,7 @@ static void ack_apic_level(struct irq_data *data)
irq_complete_move(cfg);
#ifdef CONFIG_GENERIC_PENDING_IRQ
/* If we are moving the irq we need to mask it */
- if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
+ if (unlikely(irqd_is_setaffinity_pending(data))) {
do_unmask_irq = 1;
mask_ioapic(cfg);
}
@@ -2551,7 +2521,7 @@ static void ack_apic_level(struct irq_data *data)
* and you can go talk to the chipset vendor about it.
*/
if (!io_apic_level_ack_pending(cfg))
- move_masked_irq(irq);
+ irq_move_masked_irq(data);
unmask_ioapic(cfg);
}
}
@@ -2614,7 +2584,7 @@ static inline void init_IO_APIC_traps(void)
* 0x80, because int 0x80 is hm, kind of importantish. ;)
*/
for_each_active_irq(irq) {
- cfg = get_irq_chip_data(irq);
+ cfg = irq_get_chip_data(irq);
if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
/*
* Hmm.. We don't have an entry for this,
@@ -2625,7 +2595,7 @@ static inline void init_IO_APIC_traps(void)
legacy_pic->make_irq(irq);
else
/* Strange. Oh, well.. */
- set_irq_chip(irq, &no_irq_chip);
+ irq_set_chip(irq, &no_irq_chip);
}
}
}
@@ -2665,7 +2635,7 @@ static struct irq_chip lapic_chip __read_mostly = {
static void lapic_register_intr(int irq)
{
irq_clear_status_flags(irq, IRQ_LEVEL);
- set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+ irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
"edge");
}
@@ -2749,7 +2719,7 @@ int timer_through_8259 __initdata;
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = get_irq_chip_data(0);
+ struct irq_cfg *cfg = irq_get_chip_data(0);
int node = cpu_to_node(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
@@ -2935,7 +2905,7 @@ void __init setup_IO_APIC(void)
}
/*
- * Called after all the initialization is done. If we didnt find any
+ * Called after all the initialization is done. If we didn't find any
* APIC bugs then we can allow the modify fast path
*/
@@ -2948,89 +2918,84 @@ static int __init io_apic_bug_finalize(void)
late_initcall(io_apic_bug_finalize);
-struct sysfs_ioapic_data {
- struct sys_device dev;
- struct IO_APIC_route_entry entry[0];
-};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct IO_APIC_route_entry *ioapic_saved_data[MAX_IO_APICS];
-static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
+static void suspend_ioapic(int ioapic_id)
{
- struct IO_APIC_route_entry *entry;
- struct sysfs_ioapic_data *data;
+ struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
int i;
- data = container_of(dev, struct sysfs_ioapic_data, dev);
- entry = data->entry;
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ )
- *entry = ioapic_read_entry(dev->id, i);
+ if (!saved_data)
+ return;
+
+ for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+ saved_data[i] = ioapic_read_entry(ioapic_id, i);
+}
+
+static int ioapic_suspend(void)
+{
+ int ioapic_id;
+
+ for (ioapic_id = 0; ioapic_id < nr_ioapics; ioapic_id++)
+ suspend_ioapic(ioapic_id);
return 0;
}
-static int ioapic_resume(struct sys_device *dev)
+static void resume_ioapic(int ioapic_id)
{
- struct IO_APIC_route_entry *entry;
- struct sysfs_ioapic_data *data;
+ struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
unsigned long flags;
union IO_APIC_reg_00 reg_00;
int i;
- data = container_of(dev, struct sysfs_ioapic_data, dev);
- entry = data->entry;
+ if (!saved_data)
+ return;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].apicid;
- io_apic_write(dev->id, 0, reg_00.raw);
+ reg_00.raw = io_apic_read(ioapic_id, 0);
+ if (reg_00.bits.ID != mp_ioapics[ioapic_id].apicid) {
+ reg_00.bits.ID = mp_ioapics[ioapic_id].apicid;
+ io_apic_write(ioapic_id, 0, reg_00.raw);
}
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
- ioapic_write_entry(dev->id, i, entry[i]);
+ for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+ ioapic_write_entry(ioapic_id, i, saved_data[i]);
+}
- return 0;
+static void ioapic_resume(void)
+{
+ int ioapic_id;
+
+ for (ioapic_id = nr_ioapics - 1; ioapic_id >= 0; ioapic_id--)
+ resume_ioapic(ioapic_id);
}
-static struct sysdev_class ioapic_sysdev_class = {
- .name = "ioapic",
+static struct syscore_ops ioapic_syscore_ops = {
.suspend = ioapic_suspend,
.resume = ioapic_resume,
};
-static int __init ioapic_init_sysfs(void)
+static int __init ioapic_init_ops(void)
{
- struct sys_device * dev;
- int i, size, error;
+ int i;
- error = sysdev_class_register(&ioapic_sysdev_class);
- if (error)
- return error;
+ for (i = 0; i < nr_ioapics; i++) {
+ unsigned int size;
- for (i = 0; i < nr_ioapics; i++ ) {
- size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ size = nr_ioapic_registers[i]
* sizeof(struct IO_APIC_route_entry);
- mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
- if (!mp_ioapic_data[i]) {
- printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
- continue;
- }
- dev = &mp_ioapic_data[i]->dev;
- dev->id = i;
- dev->cls = &ioapic_sysdev_class;
- error = sysdev_register(dev);
- if (error) {
- kfree(mp_ioapic_data[i]);
- mp_ioapic_data[i] = NULL;
- printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
- continue;
- }
+ ioapic_saved_data[i] = kzalloc(size, GFP_KERNEL);
+ if (!ioapic_saved_data[i])
+ pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
}
+ register_syscore_ops(&ioapic_syscore_ops);
+
return 0;
}
-device_initcall(ioapic_init_sysfs);
+device_initcall(ioapic_init_ops);
/*
* Dynamic irq allocate and deallocation
@@ -3060,7 +3025,7 @@ unsigned int create_irq_nr(unsigned int from, int node)
raw_spin_unlock_irqrestore(&vector_lock, flags);
if (ret) {
- set_irq_chip_data(irq, cfg);
+ irq_set_chip_data(irq, cfg);
irq_clear_status_flags(irq, IRQ_NOREQUEST);
} else {
free_irq_at(irq, cfg);
@@ -3085,7 +3050,7 @@ int create_irq(void)
void destroy_irq(unsigned int irq)
{
- struct irq_cfg *cfg = get_irq_chip_data(irq);
+ struct irq_cfg *cfg = irq_get_chip_data(irq);
unsigned long flags;
irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
@@ -3119,7 +3084,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
- if (irq_remapped(get_irq_chip_data(irq))) {
+ if (irq_remapped(cfg)) {
struct irte irte;
int ir_index;
u16 sub_handle;
@@ -3291,6 +3256,7 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
{
+ struct irq_chip *chip = &msi_chip;
struct msi_msg msg;
int ret;
@@ -3298,14 +3264,15 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
if (ret < 0)
return ret;
- set_irq_msi(irq, msidesc);
+ irq_set_msi_desc(irq, msidesc);
write_msi_msg(irq, &msg);
- if (irq_remapped(get_irq_chip_data(irq))) {
+ if (irq_remapped(irq_get_chip_data(irq))) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
- } else
- set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+ chip = &msi_ir_chip;
+ }
+
+ irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
@@ -3423,8 +3390,8 @@ int arch_setup_dmar_msi(unsigned int irq)
if (ret < 0)
return ret;
dmar_msi_write(irq, &msg);
- set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
+ irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+ "edge");
return 0;
}
#endif
@@ -3482,6 +3449,7 @@ static struct irq_chip hpet_msi_type = {
int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
{
+ struct irq_chip *chip = &hpet_msi_type;
struct msi_msg msg;
int ret;
@@ -3501,15 +3469,12 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
if (ret < 0)
return ret;
- hpet_msi_write(get_irq_data(irq), &msg);
+ hpet_msi_write(irq_get_handler_data(irq), &msg);
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- if (irq_remapped(get_irq_chip_data(irq)))
- set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
- handle_edge_irq, "edge");
- else
- set_irq_chip_and_handler_name(irq, &hpet_msi_type,
- handle_edge_irq, "edge");
+ if (irq_remapped(irq_get_chip_data(irq)))
+ chip = &ir_hpet_msi_type;
+ irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
return 0;
}
#endif
@@ -3596,7 +3561,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
write_ht_irq_msg(irq, &msg);
- set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+ irq_set_chip_and_handler_name(irq, &ht_irq_chip,
handle_edge_irq, "edge");
dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
@@ -3605,7 +3570,40 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
}
#endif /* CONFIG_HT_IRQ */
-int __init io_apic_get_redir_entries (int ioapic)
+static int
+io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
+{
+ struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
+ int ret;
+
+ if (!cfg)
+ return -EINVAL;
+ ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
+ if (!ret)
+ setup_ioapic_irq(attr->ioapic, attr->ioapic_pin, irq, cfg,
+ attr->trigger, attr->polarity);
+ return ret;
+}
+
+int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+ struct io_apic_irq_attr *attr)
+{
+ unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
+ int ret;
+
+ /* Avoid redundant programming */
+ if (test_bit(pin, mp_ioapic_routing[id].pin_programmed)) {
+ pr_debug("Pin %d-%d already programmed\n",
+ mp_ioapics[id].apicid, pin);
+ return 0;
+ }
+ ret = io_apic_setup_irq_pin(irq, node, attr);
+ if (!ret)
+ set_bit(pin, mp_ioapic_routing[id].pin_programmed);
+ return ret;
+}
+
+static int __init io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -3659,96 +3657,24 @@ int __init arch_probe_nr_irqs(void)
}
#endif
-static int __io_apic_set_pci_routing(struct device *dev, int irq,
- struct io_apic_irq_attr *irq_attr)
+int io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr)
{
- struct irq_cfg *cfg;
int node;
- int ioapic, pin;
- int trigger, polarity;
- ioapic = irq_attr->ioapic;
if (!IO_APIC_IRQ(irq)) {
apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
- ioapic);
+ irq_attr->ioapic);
return -EINVAL;
}
- if (dev)
- node = dev_to_node(dev);
- else
- node = cpu_to_node(0);
-
- cfg = alloc_irq_and_cfg_at(irq, node);
- if (!cfg)
- return 0;
-
- pin = irq_attr->ioapic_pin;
- trigger = irq_attr->trigger;
- polarity = irq_attr->polarity;
-
- /*
- * IRQs < 16 are already in the irq_2_pin[] map
- */
- if (irq >= legacy_pic->nr_legacy_irqs) {
- if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
- printk(KERN_INFO "can not add pin %d for irq %d\n",
- pin, irq);
- return 0;
- }
- }
-
- setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
-
- return 0;
-}
-
-int io_apic_set_pci_routing(struct device *dev, int irq,
- struct io_apic_irq_attr *irq_attr)
-{
- int ioapic, pin;
- /*
- * Avoid pin reprogramming. PRTs typically include entries
- * with redundant pin->gsi mappings (but unique PCI devices);
- * we only program the IOAPIC on the first.
- */
- ioapic = irq_attr->ioapic;
- pin = irq_attr->ioapic_pin;
- if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mp_ioapics[ioapic].apicid, pin);
- return 0;
- }
- set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
-
- return __io_apic_set_pci_routing(dev, irq, irq_attr);
-}
-
-u8 __init io_apic_unique_id(u8 id)
-{
-#ifdef CONFIG_X86_32
- if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
- !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
- return io_apic_get_unique_id(nr_ioapics, id);
- else
- return id;
-#else
- int i;
- DECLARE_BITMAP(used, 256);
+ node = dev ? dev_to_node(dev) : cpu_to_node(0);
- bitmap_zero(used, 256);
- for (i = 0; i < nr_ioapics; i++) {
- struct mpc_ioapic *ia = &mp_ioapics[i];
- __set_bit(ia->apicid, used);
- }
- if (!test_bit(id, used))
- return id;
- return find_first_zero_bit(used, 256);
-#endif
+ return io_apic_setup_irq_pin_once(irq, node, irq_attr);
}
#ifdef CONFIG_X86_32
-int __init io_apic_get_unique_id(int ioapic, int apic_id)
+static int __init io_apic_get_unique_id(int ioapic, int apic_id)
{
union IO_APIC_reg_00 reg_00;
static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -3821,9 +3747,33 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
return apic_id;
}
+
+static u8 __init io_apic_unique_id(u8 id)
+{
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+ !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+ return io_apic_get_unique_id(nr_ioapics, id);
+ else
+ return id;
+}
+#else
+static u8 __init io_apic_unique_id(u8 id)
+{
+ int i;
+ DECLARE_BITMAP(used, 256);
+
+ bitmap_zero(used, 256);
+ for (i = 0; i < nr_ioapics; i++) {
+ struct mpc_ioapic *ia = &mp_ioapics[i];
+ __set_bit(ia->apicid, used);
+ }
+ if (!test_bit(id, used))
+ return id;
+ return find_first_zero_bit(used, 256);
+}
#endif
-int __init io_apic_get_version(int ioapic)
+static int __init io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -3868,8 +3818,8 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity)
void __init setup_ioapic_dest(void)
{
int pin, ioapic, irq, irq_entry;
- struct irq_desc *desc;
const struct cpumask *mask;
+ struct irq_data *idata;
if (skip_ioapic_setup == 1)
return;
@@ -3884,21 +3834,20 @@ void __init setup_ioapic_dest(void)
if ((ioapic > 0) && (irq > 16))
continue;
- desc = irq_to_desc(irq);
+ idata = irq_get_irq_data(irq);
/*
* Honour affinities which have been set in early boot
*/
- if (desc->status &
- (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = desc->irq_data.affinity;
+ if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
+ mask = idata->affinity;
else
mask = apic->target_cpus();
if (intr_remapping_enabled)
- ir_ioapic_set_affinity(&desc->irq_data, mask, false);
+ ir_ioapic_set_affinity(idata, mask, false);
else
- ioapic_set_affinity(&desc->irq_data, mask, false);
+ ioapic_set_affinity(idata, mask, false);
}
}
@@ -4002,6 +3951,9 @@ int mp_find_ioapic(u32 gsi)
{
int i = 0;
+ if (nr_ioapics == 0)
+ return -1;
+
/* Find the IOAPIC that manages this GSI. */
for (i = 0; i < nr_ioapics; i++) {
if ((gsi >= mp_gsi_routing[i].gsi_base)
@@ -4023,10 +3975,10 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
return gsi - mp_gsi_routing[ioapic].gsi_base;
}
-static int bad_ioapic(unsigned long address)
+static __init int bad_ioapic(unsigned long address)
{
if (nr_ioapics >= MAX_IO_APICS) {
- printk(KERN_WARNING "WARING: Max # of I/O APICs (%d) exceeded "
+ printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded "
"(found %d), skipping\n", MAX_IO_APICS, nr_ioapics);
return 1;
}
@@ -4083,20 +4035,16 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
/* Enable IOAPIC early just for system timer */
void __init pre_init_apic_IRQ0(void)
{
- struct irq_cfg *cfg;
+ struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
printk(KERN_INFO "Early APIC setup for system timer0\n");
#ifndef CONFIG_SMP
physid_set_mask_of_physid(boot_cpu_physical_apicid,
&phys_cpu_present_map);
#endif
- /* Make sure the irq descriptor is set up */
- cfg = alloc_irq_and_cfg_at(0, 0);
-
setup_local_APIC();
- add_pin_to_irq_node(cfg, 0, 0, 0);
- set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
-
- setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
+ io_apic_setup_irq_pin(0, 0, &attr);
+ irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
+ "edge");
}
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 08385e090a6..cce91bf2667 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -56,6 +56,8 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
local_irq_restore(flags);
}
+#ifdef CONFIG_X86_32
+
void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
int vector)
{
@@ -71,8 +73,8 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
local_irq_save(flags);
for_each_cpu(query_cpu, mask)
__default_send_IPI_dest_field(
- apic->cpu_to_logical_apicid(query_cpu), vector,
- apic->dest_logical);
+ early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+ vector, apic->dest_logical);
local_irq_restore(flags);
}
@@ -90,14 +92,12 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
if (query_cpu == this_cpu)
continue;
__default_send_IPI_dest_field(
- apic->cpu_to_logical_apicid(query_cpu), vector,
- apic->dest_logical);
+ early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+ vector, apic->dest_logical);
}
local_irq_restore(flags);
}
-#ifdef CONFIG_X86_32
-
/*
* This is only used on smaller machines.
*/
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 960f26ab5c9..6273eee5134 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -373,13 +373,6 @@ static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask
return physids_promote(0xFUL, retmap);
}
-static inline int numaq_cpu_to_logical_apicid(int cpu)
-{
- if (cpu >= nr_cpu_ids)
- return BAD_APICID;
- return cpu_2_logical_apicid[cpu];
-}
-
/*
* Supporting over 60 cpus on NUMA-Q requires a locality-dependent
* cpu to APIC ID relation to properly interact with the intelligent
@@ -398,6 +391,15 @@ static inline int numaq_apicid_to_node(int logical_apicid)
return logical_apicid >> 4;
}
+static int numaq_numa_cpu_node(int cpu)
+{
+ int logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+
+ if (logical_apicid != BAD_APICID)
+ return numaq_apicid_to_node(logical_apicid);
+ return NUMA_NO_NODE;
+}
+
static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap)
{
int node = numaq_apicid_to_node(logical_apicid);
@@ -508,8 +510,6 @@ struct apic __refdata apic_numaq = {
.ioapic_phys_id_map = numaq_ioapic_phys_id_map,
.setup_apic_routing = numaq_setup_apic_routing,
.multi_timer_check = numaq_multi_timer_check,
- .apicid_to_node = numaq_apicid_to_node,
- .cpu_to_logical_apicid = numaq_cpu_to_logical_apicid,
.cpu_present_to_apicid = numaq_cpu_present_to_apicid,
.apicid_to_cpu_present = numaq_apicid_to_cpu_present,
.setup_portio_remap = numaq_setup_portio_remap,
@@ -547,4 +547,7 @@ struct apic __refdata apic_numaq = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+
+ .x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid,
+ .x86_32_numa_cpu_node = numaq_numa_cpu_node,
};
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 99d2fe01608..fc84c7b6110 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -77,6 +77,11 @@ void __init default_setup_apic_routing(void)
apic->setup_apic_routing();
}
+static int default_x86_32_early_logical_apicid(int cpu)
+{
+ return 1 << cpu;
+}
+
static void setup_apic_flat_routing(void)
{
#ifdef CONFIG_X86_IO_APIC
@@ -130,8 +135,6 @@ struct apic apic_default = {
.ioapic_phys_id_map = default_ioapic_phys_id_map,
.setup_apic_routing = setup_apic_flat_routing,
.multi_timer_check = NULL,
- .apicid_to_node = default_apicid_to_node,
- .cpu_to_logical_apicid = default_cpu_to_logical_apicid,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = physid_set_mask_of_physid,
.setup_portio_remap = NULL,
@@ -167,6 +170,9 @@ struct apic apic_default = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+
+ .x86_32_early_logical_apicid = default_x86_32_early_logical_apicid,
+ .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node,
};
extern struct apic apic_numaq;
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9b419263d90..e4b8059b414 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -194,11 +194,10 @@ static unsigned long summit_check_apicid_present(int bit)
return 1;
}
-static void summit_init_apic_ldr(void)
+static int summit_early_logical_apicid(int cpu)
{
- unsigned long val, id;
int count = 0;
- u8 my_id = (u8)hard_smp_processor_id();
+ u8 my_id = early_per_cpu(x86_cpu_to_apicid, cpu);
u8 my_cluster = APIC_CLUSTER(my_id);
#ifdef CONFIG_SMP
u8 lid;
@@ -206,7 +205,7 @@ static void summit_init_apic_ldr(void)
/* Create logical APIC IDs by counting CPUs already in cluster. */
for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
- lid = cpu_2_logical_apicid[i];
+ lid = early_per_cpu(x86_cpu_to_logical_apicid, i);
if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster)
++count;
}
@@ -214,7 +213,15 @@ static void summit_init_apic_ldr(void)
/* We only have a 4 wide bitmap in cluster mode. If a deranged
* BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
- id = my_cluster | (1UL << count);
+ return my_cluster | (1UL << count);
+}
+
+static void summit_init_apic_ldr(void)
+{
+ int cpu = smp_processor_id();
+ unsigned long id = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+ unsigned long val;
+
apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE);
val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
val |= SET_APIC_LOGICAL_ID(id);
@@ -232,27 +239,6 @@ static void summit_setup_apic_routing(void)
nr_ioapics);
}
-static int summit_apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
- return apicid_2_node[hard_smp_processor_id()];
-#else
- return 0;
-#endif
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int summit_cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
- if (cpu >= nr_cpu_ids)
- return BAD_APICID;
- return cpu_2_logical_apicid[cpu];
-#else
- return logical_smp_processor_id();
-#endif
-}
-
static int summit_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids)
@@ -286,7 +272,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
* The cpus in the mask must all be on the apic cluster.
*/
for_each_cpu(cpu, cpumask) {
- int new_apicid = summit_cpu_to_logical_apicid(cpu);
+ int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
printk("%s: Not a valid mask!\n", __func__);
@@ -301,7 +287,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
const struct cpumask *andmask)
{
- int apicid = summit_cpu_to_logical_apicid(0);
+ int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
cpumask_var_t cpumask;
if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -528,8 +514,6 @@ struct apic apic_summit = {
.ioapic_phys_id_map = summit_ioapic_phys_id_map,
.setup_apic_routing = summit_setup_apic_routing,
.multi_timer_check = NULL,
- .apicid_to_node = summit_apicid_to_node,
- .cpu_to_logical_apicid = summit_cpu_to_logical_apicid,
.cpu_present_to_apicid = summit_cpu_present_to_apicid,
.apicid_to_cpu_present = summit_apicid_to_cpu_present,
.setup_portio_remap = NULL,
@@ -565,4 +549,7 @@ struct apic apic_summit = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+
+ .x86_32_early_logical_apicid = summit_early_logical_apicid,
+ .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node,
};
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cf69c59f491..90949bbd566 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -206,8 +206,6 @@ struct apic apic_x2apic_cluster = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
- .apicid_to_node = NULL,
- .cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8972f38c5ce..c7e6d6645bf 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -195,8 +195,6 @@ struct apic apic_x2apic_phys = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
- .apicid_to_node = NULL,
- .cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index bd16b58b885..7acd2d2ac96 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -23,6 +23,8 @@
#include <linux/io.h>
#include <linux/pci.h>
#include <linux/kdebug.h>
+#include <linux/delay.h>
+#include <linux/crash_dump.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
@@ -34,6 +36,14 @@
#include <asm/ipi.h>
#include <asm/smp.h>
#include <asm/x86_init.h>
+#include <asm/emergency-restart.h>
+#include <asm/nmi.h>
+
+/* BMC sets a bit this MMR non-zero before sending an NMI */
+#define UVH_NMI_MMR UVH_SCRATCH5
+#define UVH_NMI_MMR_CLEAR (UVH_NMI_MMR + 8)
+#define UV_NMI_PENDING_MASK (1UL << 63)
+DEFINE_PER_CPU(unsigned long, cpu_last_nmi_count);
DEFINE_PER_CPU(int, x2apic_extra_bits);
@@ -338,8 +348,6 @@ struct apic __refdata apic_x2apic_uv_x = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
- .apicid_to_node = NULL,
- .cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
@@ -641,18 +649,46 @@ void __cpuinit uv_cpu_init(void)
*/
int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
{
+ unsigned long real_uv_nmi;
+ int bid;
+
if (reason != DIE_NMIUNKNOWN)
return NOTIFY_OK;
if (in_crash_kexec)
/* do nothing if entering the crash kernel */
return NOTIFY_OK;
+
+ /*
+ * Each blade has an MMR that indicates when an NMI has been sent
+ * to cpus on the blade. If an NMI is detected, atomically
+ * clear the MMR and update a per-blade NMI count used to
+ * cause each cpu on the blade to notice a new NMI.
+ */
+ bid = uv_numa_blade_id();
+ real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
+
+ if (unlikely(real_uv_nmi)) {
+ spin_lock(&uv_blade_info[bid].nmi_lock);
+ real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
+ if (real_uv_nmi) {
+ uv_blade_info[bid].nmi_count++;
+ uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK);
+ }
+ spin_unlock(&uv_blade_info[bid].nmi_lock);
+ }
+
+ if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
+ return NOTIFY_DONE;
+
+ __get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count;
+
/*
- * Use a lock so only one cpu prints at a time
- * to prevent intermixed output.
+ * Use a lock so only one cpu prints at a time.
+ * This prevents intermixed output.
*/
spin_lock(&uv_nmi_lock);
- pr_info("NMI stack dump cpu %u:\n", smp_processor_id());
+ pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id());
dump_stack();
spin_unlock(&uv_nmi_lock);
@@ -660,7 +696,8 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
}
static struct notifier_block uv_dump_stack_nmi_nb = {
- .notifier_call = uv_handle_nmi
+ .notifier_call = uv_handle_nmi,
+ .priority = NMI_LOCAL_LOW_PRIOR - 1,
};
void uv_register_nmi_notifier(void)
@@ -719,8 +756,9 @@ void __init uv_system_init(void)
printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
- uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+ uv_blade_info = kzalloc(bytes, GFP_KERNEL);
BUG_ON(!uv_blade_info);
+
for (blade = 0; blade < uv_num_possible_blades(); blade++)
uv_blade_info[blade].memory_nid = -1;
@@ -746,6 +784,7 @@ void __init uv_system_init(void)
uv_blade_info[blade].pnode = pnode;
uv_blade_info[blade].nr_possible_cpus = 0;
uv_blade_info[blade].nr_online_cpus = 0;
+ spin_lock_init(&uv_blade_info[blade].nmi_lock);
max_pnode = max(pnode, max_pnode);
blade++;
}
@@ -812,4 +851,11 @@ void __init uv_system_init(void)
/* register Legacy VGA I/O redirection handler */
pci_register_set_vga_state(uv_set_vga_state);
+
+ /*
+ * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
+ * EFI is not enabled in the kdump kernel.
+ */
+ if (is_kdump_kernel())
+ reboot_type = BOOT_ACPI;
}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0e4f24c2a74..adee12e0da1 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -66,7 +66,7 @@
* 1.5: Fix segment register reloading (in case of bad segments saved
* across BIOS call).
* Stephen Rothwell
- * 1.6: Cope with complier/assembler differences.
+ * 1.6: Cope with compiler/assembler differences.
* Only try to turn off the first display device.
* Fix OOPS at power off with no APM BIOS by Jan Echternach
* <echter@informatik.uni-rostock.de>
@@ -227,6 +227,8 @@
#include <linux/suspend.h>
#include <linux/kthread.h>
#include <linux/jiffies.h>
+#include <linux/acpi.h>
+#include <linux/syscore_ops.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -975,20 +977,10 @@ recalc:
static void apm_power_off(void)
{
- unsigned char po_bios_call[] = {
- 0xb8, 0x00, 0x10, /* movw $0x1000,ax */
- 0x8e, 0xd0, /* movw ax,ss */
- 0xbc, 0x00, 0xf0, /* movw $0xf000,sp */
- 0xb8, 0x07, 0x53, /* movw $0x5307,ax */
- 0xbb, 0x01, 0x00, /* movw $0x0001,bx */
- 0xb9, 0x03, 0x00, /* movw $0x0003,cx */
- 0xcd, 0x15 /* int $0x15 */
- };
-
/* Some bioses don't like being called from CPU != 0 */
if (apm_info.realmode_power_off) {
set_cpus_allowed_ptr(current, cpumask_of(0));
- machine_real_restart(po_bios_call, sizeof(po_bios_call));
+ machine_real_restart(MRR_APM);
} else {
(void)set_system_power_state(APM_STATE_OFF);
}
@@ -1247,6 +1239,7 @@ static int suspend(int vetoable)
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
+ syscore_suspend();
local_irq_enable();
@@ -1264,6 +1257,7 @@ static int suspend(int vetoable)
apm_error("suspend", err);
err = (err == APM_SUCCESS) ? 0 : -EIO;
+ syscore_resume();
sysdev_resume();
local_irq_enable();
@@ -1289,6 +1283,7 @@ static void standby(void)
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
+ syscore_suspend();
local_irq_enable();
err = set_system_power_state(APM_STATE_STANDBY);
@@ -1296,6 +1291,7 @@ static void standby(void)
apm_error("standby", err);
local_irq_disable();
+ syscore_resume();
sysdev_resume();
local_irq_enable();
@@ -2331,12 +2327,11 @@ static int __init apm_init(void)
apm_info.disabled = 1;
return -ENODEV;
}
- if (pm_flags & PM_ACPI) {
+ if (!acpi_disabled) {
printk(KERN_NOTICE "apm: overridden by ACPI.\n");
apm_info.disabled = 1;
return -ENODEV;
}
- pm_flags |= PM_APM;
/*
* Set up the long jump entry point to the APM BIOS, which is called
@@ -2428,7 +2423,6 @@ static void __exit apm_exit(void)
kthread_stop(kapmd_task);
kapmd_task = NULL;
}
- pm_flags &= ~PM_APM;
}
module_init(apm_init);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index cfa82c899f4..4f13fafc526 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -1,5 +1,70 @@
+/*
+ * Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed to extract
+ * and format the required data.
+ */
+#define COMPILE_OFFSETS
+
+#include <linux/crypto.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/hardirq.h>
+#include <linux/suspend.h>
+#include <linux/kbuild.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+#include <asm/sigframe.h>
+#include <asm/bootparam.h>
+#include <asm/suspend.h>
+
+#ifdef CONFIG_XEN
+#include <xen/interface/xen.h>
+#endif
+
#ifdef CONFIG_X86_32
# include "asm-offsets_32.c"
#else
# include "asm-offsets_64.c"
#endif
+
+void common(void) {
+ BLANK();
+ OFFSET(TI_flags, thread_info, flags);
+ OFFSET(TI_status, thread_info, status);
+ OFFSET(TI_addr_limit, thread_info, addr_limit);
+ OFFSET(TI_preempt_count, thread_info, preempt_count);
+
+ BLANK();
+ OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
+
+ BLANK();
+ OFFSET(pbe_address, pbe, address);
+ OFFSET(pbe_orig_address, pbe, orig_address);
+ OFFSET(pbe_next, pbe, next);
+
+#ifdef CONFIG_PARAVIRT
+ BLANK();
+ OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
+ OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
+ OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
+ OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
+ OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
+ OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+ OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+ OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
+ OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+#endif
+
+#ifdef CONFIG_XEN
+ BLANK();
+ OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
+ OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+#endif
+
+ BLANK();
+ OFFSET(BP_scratch, boot_params, scratch);
+ OFFSET(BP_loadflags, boot_params, hdr.loadflags);
+ OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
+ OFFSET(BP_version, boot_params, hdr.version);
+ OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+}
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 1a4088dda37..c29d631af6f 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -1,26 +1,4 @@
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed
- * to extract and format the required data.
- */
-
-#include <linux/crypto.h>
-#include <linux/sched.h>
-#include <linux/signal.h>
-#include <linux/personality.h>
-#include <linux/suspend.h>
-#include <linux/kbuild.h>
#include <asm/ucontext.h>
-#include <asm/sigframe.h>
-#include <asm/pgtable.h>
-#include <asm/fixmap.h>
-#include <asm/processor.h>
-#include <asm/thread_info.h>
-#include <asm/bootparam.h>
-#include <asm/elf.h>
-#include <asm/suspend.h>
-
-#include <xen/interface/xen.h>
#include <linux/lguest.h>
#include "../../../drivers/lguest/lg.h"
@@ -51,21 +29,10 @@ void foo(void)
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
BLANK();
- OFFSET(TI_task, thread_info, task);
- OFFSET(TI_exec_domain, thread_info, exec_domain);
- OFFSET(TI_flags, thread_info, flags);
- OFFSET(TI_status, thread_info, status);
- OFFSET(TI_preempt_count, thread_info, preempt_count);
- OFFSET(TI_addr_limit, thread_info, addr_limit);
- OFFSET(TI_restart_block, thread_info, restart_block);
OFFSET(TI_sysenter_return, thread_info, sysenter_return);
OFFSET(TI_cpu, thread_info, cpu);
BLANK();
- OFFSET(GDS_size, desc_ptr, size);
- OFFSET(GDS_address, desc_ptr, address);
- BLANK();
-
OFFSET(PT_EBX, pt_regs, bx);
OFFSET(PT_ECX, pt_regs, cx);
OFFSET(PT_EDX, pt_regs, dx);
@@ -85,42 +52,13 @@ void foo(void)
OFFSET(PT_OLDSS, pt_regs, ss);
BLANK();
- OFFSET(EXEC_DOMAIN_handler, exec_domain, handler);
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
BLANK();
- OFFSET(pbe_address, pbe, address);
- OFFSET(pbe_orig_address, pbe, orig_address);
- OFFSET(pbe_next, pbe, next);
-
/* Offset from the sysenter stack to tss.sp0 */
DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
sizeof(struct tss_struct));
- DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
- DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT);
- DEFINE(THREAD_SIZE_asm, THREAD_SIZE);
-
- OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
-
-#ifdef CONFIG_PARAVIRT
- BLANK();
- OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
- OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
- OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
- OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
- OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
-#endif
-
-#ifdef CONFIG_XEN
- BLANK();
- OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
- OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
-#endif
-
#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
BLANK();
OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
@@ -139,11 +77,4 @@ void foo(void)
OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
#endif
-
- BLANK();
- OFFSET(BP_scratch, boot_params, scratch);
- OFFSET(BP_loadflags, boot_params, hdr.loadflags);
- OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
- OFFSET(BP_version, boot_params, hdr.version);
- OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 4a6aeedcd96..e72a1194af2 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,27 +1,4 @@
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed to extract
- * and format the required data.
- */
-#define COMPILE_OFFSETS
-
-#include <linux/crypto.h>
-#include <linux/sched.h>
-#include <linux/stddef.h>
-#include <linux/errno.h>
-#include <linux/hardirq.h>
-#include <linux/suspend.h>
-#include <linux/kbuild.h>
-#include <asm/processor.h>
-#include <asm/segment.h>
-#include <asm/thread_info.h>
#include <asm/ia32.h>
-#include <asm/bootparam.h>
-#include <asm/suspend.h>
-
-#include <xen/interface/xen.h>
-
-#include <asm/sigframe.h>
#define __NO_STUBS 1
#undef __SYSCALL
@@ -33,41 +10,19 @@ static char syscalls[] = {
int main(void)
{
-#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
- ENTRY(state);
- ENTRY(flags);
- ENTRY(pid);
- BLANK();
-#undef ENTRY
-#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry))
- ENTRY(flags);
- ENTRY(addr_limit);
- ENTRY(preempt_count);
- ENTRY(status);
-#ifdef CONFIG_IA32_EMULATION
- ENTRY(sysenter_return);
-#endif
- BLANK();
-#undef ENTRY
#ifdef CONFIG_PARAVIRT
- BLANK();
- OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
- OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
- OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
- OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
- OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+ BLANK();
#endif
-
#ifdef CONFIG_IA32_EMULATION
-#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct sigcontext_ia32, entry))
+ OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+ BLANK();
+
+#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
ENTRY(ax);
ENTRY(bx);
ENTRY(cx);
@@ -79,15 +34,12 @@ int main(void)
ENTRY(ip);
BLANK();
#undef ENTRY
- DEFINE(IA32_RT_SIGFRAME_sigcontext,
- offsetof (struct rt_sigframe_ia32, uc.uc_mcontext));
+
+ OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
BLANK();
#endif
- DEFINE(pbe_address, offsetof(struct pbe, address));
- DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
- DEFINE(pbe_next, offsetof(struct pbe, next));
- BLANK();
-#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry))
+
+#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
ENTRY(bx);
ENTRY(cx);
@@ -107,7 +59,8 @@ int main(void)
ENTRY(flags);
BLANK();
#undef ENTRY
-#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry))
+
+#define ENTRY(entry) OFFSET(saved_context_ ## entry, saved_context, entry)
ENTRY(cr0);
ENTRY(cr2);
ENTRY(cr3);
@@ -115,26 +68,11 @@ int main(void)
ENTRY(cr8);
BLANK();
#undef ENTRY
- DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist));
- BLANK();
- DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
- BLANK();
- DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+ OFFSET(TSS_ist, tss_struct, x86_tss.ist);
BLANK();
- OFFSET(BP_scratch, boot_params, scratch);
- OFFSET(BP_loadflags, boot_params, hdr.loadflags);
- OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
- OFFSET(BP_version, boot_params, hdr.version);
- OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
- BLANK();
- DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
-#ifdef CONFIG_XEN
- BLANK();
- OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
- OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
-#undef ENTRY
-#endif
+ DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+
return 0;
}
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 13a38917951..452932d3473 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -106,8 +106,8 @@ void __init setup_bios_corruption_check(void)
addr += size;
}
- printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
- num_scan_areas);
+ if (num_scan_areas)
+ printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas);
}
@@ -143,12 +143,12 @@ static void check_corruption(struct work_struct *dummy)
{
check_for_bios_corruption();
schedule_delayed_work(&bios_check_work,
- round_jiffies_relative(corruption_check_period*HZ));
+ round_jiffies_relative(corruption_check_period*HZ));
}
static int start_periodic_check_for_corruption(void)
{
- if (!memory_corruption_check || corruption_check_period == 0)
+ if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0)
return 0;
printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 3f0ebe429a0..6042981d030 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -30,7 +30,6 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o
obj-$(CONFIG_X86_MCE) += mcheck/
obj-$(CONFIG_MTRR) += mtrr/
-obj-$(CONFIG_CPU_FREQ) += cpufreq/
obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7c7bedb83c5..6f9d1f6063e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -233,18 +233,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
}
#endif
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config. Read the comment in
+ * srat_detect_node().
+ */
static int __cpuinit nearby_node(int apicid)
{
int i, node;
for (i = apicid - 1; i >= 0; i--) {
- node = apicid_to_node[i];
+ node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
- node = apicid_to_node[i];
+ node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
@@ -261,7 +265,7 @@ static int __cpuinit nearby_node(int apicid)
#ifdef CONFIG_X86_HT
static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
{
- u32 nodes;
+ u32 nodes, cores_per_cu = 1;
u8 node_id;
int cpu = smp_processor_id();
@@ -276,6 +280,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
/* get compute unit information */
smp_num_siblings = ((ebx >> 8) & 3) + 1;
c->compute_unit_id = ebx & 0xff;
+ cores_per_cu += ((ebx >> 8) & 3);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
@@ -288,15 +293,18 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
/* fixup multi-node processor information */
if (nodes > 1) {
u32 cores_per_node;
+ u32 cus_per_node;
set_cpu_cap(c, X86_FEATURE_AMD_DCM);
cores_per_node = c->x86_max_cores / nodes;
+ cus_per_node = cores_per_node / cores_per_cu;
/* store NodeID, use llc_shared_map to store sibling info */
per_cpu(cpu_llc_id, cpu) = node_id;
- /* core id to be in range from 0 to (cores_per_node - 1) */
- c->cpu_core_id = c->cpu_core_id % cores_per_node;
+ /* core id has to be in the [0 .. cores_per_node - 1] range */
+ c->cpu_core_id %= cores_per_node;
+ c->compute_unit_id %= cus_per_node;
}
}
#endif
@@ -334,31 +342,40 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id);
static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
unsigned apicid = c->apicid;
- node = per_cpu(cpu_llc_id, cpu);
+ node = numa_cpu_node(cpu);
+ if (node == NUMA_NO_NODE)
+ node = per_cpu(cpu_llc_id, cpu);
- if (apicid_to_node[apicid] != NUMA_NO_NODE)
- node = apicid_to_node[apicid];
if (!node_online(node)) {
- /* Two possibilities here:
- - The CPU is missing memory and no node was created.
- In that case try picking one from a nearby CPU
- - The APIC IDs differ from the HyperTransport node IDs
- which the K8 northbridge parsing fills in.
- Assume they are all increased by a constant offset,
- but in the same order as the HT nodeids.
- If that doesn't result in a usable node fall back to the
- path for the previous case. */
-
+ /*
+ * Two possibilities here:
+ *
+ * - The CPU is missing memory and no node was created. In
+ * that case try picking one from a nearby CPU.
+ *
+ * - The APIC IDs differ from the HyperTransport node IDs
+ * which the K8 northbridge parsing fills in. Assume
+ * they are all increased by a constant offset, but in
+ * the same order as the HT nodeids. If that doesn't
+ * result in a usable node fall back to the path for the
+ * previous case.
+ *
+ * This workaround operates directly on the mapping between
+ * APIC ID and NUMA node, assuming certain relationship
+ * between APIC ID, HT node ID and NUMA topology. As going
+ * through CPU mapping may alter the outcome, directly
+ * access __apicid_to_node[].
+ */
int ht_nodeid = c->initial_apicid;
if (ht_nodeid >= 0 &&
- apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
- node = apicid_to_node[ht_nodeid];
+ __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+ node = __apicid_to_node[ht_nodeid];
/* Pick a nearby node */
if (!node_online(node))
node = nearby_node(apicid);
@@ -594,6 +611,29 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
#endif
+
+ /* As a rule processors have APIC timer running in deep C states */
+ if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+ set_cpu_cap(c, X86_FEATURE_ARAT);
+
+ /*
+ * Disable GART TLB Walk Errors on Fam10h. We do this here
+ * because this is always needed when GART is enabled, even in a
+ * kernel which has no MCE support built in.
+ */
+ if (c->x86 == 0x10) {
+ /*
+ * BIOS should disable GartTlbWlk Errors themself. If
+ * it doesn't do it here as suggested by the BKDG.
+ *
+ * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+ */
+ u64 mask;
+
+ rdmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ mask |= (1 << 10);
+ wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ }
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1d59834396b..e2ced0074a4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -675,7 +675,7 @@ void __init early_cpu_init(void)
const struct cpu_dev *const *cdev;
int count = 0;
-#ifdef PROCESSOR_SELECT
+#ifdef CONFIG_PROCESSOR_SELECT
printk(KERN_INFO "KERNEL supported cpus:\n");
#endif
@@ -687,7 +687,7 @@ void __init early_cpu_init(void)
cpu_devs[count] = cpudev;
count++;
-#ifdef PROCESSOR_SELECT
+#ifdef CONFIG_PROCESSOR_SELECT
{
unsigned int j;
@@ -869,7 +869,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
select_idle_routine(c);
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
numa_add_cpu(smp_processor_id());
#endif
}
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
deleted file mode 100644
index 870e6cc6ad2..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ /dev/null
@@ -1,266 +0,0 @@
-#
-# CPU Frequency scaling
-#
-
-menu "CPU Frequency scaling"
-
-source "drivers/cpufreq/Kconfig"
-
-if CPU_FREQ
-
-comment "CPUFreq processor drivers"
-
-config X86_PCC_CPUFREQ
- tristate "Processor Clocking Control interface driver"
- depends on ACPI && ACPI_PROCESSOR
- help
- This driver adds support for the PCC interface.
-
- For details, take a look at:
- <file:Documentation/cpu-freq/pcc-cpufreq.txt>.
-
- To compile this driver as a module, choose M here: the
- module will be called pcc-cpufreq.
-
- If in doubt, say N.
-
-config X86_ACPI_CPUFREQ
- tristate "ACPI Processor P-States driver"
- select CPU_FREQ_TABLE
- depends on ACPI_PROCESSOR
- help
- This driver adds a CPUFreq driver which utilizes the ACPI
- Processor Performance States.
- This driver also supports Intel Enhanced Speedstep.
-
- To compile this driver as a module, choose M here: the
- module will be called acpi-cpufreq.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config ELAN_CPUFREQ
- tristate "AMD Elan SC400 and SC410"
- select CPU_FREQ_TABLE
- depends on X86_ELAN
- ---help---
- This adds the CPUFreq driver for AMD Elan SC400 and SC410
- processors.
-
- You need to specify the processor maximum speed as boot
- parameter: elanfreq=maxspeed (in kHz) or as module
- parameter "max_freq".
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config SC520_CPUFREQ
- tristate "AMD Elan SC520"
- select CPU_FREQ_TABLE
- depends on X86_ELAN
- ---help---
- This adds the CPUFreq driver for AMD Elan SC520 processor.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-
-config X86_POWERNOW_K6
- tristate "AMD Mobile K6-2/K6-3 PowerNow!"
- select CPU_FREQ_TABLE
- depends on X86_32
- help
- This adds the CPUFreq driver for mobile AMD K6-2+ and mobile
- AMD K6-3+ processors.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_POWERNOW_K7
- tristate "AMD Mobile Athlon/Duron PowerNow!"
- select CPU_FREQ_TABLE
- depends on X86_32
- help
- This adds the CPUFreq driver for mobile AMD K7 mobile processors.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_POWERNOW_K7_ACPI
- bool
- depends on X86_POWERNOW_K7 && ACPI_PROCESSOR
- depends on !(X86_POWERNOW_K7 = y && ACPI_PROCESSOR = m)
- depends on X86_32
- default y
-
-config X86_POWERNOW_K8
- tristate "AMD Opteron/Athlon64 PowerNow!"
- select CPU_FREQ_TABLE
- depends on ACPI && ACPI_PROCESSOR
- help
- This adds the CPUFreq driver for K8/K10 Opteron/Athlon64 processors.
-
- To compile this driver as a module, choose M here: the
- module will be called powernow-k8.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
-config X86_GX_SUSPMOD
- tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation"
- depends on X86_32 && PCI
- help
- This add the CPUFreq driver for NatSemi Geode processors which
- support suspend modulation.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_SPEEDSTEP_CENTRINO
- tristate "Intel Enhanced SpeedStep (deprecated)"
- select CPU_FREQ_TABLE
- select X86_SPEEDSTEP_CENTRINO_TABLE if X86_32
- depends on X86_32 || (X86_64 && ACPI_PROCESSOR)
- help
- This is deprecated and this functionality is now merged into
- acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of
- speedstep_centrino.
- This adds the CPUFreq driver for Enhanced SpeedStep enabled
- mobile CPUs. This means Intel Pentium M (Centrino) CPUs
- or 64bit enabled Intel Xeons.
-
- To compile this driver as a module, choose M here: the
- module will be called speedstep-centrino.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_SPEEDSTEP_CENTRINO_TABLE
- bool "Built-in tables for Banias CPUs"
- depends on X86_32 && X86_SPEEDSTEP_CENTRINO
- default y
- help
- Use built-in tables for Banias CPUs if ACPI encoding
- is not available.
-
- If in doubt, say N.
-
-config X86_SPEEDSTEP_ICH
- tristate "Intel Speedstep on ICH-M chipsets (ioport interface)"
- select CPU_FREQ_TABLE
- depends on X86_32
- help
- This adds the CPUFreq driver for certain mobile Intel Pentium III
- (Coppermine), all mobile Intel Pentium III-M (Tualatin) and all
- mobile Intel Pentium 4 P4-M on systems which have an Intel ICH2,
- ICH3 or ICH4 southbridge.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_SPEEDSTEP_SMI
- tristate "Intel SpeedStep on 440BX/ZX/MX chipsets (SMI interface)"
- select CPU_FREQ_TABLE
- depends on X86_32 && EXPERIMENTAL
- help
- This adds the CPUFreq driver for certain mobile Intel Pentium III
- (Coppermine), all mobile Intel Pentium III-M (Tualatin)
- on systems which have an Intel 440BX/ZX/MX southbridge.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_P4_CLOCKMOD
- tristate "Intel Pentium 4 clock modulation"
- select CPU_FREQ_TABLE
- help
- This adds the CPUFreq driver for Intel Pentium 4 / XEON
- processors. When enabled it will lower CPU temperature by skipping
- clocks.
-
- This driver should be only used in exceptional
- circumstances when very low power is needed because it causes severe
- slowdowns and noticeable latencies. Normally Speedstep should be used
- instead.
-
- To compile this driver as a module, choose M here: the
- module will be called p4-clockmod.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- Unless you are absolutely sure say N.
-
-config X86_CPUFREQ_NFORCE2
- tristate "nVidia nForce2 FSB changing"
- depends on X86_32 && EXPERIMENTAL
- help
- This adds the CPUFreq driver for FSB changing on nVidia nForce2
- platforms.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_LONGRUN
- tristate "Transmeta LongRun"
- depends on X86_32
- help
- This adds the CPUFreq driver for Transmeta Crusoe and Efficeon processors
- which support LongRun.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_LONGHAUL
- tristate "VIA Cyrix III Longhaul"
- select CPU_FREQ_TABLE
- depends on X86_32 && ACPI_PROCESSOR
- help
- This adds the CPUFreq driver for VIA Samuel/CyrixIII,
- VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T
- processors.
-
- For details, take a look at <file:Documentation/cpu-freq/>.
-
- If in doubt, say N.
-
-config X86_E_POWERSAVER
- tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
- select CPU_FREQ_TABLE
- depends on X86_32 && EXPERIMENTAL
- help
- This adds the CPUFreq driver for VIA C7 processors. However, this driver
- does not have any safeguards to prevent operating the CPU out of spec
- and is thus considered dangerous. Please use the regular ACPI cpufreq
- driver, enabled by CONFIG_X86_ACPI_CPUFREQ.
-
- If in doubt, say N.
-
-comment "shared options"
-
-config X86_SPEEDSTEP_LIB
- tristate
- default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
-
-config X86_SPEEDSTEP_RELAXED_CAP_CHECK
- bool "Relaxed speedstep capability checks"
- depends on X86_32 && (X86_SPEEDSTEP_SMI || X86_SPEEDSTEP_ICH)
- help
- Don't perform all checks for a speedstep capable system which would
- normally be done. Some ancient or strange systems, though speedstep
- capable, don't always indicate that they are speedstep capable. This
- option lets the probing code bypass some of those checks if the
- parameter "relaxed_check=1" is passed to the module.
-
-endif # CPU_FREQ
-
-endmenu
diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile
deleted file mode 100644
index bd54bf67e6f..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/Makefile
+++ /dev/null
@@ -1,21 +0,0 @@
-# Link order matters. K8 is preferred to ACPI because of firmware bugs in early
-# K8 systems. ACPI is preferred to all other hardware-specific drivers.
-# speedstep-* is preferred over p4-clockmod.
-
-obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o mperf.o
-obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o mperf.o
-obj-$(CONFIG_X86_PCC_CPUFREQ) += pcc-cpufreq.o
-obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o
-obj-$(CONFIG_X86_POWERNOW_K7) += powernow-k7.o
-obj-$(CONFIG_X86_LONGHAUL) += longhaul.o
-obj-$(CONFIG_X86_E_POWERSAVER) += e_powersaver.o
-obj-$(CONFIG_ELAN_CPUFREQ) += elanfreq.o
-obj-$(CONFIG_SC520_CPUFREQ) += sc520_freq.o
-obj-$(CONFIG_X86_LONGRUN) += longrun.o
-obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o
-obj-$(CONFIG_X86_SPEEDSTEP_ICH) += speedstep-ich.o
-obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o
-obj-$(CONFIG_X86_SPEEDSTEP_SMI) += speedstep-smi.o
-obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o
-obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o
-obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
deleted file mode 100644
index a2baafb2fe6..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ /dev/null
@@ -1,776 +0,0 @@
-/*
- * acpi-cpufreq.c - ACPI Processor P-States Driver
- *
- * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
- * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
- * Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de>
- * Copyright (C) 2006 Denis Sadykov <denis.m.sadykov@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/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/cpufreq.h>
-#include <linux/compiler.h>
-#include <linux/dmi.h>
-#include <linux/slab.h>
-
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-#include <linux/uaccess.h>
-
-#include <acpi/processor.h>
-
-#include <asm/msr.h>
-#include <asm/processor.h>
-#include <asm/cpufeature.h>
-#include "mperf.h"
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "acpi-cpufreq", msg)
-
-MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
-MODULE_DESCRIPTION("ACPI Processor P-States Driver");
-MODULE_LICENSE("GPL");
-
-enum {
- UNDEFINED_CAPABLE = 0,
- SYSTEM_INTEL_MSR_CAPABLE,
- SYSTEM_IO_CAPABLE,
-};
-
-#define INTEL_MSR_RANGE (0xffff)
-
-struct acpi_cpufreq_data {
- struct acpi_processor_performance *acpi_data;
- struct cpufreq_frequency_table *freq_table;
- unsigned int resume;
- unsigned int cpu_feature;
-};
-
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
-
-/* acpi_perf_data is a pointer to percpu data. */
-static struct acpi_processor_performance __percpu *acpi_perf_data;
-
-static struct cpufreq_driver acpi_cpufreq_driver;
-
-static unsigned int acpi_pstate_strict;
-
-static int check_est_cpu(unsigned int cpuid)
-{
- struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
-
- return cpu_has(cpu, X86_FEATURE_EST);
-}
-
-static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
-{
- struct acpi_processor_performance *perf;
- int i;
-
- perf = data->acpi_data;
-
- for (i = 0; i < perf->state_count; i++) {
- if (value == perf->states[i].status)
- return data->freq_table[i].frequency;
- }
- return 0;
-}
-
-static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
-{
- int i;
- struct acpi_processor_performance *perf;
-
- msr &= INTEL_MSR_RANGE;
- perf = data->acpi_data;
-
- for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
- if (msr == perf->states[data->freq_table[i].index].status)
- return data->freq_table[i].frequency;
- }
- return data->freq_table[0].frequency;
-}
-
-static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
-{
- switch (data->cpu_feature) {
- case SYSTEM_INTEL_MSR_CAPABLE:
- return extract_msr(val, data);
- case SYSTEM_IO_CAPABLE:
- return extract_io(val, data);
- default:
- return 0;
- }
-}
-
-struct msr_addr {
- u32 reg;
-};
-
-struct io_addr {
- u16 port;
- u8 bit_width;
-};
-
-struct drv_cmd {
- unsigned int type;
- const struct cpumask *mask;
- union {
- struct msr_addr msr;
- struct io_addr io;
- } addr;
- u32 val;
-};
-
-/* Called via smp_call_function_single(), on the target CPU */
-static void do_drv_read(void *_cmd)
-{
- struct drv_cmd *cmd = _cmd;
- u32 h;
-
- switch (cmd->type) {
- case SYSTEM_INTEL_MSR_CAPABLE:
- rdmsr(cmd->addr.msr.reg, cmd->val, h);
- break;
- case SYSTEM_IO_CAPABLE:
- acpi_os_read_port((acpi_io_address)cmd->addr.io.port,
- &cmd->val,
- (u32)cmd->addr.io.bit_width);
- break;
- default:
- break;
- }
-}
-
-/* Called via smp_call_function_many(), on the target CPUs */
-static void do_drv_write(void *_cmd)
-{
- struct drv_cmd *cmd = _cmd;
- u32 lo, hi;
-
- switch (cmd->type) {
- case SYSTEM_INTEL_MSR_CAPABLE:
- rdmsr(cmd->addr.msr.reg, lo, hi);
- lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
- wrmsr(cmd->addr.msr.reg, lo, hi);
- break;
- case SYSTEM_IO_CAPABLE:
- acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
- cmd->val,
- (u32)cmd->addr.io.bit_width);
- break;
- default:
- break;
- }
-}
-
-static void drv_read(struct drv_cmd *cmd)
-{
- int err;
- cmd->val = 0;
-
- err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
- WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */
-}
-
-static void drv_write(struct drv_cmd *cmd)
-{
- int this_cpu;
-
- this_cpu = get_cpu();
- if (cpumask_test_cpu(this_cpu, cmd->mask))
- do_drv_write(cmd);
- smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
- put_cpu();
-}
-
-static u32 get_cur_val(const struct cpumask *mask)
-{
- struct acpi_processor_performance *perf;
- struct drv_cmd cmd;
-
- if (unlikely(cpumask_empty(mask)))
- return 0;
-
- switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
- case SYSTEM_INTEL_MSR_CAPABLE:
- cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
- cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
- break;
- case SYSTEM_IO_CAPABLE:
- cmd.type = SYSTEM_IO_CAPABLE;
- perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
- cmd.addr.io.port = perf->control_register.address;
- cmd.addr.io.bit_width = perf->control_register.bit_width;
- break;
- default:
- return 0;
- }
-
- cmd.mask = mask;
- drv_read(&cmd);
-
- dprintk("get_cur_val = %u\n", cmd.val);
-
- return cmd.val;
-}
-
-static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
-{
- struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
- unsigned int freq;
- unsigned int cached_freq;
-
- dprintk("get_cur_freq_on_cpu (%d)\n", cpu);
-
- if (unlikely(data == NULL ||
- data->acpi_data == NULL || data->freq_table == NULL)) {
- return 0;
- }
-
- cached_freq = data->freq_table[data->acpi_data->state].frequency;
- freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
- if (freq != cached_freq) {
- /*
- * The dreaded BIOS frequency change behind our back.
- * Force set the frequency on next target call.
- */
- data->resume = 1;
- }
-
- dprintk("cur freq = %u\n", freq);
-
- return freq;
-}
-
-static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
- struct acpi_cpufreq_data *data)
-{
- unsigned int cur_freq;
- unsigned int i;
-
- for (i = 0; i < 100; i++) {
- cur_freq = extract_freq(get_cur_val(mask), data);
- if (cur_freq == freq)
- return 1;
- udelay(10);
- }
- return 0;
-}
-
-static int acpi_cpufreq_target(struct cpufreq_policy *policy,
- unsigned int target_freq, unsigned int relation)
-{
- struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
- struct acpi_processor_performance *perf;
- struct cpufreq_freqs freqs;
- struct drv_cmd cmd;
- unsigned int next_state = 0; /* Index into freq_table */
- unsigned int next_perf_state = 0; /* Index into perf table */
- unsigned int i;
- int result = 0;
-
- dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
-
- if (unlikely(data == NULL ||
- data->acpi_data == NULL || data->freq_table == NULL)) {
- return -ENODEV;
- }
-
- perf = data->acpi_data;
- result = cpufreq_frequency_table_target(policy,
- data->freq_table,
- target_freq,
- relation, &next_state);
- if (unlikely(result)) {
- result = -ENODEV;
- goto out;
- }
-
- next_perf_state = data->freq_table[next_state].index;
- if (perf->state == next_perf_state) {
- if (unlikely(data->resume)) {
- dprintk("Called after resume, resetting to P%d\n",
- next_perf_state);
- data->resume = 0;
- } else {
- dprintk("Already at target state (P%d)\n",
- next_perf_state);
- goto out;
- }
- }
-
- switch (data->cpu_feature) {
- case SYSTEM_INTEL_MSR_CAPABLE:
- cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
- cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
- cmd.val = (u32) perf->states[next_perf_state].control;
- break;
- case SYSTEM_IO_CAPABLE:
- cmd.type = SYSTEM_IO_CAPABLE;
- cmd.addr.io.port = perf->control_register.address;
- cmd.addr.io.bit_width = perf->control_register.bit_width;
- cmd.val = (u32) perf->states[next_perf_state].control;
- break;
- default:
- result = -ENODEV;
- goto out;
- }
-
- /* cpufreq holds the hotplug lock, so we are safe from here on */
- if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
- cmd.mask = policy->cpus;
- else
- cmd.mask = cpumask_of(policy->cpu);
-
- freqs.old = perf->states[perf->state].core_frequency * 1000;
- freqs.new = data->freq_table[next_state].frequency;
- for_each_cpu(i, policy->cpus) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- }
-
- drv_write(&cmd);
-
- if (acpi_pstate_strict) {
- if (!check_freqs(cmd.mask, freqs.new, data)) {
- dprintk("acpi_cpufreq_target failed (%d)\n",
- policy->cpu);
- result = -EAGAIN;
- goto out;
- }
- }
-
- for_each_cpu(i, policy->cpus) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
- perf->state = next_perf_state;
-
-out:
- return result;
-}
-
-static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
-{
- struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
-
- dprintk("acpi_cpufreq_verify\n");
-
- return cpufreq_frequency_table_verify(policy, data->freq_table);
-}
-
-static unsigned long
-acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
-{
- struct acpi_processor_performance *perf = data->acpi_data;
-
- if (cpu_khz) {
- /* search the closest match to cpu_khz */
- unsigned int i;
- unsigned long freq;
- unsigned long freqn = perf->states[0].core_frequency * 1000;
-
- for (i = 0; i < (perf->state_count-1); i++) {
- freq = freqn;
- freqn = perf->states[i+1].core_frequency * 1000;
- if ((2 * cpu_khz) > (freqn + freq)) {
- perf->state = i;
- return freq;
- }
- }
- perf->state = perf->state_count-1;
- return freqn;
- } else {
- /* assume CPU is at P0... */
- perf->state = 0;
- return perf->states[0].core_frequency * 1000;
- }
-}
-
-static void free_acpi_perf_data(void)
-{
- unsigned int i;
-
- /* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */
- for_each_possible_cpu(i)
- free_cpumask_var(per_cpu_ptr(acpi_perf_data, i)
- ->shared_cpu_map);
- free_percpu(acpi_perf_data);
-}
-
-/*
- * acpi_cpufreq_early_init - initialize ACPI P-States library
- *
- * Initialize the ACPI P-States library (drivers/acpi/processor_perflib.c)
- * in order to determine correct frequency and voltage pairings. We can
- * do _PDC and _PSD and find out the processor dependency for the
- * actual init that will happen later...
- */
-static int __init acpi_cpufreq_early_init(void)
-{
- unsigned int i;
- dprintk("acpi_cpufreq_early_init\n");
-
- acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
- if (!acpi_perf_data) {
- dprintk("Memory allocation error for acpi_perf_data.\n");
- return -ENOMEM;
- }
- for_each_possible_cpu(i) {
- if (!zalloc_cpumask_var_node(
- &per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
- GFP_KERNEL, cpu_to_node(i))) {
-
- /* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
- free_acpi_perf_data();
- return -ENOMEM;
- }
- }
-
- /* Do initialization in ACPI core */
- acpi_processor_preregister_performance(acpi_perf_data);
- return 0;
-}
-
-#ifdef CONFIG_SMP
-/*
- * Some BIOSes do SW_ANY coordination internally, either set it up in hw
- * or do it in BIOS firmware and won't inform about it to OS. If not
- * detected, this has a side effect of making CPU run at a different speed
- * than OS intended it to run at. Detect it and handle it cleanly.
- */
-static int bios_with_sw_any_bug;
-
-static int sw_any_bug_found(const struct dmi_system_id *d)
-{
- bios_with_sw_any_bug = 1;
- return 0;
-}
-
-static const struct dmi_system_id sw_any_bug_dmi_table[] = {
- {
- .callback = sw_any_bug_found,
- .ident = "Supermicro Server X6DLP",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
- DMI_MATCH(DMI_BIOS_VERSION, "080010"),
- DMI_MATCH(DMI_PRODUCT_NAME, "X6DLP"),
- },
- },
- { }
-};
-
-static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
-{
- /* Intel Xeon Processor 7100 Series Specification Update
- * http://www.intel.com/Assets/PDF/specupdate/314554.pdf
- * AL30: A Machine Check Exception (MCE) Occurring during an
- * Enhanced Intel SpeedStep Technology Ratio Change May Cause
- * Both Processor Cores to Lock Up. */
- if (c->x86_vendor == X86_VENDOR_INTEL) {
- if ((c->x86 == 15) &&
- (c->x86_model == 6) &&
- (c->x86_mask == 8)) {
- printk(KERN_INFO "acpi-cpufreq: Intel(R) "
- "Xeon(R) 7100 Errata AL30, processors may "
- "lock up on frequency changes: disabling "
- "acpi-cpufreq.\n");
- return -ENODEV;
- }
- }
- return 0;
-}
-#endif
-
-static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
-{
- unsigned int i;
- unsigned int valid_states = 0;
- unsigned int cpu = policy->cpu;
- struct acpi_cpufreq_data *data;
- unsigned int result = 0;
- struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
- struct acpi_processor_performance *perf;
-#ifdef CONFIG_SMP
- static int blacklisted;
-#endif
-
- dprintk("acpi_cpufreq_cpu_init\n");
-
-#ifdef CONFIG_SMP
- if (blacklisted)
- return blacklisted;
- blacklisted = acpi_cpufreq_blacklist(c);
- if (blacklisted)
- return blacklisted;
-#endif
-
- data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
-
- data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
- per_cpu(acfreq_data, cpu) = data;
-
- if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
- acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
-
- result = acpi_processor_register_performance(data->acpi_data, cpu);
- if (result)
- goto err_free;
-
- perf = data->acpi_data;
- policy->shared_type = perf->shared_type;
-
- /*
- * Will let policy->cpus know about dependency only when software
- * coordination is required.
- */
- if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
- policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
- cpumask_copy(policy->cpus, perf->shared_cpu_map);
- }
- cpumask_copy(policy->related_cpus, perf->shared_cpu_map);
-
-#ifdef CONFIG_SMP
- dmi_check_system(sw_any_bug_dmi_table);
- if (bios_with_sw_any_bug && cpumask_weight(policy->cpus) == 1) {
- policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
- cpumask_copy(policy->cpus, cpu_core_mask(cpu));
- }
-#endif
-
- /* capability check */
- if (perf->state_count <= 1) {
- dprintk("No P-States\n");
- result = -ENODEV;
- goto err_unreg;
- }
-
- if (perf->control_register.space_id != perf->status_register.space_id) {
- result = -ENODEV;
- goto err_unreg;
- }
-
- switch (perf->control_register.space_id) {
- case ACPI_ADR_SPACE_SYSTEM_IO:
- dprintk("SYSTEM IO addr space\n");
- data->cpu_feature = SYSTEM_IO_CAPABLE;
- break;
- case ACPI_ADR_SPACE_FIXED_HARDWARE:
- dprintk("HARDWARE addr space\n");
- if (!check_est_cpu(cpu)) {
- result = -ENODEV;
- goto err_unreg;
- }
- data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
- break;
- default:
- dprintk("Unknown addr space %d\n",
- (u32) (perf->control_register.space_id));
- result = -ENODEV;
- goto err_unreg;
- }
-
- data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) *
- (perf->state_count+1), GFP_KERNEL);
- if (!data->freq_table) {
- result = -ENOMEM;
- goto err_unreg;
- }
-
- /* detect transition latency */
- policy->cpuinfo.transition_latency = 0;
- for (i = 0; i < perf->state_count; i++) {
- if ((perf->states[i].transition_latency * 1000) >
- policy->cpuinfo.transition_latency)
- policy->cpuinfo.transition_latency =
- perf->states[i].transition_latency * 1000;
- }
-
- /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
- if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
- policy->cpuinfo.transition_latency > 20 * 1000) {
- policy->cpuinfo.transition_latency = 20 * 1000;
- printk_once(KERN_INFO
- "P-state transition latency capped at 20 uS\n");
- }
-
- /* table init */
- for (i = 0; i < perf->state_count; i++) {
- if (i > 0 && perf->states[i].core_frequency >=
- data->freq_table[valid_states-1].frequency / 1000)
- continue;
-
- data->freq_table[valid_states].index = i;
- data->freq_table[valid_states].frequency =
- perf->states[i].core_frequency * 1000;
- valid_states++;
- }
- data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
- perf->state = 0;
-
- result = cpufreq_frequency_table_cpuinfo(policy, data->freq_table);
- if (result)
- goto err_freqfree;
-
- if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
- printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
-
- switch (perf->control_register.space_id) {
- case ACPI_ADR_SPACE_SYSTEM_IO:
- /* Current speed is unknown and not detectable by IO port */
- policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu);
- break;
- case ACPI_ADR_SPACE_FIXED_HARDWARE:
- acpi_cpufreq_driver.get = get_cur_freq_on_cpu;
- policy->cur = get_cur_freq_on_cpu(cpu);
- break;
- default:
- break;
- }
-
- /* notify BIOS that we exist */
- acpi_processor_notify_smm(THIS_MODULE);
-
- /* Check for APERF/MPERF support in hardware */
- if (cpu_has(c, X86_FEATURE_APERFMPERF))
- acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf;
-
- dprintk("CPU%u - ACPI performance management activated.\n", cpu);
- for (i = 0; i < perf->state_count; i++)
- dprintk(" %cP%d: %d MHz, %d mW, %d uS\n",
- (i == perf->state ? '*' : ' '), i,
- (u32) perf->states[i].core_frequency,
- (u32) perf->states[i].power,
- (u32) perf->states[i].transition_latency);
-
- cpufreq_frequency_table_get_attr(data->freq_table, policy->cpu);
-
- /*
- * the first call to ->target() should result in us actually
- * writing something to the appropriate registers.
- */
- data->resume = 1;
-
- return result;
-
-err_freqfree:
- kfree(data->freq_table);
-err_unreg:
- acpi_processor_unregister_performance(perf, cpu);
-err_free:
- kfree(data);
- per_cpu(acfreq_data, cpu) = NULL;
-
- return result;
-}
-
-static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
-{
- struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
-
- dprintk("acpi_cpufreq_cpu_exit\n");
-
- if (data) {
- cpufreq_frequency_table_put_attr(policy->cpu);
- per_cpu(acfreq_data, policy->cpu) = NULL;
- acpi_processor_unregister_performance(data->acpi_data,
- policy->cpu);
- kfree(data->freq_table);
- kfree(data);
- }
-
- return 0;
-}
-
-static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
-{
- struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
-
- dprintk("acpi_cpufreq_resume\n");
-
- data->resume = 1;
-
- return 0;
-}
-
-static struct freq_attr *acpi_cpufreq_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver acpi_cpufreq_driver = {
- .verify = acpi_cpufreq_verify,
- .target = acpi_cpufreq_target,
- .bios_limit = acpi_processor_get_bios_limit,
- .init = acpi_cpufreq_cpu_init,
- .exit = acpi_cpufreq_cpu_exit,
- .resume = acpi_cpufreq_resume,
- .name = "acpi-cpufreq",
- .owner = THIS_MODULE,
- .attr = acpi_cpufreq_attr,
-};
-
-static int __init acpi_cpufreq_init(void)
-{
- int ret;
-
- if (acpi_disabled)
- return 0;
-
- dprintk("acpi_cpufreq_init\n");
-
- ret = acpi_cpufreq_early_init();
- if (ret)
- return ret;
-
- ret = cpufreq_register_driver(&acpi_cpufreq_driver);
- if (ret)
- free_acpi_perf_data();
-
- return ret;
-}
-
-static void __exit acpi_cpufreq_exit(void)
-{
- dprintk("acpi_cpufreq_exit\n");
-
- cpufreq_unregister_driver(&acpi_cpufreq_driver);
-
- free_percpu(acpi_perf_data);
-}
-
-module_param(acpi_pstate_strict, uint, 0644);
-MODULE_PARM_DESC(acpi_pstate_strict,
- "value 0 or non-zero. non-zero -> strict ACPI checks are "
- "performed during frequency changes.");
-
-late_initcall(acpi_cpufreq_init);
-module_exit(acpi_cpufreq_exit);
-
-MODULE_ALIAS("acpi");
diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
deleted file mode 100644
index 141abebc451..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
+++ /dev/null
@@ -1,446 +0,0 @@
-/*
- * (C) 2004-2006 Sebastian Witt <se.witt@gmx.net>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- * Based upon reverse engineered information
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-
-#define NFORCE2_XTAL 25
-#define NFORCE2_BOOTFSB 0x48
-#define NFORCE2_PLLENABLE 0xa8
-#define NFORCE2_PLLREG 0xa4
-#define NFORCE2_PLLADR 0xa0
-#define NFORCE2_PLL(mul, div) (0x100000 | (mul << 8) | div)
-
-#define NFORCE2_MIN_FSB 50
-#define NFORCE2_SAFE_DISTANCE 50
-
-/* Delay in ms between FSB changes */
-/* #define NFORCE2_DELAY 10 */
-
-/*
- * nforce2_chipset:
- * FSB is changed using the chipset
- */
-static struct pci_dev *nforce2_dev;
-
-/* fid:
- * multiplier * 10
- */
-static int fid;
-
-/* min_fsb, max_fsb:
- * minimum and maximum FSB (= FSB at boot time)
- */
-static int min_fsb;
-static int max_fsb;
-
-MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
-MODULE_DESCRIPTION("nForce2 FSB changing cpufreq driver");
-MODULE_LICENSE("GPL");
-
-module_param(fid, int, 0444);
-module_param(min_fsb, int, 0444);
-
-MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)");
-MODULE_PARM_DESC(min_fsb,
- "Minimum FSB to use, if not defined: current FSB - 50");
-
-#define PFX "cpufreq-nforce2: "
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "cpufreq-nforce2", msg)
-
-/**
- * nforce2_calc_fsb - calculate FSB
- * @pll: PLL value
- *
- * Calculates FSB from PLL value
- */
-static int nforce2_calc_fsb(int pll)
-{
- unsigned char mul, div;
-
- mul = (pll >> 8) & 0xff;
- div = pll & 0xff;
-
- if (div > 0)
- return NFORCE2_XTAL * mul / div;
-
- return 0;
-}
-
-/**
- * nforce2_calc_pll - calculate PLL value
- * @fsb: FSB
- *
- * Calculate PLL value for given FSB
- */
-static int nforce2_calc_pll(unsigned int fsb)
-{
- unsigned char xmul, xdiv;
- unsigned char mul = 0, div = 0;
- int tried = 0;
-
- /* Try to calculate multiplier and divider up to 4 times */
- while (((mul == 0) || (div == 0)) && (tried <= 3)) {
- for (xdiv = 2; xdiv <= 0x80; xdiv++)
- for (xmul = 1; xmul <= 0xfe; xmul++)
- if (nforce2_calc_fsb(NFORCE2_PLL(xmul, xdiv)) ==
- fsb + tried) {
- mul = xmul;
- div = xdiv;
- }
- tried++;
- }
-
- if ((mul == 0) || (div == 0))
- return -1;
-
- return NFORCE2_PLL(mul, div);
-}
-
-/**
- * nforce2_write_pll - write PLL value to chipset
- * @pll: PLL value
- *
- * Writes new FSB PLL value to chipset
- */
-static void nforce2_write_pll(int pll)
-{
- int temp;
-
- /* Set the pll addr. to 0x00 */
- pci_write_config_dword(nforce2_dev, NFORCE2_PLLADR, 0);
-
- /* Now write the value in all 64 registers */
- for (temp = 0; temp <= 0x3f; temp++)
- pci_write_config_dword(nforce2_dev, NFORCE2_PLLREG, pll);
-
- return;
-}
-
-/**
- * nforce2_fsb_read - Read FSB
- *
- * Read FSB from chipset
- * If bootfsb != 0, return FSB at boot-time
- */
-static unsigned int nforce2_fsb_read(int bootfsb)
-{
- struct pci_dev *nforce2_sub5;
- u32 fsb, temp = 0;
-
- /* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */
- nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, 0x01EF,
- PCI_ANY_ID, PCI_ANY_ID, NULL);
- if (!nforce2_sub5)
- return 0;
-
- pci_read_config_dword(nforce2_sub5, NFORCE2_BOOTFSB, &fsb);
- fsb /= 1000000;
-
- /* Check if PLL register is already set */
- pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
-
- if (bootfsb || !temp)
- return fsb;
-
- /* Use PLL register FSB value */
- pci_read_config_dword(nforce2_dev, NFORCE2_PLLREG, &temp);
- fsb = nforce2_calc_fsb(temp);
-
- return fsb;
-}
-
-/**
- * nforce2_set_fsb - set new FSB
- * @fsb: New FSB
- *
- * Sets new FSB
- */
-static int nforce2_set_fsb(unsigned int fsb)
-{
- u32 temp = 0;
- unsigned int tfsb;
- int diff;
- int pll = 0;
-
- if ((fsb > max_fsb) || (fsb < NFORCE2_MIN_FSB)) {
- printk(KERN_ERR PFX "FSB %d is out of range!\n", fsb);
- return -EINVAL;
- }
-
- tfsb = nforce2_fsb_read(0);
- if (!tfsb) {
- printk(KERN_ERR PFX "Error while reading the FSB\n");
- return -EINVAL;
- }
-
- /* First write? Then set actual value */
- pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
- if (!temp) {
- pll = nforce2_calc_pll(tfsb);
-
- if (pll < 0)
- return -EINVAL;
-
- nforce2_write_pll(pll);
- }
-
- /* Enable write access */
- temp = 0x01;
- pci_write_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8)temp);
-
- diff = tfsb - fsb;
-
- if (!diff)
- return 0;
-
- while ((tfsb != fsb) && (tfsb <= max_fsb) && (tfsb >= min_fsb)) {
- if (diff < 0)
- tfsb++;
- else
- tfsb--;
-
- /* Calculate the PLL reg. value */
- pll = nforce2_calc_pll(tfsb);
- if (pll == -1)
- return -EINVAL;
-
- nforce2_write_pll(pll);
-#ifdef NFORCE2_DELAY
- mdelay(NFORCE2_DELAY);
-#endif
- }
-
- temp = 0x40;
- pci_write_config_byte(nforce2_dev, NFORCE2_PLLADR, (u8)temp);
-
- return 0;
-}
-
-/**
- * nforce2_get - get the CPU frequency
- * @cpu: CPU number
- *
- * Returns the CPU frequency
- */
-static unsigned int nforce2_get(unsigned int cpu)
-{
- if (cpu)
- return 0;
- return nforce2_fsb_read(0) * fid * 100;
-}
-
-/**
- * nforce2_target - set a new CPUFreq policy
- * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
- *
- * Sets a new CPUFreq policy.
- */
-static int nforce2_target(struct cpufreq_policy *policy,
- unsigned int target_freq, unsigned int relation)
-{
-/* unsigned long flags; */
- struct cpufreq_freqs freqs;
- unsigned int target_fsb;
-
- if ((target_freq > policy->max) || (target_freq < policy->min))
- return -EINVAL;
-
- target_fsb = target_freq / (fid * 100);
-
- freqs.old = nforce2_get(policy->cpu);
- freqs.new = target_fsb * fid * 100;
- freqs.cpu = 0; /* Only one CPU on nForce2 platforms */
-
- if (freqs.old == freqs.new)
- return 0;
-
- dprintk("Old CPU frequency %d kHz, new %d kHz\n",
- freqs.old, freqs.new);
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- /* Disable IRQs */
- /* local_irq_save(flags); */
-
- if (nforce2_set_fsb(target_fsb) < 0)
- printk(KERN_ERR PFX "Changing FSB to %d failed\n",
- target_fsb);
- else
- dprintk("Changed FSB successfully to %d\n",
- target_fsb);
-
- /* Enable IRQs */
- /* local_irq_restore(flags); */
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
- return 0;
-}
-
-/**
- * nforce2_verify - verifies a new CPUFreq policy
- * @policy: new policy
- */
-static int nforce2_verify(struct cpufreq_policy *policy)
-{
- unsigned int fsb_pol_max;
-
- fsb_pol_max = policy->max / (fid * 100);
-
- if (policy->min < (fsb_pol_max * fid * 100))
- policy->max = (fsb_pol_max + 1) * fid * 100;
-
- cpufreq_verify_within_limits(policy,
- policy->cpuinfo.min_freq,
- policy->cpuinfo.max_freq);
- return 0;
-}
-
-static int nforce2_cpu_init(struct cpufreq_policy *policy)
-{
- unsigned int fsb;
- unsigned int rfid;
-
- /* capability check */
- if (policy->cpu != 0)
- return -ENODEV;
-
- /* Get current FSB */
- fsb = nforce2_fsb_read(0);
-
- if (!fsb)
- return -EIO;
-
- /* FIX: Get FID from CPU */
- if (!fid) {
- if (!cpu_khz) {
- printk(KERN_WARNING PFX
- "cpu_khz not set, can't calculate multiplier!\n");
- return -ENODEV;
- }
-
- fid = cpu_khz / (fsb * 100);
- rfid = fid % 5;
-
- if (rfid) {
- if (rfid > 2)
- fid += 5 - rfid;
- else
- fid -= rfid;
- }
- }
-
- printk(KERN_INFO PFX "FSB currently at %i MHz, FID %d.%d\n", fsb,
- fid / 10, fid % 10);
-
- /* Set maximum FSB to FSB at boot time */
- max_fsb = nforce2_fsb_read(1);
-
- if (!max_fsb)
- return -EIO;
-
- if (!min_fsb)
- min_fsb = max_fsb - NFORCE2_SAFE_DISTANCE;
-
- if (min_fsb < NFORCE2_MIN_FSB)
- min_fsb = NFORCE2_MIN_FSB;
-
- /* cpuinfo and default policy values */
- policy->cpuinfo.min_freq = min_fsb * fid * 100;
- policy->cpuinfo.max_freq = max_fsb * fid * 100;
- policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
- policy->cur = nforce2_get(policy->cpu);
- policy->min = policy->cpuinfo.min_freq;
- policy->max = policy->cpuinfo.max_freq;
-
- return 0;
-}
-
-static int nforce2_cpu_exit(struct cpufreq_policy *policy)
-{
- return 0;
-}
-
-static struct cpufreq_driver nforce2_driver = {
- .name = "nforce2",
- .verify = nforce2_verify,
- .target = nforce2_target,
- .get = nforce2_get,
- .init = nforce2_cpu_init,
- .exit = nforce2_cpu_exit,
- .owner = THIS_MODULE,
-};
-
-/**
- * nforce2_detect_chipset - detect the Southbridge which contains FSB PLL logic
- *
- * Detects nForce2 A2 and C1 stepping
- *
- */
-static int nforce2_detect_chipset(void)
-{
- nforce2_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA,
- PCI_DEVICE_ID_NVIDIA_NFORCE2,
- PCI_ANY_ID, PCI_ANY_ID, NULL);
-
- if (nforce2_dev == NULL)
- return -ENODEV;
-
- printk(KERN_INFO PFX "Detected nForce2 chipset revision %X\n",
- nforce2_dev->revision);
- printk(KERN_INFO PFX
- "FSB changing is maybe unstable and can lead to "
- "crashes and data loss.\n");
-
- return 0;
-}
-
-/**
- * nforce2_init - initializes the nForce2 CPUFreq driver
- *
- * Initializes the nForce2 FSB support. Returns -ENODEV on unsupported
- * devices, -EINVAL on problems during initiatization, and zero on
- * success.
- */
-static int __init nforce2_init(void)
-{
- /* TODO: do we need to detect the processor? */
-
- /* detect chipset */
- if (nforce2_detect_chipset()) {
- printk(KERN_INFO PFX "No nForce2 chipset.\n");
- return -ENODEV;
- }
-
- return cpufreq_register_driver(&nforce2_driver);
-}
-
-/**
- * nforce2_exit - unregisters cpufreq module
- *
- * Unregisters nForce2 FSB change support.
- */
-static void __exit nforce2_exit(void)
-{
- cpufreq_unregister_driver(&nforce2_driver);
-}
-
-module_init(nforce2_init);
-module_exit(nforce2_exit);
-
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
deleted file mode 100644
index 35a257dd4bb..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ /dev/null
@@ -1,367 +0,0 @@
-/*
- * Based on documentation provided by Dave Jones. Thanks!
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/ioport.h>
-#include <linux/slab.h>
-#include <linux/timex.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/msr.h>
-#include <asm/tsc.h>
-
-#define EPS_BRAND_C7M 0
-#define EPS_BRAND_C7 1
-#define EPS_BRAND_EDEN 2
-#define EPS_BRAND_C3 3
-#define EPS_BRAND_C7D 4
-
-struct eps_cpu_data {
- u32 fsb;
- struct cpufreq_frequency_table freq_table[];
-};
-
-static struct eps_cpu_data *eps_cpu[NR_CPUS];
-
-
-static unsigned int eps_get(unsigned int cpu)
-{
- struct eps_cpu_data *centaur;
- u32 lo, hi;
-
- if (cpu)
- return 0;
- centaur = eps_cpu[cpu];
- if (centaur == NULL)
- return 0;
-
- /* Return current frequency */
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- return centaur->fsb * ((lo >> 8) & 0xff);
-}
-
-static int eps_set_state(struct eps_cpu_data *centaur,
- unsigned int cpu,
- u32 dest_state)
-{
- struct cpufreq_freqs freqs;
- u32 lo, hi;
- int err = 0;
- int i;
-
- freqs.old = eps_get(cpu);
- freqs.new = centaur->fsb * ((dest_state >> 8) & 0xff);
- freqs.cpu = cpu;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- /* Wait while CPU is busy */
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- i = 0;
- while (lo & ((1 << 16) | (1 << 17))) {
- udelay(16);
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- i++;
- if (unlikely(i > 64)) {
- err = -ENODEV;
- goto postchange;
- }
- }
- /* Set new multiplier and voltage */
- wrmsr(MSR_IA32_PERF_CTL, dest_state & 0xffff, 0);
- /* Wait until transition end */
- i = 0;
- do {
- udelay(16);
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- i++;
- if (unlikely(i > 64)) {
- err = -ENODEV;
- goto postchange;
- }
- } while (lo & ((1 << 16) | (1 << 17)));
-
- /* Return current frequency */
-postchange:
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- freqs.new = centaur->fsb * ((lo >> 8) & 0xff);
-
-#ifdef DEBUG
- {
- u8 current_multiplier, current_voltage;
-
- /* Print voltage and multiplier */
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- current_voltage = lo & 0xff;
- printk(KERN_INFO "eps: Current voltage = %dmV\n",
- current_voltage * 16 + 700);
- current_multiplier = (lo >> 8) & 0xff;
- printk(KERN_INFO "eps: Current multiplier = %d\n",
- current_multiplier);
- }
-#endif
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- return err;
-}
-
-static int eps_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- struct eps_cpu_data *centaur;
- unsigned int newstate = 0;
- unsigned int cpu = policy->cpu;
- unsigned int dest_state;
- int ret;
-
- if (unlikely(eps_cpu[cpu] == NULL))
- return -ENODEV;
- centaur = eps_cpu[cpu];
-
- if (unlikely(cpufreq_frequency_table_target(policy,
- &eps_cpu[cpu]->freq_table[0],
- target_freq,
- relation,
- &newstate))) {
- return -EINVAL;
- }
-
- /* Make frequency transition */
- dest_state = centaur->freq_table[newstate].index & 0xffff;
- ret = eps_set_state(centaur, cpu, dest_state);
- if (ret)
- printk(KERN_ERR "eps: Timeout!\n");
- return ret;
-}
-
-static int eps_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy,
- &eps_cpu[policy->cpu]->freq_table[0]);
-}
-
-static int eps_cpu_init(struct cpufreq_policy *policy)
-{
- unsigned int i;
- u32 lo, hi;
- u64 val;
- u8 current_multiplier, current_voltage;
- u8 max_multiplier, max_voltage;
- u8 min_multiplier, min_voltage;
- u8 brand = 0;
- u32 fsb;
- struct eps_cpu_data *centaur;
- struct cpuinfo_x86 *c = &cpu_data(0);
- struct cpufreq_frequency_table *f_table;
- int k, step, voltage;
- int ret;
- int states;
-
- if (policy->cpu != 0)
- return -ENODEV;
-
- /* Check brand */
- printk(KERN_INFO "eps: Detected VIA ");
-
- switch (c->x86_model) {
- case 10:
- rdmsr(0x1153, lo, hi);
- brand = (((lo >> 2) ^ lo) >> 18) & 3;
- printk(KERN_CONT "Model A ");
- break;
- case 13:
- rdmsr(0x1154, lo, hi);
- brand = (((lo >> 4) ^ (lo >> 2))) & 0x000000ff;
- printk(KERN_CONT "Model D ");
- break;
- }
-
- switch (brand) {
- case EPS_BRAND_C7M:
- printk(KERN_CONT "C7-M\n");
- break;
- case EPS_BRAND_C7:
- printk(KERN_CONT "C7\n");
- break;
- case EPS_BRAND_EDEN:
- printk(KERN_CONT "Eden\n");
- break;
- case EPS_BRAND_C7D:
- printk(KERN_CONT "C7-D\n");
- break;
- case EPS_BRAND_C3:
- printk(KERN_CONT "C3\n");
- return -ENODEV;
- break;
- }
- /* Enable Enhanced PowerSaver */
- rdmsrl(MSR_IA32_MISC_ENABLE, val);
- if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
- val |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
- wrmsrl(MSR_IA32_MISC_ENABLE, val);
- /* Can be locked at 0 */
- rdmsrl(MSR_IA32_MISC_ENABLE, val);
- if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
- printk(KERN_INFO "eps: Can't enable Enhanced PowerSaver\n");
- return -ENODEV;
- }
- }
-
- /* Print voltage and multiplier */
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- current_voltage = lo & 0xff;
- printk(KERN_INFO "eps: Current voltage = %dmV\n",
- current_voltage * 16 + 700);
- current_multiplier = (lo >> 8) & 0xff;
- printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier);
-
- /* Print limits */
- max_voltage = hi & 0xff;
- printk(KERN_INFO "eps: Highest voltage = %dmV\n",
- max_voltage * 16 + 700);
- max_multiplier = (hi >> 8) & 0xff;
- printk(KERN_INFO "eps: Highest multiplier = %d\n", max_multiplier);
- min_voltage = (hi >> 16) & 0xff;
- printk(KERN_INFO "eps: Lowest voltage = %dmV\n",
- min_voltage * 16 + 700);
- min_multiplier = (hi >> 24) & 0xff;
- printk(KERN_INFO "eps: Lowest multiplier = %d\n", min_multiplier);
-
- /* Sanity checks */
- if (current_multiplier == 0 || max_multiplier == 0
- || min_multiplier == 0)
- return -EINVAL;
- if (current_multiplier > max_multiplier
- || max_multiplier <= min_multiplier)
- return -EINVAL;
- if (current_voltage > 0x1f || max_voltage > 0x1f)
- return -EINVAL;
- if (max_voltage < min_voltage)
- return -EINVAL;
-
- /* Calc FSB speed */
- fsb = cpu_khz / current_multiplier;
- /* Calc number of p-states supported */
- if (brand == EPS_BRAND_C7M)
- states = max_multiplier - min_multiplier + 1;
- else
- states = 2;
-
- /* Allocate private data and frequency table for current cpu */
- centaur = kzalloc(sizeof(struct eps_cpu_data)
- + (states + 1) * sizeof(struct cpufreq_frequency_table),
- GFP_KERNEL);
- if (!centaur)
- return -ENOMEM;
- eps_cpu[0] = centaur;
-
- /* Copy basic values */
- centaur->fsb = fsb;
-
- /* Fill frequency and MSR value table */
- f_table = &centaur->freq_table[0];
- if (brand != EPS_BRAND_C7M) {
- f_table[0].frequency = fsb * min_multiplier;
- f_table[0].index = (min_multiplier << 8) | min_voltage;
- f_table[1].frequency = fsb * max_multiplier;
- f_table[1].index = (max_multiplier << 8) | max_voltage;
- f_table[2].frequency = CPUFREQ_TABLE_END;
- } else {
- k = 0;
- step = ((max_voltage - min_voltage) * 256)
- / (max_multiplier - min_multiplier);
- for (i = min_multiplier; i <= max_multiplier; i++) {
- voltage = (k * step) / 256 + min_voltage;
- f_table[k].frequency = fsb * i;
- f_table[k].index = (i << 8) | voltage;
- k++;
- }
- f_table[k].frequency = CPUFREQ_TABLE_END;
- }
-
- policy->cpuinfo.transition_latency = 140000; /* 844mV -> 700mV in ns */
- policy->cur = fsb * current_multiplier;
-
- ret = cpufreq_frequency_table_cpuinfo(policy, &centaur->freq_table[0]);
- if (ret) {
- kfree(centaur);
- return ret;
- }
-
- cpufreq_frequency_table_get_attr(&centaur->freq_table[0], policy->cpu);
- return 0;
-}
-
-static int eps_cpu_exit(struct cpufreq_policy *policy)
-{
- unsigned int cpu = policy->cpu;
- struct eps_cpu_data *centaur;
- u32 lo, hi;
-
- if (eps_cpu[cpu] == NULL)
- return -ENODEV;
- centaur = eps_cpu[cpu];
-
- /* Get max frequency */
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- /* Set max frequency */
- eps_set_state(centaur, cpu, hi & 0xffff);
- /* Bye */
- cpufreq_frequency_table_put_attr(policy->cpu);
- kfree(eps_cpu[cpu]);
- eps_cpu[cpu] = NULL;
- return 0;
-}
-
-static struct freq_attr *eps_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver eps_driver = {
- .verify = eps_verify,
- .target = eps_target,
- .init = eps_cpu_init,
- .exit = eps_cpu_exit,
- .get = eps_get,
- .name = "e_powersaver",
- .owner = THIS_MODULE,
- .attr = eps_attr,
-};
-
-static int __init eps_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- /* This driver will work only on Centaur C7 processors with
- * Enhanced SpeedStep/PowerSaver registers */
- if (c->x86_vendor != X86_VENDOR_CENTAUR
- || c->x86 != 6 || c->x86_model < 10)
- return -ENODEV;
- if (!cpu_has(c, X86_FEATURE_EST))
- return -ENODEV;
-
- if (cpufreq_register_driver(&eps_driver))
- return -EINVAL;
- return 0;
-}
-
-static void __exit eps_exit(void)
-{
- cpufreq_unregister_driver(&eps_driver);
-}
-
-MODULE_AUTHOR("Rafal Bilski <rafalbilski@interia.pl>");
-MODULE_DESCRIPTION("Enhanced PowerSaver driver for VIA C7 CPU's.");
-MODULE_LICENSE("GPL");
-
-module_init(eps_init);
-module_exit(eps_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
deleted file mode 100644
index c587db472a7..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ /dev/null
@@ -1,309 +0,0 @@
-/*
- * elanfreq: cpufreq driver for the AMD ELAN family
- *
- * (c) Copyright 2002 Robert Schwebel <r.schwebel@pengutronix.de>
- *
- * Parts of this code are (c) Sven Geggus <sven@geggus.net>
- *
- * All Rights Reserved.
- *
- * 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.
- *
- * 2002-02-13: - initial revision for 2.4.18-pre9 by Robert Schwebel
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-
-#include <linux/delay.h>
-#include <linux/cpufreq.h>
-
-#include <asm/msr.h>
-#include <linux/timex.h>
-#include <linux/io.h>
-
-#define REG_CSCIR 0x22 /* Chip Setup and Control Index Register */
-#define REG_CSCDR 0x23 /* Chip Setup and Control Data Register */
-
-/* Module parameter */
-static int max_freq;
-
-struct s_elan_multiplier {
- int clock; /* frequency in kHz */
- int val40h; /* PMU Force Mode register */
- int val80h; /* CPU Clock Speed Register */
-};
-
-/*
- * It is important that the frequencies
- * are listed in ascending order here!
- */
-static struct s_elan_multiplier elan_multiplier[] = {
- {1000, 0x02, 0x18},
- {2000, 0x02, 0x10},
- {4000, 0x02, 0x08},
- {8000, 0x00, 0x00},
- {16000, 0x00, 0x02},
- {33000, 0x00, 0x04},
- {66000, 0x01, 0x04},
- {99000, 0x01, 0x05}
-};
-
-static struct cpufreq_frequency_table elanfreq_table[] = {
- {0, 1000},
- {1, 2000},
- {2, 4000},
- {3, 8000},
- {4, 16000},
- {5, 33000},
- {6, 66000},
- {7, 99000},
- {0, CPUFREQ_TABLE_END},
-};
-
-
-/**
- * elanfreq_get_cpu_frequency: determine current cpu speed
- *
- * Finds out at which frequency the CPU of the Elan SOC runs
- * at the moment. Frequencies from 1 to 33 MHz are generated
- * the normal way, 66 and 99 MHz are called "Hyperspeed Mode"
- * and have the rest of the chip running with 33 MHz.
- */
-
-static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu)
-{
- u8 clockspeed_reg; /* Clock Speed Register */
-
- local_irq_disable();
- outb_p(0x80, REG_CSCIR);
- clockspeed_reg = inb_p(REG_CSCDR);
- local_irq_enable();
-
- if ((clockspeed_reg & 0xE0) == 0xE0)
- return 0;
-
- /* Are we in CPU clock multiplied mode (66/99 MHz)? */
- if ((clockspeed_reg & 0xE0) == 0xC0) {
- if ((clockspeed_reg & 0x01) == 0)
- return 66000;
- else
- return 99000;
- }
-
- /* 33 MHz is not 32 MHz... */
- if ((clockspeed_reg & 0xE0) == 0xA0)
- return 33000;
-
- return (1<<((clockspeed_reg & 0xE0) >> 5)) * 1000;
-}
-
-
-/**
- * elanfreq_set_cpu_frequency: Change the CPU core frequency
- * @cpu: cpu number
- * @freq: frequency in kHz
- *
- * This function takes a frequency value and changes the CPU frequency
- * according to this. Note that the frequency has to be checked by
- * elanfreq_validatespeed() for correctness!
- *
- * There is no return value.
- */
-
-static void elanfreq_set_cpu_state(unsigned int state)
-{
- struct cpufreq_freqs freqs;
-
- freqs.old = elanfreq_get_cpu_frequency(0);
- freqs.new = elan_multiplier[state].clock;
- freqs.cpu = 0; /* elanfreq.c is UP only driver */
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- printk(KERN_INFO "elanfreq: attempting to set frequency to %i kHz\n",
- elan_multiplier[state].clock);
-
-
- /*
- * Access to the Elan's internal registers is indexed via
- * 0x22: Chip Setup & Control Register Index Register (CSCI)
- * 0x23: Chip Setup & Control Register Data Register (CSCD)
- *
- */
-
- /*
- * 0x40 is the Power Management Unit's Force Mode Register.
- * Bit 6 enables Hyperspeed Mode (66/100 MHz core frequency)
- */
-
- local_irq_disable();
- outb_p(0x40, REG_CSCIR); /* Disable hyperspeed mode */
- outb_p(0x00, REG_CSCDR);
- local_irq_enable(); /* wait till internal pipelines and */
- udelay(1000); /* buffers have cleaned up */
-
- local_irq_disable();
-
- /* now, set the CPU clock speed register (0x80) */
- outb_p(0x80, REG_CSCIR);
- outb_p(elan_multiplier[state].val80h, REG_CSCDR);
-
- /* now, the hyperspeed bit in PMU Force Mode Register (0x40) */
- outb_p(0x40, REG_CSCIR);
- outb_p(elan_multiplier[state].val40h, REG_CSCDR);
- udelay(10000);
- local_irq_enable();
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-};
-
-
-/**
- * elanfreq_validatespeed: test if frequency range is valid
- * @policy: the policy to validate
- *
- * This function checks if a given frequency range in kHz is valid
- * for the hardware supported by the driver.
- */
-
-static int elanfreq_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, &elanfreq_table[0]);
-}
-
-static int elanfreq_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate = 0;
-
- if (cpufreq_frequency_table_target(policy, &elanfreq_table[0],
- target_freq, relation, &newstate))
- return -EINVAL;
-
- elanfreq_set_cpu_state(newstate);
-
- return 0;
-}
-
-
-/*
- * Module init and exit code
- */
-
-static int elanfreq_cpu_init(struct cpufreq_policy *policy)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- unsigned int i;
- int result;
-
- /* capability check */
- if ((c->x86_vendor != X86_VENDOR_AMD) ||
- (c->x86 != 4) || (c->x86_model != 10))
- return -ENODEV;
-
- /* max freq */
- if (!max_freq)
- max_freq = elanfreq_get_cpu_frequency(0);
-
- /* table init */
- for (i = 0; (elanfreq_table[i].frequency != CPUFREQ_TABLE_END); i++) {
- if (elanfreq_table[i].frequency > max_freq)
- elanfreq_table[i].frequency = CPUFREQ_ENTRY_INVALID;
- }
-
- /* cpuinfo and default policy values */
- policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
- policy->cur = elanfreq_get_cpu_frequency(0);
-
- result = cpufreq_frequency_table_cpuinfo(policy, elanfreq_table);
- if (result)
- return result;
-
- cpufreq_frequency_table_get_attr(elanfreq_table, policy->cpu);
- return 0;
-}
-
-
-static int elanfreq_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-
-#ifndef MODULE
-/**
- * elanfreq_setup - elanfreq command line parameter parsing
- *
- * elanfreq command line parameter. Use:
- * elanfreq=66000
- * to set the maximum CPU frequency to 66 MHz. Note that in
- * case you do not give this boot parameter, the maximum
- * frequency will fall back to _current_ CPU frequency which
- * might be lower. If you build this as a module, use the
- * max_freq module parameter instead.
- */
-static int __init elanfreq_setup(char *str)
-{
- max_freq = simple_strtoul(str, &str, 0);
- printk(KERN_WARNING "You're using the deprecated elanfreq command line option. Use elanfreq.max_freq instead, please!\n");
- return 1;
-}
-__setup("elanfreq=", elanfreq_setup);
-#endif
-
-
-static struct freq_attr *elanfreq_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-
-static struct cpufreq_driver elanfreq_driver = {
- .get = elanfreq_get_cpu_frequency,
- .verify = elanfreq_verify,
- .target = elanfreq_target,
- .init = elanfreq_cpu_init,
- .exit = elanfreq_cpu_exit,
- .name = "elanfreq",
- .owner = THIS_MODULE,
- .attr = elanfreq_attr,
-};
-
-
-static int __init elanfreq_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- /* Test if we have the right hardware */
- if ((c->x86_vendor != X86_VENDOR_AMD) ||
- (c->x86 != 4) || (c->x86_model != 10)) {
- printk(KERN_INFO "elanfreq: error: no Elan processor found!\n");
- return -ENODEV;
- }
- return cpufreq_register_driver(&elanfreq_driver);
-}
-
-
-static void __exit elanfreq_exit(void)
-{
- cpufreq_unregister_driver(&elanfreq_driver);
-}
-
-
-module_param(max_freq, int, 0444);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Robert Schwebel <r.schwebel@pengutronix.de>, "
- "Sven Geggus <sven@geggus.net>");
-MODULE_DESCRIPTION("cpufreq driver for AMD's Elan CPUs");
-
-module_init(elanfreq_init);
-module_exit(elanfreq_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
deleted file mode 100644
index 32974cf8423..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ /dev/null
@@ -1,517 +0,0 @@
-/*
- * Cyrix MediaGX and NatSemi Geode Suspend Modulation
- * (C) 2002 Zwane Mwaikambo <zwane@commfireservices.com>
- * (C) 2002 Hiroshi Miura <miura@da-cha.org>
- * All Rights Reserved
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation
- *
- * The author(s) of this software shall not be held liable for damages
- * of any nature resulting due to the use of this software. This
- * software is provided AS-IS with no warranties.
- *
- * Theoretical note:
- *
- * (see Geode(tm) CS5530 manual (rev.4.1) page.56)
- *
- * CPU frequency control on NatSemi Geode GX1/GXLV processor and CS55x0
- * are based on Suspend Modulation.
- *
- * Suspend Modulation works by asserting and de-asserting the SUSP# pin
- * to CPU(GX1/GXLV) for configurable durations. When asserting SUSP#
- * the CPU enters an idle state. GX1 stops its core clock when SUSP# is
- * asserted then power consumption is reduced.
- *
- * Suspend Modulation's OFF/ON duration are configurable
- * with 'Suspend Modulation OFF Count Register'
- * and 'Suspend Modulation ON Count Register'.
- * These registers are 8bit counters that represent the number of
- * 32us intervals which the SUSP# pin is asserted(ON)/de-asserted(OFF)
- * to the processor.
- *
- * These counters define a ratio which is the effective frequency
- * of operation of the system.
- *
- * OFF Count
- * F_eff = Fgx * ----------------------
- * OFF Count + ON Count
- *
- * 0 <= On Count, Off Count <= 255
- *
- * From these limits, we can get register values
- *
- * off_duration + on_duration <= MAX_DURATION
- * on_duration = off_duration * (stock_freq - freq) / freq
- *
- * off_duration = (freq * DURATION) / stock_freq
- * on_duration = DURATION - off_duration
- *
- *
- *---------------------------------------------------------------------------
- *
- * ChangeLog:
- * Dec. 12, 2003 Hiroshi Miura <miura@da-cha.org>
- * - fix on/off register mistake
- * - fix cpu_khz calc when it stops cpu modulation.
- *
- * Dec. 11, 2002 Hiroshi Miura <miura@da-cha.org>
- * - rewrite for Cyrix MediaGX Cx5510/5520 and
- * NatSemi Geode Cs5530(A).
- *
- * Jul. ??, 2002 Zwane Mwaikambo <zwane@commfireservices.com>
- * - cs5530_mod patch for 2.4.19-rc1.
- *
- *---------------------------------------------------------------------------
- *
- * Todo
- * Test on machines with 5510, 5530, 5530A
- */
-
-/************************************************************************
- * Suspend Modulation - Definitions *
- ************************************************************************/
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/cpufreq.h>
-#include <linux/pci.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-
-#include <asm/processor-cyrix.h>
-
-/* PCI config registers, all at F0 */
-#define PCI_PMER1 0x80 /* power management enable register 1 */
-#define PCI_PMER2 0x81 /* power management enable register 2 */
-#define PCI_PMER3 0x82 /* power management enable register 3 */
-#define PCI_IRQTC 0x8c /* irq speedup timer counter register:typical 2 to 4ms */
-#define PCI_VIDTC 0x8d /* video speedup timer counter register: typical 50 to 100ms */
-#define PCI_MODOFF 0x94 /* suspend modulation OFF counter register, 1 = 32us */
-#define PCI_MODON 0x95 /* suspend modulation ON counter register */
-#define PCI_SUSCFG 0x96 /* suspend configuration register */
-
-/* PMER1 bits */
-#define GPM (1<<0) /* global power management */
-#define GIT (1<<1) /* globally enable PM device idle timers */
-#define GTR (1<<2) /* globally enable IO traps */
-#define IRQ_SPDUP (1<<3) /* disable clock throttle during interrupt handling */
-#define VID_SPDUP (1<<4) /* disable clock throttle during vga video handling */
-
-/* SUSCFG bits */
-#define SUSMOD (1<<0) /* enable/disable suspend modulation */
-/* the below is supported only with cs5530 (after rev.1.2)/cs5530A */
-#define SMISPDUP (1<<1) /* select how SMI re-enable suspend modulation: */
- /* IRQTC timer or read SMI speedup disable reg.(F1BAR[08-09h]) */
-#define SUSCFG (1<<2) /* enable powering down a GXLV processor. "Special 3Volt Suspend" mode */
-/* the below is supported only with cs5530A */
-#define PWRSVE_ISA (1<<3) /* stop ISA clock */
-#define PWRSVE (1<<4) /* active idle */
-
-struct gxfreq_params {
- u8 on_duration;
- u8 off_duration;
- u8 pci_suscfg;
- u8 pci_pmer1;
- u8 pci_pmer2;
- struct pci_dev *cs55x0;
-};
-
-static struct gxfreq_params *gx_params;
-static int stock_freq;
-
-/* PCI bus clock - defaults to 30.000 if cpu_khz is not available */
-static int pci_busclk;
-module_param(pci_busclk, int, 0444);
-
-/* maximum duration for which the cpu may be suspended
- * (32us * MAX_DURATION). If no parameter is given, this defaults
- * to 255.
- * Note that this leads to a maximum of 8 ms(!) where the CPU clock
- * is suspended -- processing power is just 0.39% of what it used to be,
- * though. 781.25 kHz(!) for a 200 MHz processor -- wow. */
-static int max_duration = 255;
-module_param(max_duration, int, 0444);
-
-/* For the default policy, we want at least some processing power
- * - let's say 5%. (min = maxfreq / POLICY_MIN_DIV)
- */
-#define POLICY_MIN_DIV 20
-
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "gx-suspmod", msg)
-
-/**
- * we can detect a core multipiler from dir0_lsb
- * from GX1 datasheet p.56,
- * MULT[3:0]:
- * 0000 = SYSCLK multiplied by 4 (test only)
- * 0001 = SYSCLK multiplied by 10
- * 0010 = SYSCLK multiplied by 4
- * 0011 = SYSCLK multiplied by 6
- * 0100 = SYSCLK multiplied by 9
- * 0101 = SYSCLK multiplied by 5
- * 0110 = SYSCLK multiplied by 7
- * 0111 = SYSCLK multiplied by 8
- * of 33.3MHz
- **/
-static int gx_freq_mult[16] = {
- 4, 10, 4, 6, 9, 5, 7, 8,
- 0, 0, 0, 0, 0, 0, 0, 0
-};
-
-
-/****************************************************************
- * Low Level chipset interface *
- ****************************************************************/
-static struct pci_device_id gx_chipset_tbl[] __initdata = {
- { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY), },
- { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5520), },
- { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5510), },
- { 0, },
-};
-
-static void gx_write_byte(int reg, int value)
-{
- pci_write_config_byte(gx_params->cs55x0, reg, value);
-}
-
-/**
- * gx_detect_chipset:
- *
- **/
-static __init struct pci_dev *gx_detect_chipset(void)
-{
- struct pci_dev *gx_pci = NULL;
-
- /* check if CPU is a MediaGX or a Geode. */
- if ((boot_cpu_data.x86_vendor != X86_VENDOR_NSC) &&
- (boot_cpu_data.x86_vendor != X86_VENDOR_CYRIX)) {
- dprintk("error: no MediaGX/Geode processor found!\n");
- return NULL;
- }
-
- /* detect which companion chip is used */
- for_each_pci_dev(gx_pci) {
- if ((pci_match_id(gx_chipset_tbl, gx_pci)) != NULL)
- return gx_pci;
- }
-
- dprintk("error: no supported chipset found!\n");
- return NULL;
-}
-
-/**
- * gx_get_cpuspeed:
- *
- * Finds out at which efficient frequency the Cyrix MediaGX/NatSemi
- * Geode CPU runs.
- */
-static unsigned int gx_get_cpuspeed(unsigned int cpu)
-{
- if ((gx_params->pci_suscfg & SUSMOD) == 0)
- return stock_freq;
-
- return (stock_freq * gx_params->off_duration)
- / (gx_params->on_duration + gx_params->off_duration);
-}
-
-/**
- * gx_validate_speed:
- * determine current cpu speed
- *
- **/
-
-static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration,
- u8 *off_duration)
-{
- unsigned int i;
- u8 tmp_on, tmp_off;
- int old_tmp_freq = stock_freq;
- int tmp_freq;
-
- *off_duration = 1;
- *on_duration = 0;
-
- for (i = max_duration; i > 0; i--) {
- tmp_off = ((khz * i) / stock_freq) & 0xff;
- tmp_on = i - tmp_off;
- tmp_freq = (stock_freq * tmp_off) / i;
- /* if this relation is closer to khz, use this. If it's equal,
- * prefer it, too - lower latency */
- if (abs(tmp_freq - khz) <= abs(old_tmp_freq - khz)) {
- *on_duration = tmp_on;
- *off_duration = tmp_off;
- old_tmp_freq = tmp_freq;
- }
- }
-
- return old_tmp_freq;
-}
-
-
-/**
- * gx_set_cpuspeed:
- * set cpu speed in khz.
- **/
-
-static void gx_set_cpuspeed(unsigned int khz)
-{
- u8 suscfg, pmer1;
- unsigned int new_khz;
- unsigned long flags;
- struct cpufreq_freqs freqs;
-
- freqs.cpu = 0;
- freqs.old = gx_get_cpuspeed(0);
-
- new_khz = gx_validate_speed(khz, &gx_params->on_duration,
- &gx_params->off_duration);
-
- freqs.new = new_khz;
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- local_irq_save(flags);
-
-
-
- if (new_khz != stock_freq) {
- /* if new khz == 100% of CPU speed, it is special case */
- switch (gx_params->cs55x0->device) {
- case PCI_DEVICE_ID_CYRIX_5530_LEGACY:
- pmer1 = gx_params->pci_pmer1 | IRQ_SPDUP | VID_SPDUP;
- /* FIXME: need to test other values -- Zwane,Miura */
- /* typical 2 to 4ms */
- gx_write_byte(PCI_IRQTC, 4);
- /* typical 50 to 100ms */
- gx_write_byte(PCI_VIDTC, 100);
- gx_write_byte(PCI_PMER1, pmer1);
-
- if (gx_params->cs55x0->revision < 0x10) {
- /* CS5530(rev 1.2, 1.3) */
- suscfg = gx_params->pci_suscfg|SUSMOD;
- } else {
- /* CS5530A,B.. */
- suscfg = gx_params->pci_suscfg|SUSMOD|PWRSVE;
- }
- break;
- case PCI_DEVICE_ID_CYRIX_5520:
- case PCI_DEVICE_ID_CYRIX_5510:
- suscfg = gx_params->pci_suscfg | SUSMOD;
- break;
- default:
- local_irq_restore(flags);
- dprintk("fatal: try to set unknown chipset.\n");
- return;
- }
- } else {
- suscfg = gx_params->pci_suscfg & ~(SUSMOD);
- gx_params->off_duration = 0;
- gx_params->on_duration = 0;
- dprintk("suspend modulation disabled: cpu runs 100%% speed.\n");
- }
-
- gx_write_byte(PCI_MODOFF, gx_params->off_duration);
- gx_write_byte(PCI_MODON, gx_params->on_duration);
-
- gx_write_byte(PCI_SUSCFG, suscfg);
- pci_read_config_byte(gx_params->cs55x0, PCI_SUSCFG, &suscfg);
-
- local_irq_restore(flags);
-
- gx_params->pci_suscfg = suscfg;
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
- dprintk("suspend modulation w/ duration of ON:%d us, OFF:%d us\n",
- gx_params->on_duration * 32, gx_params->off_duration * 32);
- dprintk("suspend modulation w/ clock speed: %d kHz.\n", freqs.new);
-}
-
-/****************************************************************
- * High level functions *
- ****************************************************************/
-
-/*
- * cpufreq_gx_verify: test if frequency range is valid
- *
- * This function checks if a given frequency range in kHz is valid
- * for the hardware supported by the driver.
- */
-
-static int cpufreq_gx_verify(struct cpufreq_policy *policy)
-{
- unsigned int tmp_freq = 0;
- u8 tmp1, tmp2;
-
- if (!stock_freq || !policy)
- return -EINVAL;
-
- policy->cpu = 0;
- cpufreq_verify_within_limits(policy, (stock_freq / max_duration),
- stock_freq);
-
- /* it needs to be assured that at least one supported frequency is
- * within policy->min and policy->max. If it is not, policy->max
- * needs to be increased until one freuqency is supported.
- * policy->min may not be decreased, though. This way we guarantee a
- * specific processing capacity.
- */
- tmp_freq = gx_validate_speed(policy->min, &tmp1, &tmp2);
- if (tmp_freq < policy->min)
- tmp_freq += stock_freq / max_duration;
- policy->min = tmp_freq;
- if (policy->min > policy->max)
- policy->max = tmp_freq;
- tmp_freq = gx_validate_speed(policy->max, &tmp1, &tmp2);
- if (tmp_freq > policy->max)
- tmp_freq -= stock_freq / max_duration;
- policy->max = tmp_freq;
- if (policy->max < policy->min)
- policy->max = policy->min;
- cpufreq_verify_within_limits(policy, (stock_freq / max_duration),
- stock_freq);
-
- return 0;
-}
-
-/*
- * cpufreq_gx_target:
- *
- */
-static int cpufreq_gx_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- u8 tmp1, tmp2;
- unsigned int tmp_freq;
-
- if (!stock_freq || !policy)
- return -EINVAL;
-
- policy->cpu = 0;
-
- tmp_freq = gx_validate_speed(target_freq, &tmp1, &tmp2);
- while (tmp_freq < policy->min) {
- tmp_freq += stock_freq / max_duration;
- tmp_freq = gx_validate_speed(tmp_freq, &tmp1, &tmp2);
- }
- while (tmp_freq > policy->max) {
- tmp_freq -= stock_freq / max_duration;
- tmp_freq = gx_validate_speed(tmp_freq, &tmp1, &tmp2);
- }
-
- gx_set_cpuspeed(tmp_freq);
-
- return 0;
-}
-
-static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy)
-{
- unsigned int maxfreq, curfreq;
-
- if (!policy || policy->cpu != 0)
- return -ENODEV;
-
- /* determine maximum frequency */
- if (pci_busclk)
- maxfreq = pci_busclk * gx_freq_mult[getCx86(CX86_DIR1) & 0x0f];
- else if (cpu_khz)
- maxfreq = cpu_khz;
- else
- maxfreq = 30000 * gx_freq_mult[getCx86(CX86_DIR1) & 0x0f];
-
- stock_freq = maxfreq;
- curfreq = gx_get_cpuspeed(0);
-
- dprintk("cpu max frequency is %d.\n", maxfreq);
- dprintk("cpu current frequency is %dkHz.\n", curfreq);
-
- /* setup basic struct for cpufreq API */
- policy->cpu = 0;
-
- if (max_duration < POLICY_MIN_DIV)
- policy->min = maxfreq / max_duration;
- else
- policy->min = maxfreq / POLICY_MIN_DIV;
- policy->max = maxfreq;
- policy->cur = curfreq;
- policy->cpuinfo.min_freq = maxfreq / max_duration;
- policy->cpuinfo.max_freq = maxfreq;
- policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
-
- return 0;
-}
-
-/*
- * cpufreq_gx_init:
- * MediaGX/Geode GX initialize cpufreq driver
- */
-static struct cpufreq_driver gx_suspmod_driver = {
- .get = gx_get_cpuspeed,
- .verify = cpufreq_gx_verify,
- .target = cpufreq_gx_target,
- .init = cpufreq_gx_cpu_init,
- .name = "gx-suspmod",
- .owner = THIS_MODULE,
-};
-
-static int __init cpufreq_gx_init(void)
-{
- int ret;
- struct gxfreq_params *params;
- struct pci_dev *gx_pci;
-
- /* Test if we have the right hardware */
- gx_pci = gx_detect_chipset();
- if (gx_pci == NULL)
- return -ENODEV;
-
- /* check whether module parameters are sane */
- if (max_duration > 0xff)
- max_duration = 0xff;
-
- dprintk("geode suspend modulation available.\n");
-
- params = kzalloc(sizeof(struct gxfreq_params), GFP_KERNEL);
- if (params == NULL)
- return -ENOMEM;
-
- params->cs55x0 = gx_pci;
- gx_params = params;
-
- /* keep cs55x0 configurations */
- pci_read_config_byte(params->cs55x0, PCI_SUSCFG, &(params->pci_suscfg));
- pci_read_config_byte(params->cs55x0, PCI_PMER1, &(params->pci_pmer1));
- pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2));
- pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration));
- pci_read_config_byte(params->cs55x0, PCI_MODOFF,
- &(params->off_duration));
-
- ret = cpufreq_register_driver(&gx_suspmod_driver);
- if (ret) {
- kfree(params);
- return ret; /* register error! */
- }
-
- return 0;
-}
-
-static void __exit cpufreq_gx_exit(void)
-{
- cpufreq_unregister_driver(&gx_suspmod_driver);
- pci_dev_put(gx_params->cs55x0);
- kfree(gx_params);
-}
-
-MODULE_AUTHOR("Hiroshi Miura <miura@da-cha.org>");
-MODULE_DESCRIPTION("Cpufreq driver for Cyrix MediaGX and NatSemi Geode");
-MODULE_LICENSE("GPL");
-
-module_init(cpufreq_gx_init);
-module_exit(cpufreq_gx_exit);
-
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
deleted file mode 100644
index 03162dac627..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ /dev/null
@@ -1,1029 +0,0 @@
-/*
- * (C) 2001-2004 Dave Jones. <davej@redhat.com>
- * (C) 2002 Padraig Brady. <padraig@antefacto.com>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- * Based upon datasheets & sample CPUs kindly provided by VIA.
- *
- * VIA have currently 3 different versions of Longhaul.
- * Version 1 (Longhaul) uses the BCR2 MSR at 0x1147.
- * It is present only in Samuel 1 (C5A), Samuel 2 (C5B) stepping 0.
- * Version 2 of longhaul is backward compatible with v1, but adds
- * LONGHAUL MSR for purpose of both frequency and voltage scaling.
- * Present in Samuel 2 (steppings 1-7 only) (C5B), and Ezra (C5C).
- * Version 3 of longhaul got renamed to Powersaver and redesigned
- * to use only the POWERSAVER MSR at 0x110a.
- * It is present in Ezra-T (C5M), Nehemiah (C5X) and above.
- * It's pretty much the same feature wise to longhaul v2, though
- * there is provision for scaling FSB too, but this doesn't work
- * too well in practice so we don't even try to use this.
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/timex.h>
-#include <linux/io.h>
-#include <linux/acpi.h>
-
-#include <asm/msr.h>
-#include <acpi/processor.h>
-
-#include "longhaul.h"
-
-#define PFX "longhaul: "
-
-#define TYPE_LONGHAUL_V1 1
-#define TYPE_LONGHAUL_V2 2
-#define TYPE_POWERSAVER 3
-
-#define CPU_SAMUEL 1
-#define CPU_SAMUEL2 2
-#define CPU_EZRA 3
-#define CPU_EZRA_T 4
-#define CPU_NEHEMIAH 5
-#define CPU_NEHEMIAH_C 6
-
-/* Flags */
-#define USE_ACPI_C3 (1 << 1)
-#define USE_NORTHBRIDGE (1 << 2)
-
-static int cpu_model;
-static unsigned int numscales = 16;
-static unsigned int fsb;
-
-static const struct mV_pos *vrm_mV_table;
-static const unsigned char *mV_vrm_table;
-
-static unsigned int highest_speed, lowest_speed; /* kHz */
-static unsigned int minmult, maxmult;
-static int can_scale_voltage;
-static struct acpi_processor *pr;
-static struct acpi_processor_cx *cx;
-static u32 acpi_regs_addr;
-static u8 longhaul_flags;
-static unsigned int longhaul_index;
-
-/* Module parameters */
-static int scale_voltage;
-static int disable_acpi_c3;
-static int revid_errata;
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "longhaul", msg)
-
-
-/* Clock ratios multiplied by 10 */
-static int mults[32];
-static int eblcr[32];
-static int longhaul_version;
-static struct cpufreq_frequency_table *longhaul_table;
-
-#ifdef CONFIG_CPU_FREQ_DEBUG
-static char speedbuffer[8];
-
-static char *print_speed(int speed)
-{
- if (speed < 1000) {
- snprintf(speedbuffer, sizeof(speedbuffer), "%dMHz", speed);
- return speedbuffer;
- }
-
- if (speed%1000 == 0)
- snprintf(speedbuffer, sizeof(speedbuffer),
- "%dGHz", speed/1000);
- else
- snprintf(speedbuffer, sizeof(speedbuffer),
- "%d.%dGHz", speed/1000, (speed%1000)/100);
-
- return speedbuffer;
-}
-#endif
-
-
-static unsigned int calc_speed(int mult)
-{
- int khz;
- khz = (mult/10)*fsb;
- if (mult%10)
- khz += fsb/2;
- khz *= 1000;
- return khz;
-}
-
-
-static int longhaul_get_cpu_mult(void)
-{
- unsigned long invalue = 0, lo, hi;
-
- rdmsr(MSR_IA32_EBL_CR_POWERON, lo, hi);
- invalue = (lo & (1<<22|1<<23|1<<24|1<<25))>>22;
- if (longhaul_version == TYPE_LONGHAUL_V2 ||
- longhaul_version == TYPE_POWERSAVER) {
- if (lo & (1<<27))
- invalue += 16;
- }
- return eblcr[invalue];
-}
-
-/* For processor with BCR2 MSR */
-
-static void do_longhaul1(unsigned int mults_index)
-{
- union msr_bcr2 bcr2;
-
- rdmsrl(MSR_VIA_BCR2, bcr2.val);
- /* Enable software clock multiplier */
- bcr2.bits.ESOFTBF = 1;
- bcr2.bits.CLOCKMUL = mults_index & 0xff;
-
- /* Sync to timer tick */
- safe_halt();
- /* Change frequency on next halt or sleep */
- wrmsrl(MSR_VIA_BCR2, bcr2.val);
- /* Invoke transition */
- ACPI_FLUSH_CPU_CACHE();
- halt();
-
- /* Disable software clock multiplier */
- local_irq_disable();
- rdmsrl(MSR_VIA_BCR2, bcr2.val);
- bcr2.bits.ESOFTBF = 0;
- wrmsrl(MSR_VIA_BCR2, bcr2.val);
-}
-
-/* For processor with Longhaul MSR */
-
-static void do_powersaver(int cx_address, unsigned int mults_index,
- unsigned int dir)
-{
- union msr_longhaul longhaul;
- u32 t;
-
- rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- /* Setup new frequency */
- if (!revid_errata)
- longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
- else
- longhaul.bits.RevisionKey = 0;
- longhaul.bits.SoftBusRatio = mults_index & 0xf;
- longhaul.bits.SoftBusRatio4 = (mults_index & 0x10) >> 4;
- /* Setup new voltage */
- if (can_scale_voltage)
- longhaul.bits.SoftVID = (mults_index >> 8) & 0x1f;
- /* Sync to timer tick */
- safe_halt();
- /* Raise voltage if necessary */
- if (can_scale_voltage && dir) {
- longhaul.bits.EnableSoftVID = 1;
- wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- /* Change voltage */
- if (!cx_address) {
- ACPI_FLUSH_CPU_CACHE();
- halt();
- } else {
- ACPI_FLUSH_CPU_CACHE();
- /* Invoke C3 */
- inb(cx_address);
- /* Dummy op - must do something useless after P_LVL3
- * read */
- t = inl(acpi_gbl_FADT.xpm_timer_block.address);
- }
- longhaul.bits.EnableSoftVID = 0;
- wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- }
-
- /* Change frequency on next halt or sleep */
- longhaul.bits.EnableSoftBusRatio = 1;
- wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- if (!cx_address) {
- ACPI_FLUSH_CPU_CACHE();
- halt();
- } else {
- ACPI_FLUSH_CPU_CACHE();
- /* Invoke C3 */
- inb(cx_address);
- /* Dummy op - must do something useless after P_LVL3 read */
- t = inl(acpi_gbl_FADT.xpm_timer_block.address);
- }
- /* Disable bus ratio bit */
- longhaul.bits.EnableSoftBusRatio = 0;
- wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
-
- /* Reduce voltage if necessary */
- if (can_scale_voltage && !dir) {
- longhaul.bits.EnableSoftVID = 1;
- wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- /* Change voltage */
- if (!cx_address) {
- ACPI_FLUSH_CPU_CACHE();
- halt();
- } else {
- ACPI_FLUSH_CPU_CACHE();
- /* Invoke C3 */
- inb(cx_address);
- /* Dummy op - must do something useless after P_LVL3
- * read */
- t = inl(acpi_gbl_FADT.xpm_timer_block.address);
- }
- longhaul.bits.EnableSoftVID = 0;
- wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- }
-}
-
-/**
- * longhaul_set_cpu_frequency()
- * @mults_index : bitpattern of the new multiplier.
- *
- * Sets a new clock ratio.
- */
-
-static void longhaul_setstate(unsigned int table_index)
-{
- unsigned int mults_index;
- int speed, mult;
- struct cpufreq_freqs freqs;
- unsigned long flags;
- unsigned int pic1_mask, pic2_mask;
- u16 bm_status = 0;
- u32 bm_timeout = 1000;
- unsigned int dir = 0;
-
- mults_index = longhaul_table[table_index].index;
- /* Safety precautions */
- mult = mults[mults_index & 0x1f];
- if (mult == -1)
- return;
- speed = calc_speed(mult);
- if ((speed > highest_speed) || (speed < lowest_speed))
- return;
- /* Voltage transition before frequency transition? */
- if (can_scale_voltage && longhaul_index < table_index)
- dir = 1;
-
- freqs.old = calc_speed(longhaul_get_cpu_mult());
- freqs.new = speed;
- freqs.cpu = 0; /* longhaul.c is UP only driver */
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- dprintk("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
- fsb, mult/10, mult%10, print_speed(speed/1000));
-retry_loop:
- preempt_disable();
- local_irq_save(flags);
-
- pic2_mask = inb(0xA1);
- pic1_mask = inb(0x21); /* works on C3. save mask. */
- outb(0xFF, 0xA1); /* Overkill */
- outb(0xFE, 0x21); /* TMR0 only */
-
- /* Wait while PCI bus is busy. */
- if (acpi_regs_addr && (longhaul_flags & USE_NORTHBRIDGE
- || ((pr != NULL) && pr->flags.bm_control))) {
- bm_status = inw(acpi_regs_addr);
- bm_status &= 1 << 4;
- while (bm_status && bm_timeout) {
- outw(1 << 4, acpi_regs_addr);
- bm_timeout--;
- bm_status = inw(acpi_regs_addr);
- bm_status &= 1 << 4;
- }
- }
-
- if (longhaul_flags & USE_NORTHBRIDGE) {
- /* Disable AGP and PCI arbiters */
- outb(3, 0x22);
- } else if ((pr != NULL) && pr->flags.bm_control) {
- /* Disable bus master arbitration */
- acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
- }
- switch (longhaul_version) {
-
- /*
- * Longhaul v1. (Samuel[C5A] and Samuel2 stepping 0[C5B])
- * Software controlled multipliers only.
- */
- case TYPE_LONGHAUL_V1:
- do_longhaul1(mults_index);
- break;
-
- /*
- * Longhaul v2 appears in Samuel2 Steppings 1->7 [C5B] and Ezra [C5C]
- *
- * Longhaul v3 (aka Powersaver). (Ezra-T [C5M] & Nehemiah [C5N])
- * Nehemiah can do FSB scaling too, but this has never been proven
- * to work in practice.
- */
- case TYPE_LONGHAUL_V2:
- case TYPE_POWERSAVER:
- if (longhaul_flags & USE_ACPI_C3) {
- /* Don't allow wakeup */
- acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 0);
- do_powersaver(cx->address, mults_index, dir);
- } else {
- do_powersaver(0, mults_index, dir);
- }
- break;
- }
-
- if (longhaul_flags & USE_NORTHBRIDGE) {
- /* Enable arbiters */
- outb(0, 0x22);
- } else if ((pr != NULL) && pr->flags.bm_control) {
- /* Enable bus master arbitration */
- acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
- }
- outb(pic2_mask, 0xA1); /* restore mask */
- outb(pic1_mask, 0x21);
-
- local_irq_restore(flags);
- preempt_enable();
-
- freqs.new = calc_speed(longhaul_get_cpu_mult());
- /* Check if requested frequency is set. */
- if (unlikely(freqs.new != speed)) {
- printk(KERN_INFO PFX "Failed to set requested frequency!\n");
- /* Revision ID = 1 but processor is expecting revision key
- * equal to 0. Jumpers at the bottom of processor will change
- * multiplier and FSB, but will not change bits in Longhaul
- * MSR nor enable voltage scaling. */
- if (!revid_errata) {
- printk(KERN_INFO PFX "Enabling \"Ignore Revision ID\" "
- "option.\n");
- revid_errata = 1;
- msleep(200);
- goto retry_loop;
- }
- /* Why ACPI C3 sometimes doesn't work is a mystery for me.
- * But it does happen. Processor is entering ACPI C3 state,
- * but it doesn't change frequency. I tried poking various
- * bits in northbridge registers, but without success. */
- if (longhaul_flags & USE_ACPI_C3) {
- printk(KERN_INFO PFX "Disabling ACPI C3 support.\n");
- longhaul_flags &= ~USE_ACPI_C3;
- if (revid_errata) {
- printk(KERN_INFO PFX "Disabling \"Ignore "
- "Revision ID\" option.\n");
- revid_errata = 0;
- }
- msleep(200);
- goto retry_loop;
- }
- /* This shouldn't happen. Longhaul ver. 2 was reported not
- * working on processors without voltage scaling, but with
- * RevID = 1. RevID errata will make things right. Just
- * to be 100% sure. */
- if (longhaul_version == TYPE_LONGHAUL_V2) {
- printk(KERN_INFO PFX "Switching to Longhaul ver. 1\n");
- longhaul_version = TYPE_LONGHAUL_V1;
- msleep(200);
- goto retry_loop;
- }
- }
- /* Report true CPU frequency */
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
- if (!bm_timeout)
- printk(KERN_INFO PFX "Warning: Timeout while waiting for "
- "idle PCI bus.\n");
-}
-
-/*
- * Centaur decided to make life a little more tricky.
- * Only longhaul v1 is allowed to read EBLCR BSEL[0:1].
- * Samuel2 and above have to try and guess what the FSB is.
- * We do this by assuming we booted at maximum multiplier, and interpolate
- * between that value multiplied by possible FSBs and cpu_mhz which
- * was calculated at boot time. Really ugly, but no other way to do this.
- */
-
-#define ROUNDING 0xf
-
-static int guess_fsb(int mult)
-{
- int speed = cpu_khz / 1000;
- int i;
- int speeds[] = { 666, 1000, 1333, 2000 };
- int f_max, f_min;
-
- for (i = 0; i < 4; i++) {
- f_max = ((speeds[i] * mult) + 50) / 100;
- f_max += (ROUNDING / 2);
- f_min = f_max - ROUNDING;
- if ((speed <= f_max) && (speed >= f_min))
- return speeds[i] / 10;
- }
- return 0;
-}
-
-
-static int __cpuinit longhaul_get_ranges(void)
-{
- unsigned int i, j, k = 0;
- unsigned int ratio;
- int mult;
-
- /* Get current frequency */
- mult = longhaul_get_cpu_mult();
- if (mult == -1) {
- printk(KERN_INFO PFX "Invalid (reserved) multiplier!\n");
- return -EINVAL;
- }
- fsb = guess_fsb(mult);
- if (fsb == 0) {
- printk(KERN_INFO PFX "Invalid (reserved) FSB!\n");
- return -EINVAL;
- }
- /* Get max multiplier - as we always did.
- * Longhaul MSR is usefull only when voltage scaling is enabled.
- * C3 is booting at max anyway. */
- maxmult = mult;
- /* Get min multiplier */
- switch (cpu_model) {
- case CPU_NEHEMIAH:
- minmult = 50;
- break;
- case CPU_NEHEMIAH_C:
- minmult = 40;
- break;
- default:
- minmult = 30;
- break;
- }
-
- dprintk("MinMult:%d.%dx MaxMult:%d.%dx\n",
- minmult/10, minmult%10, maxmult/10, maxmult%10);
-
- highest_speed = calc_speed(maxmult);
- lowest_speed = calc_speed(minmult);
- dprintk("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb,
- print_speed(lowest_speed/1000),
- print_speed(highest_speed/1000));
-
- if (lowest_speed == highest_speed) {
- printk(KERN_INFO PFX "highestspeed == lowest, aborting.\n");
- return -EINVAL;
- }
- if (lowest_speed > highest_speed) {
- printk(KERN_INFO PFX "nonsense! lowest (%d > %d) !\n",
- lowest_speed, highest_speed);
- return -EINVAL;
- }
-
- longhaul_table = kmalloc((numscales + 1) * sizeof(*longhaul_table),
- GFP_KERNEL);
- if (!longhaul_table)
- return -ENOMEM;
-
- for (j = 0; j < numscales; j++) {
- ratio = mults[j];
- if (ratio == -1)
- continue;
- if (ratio > maxmult || ratio < minmult)
- continue;
- longhaul_table[k].frequency = calc_speed(ratio);
- longhaul_table[k].index = j;
- k++;
- }
- if (k <= 1) {
- kfree(longhaul_table);
- return -ENODEV;
- }
- /* Sort */
- for (j = 0; j < k - 1; j++) {
- unsigned int min_f, min_i;
- min_f = longhaul_table[j].frequency;
- min_i = j;
- for (i = j + 1; i < k; i++) {
- if (longhaul_table[i].frequency < min_f) {
- min_f = longhaul_table[i].frequency;
- min_i = i;
- }
- }
- if (min_i != j) {
- swap(longhaul_table[j].frequency,
- longhaul_table[min_i].frequency);
- swap(longhaul_table[j].index,
- longhaul_table[min_i].index);
- }
- }
-
- longhaul_table[k].frequency = CPUFREQ_TABLE_END;
-
- /* Find index we are running on */
- for (j = 0; j < k; j++) {
- if (mults[longhaul_table[j].index & 0x1f] == mult) {
- longhaul_index = j;
- break;
- }
- }
- return 0;
-}
-
-
-static void __cpuinit longhaul_setup_voltagescaling(void)
-{
- union msr_longhaul longhaul;
- struct mV_pos minvid, maxvid, vid;
- unsigned int j, speed, pos, kHz_step, numvscales;
- int min_vid_speed;
-
- rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
- if (!(longhaul.bits.RevisionID & 1)) {
- printk(KERN_INFO PFX "Voltage scaling not supported by CPU.\n");
- return;
- }
-
- if (!longhaul.bits.VRMRev) {
- printk(KERN_INFO PFX "VRM 8.5\n");
- vrm_mV_table = &vrm85_mV[0];
- mV_vrm_table = &mV_vrm85[0];
- } else {
- printk(KERN_INFO PFX "Mobile VRM\n");
- if (cpu_model < CPU_NEHEMIAH)
- return;
- vrm_mV_table = &mobilevrm_mV[0];
- mV_vrm_table = &mV_mobilevrm[0];
- }
-
- minvid = vrm_mV_table[longhaul.bits.MinimumVID];
- maxvid = vrm_mV_table[longhaul.bits.MaximumVID];
-
- if (minvid.mV == 0 || maxvid.mV == 0 || minvid.mV > maxvid.mV) {
- printk(KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. "
- "Voltage scaling disabled.\n",
- minvid.mV/1000, minvid.mV%1000,
- maxvid.mV/1000, maxvid.mV%1000);
- return;
- }
-
- if (minvid.mV == maxvid.mV) {
- printk(KERN_INFO PFX "Claims to support voltage scaling but "
- "min & max are both %d.%03d. "
- "Voltage scaling disabled\n",
- maxvid.mV/1000, maxvid.mV%1000);
- return;
- }
-
- /* How many voltage steps*/
- numvscales = maxvid.pos - minvid.pos + 1;
- printk(KERN_INFO PFX
- "Max VID=%d.%03d "
- "Min VID=%d.%03d, "
- "%d possible voltage scales\n",
- maxvid.mV/1000, maxvid.mV%1000,
- minvid.mV/1000, minvid.mV%1000,
- numvscales);
-
- /* Calculate max frequency at min voltage */
- j = longhaul.bits.MinMHzBR;
- if (longhaul.bits.MinMHzBR4)
- j += 16;
- min_vid_speed = eblcr[j];
- if (min_vid_speed == -1)
- return;
- switch (longhaul.bits.MinMHzFSB) {
- case 0:
- min_vid_speed *= 13333;
- break;
- case 1:
- min_vid_speed *= 10000;
- break;
- case 3:
- min_vid_speed *= 6666;
- break;
- default:
- return;
- break;
- }
- if (min_vid_speed >= highest_speed)
- return;
- /* Calculate kHz for one voltage step */
- kHz_step = (highest_speed - min_vid_speed) / numvscales;
-
- j = 0;
- while (longhaul_table[j].frequency != CPUFREQ_TABLE_END) {
- speed = longhaul_table[j].frequency;
- if (speed > min_vid_speed)
- pos = (speed - min_vid_speed) / kHz_step + minvid.pos;
- else
- pos = minvid.pos;
- longhaul_table[j].index |= mV_vrm_table[pos] << 8;
- vid = vrm_mV_table[mV_vrm_table[pos]];
- printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n",
- speed, j, vid.mV);
- j++;
- }
-
- can_scale_voltage = 1;
- printk(KERN_INFO PFX "Voltage scaling enabled.\n");
-}
-
-
-static int longhaul_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, longhaul_table);
-}
-
-
-static int longhaul_target(struct cpufreq_policy *policy,
- unsigned int target_freq, unsigned int relation)
-{
- unsigned int table_index = 0;
- unsigned int i;
- unsigned int dir = 0;
- u8 vid, current_vid;
-
- if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq,
- relation, &table_index))
- return -EINVAL;
-
- /* Don't set same frequency again */
- if (longhaul_index == table_index)
- return 0;
-
- if (!can_scale_voltage)
- longhaul_setstate(table_index);
- else {
- /* On test system voltage transitions exceeding single
- * step up or down were turning motherboard off. Both
- * "ondemand" and "userspace" are unsafe. C7 is doing
- * this in hardware, C3 is old and we need to do this
- * in software. */
- i = longhaul_index;
- current_vid = (longhaul_table[longhaul_index].index >> 8);
- current_vid &= 0x1f;
- if (table_index > longhaul_index)
- dir = 1;
- while (i != table_index) {
- vid = (longhaul_table[i].index >> 8) & 0x1f;
- if (vid != current_vid) {
- longhaul_setstate(i);
- current_vid = vid;
- msleep(200);
- }
- if (dir)
- i++;
- else
- i--;
- }
- longhaul_setstate(table_index);
- }
- longhaul_index = table_index;
- return 0;
-}
-
-
-static unsigned int longhaul_get(unsigned int cpu)
-{
- if (cpu)
- return 0;
- return calc_speed(longhaul_get_cpu_mult());
-}
-
-static acpi_status longhaul_walk_callback(acpi_handle obj_handle,
- u32 nesting_level,
- void *context, void **return_value)
-{
- struct acpi_device *d;
-
- if (acpi_bus_get_device(obj_handle, &d))
- return 0;
-
- *return_value = acpi_driver_data(d);
- return 1;
-}
-
-/* VIA don't support PM2 reg, but have something similar */
-static int enable_arbiter_disable(void)
-{
- struct pci_dev *dev;
- int status = 1;
- int reg;
- u8 pci_cmd;
-
- /* Find PLE133 host bridge */
- reg = 0x78;
- dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8601_0,
- NULL);
- /* Find PM133/VT8605 host bridge */
- if (dev == NULL)
- dev = pci_get_device(PCI_VENDOR_ID_VIA,
- PCI_DEVICE_ID_VIA_8605_0, NULL);
- /* Find CLE266 host bridge */
- if (dev == NULL) {
- reg = 0x76;
- dev = pci_get_device(PCI_VENDOR_ID_VIA,
- PCI_DEVICE_ID_VIA_862X_0, NULL);
- /* Find CN400 V-Link host bridge */
- if (dev == NULL)
- dev = pci_get_device(PCI_VENDOR_ID_VIA, 0x7259, NULL);
- }
- if (dev != NULL) {
- /* Enable access to port 0x22 */
- pci_read_config_byte(dev, reg, &pci_cmd);
- if (!(pci_cmd & 1<<7)) {
- pci_cmd |= 1<<7;
- pci_write_config_byte(dev, reg, pci_cmd);
- pci_read_config_byte(dev, reg, &pci_cmd);
- if (!(pci_cmd & 1<<7)) {
- printk(KERN_ERR PFX
- "Can't enable access to port 0x22.\n");
- status = 0;
- }
- }
- pci_dev_put(dev);
- return status;
- }
- return 0;
-}
-
-static int longhaul_setup_southbridge(void)
-{
- struct pci_dev *dev;
- u8 pci_cmd;
-
- /* Find VT8235 southbridge */
- dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL);
- if (dev == NULL)
- /* Find VT8237 southbridge */
- dev = pci_get_device(PCI_VENDOR_ID_VIA,
- PCI_DEVICE_ID_VIA_8237, NULL);
- if (dev != NULL) {
- /* Set transition time to max */
- pci_read_config_byte(dev, 0xec, &pci_cmd);
- pci_cmd &= ~(1 << 2);
- pci_write_config_byte(dev, 0xec, pci_cmd);
- pci_read_config_byte(dev, 0xe4, &pci_cmd);
- pci_cmd &= ~(1 << 7);
- pci_write_config_byte(dev, 0xe4, pci_cmd);
- pci_read_config_byte(dev, 0xe5, &pci_cmd);
- pci_cmd |= 1 << 7;
- pci_write_config_byte(dev, 0xe5, pci_cmd);
- /* Get address of ACPI registers block*/
- pci_read_config_byte(dev, 0x81, &pci_cmd);
- if (pci_cmd & 1 << 7) {
- pci_read_config_dword(dev, 0x88, &acpi_regs_addr);
- acpi_regs_addr &= 0xff00;
- printk(KERN_INFO PFX "ACPI I/O at 0x%x\n",
- acpi_regs_addr);
- }
-
- pci_dev_put(dev);
- return 1;
- }
- return 0;
-}
-
-static int __cpuinit longhaul_cpu_init(struct cpufreq_policy *policy)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- char *cpuname = NULL;
- int ret;
- u32 lo, hi;
-
- /* Check what we have on this motherboard */
- switch (c->x86_model) {
- case 6:
- cpu_model = CPU_SAMUEL;
- cpuname = "C3 'Samuel' [C5A]";
- longhaul_version = TYPE_LONGHAUL_V1;
- memcpy(mults, samuel1_mults, sizeof(samuel1_mults));
- memcpy(eblcr, samuel1_eblcr, sizeof(samuel1_eblcr));
- break;
-
- case 7:
- switch (c->x86_mask) {
- case 0:
- longhaul_version = TYPE_LONGHAUL_V1;
- cpu_model = CPU_SAMUEL2;
- cpuname = "C3 'Samuel 2' [C5B]";
- /* Note, this is not a typo, early Samuel2's had
- * Samuel1 ratios. */
- memcpy(mults, samuel1_mults, sizeof(samuel1_mults));
- memcpy(eblcr, samuel2_eblcr, sizeof(samuel2_eblcr));
- break;
- case 1 ... 15:
- longhaul_version = TYPE_LONGHAUL_V2;
- if (c->x86_mask < 8) {
- cpu_model = CPU_SAMUEL2;
- cpuname = "C3 'Samuel 2' [C5B]";
- } else {
- cpu_model = CPU_EZRA;
- cpuname = "C3 'Ezra' [C5C]";
- }
- memcpy(mults, ezra_mults, sizeof(ezra_mults));
- memcpy(eblcr, ezra_eblcr, sizeof(ezra_eblcr));
- break;
- }
- break;
-
- case 8:
- cpu_model = CPU_EZRA_T;
- cpuname = "C3 'Ezra-T' [C5M]";
- longhaul_version = TYPE_POWERSAVER;
- numscales = 32;
- memcpy(mults, ezrat_mults, sizeof(ezrat_mults));
- memcpy(eblcr, ezrat_eblcr, sizeof(ezrat_eblcr));
- break;
-
- case 9:
- longhaul_version = TYPE_POWERSAVER;
- numscales = 32;
- memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults));
- memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr));
- switch (c->x86_mask) {
- case 0 ... 1:
- cpu_model = CPU_NEHEMIAH;
- cpuname = "C3 'Nehemiah A' [C5XLOE]";
- break;
- case 2 ... 4:
- cpu_model = CPU_NEHEMIAH;
- cpuname = "C3 'Nehemiah B' [C5XLOH]";
- break;
- case 5 ... 15:
- cpu_model = CPU_NEHEMIAH_C;
- cpuname = "C3 'Nehemiah C' [C5P]";
- break;
- }
- break;
-
- default:
- cpuname = "Unknown";
- break;
- }
- /* Check Longhaul ver. 2 */
- if (longhaul_version == TYPE_LONGHAUL_V2) {
- rdmsr(MSR_VIA_LONGHAUL, lo, hi);
- if (lo == 0 && hi == 0)
- /* Looks like MSR isn't present */
- longhaul_version = TYPE_LONGHAUL_V1;
- }
-
- printk(KERN_INFO PFX "VIA %s CPU detected. ", cpuname);
- switch (longhaul_version) {
- case TYPE_LONGHAUL_V1:
- case TYPE_LONGHAUL_V2:
- printk(KERN_CONT "Longhaul v%d supported.\n", longhaul_version);
- break;
- case TYPE_POWERSAVER:
- printk(KERN_CONT "Powersaver supported.\n");
- break;
- };
-
- /* Doesn't hurt */
- longhaul_setup_southbridge();
-
- /* Find ACPI data for processor */
- acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
- ACPI_UINT32_MAX, &longhaul_walk_callback, NULL,
- NULL, (void *)&pr);
-
- /* Check ACPI support for C3 state */
- if (pr != NULL && longhaul_version == TYPE_POWERSAVER) {
- cx = &pr->power.states[ACPI_STATE_C3];
- if (cx->address > 0 && cx->latency <= 1000)
- longhaul_flags |= USE_ACPI_C3;
- }
- /* Disable if it isn't working */
- if (disable_acpi_c3)
- longhaul_flags &= ~USE_ACPI_C3;
- /* Check if northbridge is friendly */
- if (enable_arbiter_disable())
- longhaul_flags |= USE_NORTHBRIDGE;
-
- /* Check ACPI support for bus master arbiter disable */
- if (!(longhaul_flags & USE_ACPI_C3
- || longhaul_flags & USE_NORTHBRIDGE)
- && ((pr == NULL) || !(pr->flags.bm_control))) {
- printk(KERN_ERR PFX
- "No ACPI support. Unsupported northbridge.\n");
- return -ENODEV;
- }
-
- if (longhaul_flags & USE_NORTHBRIDGE)
- printk(KERN_INFO PFX "Using northbridge support.\n");
- if (longhaul_flags & USE_ACPI_C3)
- printk(KERN_INFO PFX "Using ACPI support.\n");
-
- ret = longhaul_get_ranges();
- if (ret != 0)
- return ret;
-
- if ((longhaul_version != TYPE_LONGHAUL_V1) && (scale_voltage != 0))
- longhaul_setup_voltagescaling();
-
- policy->cpuinfo.transition_latency = 200000; /* nsec */
- policy->cur = calc_speed(longhaul_get_cpu_mult());
-
- ret = cpufreq_frequency_table_cpuinfo(policy, longhaul_table);
- if (ret)
- return ret;
-
- cpufreq_frequency_table_get_attr(longhaul_table, policy->cpu);
-
- return 0;
-}
-
-static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-static struct freq_attr *longhaul_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver longhaul_driver = {
- .verify = longhaul_verify,
- .target = longhaul_target,
- .get = longhaul_get,
- .init = longhaul_cpu_init,
- .exit = __devexit_p(longhaul_cpu_exit),
- .name = "longhaul",
- .owner = THIS_MODULE,
- .attr = longhaul_attr,
-};
-
-
-static int __init longhaul_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- if (c->x86_vendor != X86_VENDOR_CENTAUR || c->x86 != 6)
- return -ENODEV;
-
-#ifdef CONFIG_SMP
- if (num_online_cpus() > 1) {
- printk(KERN_ERR PFX "More than 1 CPU detected, "
- "longhaul disabled.\n");
- return -ENODEV;
- }
-#endif
-#ifdef CONFIG_X86_IO_APIC
- if (cpu_has_apic) {
- printk(KERN_ERR PFX "APIC detected. Longhaul is currently "
- "broken in this configuration.\n");
- return -ENODEV;
- }
-#endif
- switch (c->x86_model) {
- case 6 ... 9:
- return cpufreq_register_driver(&longhaul_driver);
- case 10:
- printk(KERN_ERR PFX "Use acpi-cpufreq driver for VIA C7\n");
- default:
- ;
- }
-
- return -ENODEV;
-}
-
-
-static void __exit longhaul_exit(void)
-{
- int i;
-
- for (i = 0; i < numscales; i++) {
- if (mults[i] == maxmult) {
- longhaul_setstate(i);
- break;
- }
- }
-
- cpufreq_unregister_driver(&longhaul_driver);
- kfree(longhaul_table);
-}
-
-/* Even if BIOS is exporting ACPI C3 state, and it is used
- * with success when CPU is idle, this state doesn't
- * trigger frequency transition in some cases. */
-module_param(disable_acpi_c3, int, 0644);
-MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support");
-/* Change CPU voltage with frequency. Very usefull to save
- * power, but most VIA C3 processors aren't supporting it. */
-module_param(scale_voltage, int, 0644);
-MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor");
-/* Force revision key to 0 for processors which doesn't
- * support voltage scaling, but are introducing itself as
- * such. */
-module_param(revid_errata, int, 0644);
-MODULE_PARM_DESC(revid_errata, "Ignore CPU Revision ID");
-
-MODULE_AUTHOR("Dave Jones <davej@redhat.com>");
-MODULE_DESCRIPTION("Longhaul driver for VIA Cyrix processors.");
-MODULE_LICENSE("GPL");
-
-late_initcall(longhaul_init);
-module_exit(longhaul_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.h b/arch/x86/kernel/cpu/cpufreq/longhaul.h
deleted file mode 100644
index cbf48fbca88..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.h
+++ /dev/null
@@ -1,353 +0,0 @@
-/*
- * longhaul.h
- * (C) 2003 Dave Jones.
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * VIA-specific information
- */
-
-union msr_bcr2 {
- struct {
- unsigned Reseved:19, // 18:0
- ESOFTBF:1, // 19
- Reserved2:3, // 22:20
- CLOCKMUL:4, // 26:23
- Reserved3:5; // 31:27
- } bits;
- unsigned long val;
-};
-
-union msr_longhaul {
- struct {
- unsigned RevisionID:4, // 3:0
- RevisionKey:4, // 7:4
- EnableSoftBusRatio:1, // 8
- EnableSoftVID:1, // 9
- EnableSoftBSEL:1, // 10
- Reserved:3, // 11:13
- SoftBusRatio4:1, // 14
- VRMRev:1, // 15
- SoftBusRatio:4, // 19:16
- SoftVID:5, // 24:20
- Reserved2:3, // 27:25
- SoftBSEL:2, // 29:28
- Reserved3:2, // 31:30
- MaxMHzBR:4, // 35:32
- MaximumVID:5, // 40:36
- MaxMHzFSB:2, // 42:41
- MaxMHzBR4:1, // 43
- Reserved4:4, // 47:44
- MinMHzBR:4, // 51:48
- MinimumVID:5, // 56:52
- MinMHzFSB:2, // 58:57
- MinMHzBR4:1, // 59
- Reserved5:4; // 63:60
- } bits;
- unsigned long long val;
-};
-
-/*
- * Clock ratio tables. Div/Mod by 10 to get ratio.
- * The eblcr values specify the ratio read from the CPU.
- * The mults values specify what to write to the CPU.
- */
-
-/*
- * VIA C3 Samuel 1 & Samuel 2 (stepping 0)
- */
-static const int __cpuinitdata samuel1_mults[16] = {
- -1, /* 0000 -> RESERVED */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- -1, /* 0011 -> RESERVED */
- -1, /* 0100 -> RESERVED */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- 55, /* 0111 -> 5.5x */
- 60, /* 1000 -> 6.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 50, /* 1011 -> 5.0x */
- 65, /* 1100 -> 6.5x */
- 75, /* 1101 -> 7.5x */
- -1, /* 1110 -> RESERVED */
- -1, /* 1111 -> RESERVED */
-};
-
-static const int __cpuinitdata samuel1_eblcr[16] = {
- 50, /* 0000 -> RESERVED */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- -1, /* 0011 -> RESERVED */
- 55, /* 0100 -> 5.5x */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- -1, /* 0111 -> RESERVED */
- -1, /* 1000 -> RESERVED */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 60, /* 1011 -> 6.0x */
- -1, /* 1100 -> RESERVED */
- 75, /* 1101 -> 7.5x */
- -1, /* 1110 -> RESERVED */
- 65, /* 1111 -> 6.5x */
-};
-
-/*
- * VIA C3 Samuel2 Stepping 1->15
- */
-static const int __cpuinitdata samuel2_eblcr[16] = {
- 50, /* 0000 -> 5.0x */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- 100, /* 0011 -> 10.0x */
- 55, /* 0100 -> 5.5x */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- 110, /* 0111 -> 11.0x */
- 90, /* 1000 -> 9.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 60, /* 1011 -> 6.0x */
- 120, /* 1100 -> 12.0x */
- 75, /* 1101 -> 7.5x */
- 130, /* 1110 -> 13.0x */
- 65, /* 1111 -> 6.5x */
-};
-
-/*
- * VIA C3 Ezra
- */
-static const int __cpuinitdata ezra_mults[16] = {
- 100, /* 0000 -> 10.0x */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- 90, /* 0011 -> 9.0x */
- 95, /* 0100 -> 9.5x */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- 55, /* 0111 -> 5.5x */
- 60, /* 1000 -> 6.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 50, /* 1011 -> 5.0x */
- 65, /* 1100 -> 6.5x */
- 75, /* 1101 -> 7.5x */
- 85, /* 1110 -> 8.5x */
- 120, /* 1111 -> 12.0x */
-};
-
-static const int __cpuinitdata ezra_eblcr[16] = {
- 50, /* 0000 -> 5.0x */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- 100, /* 0011 -> 10.0x */
- 55, /* 0100 -> 5.5x */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- 95, /* 0111 -> 9.5x */
- 90, /* 1000 -> 9.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 60, /* 1011 -> 6.0x */
- 120, /* 1100 -> 12.0x */
- 75, /* 1101 -> 7.5x */
- 85, /* 1110 -> 8.5x */
- 65, /* 1111 -> 6.5x */
-};
-
-/*
- * VIA C3 (Ezra-T) [C5M].
- */
-static const int __cpuinitdata ezrat_mults[32] = {
- 100, /* 0000 -> 10.0x */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- 90, /* 0011 -> 9.0x */
- 95, /* 0100 -> 9.5x */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- 55, /* 0111 -> 5.5x */
- 60, /* 1000 -> 6.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 50, /* 1011 -> 5.0x */
- 65, /* 1100 -> 6.5x */
- 75, /* 1101 -> 7.5x */
- 85, /* 1110 -> 8.5x */
- 120, /* 1111 -> 12.0x */
-
- -1, /* 0000 -> RESERVED (10.0x) */
- 110, /* 0001 -> 11.0x */
- -1, /* 0010 -> 12.0x */
- -1, /* 0011 -> RESERVED (9.0x)*/
- 105, /* 0100 -> 10.5x */
- 115, /* 0101 -> 11.5x */
- 125, /* 0110 -> 12.5x */
- 135, /* 0111 -> 13.5x */
- 140, /* 1000 -> 14.0x */
- 150, /* 1001 -> 15.0x */
- 160, /* 1010 -> 16.0x */
- 130, /* 1011 -> 13.0x */
- 145, /* 1100 -> 14.5x */
- 155, /* 1101 -> 15.5x */
- -1, /* 1110 -> RESERVED (13.0x) */
- -1, /* 1111 -> RESERVED (12.0x) */
-};
-
-static const int __cpuinitdata ezrat_eblcr[32] = {
- 50, /* 0000 -> 5.0x */
- 30, /* 0001 -> 3.0x */
- 40, /* 0010 -> 4.0x */
- 100, /* 0011 -> 10.0x */
- 55, /* 0100 -> 5.5x */
- 35, /* 0101 -> 3.5x */
- 45, /* 0110 -> 4.5x */
- 95, /* 0111 -> 9.5x */
- 90, /* 1000 -> 9.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 60, /* 1011 -> 6.0x */
- 120, /* 1100 -> 12.0x */
- 75, /* 1101 -> 7.5x */
- 85, /* 1110 -> 8.5x */
- 65, /* 1111 -> 6.5x */
-
- -1, /* 0000 -> RESERVED (9.0x) */
- 110, /* 0001 -> 11.0x */
- 120, /* 0010 -> 12.0x */
- -1, /* 0011 -> RESERVED (10.0x)*/
- 135, /* 0100 -> 13.5x */
- 115, /* 0101 -> 11.5x */
- 125, /* 0110 -> 12.5x */
- 105, /* 0111 -> 10.5x */
- 130, /* 1000 -> 13.0x */
- 150, /* 1001 -> 15.0x */
- 160, /* 1010 -> 16.0x */
- 140, /* 1011 -> 14.0x */
- -1, /* 1100 -> RESERVED (12.0x) */
- 155, /* 1101 -> 15.5x */
- -1, /* 1110 -> RESERVED (13.0x) */
- 145, /* 1111 -> 14.5x */
-};
-
-/*
- * VIA C3 Nehemiah */
-
-static const int __cpuinitdata nehemiah_mults[32] = {
- 100, /* 0000 -> 10.0x */
- -1, /* 0001 -> 16.0x */
- 40, /* 0010 -> 4.0x */
- 90, /* 0011 -> 9.0x */
- 95, /* 0100 -> 9.5x */
- -1, /* 0101 -> RESERVED */
- 45, /* 0110 -> 4.5x */
- 55, /* 0111 -> 5.5x */
- 60, /* 1000 -> 6.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 50, /* 1011 -> 5.0x */
- 65, /* 1100 -> 6.5x */
- 75, /* 1101 -> 7.5x */
- 85, /* 1110 -> 8.5x */
- 120, /* 1111 -> 12.0x */
- -1, /* 0000 -> 10.0x */
- 110, /* 0001 -> 11.0x */
- -1, /* 0010 -> 12.0x */
- -1, /* 0011 -> 9.0x */
- 105, /* 0100 -> 10.5x */
- 115, /* 0101 -> 11.5x */
- 125, /* 0110 -> 12.5x */
- 135, /* 0111 -> 13.5x */
- 140, /* 1000 -> 14.0x */
- 150, /* 1001 -> 15.0x */
- 160, /* 1010 -> 16.0x */
- 130, /* 1011 -> 13.0x */
- 145, /* 1100 -> 14.5x */
- 155, /* 1101 -> 15.5x */
- -1, /* 1110 -> RESERVED (13.0x) */
- -1, /* 1111 -> 12.0x */
-};
-
-static const int __cpuinitdata nehemiah_eblcr[32] = {
- 50, /* 0000 -> 5.0x */
- 160, /* 0001 -> 16.0x */
- 40, /* 0010 -> 4.0x */
- 100, /* 0011 -> 10.0x */
- 55, /* 0100 -> 5.5x */
- -1, /* 0101 -> RESERVED */
- 45, /* 0110 -> 4.5x */
- 95, /* 0111 -> 9.5x */
- 90, /* 1000 -> 9.0x */
- 70, /* 1001 -> 7.0x */
- 80, /* 1010 -> 8.0x */
- 60, /* 1011 -> 6.0x */
- 120, /* 1100 -> 12.0x */
- 75, /* 1101 -> 7.5x */
- 85, /* 1110 -> 8.5x */
- 65, /* 1111 -> 6.5x */
- 90, /* 0000 -> 9.0x */
- 110, /* 0001 -> 11.0x */
- 120, /* 0010 -> 12.0x */
- 100, /* 0011 -> 10.0x */
- 135, /* 0100 -> 13.5x */
- 115, /* 0101 -> 11.5x */
- 125, /* 0110 -> 12.5x */
- 105, /* 0111 -> 10.5x */
- 130, /* 1000 -> 13.0x */
- 150, /* 1001 -> 15.0x */
- 160, /* 1010 -> 16.0x */
- 140, /* 1011 -> 14.0x */
- 120, /* 1100 -> 12.0x */
- 155, /* 1101 -> 15.5x */
- -1, /* 1110 -> RESERVED (13.0x) */
- 145 /* 1111 -> 14.5x */
-};
-
-/*
- * Voltage scales. Div/Mod by 1000 to get actual voltage.
- * Which scale to use depends on the VRM type in use.
- */
-
-struct mV_pos {
- unsigned short mV;
- unsigned short pos;
-};
-
-static const struct mV_pos __cpuinitdata vrm85_mV[32] = {
- {1250, 8}, {1200, 6}, {1150, 4}, {1100, 2},
- {1050, 0}, {1800, 30}, {1750, 28}, {1700, 26},
- {1650, 24}, {1600, 22}, {1550, 20}, {1500, 18},
- {1450, 16}, {1400, 14}, {1350, 12}, {1300, 10},
- {1275, 9}, {1225, 7}, {1175, 5}, {1125, 3},
- {1075, 1}, {1825, 31}, {1775, 29}, {1725, 27},
- {1675, 25}, {1625, 23}, {1575, 21}, {1525, 19},
- {1475, 17}, {1425, 15}, {1375, 13}, {1325, 11}
-};
-
-static const unsigned char __cpuinitdata mV_vrm85[32] = {
- 0x04, 0x14, 0x03, 0x13, 0x02, 0x12, 0x01, 0x11,
- 0x00, 0x10, 0x0f, 0x1f, 0x0e, 0x1e, 0x0d, 0x1d,
- 0x0c, 0x1c, 0x0b, 0x1b, 0x0a, 0x1a, 0x09, 0x19,
- 0x08, 0x18, 0x07, 0x17, 0x06, 0x16, 0x05, 0x15
-};
-
-static const struct mV_pos __cpuinitdata mobilevrm_mV[32] = {
- {1750, 31}, {1700, 30}, {1650, 29}, {1600, 28},
- {1550, 27}, {1500, 26}, {1450, 25}, {1400, 24},
- {1350, 23}, {1300, 22}, {1250, 21}, {1200, 20},
- {1150, 19}, {1100, 18}, {1050, 17}, {1000, 16},
- {975, 15}, {950, 14}, {925, 13}, {900, 12},
- {875, 11}, {850, 10}, {825, 9}, {800, 8},
- {775, 7}, {750, 6}, {725, 5}, {700, 4},
- {675, 3}, {650, 2}, {625, 1}, {600, 0}
-};
-
-static const unsigned char __cpuinitdata mV_mobilevrm[32] = {
- 0x1f, 0x1e, 0x1d, 0x1c, 0x1b, 0x1a, 0x19, 0x18,
- 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10,
- 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08,
- 0x07, 0x06, 0x05, 0x04, 0x03, 0x02, 0x01, 0x00
-};
-
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
deleted file mode 100644
index d9f51367666..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ /dev/null
@@ -1,327 +0,0 @@
-/*
- * (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/timex.h>
-
-#include <asm/msr.h>
-#include <asm/processor.h>
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "longrun", msg)
-
-static struct cpufreq_driver longrun_driver;
-
-/**
- * longrun_{low,high}_freq is needed for the conversion of cpufreq kHz
- * values into per cent values. In TMTA microcode, the following is valid:
- * performance_pctg = (current_freq - low_freq)/(high_freq - low_freq)
- */
-static unsigned int longrun_low_freq, longrun_high_freq;
-
-
-/**
- * longrun_get_policy - get the current LongRun policy
- * @policy: struct cpufreq_policy where current policy is written into
- *
- * Reads the current LongRun policy by access to MSR_TMTA_LONGRUN_FLAGS
- * and MSR_TMTA_LONGRUN_CTRL
- */
-static void __cpuinit longrun_get_policy(struct cpufreq_policy *policy)
-{
- u32 msr_lo, msr_hi;
-
- rdmsr(MSR_TMTA_LONGRUN_FLAGS, msr_lo, msr_hi);
- dprintk("longrun flags are %x - %x\n", msr_lo, msr_hi);
- if (msr_lo & 0x01)
- policy->policy = CPUFREQ_POLICY_PERFORMANCE;
- else
- policy->policy = CPUFREQ_POLICY_POWERSAVE;
-
- rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
- dprintk("longrun ctrl is %x - %x\n", msr_lo, msr_hi);
- msr_lo &= 0x0000007F;
- msr_hi &= 0x0000007F;
-
- if (longrun_high_freq <= longrun_low_freq) {
- /* Assume degenerate Longrun table */
- policy->min = policy->max = longrun_high_freq;
- } else {
- policy->min = longrun_low_freq + msr_lo *
- ((longrun_high_freq - longrun_low_freq) / 100);
- policy->max = longrun_low_freq + msr_hi *
- ((longrun_high_freq - longrun_low_freq) / 100);
- }
- policy->cpu = 0;
-}
-
-
-/**
- * longrun_set_policy - sets a new CPUFreq policy
- * @policy: new policy
- *
- * Sets a new CPUFreq policy on LongRun-capable processors. This function
- * has to be called with cpufreq_driver locked.
- */
-static int longrun_set_policy(struct cpufreq_policy *policy)
-{
- u32 msr_lo, msr_hi;
- u32 pctg_lo, pctg_hi;
-
- if (!policy)
- return -EINVAL;
-
- if (longrun_high_freq <= longrun_low_freq) {
- /* Assume degenerate Longrun table */
- pctg_lo = pctg_hi = 100;
- } else {
- pctg_lo = (policy->min - longrun_low_freq) /
- ((longrun_high_freq - longrun_low_freq) / 100);
- pctg_hi = (policy->max - longrun_low_freq) /
- ((longrun_high_freq - longrun_low_freq) / 100);
- }
-
- if (pctg_hi > 100)
- pctg_hi = 100;
- if (pctg_lo > pctg_hi)
- pctg_lo = pctg_hi;
-
- /* performance or economy mode */
- rdmsr(MSR_TMTA_LONGRUN_FLAGS, msr_lo, msr_hi);
- msr_lo &= 0xFFFFFFFE;
- switch (policy->policy) {
- case CPUFREQ_POLICY_PERFORMANCE:
- msr_lo |= 0x00000001;
- break;
- case CPUFREQ_POLICY_POWERSAVE:
- break;
- }
- wrmsr(MSR_TMTA_LONGRUN_FLAGS, msr_lo, msr_hi);
-
- /* lower and upper boundary */
- rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
- msr_lo &= 0xFFFFFF80;
- msr_hi &= 0xFFFFFF80;
- msr_lo |= pctg_lo;
- msr_hi |= pctg_hi;
- wrmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
-
- return 0;
-}
-
-
-/**
- * longrun_verify_poliy - verifies a new CPUFreq policy
- * @policy: the policy to verify
- *
- * Validates a new CPUFreq policy. This function has to be called with
- * cpufreq_driver locked.
- */
-static int longrun_verify_policy(struct cpufreq_policy *policy)
-{
- if (!policy)
- return -EINVAL;
-
- policy->cpu = 0;
- cpufreq_verify_within_limits(policy,
- policy->cpuinfo.min_freq,
- policy->cpuinfo.max_freq);
-
- if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
- (policy->policy != CPUFREQ_POLICY_PERFORMANCE))
- return -EINVAL;
-
- return 0;
-}
-
-static unsigned int longrun_get(unsigned int cpu)
-{
- u32 eax, ebx, ecx, edx;
-
- if (cpu)
- return 0;
-
- cpuid(0x80860007, &eax, &ebx, &ecx, &edx);
- dprintk("cpuid eax is %u\n", eax);
-
- return eax * 1000;
-}
-
-/**
- * longrun_determine_freqs - determines the lowest and highest possible core frequency
- * @low_freq: an int to put the lowest frequency into
- * @high_freq: an int to put the highest frequency into
- *
- * Determines the lowest and highest possible core frequencies on this CPU.
- * This is necessary to calculate the performance percentage according to
- * TMTA rules:
- * performance_pctg = (target_freq - low_freq)/(high_freq - low_freq)
- */
-static int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
- unsigned int *high_freq)
-{
- u32 msr_lo, msr_hi;
- u32 save_lo, save_hi;
- u32 eax, ebx, ecx, edx;
- u32 try_hi;
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- if (!low_freq || !high_freq)
- return -EINVAL;
-
- if (cpu_has(c, X86_FEATURE_LRTI)) {
- /* if the LongRun Table Interface is present, the
- * detection is a bit easier:
- * For minimum frequency, read out the maximum
- * level (msr_hi), write that into "currently
- * selected level", and read out the frequency.
- * For maximum frequency, read out level zero.
- */
- /* minimum */
- rdmsr(MSR_TMTA_LRTI_READOUT, msr_lo, msr_hi);
- wrmsr(MSR_TMTA_LRTI_READOUT, msr_hi, msr_hi);
- rdmsr(MSR_TMTA_LRTI_VOLT_MHZ, msr_lo, msr_hi);
- *low_freq = msr_lo * 1000; /* to kHz */
-
- /* maximum */
- wrmsr(MSR_TMTA_LRTI_READOUT, 0, msr_hi);
- rdmsr(MSR_TMTA_LRTI_VOLT_MHZ, msr_lo, msr_hi);
- *high_freq = msr_lo * 1000; /* to kHz */
-
- dprintk("longrun table interface told %u - %u kHz\n",
- *low_freq, *high_freq);
-
- if (*low_freq > *high_freq)
- *low_freq = *high_freq;
- return 0;
- }
-
- /* set the upper border to the value determined during TSC init */
- *high_freq = (cpu_khz / 1000);
- *high_freq = *high_freq * 1000;
- dprintk("high frequency is %u kHz\n", *high_freq);
-
- /* get current borders */
- rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
- save_lo = msr_lo & 0x0000007F;
- save_hi = msr_hi & 0x0000007F;
-
- /* if current perf_pctg is larger than 90%, we need to decrease the
- * upper limit to make the calculation more accurate.
- */
- cpuid(0x80860007, &eax, &ebx, &ecx, &edx);
- /* try decreasing in 10% steps, some processors react only
- * on some barrier values */
- for (try_hi = 80; try_hi > 0 && ecx > 90; try_hi -= 10) {
- /* set to 0 to try_hi perf_pctg */
- msr_lo &= 0xFFFFFF80;
- msr_hi &= 0xFFFFFF80;
- msr_hi |= try_hi;
- wrmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
-
- /* read out current core MHz and current perf_pctg */
- cpuid(0x80860007, &eax, &ebx, &ecx, &edx);
-
- /* restore values */
- wrmsr(MSR_TMTA_LONGRUN_CTRL, save_lo, save_hi);
- }
- dprintk("percentage is %u %%, freq is %u MHz\n", ecx, eax);
-
- /* performance_pctg = (current_freq - low_freq)/(high_freq - low_freq)
- * eqals
- * low_freq * (1 - perf_pctg) = (cur_freq - high_freq * perf_pctg)
- *
- * high_freq * perf_pctg is stored tempoarily into "ebx".
- */
- ebx = (((cpu_khz / 1000) * ecx) / 100); /* to MHz */
-
- if ((ecx > 95) || (ecx == 0) || (eax < ebx))
- return -EIO;
-
- edx = ((eax - ebx) * 100) / (100 - ecx);
- *low_freq = edx * 1000; /* back to kHz */
-
- dprintk("low frequency is %u kHz\n", *low_freq);
-
- if (*low_freq > *high_freq)
- *low_freq = *high_freq;
-
- return 0;
-}
-
-
-static int __cpuinit longrun_cpu_init(struct cpufreq_policy *policy)
-{
- int result = 0;
-
- /* capability check */
- if (policy->cpu != 0)
- return -ENODEV;
-
- /* detect low and high frequency */
- result = longrun_determine_freqs(&longrun_low_freq, &longrun_high_freq);
- if (result)
- return result;
-
- /* cpuinfo and default policy values */
- policy->cpuinfo.min_freq = longrun_low_freq;
- policy->cpuinfo.max_freq = longrun_high_freq;
- policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
- longrun_get_policy(policy);
-
- return 0;
-}
-
-
-static struct cpufreq_driver longrun_driver = {
- .flags = CPUFREQ_CONST_LOOPS,
- .verify = longrun_verify_policy,
- .setpolicy = longrun_set_policy,
- .get = longrun_get,
- .init = longrun_cpu_init,
- .name = "longrun",
- .owner = THIS_MODULE,
-};
-
-
-/**
- * longrun_init - initializes the Transmeta Crusoe LongRun CPUFreq driver
- *
- * Initializes the LongRun support.
- */
-static int __init longrun_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- if (c->x86_vendor != X86_VENDOR_TRANSMETA ||
- !cpu_has(c, X86_FEATURE_LONGRUN))
- return -ENODEV;
-
- return cpufreq_register_driver(&longrun_driver);
-}
-
-
-/**
- * longrun_exit - unregisters LongRun support
- */
-static void __exit longrun_exit(void)
-{
- cpufreq_unregister_driver(&longrun_driver);
-}
-
-
-MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
-MODULE_DESCRIPTION("LongRun driver for Transmeta Crusoe and "
- "Efficeon processors.");
-MODULE_LICENSE("GPL");
-
-module_init(longrun_init);
-module_exit(longrun_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.c b/arch/x86/kernel/cpu/cpufreq/mperf.c
deleted file mode 100644
index 911e193018a..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/mperf.c
+++ /dev/null
@@ -1,51 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/slab.h>
-
-#include "mperf.h"
-
-static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
-
-/* Called via smp_call_function_single(), on the target CPU */
-static void read_measured_perf_ctrs(void *_cur)
-{
- struct aperfmperf *am = _cur;
-
- get_aperfmperf(am);
-}
-
-/*
- * Return the measured active (C0) frequency on this CPU since last call
- * to this function.
- * Input: cpu number
- * Return: Average CPU frequency in terms of max frequency (zero on error)
- *
- * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
- * over a period of time, while CPU is in C0 state.
- * IA32_MPERF counts at the rate of max advertised frequency
- * IA32_APERF counts at the rate of actual CPU frequency
- * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
- * no meaning should be associated with absolute values of these MSRs.
- */
-unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
- unsigned int cpu)
-{
- struct aperfmperf perf;
- unsigned long ratio;
- unsigned int retval;
-
- if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
- return 0;
-
- ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
- per_cpu(acfreq_old_perf, cpu) = perf;
-
- retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
-
- return retval;
-}
-EXPORT_SYMBOL_GPL(cpufreq_get_measured_perf);
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.h b/arch/x86/kernel/cpu/cpufreq/mperf.h
deleted file mode 100644
index 5dbf2950dc2..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/mperf.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * (c) 2010 Advanced Micro Devices, Inc.
- * Your use of this code is subject to the terms and conditions of the
- * GNU general public license version 2. See "COPYING" or
- * http://www.gnu.org/licenses/gpl.html
- */
-
-unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
- unsigned int cpu);
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
deleted file mode 100644
index bd1cac747f6..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ /dev/null
@@ -1,331 +0,0 @@
-/*
- * Pentium 4/Xeon CPU on demand clock modulation/speed scaling
- * (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
- * (C) 2002 Zwane Mwaikambo <zwane@commfireservices.com>
- * (C) 2002 Arjan van de Ven <arjanv@redhat.com>
- * (C) 2002 Tora T. Engstad
- * All Rights Reserved
- *
- * 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.
- *
- * The author(s) of this software shall not be held liable for damages
- * of any nature resulting due to the use of this software. This
- * software is provided AS-IS with no warranties.
- *
- * Date Errata Description
- * 20020525 N44, O17 12.5% or 25% DC causes lockup
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/cpufreq.h>
-#include <linux/cpumask.h>
-#include <linux/timex.h>
-
-#include <asm/processor.h>
-#include <asm/msr.h>
-#include <asm/timer.h>
-
-#include "speedstep-lib.h"
-
-#define PFX "p4-clockmod: "
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "p4-clockmod", msg)
-
-/*
- * Duty Cycle (3bits), note DC_DISABLE is not specified in
- * intel docs i just use it to mean disable
- */
-enum {
- DC_RESV, DC_DFLT, DC_25PT, DC_38PT, DC_50PT,
- DC_64PT, DC_75PT, DC_88PT, DC_DISABLE
-};
-
-#define DC_ENTRIES 8
-
-
-static int has_N44_O17_errata[NR_CPUS];
-static unsigned int stock_freq;
-static struct cpufreq_driver p4clockmod_driver;
-static unsigned int cpufreq_p4_get(unsigned int cpu);
-
-static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate)
-{
- u32 l, h;
-
- if (!cpu_online(cpu) ||
- (newstate > DC_DISABLE) || (newstate == DC_RESV))
- return -EINVAL;
-
- rdmsr_on_cpu(cpu, MSR_IA32_THERM_STATUS, &l, &h);
-
- if (l & 0x01)
- dprintk("CPU#%d currently thermal throttled\n", cpu);
-
- if (has_N44_O17_errata[cpu] &&
- (newstate == DC_25PT || newstate == DC_DFLT))
- newstate = DC_38PT;
-
- rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h);
- if (newstate == DC_DISABLE) {
- dprintk("CPU#%d disabling modulation\n", cpu);
- wrmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, l & ~(1<<4), h);
- } else {
- dprintk("CPU#%d setting duty cycle to %d%%\n",
- cpu, ((125 * newstate) / 10));
- /* bits 63 - 5 : reserved
- * bit 4 : enable/disable
- * bits 3-1 : duty cycle
- * bit 0 : reserved
- */
- l = (l & ~14);
- l = l | (1<<4) | ((newstate & 0x7)<<1);
- wrmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, l, h);
- }
-
- return 0;
-}
-
-
-static struct cpufreq_frequency_table p4clockmod_table[] = {
- {DC_RESV, CPUFREQ_ENTRY_INVALID},
- {DC_DFLT, 0},
- {DC_25PT, 0},
- {DC_38PT, 0},
- {DC_50PT, 0},
- {DC_64PT, 0},
- {DC_75PT, 0},
- {DC_88PT, 0},
- {DC_DISABLE, 0},
- {DC_RESV, CPUFREQ_TABLE_END},
-};
-
-
-static int cpufreq_p4_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate = DC_RESV;
- struct cpufreq_freqs freqs;
- int i;
-
- if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0],
- target_freq, relation, &newstate))
- return -EINVAL;
-
- freqs.old = cpufreq_p4_get(policy->cpu);
- freqs.new = stock_freq * p4clockmod_table[newstate].index / 8;
-
- if (freqs.new == freqs.old)
- return 0;
-
- /* notifiers */
- for_each_cpu(i, policy->cpus) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- }
-
- /* run on each logical CPU,
- * see section 13.15.3 of IA32 Intel Architecture Software
- * Developer's Manual, Volume 3
- */
- for_each_cpu(i, policy->cpus)
- cpufreq_p4_setdc(i, p4clockmod_table[newstate].index);
-
- /* notifiers */
- for_each_cpu(i, policy->cpus) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
-
- return 0;
-}
-
-
-static int cpufreq_p4_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, &p4clockmod_table[0]);
-}
-
-
-static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
-{
- if (c->x86 == 0x06) {
- if (cpu_has(c, X86_FEATURE_EST))
- printk(KERN_WARNING PFX "Warning: EST-capable CPU "
- "detected. The acpi-cpufreq module offers "
- "voltage scaling in addition of frequency "
- "scaling. You should use that instead of "
- "p4-clockmod, if possible.\n");
- switch (c->x86_model) {
- case 0x0E: /* Core */
- case 0x0F: /* Core Duo */
- case 0x16: /* Celeron Core */
- case 0x1C: /* Atom */
- p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
- return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE);
- case 0x0D: /* Pentium M (Dothan) */
- p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
- /* fall through */
- case 0x09: /* Pentium M (Banias) */
- return speedstep_get_frequency(SPEEDSTEP_CPU_PM);
- }
- }
-
- if (c->x86 != 0xF)
- return 0;
-
- /* on P-4s, the TSC runs with constant frequency independent whether
- * throttling is active or not. */
- p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
-
- if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4M) {
- printk(KERN_WARNING PFX "Warning: Pentium 4-M detected. "
- "The speedstep-ich or acpi cpufreq modules offer "
- "voltage scaling in addition of frequency scaling. "
- "You should use either one instead of p4-clockmod, "
- "if possible.\n");
- return speedstep_get_frequency(SPEEDSTEP_CPU_P4M);
- }
-
- return speedstep_get_frequency(SPEEDSTEP_CPU_P4D);
-}
-
-
-
-static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
-{
- struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
- int cpuid = 0;
- unsigned int i;
-
-#ifdef CONFIG_SMP
- cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
-#endif
-
- /* Errata workaround */
- cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_mask;
- switch (cpuid) {
- case 0x0f07:
- case 0x0f0a:
- case 0x0f11:
- case 0x0f12:
- has_N44_O17_errata[policy->cpu] = 1;
- dprintk("has errata -- disabling low frequencies\n");
- }
-
- if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4D &&
- c->x86_model < 2) {
- /* switch to maximum frequency and measure result */
- cpufreq_p4_setdc(policy->cpu, DC_DISABLE);
- recalibrate_cpu_khz();
- }
- /* get max frequency */
- stock_freq = cpufreq_p4_get_frequency(c);
- if (!stock_freq)
- return -EINVAL;
-
- /* table init */
- for (i = 1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) {
- if ((i < 2) && (has_N44_O17_errata[policy->cpu]))
- p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID;
- else
- p4clockmod_table[i].frequency = (stock_freq * i)/8;
- }
- cpufreq_frequency_table_get_attr(p4clockmod_table, policy->cpu);
-
- /* cpuinfo and default policy values */
-
- /* the transition latency is set to be 1 higher than the maximum
- * transition latency of the ondemand governor */
- policy->cpuinfo.transition_latency = 10000001;
- policy->cur = stock_freq;
-
- return cpufreq_frequency_table_cpuinfo(policy, &p4clockmod_table[0]);
-}
-
-
-static int cpufreq_p4_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-static unsigned int cpufreq_p4_get(unsigned int cpu)
-{
- u32 l, h;
-
- rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h);
-
- if (l & 0x10) {
- l = l >> 1;
- l &= 0x7;
- } else
- l = DC_DISABLE;
-
- if (l != DC_DISABLE)
- return stock_freq * l / 8;
-
- return stock_freq;
-}
-
-static struct freq_attr *p4clockmod_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver p4clockmod_driver = {
- .verify = cpufreq_p4_verify,
- .target = cpufreq_p4_target,
- .init = cpufreq_p4_cpu_init,
- .exit = cpufreq_p4_cpu_exit,
- .get = cpufreq_p4_get,
- .name = "p4-clockmod",
- .owner = THIS_MODULE,
- .attr = p4clockmod_attr,
-};
-
-
-static int __init cpufreq_p4_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- int ret;
-
- /*
- * THERM_CONTROL is architectural for IA32 now, so
- * we can rely on the capability checks
- */
- if (c->x86_vendor != X86_VENDOR_INTEL)
- return -ENODEV;
-
- if (!test_cpu_cap(c, X86_FEATURE_ACPI) ||
- !test_cpu_cap(c, X86_FEATURE_ACC))
- return -ENODEV;
-
- ret = cpufreq_register_driver(&p4clockmod_driver);
- if (!ret)
- printk(KERN_INFO PFX "P4/Xeon(TM) CPU On-Demand Clock "
- "Modulation available\n");
-
- return ret;
-}
-
-
-static void __exit cpufreq_p4_exit(void)
-{
- cpufreq_unregister_driver(&p4clockmod_driver);
-}
-
-
-MODULE_AUTHOR("Zwane Mwaikambo <zwane@commfireservices.com>");
-MODULE_DESCRIPTION("cpufreq driver for Pentium(TM) 4/Xeon(TM)");
-MODULE_LICENSE("GPL");
-
-late_initcall(cpufreq_p4_init);
-module_exit(cpufreq_p4_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
deleted file mode 100644
index 4f6f679f279..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ /dev/null
@@ -1,626 +0,0 @@
-/*
- * pcc-cpufreq.c - Processor Clocking Control firmware cpufreq interface
- *
- * Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
- * Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
- * Nagananda Chumbalkar <nagananda.chumbalkar@hp.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; version 2 of the License.
- *
- * 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, GOOD TITLE or NON
- * INFRINGEMENT. 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.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/cpufreq.h>
-#include <linux/compiler.h>
-#include <linux/slab.h>
-
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/spinlock.h>
-#include <linux/uaccess.h>
-
-#include <acpi/processor.h>
-
-#define PCC_VERSION "1.00.00"
-#define POLL_LOOPS 300
-
-#define CMD_COMPLETE 0x1
-#define CMD_GET_FREQ 0x0
-#define CMD_SET_FREQ 0x1
-
-#define BUF_SZ 4
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "pcc-cpufreq", msg)
-
-struct pcc_register_resource {
- u8 descriptor;
- u16 length;
- u8 space_id;
- u8 bit_width;
- u8 bit_offset;
- u8 access_size;
- u64 address;
-} __attribute__ ((packed));
-
-struct pcc_memory_resource {
- u8 descriptor;
- u16 length;
- u8 space_id;
- u8 resource_usage;
- u8 type_specific;
- u64 granularity;
- u64 minimum;
- u64 maximum;
- u64 translation_offset;
- u64 address_length;
-} __attribute__ ((packed));
-
-static struct cpufreq_driver pcc_cpufreq_driver;
-
-struct pcc_header {
- u32 signature;
- u16 length;
- u8 major;
- u8 minor;
- u32 features;
- u16 command;
- u16 status;
- u32 latency;
- u32 minimum_time;
- u32 maximum_time;
- u32 nominal;
- u32 throttled_frequency;
- u32 minimum_frequency;
-};
-
-static void __iomem *pcch_virt_addr;
-static struct pcc_header __iomem *pcch_hdr;
-
-static DEFINE_SPINLOCK(pcc_lock);
-
-static struct acpi_generic_address doorbell;
-
-static u64 doorbell_preserve;
-static u64 doorbell_write;
-
-static u8 OSC_UUID[16] = {0x63, 0x9B, 0x2C, 0x9F, 0x70, 0x91, 0x49, 0x1f,
- 0xBB, 0x4F, 0xA5, 0x98, 0x2F, 0xA1, 0xB5, 0x46};
-
-struct pcc_cpu {
- u32 input_offset;
- u32 output_offset;
-};
-
-static struct pcc_cpu __percpu *pcc_cpu_info;
-
-static int pcc_cpufreq_verify(struct cpufreq_policy *policy)
-{
- cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
- policy->cpuinfo.max_freq);
- return 0;
-}
-
-static inline void pcc_cmd(void)
-{
- u64 doorbell_value;
- int i;
-
- acpi_read(&doorbell_value, &doorbell);
- acpi_write((doorbell_value & doorbell_preserve) | doorbell_write,
- &doorbell);
-
- for (i = 0; i < POLL_LOOPS; i++) {
- if (ioread16(&pcch_hdr->status) & CMD_COMPLETE)
- break;
- }
-}
-
-static inline void pcc_clear_mapping(void)
-{
- if (pcch_virt_addr)
- iounmap(pcch_virt_addr);
- pcch_virt_addr = NULL;
-}
-
-static unsigned int pcc_get_freq(unsigned int cpu)
-{
- struct pcc_cpu *pcc_cpu_data;
- unsigned int curr_freq;
- unsigned int freq_limit;
- u16 status;
- u32 input_buffer;
- u32 output_buffer;
-
- spin_lock(&pcc_lock);
-
- dprintk("get: get_freq for CPU %d\n", cpu);
- pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
-
- input_buffer = 0x1;
- iowrite32(input_buffer,
- (pcch_virt_addr + pcc_cpu_data->input_offset));
- iowrite16(CMD_GET_FREQ, &pcch_hdr->command);
-
- pcc_cmd();
-
- output_buffer =
- ioread32(pcch_virt_addr + pcc_cpu_data->output_offset);
-
- /* Clear the input buffer - we are done with the current command */
- memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
-
- status = ioread16(&pcch_hdr->status);
- if (status != CMD_COMPLETE) {
- dprintk("get: FAILED: for CPU %d, status is %d\n",
- cpu, status);
- goto cmd_incomplete;
- }
- iowrite16(0, &pcch_hdr->status);
- curr_freq = (((ioread32(&pcch_hdr->nominal) * (output_buffer & 0xff))
- / 100) * 1000);
-
- dprintk("get: SUCCESS: (virtual) output_offset for cpu %d is "
- "0x%x, contains a value of: 0x%x. Speed is: %d MHz\n",
- cpu, (pcch_virt_addr + pcc_cpu_data->output_offset),
- output_buffer, curr_freq);
-
- freq_limit = (output_buffer >> 8) & 0xff;
- if (freq_limit != 0xff) {
- dprintk("get: frequency for cpu %d is being temporarily"
- " capped at %d\n", cpu, curr_freq);
- }
-
- spin_unlock(&pcc_lock);
- return curr_freq;
-
-cmd_incomplete:
- iowrite16(0, &pcch_hdr->status);
- spin_unlock(&pcc_lock);
- return -EINVAL;
-}
-
-static int pcc_cpufreq_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- struct pcc_cpu *pcc_cpu_data;
- struct cpufreq_freqs freqs;
- u16 status;
- u32 input_buffer;
- int cpu;
-
- spin_lock(&pcc_lock);
- cpu = policy->cpu;
- pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
-
- dprintk("target: CPU %d should go to target freq: %d "
- "(virtual) input_offset is 0x%x\n",
- cpu, target_freq,
- (pcch_virt_addr + pcc_cpu_data->input_offset));
-
- freqs.new = target_freq;
- freqs.cpu = cpu;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- input_buffer = 0x1 | (((target_freq * 100)
- / (ioread32(&pcch_hdr->nominal) * 1000)) << 8);
- iowrite32(input_buffer,
- (pcch_virt_addr + pcc_cpu_data->input_offset));
- iowrite16(CMD_SET_FREQ, &pcch_hdr->command);
-
- pcc_cmd();
-
- /* Clear the input buffer - we are done with the current command */
- memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
-
- status = ioread16(&pcch_hdr->status);
- if (status != CMD_COMPLETE) {
- dprintk("target: FAILED for cpu %d, with status: 0x%x\n",
- cpu, status);
- goto cmd_incomplete;
- }
- iowrite16(0, &pcch_hdr->status);
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- dprintk("target: was SUCCESSFUL for cpu %d\n", cpu);
- spin_unlock(&pcc_lock);
-
- return 0;
-
-cmd_incomplete:
- iowrite16(0, &pcch_hdr->status);
- spin_unlock(&pcc_lock);
- return -EINVAL;
-}
-
-static int pcc_get_offset(int cpu)
-{
- acpi_status status;
- struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
- union acpi_object *pccp, *offset;
- struct pcc_cpu *pcc_cpu_data;
- struct acpi_processor *pr;
- int ret = 0;
-
- pr = per_cpu(processors, cpu);
- pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
-
- status = acpi_evaluate_object(pr->handle, "PCCP", NULL, &buffer);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- pccp = buffer.pointer;
- if (!pccp || pccp->type != ACPI_TYPE_PACKAGE) {
- ret = -ENODEV;
- goto out_free;
- };
-
- offset = &(pccp->package.elements[0]);
- if (!offset || offset->type != ACPI_TYPE_INTEGER) {
- ret = -ENODEV;
- goto out_free;
- }
-
- pcc_cpu_data->input_offset = offset->integer.value;
-
- offset = &(pccp->package.elements[1]);
- if (!offset || offset->type != ACPI_TYPE_INTEGER) {
- ret = -ENODEV;
- goto out_free;
- }
-
- pcc_cpu_data->output_offset = offset->integer.value;
-
- memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
- memset_io((pcch_virt_addr + pcc_cpu_data->output_offset), 0, BUF_SZ);
-
- dprintk("pcc_get_offset: for CPU %d: pcc_cpu_data "
- "input_offset: 0x%x, pcc_cpu_data output_offset: 0x%x\n",
- cpu, pcc_cpu_data->input_offset, pcc_cpu_data->output_offset);
-out_free:
- kfree(buffer.pointer);
- return ret;
-}
-
-static int __init pcc_cpufreq_do_osc(acpi_handle *handle)
-{
- acpi_status status;
- struct acpi_object_list input;
- struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
- union acpi_object in_params[4];
- union acpi_object *out_obj;
- u32 capabilities[2];
- u32 errors;
- u32 supported;
- int ret = 0;
-
- input.count = 4;
- input.pointer = in_params;
- input.count = 4;
- input.pointer = in_params;
- in_params[0].type = ACPI_TYPE_BUFFER;
- in_params[0].buffer.length = 16;
- in_params[0].buffer.pointer = OSC_UUID;
- in_params[1].type = ACPI_TYPE_INTEGER;
- in_params[1].integer.value = 1;
- in_params[2].type = ACPI_TYPE_INTEGER;
- in_params[2].integer.value = 2;
- in_params[3].type = ACPI_TYPE_BUFFER;
- in_params[3].buffer.length = 8;
- in_params[3].buffer.pointer = (u8 *)&capabilities;
-
- capabilities[0] = OSC_QUERY_ENABLE;
- capabilities[1] = 0x1;
-
- status = acpi_evaluate_object(*handle, "_OSC", &input, &output);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- if (!output.length)
- return -ENODEV;
-
- out_obj = output.pointer;
- if (out_obj->type != ACPI_TYPE_BUFFER) {
- ret = -ENODEV;
- goto out_free;
- }
-
- errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
- if (errors) {
- ret = -ENODEV;
- goto out_free;
- }
-
- supported = *((u32 *)(out_obj->buffer.pointer + 4));
- if (!(supported & 0x1)) {
- ret = -ENODEV;
- goto out_free;
- }
-
- kfree(output.pointer);
- capabilities[0] = 0x0;
- capabilities[1] = 0x1;
-
- status = acpi_evaluate_object(*handle, "_OSC", &input, &output);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- if (!output.length)
- return -ENODEV;
-
- out_obj = output.pointer;
- if (out_obj->type != ACPI_TYPE_BUFFER) {
- ret = -ENODEV;
- goto out_free;
- }
-
- errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
- if (errors) {
- ret = -ENODEV;
- goto out_free;
- }
-
- supported = *((u32 *)(out_obj->buffer.pointer + 4));
- if (!(supported & 0x1)) {
- ret = -ENODEV;
- goto out_free;
- }
-
-out_free:
- kfree(output.pointer);
- return ret;
-}
-
-static int __init pcc_cpufreq_probe(void)
-{
- acpi_status status;
- struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
- struct pcc_memory_resource *mem_resource;
- struct pcc_register_resource *reg_resource;
- union acpi_object *out_obj, *member;
- acpi_handle handle, osc_handle, pcch_handle;
- int ret = 0;
-
- status = acpi_get_handle(NULL, "\\_SB", &handle);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- status = acpi_get_handle(handle, "PCCH", &pcch_handle);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- status = acpi_get_handle(handle, "_OSC", &osc_handle);
- if (ACPI_SUCCESS(status)) {
- ret = pcc_cpufreq_do_osc(&osc_handle);
- if (ret)
- dprintk("probe: _OSC evaluation did not succeed\n");
- /* Firmware's use of _OSC is optional */
- ret = 0;
- }
-
- status = acpi_evaluate_object(handle, "PCCH", NULL, &output);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- out_obj = output.pointer;
- if (out_obj->type != ACPI_TYPE_PACKAGE) {
- ret = -ENODEV;
- goto out_free;
- }
-
- member = &out_obj->package.elements[0];
- if (member->type != ACPI_TYPE_BUFFER) {
- ret = -ENODEV;
- goto out_free;
- }
-
- mem_resource = (struct pcc_memory_resource *)member->buffer.pointer;
-
- dprintk("probe: mem_resource descriptor: 0x%x,"
- " length: %d, space_id: %d, resource_usage: %d,"
- " type_specific: %d, granularity: 0x%llx,"
- " minimum: 0x%llx, maximum: 0x%llx,"
- " translation_offset: 0x%llx, address_length: 0x%llx\n",
- mem_resource->descriptor, mem_resource->length,
- mem_resource->space_id, mem_resource->resource_usage,
- mem_resource->type_specific, mem_resource->granularity,
- mem_resource->minimum, mem_resource->maximum,
- mem_resource->translation_offset,
- mem_resource->address_length);
-
- if (mem_resource->space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY) {
- ret = -ENODEV;
- goto out_free;
- }
-
- pcch_virt_addr = ioremap_nocache(mem_resource->minimum,
- mem_resource->address_length);
- if (pcch_virt_addr == NULL) {
- dprintk("probe: could not map shared mem region\n");
- goto out_free;
- }
- pcch_hdr = pcch_virt_addr;
-
- dprintk("probe: PCCH header (virtual) addr: 0x%p\n", pcch_hdr);
- dprintk("probe: PCCH header is at physical address: 0x%llx,"
- " signature: 0x%x, length: %d bytes, major: %d, minor: %d,"
- " supported features: 0x%x, command field: 0x%x,"
- " status field: 0x%x, nominal latency: %d us\n",
- mem_resource->minimum, ioread32(&pcch_hdr->signature),
- ioread16(&pcch_hdr->length), ioread8(&pcch_hdr->major),
- ioread8(&pcch_hdr->minor), ioread32(&pcch_hdr->features),
- ioread16(&pcch_hdr->command), ioread16(&pcch_hdr->status),
- ioread32(&pcch_hdr->latency));
-
- dprintk("probe: min time between commands: %d us,"
- " max time between commands: %d us,"
- " nominal CPU frequency: %d MHz,"
- " minimum CPU frequency: %d MHz,"
- " minimum CPU frequency without throttling: %d MHz\n",
- ioread32(&pcch_hdr->minimum_time),
- ioread32(&pcch_hdr->maximum_time),
- ioread32(&pcch_hdr->nominal),
- ioread32(&pcch_hdr->throttled_frequency),
- ioread32(&pcch_hdr->minimum_frequency));
-
- member = &out_obj->package.elements[1];
- if (member->type != ACPI_TYPE_BUFFER) {
- ret = -ENODEV;
- goto pcch_free;
- }
-
- reg_resource = (struct pcc_register_resource *)member->buffer.pointer;
-
- doorbell.space_id = reg_resource->space_id;
- doorbell.bit_width = reg_resource->bit_width;
- doorbell.bit_offset = reg_resource->bit_offset;
- doorbell.access_width = 64;
- doorbell.address = reg_resource->address;
-
- dprintk("probe: doorbell: space_id is %d, bit_width is %d, "
- "bit_offset is %d, access_width is %d, address is 0x%llx\n",
- doorbell.space_id, doorbell.bit_width, doorbell.bit_offset,
- doorbell.access_width, reg_resource->address);
-
- member = &out_obj->package.elements[2];
- if (member->type != ACPI_TYPE_INTEGER) {
- ret = -ENODEV;
- goto pcch_free;
- }
-
- doorbell_preserve = member->integer.value;
-
- member = &out_obj->package.elements[3];
- if (member->type != ACPI_TYPE_INTEGER) {
- ret = -ENODEV;
- goto pcch_free;
- }
-
- doorbell_write = member->integer.value;
-
- dprintk("probe: doorbell_preserve: 0x%llx,"
- " doorbell_write: 0x%llx\n",
- doorbell_preserve, doorbell_write);
-
- pcc_cpu_info = alloc_percpu(struct pcc_cpu);
- if (!pcc_cpu_info) {
- ret = -ENOMEM;
- goto pcch_free;
- }
-
- printk(KERN_DEBUG "pcc-cpufreq: (v%s) driver loaded with frequency"
- " limits: %d MHz, %d MHz\n", PCC_VERSION,
- ioread32(&pcch_hdr->minimum_frequency),
- ioread32(&pcch_hdr->nominal));
- kfree(output.pointer);
- return ret;
-pcch_free:
- pcc_clear_mapping();
-out_free:
- kfree(output.pointer);
- return ret;
-}
-
-static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
-{
- unsigned int cpu = policy->cpu;
- unsigned int result = 0;
-
- if (!pcch_virt_addr) {
- result = -1;
- goto out;
- }
-
- result = pcc_get_offset(cpu);
- if (result) {
- dprintk("init: PCCP evaluation failed\n");
- goto out;
- }
-
- policy->max = policy->cpuinfo.max_freq =
- ioread32(&pcch_hdr->nominal) * 1000;
- policy->min = policy->cpuinfo.min_freq =
- ioread32(&pcch_hdr->minimum_frequency) * 1000;
- policy->cur = pcc_get_freq(cpu);
-
- if (!policy->cur) {
- dprintk("init: Unable to get current CPU frequency\n");
- result = -EINVAL;
- goto out;
- }
-
- dprintk("init: policy->max is %d, policy->min is %d\n",
- policy->max, policy->min);
-out:
- return result;
-}
-
-static int pcc_cpufreq_cpu_exit(struct cpufreq_policy *policy)
-{
- return 0;
-}
-
-static struct cpufreq_driver pcc_cpufreq_driver = {
- .flags = CPUFREQ_CONST_LOOPS,
- .get = pcc_get_freq,
- .verify = pcc_cpufreq_verify,
- .target = pcc_cpufreq_target,
- .init = pcc_cpufreq_cpu_init,
- .exit = pcc_cpufreq_cpu_exit,
- .name = "pcc-cpufreq",
- .owner = THIS_MODULE,
-};
-
-static int __init pcc_cpufreq_init(void)
-{
- int ret;
-
- if (acpi_disabled)
- return 0;
-
- ret = pcc_cpufreq_probe();
- if (ret) {
- dprintk("pcc_cpufreq_init: PCCH evaluation failed\n");
- return ret;
- }
-
- ret = cpufreq_register_driver(&pcc_cpufreq_driver);
-
- return ret;
-}
-
-static void __exit pcc_cpufreq_exit(void)
-{
- cpufreq_unregister_driver(&pcc_cpufreq_driver);
-
- pcc_clear_mapping();
-
- free_percpu(pcc_cpu_info);
-}
-
-MODULE_AUTHOR("Matthew Garrett, Naga Chumbalkar");
-MODULE_VERSION(PCC_VERSION);
-MODULE_DESCRIPTION("Processor Clocking Control interface driver");
-MODULE_LICENSE("GPL");
-
-late_initcall(pcc_cpufreq_init);
-module_exit(pcc_cpufreq_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
deleted file mode 100644
index b3379d6a5c5..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ /dev/null
@@ -1,261 +0,0 @@
-/*
- * This file was based upon code in Powertweak Linux (http://powertweak.sf.net)
- * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä,
- * Dominik Brodowski.
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/io.h>
-
-#include <asm/msr.h>
-
-#define POWERNOW_IOPORT 0xfff0 /* it doesn't matter where, as long
- as it is unused */
-
-#define PFX "powernow-k6: "
-static unsigned int busfreq; /* FSB, in 10 kHz */
-static unsigned int max_multiplier;
-
-
-/* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
-static struct cpufreq_frequency_table clock_ratio[] = {
- {45, /* 000 -> 4.5x */ 0},
- {50, /* 001 -> 5.0x */ 0},
- {40, /* 010 -> 4.0x */ 0},
- {55, /* 011 -> 5.5x */ 0},
- {20, /* 100 -> 2.0x */ 0},
- {30, /* 101 -> 3.0x */ 0},
- {60, /* 110 -> 6.0x */ 0},
- {35, /* 111 -> 3.5x */ 0},
- {0, CPUFREQ_TABLE_END}
-};
-
-
-/**
- * powernow_k6_get_cpu_multiplier - returns the current FSB multiplier
- *
- * Returns the current setting of the frequency multiplier. Core clock
- * speed is frequency of the Front-Side Bus multiplied with this value.
- */
-static int powernow_k6_get_cpu_multiplier(void)
-{
- u64 invalue = 0;
- u32 msrval;
-
- msrval = POWERNOW_IOPORT + 0x1;
- wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
- invalue = inl(POWERNOW_IOPORT + 0x8);
- msrval = POWERNOW_IOPORT + 0x0;
- wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
-
- return clock_ratio[(invalue >> 5)&7].index;
-}
-
-
-/**
- * powernow_k6_set_state - set the PowerNow! multiplier
- * @best_i: clock_ratio[best_i] is the target multiplier
- *
- * Tries to change the PowerNow! multiplier
- */
-static void powernow_k6_set_state(unsigned int best_i)
-{
- unsigned long outvalue = 0, invalue = 0;
- unsigned long msrval;
- struct cpufreq_freqs freqs;
-
- if (clock_ratio[best_i].index > max_multiplier) {
- printk(KERN_ERR PFX "invalid target frequency\n");
- return;
- }
-
- freqs.old = busfreq * powernow_k6_get_cpu_multiplier();
- freqs.new = busfreq * clock_ratio[best_i].index;
- freqs.cpu = 0; /* powernow-k6.c is UP only driver */
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- /* we now need to transform best_i to the BVC format, see AMD#23446 */
-
- outvalue = (1<<12) | (1<<10) | (1<<9) | (best_i<<5);
-
- msrval = POWERNOW_IOPORT + 0x1;
- wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
- invalue = inl(POWERNOW_IOPORT + 0x8);
- invalue = invalue & 0xf;
- outvalue = outvalue | invalue;
- outl(outvalue , (POWERNOW_IOPORT + 0x8));
- msrval = POWERNOW_IOPORT + 0x0;
- wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
- return;
-}
-
-
-/**
- * powernow_k6_verify - verifies a new CPUfreq policy
- * @policy: new policy
- *
- * Policy must be within lowest and highest possible CPU Frequency,
- * and at least one possible state must be within min and max.
- */
-static int powernow_k6_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, &clock_ratio[0]);
-}
-
-
-/**
- * powernow_k6_setpolicy - sets a new CPUFreq policy
- * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
- *
- * sets a new CPUFreq policy
- */
-static int powernow_k6_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate = 0;
-
- if (cpufreq_frequency_table_target(policy, &clock_ratio[0],
- target_freq, relation, &newstate))
- return -EINVAL;
-
- powernow_k6_set_state(newstate);
-
- return 0;
-}
-
-
-static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
-{
- unsigned int i, f;
- int result;
-
- if (policy->cpu != 0)
- return -ENODEV;
-
- /* get frequencies */
- max_multiplier = powernow_k6_get_cpu_multiplier();
- busfreq = cpu_khz / max_multiplier;
-
- /* table init */
- for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
- f = clock_ratio[i].index;
- if (f > max_multiplier)
- clock_ratio[i].frequency = CPUFREQ_ENTRY_INVALID;
- else
- clock_ratio[i].frequency = busfreq * f;
- }
-
- /* cpuinfo and default policy values */
- policy->cpuinfo.transition_latency = 200000;
- policy->cur = busfreq * max_multiplier;
-
- result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio);
- if (result)
- return result;
-
- cpufreq_frequency_table_get_attr(clock_ratio, policy->cpu);
-
- return 0;
-}
-
-
-static int powernow_k6_cpu_exit(struct cpufreq_policy *policy)
-{
- unsigned int i;
- for (i = 0; i < 8; i++) {
- if (i == max_multiplier)
- powernow_k6_set_state(i);
- }
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-static unsigned int powernow_k6_get(unsigned int cpu)
-{
- unsigned int ret;
- ret = (busfreq * powernow_k6_get_cpu_multiplier());
- return ret;
-}
-
-static struct freq_attr *powernow_k6_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver powernow_k6_driver = {
- .verify = powernow_k6_verify,
- .target = powernow_k6_target,
- .init = powernow_k6_cpu_init,
- .exit = powernow_k6_cpu_exit,
- .get = powernow_k6_get,
- .name = "powernow-k6",
- .owner = THIS_MODULE,
- .attr = powernow_k6_attr,
-};
-
-
-/**
- * powernow_k6_init - initializes the k6 PowerNow! CPUFreq driver
- *
- * Initializes the K6 PowerNow! support. Returns -ENODEV on unsupported
- * devices, -EINVAL or -ENOMEM on problems during initiatization, and zero
- * on success.
- */
-static int __init powernow_k6_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 != 5) ||
- ((c->x86_model != 12) && (c->x86_model != 13)))
- return -ENODEV;
-
- if (!request_region(POWERNOW_IOPORT, 16, "PowerNow!")) {
- printk(KERN_INFO PFX "PowerNow IOPORT region already used.\n");
- return -EIO;
- }
-
- if (cpufreq_register_driver(&powernow_k6_driver)) {
- release_region(POWERNOW_IOPORT, 16);
- return -EINVAL;
- }
-
- return 0;
-}
-
-
-/**
- * powernow_k6_exit - unregisters AMD K6-2+/3+ PowerNow! support
- *
- * Unregisters AMD K6-2+ / K6-3+ PowerNow! support.
- */
-static void __exit powernow_k6_exit(void)
-{
- cpufreq_unregister_driver(&powernow_k6_driver);
- release_region(POWERNOW_IOPORT, 16);
-}
-
-
-MODULE_AUTHOR("Arjan van de Ven, Dave Jones <davej@redhat.com>, "
- "Dominik Brodowski <linux@brodo.de>");
-MODULE_DESCRIPTION("PowerNow! driver for AMD K6-2+ / K6-3+ processors.");
-MODULE_LICENSE("GPL");
-
-module_init(powernow_k6_init);
-module_exit(powernow_k6_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
deleted file mode 100644
index 4a45fd6e41b..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ /dev/null
@@ -1,752 +0,0 @@
-/*
- * AMD K7 Powernow driver.
- * (C) 2003 Dave Jones on behalf of SuSE Labs.
- * (C) 2003-2004 Dave Jones <davej@redhat.com>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- * Based upon datasheets & sample CPUs kindly provided by AMD.
- *
- * Errata 5:
- * CPU may fail to execute a FID/VID change in presence of interrupt.
- * - We cli/sti on stepping A0 CPUs around the FID/VID transition.
- * Errata 15:
- * CPU with half frequency multipliers may hang upon wakeup from disconnect.
- * - We disable half multipliers if ACPI is used on A0 stepping CPUs.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/dmi.h>
-#include <linux/timex.h>
-#include <linux/io.h>
-
-#include <asm/timer.h> /* Needed for recalibrate_cpu_khz() */
-#include <asm/msr.h>
-#include <asm/system.h>
-
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
-#include <linux/acpi.h>
-#include <acpi/processor.h>
-#endif
-
-#include "powernow-k7.h"
-
-#define PFX "powernow: "
-
-
-struct psb_s {
- u8 signature[10];
- u8 tableversion;
- u8 flags;
- u16 settlingtime;
- u8 reserved1;
- u8 numpst;
-};
-
-struct pst_s {
- u32 cpuid;
- u8 fsbspeed;
- u8 maxfid;
- u8 startvid;
- u8 numpstates;
-};
-
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
-union powernow_acpi_control_t {
- struct {
- unsigned long fid:5,
- vid:5,
- sgtc:20,
- res1:2;
- } bits;
- unsigned long val;
-};
-#endif
-
-#ifdef CONFIG_CPU_FREQ_DEBUG
-/* divide by 1000 to get VCore voltage in V. */
-static const int mobile_vid_table[32] = {
- 2000, 1950, 1900, 1850, 1800, 1750, 1700, 1650,
- 1600, 1550, 1500, 1450, 1400, 1350, 1300, 0,
- 1275, 1250, 1225, 1200, 1175, 1150, 1125, 1100,
- 1075, 1050, 1025, 1000, 975, 950, 925, 0,
-};
-#endif
-
-/* divide by 10 to get FID. */
-static const int fid_codes[32] = {
- 110, 115, 120, 125, 50, 55, 60, 65,
- 70, 75, 80, 85, 90, 95, 100, 105,
- 30, 190, 40, 200, 130, 135, 140, 210,
- 150, 225, 160, 165, 170, 180, -1, -1,
-};
-
-/* This parameter is used in order to force ACPI instead of legacy method for
- * configuration purpose.
- */
-
-static int acpi_force;
-
-static struct cpufreq_frequency_table *powernow_table;
-
-static unsigned int can_scale_bus;
-static unsigned int can_scale_vid;
-static unsigned int minimum_speed = -1;
-static unsigned int maximum_speed;
-static unsigned int number_scales;
-static unsigned int fsb;
-static unsigned int latency;
-static char have_a0;
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "powernow-k7", msg)
-
-static int check_fsb(unsigned int fsbspeed)
-{
- int delta;
- unsigned int f = fsb / 1000;
-
- delta = (fsbspeed > f) ? fsbspeed - f : f - fsbspeed;
- return delta < 5;
-}
-
-static int check_powernow(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- unsigned int maxei, eax, ebx, ecx, edx;
-
- if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 != 6)) {
-#ifdef MODULE
- printk(KERN_INFO PFX "This module only works with "
- "AMD K7 CPUs\n");
-#endif
- return 0;
- }
-
- /* Get maximum capabilities */
- maxei = cpuid_eax(0x80000000);
- if (maxei < 0x80000007) { /* Any powernow info ? */
-#ifdef MODULE
- printk(KERN_INFO PFX "No powernow capabilities detected\n");
-#endif
- return 0;
- }
-
- if ((c->x86_model == 6) && (c->x86_mask == 0)) {
- printk(KERN_INFO PFX "K7 660[A0] core detected, "
- "enabling errata workarounds\n");
- have_a0 = 1;
- }
-
- cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
-
- /* Check we can actually do something before we say anything.*/
- if (!(edx & (1 << 1 | 1 << 2)))
- return 0;
-
- printk(KERN_INFO PFX "PowerNOW! Technology present. Can scale: ");
-
- if (edx & 1 << 1) {
- printk("frequency");
- can_scale_bus = 1;
- }
-
- if ((edx & (1 << 1 | 1 << 2)) == 0x6)
- printk(" and ");
-
- if (edx & 1 << 2) {
- printk("voltage");
- can_scale_vid = 1;
- }
-
- printk(".\n");
- return 1;
-}
-
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
-static void invalidate_entry(unsigned int entry)
-{
- powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
-}
-#endif
-
-static int get_ranges(unsigned char *pst)
-{
- unsigned int j;
- unsigned int speed;
- u8 fid, vid;
-
- powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) *
- (number_scales + 1)), GFP_KERNEL);
- if (!powernow_table)
- return -ENOMEM;
-
- for (j = 0 ; j < number_scales; j++) {
- fid = *pst++;
-
- powernow_table[j].frequency = (fsb * fid_codes[fid]) / 10;
- powernow_table[j].index = fid; /* lower 8 bits */
-
- speed = powernow_table[j].frequency;
-
- if ((fid_codes[fid] % 10) == 5) {
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
- if (have_a0 == 1)
- invalidate_entry(j);
-#endif
- }
-
- if (speed < minimum_speed)
- minimum_speed = speed;
- if (speed > maximum_speed)
- maximum_speed = speed;
-
- vid = *pst++;
- powernow_table[j].index |= (vid << 8); /* upper 8 bits */
-
- dprintk(" FID: 0x%x (%d.%dx [%dMHz]) "
- "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10,
- fid_codes[fid] % 10, speed/1000, vid,
- mobile_vid_table[vid]/1000,
- mobile_vid_table[vid]%1000);
- }
- powernow_table[number_scales].frequency = CPUFREQ_TABLE_END;
- powernow_table[number_scales].index = 0;
-
- return 0;
-}
-
-
-static void change_FID(int fid)
-{
- union msr_fidvidctl fidvidctl;
-
- rdmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val);
- if (fidvidctl.bits.FID != fid) {
- fidvidctl.bits.SGTC = latency;
- fidvidctl.bits.FID = fid;
- fidvidctl.bits.VIDC = 0;
- fidvidctl.bits.FIDC = 1;
- wrmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val);
- }
-}
-
-
-static void change_VID(int vid)
-{
- union msr_fidvidctl fidvidctl;
-
- rdmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val);
- if (fidvidctl.bits.VID != vid) {
- fidvidctl.bits.SGTC = latency;
- fidvidctl.bits.VID = vid;
- fidvidctl.bits.FIDC = 0;
- fidvidctl.bits.VIDC = 1;
- wrmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val);
- }
-}
-
-
-static void change_speed(unsigned int index)
-{
- u8 fid, vid;
- struct cpufreq_freqs freqs;
- union msr_fidvidstatus fidvidstatus;
- int cfid;
-
- /* fid are the lower 8 bits of the index we stored into
- * the cpufreq frequency table in powernow_decode_bios,
- * vid are the upper 8 bits.
- */
-
- fid = powernow_table[index].index & 0xFF;
- vid = (powernow_table[index].index & 0xFF00) >> 8;
-
- freqs.cpu = 0;
-
- rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val);
- cfid = fidvidstatus.bits.CFID;
- freqs.old = fsb * fid_codes[cfid] / 10;
-
- freqs.new = powernow_table[index].frequency;
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- /* Now do the magic poking into the MSRs. */
-
- if (have_a0 == 1) /* A0 errata 5 */
- local_irq_disable();
-
- if (freqs.old > freqs.new) {
- /* Going down, so change FID first */
- change_FID(fid);
- change_VID(vid);
- } else {
- /* Going up, so change VID first */
- change_VID(vid);
- change_FID(fid);
- }
-
-
- if (have_a0 == 1)
- local_irq_enable();
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-}
-
-
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
-
-static struct acpi_processor_performance *acpi_processor_perf;
-
-static int powernow_acpi_init(void)
-{
- int i;
- int retval = 0;
- union powernow_acpi_control_t pc;
-
- if (acpi_processor_perf != NULL && powernow_table != NULL) {
- retval = -EINVAL;
- goto err0;
- }
-
- acpi_processor_perf = kzalloc(sizeof(struct acpi_processor_performance),
- GFP_KERNEL);
- if (!acpi_processor_perf) {
- retval = -ENOMEM;
- goto err0;
- }
-
- if (!zalloc_cpumask_var(&acpi_processor_perf->shared_cpu_map,
- GFP_KERNEL)) {
- retval = -ENOMEM;
- goto err05;
- }
-
- if (acpi_processor_register_performance(acpi_processor_perf, 0)) {
- retval = -EIO;
- goto err1;
- }
-
- if (acpi_processor_perf->control_register.space_id !=
- ACPI_ADR_SPACE_FIXED_HARDWARE) {
- retval = -ENODEV;
- goto err2;
- }
-
- if (acpi_processor_perf->status_register.space_id !=
- ACPI_ADR_SPACE_FIXED_HARDWARE) {
- retval = -ENODEV;
- goto err2;
- }
-
- number_scales = acpi_processor_perf->state_count;
-
- if (number_scales < 2) {
- retval = -ENODEV;
- goto err2;
- }
-
- powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) *
- (number_scales + 1)), GFP_KERNEL);
- if (!powernow_table) {
- retval = -ENOMEM;
- goto err2;
- }
-
- pc.val = (unsigned long) acpi_processor_perf->states[0].control;
- for (i = 0; i < number_scales; i++) {
- u8 fid, vid;
- struct acpi_processor_px *state =
- &acpi_processor_perf->states[i];
- unsigned int speed, speed_mhz;
-
- pc.val = (unsigned long) state->control;
- dprintk("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n",
- i,
- (u32) state->core_frequency,
- (u32) state->power,
- (u32) state->transition_latency,
- (u32) state->control,
- pc.bits.sgtc);
-
- vid = pc.bits.vid;
- fid = pc.bits.fid;
-
- powernow_table[i].frequency = fsb * fid_codes[fid] / 10;
- powernow_table[i].index = fid; /* lower 8 bits */
- powernow_table[i].index |= (vid << 8); /* upper 8 bits */
-
- speed = powernow_table[i].frequency;
- speed_mhz = speed / 1000;
-
- /* processor_perflib will multiply the MHz value by 1000 to
- * get a KHz value (e.g. 1266000). However, powernow-k7 works
- * with true KHz values (e.g. 1266768). To ensure that all
- * powernow frequencies are available, we must ensure that
- * ACPI doesn't restrict them, so we round up the MHz value
- * to ensure that perflib's computed KHz value is greater than
- * or equal to powernow's KHz value.
- */
- if (speed % 1000 > 0)
- speed_mhz++;
-
- if ((fid_codes[fid] % 10) == 5) {
- if (have_a0 == 1)
- invalidate_entry(i);
- }
-
- dprintk(" FID: 0x%x (%d.%dx [%dMHz]) "
- "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10,
- fid_codes[fid] % 10, speed_mhz, vid,
- mobile_vid_table[vid]/1000,
- mobile_vid_table[vid]%1000);
-
- if (state->core_frequency != speed_mhz) {
- state->core_frequency = speed_mhz;
- dprintk(" Corrected ACPI frequency to %d\n",
- speed_mhz);
- }
-
- if (latency < pc.bits.sgtc)
- latency = pc.bits.sgtc;
-
- if (speed < minimum_speed)
- minimum_speed = speed;
- if (speed > maximum_speed)
- maximum_speed = speed;
- }
-
- powernow_table[i].frequency = CPUFREQ_TABLE_END;
- powernow_table[i].index = 0;
-
- /* notify BIOS that we exist */
- acpi_processor_notify_smm(THIS_MODULE);
-
- return 0;
-
-err2:
- acpi_processor_unregister_performance(acpi_processor_perf, 0);
-err1:
- free_cpumask_var(acpi_processor_perf->shared_cpu_map);
-err05:
- kfree(acpi_processor_perf);
-err0:
- printk(KERN_WARNING PFX "ACPI perflib can not be used on "
- "this platform\n");
- acpi_processor_perf = NULL;
- return retval;
-}
-#else
-static int powernow_acpi_init(void)
-{
- printk(KERN_INFO PFX "no support for ACPI processor found."
- " Please recompile your kernel with ACPI processor\n");
- return -EINVAL;
-}
-#endif
-
-static void print_pst_entry(struct pst_s *pst, unsigned int j)
-{
- dprintk("PST:%d (@%p)\n", j, pst);
- dprintk(" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n",
- pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid);
-}
-
-static int powernow_decode_bios(int maxfid, int startvid)
-{
- struct psb_s *psb;
- struct pst_s *pst;
- unsigned int i, j;
- unsigned char *p;
- unsigned int etuple;
- unsigned int ret;
-
- etuple = cpuid_eax(0x80000001);
-
- for (i = 0xC0000; i < 0xffff0 ; i += 16) {
-
- p = phys_to_virt(i);
-
- if (memcmp(p, "AMDK7PNOW!", 10) == 0) {
- dprintk("Found PSB header at %p\n", p);
- psb = (struct psb_s *) p;
- dprintk("Table version: 0x%x\n", psb->tableversion);
- if (psb->tableversion != 0x12) {
- printk(KERN_INFO PFX "Sorry, only v1.2 tables"
- " supported right now\n");
- return -ENODEV;
- }
-
- dprintk("Flags: 0x%x\n", psb->flags);
- if ((psb->flags & 1) == 0)
- dprintk("Mobile voltage regulator\n");
- else
- dprintk("Desktop voltage regulator\n");
-
- latency = psb->settlingtime;
- if (latency < 100) {
- printk(KERN_INFO PFX "BIOS set settling time "
- "to %d microseconds. "
- "Should be at least 100. "
- "Correcting.\n", latency);
- latency = 100;
- }
- dprintk("Settling Time: %d microseconds.\n",
- psb->settlingtime);
- dprintk("Has %d PST tables. (Only dumping ones "
- "relevant to this CPU).\n",
- psb->numpst);
-
- p += sizeof(struct psb_s);
-
- pst = (struct pst_s *) p;
-
- for (j = 0; j < psb->numpst; j++) {
- pst = (struct pst_s *) p;
- number_scales = pst->numpstates;
-
- if ((etuple == pst->cpuid) &&
- check_fsb(pst->fsbspeed) &&
- (maxfid == pst->maxfid) &&
- (startvid == pst->startvid)) {
- print_pst_entry(pst, j);
- p = (char *)pst + sizeof(struct pst_s);
- ret = get_ranges(p);
- return ret;
- } else {
- unsigned int k;
- p = (char *)pst + sizeof(struct pst_s);
- for (k = 0; k < number_scales; k++)
- p += 2;
- }
- }
- printk(KERN_INFO PFX "No PST tables match this cpuid "
- "(0x%x)\n", etuple);
- printk(KERN_INFO PFX "This is indicative of a broken "
- "BIOS.\n");
-
- return -EINVAL;
- }
- p++;
- }
-
- return -ENODEV;
-}
-
-
-static int powernow_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate;
-
- if (cpufreq_frequency_table_target(policy, powernow_table, target_freq,
- relation, &newstate))
- return -EINVAL;
-
- change_speed(newstate);
-
- return 0;
-}
-
-
-static int powernow_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, powernow_table);
-}
-
-/*
- * We use the fact that the bus frequency is somehow
- * a multiple of 100000/3 khz, then we compute sgtc according
- * to this multiple.
- * That way, we match more how AMD thinks all of that work.
- * We will then get the same kind of behaviour already tested under
- * the "well-known" other OS.
- */
-static int __cpuinit fixup_sgtc(void)
-{
- unsigned int sgtc;
- unsigned int m;
-
- m = fsb / 3333;
- if ((m % 10) >= 5)
- m += 5;
-
- m /= 10;
-
- sgtc = 100 * m * latency;
- sgtc = sgtc / 3;
- if (sgtc > 0xfffff) {
- printk(KERN_WARNING PFX "SGTC too large %d\n", sgtc);
- sgtc = 0xfffff;
- }
- return sgtc;
-}
-
-static unsigned int powernow_get(unsigned int cpu)
-{
- union msr_fidvidstatus fidvidstatus;
- unsigned int cfid;
-
- if (cpu)
- return 0;
- rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val);
- cfid = fidvidstatus.bits.CFID;
-
- return fsb * fid_codes[cfid] / 10;
-}
-
-
-static int __cpuinit acer_cpufreq_pst(const struct dmi_system_id *d)
-{
- printk(KERN_WARNING PFX
- "%s laptop with broken PST tables in BIOS detected.\n",
- d->ident);
- printk(KERN_WARNING PFX
- "You need to downgrade to 3A21 (09/09/2002), or try a newer "
- "BIOS than 3A71 (01/20/2003)\n");
- printk(KERN_WARNING PFX
- "cpufreq scaling has been disabled as a result of this.\n");
- return 0;
-}
-
-/*
- * Some Athlon laptops have really fucked PST tables.
- * A BIOS update is all that can save them.
- * Mention this, and disable cpufreq.
- */
-static struct dmi_system_id __cpuinitdata powernow_dmi_table[] = {
- {
- .callback = acer_cpufreq_pst,
- .ident = "Acer Aspire",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Insyde Software"),
- DMI_MATCH(DMI_BIOS_VERSION, "3A71"),
- },
- },
- { }
-};
-
-static int __cpuinit powernow_cpu_init(struct cpufreq_policy *policy)
-{
- union msr_fidvidstatus fidvidstatus;
- int result;
-
- if (policy->cpu != 0)
- return -ENODEV;
-
- rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val);
-
- recalibrate_cpu_khz();
-
- fsb = (10 * cpu_khz) / fid_codes[fidvidstatus.bits.CFID];
- if (!fsb) {
- printk(KERN_WARNING PFX "can not determine bus frequency\n");
- return -EINVAL;
- }
- dprintk("FSB: %3dMHz\n", fsb/1000);
-
- if (dmi_check_system(powernow_dmi_table) || acpi_force) {
- printk(KERN_INFO PFX "PSB/PST known to be broken. "
- "Trying ACPI instead\n");
- result = powernow_acpi_init();
- } else {
- result = powernow_decode_bios(fidvidstatus.bits.MFID,
- fidvidstatus.bits.SVID);
- if (result) {
- printk(KERN_INFO PFX "Trying ACPI perflib\n");
- maximum_speed = 0;
- minimum_speed = -1;
- latency = 0;
- result = powernow_acpi_init();
- if (result) {
- printk(KERN_INFO PFX
- "ACPI and legacy methods failed\n");
- }
- } else {
- /* SGTC use the bus clock as timer */
- latency = fixup_sgtc();
- printk(KERN_INFO PFX "SGTC: %d\n", latency);
- }
- }
-
- if (result)
- return result;
-
- printk(KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n",
- minimum_speed/1000, maximum_speed/1000);
-
- policy->cpuinfo.transition_latency =
- cpufreq_scale(2000000UL, fsb, latency);
-
- policy->cur = powernow_get(0);
-
- cpufreq_frequency_table_get_attr(powernow_table, policy->cpu);
-
- return cpufreq_frequency_table_cpuinfo(policy, powernow_table);
-}
-
-static int powernow_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
-
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
- if (acpi_processor_perf) {
- acpi_processor_unregister_performance(acpi_processor_perf, 0);
- free_cpumask_var(acpi_processor_perf->shared_cpu_map);
- kfree(acpi_processor_perf);
- }
-#endif
-
- kfree(powernow_table);
- return 0;
-}
-
-static struct freq_attr *powernow_table_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver powernow_driver = {
- .verify = powernow_verify,
- .target = powernow_target,
- .get = powernow_get,
-#ifdef CONFIG_X86_POWERNOW_K7_ACPI
- .bios_limit = acpi_processor_get_bios_limit,
-#endif
- .init = powernow_cpu_init,
- .exit = powernow_cpu_exit,
- .name = "powernow-k7",
- .owner = THIS_MODULE,
- .attr = powernow_table_attr,
-};
-
-static int __init powernow_init(void)
-{
- if (check_powernow() == 0)
- return -ENODEV;
- return cpufreq_register_driver(&powernow_driver);
-}
-
-
-static void __exit powernow_exit(void)
-{
- cpufreq_unregister_driver(&powernow_driver);
-}
-
-module_param(acpi_force, int, 0444);
-MODULE_PARM_DESC(acpi_force, "Force ACPI to be used.");
-
-MODULE_AUTHOR("Dave Jones <davej@redhat.com>");
-MODULE_DESCRIPTION("Powernow driver for AMD K7 processors.");
-MODULE_LICENSE("GPL");
-
-late_initcall(powernow_init);
-module_exit(powernow_exit);
-
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.h b/arch/x86/kernel/cpu/cpufreq/powernow-k7.h
deleted file mode 100644
index 35fb4eaf6e1..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * (C) 2003 Dave Jones.
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * AMD-specific information
- *
- */
-
-union msr_fidvidctl {
- struct {
- unsigned FID:5, // 4:0
- reserved1:3, // 7:5
- VID:5, // 12:8
- reserved2:3, // 15:13
- FIDC:1, // 16
- VIDC:1, // 17
- reserved3:2, // 19:18
- FIDCHGRATIO:1, // 20
- reserved4:11, // 31-21
- SGTC:20, // 32:51
- reserved5:12; // 63:52
- } bits;
- unsigned long long val;
-};
-
-union msr_fidvidstatus {
- struct {
- unsigned CFID:5, // 4:0
- reserved1:3, // 7:5
- SFID:5, // 12:8
- reserved2:3, // 15:13
- MFID:5, // 20:16
- reserved3:11, // 31:21
- CVID:5, // 36:32
- reserved4:3, // 39:37
- SVID:5, // 44:40
- reserved5:3, // 47:45
- MVID:5, // 52:48
- reserved6:11; // 63:53
- } bits;
- unsigned long long val;
-};
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
deleted file mode 100644
index 35c7e65e59b..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ /dev/null
@@ -1,1601 +0,0 @@
-/*
- * (c) 2003-2010 Advanced Micro Devices, Inc.
- * Your use of this code is subject to the terms and conditions of the
- * GNU general public license version 2. See "COPYING" or
- * http://www.gnu.org/licenses/gpl.html
- *
- * Support : mark.langsdorf@amd.com
- *
- * Based on the powernow-k7.c module written by Dave Jones.
- * (C) 2003 Dave Jones on behalf of SuSE Labs
- * (C) 2004 Dominik Brodowski <linux@brodo.de>
- * (C) 2004 Pavel Machek <pavel@ucw.cz>
- * Licensed under the terms of the GNU GPL License version 2.
- * Based upon datasheets & sample CPUs kindly provided by AMD.
- *
- * Valuable input gratefully received from Dave Jones, Pavel Machek,
- * Dominik Brodowski, Jacob Shin, and others.
- * Originally developed by Paul Devriendt.
- * Processor information obtained from Chapter 9 (Power and Thermal Management)
- * of the "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD
- * Opteron Processors" available for download from www.amd.com
- *
- * Tables for specific CPUs can be inferred from
- * http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/30430.pdf
- */
-
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/cpumask.h>
-#include <linux/sched.h> /* for current / set_cpus_allowed() */
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/msr.h>
-
-#include <linux/acpi.h>
-#include <linux/mutex.h>
-#include <acpi/processor.h>
-
-#define PFX "powernow-k8: "
-#define VERSION "version 2.20.00"
-#include "powernow-k8.h"
-#include "mperf.h"
-
-/* serialize freq changes */
-static DEFINE_MUTEX(fidvid_mutex);
-
-static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
-
-static int cpu_family = CPU_OPTERON;
-
-/* core performance boost */
-static bool cpb_capable, cpb_enabled;
-static struct msr __percpu *msrs;
-
-static struct cpufreq_driver cpufreq_amd64_driver;
-
-#ifndef CONFIG_SMP
-static inline const struct cpumask *cpu_core_mask(int cpu)
-{
- return cpumask_of(0);
-}
-#endif
-
-/* Return a frequency in MHz, given an input fid */
-static u32 find_freq_from_fid(u32 fid)
-{
- return 800 + (fid * 100);
-}
-
-/* Return a frequency in KHz, given an input fid */
-static u32 find_khz_freq_from_fid(u32 fid)
-{
- return 1000 * find_freq_from_fid(fid);
-}
-
-static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data,
- u32 pstate)
-{
- return data[pstate].frequency;
-}
-
-/* Return the vco fid for an input fid
- *
- * Each "low" fid has corresponding "high" fid, and you can get to "low" fids
- * only from corresponding high fids. This returns "high" fid corresponding to
- * "low" one.
- */
-static u32 convert_fid_to_vco_fid(u32 fid)
-{
- if (fid < HI_FID_TABLE_BOTTOM)
- return 8 + (2 * fid);
- else
- return fid;
-}
-
-/*
- * Return 1 if the pending bit is set. Unless we just instructed the processor
- * to transition to a new state, seeing this bit set is really bad news.
- */
-static int pending_bit_stuck(void)
-{
- u32 lo, hi;
-
- if (cpu_family == CPU_HW_PSTATE)
- return 0;
-
- rdmsr(MSR_FIDVID_STATUS, lo, hi);
- return lo & MSR_S_LO_CHANGE_PENDING ? 1 : 0;
-}
-
-/*
- * Update the global current fid / vid values from the status msr.
- * Returns 1 on error.
- */
-static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
-{
- u32 lo, hi;
- u32 i = 0;
-
- if (cpu_family == CPU_HW_PSTATE) {
- rdmsr(MSR_PSTATE_STATUS, lo, hi);
- i = lo & HW_PSTATE_MASK;
- data->currpstate = i;
-
- /*
- * a workaround for family 11h erratum 311 might cause
- * an "out-of-range Pstate if the core is in Pstate-0
- */
- if ((boot_cpu_data.x86 == 0x11) && (i >= data->numps))
- data->currpstate = HW_PSTATE_0;
-
- return 0;
- }
- do {
- if (i++ > 10000) {
- dprintk("detected change pending stuck\n");
- return 1;
- }
- rdmsr(MSR_FIDVID_STATUS, lo, hi);
- } while (lo & MSR_S_LO_CHANGE_PENDING);
-
- data->currvid = hi & MSR_S_HI_CURRENT_VID;
- data->currfid = lo & MSR_S_LO_CURRENT_FID;
-
- return 0;
-}
-
-/* the isochronous relief time */
-static void count_off_irt(struct powernow_k8_data *data)
-{
- udelay((1 << data->irt) * 10);
- return;
-}
-
-/* the voltage stabilization time */
-static void count_off_vst(struct powernow_k8_data *data)
-{
- udelay(data->vstable * VST_UNITS_20US);
- return;
-}
-
-/* need to init the control msr to a safe value (for each cpu) */
-static void fidvid_msr_init(void)
-{
- u32 lo, hi;
- u8 fid, vid;
-
- rdmsr(MSR_FIDVID_STATUS, lo, hi);
- vid = hi & MSR_S_HI_CURRENT_VID;
- fid = lo & MSR_S_LO_CURRENT_FID;
- lo = fid | (vid << MSR_C_LO_VID_SHIFT);
- hi = MSR_C_HI_STP_GNT_BENIGN;
- dprintk("cpu%d, init lo 0x%x, hi 0x%x\n", smp_processor_id(), lo, hi);
- wrmsr(MSR_FIDVID_CTL, lo, hi);
-}
-
-/* write the new fid value along with the other control fields to the msr */
-static int write_new_fid(struct powernow_k8_data *data, u32 fid)
-{
- u32 lo;
- u32 savevid = data->currvid;
- u32 i = 0;
-
- if ((fid & INVALID_FID_MASK) || (data->currvid & INVALID_VID_MASK)) {
- printk(KERN_ERR PFX "internal error - overflow on fid write\n");
- return 1;
- }
-
- lo = fid;
- lo |= (data->currvid << MSR_C_LO_VID_SHIFT);
- lo |= MSR_C_LO_INIT_FID_VID;
-
- dprintk("writing fid 0x%x, lo 0x%x, hi 0x%x\n",
- fid, lo, data->plllock * PLL_LOCK_CONVERSION);
-
- do {
- wrmsr(MSR_FIDVID_CTL, lo, data->plllock * PLL_LOCK_CONVERSION);
- if (i++ > 100) {
- printk(KERN_ERR PFX
- "Hardware error - pending bit very stuck - "
- "no further pstate changes possible\n");
- return 1;
- }
- } while (query_current_values_with_pending_wait(data));
-
- count_off_irt(data);
-
- if (savevid != data->currvid) {
- printk(KERN_ERR PFX
- "vid change on fid trans, old 0x%x, new 0x%x\n",
- savevid, data->currvid);
- return 1;
- }
-
- if (fid != data->currfid) {
- printk(KERN_ERR PFX
- "fid trans failed, fid 0x%x, curr 0x%x\n", fid,
- data->currfid);
- return 1;
- }
-
- return 0;
-}
-
-/* Write a new vid to the hardware */
-static int write_new_vid(struct powernow_k8_data *data, u32 vid)
-{
- u32 lo;
- u32 savefid = data->currfid;
- int i = 0;
-
- if ((data->currfid & INVALID_FID_MASK) || (vid & INVALID_VID_MASK)) {
- printk(KERN_ERR PFX "internal error - overflow on vid write\n");
- return 1;
- }
-
- lo = data->currfid;
- lo |= (vid << MSR_C_LO_VID_SHIFT);
- lo |= MSR_C_LO_INIT_FID_VID;
-
- dprintk("writing vid 0x%x, lo 0x%x, hi 0x%x\n",
- vid, lo, STOP_GRANT_5NS);
-
- do {
- wrmsr(MSR_FIDVID_CTL, lo, STOP_GRANT_5NS);
- if (i++ > 100) {
- printk(KERN_ERR PFX "internal error - pending bit "
- "very stuck - no further pstate "
- "changes possible\n");
- return 1;
- }
- } while (query_current_values_with_pending_wait(data));
-
- if (savefid != data->currfid) {
- printk(KERN_ERR PFX "fid changed on vid trans, old "
- "0x%x new 0x%x\n",
- savefid, data->currfid);
- return 1;
- }
-
- if (vid != data->currvid) {
- printk(KERN_ERR PFX "vid trans failed, vid 0x%x, "
- "curr 0x%x\n",
- vid, data->currvid);
- return 1;
- }
-
- return 0;
-}
-
-/*
- * Reduce the vid by the max of step or reqvid.
- * Decreasing vid codes represent increasing voltages:
- * vid of 0 is 1.550V, vid of 0x1e is 0.800V, vid of VID_OFF is off.
- */
-static int decrease_vid_code_by_step(struct powernow_k8_data *data,
- u32 reqvid, u32 step)
-{
- if ((data->currvid - reqvid) > step)
- reqvid = data->currvid - step;
-
- if (write_new_vid(data, reqvid))
- return 1;
-
- count_off_vst(data);
-
- return 0;
-}
-
-/* Change hardware pstate by single MSR write */
-static int transition_pstate(struct powernow_k8_data *data, u32 pstate)
-{
- wrmsr(MSR_PSTATE_CTRL, pstate, 0);
- data->currpstate = pstate;
- return 0;
-}
-
-/* Change Opteron/Athlon64 fid and vid, by the 3 phases. */
-static int transition_fid_vid(struct powernow_k8_data *data,
- u32 reqfid, u32 reqvid)
-{
- if (core_voltage_pre_transition(data, reqvid, reqfid))
- return 1;
-
- if (core_frequency_transition(data, reqfid))
- return 1;
-
- if (core_voltage_post_transition(data, reqvid))
- return 1;
-
- if (query_current_values_with_pending_wait(data))
- return 1;
-
- if ((reqfid != data->currfid) || (reqvid != data->currvid)) {
- printk(KERN_ERR PFX "failed (cpu%d): req 0x%x 0x%x, "
- "curr 0x%x 0x%x\n",
- smp_processor_id(),
- reqfid, reqvid, data->currfid, data->currvid);
- return 1;
- }
-
- dprintk("transitioned (cpu%d): new fid 0x%x, vid 0x%x\n",
- smp_processor_id(), data->currfid, data->currvid);
-
- return 0;
-}
-
-/* Phase 1 - core voltage transition ... setup voltage */
-static int core_voltage_pre_transition(struct powernow_k8_data *data,
- u32 reqvid, u32 reqfid)
-{
- u32 rvosteps = data->rvo;
- u32 savefid = data->currfid;
- u32 maxvid, lo, rvomult = 1;
-
- dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, "
- "reqvid 0x%x, rvo 0x%x\n",
- smp_processor_id(),
- data->currfid, data->currvid, reqvid, data->rvo);
-
- if ((savefid < LO_FID_TABLE_TOP) && (reqfid < LO_FID_TABLE_TOP))
- rvomult = 2;
- rvosteps *= rvomult;
- rdmsr(MSR_FIDVID_STATUS, lo, maxvid);
- maxvid = 0x1f & (maxvid >> 16);
- dprintk("ph1 maxvid=0x%x\n", maxvid);
- if (reqvid < maxvid) /* lower numbers are higher voltages */
- reqvid = maxvid;
-
- while (data->currvid > reqvid) {
- dprintk("ph1: curr 0x%x, req vid 0x%x\n",
- data->currvid, reqvid);
- if (decrease_vid_code_by_step(data, reqvid, data->vidmvs))
- return 1;
- }
-
- while ((rvosteps > 0) &&
- ((rvomult * data->rvo + data->currvid) > reqvid)) {
- if (data->currvid == maxvid) {
- rvosteps = 0;
- } else {
- dprintk("ph1: changing vid for rvo, req 0x%x\n",
- data->currvid - 1);
- if (decrease_vid_code_by_step(data, data->currvid-1, 1))
- return 1;
- rvosteps--;
- }
- }
-
- if (query_current_values_with_pending_wait(data))
- return 1;
-
- if (savefid != data->currfid) {
- printk(KERN_ERR PFX "ph1 err, currfid changed 0x%x\n",
- data->currfid);
- return 1;
- }
-
- dprintk("ph1 complete, currfid 0x%x, currvid 0x%x\n",
- data->currfid, data->currvid);
-
- return 0;
-}
-
-/* Phase 2 - core frequency transition */
-static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
-{
- u32 vcoreqfid, vcocurrfid, vcofiddiff;
- u32 fid_interval, savevid = data->currvid;
-
- if (data->currfid == reqfid) {
- printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n",
- data->currfid);
- return 0;
- }
-
- dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, "
- "reqfid 0x%x\n",
- smp_processor_id(),
- data->currfid, data->currvid, reqfid);
-
- vcoreqfid = convert_fid_to_vco_fid(reqfid);
- vcocurrfid = convert_fid_to_vco_fid(data->currfid);
- vcofiddiff = vcocurrfid > vcoreqfid ? vcocurrfid - vcoreqfid
- : vcoreqfid - vcocurrfid;
-
- if ((reqfid <= LO_FID_TABLE_TOP) && (data->currfid <= LO_FID_TABLE_TOP))
- vcofiddiff = 0;
-
- while (vcofiddiff > 2) {
- (data->currfid & 1) ? (fid_interval = 1) : (fid_interval = 2);
-
- if (reqfid > data->currfid) {
- if (data->currfid > LO_FID_TABLE_TOP) {
- if (write_new_fid(data,
- data->currfid + fid_interval))
- return 1;
- } else {
- if (write_new_fid
- (data,
- 2 + convert_fid_to_vco_fid(data->currfid)))
- return 1;
- }
- } else {
- if (write_new_fid(data, data->currfid - fid_interval))
- return 1;
- }
-
- vcocurrfid = convert_fid_to_vco_fid(data->currfid);
- vcofiddiff = vcocurrfid > vcoreqfid ? vcocurrfid - vcoreqfid
- : vcoreqfid - vcocurrfid;
- }
-
- if (write_new_fid(data, reqfid))
- return 1;
-
- if (query_current_values_with_pending_wait(data))
- return 1;
-
- if (data->currfid != reqfid) {
- printk(KERN_ERR PFX
- "ph2: mismatch, failed fid transition, "
- "curr 0x%x, req 0x%x\n",
- data->currfid, reqfid);
- return 1;
- }
-
- if (savevid != data->currvid) {
- printk(KERN_ERR PFX "ph2: vid changed, save 0x%x, curr 0x%x\n",
- savevid, data->currvid);
- return 1;
- }
-
- dprintk("ph2 complete, currfid 0x%x, currvid 0x%x\n",
- data->currfid, data->currvid);
-
- return 0;
-}
-
-/* Phase 3 - core voltage transition flow ... jump to the final vid. */
-static int core_voltage_post_transition(struct powernow_k8_data *data,
- u32 reqvid)
-{
- u32 savefid = data->currfid;
- u32 savereqvid = reqvid;
-
- dprintk("ph3 (cpu%d): starting, currfid 0x%x, currvid 0x%x\n",
- smp_processor_id(),
- data->currfid, data->currvid);
-
- if (reqvid != data->currvid) {
- if (write_new_vid(data, reqvid))
- return 1;
-
- if (savefid != data->currfid) {
- printk(KERN_ERR PFX
- "ph3: bad fid change, save 0x%x, curr 0x%x\n",
- savefid, data->currfid);
- return 1;
- }
-
- if (data->currvid != reqvid) {
- printk(KERN_ERR PFX
- "ph3: failed vid transition\n, "
- "req 0x%x, curr 0x%x",
- reqvid, data->currvid);
- return 1;
- }
- }
-
- if (query_current_values_with_pending_wait(data))
- return 1;
-
- if (savereqvid != data->currvid) {
- dprintk("ph3 failed, currvid 0x%x\n", data->currvid);
- return 1;
- }
-
- if (savefid != data->currfid) {
- dprintk("ph3 failed, currfid changed 0x%x\n",
- data->currfid);
- return 1;
- }
-
- dprintk("ph3 complete, currfid 0x%x, currvid 0x%x\n",
- data->currfid, data->currvid);
-
- return 0;
-}
-
-static void check_supported_cpu(void *_rc)
-{
- u32 eax, ebx, ecx, edx;
- int *rc = _rc;
-
- *rc = -ENODEV;
-
- if (__this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_AMD)
- return;
-
- eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
- if (((eax & CPUID_XFAM) != CPUID_XFAM_K8) &&
- ((eax & CPUID_XFAM) < CPUID_XFAM_10H))
- return;
-
- if ((eax & CPUID_XFAM) == CPUID_XFAM_K8) {
- if (((eax & CPUID_USE_XFAM_XMOD) != CPUID_USE_XFAM_XMOD) ||
- ((eax & CPUID_XMOD) > CPUID_XMOD_REV_MASK)) {
- printk(KERN_INFO PFX
- "Processor cpuid %x not supported\n", eax);
- return;
- }
-
- eax = cpuid_eax(CPUID_GET_MAX_CAPABILITIES);
- if (eax < CPUID_FREQ_VOLT_CAPABILITIES) {
- printk(KERN_INFO PFX
- "No frequency change capabilities detected\n");
- return;
- }
-
- cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
- if ((edx & P_STATE_TRANSITION_CAPABLE)
- != P_STATE_TRANSITION_CAPABLE) {
- printk(KERN_INFO PFX
- "Power state transitions not supported\n");
- return;
- }
- } else { /* must be a HW Pstate capable processor */
- cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
- if ((edx & USE_HW_PSTATE) == USE_HW_PSTATE)
- cpu_family = CPU_HW_PSTATE;
- else
- return;
- }
-
- *rc = 0;
-}
-
-static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst,
- u8 maxvid)
-{
- unsigned int j;
- u8 lastfid = 0xff;
-
- for (j = 0; j < data->numps; j++) {
- if (pst[j].vid > LEAST_VID) {
- printk(KERN_ERR FW_BUG PFX "vid %d invalid : 0x%x\n",
- j, pst[j].vid);
- return -EINVAL;
- }
- if (pst[j].vid < data->rvo) {
- /* vid + rvo >= 0 */
- printk(KERN_ERR FW_BUG PFX "0 vid exceeded with pstate"
- " %d\n", j);
- return -ENODEV;
- }
- if (pst[j].vid < maxvid + data->rvo) {
- /* vid + rvo >= maxvid */
- printk(KERN_ERR FW_BUG PFX "maxvid exceeded with pstate"
- " %d\n", j);
- return -ENODEV;
- }
- if (pst[j].fid > MAX_FID) {
- printk(KERN_ERR FW_BUG PFX "maxfid exceeded with pstate"
- " %d\n", j);
- return -ENODEV;
- }
- if (j && (pst[j].fid < HI_FID_TABLE_BOTTOM)) {
- /* Only first fid is allowed to be in "low" range */
- printk(KERN_ERR FW_BUG PFX "two low fids - %d : "
- "0x%x\n", j, pst[j].fid);
- return -EINVAL;
- }
- if (pst[j].fid < lastfid)
- lastfid = pst[j].fid;
- }
- if (lastfid & 1) {
- printk(KERN_ERR FW_BUG PFX "lastfid invalid\n");
- return -EINVAL;
- }
- if (lastfid > LO_FID_TABLE_TOP)
- printk(KERN_INFO FW_BUG PFX
- "first fid not from lo freq table\n");
-
- return 0;
-}
-
-static void invalidate_entry(struct cpufreq_frequency_table *powernow_table,
- unsigned int entry)
-{
- powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
-}
-
-static void print_basics(struct powernow_k8_data *data)
-{
- int j;
- for (j = 0; j < data->numps; j++) {
- if (data->powernow_table[j].frequency !=
- CPUFREQ_ENTRY_INVALID) {
- if (cpu_family == CPU_HW_PSTATE) {
- printk(KERN_INFO PFX
- " %d : pstate %d (%d MHz)\n", j,
- data->powernow_table[j].index,
- data->powernow_table[j].frequency/1000);
- } else {
- printk(KERN_INFO PFX
- " %d : fid 0x%x (%d MHz), vid 0x%x\n",
- j,
- data->powernow_table[j].index & 0xff,
- data->powernow_table[j].frequency/1000,
- data->powernow_table[j].index >> 8);
- }
- }
- }
- if (data->batps)
- printk(KERN_INFO PFX "Only %d pstates on battery\n",
- data->batps);
-}
-
-static u32 freq_from_fid_did(u32 fid, u32 did)
-{
- u32 mhz = 0;
-
- if (boot_cpu_data.x86 == 0x10)
- mhz = (100 * (fid + 0x10)) >> did;
- else if (boot_cpu_data.x86 == 0x11)
- mhz = (100 * (fid + 8)) >> did;
- else
- BUG();
-
- return mhz * 1000;
-}
-
-static int fill_powernow_table(struct powernow_k8_data *data,
- struct pst_s *pst, u8 maxvid)
-{
- struct cpufreq_frequency_table *powernow_table;
- unsigned int j;
-
- if (data->batps) {
- /* use ACPI support to get full speed on mains power */
- printk(KERN_WARNING PFX
- "Only %d pstates usable (use ACPI driver for full "
- "range\n", data->batps);
- data->numps = data->batps;
- }
-
- for (j = 1; j < data->numps; j++) {
- if (pst[j-1].fid >= pst[j].fid) {
- printk(KERN_ERR PFX "PST out of sequence\n");
- return -EINVAL;
- }
- }
-
- if (data->numps < 2) {
- printk(KERN_ERR PFX "no p states to transition\n");
- return -ENODEV;
- }
-
- if (check_pst_table(data, pst, maxvid))
- return -EINVAL;
-
- powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
- * (data->numps + 1)), GFP_KERNEL);
- if (!powernow_table) {
- printk(KERN_ERR PFX "powernow_table memory alloc failure\n");
- return -ENOMEM;
- }
-
- for (j = 0; j < data->numps; j++) {
- int freq;
- powernow_table[j].index = pst[j].fid; /* lower 8 bits */
- powernow_table[j].index |= (pst[j].vid << 8); /* upper 8 bits */
- freq = find_khz_freq_from_fid(pst[j].fid);
- powernow_table[j].frequency = freq;
- }
- powernow_table[data->numps].frequency = CPUFREQ_TABLE_END;
- powernow_table[data->numps].index = 0;
-
- if (query_current_values_with_pending_wait(data)) {
- kfree(powernow_table);
- return -EIO;
- }
-
- dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
- data->powernow_table = powernow_table;
- if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
- print_basics(data);
-
- for (j = 0; j < data->numps; j++)
- if ((pst[j].fid == data->currfid) &&
- (pst[j].vid == data->currvid))
- return 0;
-
- dprintk("currfid/vid do not match PST, ignoring\n");
- return 0;
-}
-
-/* Find and validate the PSB/PST table in BIOS. */
-static int find_psb_table(struct powernow_k8_data *data)
-{
- struct psb_s *psb;
- unsigned int i;
- u32 mvs;
- u8 maxvid;
- u32 cpst = 0;
- u32 thiscpuid;
-
- for (i = 0xc0000; i < 0xffff0; i += 0x10) {
- /* Scan BIOS looking for the signature. */
- /* It can not be at ffff0 - it is too big. */
-
- psb = phys_to_virt(i);
- if (memcmp(psb, PSB_ID_STRING, PSB_ID_STRING_LEN) != 0)
- continue;
-
- dprintk("found PSB header at 0x%p\n", psb);
-
- dprintk("table vers: 0x%x\n", psb->tableversion);
- if (psb->tableversion != PSB_VERSION_1_4) {
- printk(KERN_ERR FW_BUG PFX "PSB table is not v1.4\n");
- return -ENODEV;
- }
-
- dprintk("flags: 0x%x\n", psb->flags1);
- if (psb->flags1) {
- printk(KERN_ERR FW_BUG PFX "unknown flags\n");
- return -ENODEV;
- }
-
- data->vstable = psb->vstable;
- dprintk("voltage stabilization time: %d(*20us)\n",
- data->vstable);
-
- dprintk("flags2: 0x%x\n", psb->flags2);
- data->rvo = psb->flags2 & 3;
- data->irt = ((psb->flags2) >> 2) & 3;
- mvs = ((psb->flags2) >> 4) & 3;
- data->vidmvs = 1 << mvs;
- data->batps = ((psb->flags2) >> 6) & 3;
-
- dprintk("ramp voltage offset: %d\n", data->rvo);
- dprintk("isochronous relief time: %d\n", data->irt);
- dprintk("maximum voltage step: %d - 0x%x\n", mvs, data->vidmvs);
-
- dprintk("numpst: 0x%x\n", psb->num_tables);
- cpst = psb->num_tables;
- if ((psb->cpuid == 0x00000fc0) ||
- (psb->cpuid == 0x00000fe0)) {
- thiscpuid = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
- if ((thiscpuid == 0x00000fc0) ||
- (thiscpuid == 0x00000fe0))
- cpst = 1;
- }
- if (cpst != 1) {
- printk(KERN_ERR FW_BUG PFX "numpst must be 1\n");
- return -ENODEV;
- }
-
- data->plllock = psb->plllocktime;
- dprintk("plllocktime: 0x%x (units 1us)\n", psb->plllocktime);
- dprintk("maxfid: 0x%x\n", psb->maxfid);
- dprintk("maxvid: 0x%x\n", psb->maxvid);
- maxvid = psb->maxvid;
-
- data->numps = psb->numps;
- dprintk("numpstates: 0x%x\n", data->numps);
- return fill_powernow_table(data,
- (struct pst_s *)(psb+1), maxvid);
- }
- /*
- * If you see this message, complain to BIOS manufacturer. If
- * he tells you "we do not support Linux" or some similar
- * nonsense, remember that Windows 2000 uses the same legacy
- * mechanism that the old Linux PSB driver uses. Tell them it
- * is broken with Windows 2000.
- *
- * The reference to the AMD documentation is chapter 9 in the
- * BIOS and Kernel Developer's Guide, which is available on
- * www.amd.com
- */
- printk(KERN_ERR FW_BUG PFX "No PSB or ACPI _PSS objects\n");
- printk(KERN_ERR PFX "Make sure that your BIOS is up to date"
- " and Cool'N'Quiet support is enabled in BIOS setup\n");
- return -ENODEV;
-}
-
-static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data,
- unsigned int index)
-{
- u64 control;
-
- if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE))
- return;
-
- control = data->acpi_data.states[index].control;
- data->irt = (control >> IRT_SHIFT) & IRT_MASK;
- data->rvo = (control >> RVO_SHIFT) & RVO_MASK;
- data->exttype = (control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK;
- data->plllock = (control >> PLL_L_SHIFT) & PLL_L_MASK;
- data->vidmvs = 1 << ((control >> MVS_SHIFT) & MVS_MASK);
- data->vstable = (control >> VST_SHIFT) & VST_MASK;
-}
-
-static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
-{
- struct cpufreq_frequency_table *powernow_table;
- int ret_val = -ENODEV;
- u64 control, status;
-
- if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
- dprintk("register performance failed: bad ACPI data\n");
- return -EIO;
- }
-
- /* verify the data contained in the ACPI structures */
- if (data->acpi_data.state_count <= 1) {
- dprintk("No ACPI P-States\n");
- goto err_out;
- }
-
- control = data->acpi_data.control_register.space_id;
- status = data->acpi_data.status_register.space_id;
-
- if ((control != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
- (status != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
- dprintk("Invalid control/status registers (%x - %x)\n",
- control, status);
- goto err_out;
- }
-
- /* fill in data->powernow_table */
- powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
- * (data->acpi_data.state_count + 1)), GFP_KERNEL);
- if (!powernow_table) {
- dprintk("powernow_table memory alloc failure\n");
- goto err_out;
- }
-
- /* fill in data */
- data->numps = data->acpi_data.state_count;
- powernow_k8_acpi_pst_values(data, 0);
-
- if (cpu_family == CPU_HW_PSTATE)
- ret_val = fill_powernow_table_pstate(data, powernow_table);
- else
- ret_val = fill_powernow_table_fidvid(data, powernow_table);
- if (ret_val)
- goto err_out_mem;
-
- powernow_table[data->acpi_data.state_count].frequency =
- CPUFREQ_TABLE_END;
- powernow_table[data->acpi_data.state_count].index = 0;
- data->powernow_table = powernow_table;
-
- if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
- print_basics(data);
-
- /* notify BIOS that we exist */
- acpi_processor_notify_smm(THIS_MODULE);
-
- if (!zalloc_cpumask_var(&data->acpi_data.shared_cpu_map, GFP_KERNEL)) {
- printk(KERN_ERR PFX
- "unable to alloc powernow_k8_data cpumask\n");
- ret_val = -ENOMEM;
- goto err_out_mem;
- }
-
- return 0;
-
-err_out_mem:
- kfree(powernow_table);
-
-err_out:
- acpi_processor_unregister_performance(&data->acpi_data, data->cpu);
-
- /* data->acpi_data.state_count informs us at ->exit()
- * whether ACPI was used */
- data->acpi_data.state_count = 0;
-
- return ret_val;
-}
-
-static int fill_powernow_table_pstate(struct powernow_k8_data *data,
- struct cpufreq_frequency_table *powernow_table)
-{
- int i;
- u32 hi = 0, lo = 0;
- rdmsr(MSR_PSTATE_CUR_LIMIT, lo, hi);
- data->max_hw_pstate = (lo & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT;
-
- for (i = 0; i < data->acpi_data.state_count; i++) {
- u32 index;
-
- index = data->acpi_data.states[i].control & HW_PSTATE_MASK;
- if (index > data->max_hw_pstate) {
- printk(KERN_ERR PFX "invalid pstate %d - "
- "bad value %d.\n", i, index);
- printk(KERN_ERR PFX "Please report to BIOS "
- "manufacturer\n");
- invalidate_entry(powernow_table, i);
- continue;
- }
- rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
- if (!(hi & HW_PSTATE_VALID_MASK)) {
- dprintk("invalid pstate %d, ignoring\n", index);
- invalidate_entry(powernow_table, i);
- continue;
- }
-
- powernow_table[i].index = index;
-
- /* Frequency may be rounded for these */
- if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
- || boot_cpu_data.x86 == 0x11) {
- powernow_table[i].frequency =
- freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
- } else
- powernow_table[i].frequency =
- data->acpi_data.states[i].core_frequency * 1000;
- }
- return 0;
-}
-
-static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
- struct cpufreq_frequency_table *powernow_table)
-{
- int i;
-
- for (i = 0; i < data->acpi_data.state_count; i++) {
- u32 fid;
- u32 vid;
- u32 freq, index;
- u64 status, control;
-
- if (data->exttype) {
- status = data->acpi_data.states[i].status;
- fid = status & EXT_FID_MASK;
- vid = (status >> VID_SHIFT) & EXT_VID_MASK;
- } else {
- control = data->acpi_data.states[i].control;
- fid = control & FID_MASK;
- vid = (control >> VID_SHIFT) & VID_MASK;
- }
-
- dprintk(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid);
-
- index = fid | (vid<<8);
- powernow_table[i].index = index;
-
- freq = find_khz_freq_from_fid(fid);
- powernow_table[i].frequency = freq;
-
- /* verify frequency is OK */
- if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) {
- dprintk("invalid freq %u kHz, ignoring\n", freq);
- invalidate_entry(powernow_table, i);
- continue;
- }
-
- /* verify voltage is OK -
- * BIOSs are using "off" to indicate invalid */
- if (vid == VID_OFF) {
- dprintk("invalid vid %u, ignoring\n", vid);
- invalidate_entry(powernow_table, i);
- continue;
- }
-
- if (freq != (data->acpi_data.states[i].core_frequency * 1000)) {
- printk(KERN_INFO PFX "invalid freq entries "
- "%u kHz vs. %u kHz\n", freq,
- (unsigned int)
- (data->acpi_data.states[i].core_frequency
- * 1000));
- invalidate_entry(powernow_table, i);
- continue;
- }
- }
- return 0;
-}
-
-static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
-{
- if (data->acpi_data.state_count)
- acpi_processor_unregister_performance(&data->acpi_data,
- data->cpu);
- free_cpumask_var(data->acpi_data.shared_cpu_map);
-}
-
-static int get_transition_latency(struct powernow_k8_data *data)
-{
- int max_latency = 0;
- int i;
- for (i = 0; i < data->acpi_data.state_count; i++) {
- int cur_latency = data->acpi_data.states[i].transition_latency
- + data->acpi_data.states[i].bus_master_latency;
- if (cur_latency > max_latency)
- max_latency = cur_latency;
- }
- if (max_latency == 0) {
- /*
- * Fam 11h and later may return 0 as transition latency. This
- * is intended and means "very fast". While cpufreq core and
- * governors currently can handle that gracefully, better set it
- * to 1 to avoid problems in the future.
- */
- if (boot_cpu_data.x86 < 0x11)
- printk(KERN_ERR FW_WARN PFX "Invalid zero transition "
- "latency\n");
- max_latency = 1;
- }
- /* value in usecs, needs to be in nanoseconds */
- return 1000 * max_latency;
-}
-
-/* Take a frequency, and issue the fid/vid transition command */
-static int transition_frequency_fidvid(struct powernow_k8_data *data,
- unsigned int index)
-{
- u32 fid = 0;
- u32 vid = 0;
- int res, i;
- struct cpufreq_freqs freqs;
-
- dprintk("cpu %d transition to index %u\n", smp_processor_id(), index);
-
- /* fid/vid correctness check for k8 */
- /* fid are the lower 8 bits of the index we stored into
- * the cpufreq frequency table in find_psb_table, vid
- * are the upper 8 bits.
- */
- fid = data->powernow_table[index].index & 0xFF;
- vid = (data->powernow_table[index].index & 0xFF00) >> 8;
-
- dprintk("table matched fid 0x%x, giving vid 0x%x\n", fid, vid);
-
- if (query_current_values_with_pending_wait(data))
- return 1;
-
- if ((data->currvid == vid) && (data->currfid == fid)) {
- dprintk("target matches current values (fid 0x%x, vid 0x%x)\n",
- fid, vid);
- return 0;
- }
-
- dprintk("cpu %d, changing to fid 0x%x, vid 0x%x\n",
- smp_processor_id(), fid, vid);
- freqs.old = find_khz_freq_from_fid(data->currfid);
- freqs.new = find_khz_freq_from_fid(fid);
-
- for_each_cpu(i, data->available_cores) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- }
-
- res = transition_fid_vid(data, fid, vid);
- freqs.new = find_khz_freq_from_fid(data->currfid);
-
- for_each_cpu(i, data->available_cores) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
- return res;
-}
-
-/* Take a frequency, and issue the hardware pstate transition command */
-static int transition_frequency_pstate(struct powernow_k8_data *data,
- unsigned int index)
-{
- u32 pstate = 0;
- int res, i;
- struct cpufreq_freqs freqs;
-
- dprintk("cpu %d transition to index %u\n", smp_processor_id(), index);
-
- /* get MSR index for hardware pstate transition */
- pstate = index & HW_PSTATE_MASK;
- if (pstate > data->max_hw_pstate)
- return 0;
- freqs.old = find_khz_freq_from_pstate(data->powernow_table,
- data->currpstate);
- freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate);
-
- for_each_cpu(i, data->available_cores) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- }
-
- res = transition_pstate(data, pstate);
- freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate);
-
- for_each_cpu(i, data->available_cores) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
- return res;
-}
-
-/* Driver entry point to switch to the target frequency */
-static int powernowk8_target(struct cpufreq_policy *pol,
- unsigned targfreq, unsigned relation)
-{
- cpumask_var_t oldmask;
- struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
- u32 checkfid;
- u32 checkvid;
- unsigned int newstate;
- int ret = -EIO;
-
- if (!data)
- return -EINVAL;
-
- checkfid = data->currfid;
- checkvid = data->currvid;
-
- /* only run on specific CPU from here on. */
- /* This is poor form: use a workqueue or smp_call_function_single */
- if (!alloc_cpumask_var(&oldmask, GFP_KERNEL))
- return -ENOMEM;
-
- cpumask_copy(oldmask, tsk_cpus_allowed(current));
- set_cpus_allowed_ptr(current, cpumask_of(pol->cpu));
-
- if (smp_processor_id() != pol->cpu) {
- printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
- goto err_out;
- }
-
- if (pending_bit_stuck()) {
- printk(KERN_ERR PFX "failing targ, change pending bit set\n");
- goto err_out;
- }
-
- dprintk("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n",
- pol->cpu, targfreq, pol->min, pol->max, relation);
-
- if (query_current_values_with_pending_wait(data))
- goto err_out;
-
- if (cpu_family != CPU_HW_PSTATE) {
- dprintk("targ: curr fid 0x%x, vid 0x%x\n",
- data->currfid, data->currvid);
-
- if ((checkvid != data->currvid) ||
- (checkfid != data->currfid)) {
- printk(KERN_INFO PFX
- "error - out of sync, fix 0x%x 0x%x, "
- "vid 0x%x 0x%x\n",
- checkfid, data->currfid,
- checkvid, data->currvid);
- }
- }
-
- if (cpufreq_frequency_table_target(pol, data->powernow_table,
- targfreq, relation, &newstate))
- goto err_out;
-
- mutex_lock(&fidvid_mutex);
-
- powernow_k8_acpi_pst_values(data, newstate);
-
- if (cpu_family == CPU_HW_PSTATE)
- ret = transition_frequency_pstate(data, newstate);
- else
- ret = transition_frequency_fidvid(data, newstate);
- if (ret) {
- printk(KERN_ERR PFX "transition frequency failed\n");
- ret = 1;
- mutex_unlock(&fidvid_mutex);
- goto err_out;
- }
- mutex_unlock(&fidvid_mutex);
-
- if (cpu_family == CPU_HW_PSTATE)
- pol->cur = find_khz_freq_from_pstate(data->powernow_table,
- newstate);
- else
- pol->cur = find_khz_freq_from_fid(data->currfid);
- ret = 0;
-
-err_out:
- set_cpus_allowed_ptr(current, oldmask);
- free_cpumask_var(oldmask);
- return ret;
-}
-
-/* Driver entry point to verify the policy and range of frequencies */
-static int powernowk8_verify(struct cpufreq_policy *pol)
-{
- struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
-
- if (!data)
- return -EINVAL;
-
- return cpufreq_frequency_table_verify(pol, data->powernow_table);
-}
-
-struct init_on_cpu {
- struct powernow_k8_data *data;
- int rc;
-};
-
-static void __cpuinit powernowk8_cpu_init_on_cpu(void *_init_on_cpu)
-{
- struct init_on_cpu *init_on_cpu = _init_on_cpu;
-
- if (pending_bit_stuck()) {
- printk(KERN_ERR PFX "failing init, change pending bit set\n");
- init_on_cpu->rc = -ENODEV;
- return;
- }
-
- if (query_current_values_with_pending_wait(init_on_cpu->data)) {
- init_on_cpu->rc = -ENODEV;
- return;
- }
-
- if (cpu_family == CPU_OPTERON)
- fidvid_msr_init();
-
- init_on_cpu->rc = 0;
-}
-
-/* per CPU init entry point to the driver */
-static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
-{
- static const char ACPI_PSS_BIOS_BUG_MSG[] =
- KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
- FW_BUG PFX "Try again with latest BIOS.\n";
- struct powernow_k8_data *data;
- struct init_on_cpu init_on_cpu;
- int rc;
- struct cpuinfo_x86 *c = &cpu_data(pol->cpu);
-
- if (!cpu_online(pol->cpu))
- return -ENODEV;
-
- smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
- if (rc)
- return -ENODEV;
-
- data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL);
- if (!data) {
- printk(KERN_ERR PFX "unable to alloc powernow_k8_data");
- return -ENOMEM;
- }
-
- data->cpu = pol->cpu;
- data->currpstate = HW_PSTATE_INVALID;
-
- if (powernow_k8_cpu_init_acpi(data)) {
- /*
- * Use the PSB BIOS structure. This is only availabe on
- * an UP version, and is deprecated by AMD.
- */
- if (num_online_cpus() != 1) {
- printk_once(ACPI_PSS_BIOS_BUG_MSG);
- goto err_out;
- }
- if (pol->cpu != 0) {
- printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
- "CPU other than CPU0. Complain to your BIOS "
- "vendor.\n");
- goto err_out;
- }
- rc = find_psb_table(data);
- if (rc)
- goto err_out;
-
- /* Take a crude guess here.
- * That guess was in microseconds, so multiply with 1000 */
- pol->cpuinfo.transition_latency = (
- ((data->rvo + 8) * data->vstable * VST_UNITS_20US) +
- ((1 << data->irt) * 30)) * 1000;
- } else /* ACPI _PSS objects available */
- pol->cpuinfo.transition_latency = get_transition_latency(data);
-
- /* only run on specific CPU from here on */
- init_on_cpu.data = data;
- smp_call_function_single(data->cpu, powernowk8_cpu_init_on_cpu,
- &init_on_cpu, 1);
- rc = init_on_cpu.rc;
- if (rc != 0)
- goto err_out_exit_acpi;
-
- if (cpu_family == CPU_HW_PSTATE)
- cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
- else
- cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
- data->available_cores = pol->cpus;
-
- if (cpu_family == CPU_HW_PSTATE)
- pol->cur = find_khz_freq_from_pstate(data->powernow_table,
- data->currpstate);
- else
- pol->cur = find_khz_freq_from_fid(data->currfid);
- dprintk("policy current frequency %d kHz\n", pol->cur);
-
- /* min/max the cpu is capable of */
- if (cpufreq_frequency_table_cpuinfo(pol, data->powernow_table)) {
- printk(KERN_ERR FW_BUG PFX "invalid powernow_table\n");
- powernow_k8_cpu_exit_acpi(data);
- kfree(data->powernow_table);
- kfree(data);
- return -EINVAL;
- }
-
- /* Check for APERF/MPERF support in hardware */
- if (cpu_has(c, X86_FEATURE_APERFMPERF))
- cpufreq_amd64_driver.getavg = cpufreq_get_measured_perf;
-
- cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu);
-
- if (cpu_family == CPU_HW_PSTATE)
- dprintk("cpu_init done, current pstate 0x%x\n",
- data->currpstate);
- else
- dprintk("cpu_init done, current fid 0x%x, vid 0x%x\n",
- data->currfid, data->currvid);
-
- per_cpu(powernow_data, pol->cpu) = data;
-
- return 0;
-
-err_out_exit_acpi:
- powernow_k8_cpu_exit_acpi(data);
-
-err_out:
- kfree(data);
- return -ENODEV;
-}
-
-static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
-{
- struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
-
- if (!data)
- return -EINVAL;
-
- powernow_k8_cpu_exit_acpi(data);
-
- cpufreq_frequency_table_put_attr(pol->cpu);
-
- kfree(data->powernow_table);
- kfree(data);
- per_cpu(powernow_data, pol->cpu) = NULL;
-
- return 0;
-}
-
-static void query_values_on_cpu(void *_err)
-{
- int *err = _err;
- struct powernow_k8_data *data = __this_cpu_read(powernow_data);
-
- *err = query_current_values_with_pending_wait(data);
-}
-
-static unsigned int powernowk8_get(unsigned int cpu)
-{
- struct powernow_k8_data *data = per_cpu(powernow_data, cpu);
- unsigned int khz = 0;
- int err;
-
- if (!data)
- return 0;
-
- smp_call_function_single(cpu, query_values_on_cpu, &err, true);
- if (err)
- goto out;
-
- if (cpu_family == CPU_HW_PSTATE)
- khz = find_khz_freq_from_pstate(data->powernow_table,
- data->currpstate);
- else
- khz = find_khz_freq_from_fid(data->currfid);
-
-
-out:
- return khz;
-}
-
-static void _cpb_toggle_msrs(bool t)
-{
- int cpu;
-
- get_online_cpus();
-
- rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
-
- for_each_cpu(cpu, cpu_online_mask) {
- struct msr *reg = per_cpu_ptr(msrs, cpu);
- if (t)
- reg->l &= ~BIT(25);
- else
- reg->l |= BIT(25);
- }
- wrmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
-
- put_online_cpus();
-}
-
-/*
- * Switch on/off core performance boosting.
- *
- * 0=disable
- * 1=enable.
- */
-static void cpb_toggle(bool t)
-{
- if (!cpb_capable)
- return;
-
- if (t && !cpb_enabled) {
- cpb_enabled = true;
- _cpb_toggle_msrs(t);
- printk(KERN_INFO PFX "Core Boosting enabled.\n");
- } else if (!t && cpb_enabled) {
- cpb_enabled = false;
- _cpb_toggle_msrs(t);
- printk(KERN_INFO PFX "Core Boosting disabled.\n");
- }
-}
-
-static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
- size_t count)
-{
- int ret = -EINVAL;
- unsigned long val = 0;
-
- ret = strict_strtoul(buf, 10, &val);
- if (!ret && (val == 0 || val == 1) && cpb_capable)
- cpb_toggle(val);
- else
- return -EINVAL;
-
- return count;
-}
-
-static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
-{
- return sprintf(buf, "%u\n", cpb_enabled);
-}
-
-#define define_one_rw(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_rw(cpb);
-
-static struct freq_attr *powernow_k8_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- &cpb,
- NULL,
-};
-
-static struct cpufreq_driver cpufreq_amd64_driver = {
- .verify = powernowk8_verify,
- .target = powernowk8_target,
- .bios_limit = acpi_processor_get_bios_limit,
- .init = powernowk8_cpu_init,
- .exit = __devexit_p(powernowk8_cpu_exit),
- .get = powernowk8_get,
- .name = "powernow-k8",
- .owner = THIS_MODULE,
- .attr = powernow_k8_attr,
-};
-
-/*
- * Clear the boost-disable flag on the CPU_DOWN path so that this cpu
- * cannot block the remaining ones from boosting. On the CPU_UP path we
- * simply keep the boost-disable flag in sync with the current global
- * state.
- */
-static int cpb_notify(struct notifier_block *nb, unsigned long action,
- void *hcpu)
-{
- unsigned cpu = (long)hcpu;
- u32 lo, hi;
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
-
- if (!cpb_enabled) {
- rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
- lo |= BIT(25);
- wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi);
- }
- break;
-
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
- lo &= ~BIT(25);
- wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi);
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block cpb_nb = {
- .notifier_call = cpb_notify,
-};
-
-/* driver entry point for init */
-static int __cpuinit powernowk8_init(void)
-{
- unsigned int i, supported_cpus = 0, cpu;
-
- for_each_online_cpu(i) {
- int rc;
- smp_call_function_single(i, check_supported_cpu, &rc, 1);
- if (rc == 0)
- supported_cpus++;
- }
-
- if (supported_cpus != num_online_cpus())
- return -ENODEV;
-
- printk(KERN_INFO PFX "Found %d %s (%d cpu cores) (" VERSION ")\n",
- num_online_nodes(), boot_cpu_data.x86_model_id, supported_cpus);
-
- if (boot_cpu_has(X86_FEATURE_CPB)) {
-
- cpb_capable = true;
-
- register_cpu_notifier(&cpb_nb);
-
- msrs = msrs_alloc();
- if (!msrs) {
- printk(KERN_ERR "%s: Error allocating msrs!\n", __func__);
- return -ENOMEM;
- }
-
- rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
-
- for_each_cpu(cpu, cpu_online_mask) {
- struct msr *reg = per_cpu_ptr(msrs, cpu);
- cpb_enabled |= !(!!(reg->l & BIT(25)));
- }
-
- printk(KERN_INFO PFX "Core Performance Boosting: %s.\n",
- (cpb_enabled ? "on" : "off"));
- }
-
- return cpufreq_register_driver(&cpufreq_amd64_driver);
-}
-
-/* driver entry point for term */
-static void __exit powernowk8_exit(void)
-{
- dprintk("exit\n");
-
- if (boot_cpu_has(X86_FEATURE_CPB)) {
- msrs_free(msrs);
- msrs = NULL;
-
- unregister_cpu_notifier(&cpb_nb);
- }
-
- cpufreq_unregister_driver(&cpufreq_amd64_driver);
-}
-
-MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and "
- "Mark Langsdorf <mark.langsdorf@amd.com>");
-MODULE_DESCRIPTION("AMD Athlon 64 and Opteron processor frequency driver.");
-MODULE_LICENSE("GPL");
-
-late_initcall(powernowk8_init);
-module_exit(powernowk8_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
deleted file mode 100644
index df3529b1c02..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- * (c) 2003-2006 Advanced Micro Devices, Inc.
- * Your use of this code is subject to the terms and conditions of the
- * GNU general public license version 2. See "COPYING" or
- * http://www.gnu.org/licenses/gpl.html
- */
-
-enum pstate {
- HW_PSTATE_INVALID = 0xff,
- HW_PSTATE_0 = 0,
- HW_PSTATE_1 = 1,
- HW_PSTATE_2 = 2,
- HW_PSTATE_3 = 3,
- HW_PSTATE_4 = 4,
- HW_PSTATE_5 = 5,
- HW_PSTATE_6 = 6,
- HW_PSTATE_7 = 7,
-};
-
-struct powernow_k8_data {
- unsigned int cpu;
-
- u32 numps; /* number of p-states */
- u32 batps; /* number of p-states supported on battery */
- u32 max_hw_pstate; /* maximum legal hardware pstate */
-
- /* these values are constant when the PSB is used to determine
- * vid/fid pairings, but are modified during the ->target() call
- * when ACPI is used */
- u32 rvo; /* ramp voltage offset */
- u32 irt; /* isochronous relief time */
- u32 vidmvs; /* usable value calculated from mvs */
- u32 vstable; /* voltage stabilization time, units 20 us */
- u32 plllock; /* pll lock time, units 1 us */
- u32 exttype; /* extended interface = 1 */
-
- /* keep track of the current fid / vid or pstate */
- u32 currvid;
- u32 currfid;
- enum pstate currpstate;
-
- /* the powernow_table includes all frequency and vid/fid pairings:
- * fid are the lower 8 bits of the index, vid are the upper 8 bits.
- * frequency is in kHz */
- struct cpufreq_frequency_table *powernow_table;
-
- /* the acpi table needs to be kept. it's only available if ACPI was
- * used to determine valid frequency/vid/fid states */
- struct acpi_processor_performance acpi_data;
-
- /* we need to keep track of associated cores, but let cpufreq
- * handle hotplug events - so just point at cpufreq pol->cpus
- * structure */
- struct cpumask *available_cores;
-};
-
-/* processor's cpuid instruction support */
-#define CPUID_PROCESSOR_SIGNATURE 1 /* function 1 */
-#define CPUID_XFAM 0x0ff00000 /* extended family */
-#define CPUID_XFAM_K8 0
-#define CPUID_XMOD 0x000f0000 /* extended model */
-#define CPUID_XMOD_REV_MASK 0x000c0000
-#define CPUID_XFAM_10H 0x00100000 /* family 0x10 */
-#define CPUID_USE_XFAM_XMOD 0x00000f00
-#define CPUID_GET_MAX_CAPABILITIES 0x80000000
-#define CPUID_FREQ_VOLT_CAPABILITIES 0x80000007
-#define P_STATE_TRANSITION_CAPABLE 6
-
-/* Model Specific Registers for p-state transitions. MSRs are 64-bit. For */
-/* writes (wrmsr - opcode 0f 30), the register number is placed in ecx, and */
-/* the value to write is placed in edx:eax. For reads (rdmsr - opcode 0f 32), */
-/* the register number is placed in ecx, and the data is returned in edx:eax. */
-
-#define MSR_FIDVID_CTL 0xc0010041
-#define MSR_FIDVID_STATUS 0xc0010042
-
-/* Field definitions within the FID VID Low Control MSR : */
-#define MSR_C_LO_INIT_FID_VID 0x00010000
-#define MSR_C_LO_NEW_VID 0x00003f00
-#define MSR_C_LO_NEW_FID 0x0000003f
-#define MSR_C_LO_VID_SHIFT 8
-
-/* Field definitions within the FID VID High Control MSR : */
-#define MSR_C_HI_STP_GNT_TO 0x000fffff
-
-/* Field definitions within the FID VID Low Status MSR : */
-#define MSR_S_LO_CHANGE_PENDING 0x80000000 /* cleared when completed */
-#define MSR_S_LO_MAX_RAMP_VID 0x3f000000
-#define MSR_S_LO_MAX_FID 0x003f0000
-#define MSR_S_LO_START_FID 0x00003f00
-#define MSR_S_LO_CURRENT_FID 0x0000003f
-
-/* Field definitions within the FID VID High Status MSR : */
-#define MSR_S_HI_MIN_WORKING_VID 0x3f000000
-#define MSR_S_HI_MAX_WORKING_VID 0x003f0000
-#define MSR_S_HI_START_VID 0x00003f00
-#define MSR_S_HI_CURRENT_VID 0x0000003f
-#define MSR_C_HI_STP_GNT_BENIGN 0x00000001
-
-
-/* Hardware Pstate _PSS and MSR definitions */
-#define USE_HW_PSTATE 0x00000080
-#define HW_PSTATE_MASK 0x00000007
-#define HW_PSTATE_VALID_MASK 0x80000000
-#define HW_PSTATE_MAX_MASK 0x000000f0
-#define HW_PSTATE_MAX_SHIFT 4
-#define MSR_PSTATE_DEF_BASE 0xc0010064 /* base of Pstate MSRs */
-#define MSR_PSTATE_STATUS 0xc0010063 /* Pstate Status MSR */
-#define MSR_PSTATE_CTRL 0xc0010062 /* Pstate control MSR */
-#define MSR_PSTATE_CUR_LIMIT 0xc0010061 /* pstate current limit MSR */
-
-/* define the two driver architectures */
-#define CPU_OPTERON 0
-#define CPU_HW_PSTATE 1
-
-
-/*
- * There are restrictions frequencies have to follow:
- * - only 1 entry in the low fid table ( <=1.4GHz )
- * - lowest entry in the high fid table must be >= 2 * the entry in the
- * low fid table
- * - lowest entry in the high fid table must be a <= 200MHz + 2 * the entry
- * in the low fid table
- * - the parts can only step at <= 200 MHz intervals, odd fid values are
- * supported in revision G and later revisions.
- * - lowest frequency must be >= interprocessor hypertransport link speed
- * (only applies to MP systems obviously)
- */
-
-/* fids (frequency identifiers) are arranged in 2 tables - lo and hi */
-#define LO_FID_TABLE_TOP 7 /* fid values marking the boundary */
-#define HI_FID_TABLE_BOTTOM 8 /* between the low and high tables */
-
-#define LO_VCOFREQ_TABLE_TOP 1400 /* corresponding vco frequency values */
-#define HI_VCOFREQ_TABLE_BOTTOM 1600
-
-#define MIN_FREQ_RESOLUTION 200 /* fids jump by 2 matching freq jumps by 200 */
-
-#define MAX_FID 0x2a /* Spec only gives FID values as far as 5 GHz */
-#define LEAST_VID 0x3e /* Lowest (numerically highest) useful vid value */
-
-#define MIN_FREQ 800 /* Min and max freqs, per spec */
-#define MAX_FREQ 5000
-
-#define INVALID_FID_MASK 0xffffffc0 /* not a valid fid if these bits are set */
-#define INVALID_VID_MASK 0xffffffc0 /* not a valid vid if these bits are set */
-
-#define VID_OFF 0x3f
-
-#define STOP_GRANT_5NS 1 /* min poss memory access latency for voltage change */
-
-#define PLL_LOCK_CONVERSION (1000/5) /* ms to ns, then divide by clock period */
-
-#define MAXIMUM_VID_STEPS 1 /* Current cpus only allow a single step of 25mV */
-#define VST_UNITS_20US 20 /* Voltage Stabilization Time is in units of 20us */
-
-/*
- * Most values of interest are encoded in a single field of the _PSS
- * entries: the "control" value.
- */
-
-#define IRT_SHIFT 30
-#define RVO_SHIFT 28
-#define EXT_TYPE_SHIFT 27
-#define PLL_L_SHIFT 20
-#define MVS_SHIFT 18
-#define VST_SHIFT 11
-#define VID_SHIFT 6
-#define IRT_MASK 3
-#define RVO_MASK 3
-#define EXT_TYPE_MASK 1
-#define PLL_L_MASK 0x7f
-#define MVS_MASK 3
-#define VST_MASK 0x7f
-#define VID_MASK 0x1f
-#define FID_MASK 0x1f
-#define EXT_VID_MASK 0x3f
-#define EXT_FID_MASK 0x3f
-
-
-/*
- * Version 1.4 of the PSB table. This table is constructed by BIOS and is
- * to tell the OS's power management driver which VIDs and FIDs are
- * supported by this particular processor.
- * If the data in the PSB / PST is wrong, then this driver will program the
- * wrong values into hardware, which is very likely to lead to a crash.
- */
-
-#define PSB_ID_STRING "AMDK7PNOW!"
-#define PSB_ID_STRING_LEN 10
-
-#define PSB_VERSION_1_4 0x14
-
-struct psb_s {
- u8 signature[10];
- u8 tableversion;
- u8 flags1;
- u16 vstable;
- u8 flags2;
- u8 num_tables;
- u32 cpuid;
- u8 plllocktime;
- u8 maxfid;
- u8 maxvid;
- u8 numps;
-};
-
-/* Pairs of fid/vid values are appended to the version 1.4 PSB table. */
-struct pst_s {
- u8 fid;
- u8 vid;
-};
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k8", msg)
-
-static int core_voltage_pre_transition(struct powernow_k8_data *data,
- u32 reqvid, u32 regfid);
-static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid);
-static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid);
-
-static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index);
-
-static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);
-static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);
diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c
deleted file mode 100644
index 435a996a613..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c
+++ /dev/null
@@ -1,194 +0,0 @@
-/*
- * sc520_freq.c: cpufreq driver for the AMD Elan sc520
- *
- * Copyright (C) 2005 Sean Young <sean@mess.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.
- *
- * Based on elanfreq.c
- *
- * 2005-03-30: - initial revision
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-
-#include <linux/delay.h>
-#include <linux/cpufreq.h>
-#include <linux/timex.h>
-#include <linux/io.h>
-
-#include <asm/msr.h>
-
-#define MMCR_BASE 0xfffef000 /* The default base address */
-#define OFFS_CPUCTL 0x2 /* CPU Control Register */
-
-static __u8 __iomem *cpuctl;
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "sc520_freq", msg)
-#define PFX "sc520_freq: "
-
-static struct cpufreq_frequency_table sc520_freq_table[] = {
- {0x01, 100000},
- {0x02, 133000},
- {0, CPUFREQ_TABLE_END},
-};
-
-static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)
-{
- u8 clockspeed_reg = *cpuctl;
-
- switch (clockspeed_reg & 0x03) {
- default:
- printk(KERN_ERR PFX "error: cpuctl register has unexpected "
- "value %02x\n", clockspeed_reg);
- case 0x01:
- return 100000;
- case 0x02:
- return 133000;
- }
-}
-
-static void sc520_freq_set_cpu_state(unsigned int state)
-{
-
- struct cpufreq_freqs freqs;
- u8 clockspeed_reg;
-
- freqs.old = sc520_freq_get_cpu_frequency(0);
- freqs.new = sc520_freq_table[state].frequency;
- freqs.cpu = 0; /* AMD Elan is UP */
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
- dprintk("attempting to set frequency to %i kHz\n",
- sc520_freq_table[state].frequency);
-
- local_irq_disable();
-
- clockspeed_reg = *cpuctl & ~0x03;
- *cpuctl = clockspeed_reg | sc520_freq_table[state].index;
-
- local_irq_enable();
-
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-};
-
-static int sc520_freq_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, &sc520_freq_table[0]);
-}
-
-static int sc520_freq_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate = 0;
-
- if (cpufreq_frequency_table_target(policy, sc520_freq_table,
- target_freq, relation, &newstate))
- return -EINVAL;
-
- sc520_freq_set_cpu_state(newstate);
-
- return 0;
-}
-
-
-/*
- * Module init and exit code
- */
-
-static int sc520_freq_cpu_init(struct cpufreq_policy *policy)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- int result;
-
- /* capability check */
- if (c->x86_vendor != X86_VENDOR_AMD ||
- c->x86 != 4 || c->x86_model != 9)
- return -ENODEV;
-
- /* cpuinfo and default policy values */
- policy->cpuinfo.transition_latency = 1000000; /* 1ms */
- policy->cur = sc520_freq_get_cpu_frequency(0);
-
- result = cpufreq_frequency_table_cpuinfo(policy, sc520_freq_table);
- if (result)
- return result;
-
- cpufreq_frequency_table_get_attr(sc520_freq_table, policy->cpu);
-
- return 0;
-}
-
-
-static int sc520_freq_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-
-static struct freq_attr *sc520_freq_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-
-static struct cpufreq_driver sc520_freq_driver = {
- .get = sc520_freq_get_cpu_frequency,
- .verify = sc520_freq_verify,
- .target = sc520_freq_target,
- .init = sc520_freq_cpu_init,
- .exit = sc520_freq_cpu_exit,
- .name = "sc520_freq",
- .owner = THIS_MODULE,
- .attr = sc520_freq_attr,
-};
-
-
-static int __init sc520_freq_init(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- int err;
-
- /* Test if we have the right hardware */
- if (c->x86_vendor != X86_VENDOR_AMD ||
- c->x86 != 4 || c->x86_model != 9) {
- dprintk("no Elan SC520 processor found!\n");
- return -ENODEV;
- }
- cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1);
- if (!cpuctl) {
- printk(KERN_ERR "sc520_freq: error: failed to remap memory\n");
- return -ENOMEM;
- }
-
- err = cpufreq_register_driver(&sc520_freq_driver);
- if (err)
- iounmap(cpuctl);
-
- return err;
-}
-
-
-static void __exit sc520_freq_exit(void)
-{
- cpufreq_unregister_driver(&sc520_freq_driver);
- iounmap(cpuctl);
-}
-
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Sean Young <sean@mess.org>");
-MODULE_DESCRIPTION("cpufreq driver for AMD's Elan sc520 CPU");
-
-module_init(sc520_freq_init);
-module_exit(sc520_freq_exit);
-
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
deleted file mode 100644
index 9b1ff37de46..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ /dev/null
@@ -1,636 +0,0 @@
-/*
- * cpufreq driver for Enhanced SpeedStep, as found in Intel's Pentium
- * M (part of the Centrino chipset).
- *
- * Since the original Pentium M, most new Intel CPUs support Enhanced
- * SpeedStep.
- *
- * Despite the "SpeedStep" in the name, this is almost entirely unlike
- * traditional SpeedStep.
- *
- * Modelled on speedstep.c
- *
- * Copyright (C) 2003 Jeremy Fitzhardinge <jeremy@goop.org>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/sched.h> /* current */
-#include <linux/delay.h>
-#include <linux/compiler.h>
-#include <linux/gfp.h>
-
-#include <asm/msr.h>
-#include <asm/processor.h>
-#include <asm/cpufeature.h>
-
-#define PFX "speedstep-centrino: "
-#define MAINTAINER "cpufreq@vger.kernel.org"
-
-#define dprintk(msg...) \
- cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg)
-
-#define INTEL_MSR_RANGE (0xffff)
-
-struct cpu_id
-{
- __u8 x86; /* CPU family */
- __u8 x86_model; /* model */
- __u8 x86_mask; /* stepping */
-};
-
-enum {
- CPU_BANIAS,
- CPU_DOTHAN_A1,
- CPU_DOTHAN_A2,
- CPU_DOTHAN_B0,
- CPU_MP4HT_D0,
- CPU_MP4HT_E0,
-};
-
-static const struct cpu_id cpu_ids[] = {
- [CPU_BANIAS] = { 6, 9, 5 },
- [CPU_DOTHAN_A1] = { 6, 13, 1 },
- [CPU_DOTHAN_A2] = { 6, 13, 2 },
- [CPU_DOTHAN_B0] = { 6, 13, 6 },
- [CPU_MP4HT_D0] = {15, 3, 4 },
- [CPU_MP4HT_E0] = {15, 4, 1 },
-};
-#define N_IDS ARRAY_SIZE(cpu_ids)
-
-struct cpu_model
-{
- const struct cpu_id *cpu_id;
- const char *model_name;
- unsigned max_freq; /* max clock in kHz */
-
- struct cpufreq_frequency_table *op_points; /* clock/voltage pairs */
-};
-static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c,
- const struct cpu_id *x);
-
-/* Operating points for current CPU */
-static DEFINE_PER_CPU(struct cpu_model *, centrino_model);
-static DEFINE_PER_CPU(const struct cpu_id *, centrino_cpu);
-
-static struct cpufreq_driver centrino_driver;
-
-#ifdef CONFIG_X86_SPEEDSTEP_CENTRINO_TABLE
-
-/* Computes the correct form for IA32_PERF_CTL MSR for a particular
- frequency/voltage operating point; frequency in MHz, volts in mV.
- This is stored as "index" in the structure. */
-#define OP(mhz, mv) \
- { \
- .frequency = (mhz) * 1000, \
- .index = (((mhz)/100) << 8) | ((mv - 700) / 16) \
- }
-
-/*
- * These voltage tables were derived from the Intel Pentium M
- * datasheet, document 25261202.pdf, Table 5. I have verified they
- * are consistent with my IBM ThinkPad X31, which has a 1.3GHz Pentium
- * M.
- */
-
-/* Ultra Low Voltage Intel Pentium M processor 900MHz (Banias) */
-static struct cpufreq_frequency_table banias_900[] =
-{
- OP(600, 844),
- OP(800, 988),
- OP(900, 1004),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Ultra Low Voltage Intel Pentium M processor 1000MHz (Banias) */
-static struct cpufreq_frequency_table banias_1000[] =
-{
- OP(600, 844),
- OP(800, 972),
- OP(900, 988),
- OP(1000, 1004),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Low Voltage Intel Pentium M processor 1.10GHz (Banias) */
-static struct cpufreq_frequency_table banias_1100[] =
-{
- OP( 600, 956),
- OP( 800, 1020),
- OP( 900, 1100),
- OP(1000, 1164),
- OP(1100, 1180),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-
-/* Low Voltage Intel Pentium M processor 1.20GHz (Banias) */
-static struct cpufreq_frequency_table banias_1200[] =
-{
- OP( 600, 956),
- OP( 800, 1004),
- OP( 900, 1020),
- OP(1000, 1100),
- OP(1100, 1164),
- OP(1200, 1180),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Intel Pentium M processor 1.30GHz (Banias) */
-static struct cpufreq_frequency_table banias_1300[] =
-{
- OP( 600, 956),
- OP( 800, 1260),
- OP(1000, 1292),
- OP(1200, 1356),
- OP(1300, 1388),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Intel Pentium M processor 1.40GHz (Banias) */
-static struct cpufreq_frequency_table banias_1400[] =
-{
- OP( 600, 956),
- OP( 800, 1180),
- OP(1000, 1308),
- OP(1200, 1436),
- OP(1400, 1484),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Intel Pentium M processor 1.50GHz (Banias) */
-static struct cpufreq_frequency_table banias_1500[] =
-{
- OP( 600, 956),
- OP( 800, 1116),
- OP(1000, 1228),
- OP(1200, 1356),
- OP(1400, 1452),
- OP(1500, 1484),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Intel Pentium M processor 1.60GHz (Banias) */
-static struct cpufreq_frequency_table banias_1600[] =
-{
- OP( 600, 956),
- OP( 800, 1036),
- OP(1000, 1164),
- OP(1200, 1276),
- OP(1400, 1420),
- OP(1600, 1484),
- { .frequency = CPUFREQ_TABLE_END }
-};
-
-/* Intel Pentium M processor 1.70GHz (Banias) */
-static struct cpufreq_frequency_table banias_1700[] =
-{
- OP( 600, 956),
- OP( 800, 1004),
- OP(1000, 1116),
- OP(1200, 1228),
- OP(1400, 1308),
- OP(1700, 1484),
- { .frequency = CPUFREQ_TABLE_END }
-};
-#undef OP
-
-#define _BANIAS(cpuid, max, name) \
-{ .cpu_id = cpuid, \
- .model_name = "Intel(R) Pentium(R) M processor " name "MHz", \
- .max_freq = (max)*1000, \
- .op_points = banias_##max, \
-}
-#define BANIAS(max) _BANIAS(&cpu_ids[CPU_BANIAS], max, #max)
-
-/* CPU models, their operating frequency range, and freq/voltage
- operating points */
-static struct cpu_model models[] =
-{
- _BANIAS(&cpu_ids[CPU_BANIAS], 900, " 900"),
- BANIAS(1000),
- BANIAS(1100),
- BANIAS(1200),
- BANIAS(1300),
- BANIAS(1400),
- BANIAS(1500),
- BANIAS(1600),
- BANIAS(1700),
-
- /* NULL model_name is a wildcard */
- { &cpu_ids[CPU_DOTHAN_A1], NULL, 0, NULL },
- { &cpu_ids[CPU_DOTHAN_A2], NULL, 0, NULL },
- { &cpu_ids[CPU_DOTHAN_B0], NULL, 0, NULL },
- { &cpu_ids[CPU_MP4HT_D0], NULL, 0, NULL },
- { &cpu_ids[CPU_MP4HT_E0], NULL, 0, NULL },
-
- { NULL, }
-};
-#undef _BANIAS
-#undef BANIAS
-
-static int centrino_cpu_init_table(struct cpufreq_policy *policy)
-{
- struct cpuinfo_x86 *cpu = &cpu_data(policy->cpu);
- struct cpu_model *model;
-
- for(model = models; model->cpu_id != NULL; model++)
- if (centrino_verify_cpu_id(cpu, model->cpu_id) &&
- (model->model_name == NULL ||
- strcmp(cpu->x86_model_id, model->model_name) == 0))
- break;
-
- if (model->cpu_id == NULL) {
- /* No match at all */
- dprintk("no support for CPU model \"%s\": "
- "send /proc/cpuinfo to " MAINTAINER "\n",
- cpu->x86_model_id);
- return -ENOENT;
- }
-
- if (model->op_points == NULL) {
- /* Matched a non-match */
- dprintk("no table support for CPU model \"%s\"\n",
- cpu->x86_model_id);
- dprintk("try using the acpi-cpufreq driver\n");
- return -ENOENT;
- }
-
- per_cpu(centrino_model, policy->cpu) = model;
-
- dprintk("found \"%s\": max frequency: %dkHz\n",
- model->model_name, model->max_freq);
-
- return 0;
-}
-
-#else
-static inline int centrino_cpu_init_table(struct cpufreq_policy *policy)
-{
- return -ENODEV;
-}
-#endif /* CONFIG_X86_SPEEDSTEP_CENTRINO_TABLE */
-
-static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c,
- const struct cpu_id *x)
-{
- if ((c->x86 == x->x86) &&
- (c->x86_model == x->x86_model) &&
- (c->x86_mask == x->x86_mask))
- return 1;
- return 0;
-}
-
-/* To be called only after centrino_model is initialized */
-static unsigned extract_clock(unsigned msr, unsigned int cpu, int failsafe)
-{
- int i;
-
- /*
- * Extract clock in kHz from PERF_CTL value
- * for centrino, as some DSDTs are buggy.
- * Ideally, this can be done using the acpi_data structure.
- */
- if ((per_cpu(centrino_cpu, cpu) == &cpu_ids[CPU_BANIAS]) ||
- (per_cpu(centrino_cpu, cpu) == &cpu_ids[CPU_DOTHAN_A1]) ||
- (per_cpu(centrino_cpu, cpu) == &cpu_ids[CPU_DOTHAN_B0])) {
- msr = (msr >> 8) & 0xff;
- return msr * 100000;
- }
-
- if ((!per_cpu(centrino_model, cpu)) ||
- (!per_cpu(centrino_model, cpu)->op_points))
- return 0;
-
- msr &= 0xffff;
- for (i = 0;
- per_cpu(centrino_model, cpu)->op_points[i].frequency
- != CPUFREQ_TABLE_END;
- i++) {
- if (msr == per_cpu(centrino_model, cpu)->op_points[i].index)
- return per_cpu(centrino_model, cpu)->
- op_points[i].frequency;
- }
- if (failsafe)
- return per_cpu(centrino_model, cpu)->op_points[i-1].frequency;
- else
- return 0;
-}
-
-/* Return the current CPU frequency in kHz */
-static unsigned int get_cur_freq(unsigned int cpu)
-{
- unsigned l, h;
- unsigned clock_freq;
-
- rdmsr_on_cpu(cpu, MSR_IA32_PERF_STATUS, &l, &h);
- clock_freq = extract_clock(l, cpu, 0);
-
- if (unlikely(clock_freq == 0)) {
- /*
- * On some CPUs, we can see transient MSR values (which are
- * not present in _PSS), while CPU is doing some automatic
- * P-state transition (like TM2). Get the last freq set
- * in PERF_CTL.
- */
- rdmsr_on_cpu(cpu, MSR_IA32_PERF_CTL, &l, &h);
- clock_freq = extract_clock(l, cpu, 1);
- }
- return clock_freq;
-}
-
-
-static int centrino_cpu_init(struct cpufreq_policy *policy)
-{
- struct cpuinfo_x86 *cpu = &cpu_data(policy->cpu);
- unsigned freq;
- unsigned l, h;
- int ret;
- int i;
-
- /* Only Intel makes Enhanced Speedstep-capable CPUs */
- if (cpu->x86_vendor != X86_VENDOR_INTEL ||
- !cpu_has(cpu, X86_FEATURE_EST))
- return -ENODEV;
-
- if (cpu_has(cpu, X86_FEATURE_CONSTANT_TSC))
- centrino_driver.flags |= CPUFREQ_CONST_LOOPS;
-
- if (policy->cpu != 0)
- return -ENODEV;
-
- for (i = 0; i < N_IDS; i++)
- if (centrino_verify_cpu_id(cpu, &cpu_ids[i]))
- break;
-
- if (i != N_IDS)
- per_cpu(centrino_cpu, policy->cpu) = &cpu_ids[i];
-
- if (!per_cpu(centrino_cpu, policy->cpu)) {
- dprintk("found unsupported CPU with "
- "Enhanced SpeedStep: send /proc/cpuinfo to "
- MAINTAINER "\n");
- return -ENODEV;
- }
-
- if (centrino_cpu_init_table(policy)) {
- return -ENODEV;
- }
-
- /* Check to see if Enhanced SpeedStep is enabled, and try to
- enable it if not. */
- rdmsr(MSR_IA32_MISC_ENABLE, l, h);
-
- if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
- l |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
- dprintk("trying to enable Enhanced SpeedStep (%x)\n", l);
- wrmsr(MSR_IA32_MISC_ENABLE, l, h);
-
- /* check to see if it stuck */
- rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
- printk(KERN_INFO PFX
- "couldn't enable Enhanced SpeedStep\n");
- return -ENODEV;
- }
- }
-
- freq = get_cur_freq(policy->cpu);
- policy->cpuinfo.transition_latency = 10000;
- /* 10uS transition latency */
- policy->cur = freq;
-
- dprintk("centrino_cpu_init: cur=%dkHz\n", policy->cur);
-
- ret = cpufreq_frequency_table_cpuinfo(policy,
- per_cpu(centrino_model, policy->cpu)->op_points);
- if (ret)
- return (ret);
-
- cpufreq_frequency_table_get_attr(
- per_cpu(centrino_model, policy->cpu)->op_points, policy->cpu);
-
- return 0;
-}
-
-static int centrino_cpu_exit(struct cpufreq_policy *policy)
-{
- unsigned int cpu = policy->cpu;
-
- if (!per_cpu(centrino_model, cpu))
- return -ENODEV;
-
- cpufreq_frequency_table_put_attr(cpu);
-
- per_cpu(centrino_model, cpu) = NULL;
-
- return 0;
-}
-
-/**
- * centrino_verify - verifies a new CPUFreq policy
- * @policy: new policy
- *
- * Limit must be within this model's frequency range at least one
- * border included.
- */
-static int centrino_verify (struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy,
- per_cpu(centrino_model, policy->cpu)->op_points);
-}
-
-/**
- * centrino_setpolicy - set a new CPUFreq policy
- * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
- *
- * Sets a new CPUFreq policy.
- */
-static int centrino_target (struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate = 0;
- unsigned int msr, oldmsr = 0, h = 0, cpu = policy->cpu;
- struct cpufreq_freqs freqs;
- int retval = 0;
- unsigned int j, k, first_cpu, tmp;
- cpumask_var_t covered_cpus;
-
- if (unlikely(!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL)))
- return -ENOMEM;
-
- if (unlikely(per_cpu(centrino_model, cpu) == NULL)) {
- retval = -ENODEV;
- goto out;
- }
-
- if (unlikely(cpufreq_frequency_table_target(policy,
- per_cpu(centrino_model, cpu)->op_points,
- target_freq,
- relation,
- &newstate))) {
- retval = -EINVAL;
- goto out;
- }
-
- first_cpu = 1;
- for_each_cpu(j, policy->cpus) {
- int good_cpu;
-
- /* cpufreq holds the hotplug lock, so we are safe here */
- if (!cpu_online(j))
- continue;
-
- /*
- * Support for SMP systems.
- * Make sure we are running on CPU that wants to change freq
- */
- if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
- good_cpu = cpumask_any_and(policy->cpus,
- cpu_online_mask);
- else
- good_cpu = j;
-
- if (good_cpu >= nr_cpu_ids) {
- dprintk("couldn't limit to CPUs in this domain\n");
- retval = -EAGAIN;
- if (first_cpu) {
- /* We haven't started the transition yet. */
- goto out;
- }
- break;
- }
-
- msr = per_cpu(centrino_model, cpu)->op_points[newstate].index;
-
- if (first_cpu) {
- rdmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, &oldmsr, &h);
- if (msr == (oldmsr & 0xffff)) {
- dprintk("no change needed - msr was and needs "
- "to be %x\n", oldmsr);
- retval = 0;
- goto out;
- }
-
- freqs.old = extract_clock(oldmsr, cpu, 0);
- freqs.new = extract_clock(msr, cpu, 0);
-
- dprintk("target=%dkHz old=%d new=%d msr=%04x\n",
- target_freq, freqs.old, freqs.new, msr);
-
- for_each_cpu(k, policy->cpus) {
- if (!cpu_online(k))
- continue;
- freqs.cpu = k;
- cpufreq_notify_transition(&freqs,
- CPUFREQ_PRECHANGE);
- }
-
- first_cpu = 0;
- /* all but 16 LSB are reserved, treat them with care */
- oldmsr &= ~0xffff;
- msr &= 0xffff;
- oldmsr |= msr;
- }
-
- wrmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, oldmsr, h);
- if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
- break;
-
- cpumask_set_cpu(j, covered_cpus);
- }
-
- for_each_cpu(k, policy->cpus) {
- if (!cpu_online(k))
- continue;
- freqs.cpu = k;
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
-
- if (unlikely(retval)) {
- /*
- * We have failed halfway through the frequency change.
- * We have sent callbacks to policy->cpus and
- * MSRs have already been written on coverd_cpus.
- * Best effort undo..
- */
-
- for_each_cpu(j, covered_cpus)
- wrmsr_on_cpu(j, MSR_IA32_PERF_CTL, oldmsr, h);
-
- tmp = freqs.new;
- freqs.new = freqs.old;
- freqs.old = tmp;
- for_each_cpu(j, policy->cpus) {
- if (!cpu_online(j))
- continue;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
- }
- retval = 0;
-
-out:
- free_cpumask_var(covered_cpus);
- return retval;
-}
-
-static struct freq_attr* centrino_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver centrino_driver = {
- .name = "centrino", /* should be speedstep-centrino,
- but there's a 16 char limit */
- .init = centrino_cpu_init,
- .exit = centrino_cpu_exit,
- .verify = centrino_verify,
- .target = centrino_target,
- .get = get_cur_freq,
- .attr = centrino_attr,
- .owner = THIS_MODULE,
-};
-
-
-/**
- * centrino_init - initializes the Enhanced SpeedStep CPUFreq driver
- *
- * Initializes the Enhanced SpeedStep support. Returns -ENODEV on
- * unsupported devices, -ENOENT if there's no voltage table for this
- * particular CPU model, -EINVAL on problems during initiatization,
- * and zero on success.
- *
- * This is quite picky. Not only does the CPU have to advertise the
- * "est" flag in the cpuid capability flags, we look for a specific
- * CPU model and stepping, and we need to have the exact model name in
- * our voltage tables. That is, be paranoid about not releasing
- * someone's valuable magic smoke.
- */
-static int __init centrino_init(void)
-{
- struct cpuinfo_x86 *cpu = &cpu_data(0);
-
- if (!cpu_has(cpu, X86_FEATURE_EST))
- return -ENODEV;
-
- return cpufreq_register_driver(&centrino_driver);
-}
-
-static void __exit centrino_exit(void)
-{
- cpufreq_unregister_driver(&centrino_driver);
-}
-
-MODULE_AUTHOR ("Jeremy Fitzhardinge <jeremy@goop.org>");
-MODULE_DESCRIPTION ("Enhanced SpeedStep driver for Intel Pentium M processors.");
-MODULE_LICENSE ("GPL");
-
-late_initcall(centrino_init);
-module_exit(centrino_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
deleted file mode 100644
index 561758e9518..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ /dev/null
@@ -1,452 +0,0 @@
-/*
- * (C) 2001 Dave Jones, Arjan van de ven.
- * (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- * Based upon reverse engineered information, and on Intel documentation
- * for chipsets ICH2-M and ICH3-M.
- *
- * Many thanks to Ducrot Bruno for finding and fixing the last
- * "missing link" for ICH2-M/ICH3-M support, and to Thomas Winkler
- * for extensive testing.
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-
-/*********************************************************************
- * SPEEDSTEP - DEFINITIONS *
- *********************************************************************/
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/pci.h>
-#include <linux/sched.h>
-
-#include "speedstep-lib.h"
-
-
-/* speedstep_chipset:
- * It is necessary to know which chipset is used. As accesses to
- * this device occur at various places in this module, we need a
- * static struct pci_dev * pointing to that device.
- */
-static struct pci_dev *speedstep_chipset_dev;
-
-
-/* speedstep_processor
- */
-static enum speedstep_processor speedstep_processor;
-
-static u32 pmbase;
-
-/*
- * There are only two frequency states for each processor. Values
- * are in kHz for the time being.
- */
-static struct cpufreq_frequency_table speedstep_freqs[] = {
- {SPEEDSTEP_HIGH, 0},
- {SPEEDSTEP_LOW, 0},
- {0, CPUFREQ_TABLE_END},
-};
-
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "speedstep-ich", msg)
-
-
-/**
- * speedstep_find_register - read the PMBASE address
- *
- * Returns: -ENODEV if no register could be found
- */
-static int speedstep_find_register(void)
-{
- if (!speedstep_chipset_dev)
- return -ENODEV;
-
- /* get PMBASE */
- pci_read_config_dword(speedstep_chipset_dev, 0x40, &pmbase);
- if (!(pmbase & 0x01)) {
- printk(KERN_ERR "speedstep-ich: could not find speedstep register\n");
- return -ENODEV;
- }
-
- pmbase &= 0xFFFFFFFE;
- if (!pmbase) {
- printk(KERN_ERR "speedstep-ich: could not find speedstep register\n");
- return -ENODEV;
- }
-
- dprintk("pmbase is 0x%x\n", pmbase);
- return 0;
-}
-
-/**
- * speedstep_set_state - set the SpeedStep state
- * @state: new processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH)
- *
- * Tries to change the SpeedStep state. Can be called from
- * smp_call_function_single.
- */
-static void speedstep_set_state(unsigned int state)
-{
- u8 pm2_blk;
- u8 value;
- unsigned long flags;
-
- if (state > 0x1)
- return;
-
- /* Disable IRQs */
- local_irq_save(flags);
-
- /* read state */
- value = inb(pmbase + 0x50);
-
- dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value);
-
- /* write new state */
- value &= 0xFE;
- value |= state;
-
- dprintk("writing 0x%x to pmbase 0x%x + 0x50\n", value, pmbase);
-
- /* Disable bus master arbitration */
- pm2_blk = inb(pmbase + 0x20);
- pm2_blk |= 0x01;
- outb(pm2_blk, (pmbase + 0x20));
-
- /* Actual transition */
- outb(value, (pmbase + 0x50));
-
- /* Restore bus master arbitration */
- pm2_blk &= 0xfe;
- outb(pm2_blk, (pmbase + 0x20));
-
- /* check if transition was successful */
- value = inb(pmbase + 0x50);
-
- /* Enable IRQs */
- local_irq_restore(flags);
-
- dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value);
-
- if (state == (value & 0x1))
- dprintk("change to %u MHz succeeded\n",
- speedstep_get_frequency(speedstep_processor) / 1000);
- else
- printk(KERN_ERR "cpufreq: change failed - I/O error\n");
-
- return;
-}
-
-/* Wrapper for smp_call_function_single. */
-static void _speedstep_set_state(void *_state)
-{
- speedstep_set_state(*(unsigned int *)_state);
-}
-
-/**
- * speedstep_activate - activate SpeedStep control in the chipset
- *
- * Tries to activate the SpeedStep status and control registers.
- * Returns -EINVAL on an unsupported chipset, and zero on success.
- */
-static int speedstep_activate(void)
-{
- u16 value = 0;
-
- if (!speedstep_chipset_dev)
- return -EINVAL;
-
- pci_read_config_word(speedstep_chipset_dev, 0x00A0, &value);
- if (!(value & 0x08)) {
- value |= 0x08;
- dprintk("activating SpeedStep (TM) registers\n");
- pci_write_config_word(speedstep_chipset_dev, 0x00A0, value);
- }
-
- return 0;
-}
-
-
-/**
- * speedstep_detect_chipset - detect the Southbridge which contains SpeedStep logic
- *
- * Detects ICH2-M, ICH3-M and ICH4-M so far. The pci_dev points to
- * the LPC bridge / PM module which contains all power-management
- * functions. Returns the SPEEDSTEP_CHIPSET_-number for the detected
- * chipset, or zero on failure.
- */
-static unsigned int speedstep_detect_chipset(void)
-{
- speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_82801DB_12,
- PCI_ANY_ID, PCI_ANY_ID,
- NULL);
- if (speedstep_chipset_dev)
- return 4; /* 4-M */
-
- speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_82801CA_12,
- PCI_ANY_ID, PCI_ANY_ID,
- NULL);
- if (speedstep_chipset_dev)
- return 3; /* 3-M */
-
-
- speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_82801BA_10,
- PCI_ANY_ID, PCI_ANY_ID,
- NULL);
- if (speedstep_chipset_dev) {
- /* speedstep.c causes lockups on Dell Inspirons 8000 and
- * 8100 which use a pretty old revision of the 82815
- * host brige. Abort on these systems.
- */
- static struct pci_dev *hostbridge;
-
- hostbridge = pci_get_subsys(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_82815_MC,
- PCI_ANY_ID, PCI_ANY_ID,
- NULL);
-
- if (!hostbridge)
- return 2; /* 2-M */
-
- if (hostbridge->revision < 5) {
- dprintk("hostbridge does not support speedstep\n");
- speedstep_chipset_dev = NULL;
- pci_dev_put(hostbridge);
- return 0;
- }
-
- pci_dev_put(hostbridge);
- return 2; /* 2-M */
- }
-
- return 0;
-}
-
-static void get_freq_data(void *_speed)
-{
- unsigned int *speed = _speed;
-
- *speed = speedstep_get_frequency(speedstep_processor);
-}
-
-static unsigned int speedstep_get(unsigned int cpu)
-{
- unsigned int speed;
-
- /* You're supposed to ensure CPU is online. */
- if (smp_call_function_single(cpu, get_freq_data, &speed, 1) != 0)
- BUG();
-
- dprintk("detected %u kHz as current frequency\n", speed);
- return speed;
-}
-
-/**
- * speedstep_target - set a new CPUFreq policy
- * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
- *
- * Sets a new CPUFreq policy.
- */
-static int speedstep_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
-{
- unsigned int newstate = 0, policy_cpu;
- struct cpufreq_freqs freqs;
- int i;
-
- if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0],
- target_freq, relation, &newstate))
- return -EINVAL;
-
- policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
- freqs.old = speedstep_get(policy_cpu);
- freqs.new = speedstep_freqs[newstate].frequency;
- freqs.cpu = policy->cpu;
-
- dprintk("transiting from %u to %u kHz\n", freqs.old, freqs.new);
-
- /* no transition necessary */
- if (freqs.old == freqs.new)
- return 0;
-
- for_each_cpu(i, policy->cpus) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- }
-
- smp_call_function_single(policy_cpu, _speedstep_set_state, &newstate,
- true);
-
- for_each_cpu(i, policy->cpus) {
- freqs.cpu = i;
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- }
-
- return 0;
-}
-
-
-/**
- * speedstep_verify - verifies a new CPUFreq policy
- * @policy: new policy
- *
- * Limit must be within speedstep_low_freq and speedstep_high_freq, with
- * at least one border included.
- */
-static int speedstep_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]);
-}
-
-struct get_freqs {
- struct cpufreq_policy *policy;
- int ret;
-};
-
-static void get_freqs_on_cpu(void *_get_freqs)
-{
- struct get_freqs *get_freqs = _get_freqs;
-
- get_freqs->ret =
- speedstep_get_freqs(speedstep_processor,
- &speedstep_freqs[SPEEDSTEP_LOW].frequency,
- &speedstep_freqs[SPEEDSTEP_HIGH].frequency,
- &get_freqs->policy->cpuinfo.transition_latency,
- &speedstep_set_state);
-}
-
-static int speedstep_cpu_init(struct cpufreq_policy *policy)
-{
- int result;
- unsigned int policy_cpu, speed;
- struct get_freqs gf;
-
- /* only run on CPU to be set, or on its sibling */
-#ifdef CONFIG_SMP
- cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
-#endif
- policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
-
- /* detect low and high frequency and transition latency */
- gf.policy = policy;
- smp_call_function_single(policy_cpu, get_freqs_on_cpu, &gf, 1);
- if (gf.ret)
- return gf.ret;
-
- /* get current speed setting */
- speed = speedstep_get(policy_cpu);
- if (!speed)
- return -EIO;
-
- dprintk("currently at %s speed setting - %i MHz\n",
- (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency)
- ? "low" : "high",
- (speed / 1000));
-
- /* cpuinfo and default policy values */
- policy->cur = speed;
-
- result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs);
- if (result)
- return result;
-
- cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu);
-
- return 0;
-}
-
-
-static int speedstep_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-static struct freq_attr *speedstep_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-
-static struct cpufreq_driver speedstep_driver = {
- .name = "speedstep-ich",
- .verify = speedstep_verify,
- .target = speedstep_target,
- .init = speedstep_cpu_init,
- .exit = speedstep_cpu_exit,
- .get = speedstep_get,
- .owner = THIS_MODULE,
- .attr = speedstep_attr,
-};
-
-
-/**
- * speedstep_init - initializes the SpeedStep CPUFreq driver
- *
- * Initializes the SpeedStep support. Returns -ENODEV on unsupported
- * devices, -EINVAL on problems during initiatization, and zero on
- * success.
- */
-static int __init speedstep_init(void)
-{
- /* detect processor */
- speedstep_processor = speedstep_detect_processor();
- if (!speedstep_processor) {
- dprintk("Intel(R) SpeedStep(TM) capable processor "
- "not found\n");
- return -ENODEV;
- }
-
- /* detect chipset */
- if (!speedstep_detect_chipset()) {
- dprintk("Intel(R) SpeedStep(TM) for this chipset not "
- "(yet) available.\n");
- return -ENODEV;
- }
-
- /* activate speedstep support */
- if (speedstep_activate()) {
- pci_dev_put(speedstep_chipset_dev);
- return -EINVAL;
- }
-
- if (speedstep_find_register())
- return -ENODEV;
-
- return cpufreq_register_driver(&speedstep_driver);
-}
-
-
-/**
- * speedstep_exit - unregisters SpeedStep support
- *
- * Unregisters SpeedStep support.
- */
-static void __exit speedstep_exit(void)
-{
- pci_dev_put(speedstep_chipset_dev);
- cpufreq_unregister_driver(&speedstep_driver);
-}
-
-
-MODULE_AUTHOR("Dave Jones <davej@redhat.com>, "
- "Dominik Brodowski <linux@brodo.de>");
-MODULE_DESCRIPTION("Speedstep driver for Intel mobile processors on chipsets "
- "with ICH-M southbridges.");
-MODULE_LICENSE("GPL");
-
-module_init(speedstep_init);
-module_exit(speedstep_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
deleted file mode 100644
index a94ec6be69f..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ /dev/null
@@ -1,481 +0,0 @@
-/*
- * (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * Library for common functions for Intel SpeedStep v.1 and v.2 support
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-
-#include <asm/msr.h>
-#include <asm/tsc.h>
-#include "speedstep-lib.h"
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "speedstep-lib", msg)
-
-#define PFX "speedstep-lib: "
-
-#ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK
-static int relaxed_check;
-#else
-#define relaxed_check 0
-#endif
-
-/*********************************************************************
- * GET PROCESSOR CORE SPEED IN KHZ *
- *********************************************************************/
-
-static unsigned int pentium3_get_frequency(enum speedstep_processor processor)
-{
- /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */
- struct {
- unsigned int ratio; /* Frequency Multiplier (x10) */
- u8 bitmap; /* power on configuration bits
- [27, 25:22] (in MSR 0x2a) */
- } msr_decode_mult[] = {
- { 30, 0x01 },
- { 35, 0x05 },
- { 40, 0x02 },
- { 45, 0x06 },
- { 50, 0x00 },
- { 55, 0x04 },
- { 60, 0x0b },
- { 65, 0x0f },
- { 70, 0x09 },
- { 75, 0x0d },
- { 80, 0x0a },
- { 85, 0x26 },
- { 90, 0x20 },
- { 100, 0x2b },
- { 0, 0xff } /* error or unknown value */
- };
-
- /* PIII(-M) FSB settings: see table b1-b of 24547206.pdf */
- struct {
- unsigned int value; /* Front Side Bus speed in MHz */
- u8 bitmap; /* power on configuration bits [18: 19]
- (in MSR 0x2a) */
- } msr_decode_fsb[] = {
- { 66, 0x0 },
- { 100, 0x2 },
- { 133, 0x1 },
- { 0, 0xff}
- };
-
- u32 msr_lo, msr_tmp;
- int i = 0, j = 0;
-
- /* read MSR 0x2a - we only need the low 32 bits */
- rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
- dprintk("P3 - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp);
- msr_tmp = msr_lo;
-
- /* decode the FSB */
- msr_tmp &= 0x00c0000;
- msr_tmp >>= 18;
- while (msr_tmp != msr_decode_fsb[i].bitmap) {
- if (msr_decode_fsb[i].bitmap == 0xff)
- return 0;
- i++;
- }
-
- /* decode the multiplier */
- if (processor == SPEEDSTEP_CPU_PIII_C_EARLY) {
- dprintk("workaround for early PIIIs\n");
- msr_lo &= 0x03c00000;
- } else
- msr_lo &= 0x0bc00000;
- msr_lo >>= 22;
- while (msr_lo != msr_decode_mult[j].bitmap) {
- if (msr_decode_mult[j].bitmap == 0xff)
- return 0;
- j++;
- }
-
- dprintk("speed is %u\n",
- (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100));
-
- return msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100;
-}
-
-
-static unsigned int pentiumM_get_frequency(void)
-{
- u32 msr_lo, msr_tmp;
-
- rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
- dprintk("PM - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp);
-
- /* see table B-2 of 24547212.pdf */
- if (msr_lo & 0x00040000) {
- printk(KERN_DEBUG PFX "PM - invalid FSB: 0x%x 0x%x\n",
- msr_lo, msr_tmp);
- return 0;
- }
-
- msr_tmp = (msr_lo >> 22) & 0x1f;
- dprintk("bits 22-26 are 0x%x, speed is %u\n",
- msr_tmp, (msr_tmp * 100 * 1000));
-
- return msr_tmp * 100 * 1000;
-}
-
-static unsigned int pentium_core_get_frequency(void)
-{
- u32 fsb = 0;
- u32 msr_lo, msr_tmp;
- int ret;
-
- rdmsr(MSR_FSB_FREQ, msr_lo, msr_tmp);
- /* see table B-2 of 25366920.pdf */
- switch (msr_lo & 0x07) {
- case 5:
- fsb = 100000;
- break;
- case 1:
- fsb = 133333;
- break;
- case 3:
- fsb = 166667;
- break;
- case 2:
- fsb = 200000;
- break;
- case 0:
- fsb = 266667;
- break;
- case 4:
- fsb = 333333;
- break;
- default:
- printk(KERN_ERR "PCORE - MSR_FSB_FREQ undefined value");
- }
-
- rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
- dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n",
- msr_lo, msr_tmp);
-
- msr_tmp = (msr_lo >> 22) & 0x1f;
- dprintk("bits 22-26 are 0x%x, speed is %u\n",
- msr_tmp, (msr_tmp * fsb));
-
- ret = (msr_tmp * fsb);
- return ret;
-}
-
-
-static unsigned int pentium4_get_frequency(void)
-{
- struct cpuinfo_x86 *c = &boot_cpu_data;
- u32 msr_lo, msr_hi, mult;
- unsigned int fsb = 0;
- unsigned int ret;
- u8 fsb_code;
-
- /* Pentium 4 Model 0 and 1 do not have the Core Clock Frequency
- * to System Bus Frequency Ratio Field in the Processor Frequency
- * Configuration Register of the MSR. Therefore the current
- * frequency cannot be calculated and has to be measured.
- */
- if (c->x86_model < 2)
- return cpu_khz;
-
- rdmsr(0x2c, msr_lo, msr_hi);
-
- dprintk("P4 - MSR_EBC_FREQUENCY_ID: 0x%x 0x%x\n", msr_lo, msr_hi);
-
- /* decode the FSB: see IA-32 Intel (C) Architecture Software
- * Developer's Manual, Volume 3: System Prgramming Guide,
- * revision #12 in Table B-1: MSRs in the Pentium 4 and
- * Intel Xeon Processors, on page B-4 and B-5.
- */
- fsb_code = (msr_lo >> 16) & 0x7;
- switch (fsb_code) {
- case 0:
- fsb = 100 * 1000;
- break;
- case 1:
- fsb = 13333 * 10;
- break;
- case 2:
- fsb = 200 * 1000;
- break;
- }
-
- if (!fsb)
- printk(KERN_DEBUG PFX "couldn't detect FSB speed. "
- "Please send an e-mail to <linux@brodo.de>\n");
-
- /* Multiplier. */
- mult = msr_lo >> 24;
-
- dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n",
- fsb, mult, (fsb * mult));
-
- ret = (fsb * mult);
- return ret;
-}
-
-
-/* Warning: may get called from smp_call_function_single. */
-unsigned int speedstep_get_frequency(enum speedstep_processor processor)
-{
- switch (processor) {
- case SPEEDSTEP_CPU_PCORE:
- return pentium_core_get_frequency();
- case SPEEDSTEP_CPU_PM:
- return pentiumM_get_frequency();
- case SPEEDSTEP_CPU_P4D:
- case SPEEDSTEP_CPU_P4M:
- return pentium4_get_frequency();
- case SPEEDSTEP_CPU_PIII_T:
- case SPEEDSTEP_CPU_PIII_C:
- case SPEEDSTEP_CPU_PIII_C_EARLY:
- return pentium3_get_frequency(processor);
- default:
- return 0;
- };
- return 0;
-}
-EXPORT_SYMBOL_GPL(speedstep_get_frequency);
-
-
-/*********************************************************************
- * DETECT SPEEDSTEP-CAPABLE PROCESSOR *
- *********************************************************************/
-
-unsigned int speedstep_detect_processor(void)
-{
- struct cpuinfo_x86 *c = &cpu_data(0);
- u32 ebx, msr_lo, msr_hi;
-
- dprintk("x86: %x, model: %x\n", c->x86, c->x86_model);
-
- if ((c->x86_vendor != X86_VENDOR_INTEL) ||
- ((c->x86 != 6) && (c->x86 != 0xF)))
- return 0;
-
- if (c->x86 == 0xF) {
- /* Intel Mobile Pentium 4-M
- * or Intel Mobile Pentium 4 with 533 MHz FSB */
- if (c->x86_model != 2)
- return 0;
-
- ebx = cpuid_ebx(0x00000001);
- ebx &= 0x000000FF;
-
- dprintk("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask);
-
- switch (c->x86_mask) {
- case 4:
- /*
- * B-stepping [M-P4-M]
- * sample has ebx = 0x0f, production has 0x0e.
- */
- if ((ebx == 0x0e) || (ebx == 0x0f))
- return SPEEDSTEP_CPU_P4M;
- break;
- case 7:
- /*
- * C-stepping [M-P4-M]
- * needs to have ebx=0x0e, else it's a celeron:
- * cf. 25130917.pdf / page 7, footnote 5 even
- * though 25072120.pdf / page 7 doesn't say
- * samples are only of B-stepping...
- */
- if (ebx == 0x0e)
- return SPEEDSTEP_CPU_P4M;
- break;
- case 9:
- /*
- * D-stepping [M-P4-M or M-P4/533]
- *
- * this is totally strange: CPUID 0x0F29 is
- * used by M-P4-M, M-P4/533 and(!) Celeron CPUs.
- * The latter need to be sorted out as they don't
- * support speedstep.
- * Celerons with CPUID 0x0F29 may have either
- * ebx=0x8 or 0xf -- 25130917.pdf doesn't say anything
- * specific.
- * M-P4-Ms may have either ebx=0xe or 0xf [see above]
- * M-P4/533 have either ebx=0xe or 0xf. [25317607.pdf]
- * also, M-P4M HTs have ebx=0x8, too
- * For now, they are distinguished by the model_id
- * string
- */
- if ((ebx == 0x0e) ||
- (strstr(c->x86_model_id,
- "Mobile Intel(R) Pentium(R) 4") != NULL))
- return SPEEDSTEP_CPU_P4M;
- break;
- default:
- break;
- }
- return 0;
- }
-
- switch (c->x86_model) {
- case 0x0B: /* Intel PIII [Tualatin] */
- /* cpuid_ebx(1) is 0x04 for desktop PIII,
- * 0x06 for mobile PIII-M */
- ebx = cpuid_ebx(0x00000001);
- dprintk("ebx is %x\n", ebx);
-
- ebx &= 0x000000FF;
-
- if (ebx != 0x06)
- return 0;
-
- /* So far all PIII-M processors support SpeedStep. See
- * Intel's 24540640.pdf of June 2003
- */
- return SPEEDSTEP_CPU_PIII_T;
-
- case 0x08: /* Intel PIII [Coppermine] */
-
- /* all mobile PIII Coppermines have FSB 100 MHz
- * ==> sort out a few desktop PIIIs. */
- rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_hi);
- dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n",
- msr_lo, msr_hi);
- msr_lo &= 0x00c0000;
- if (msr_lo != 0x0080000)
- return 0;
-
- /*
- * If the processor is a mobile version,
- * platform ID has bit 50 set
- * it has SpeedStep technology if either
- * bit 56 or 57 is set
- */
- rdmsr(MSR_IA32_PLATFORM_ID, msr_lo, msr_hi);
- dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n",
- msr_lo, msr_hi);
- if ((msr_hi & (1<<18)) &&
- (relaxed_check ? 1 : (msr_hi & (3<<24)))) {
- if (c->x86_mask == 0x01) {
- dprintk("early PIII version\n");
- return SPEEDSTEP_CPU_PIII_C_EARLY;
- } else
- return SPEEDSTEP_CPU_PIII_C;
- }
-
- default:
- return 0;
- }
-}
-EXPORT_SYMBOL_GPL(speedstep_detect_processor);
-
-
-/*********************************************************************
- * DETECT SPEEDSTEP SPEEDS *
- *********************************************************************/
-
-unsigned int speedstep_get_freqs(enum speedstep_processor processor,
- unsigned int *low_speed,
- unsigned int *high_speed,
- unsigned int *transition_latency,
- void (*set_state) (unsigned int state))
-{
- unsigned int prev_speed;
- unsigned int ret = 0;
- unsigned long flags;
- struct timeval tv1, tv2;
-
- if ((!processor) || (!low_speed) || (!high_speed) || (!set_state))
- return -EINVAL;
-
- dprintk("trying to determine both speeds\n");
-
- /* get current speed */
- prev_speed = speedstep_get_frequency(processor);
- if (!prev_speed)
- return -EIO;
-
- dprintk("previous speed is %u\n", prev_speed);
-
- local_irq_save(flags);
-
- /* switch to low state */
- set_state(SPEEDSTEP_LOW);
- *low_speed = speedstep_get_frequency(processor);
- if (!*low_speed) {
- ret = -EIO;
- goto out;
- }
-
- dprintk("low speed is %u\n", *low_speed);
-
- /* start latency measurement */
- if (transition_latency)
- do_gettimeofday(&tv1);
-
- /* switch to high state */
- set_state(SPEEDSTEP_HIGH);
-
- /* end latency measurement */
- if (transition_latency)
- do_gettimeofday(&tv2);
-
- *high_speed = speedstep_get_frequency(processor);
- if (!*high_speed) {
- ret = -EIO;
- goto out;
- }
-
- dprintk("high speed is %u\n", *high_speed);
-
- if (*low_speed == *high_speed) {
- ret = -ENODEV;
- goto out;
- }
-
- /* switch to previous state, if necessary */
- if (*high_speed != prev_speed)
- set_state(SPEEDSTEP_LOW);
-
- if (transition_latency) {
- *transition_latency = (tv2.tv_sec - tv1.tv_sec) * USEC_PER_SEC +
- tv2.tv_usec - tv1.tv_usec;
- dprintk("transition latency is %u uSec\n", *transition_latency);
-
- /* convert uSec to nSec and add 20% for safety reasons */
- *transition_latency *= 1200;
-
- /* check if the latency measurement is too high or too low
- * and set it to a safe value (500uSec) in that case
- */
- if (*transition_latency > 10000000 ||
- *transition_latency < 50000) {
- printk(KERN_WARNING PFX "frequency transition "
- "measured seems out of range (%u "
- "nSec), falling back to a safe one of"
- "%u nSec.\n",
- *transition_latency, 500000);
- *transition_latency = 500000;
- }
- }
-
-out:
- local_irq_restore(flags);
- return ret;
-}
-EXPORT_SYMBOL_GPL(speedstep_get_freqs);
-
-#ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK
-module_param(relaxed_check, int, 0444);
-MODULE_PARM_DESC(relaxed_check,
- "Don't do all checks for speedstep capability.");
-#endif
-
-MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
-MODULE_DESCRIPTION("Library for Intel SpeedStep 1 or 2 cpufreq drivers.");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h
deleted file mode 100644
index 70d9cea1219..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- * Library for common functions for Intel SpeedStep v.1 and v.2 support
- *
- * BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
- */
-
-
-
-/* processors */
-enum speedstep_processor {
- SPEEDSTEP_CPU_PIII_C_EARLY = 0x00000001, /* Coppermine core */
- SPEEDSTEP_CPU_PIII_C = 0x00000002, /* Coppermine core */
- SPEEDSTEP_CPU_PIII_T = 0x00000003, /* Tualatin core */
- SPEEDSTEP_CPU_P4M = 0x00000004, /* P4-M */
-/* the following processors are not speedstep-capable and are not auto-detected
- * in speedstep_detect_processor(). However, their speed can be detected using
- * the speedstep_get_frequency() call. */
- SPEEDSTEP_CPU_PM = 0xFFFFFF03, /* Pentium M */
- SPEEDSTEP_CPU_P4D = 0xFFFFFF04, /* desktop P4 */
- SPEEDSTEP_CPU_PCORE = 0xFFFFFF05, /* Core */
-};
-
-/* speedstep states -- only two of them */
-
-#define SPEEDSTEP_HIGH 0x00000000
-#define SPEEDSTEP_LOW 0x00000001
-
-
-/* detect a speedstep-capable processor */
-extern enum speedstep_processor speedstep_detect_processor(void);
-
-/* detect the current speed (in khz) of the processor */
-extern unsigned int speedstep_get_frequency(enum speedstep_processor processor);
-
-
-/* detect the low and high speeds of the processor. The callback
- * set_state"'s first argument is either SPEEDSTEP_HIGH or
- * SPEEDSTEP_LOW; the second argument is zero so that no
- * cpufreq_notify_transition calls are initiated.
- */
-extern unsigned int speedstep_get_freqs(enum speedstep_processor processor,
- unsigned int *low_speed,
- unsigned int *high_speed,
- unsigned int *transition_latency,
- void (*set_state) (unsigned int state));
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
deleted file mode 100644
index 8abd869baab..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ /dev/null
@@ -1,467 +0,0 @@
-/*
- * Intel SpeedStep SMI driver.
- *
- * (C) 2003 Hiroshi Miura <miura@da-cha.org>
- *
- * Licensed under the terms of the GNU GPL License version 2.
- *
- */
-
-
-/*********************************************************************
- * SPEEDSTEP - DEFINITIONS *
- *********************************************************************/
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <asm/ist.h>
-
-#include "speedstep-lib.h"
-
-/* speedstep system management interface port/command.
- *
- * These parameters are got from IST-SMI BIOS call.
- * If user gives it, these are used.
- *
- */
-static int smi_port;
-static int smi_cmd;
-static unsigned int smi_sig;
-
-/* info about the processor */
-static enum speedstep_processor speedstep_processor;
-
-/*
- * There are only two frequency states for each processor. Values
- * are in kHz for the time being.
- */
-static struct cpufreq_frequency_table speedstep_freqs[] = {
- {SPEEDSTEP_HIGH, 0},
- {SPEEDSTEP_LOW, 0},
- {0, CPUFREQ_TABLE_END},
-};
-
-#define GET_SPEEDSTEP_OWNER 0
-#define GET_SPEEDSTEP_STATE 1
-#define SET_SPEEDSTEP_STATE 2
-#define GET_SPEEDSTEP_FREQS 4
-
-/* how often shall the SMI call be tried if it failed, e.g. because
- * of DMA activity going on? */
-#define SMI_TRIES 5
-
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
- "speedstep-smi", msg)
-
-/**
- * speedstep_smi_ownership
- */
-static int speedstep_smi_ownership(void)
-{
- u32 command, result, magic, dummy;
- u32 function = GET_SPEEDSTEP_OWNER;
- unsigned char magic_data[] = "Copyright (c) 1999 Intel Corporation";
-
- command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
- magic = virt_to_phys(magic_data);
-
- dprintk("trying to obtain ownership with command %x at port %x\n",
- command, smi_port);
-
- __asm__ __volatile__(
- "push %%ebp\n"
- "out %%al, (%%dx)\n"
- "pop %%ebp\n"
- : "=D" (result),
- "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy),
- "=S" (dummy)
- : "a" (command), "b" (function), "c" (0), "d" (smi_port),
- "D" (0), "S" (magic)
- : "memory"
- );
-
- dprintk("result is %x\n", result);
-
- return result;
-}
-
-/**
- * speedstep_smi_get_freqs - get SpeedStep preferred & current freq.
- * @low: the low frequency value is placed here
- * @high: the high frequency value is placed here
- *
- * Only available on later SpeedStep-enabled systems, returns false results or
- * even hangs [cf. bugme.osdl.org # 1422] on earlier systems. Empirical testing
- * shows that the latter occurs if !(ist_info.event & 0xFFFF).
- */
-static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high)
-{
- u32 command, result = 0, edi, high_mhz, low_mhz, dummy;
- u32 state = 0;
- u32 function = GET_SPEEDSTEP_FREQS;
-
- if (!(ist_info.event & 0xFFFF)) {
- dprintk("bug #1422 -- can't read freqs from BIOS\n");
- return -ENODEV;
- }
-
- command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
-
- dprintk("trying to determine frequencies with command %x at port %x\n",
- command, smi_port);
-
- __asm__ __volatile__(
- "push %%ebp\n"
- "out %%al, (%%dx)\n"
- "pop %%ebp"
- : "=a" (result),
- "=b" (high_mhz),
- "=c" (low_mhz),
- "=d" (state), "=D" (edi), "=S" (dummy)
- : "a" (command),
- "b" (function),
- "c" (state),
- "d" (smi_port), "S" (0), "D" (0)
- );
-
- dprintk("result %x, low_freq %u, high_freq %u\n",
- result, low_mhz, high_mhz);
-
- /* abort if results are obviously incorrect... */
- if ((high_mhz + low_mhz) < 600)
- return -EINVAL;
-
- *high = high_mhz * 1000;
- *low = low_mhz * 1000;
-
- return result;
-}
-
-/**
- * speedstep_get_state - set the SpeedStep state
- * @state: processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH)
- *
- */
-static int speedstep_get_state(void)
-{
- u32 function = GET_SPEEDSTEP_STATE;
- u32 result, state, edi, command, dummy;
-
- command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
-
- dprintk("trying to determine current setting with command %x "
- "at port %x\n", command, smi_port);
-
- __asm__ __volatile__(
- "push %%ebp\n"
- "out %%al, (%%dx)\n"
- "pop %%ebp\n"
- : "=a" (result),
- "=b" (state), "=D" (edi),
- "=c" (dummy), "=d" (dummy), "=S" (dummy)
- : "a" (command), "b" (function), "c" (0),
- "d" (smi_port), "S" (0), "D" (0)
- );
-
- dprintk("state is %x, result is %x\n", state, result);
-
- return state & 1;
-}
-
-
-/**
- * speedstep_set_state - set the SpeedStep state
- * @state: new processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH)
- *
- */
-static void speedstep_set_state(unsigned int state)
-{
- unsigned int result = 0, command, new_state, dummy;
- unsigned long flags;
- unsigned int function = SET_SPEEDSTEP_STATE;
- unsigned int retry = 0;
-
- if (state > 0x1)
- return;
-
- /* Disable IRQs */
- local_irq_save(flags);
-
- command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
-
- dprintk("trying to set frequency to state %u "
- "with command %x at port %x\n",
- state, command, smi_port);
-
- do {
- if (retry) {
- dprintk("retry %u, previous result %u, waiting...\n",
- retry, result);
- mdelay(retry * 50);
- }
- retry++;
- __asm__ __volatile__(
- "push %%ebp\n"
- "out %%al, (%%dx)\n"
- "pop %%ebp"
- : "=b" (new_state), "=D" (result),
- "=c" (dummy), "=a" (dummy),
- "=d" (dummy), "=S" (dummy)
- : "a" (command), "b" (function), "c" (state),
- "d" (smi_port), "S" (0), "D" (0)
- );
- } while ((new_state != state) && (retry <= SMI_TRIES));
-
- /* enable IRQs */
- local_irq_restore(flags);
-
- if (new_state == state)
- dprintk("change to %u MHz succeeded after %u tries "
- "with result %u\n",
- (speedstep_freqs[new_state].frequency / 1000),
- retry, result);
- else
- printk(KERN_ERR "cpufreq: change to state %u "
- "failed with new_state %u and result %u\n",
- state, new_state, result);
-
- return;
-}
-
-
-/**
- * speedstep_target - set a new CPUFreq policy
- * @policy: new policy
- * @target_freq: new freq
- * @relation:
- *
- * Sets a new CPUFreq policy/freq.
- */
-static int speedstep_target(struct cpufreq_policy *policy,
- unsigned int target_freq, unsigned int relation)
-{
- unsigned int newstate = 0;
- struct cpufreq_freqs freqs;
-
- if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0],
- target_freq, relation, &newstate))
- return -EINVAL;
-
- freqs.old = speedstep_freqs[speedstep_get_state()].frequency;
- freqs.new = speedstep_freqs[newstate].frequency;
- freqs.cpu = 0; /* speedstep.c is UP only driver */
-
- if (freqs.old == freqs.new)
- return 0;
-
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
- speedstep_set_state(newstate);
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
- return 0;
-}
-
-
-/**
- * speedstep_verify - verifies a new CPUFreq policy
- * @policy: new policy
- *
- * Limit must be within speedstep_low_freq and speedstep_high_freq, with
- * at least one border included.
- */
-static int speedstep_verify(struct cpufreq_policy *policy)
-{
- return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]);
-}
-
-
-static int speedstep_cpu_init(struct cpufreq_policy *policy)
-{
- int result;
- unsigned int speed, state;
- unsigned int *low, *high;
-
- /* capability check */
- if (policy->cpu != 0)
- return -ENODEV;
-
- result = speedstep_smi_ownership();
- if (result) {
- dprintk("fails in aquiring ownership of a SMI interface.\n");
- return -EINVAL;
- }
-
- /* detect low and high frequency */
- low = &speedstep_freqs[SPEEDSTEP_LOW].frequency;
- high = &speedstep_freqs[SPEEDSTEP_HIGH].frequency;
-
- result = speedstep_smi_get_freqs(low, high);
- if (result) {
- /* fall back to speedstep_lib.c dection mechanism:
- * try both states out */
- dprintk("could not detect low and high frequencies "
- "by SMI call.\n");
- result = speedstep_get_freqs(speedstep_processor,
- low, high,
- NULL,
- &speedstep_set_state);
-
- if (result) {
- dprintk("could not detect two different speeds"
- " -- aborting.\n");
- return result;
- } else
- dprintk("workaround worked.\n");
- }
-
- /* get current speed setting */
- state = speedstep_get_state();
- speed = speedstep_freqs[state].frequency;
-
- dprintk("currently at %s speed setting - %i MHz\n",
- (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency)
- ? "low" : "high",
- (speed / 1000));
-
- /* cpuinfo and default policy values */
- policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
- policy->cur = speed;
-
- result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs);
- if (result)
- return result;
-
- cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu);
-
- return 0;
-}
-
-static int speedstep_cpu_exit(struct cpufreq_policy *policy)
-{
- cpufreq_frequency_table_put_attr(policy->cpu);
- return 0;
-}
-
-static unsigned int speedstep_get(unsigned int cpu)
-{
- if (cpu)
- return -ENODEV;
- return speedstep_get_frequency(speedstep_processor);
-}
-
-
-static int speedstep_resume(struct cpufreq_policy *policy)
-{
- int result = speedstep_smi_ownership();
-
- if (result)
- dprintk("fails in re-aquiring ownership of a SMI interface.\n");
-
- return result;
-}
-
-static struct freq_attr *speedstep_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
- NULL,
-};
-
-static struct cpufreq_driver speedstep_driver = {
- .name = "speedstep-smi",
- .verify = speedstep_verify,
- .target = speedstep_target,
- .init = speedstep_cpu_init,
- .exit = speedstep_cpu_exit,
- .get = speedstep_get,
- .resume = speedstep_resume,
- .owner = THIS_MODULE,
- .attr = speedstep_attr,
-};
-
-/**
- * speedstep_init - initializes the SpeedStep CPUFreq driver
- *
- * Initializes the SpeedStep support. Returns -ENODEV on unsupported
- * BIOS, -EINVAL on problems during initiatization, and zero on
- * success.
- */
-static int __init speedstep_init(void)
-{
- speedstep_processor = speedstep_detect_processor();
-
- switch (speedstep_processor) {
- case SPEEDSTEP_CPU_PIII_T:
- case SPEEDSTEP_CPU_PIII_C:
- case SPEEDSTEP_CPU_PIII_C_EARLY:
- break;
- default:
- speedstep_processor = 0;
- }
-
- if (!speedstep_processor) {
- dprintk("No supported Intel CPU detected.\n");
- return -ENODEV;
- }
-
- dprintk("signature:0x%.8lx, command:0x%.8lx, "
- "event:0x%.8lx, perf_level:0x%.8lx.\n",
- ist_info.signature, ist_info.command,
- ist_info.event, ist_info.perf_level);
-
- /* Error if no IST-SMI BIOS or no PARM
- sig= 'ISGE' aka 'Intel Speedstep Gate E' */
- if ((ist_info.signature != 0x47534943) && (
- (smi_port == 0) || (smi_cmd == 0)))
- return -ENODEV;
-
- if (smi_sig == 1)
- smi_sig = 0x47534943;
- else
- smi_sig = ist_info.signature;
-
- /* setup smi_port from MODLULE_PARM or BIOS */
- if ((smi_port > 0xff) || (smi_port < 0))
- return -EINVAL;
- else if (smi_port == 0)
- smi_port = ist_info.command & 0xff;
-
- if ((smi_cmd > 0xff) || (smi_cmd < 0))
- return -EINVAL;
- else if (smi_cmd == 0)
- smi_cmd = (ist_info.command >> 16) & 0xff;
-
- return cpufreq_register_driver(&speedstep_driver);
-}
-
-
-/**
- * speedstep_exit - unregisters SpeedStep support
- *
- * Unregisters SpeedStep support.
- */
-static void __exit speedstep_exit(void)
-{
- cpufreq_unregister_driver(&speedstep_driver);
-}
-
-module_param(smi_port, int, 0444);
-module_param(smi_cmd, int, 0444);
-module_param(smi_sig, uint, 0444);
-
-MODULE_PARM_DESC(smi_port, "Override the BIOS-given IST port with this value "
- "-- Intel's default setting is 0xb2");
-MODULE_PARM_DESC(smi_cmd, "Override the BIOS-given IST command with this value "
- "-- Intel's default setting is 0x82");
-MODULE_PARM_DESC(smi_sig, "Set to 1 to fake the IST signature when using the "
- "SMI interface.");
-
-MODULE_AUTHOR("Hiroshi Miura");
-MODULE_DESCRIPTION("Speedstep driver for IST applet SMI interface.");
-MODULE_LICENSE("GPL");
-
-module_init(speedstep_init);
-module_exit(speedstep_exit);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d16c2c53d6b..df86bc8c859 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -276,14 +276,13 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
unsigned node;
int cpu = smp_processor_id();
- int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
- node = apicid_to_node[apicid];
+ node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE || !node_online(node)) {
/* reuse the value from init_cpu_to_node() */
node = cpu_to_node(cpu);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index ec2c19a7b8e..1ce1af2899d 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -304,8 +304,9 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
struct _cache_attr {
struct attribute attr;
- ssize_t (*show)(struct _cpuid4_info *, char *);
- ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+ ssize_t (*show)(struct _cpuid4_info *, char *, unsigned int);
+ ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count,
+ unsigned int);
};
#ifdef CONFIG_AMD_NB
@@ -400,7 +401,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
#define SHOW_CACHE_DISABLE(slot) \
static ssize_t \
-show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf) \
+show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf, \
+ unsigned int cpu) \
{ \
return show_cache_disable(this_leaf, buf, slot); \
}
@@ -512,7 +514,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
#define STORE_CACHE_DISABLE(slot) \
static ssize_t \
store_cache_disable_##slot(struct _cpuid4_info *this_leaf, \
- const char *buf, size_t count) \
+ const char *buf, size_t count, \
+ unsigned int cpu) \
{ \
return store_cache_disable(this_leaf, buf, count, slot); \
}
@@ -524,6 +527,39 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
show_cache_disable_1, store_cache_disable_1);
+static ssize_t
+show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu)
+{
+ if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return -EINVAL;
+
+ return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
+}
+
+static ssize_t
+store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count,
+ unsigned int cpu)
+{
+ unsigned long val;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return -EINVAL;
+
+ if (strict_strtoul(buf, 16, &val) < 0)
+ return -EINVAL;
+
+ if (amd_set_subcaches(cpu, val))
+ return -EINVAL;
+
+ return count;
+}
+
+static struct _cache_attr subcaches =
+ __ATTR(subcaches, 0644, show_subcaches, store_subcaches);
+
#else /* CONFIG_AMD_NB */
#define amd_init_l3_cache(x, y)
#endif /* CONFIG_AMD_NB */
@@ -532,9 +568,9 @@ static int
__cpuinit cpuid4_cache_lookup_regs(int index,
struct _cpuid4_info_regs *this_leaf)
{
- union _cpuid4_leaf_eax eax;
- union _cpuid4_leaf_ebx ebx;
- union _cpuid4_leaf_ecx ecx;
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
unsigned edx;
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
@@ -732,11 +768,11 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
struct cpuinfo_x86 *c = &cpu_data(cpu);
if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
- for_each_cpu(i, c->llc_shared_map) {
+ for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
if (!per_cpu(ici_cpuid4_info, i))
continue;
this_leaf = CPUID4_INFO_IDX(i, index);
- for_each_cpu(sibling, c->llc_shared_map) {
+ for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
if (!cpu_online(sibling))
continue;
set_bit(sibling, this_leaf->shared_cpu_map);
@@ -870,8 +906,8 @@ static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject);
#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(ici_index_kobject, x))[y]))
#define show_one_plus(file_name, object, val) \
-static ssize_t show_##file_name \
- (struct _cpuid4_info *this_leaf, char *buf) \
+static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \
+ unsigned int cpu) \
{ \
return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \
}
@@ -882,7 +918,8 @@ show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1);
show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1);
show_one_plus(number_of_sets, ecx.split.number_of_sets, 1);
-static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int cpu)
{
return sprintf(buf, "%luK\n", this_leaf->size / 1024);
}
@@ -906,17 +943,20 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
return n;
}
-static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf)
+static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf,
+ unsigned int cpu)
{
return show_shared_cpu_map_func(leaf, 0, buf);
}
-static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
+static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf,
+ unsigned int cpu)
{
return show_shared_cpu_map_func(leaf, 1, buf);
}
-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int cpu)
{
switch (this_leaf->eax.split.type) {
case CACHE_TYPE_DATA:
@@ -974,6 +1014,9 @@ static struct attribute ** __cpuinit amd_l3_attrs(void)
if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
n += 2;
+ if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ n += 1;
+
attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
if (attrs == NULL)
return attrs = default_attrs;
@@ -986,6 +1029,9 @@ static struct attribute ** __cpuinit amd_l3_attrs(void)
attrs[n++] = &cache_disable_1.attr;
}
+ if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ attrs[n++] = &subcaches.attr;
+
return attrs;
}
#endif
@@ -998,7 +1044,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
ret = fattr->show ?
fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
- buf) :
+ buf, this_leaf->cpu) :
0;
return ret;
}
@@ -1012,7 +1058,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
ret = fattr->store ?
fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
- buf, count) :
+ buf, count, this_leaf->cpu) :
0;
return ret;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 8209472b27a..83930deec3c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -106,24 +106,34 @@ int apei_write_mce(struct mce *m)
ssize_t apei_read_mce(struct mce *m, u64 *record_id)
{
struct cper_mce_record rcd;
- ssize_t len;
-
- len = erst_read_next(&rcd.hdr, sizeof(rcd));
- if (len <= 0)
- return len;
- /* Can not skip other records in storage via ERST unless clear them */
- else if (len != sizeof(rcd) ||
- uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) {
- if (printk_ratelimit())
- pr_warning(
- "MCE-APEI: Can not skip the unknown record in ERST");
- return -EIO;
- }
-
+ int rc, pos;
+
+ rc = erst_get_record_id_begin(&pos);
+ if (rc)
+ return rc;
+retry:
+ rc = erst_get_record_id_next(&pos, record_id);
+ if (rc)
+ goto out;
+ /* no more record */
+ if (*record_id == APEI_ERST_INVALID_RECORD_ID)
+ goto out;
+ rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd));
+ /* someone else has cleared the record, try next one */
+ if (rc == -ENOENT)
+ goto retry;
+ else if (rc < 0)
+ goto out;
+ /* try to skip other type records in storage */
+ else if (rc != sizeof(rcd) ||
+ uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE))
+ goto retry;
memcpy(m, &rcd.mce, sizeof(*m));
- *record_id = rcd.hdr.record_id;
+ rc = sizeof(*m);
+out:
+ erst_get_record_id_end();
- return sizeof(*m);
+ return rc;
}
/* Check whether there is record in ERST */
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index a7797197956..0ed633c5048 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -32,7 +32,7 @@ static void inject_mce(struct mce *m)
{
struct mce *i = &per_cpu(injectm, m->extcpu);
- /* Make sure noone reads partially written injectm */
+ /* Make sure no one reads partially written injectm */
i->finished = 0;
mb();
m->finished = 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d916183b7f9..3385ea26f68 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -21,6 +21,7 @@
#include <linux/percpu.h>
#include <linux/string.h>
#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/ctype.h>
#include <linux/sched.h>
@@ -881,7 +882,7 @@ reset:
* Check if the address reported by the CPU is in a format we can parse.
* It would be possible to add code for most other cases, but all would
* be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses upto page granuality for now.
+ * parser). So only support physical addresses up to page granuality for now.
*/
static int mce_usable_address(struct mce *m)
{
@@ -1625,7 +1626,7 @@ out:
static unsigned int mce_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_wait, wait);
- if (rcu_dereference_check_mce(mcelog.next))
+ if (rcu_access_index(mcelog.next))
return POLLIN | POLLRDNORM;
if (!mce_apei_read_done && apei_check_mce())
return POLLIN | POLLRDNORM;
@@ -1749,14 +1750,14 @@ static int mce_disable_error_reporting(void)
return 0;
}
-static int mce_suspend(struct sys_device *dev, pm_message_t state)
+static int mce_suspend(void)
{
return mce_disable_error_reporting();
}
-static int mce_shutdown(struct sys_device *dev)
+static void mce_shutdown(void)
{
- return mce_disable_error_reporting();
+ mce_disable_error_reporting();
}
/*
@@ -1764,14 +1765,18 @@ static int mce_shutdown(struct sys_device *dev)
* Only one CPU is active at this time, the others get re-added later using
* CPU hotplug:
*/
-static int mce_resume(struct sys_device *dev)
+static void mce_resume(void)
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
-
- return 0;
}
+static struct syscore_ops mce_syscore_ops = {
+ .suspend = mce_suspend,
+ .shutdown = mce_shutdown,
+ .resume = mce_resume,
+};
+
static void mce_cpu_restart(void *data)
{
del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1808,9 +1813,6 @@ static void mce_enable_ce(void *all)
}
static struct sysdev_class mce_sysclass = {
- .suspend = mce_suspend,
- .shutdown = mce_shutdown,
- .resume = mce_resume,
.name = "machinecheck",
};
@@ -2139,6 +2141,7 @@ static __init int mcheck_init_device(void)
return err;
}
+ register_syscore_ops(&mce_syscore_ops);
register_hotcpu_notifier(&mce_cpu_notifier);
misc_register(&mce_log_device);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 5bf2fac52ac..bb0adad3514 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -509,6 +509,7 @@ recurse:
out_free:
if (b) {
kobject_put(&b->kobj);
+ list_del(&b->miscj);
kfree(b);
}
return err;
@@ -527,15 +528,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
int i, err = 0;
struct threshold_bank *b = NULL;
char name[32];
-#ifdef CONFIG_SMP
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-#endif
sprintf(name, "threshold_bank%i", bank);
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = cpumask_first(c->llc_shared_map);
+ i = cpumask_first(cpu_llc_shared_mask(cpu));
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
@@ -555,7 +553,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (err)
goto out;
- cpumask_copy(b->cpus, c->llc_shared_map);
+ cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu));
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9da97..0f034460260 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
*/
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
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9f27228ceff..a71efcdbb09 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -1,6 +1,6 @@
/*
* This only handles 32bit MTRR on 32bit hosts. This is strictly wrong
- * because MTRRs can span upto 40 bits (36bits on most modern x86)
+ * because MTRRs can span up to 40 bits (36bits on most modern x86)
*/
#define DEBUG
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index bebabec5b44..929739a653d 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -45,6 +45,7 @@
#include <linux/cpu.h>
#include <linux/pci.h>
#include <linux/smp.h>
+#include <linux/syscore_ops.h>
#include <asm/processor.h>
#include <asm/e820.h>
@@ -292,14 +293,24 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
/*
* HACK!
- * We use this same function to initialize the mtrrs on boot.
- * The state of the boot cpu's mtrrs has been saved, and we want
- * to replicate across all the APs.
- * If we're doing that @reg is set to something special...
+ *
+ * We use this same function to initialize the mtrrs during boot,
+ * resume, runtime cpu online and on an explicit request to set a
+ * specific MTRR.
+ *
+ * During boot or suspend, the state of the boot cpu's mtrrs has been
+ * saved, and we want to replicate that across all the cpus that come
+ * online (either at the end of boot or resume or during a runtime cpu
+ * online). If we're doing that, @reg is set to something special and on
+ * this cpu we still do mtrr_if->set_all(). During boot/resume, this
+ * is unnecessary if at this point we are still on the cpu that started
+ * the boot/resume sequence. But there is no guarantee that we are still
+ * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be
+ * sure that we are in sync with everyone else.
*/
if (reg != ~0U)
mtrr_if->set(reg, base, size, type);
- else if (!mtrr_aps_delayed_init)
+ else
mtrr_if->set_all();
/* Wait for the others */
@@ -630,7 +641,7 @@ struct mtrr_value {
static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES];
-static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
+static int mtrr_save(void)
{
int i;
@@ -642,7 +653,7 @@ static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
return 0;
}
-static int mtrr_restore(struct sys_device *sysdev)
+static void mtrr_restore(void)
{
int i;
@@ -653,12 +664,11 @@ static int mtrr_restore(struct sys_device *sysdev)
mtrr_value[i].ltype);
}
}
- return 0;
}
-static struct sysdev_driver mtrr_sysdev_driver = {
+static struct syscore_ops mtrr_syscore_ops = {
.suspend = mtrr_save,
.resume = mtrr_restore,
};
@@ -839,7 +849,7 @@ static int __init mtrr_init_finialize(void)
* TBD: is there any system with such CPU which supports
* suspend/resume? If no, we should remove the code.
*/
- sysdev_driver_register(&cpu_sysdev_class, &mtrr_sysdev_driver);
+ register_syscore_ops(&mtrr_syscore_ops);
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9d977a2ea69..e638689279d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -30,6 +30,7 @@
#include <asm/stacktrace.h>
#include <asm/nmi.h>
#include <asm/compat.h>
+#include <asm/smp.h>
#if 0
#undef wrmsrl
@@ -93,6 +94,8 @@ struct amd_nb {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
+struct intel_percore;
+
#define MAX_LBR_ENTRIES 16
struct cpu_hw_events {
@@ -128,6 +131,13 @@ struct cpu_hw_events {
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
/*
+ * Intel percore register state.
+ * Coordinate shared resources between HT threads.
+ */
+ int percore_used; /* Used by this CPU? */
+ struct intel_percore *per_core;
+
+ /*
* AMD specific bits
*/
struct amd_nb *amd_nb;
@@ -166,7 +176,7 @@ struct cpu_hw_events {
/*
* Constraint on the Event code + UMask
*/
-#define PEBS_EVENT_CONSTRAINT(c, n) \
+#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
#define EVENT_CONSTRAINT_END \
@@ -175,6 +185,28 @@ struct cpu_hw_events {
#define for_each_event_constraint(e, c) \
for ((e) = (c); (e)->weight; (e)++)
+/*
+ * Extra registers for specific events.
+ * Some events need large masks and require external MSRs.
+ * Define a mapping to these extra registers.
+ */
+struct extra_reg {
+ unsigned int event;
+ unsigned int msr;
+ u64 config_mask;
+ u64 valid_mask;
+};
+
+#define EVENT_EXTRA_REG(e, ms, m, vm) { \
+ .event = (e), \
+ .msr = (ms), \
+ .config_mask = (m), \
+ .valid_mask = (vm), \
+ }
+#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \
+ EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm)
+#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0)
+
union perf_capabilities {
struct {
u64 lbr_format : 6;
@@ -219,6 +251,7 @@ struct x86_pmu {
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
struct event_constraint *event_constraints;
+ struct event_constraint *percore_constraints;
void (*quirks)(void);
int perfctr_second_write;
@@ -247,6 +280,11 @@ struct x86_pmu {
*/
unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
int lbr_nr; /* hardware stack size */
+
+ /*
+ * Extra registers for events
+ */
+ struct extra_reg *extra_regs;
};
static struct x86_pmu x86_pmu __read_mostly;
@@ -271,6 +309,10 @@ static u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
+static u64 __read_mostly hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX];
/*
* Propagate event elapsed time into the generic event.
@@ -298,7 +340,7 @@ x86_perf_event_update(struct perf_event *event)
*/
again:
prev_raw_count = local64_read(&hwc->prev_count);
- rdmsrl(hwc->event_base + idx, new_raw_count);
+ rdmsrl(hwc->event_base, new_raw_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
@@ -321,6 +363,49 @@ again:
return new_raw_count;
}
+/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */
+static inline int x86_pmu_addr_offset(int index)
+{
+ if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
+ return index << 1;
+ return index;
+}
+
+static inline unsigned int x86_pmu_config_addr(int index)
+{
+ return x86_pmu.eventsel + x86_pmu_addr_offset(index);
+}
+
+static inline unsigned int x86_pmu_event_addr(int index)
+{
+ return x86_pmu.perfctr + x86_pmu_addr_offset(index);
+}
+
+/*
+ * Find and validate any extra registers to set up.
+ */
+static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
+{
+ struct extra_reg *er;
+
+ event->hw.extra_reg = 0;
+ event->hw.extra_config = 0;
+
+ if (!x86_pmu.extra_regs)
+ return 0;
+
+ for (er = x86_pmu.extra_regs; er->msr; er++) {
+ if (er->event != (config & er->config_mask))
+ continue;
+ if (event->attr.config1 & ~er->valid_mask)
+ return -EINVAL;
+ event->hw.extra_reg = er->msr;
+ event->hw.extra_config = event->attr.config1;
+ break;
+ }
+ return 0;
+}
+
static atomic_t active_events;
static DEFINE_MUTEX(pmc_reserve_mutex);
@@ -331,12 +416,12 @@ static bool reserve_pmc_hardware(void)
int i;
for (i = 0; i < x86_pmu.num_counters; i++) {
- if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
+ if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
goto perfctr_fail;
}
for (i = 0; i < x86_pmu.num_counters; i++) {
- if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
+ if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
goto eventsel_fail;
}
@@ -344,13 +429,13 @@ static bool reserve_pmc_hardware(void)
eventsel_fail:
for (i--; i >= 0; i--)
- release_evntsel_nmi(x86_pmu.eventsel + i);
+ release_evntsel_nmi(x86_pmu_config_addr(i));
i = x86_pmu.num_counters;
perfctr_fail:
for (i--; i >= 0; i--)
- release_perfctr_nmi(x86_pmu.perfctr + i);
+ release_perfctr_nmi(x86_pmu_event_addr(i));
return false;
}
@@ -360,8 +445,8 @@ static void release_pmc_hardware(void)
int i;
for (i = 0; i < x86_pmu.num_counters; i++) {
- release_perfctr_nmi(x86_pmu.perfctr + i);
- release_evntsel_nmi(x86_pmu.eventsel + i);
+ release_perfctr_nmi(x86_pmu_event_addr(i));
+ release_evntsel_nmi(x86_pmu_config_addr(i));
}
}
@@ -382,7 +467,7 @@ static bool check_hw_exists(void)
* complain and bail.
*/
for (i = 0; i < x86_pmu.num_counters; i++) {
- reg = x86_pmu.eventsel + i;
+ reg = x86_pmu_config_addr(i);
ret = rdmsrl_safe(reg, &val);
if (ret)
goto msr_fail;
@@ -407,20 +492,25 @@ static bool check_hw_exists(void)
* that don't trap on the MSR access and always return 0s.
*/
val = 0xabcdUL;
- ret = checking_wrmsrl(x86_pmu.perfctr, val);
- ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+ ret = checking_wrmsrl(x86_pmu_event_addr(0), val);
+ ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new);
if (ret || val != val_new)
goto msr_fail;
return true;
bios_fail:
- printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+ /*
+ * We still allow the PMU driver to operate:
+ */
+ printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
- return false;
+
+ return true;
msr_fail:
printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+
return false;
}
@@ -442,8 +532,9 @@ static inline int x86_pmu_initialized(void)
}
static inline int
-set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
+set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
{
+ struct perf_event_attr *attr = &event->attr;
unsigned int cache_type, cache_op, cache_result;
u64 config, val;
@@ -470,8 +561,8 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
return -EINVAL;
hwc->config |= val;
-
- return 0;
+ attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result];
+ return x86_pmu_extra_regs(val, event);
}
static int x86_setup_perfctr(struct perf_event *event)
@@ -495,11 +586,15 @@ static int x86_setup_perfctr(struct perf_event *event)
return -EOPNOTSUPP;
}
+ /*
+ * Do not allow config1 (extended registers) to propagate,
+ * there's no sane user-space generalization yet:
+ */
if (attr->type == PERF_TYPE_RAW)
return 0;
if (attr->type == PERF_TYPE_HW_CACHE)
- return set_ext_hw_attr(hwc, attr);
+ return set_ext_hw_attr(hwc, event);
if (attr->config >= x86_pmu.max_events)
return -EINVAL;
@@ -518,8 +613,8 @@ static int x86_setup_perfctr(struct perf_event *event)
/*
* Branch tracing:
*/
- if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
- (hwc->sample_period == 1)) {
+ if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
+ !attr->freq && hwc->sample_period == 1) {
/* BTS is not supported by this architecture. */
if (!x86_pmu.bts_active)
return -EOPNOTSUPP;
@@ -617,11 +712,11 @@ static void x86_pmu_disable_all(void)
if (!test_bit(idx, cpuc->active_mask))
continue;
- rdmsrl(x86_pmu.eventsel + idx, val);
+ rdmsrl(x86_pmu_config_addr(idx), val);
if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
continue;
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(x86_pmu.eventsel + idx, val);
+ wrmsrl(x86_pmu_config_addr(idx), val);
}
}
@@ -642,21 +737,26 @@ static void x86_pmu_disable(struct pmu *pmu)
x86_pmu.disable_all();
}
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
+ u64 enable_mask)
+{
+ if (hwc->extra_reg)
+ wrmsrl(hwc->extra_reg, hwc->extra_config);
+ wrmsrl(hwc->config_base, hwc->config | enable_mask);
+}
+
static void x86_pmu_enable_all(int added)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- struct perf_event *event = cpuc->events[idx];
- u64 val;
+ struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask))
continue;
- val = event->hw.config;
- val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(x86_pmu.eventsel + idx, val);
+ __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
}
@@ -821,15 +921,10 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->event_base = 0;
} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- /*
- * We set it so that event_base + idx in wrmsr/rdmsr maps to
- * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
- */
- hwc->event_base =
- MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED);
} else {
- hwc->config_base = x86_pmu.eventsel;
- hwc->event_base = x86_pmu.perfctr;
+ hwc->config_base = x86_pmu_config_addr(hwc->idx);
+ hwc->event_base = x86_pmu_event_addr(hwc->idx);
}
}
@@ -915,17 +1010,11 @@ static void x86_pmu_enable(struct pmu *pmu)
x86_pmu.enable_all(added);
}
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
- u64 enable_mask)
-{
- wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask);
-}
-
static inline void x86_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base + hwc->idx, hwc->config);
+ wrmsrl(hwc->config_base, hwc->config);
}
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -978,7 +1067,7 @@ x86_perf_event_set_period(struct perf_event *event)
*/
local64_set(&hwc->prev_count, (u64)-left);
- wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
+ wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
/*
* Due to erratum on certan cpu we need
@@ -986,7 +1075,7 @@ x86_perf_event_set_period(struct perf_event *event)
* is updated properly
*/
if (x86_pmu.perfctr_second_write) {
- wrmsrl(hwc->event_base + idx,
+ wrmsrl(hwc->event_base,
(u64)(-left) & x86_pmu.cntval_mask);
}
@@ -1029,7 +1118,7 @@ static int x86_pmu_add(struct perf_event *event, int flags)
/*
* If group events scheduling transaction was started,
- * skip the schedulability test here, it will be peformed
+ * skip the schedulability test here, it will be performed
* at commit time (->commit_txn) as a whole
*/
if (cpuc->group_flag & PERF_EVENT_TXN)
@@ -1113,8 +1202,8 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
- rdmsrl(x86_pmu.perfctr + idx, pmc_count);
+ rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
+ rdmsrl(x86_pmu_event_addr(idx), pmc_count);
prev_left = per_cpu(pmc_prev_left[idx], cpu);
@@ -1199,6 +1288,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
cpuc = &__get_cpu_var(cpu_hw_events);
+ /*
+ * Some chipsets need to unmask the LVTPC in a particular spot
+ * inside the nmi handler. As a result, the unmasking was pushed
+ * into all the nmi handlers.
+ *
+ * This generic handler doesn't seem to have any issues where the
+ * unmasking occurs so it was left at the top.
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
if (!test_bit(idx, cpuc->active_mask)) {
/*
@@ -1285,8 +1384,6 @@ perf_event_nmi_handler(struct notifier_block *self,
return NOTIFY_DONE;
}
- apic_write(APIC_LVTPC, APIC_DM_NMI);
-
handled = x86_pmu.handle_irq(args->regs);
if (!handled)
return NOTIFY_DONE;
@@ -1389,7 +1486,7 @@ static void __init pmu_check_apic(void)
pr_info("no hardware sampling interrupt available.\n");
}
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
{
struct event_constraint *c;
int err;
@@ -1608,7 +1705,7 @@ out:
return ret;
}
-int x86_pmu_event_init(struct perf_event *event)
+static int x86_pmu_event_init(struct perf_event *event)
{
struct pmu *tmp;
int err;
@@ -1710,7 +1807,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_store(entry, regs->ip);
- dump_trace(NULL, regs, NULL, &backtrace_ops, entry);
+ dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 67e2202a603..cf4e369cea6 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
- [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */
+ [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -127,6 +127,11 @@ static int amd_pmu_hw_config(struct perf_event *event)
/*
* AMD64 events are detected based on their event codes.
*/
+static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
+{
+ return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
+}
+
static inline int amd_is_nb_event(struct hw_perf_event *hwc)
{
return (hwc->config & 0xe0) == 0xe0;
@@ -385,13 +390,195 @@ static __initconst const struct x86_pmu amd_pmu = {
.cpu_dead = amd_pmu_cpu_dead,
};
+/* AMD Family 15h */
+
+#define AMD_EVENT_TYPE_MASK 0x000000F0ULL
+
+#define AMD_EVENT_FP 0x00000000ULL ... 0x00000010ULL
+#define AMD_EVENT_LS 0x00000020ULL ... 0x00000030ULL
+#define AMD_EVENT_DC 0x00000040ULL ... 0x00000050ULL
+#define AMD_EVENT_CU 0x00000060ULL ... 0x00000070ULL
+#define AMD_EVENT_IC_DE 0x00000080ULL ... 0x00000090ULL
+#define AMD_EVENT_EX_LS 0x000000C0ULL
+#define AMD_EVENT_DE 0x000000D0ULL
+#define AMD_EVENT_NB 0x000000E0ULL ... 0x000000F0ULL
+
+/*
+ * AMD family 15h event code/PMC mappings:
+ *
+ * type = event_code & 0x0F0:
+ *
+ * 0x000 FP PERF_CTL[5:3]
+ * 0x010 FP PERF_CTL[5:3]
+ * 0x020 LS PERF_CTL[5:0]
+ * 0x030 LS PERF_CTL[5:0]
+ * 0x040 DC PERF_CTL[5:0]
+ * 0x050 DC PERF_CTL[5:0]
+ * 0x060 CU PERF_CTL[2:0]
+ * 0x070 CU PERF_CTL[2:0]
+ * 0x080 IC/DE PERF_CTL[2:0]
+ * 0x090 IC/DE PERF_CTL[2:0]
+ * 0x0A0 ---
+ * 0x0B0 ---
+ * 0x0C0 EX/LS PERF_CTL[5:0]
+ * 0x0D0 DE PERF_CTL[2:0]
+ * 0x0E0 NB NB_PERF_CTL[3:0]
+ * 0x0F0 NB NB_PERF_CTL[3:0]
+ *
+ * Exceptions:
+ *
+ * 0x000 FP PERF_CTL[3], PERF_CTL[5:3] (*)
+ * 0x003 FP PERF_CTL[3]
+ * 0x004 FP PERF_CTL[3], PERF_CTL[5:3] (*)
+ * 0x00B FP PERF_CTL[3]
+ * 0x00D FP PERF_CTL[3]
+ * 0x023 DE PERF_CTL[2:0]
+ * 0x02D LS PERF_CTL[3]
+ * 0x02E LS PERF_CTL[3,0]
+ * 0x043 CU PERF_CTL[2:0]
+ * 0x045 CU PERF_CTL[2:0]
+ * 0x046 CU PERF_CTL[2:0]
+ * 0x054 CU PERF_CTL[2:0]
+ * 0x055 CU PERF_CTL[2:0]
+ * 0x08F IC PERF_CTL[0]
+ * 0x187 DE PERF_CTL[0]
+ * 0x188 DE PERF_CTL[0]
+ * 0x0DB EX PERF_CTL[5:0]
+ * 0x0DC LS PERF_CTL[5:0]
+ * 0x0DD LS PERF_CTL[5:0]
+ * 0x0DE LS PERF_CTL[5:0]
+ * 0x0DF LS PERF_CTL[5:0]
+ * 0x1D6 EX PERF_CTL[5:0]
+ * 0x1D8 EX PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
+ */
+
+static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0);
+static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0);
+static struct event_constraint amd_f15_PMC3 = EVENT_CONSTRAINT(0, 0x08, 0);
+static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0);
+static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
+static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
+
+static struct event_constraint *
+amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned int event_code = amd_get_event_code(hwc);
+
+ switch (event_code & AMD_EVENT_TYPE_MASK) {
+ case AMD_EVENT_FP:
+ switch (event_code) {
+ case 0x000:
+ if (!(hwc->config & 0x0000F000ULL))
+ break;
+ if (!(hwc->config & 0x00000F00ULL))
+ break;
+ return &amd_f15_PMC3;
+ case 0x004:
+ if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+ break;
+ return &amd_f15_PMC3;
+ case 0x003:
+ case 0x00B:
+ case 0x00D:
+ return &amd_f15_PMC3;
+ }
+ return &amd_f15_PMC53;
+ case AMD_EVENT_LS:
+ case AMD_EVENT_DC:
+ case AMD_EVENT_EX_LS:
+ switch (event_code) {
+ case 0x023:
+ case 0x043:
+ case 0x045:
+ case 0x046:
+ case 0x054:
+ case 0x055:
+ return &amd_f15_PMC20;
+ case 0x02D:
+ return &amd_f15_PMC3;
+ case 0x02E:
+ return &amd_f15_PMC30;
+ default:
+ return &amd_f15_PMC50;
+ }
+ case AMD_EVENT_CU:
+ case AMD_EVENT_IC_DE:
+ case AMD_EVENT_DE:
+ switch (event_code) {
+ case 0x08F:
+ case 0x187:
+ case 0x188:
+ return &amd_f15_PMC0;
+ case 0x0DB ... 0x0DF:
+ case 0x1D6:
+ case 0x1D8:
+ return &amd_f15_PMC50;
+ default:
+ return &amd_f15_PMC20;
+ }
+ case AMD_EVENT_NB:
+ /* not yet implemented */
+ return &emptyconstraint;
+ default:
+ return &emptyconstraint;
+ }
+}
+
+static __initconst const struct x86_pmu amd_pmu_f15h = {
+ .name = "AMD Family 15h",
+ .handle_irq = x86_pmu_handle_irq,
+ .disable_all = x86_pmu_disable_all,
+ .enable_all = x86_pmu_enable_all,
+ .enable = x86_pmu_enable_event,
+ .disable = x86_pmu_disable_event,
+ .hw_config = amd_pmu_hw_config,
+ .schedule_events = x86_schedule_events,
+ .eventsel = MSR_F15H_PERF_CTL,
+ .perfctr = MSR_F15H_PERF_CTR,
+ .event_map = amd_pmu_event_map,
+ .max_events = ARRAY_SIZE(amd_perfmon_event_map),
+ .num_counters = 6,
+ .cntval_bits = 48,
+ .cntval_mask = (1ULL << 48) - 1,
+ .apic = 1,
+ /* use highest bit to detect overflow */
+ .max_period = (1ULL << 47) - 1,
+ .get_event_constraints = amd_get_event_constraints_f15h,
+ /* nortbridge counters not yet implemented: */
+#if 0
+ .put_event_constraints = amd_put_event_constraints,
+
+ .cpu_prepare = amd_pmu_cpu_prepare,
+ .cpu_starting = amd_pmu_cpu_starting,
+ .cpu_dead = amd_pmu_cpu_dead,
+#endif
+};
+
static __init int amd_pmu_init(void)
{
/* Performance-monitoring supported from K7 and later: */
if (boot_cpu_data.x86 < 6)
return -ENODEV;
- x86_pmu = amd_pmu;
+ /*
+ * If core performance counter extensions exists, it must be
+ * family 15h, otherwise fail. See x86_pmu_addr_offset().
+ */
+ switch (boot_cpu_data.x86) {
+ case 0x15:
+ if (!cpu_has_perfctr_core)
+ return -ENODEV;
+ x86_pmu = amd_pmu_f15h;
+ break;
+ default:
+ if (cpu_has_perfctr_core)
+ return -ENODEV;
+ x86_pmu = amd_pmu;
+ break;
+ }
/* Events are common for all AMDs */
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 008835c1d79..447a28de6f0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1,9 +1,31 @@
#ifdef CONFIG_CPU_SUP_INTEL
+#define MAX_EXTRA_REGS 2
+
+/*
+ * Per register state.
+ */
+struct er_account {
+ int ref; /* reference count */
+ unsigned int extra_reg; /* extra MSR number */
+ u64 extra_config; /* extra MSR config */
+};
+
+/*
+ * Per core state
+ * This used to coordinate shared registers for HT threads.
+ */
+struct intel_percore {
+ raw_spinlock_t lock; /* protect structure */
+ struct er_account regs[MAX_EXTRA_REGS];
+ int refcnt; /* number of threads */
+ unsigned core_id;
+};
+
/*
* Intel PerfMon, used on Core and later.
*/
-static const u64 intel_perfmon_event_map[] =
+static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x003c,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
@@ -64,6 +86,18 @@ static struct event_constraint intel_nehalem_event_constraints[] =
EVENT_CONSTRAINT_END
};
+static struct extra_reg intel_nehalem_extra_regs[] =
+{
+ INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+ EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_nehalem_percore_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0xb7, 0),
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_westmere_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -76,6 +110,33 @@ static struct event_constraint intel_westmere_event_constraints[] =
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_snb_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
+ INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */
+ INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
+ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_westmere_extra_regs[] =
+{
+ INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+ INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff),
+ EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_westmere_percore_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0xb7, 0),
+ INTEL_EVENT_CONSTRAINT(0xbb, 0),
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_gen_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -89,6 +150,103 @@ static u64 intel_pmu_event_map(int hw_event)
return intel_perfmon_event_map[hw_event];
}
+static __initconst const u64 snb_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPLACEMENT */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES */
+ [ C(RESULT_MISS) ] = 0x0851, /* L1D.ALL_M_REPLACEMENT */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x024e, /* HW_PRE_REQ.DL1_MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0280, /* ICACHE.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_WRITE) ] = {
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_PREFETCH) ] = {
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */
+ [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */
+ [ C(RESULT_MISS) ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT */
+ [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
static __initconst const u64 westmere_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -124,16 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
- [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
+ /*
+ * Use RFO, not WRITEBACK, because a write miss would typically occur
+ * on RFO.
+ */
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
- [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
- [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -180,6 +348,59 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
};
+/*
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
+ */
+
+#define NHM_DMND_DATA_RD (1 << 0)
+#define NHM_DMND_RFO (1 << 1)
+#define NHM_DMND_IFETCH (1 << 2)
+#define NHM_DMND_WB (1 << 3)
+#define NHM_PF_DATA_RD (1 << 4)
+#define NHM_PF_DATA_RFO (1 << 5)
+#define NHM_PF_IFETCH (1 << 6)
+#define NHM_OFFCORE_OTHER (1 << 7)
+#define NHM_UNCORE_HIT (1 << 8)
+#define NHM_OTHER_CORE_HIT_SNP (1 << 9)
+#define NHM_OTHER_CORE_HITM (1 << 10)
+ /* reserved */
+#define NHM_REMOTE_CACHE_FWD (1 << 12)
+#define NHM_REMOTE_DRAM (1 << 13)
+#define NHM_LOCAL_DRAM (1 << 14)
+#define NHM_NON_DRAM (1 << 15)
+
+#define NHM_ALL_DRAM (NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+
+#define NHM_DMND_READ (NHM_DMND_DATA_RD)
+#define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB)
+#define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
+
+#define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
+#define NHM_L3_MISS (NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS)
+
+static __initconst const u64 nehalem_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_L3_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_L3_MISS,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
+ },
+ }
+};
+
static __initconst const u64 nehalem_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -187,12 +408,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
{
[ C(L1D) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
- [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
- [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
@@ -215,16 +436,26 @@ static __initconst const u64 nehalem_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
- [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
+ /*
+ * Use RFO, not WRITEBACK, because a write miss would typically occur
+ * on RFO.
+ */
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
- [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
- [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -691,8 +922,8 @@ static void intel_pmu_reset(void)
printk("clearing PMU state on CPU#%d\n", smp_processor_id());
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
- checking_wrmsrl(x86_pmu.perfctr + idx, 0ull);
+ checking_wrmsrl(x86_pmu_config_addr(idx), 0ull);
+ checking_wrmsrl(x86_pmu_event_addr(idx), 0ull);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
@@ -719,6 +950,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
cpuc = &__get_cpu_var(cpu_hw_events);
+ /*
+ * Some chipsets need to unmask the LVTPC in a particular spot
+ * inside the nmi handler. As a result, the unmasking was pushed
+ * into all the nmi handlers.
+ *
+ * This handler doesn't seem to have any issues with the unmasking
+ * so it was left at the top.
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
status = intel_pmu_get_status();
@@ -784,6 +1025,9 @@ intel_bts_constraints(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
unsigned int hw_event, bts_event;
+ if (event->attr.freq)
+ return NULL;
+
hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
@@ -794,6 +1038,67 @@ intel_bts_constraints(struct perf_event *event)
}
static struct event_constraint *
+intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT;
+ struct event_constraint *c;
+ struct intel_percore *pc;
+ struct er_account *era;
+ int i;
+ int free_slot;
+ int found;
+
+ if (!x86_pmu.percore_constraints || hwc->extra_alloc)
+ return NULL;
+
+ for (c = x86_pmu.percore_constraints; c->cmask; c++) {
+ if (e != c->code)
+ continue;
+
+ /*
+ * Allocate resource per core.
+ */
+ pc = cpuc->per_core;
+ if (!pc)
+ break;
+ c = &emptyconstraint;
+ raw_spin_lock(&pc->lock);
+ free_slot = -1;
+ found = 0;
+ for (i = 0; i < MAX_EXTRA_REGS; i++) {
+ era = &pc->regs[i];
+ if (era->ref > 0 && hwc->extra_reg == era->extra_reg) {
+ /* Allow sharing same config */
+ if (hwc->extra_config == era->extra_config) {
+ era->ref++;
+ cpuc->percore_used = 1;
+ hwc->extra_alloc = 1;
+ c = NULL;
+ }
+ /* else conflict */
+ found = 1;
+ break;
+ } else if (era->ref == 0 && free_slot == -1)
+ free_slot = i;
+ }
+ if (!found && free_slot != -1) {
+ era = &pc->regs[free_slot];
+ era->ref = 1;
+ era->extra_reg = hwc->extra_reg;
+ era->extra_config = hwc->extra_config;
+ cpuc->percore_used = 1;
+ hwc->extra_alloc = 1;
+ c = NULL;
+ }
+ raw_spin_unlock(&pc->lock);
+ return c;
+ }
+
+ return NULL;
+}
+
+static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
{
struct event_constraint *c;
@@ -806,9 +1111,51 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
if (c)
return c;
+ c = intel_percore_constraints(cpuc, event);
+ if (c)
+ return c;
+
return x86_get_event_constraints(cpuc, event);
}
+static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
+ struct perf_event *event)
+{
+ struct extra_reg *er;
+ struct intel_percore *pc;
+ struct er_account *era;
+ struct hw_perf_event *hwc = &event->hw;
+ int i, allref;
+
+ if (!cpuc->percore_used)
+ return;
+
+ for (er = x86_pmu.extra_regs; er->msr; er++) {
+ if (er->event != (hwc->config & er->config_mask))
+ continue;
+
+ pc = cpuc->per_core;
+ raw_spin_lock(&pc->lock);
+ for (i = 0; i < MAX_EXTRA_REGS; i++) {
+ era = &pc->regs[i];
+ if (era->ref > 0 &&
+ era->extra_config == hwc->extra_config &&
+ era->extra_reg == er->msr) {
+ era->ref--;
+ hwc->extra_alloc = 0;
+ break;
+ }
+ }
+ allref = 0;
+ for (i = 0; i < MAX_EXTRA_REGS; i++)
+ allref += pc->regs[i].ref;
+ if (allref == 0)
+ cpuc->percore_used = 0;
+ raw_spin_unlock(&pc->lock);
+ break;
+ }
+}
+
static int intel_pmu_hw_config(struct perf_event *event)
{
int ret = x86_pmu_hw_config(event);
@@ -880,20 +1227,67 @@ static __initconst const struct x86_pmu core_pmu = {
*/
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
+ .put_event_constraints = intel_put_event_constraints,
.event_constraints = intel_core_event_constraints,
};
+static int intel_pmu_cpu_prepare(int cpu)
+{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+ if (!cpu_has_ht_siblings())
+ return NOTIFY_OK;
+
+ cpuc->per_core = kzalloc_node(sizeof(struct intel_percore),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!cpuc->per_core)
+ return NOTIFY_BAD;
+
+ raw_spin_lock_init(&cpuc->per_core->lock);
+ cpuc->per_core->core_id = -1;
+ return NOTIFY_OK;
+}
+
static void intel_pmu_cpu_starting(int cpu)
{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ int core_id = topology_core_id(cpu);
+ int i;
+
init_debug_store_on_cpu(cpu);
/*
* Deal with CPUs that don't clear their LBRs on power-up.
*/
intel_pmu_lbr_reset();
+
+ if (!cpu_has_ht_siblings())
+ return;
+
+ for_each_cpu(i, topology_thread_cpumask(cpu)) {
+ struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core;
+
+ if (pc && pc->core_id == core_id) {
+ kfree(cpuc->per_core);
+ cpuc->per_core = pc;
+ break;
+ }
+ }
+
+ cpuc->per_core->core_id = core_id;
+ cpuc->per_core->refcnt++;
}
static void intel_pmu_cpu_dying(int cpu)
{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ struct intel_percore *pc = cpuc->per_core;
+
+ if (pc) {
+ if (pc->core_id == -1 || --pc->refcnt == 0)
+ kfree(pc);
+ cpuc->per_core = NULL;
+ }
+
fini_debug_store_on_cpu(cpu);
}
@@ -918,7 +1312,9 @@ static __initconst const struct x86_pmu intel_pmu = {
*/
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
+ .put_event_constraints = intel_put_event_constraints,
+ .cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
};
@@ -939,7 +1335,7 @@ static void intel_clovertown_quirks(void)
* AJ106 could possibly be worked around by not allowing LBR
* usage from PEBS, including the fixup.
* AJ68 could possibly be worked around by always programming
- * a pebs_event_reset[0] value and coping with the lost events.
+ * a pebs_event_reset[0] value and coping with the lost events.
*
* But taken together it might just make sense to not enable PEBS on
* these chips.
@@ -1024,6 +1420,7 @@ static __init int intel_pmu_init(void)
intel_pmu_lbr_init_core();
x86_pmu.event_constraints = intel_core2_event_constraints;
+ x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints;
pr_cont("Core2 events, ");
break;
@@ -1032,11 +1429,28 @@ static __init int intel_pmu_init(void)
case 46: /* 45 nm nehalem-ex, "Beckton" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_nehalem_event_constraints;
+ x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
+ x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+ x86_pmu.extra_regs = intel_nehalem_extra_regs;
+
+ if (ebx & 0x40) {
+ /*
+ * Erratum AAJ80 detected, we work it around by using
+ * the BR_MISP_EXEC.ANY event. This will over-count
+ * branch-misses, but it's still much better than the
+ * architectural event which is often completely bogus:
+ */
+ intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+
+ pr_cont("erratum AAJ80 worked around, ");
+ }
pr_cont("Nehalem events, ");
break;
@@ -1047,21 +1461,39 @@ static __init int intel_pmu_init(void)
intel_pmu_lbr_init_atom();
x86_pmu.event_constraints = intel_gen_event_constraints;
+ x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
pr_cont("Atom events, ");
break;
case 37: /* 32 nm nehalem, "Clarkdale" */
case 44: /* 32 nm nehalem, "Gulftown" */
+ case 47: /* 32 nm Xeon E7 */
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_westmere_event_constraints;
+ x86_pmu.percore_constraints = intel_westmere_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+ x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_westmere_extra_regs;
pr_cont("Westmere events, ");
break;
+ case 42: /* SandyBridge */
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ intel_pmu_lbr_init_nhm();
+
+ x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.pebs_constraints = intel_snb_pebs_events;
+ pr_cont("SandyBridge events, ");
+ break;
+
default:
/*
* default constraints for v2 and up
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index b7dcd9f2b8a..bab491b8ee2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -361,30 +361,70 @@ static int intel_pmu_drain_bts_buffer(void)
/*
* PEBS
*/
+static struct event_constraint intel_core2_pebs_event_constraints[] = {
+ INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+ INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_atom_pebs_event_constraints[] = {
+ INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
-static struct event_constraint intel_core_pebs_events[] = {
- PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
- PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
- PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
- PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
- PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
- PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
- PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
+static struct event_constraint intel_nehalem_pebs_event_constraints[] = {
+ INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
+ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+ INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_nehalem_pebs_events[] = {
- PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
- PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
- PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
- PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
- PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
- PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
- PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
+static struct event_constraint intel_westmere_pebs_event_constraints[] = {
+ INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_snb_pebs_events[] = {
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
+ INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
+ INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
+ INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
+ INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
+ INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
+ INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
+ INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
EVENT_CONSTRAINT_END
};
@@ -695,20 +735,17 @@ static void intel_ds_init(void)
printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
- x86_pmu.pebs_constraints = intel_core_pebs_events;
break;
case 1:
printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
- x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
break;
default:
printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
- break;
}
}
}
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index f7a0993c1e7..e93fcd55fae 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1,5 +1,5 @@
/*
- * Netburst Perfomance Events (P4, old Xeon)
+ * Netburst Performance Events (P4, old Xeon)
*
* Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org>
* Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com>
@@ -679,7 +679,7 @@ static int p4_validate_raw_event(struct perf_event *event)
*/
/*
- * if an event is shared accross the logical threads
+ * if an event is shared across the logical threads
* the user needs special permissions to be able to use it
*/
if (p4_ht_active() && p4_event_bind_map[v].shared) {
@@ -764,15 +764,21 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
u64 v;
/* an official way for overflow indication */
- rdmsrl(hwc->config_base + hwc->idx, v);
+ rdmsrl(hwc->config_base, v);
if (v & P4_CCCR_OVF) {
- wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+ wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF);
return 1;
}
- /* it might be unflagged overflow */
- rdmsrl(hwc->event_base + hwc->idx, v);
- if (!(v & ARCH_P4_CNTRVAL_MASK))
+ /*
+ * In some circumstances the overflow might issue an NMI but did
+ * not set P4_CCCR_OVF bit. Because a counter holds a negative value
+ * we simply check for high bit being set, if it's cleared it means
+ * the counter has reached zero value and continued counting before
+ * real NMI signal was received:
+ */
+ rdmsrl(hwc->event_base, v);
+ if (!(v & ARCH_P4_UNFLAGGED_BIT))
return 1;
return 0;
@@ -785,13 +791,13 @@ static void p4_pmu_disable_pebs(void)
*
* It's still allowed that two threads setup same cache
* events so we can't simply clear metrics until we knew
- * noone is depending on us, so we need kind of counter
+ * no one is depending on us, so we need kind of counter
* for "ReplayEvent" users.
*
* What is more complex -- RAW events, if user (for some
* reason) will pass some cache event metric with improper
* event opcode -- it's fine from hardware point of view
- * but completely nonsence from "meaning" of such action.
+ * but completely nonsense from "meaning" of such action.
*
* So at moment let leave metrics turned on forever -- it's
* ok for now but need to be revisited!
@@ -810,7 +816,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
* state we need to clear P4_CCCR_OVF, otherwise interrupt get
* asserted again and again
*/
- (void)checking_wrmsrl(hwc->config_base + hwc->idx,
+ (void)checking_wrmsrl(hwc->config_base,
(u64)(p4_config_unpack_cccr(hwc->config)) &
~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
}
@@ -880,7 +886,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
p4_pmu_enable_pebs(hwc->config);
(void)checking_wrmsrl(escr_addr, escr_conf);
- (void)checking_wrmsrl(hwc->config_base + hwc->idx,
+ (void)checking_wrmsrl(hwc->config_base,
(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
}
@@ -941,14 +947,23 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
if (!x86_perf_event_set_period(event))
continue;
if (perf_event_overflow(event, 1, &data, regs))
- p4_pmu_disable_event(event);
+ x86_pmu_stop(event, 0);
}
- if (handled) {
- /* p4 quirk: unmask it again */
- apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+ if (handled)
inc_irq_stat(apic_perf_irqs);
- }
+
+ /*
+ * When dealing with the unmasking of the LVTPC on P4 perf hw, it has
+ * been observed that the OVF bit flag has to be cleared first _before_
+ * the LVTPC can be unmasked.
+ *
+ * The reason is the NMI line will continue to be asserted while the OVF
+ * bit is set. This causes a second NMI to generate if the LVTPC is
+ * unmasked before the OVF bit is cleared, leading to unknown NMI
+ * messages.
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
return handled;
}
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 34ba07be2cd..20c097e3386 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -68,7 +68,7 @@ p6_pmu_disable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
+ (void)checking_wrmsrl(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
@@ -81,7 +81,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
+ (void)checking_wrmsrl(hwc->config_base, val);
}
static __initconst const struct x86_pmu p6_pmu = {
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d5a23661550..966512b2cac 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -46,6 +46,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
/* returns the bit offset of the performance counter register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
+ if (msr >= MSR_F15H_PERF_CTR)
+ return (msr - MSR_F15H_PERF_CTR) >> 1;
return msr - MSR_K7_PERFCTR0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
@@ -70,6 +72,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
/* returns the bit offset of the event selection register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
+ if (msr >= MSR_F15H_PERF_CTL)
+ return (msr - MSR_F15H_PERF_CTL) >> 1;
return msr - MSR_K7_EVNTSEL0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 227b0448960..d22d0c4edcf 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -86,7 +86,7 @@ static void __init vmware_platform_setup(void)
}
/*
- * While checking the dmi string infomation, just checking the product
+ * While checking the dmi string information, just checking the product
* serial key should be enough, as this will always have a VMware
* specific string when running under VMware hypervisor.
*/
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index d5cd13945d5..642f75a68cd 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -14,9 +14,6 @@
static void *kdump_buf_page;
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
static inline bool is_crashed_pfn_valid(unsigned long pfn)
{
#ifndef CONFIG_X86_PAE
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 994828899e0..afa64adb75e 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -10,9 +10,6 @@
#include <linux/uaccess.h>
#include <linux/io.h>
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
/**
* copy_oldmem_page - copy one page from "oldmem"
* @pfn: page frame number to be copied
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
new file mode 100644
index 00000000000..e90f08458e6
--- /dev/null
+++ b/arch/x86/kernel/devicetree.c
@@ -0,0 +1,439 @@
+/*
+ * Architecture specific OF callbacks.
+ */
+#include <linux/bootmem.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/of_pci.h>
+
+#include <asm/hpet.h>
+#include <asm/irq_controller.h>
+#include <asm/apic.h>
+#include <asm/pci_x86.h>
+
+__initdata u64 initial_dtb;
+char __initdata cmd_line[COMMAND_LINE_SIZE];
+static LIST_HEAD(irq_domains);
+static DEFINE_RAW_SPINLOCK(big_irq_lock);
+
+int __initdata of_ioapic;
+
+#ifdef CONFIG_X86_IO_APIC
+static void add_interrupt_host(struct irq_domain *ih)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&big_irq_lock, flags);
+ list_add(&ih->l, &irq_domains);
+ raw_spin_unlock_irqrestore(&big_irq_lock, flags);
+}
+#endif
+
+static struct irq_domain *get_ih_from_node(struct device_node *controller)
+{
+ struct irq_domain *ih, *found = NULL;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&big_irq_lock, flags);
+ list_for_each_entry(ih, &irq_domains, l) {
+ if (ih->controller == controller) {
+ found = ih;
+ break;
+ }
+ }
+ raw_spin_unlock_irqrestore(&big_irq_lock, flags);
+ return found;
+}
+
+unsigned int irq_create_of_mapping(struct device_node *controller,
+ const u32 *intspec, unsigned int intsize)
+{
+ struct irq_domain *ih;
+ u32 virq, type;
+ int ret;
+
+ ih = get_ih_from_node(controller);
+ if (!ih)
+ return 0;
+ ret = ih->xlate(ih, intspec, intsize, &virq, &type);
+ if (ret)
+ return 0;
+ if (type == IRQ_TYPE_NONE)
+ return virq;
+ irq_set_irq_type(virq, type);
+ return virq;
+}
+EXPORT_SYMBOL_GPL(irq_create_of_mapping);
+
+unsigned long pci_address_to_pio(phys_addr_t address)
+{
+ /*
+ * The ioport address can be directly used by inX / outX
+ */
+ BUG_ON(address >= (1 << 16));
+ return (unsigned long)address;
+}
+EXPORT_SYMBOL_GPL(pci_address_to_pio);
+
+void __init early_init_dt_scan_chosen_arch(unsigned long node)
+{
+ BUG();
+}
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+ BUG();
+}
+
+void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
+{
+ return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
+}
+
+void __init add_dtb(u64 data)
+{
+ initial_dtb = data + offsetof(struct setup_data, data);
+}
+
+/*
+ * CE4100 ids. Will be moved to machine_device_initcall() once we have it.
+ */
+static struct of_device_id __initdata ce4100_ids[] = {
+ { .compatible = "intel,ce4100-cp", },
+ { .compatible = "isa", },
+ { .compatible = "pci", },
+ {},
+};
+
+static int __init add_bus_probe(void)
+{
+ if (!of_have_populated_dt())
+ return 0;
+
+ return of_platform_bus_probe(NULL, ce4100_ids, NULL);
+}
+module_init(add_bus_probe);
+
+#ifdef CONFIG_PCI
+static int x86_of_pci_irq_enable(struct pci_dev *dev)
+{
+ struct of_irq oirq;
+ u32 virq;
+ int ret;
+ u8 pin;
+
+ ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (ret)
+ return ret;
+ if (!pin)
+ return 0;
+
+ ret = of_irq_map_pci(dev, &oirq);
+ if (ret)
+ return ret;
+
+ virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
+ oirq.size);
+ if (virq == 0)
+ return -EINVAL;
+ dev->irq = virq;
+ return 0;
+}
+
+static void x86_of_pci_irq_disable(struct pci_dev *dev)
+{
+}
+
+void __cpuinit x86_of_pci_init(void)
+{
+ struct device_node *np;
+
+ pcibios_enable_irq = x86_of_pci_irq_enable;
+ pcibios_disable_irq = x86_of_pci_irq_disable;
+
+ for_each_node_by_type(np, "pci") {
+ const void *prop;
+ struct pci_bus *bus;
+ unsigned int bus_min;
+ struct device_node *child;
+
+ prop = of_get_property(np, "bus-range", NULL);
+ if (!prop)
+ continue;
+ bus_min = be32_to_cpup(prop);
+
+ bus = pci_find_bus(0, bus_min);
+ if (!bus) {
+ printk(KERN_ERR "Can't find a node for bus %s.\n",
+ np->full_name);
+ continue;
+ }
+
+ if (bus->self)
+ bus->self->dev.of_node = np;
+ else
+ bus->dev.of_node = np;
+
+ for_each_child_of_node(np, child) {
+ struct pci_dev *dev;
+ u32 devfn;
+
+ prop = of_get_property(child, "reg", NULL);
+ if (!prop)
+ continue;
+
+ devfn = (be32_to_cpup(prop) >> 8) & 0xff;
+ dev = pci_get_slot(bus, devfn);
+ if (!dev)
+ continue;
+ dev->dev.of_node = child;
+ pci_dev_put(dev);
+ }
+ }
+}
+#endif
+
+static void __init dtb_setup_hpet(void)
+{
+#ifdef CONFIG_HPET_TIMER
+ struct device_node *dn;
+ struct resource r;
+ int ret;
+
+ dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-hpet");
+ if (!dn)
+ return;
+ ret = of_address_to_resource(dn, 0, &r);
+ if (ret) {
+ WARN_ON(1);
+ return;
+ }
+ hpet_address = r.start;
+#endif
+}
+
+static void __init dtb_lapic_setup(void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+ struct device_node *dn;
+ struct resource r;
+ int ret;
+
+ dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-lapic");
+ if (!dn)
+ return;
+
+ ret = of_address_to_resource(dn, 0, &r);
+ if (WARN_ON(ret))
+ return;
+
+ /* Did the boot loader setup the local APIC ? */
+ if (!cpu_has_apic) {
+ if (apic_force_enable(r.start))
+ return;
+ }
+ smp_found_config = 1;
+ pic_mode = 1;
+ register_lapic_address(r.start);
+ generic_processor_info(boot_cpu_physical_apicid,
+ GET_APIC_VERSION(apic_read(APIC_LVR)));
+#endif
+}
+
+#ifdef CONFIG_X86_IO_APIC
+static unsigned int ioapic_id;
+
+static void __init dtb_add_ioapic(struct device_node *dn)
+{
+ struct resource r;
+ int ret;
+
+ ret = of_address_to_resource(dn, 0, &r);
+ if (ret) {
+ printk(KERN_ERR "Can't obtain address from node %s.\n",
+ dn->full_name);
+ return;
+ }
+ mp_register_ioapic(++ioapic_id, r.start, gsi_top);
+}
+
+static void __init dtb_ioapic_setup(void)
+{
+ struct device_node *dn;
+
+ for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic")
+ dtb_add_ioapic(dn);
+
+ if (nr_ioapics) {
+ of_ioapic = 1;
+ return;
+ }
+ printk(KERN_ERR "Error: No information about IO-APIC in OF.\n");
+}
+#else
+static void __init dtb_ioapic_setup(void) {}
+#endif
+
+static void __init dtb_apic_setup(void)
+{
+ dtb_lapic_setup();
+ dtb_ioapic_setup();
+}
+
+#ifdef CONFIG_OF_FLATTREE
+static void __init x86_flattree_get_config(void)
+{
+ u32 size, map_len;
+ void *new_dtb;
+
+ if (!initial_dtb)
+ return;
+
+ map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK),
+ (u64)sizeof(struct boot_param_header));
+
+ initial_boot_params = early_memremap(initial_dtb, map_len);
+ size = be32_to_cpu(initial_boot_params->totalsize);
+ if (map_len < size) {
+ early_iounmap(initial_boot_params, map_len);
+ initial_boot_params = early_memremap(initial_dtb, size);
+ map_len = size;
+ }
+
+ new_dtb = alloc_bootmem(size);
+ memcpy(new_dtb, initial_boot_params, size);
+ early_iounmap(initial_boot_params, map_len);
+
+ initial_boot_params = new_dtb;
+
+ /* root level address cells */
+ of_scan_flat_dt(early_init_dt_scan_root, NULL);
+
+ unflatten_device_tree();
+}
+#else
+static inline void x86_flattree_get_config(void) { }
+#endif
+
+void __init x86_dtb_init(void)
+{
+ x86_flattree_get_config();
+
+ if (!of_have_populated_dt())
+ return;
+
+ dtb_setup_hpet();
+ dtb_apic_setup();
+}
+
+#ifdef CONFIG_X86_IO_APIC
+
+struct of_ioapic_type {
+ u32 out_type;
+ u32 trigger;
+ u32 polarity;
+};
+
+static struct of_ioapic_type of_ioapic_type[] =
+{
+ {
+ .out_type = IRQ_TYPE_EDGE_RISING,
+ .trigger = IOAPIC_EDGE,
+ .polarity = 1,
+ },
+ {
+ .out_type = IRQ_TYPE_LEVEL_LOW,
+ .trigger = IOAPIC_LEVEL,
+ .polarity = 0,
+ },
+ {
+ .out_type = IRQ_TYPE_LEVEL_HIGH,
+ .trigger = IOAPIC_LEVEL,
+ .polarity = 1,
+ },
+ {
+ .out_type = IRQ_TYPE_EDGE_FALLING,
+ .trigger = IOAPIC_EDGE,
+ .polarity = 0,
+ },
+};
+
+static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize,
+ u32 *out_hwirq, u32 *out_type)
+{
+ struct io_apic_irq_attr attr;
+ struct of_ioapic_type *it;
+ u32 line, idx, type;
+
+ if (intsize < 2)
+ return -EINVAL;
+
+ line = *intspec;
+ idx = (u32) id->priv;
+ *out_hwirq = line + mp_gsi_routing[idx].gsi_base;
+
+ intspec++;
+ type = *intspec;
+
+ if (type >= ARRAY_SIZE(of_ioapic_type))
+ return -EINVAL;
+
+ it = of_ioapic_type + type;
+ *out_type = it->out_type;
+
+ set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
+
+ return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr);
+}
+
+static void __init ioapic_add_ofnode(struct device_node *np)
+{
+ struct resource r;
+ int i, ret;
+
+ ret = of_address_to_resource(np, 0, &r);
+ if (ret) {
+ printk(KERN_ERR "Failed to obtain address for %s\n",
+ np->full_name);
+ return;
+ }
+
+ for (i = 0; i < nr_ioapics; i++) {
+ if (r.start == mp_ioapics[i].apicaddr) {
+ struct irq_domain *id;
+
+ id = kzalloc(sizeof(*id), GFP_KERNEL);
+ BUG_ON(!id);
+ id->controller = np;
+ id->xlate = ioapic_xlate;
+ id->priv = (void *)i;
+ add_interrupt_host(id);
+ return;
+ }
+ }
+ printk(KERN_ERR "IOxAPIC at %s is not registered.\n", np->full_name);
+}
+
+void __init x86_add_irq_domains(void)
+{
+ struct device_node *dp;
+
+ if (!of_have_populated_dt())
+ return;
+
+ for_each_node_with_property(dp, "interrupt-controller") {
+ if (of_device_is_compatible(dp, "intel,ce4100-ioapic"))
+ ioapic_add_ofnode(dp);
+ }
+}
+#else
+void __init x86_add_irq_domains(void) { }
+#endif
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index df20723a6a1..e2a3f0606da 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -27,7 +27,7 @@ static int die_counter;
void printk_address(unsigned long address, int reliable)
{
- printk(" [<%p>] %s%pS\n", (void *) address,
+ printk(" [<%p>] %s%pB\n", (void *) address,
reliable ? "" : "? ", (void *) address);
}
@@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = {
void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, char *log_lvl)
+ unsigned long *stack, unsigned long bp, char *log_lvl)
{
printk("%sCall Trace:\n", log_lvl);
- dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
+ dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
}
void show_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack)
+ unsigned long *stack, unsigned long bp)
{
- show_trace_log_lvl(task, regs, stack, "");
+ show_trace_log_lvl(task, regs, stack, bp, "");
}
void show_stack(struct task_struct *task, unsigned long *sp)
{
- show_stack_log_lvl(task, NULL, sp, "");
+ show_stack_log_lvl(task, NULL, sp, 0, "");
}
/*
@@ -197,14 +197,16 @@ void show_stack(struct task_struct *task, unsigned long *sp)
*/
void dump_stack(void)
{
+ unsigned long bp;
unsigned long stack;
+ bp = stack_frame(current, NULL);
printk("Pid: %d, comm: %.20s %s %s %.*s\n",
current->pid, current->comm, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
- show_trace(NULL, NULL, &stack);
+ show_trace(NULL, NULL, &stack, bp);
}
EXPORT_SYMBOL(dump_stack);
@@ -320,41 +322,6 @@ void die(const char *str, struct pt_regs *regs, long err)
oops_end(flags, regs, sig);
}
-void notrace __kprobes
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
- unsigned long flags;
-
- if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
- return;
-
- /*
- * We are in trouble anyway, lets at least try
- * to get a message out.
- */
- flags = oops_begin();
- printk(KERN_EMERG "%s", str);
- printk(" on CPU%d, ip %08lx, registers:\n",
- smp_processor_id(), regs->ip);
- show_registers(regs);
- oops_end(flags, regs, 0);
- if (do_panic || panic_on_oops)
- panic("Non maskable interrupt");
- nmi_exit();
- local_irq_enable();
- do_exit(SIGBUS);
-}
-
-static int __init oops_setup(char *s)
-{
- if (!s)
- return -EINVAL;
- if (!strcmp(s, "panic"))
- panic_on_oops = 1;
- return 0;
-}
-early_param("oops", oops_setup);
-
static int __init kstack_setup(char *s)
{
if (!s)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 74cc1eda384..3b97a80ce32 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,12 +17,11 @@
#include <asm/stacktrace.h>
-void dump_trace(struct task_struct *task,
- struct pt_regs *regs, unsigned long *stack,
+void dump_trace(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
int graph = 0;
- unsigned long bp;
if (!task)
task = current;
@@ -35,7 +34,9 @@ void dump_trace(struct task_struct *task,
stack = (unsigned long *)task->thread.sp;
}
- bp = stack_frame(task, regs);
+ if (!bp)
+ bp = stack_frame(task, regs);
+
for (;;) {
struct thread_info *context;
@@ -55,7 +56,7 @@ EXPORT_SYMBOL(dump_trace);
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, char *log_lvl)
+ unsigned long *sp, unsigned long bp, char *log_lvl)
{
unsigned long *stack;
int i;
@@ -77,7 +78,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
touch_nmi_watchdog();
}
printk(KERN_CONT "\n");
- show_trace_log_lvl(task, regs, sp, log_lvl);
+ show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
@@ -102,7 +103,7 @@ void show_registers(struct pt_regs *regs)
u8 *ip;
printk(KERN_EMERG "Stack:\n");
- show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
+ show_stack_log_lvl(NULL, regs, &regs->sp, 0, KERN_EMERG);
printk(KERN_EMERG "Code: ");
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index a6b6fcf7f0a..e71c98d3c0d 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
*/
-void dump_trace(struct task_struct *task,
- struct pt_regs *regs, unsigned long *stack,
+void dump_trace(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
@@ -150,7 +150,6 @@ void dump_trace(struct task_struct *task,
struct thread_info *tinfo;
int graph = 0;
unsigned long dummy;
- unsigned long bp;
if (!task)
task = current;
@@ -161,7 +160,8 @@ void dump_trace(struct task_struct *task,
stack = (unsigned long *)task->thread.sp;
}
- bp = stack_frame(task, regs);
+ if (!bp)
+ bp = stack_frame(task, regs);
/*
* Print function call entries in all stacks, starting at the
* current stack address. If the stacks consist of nested
@@ -225,7 +225,7 @@ EXPORT_SYMBOL(dump_trace);
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, char *log_lvl)
+ unsigned long *sp, unsigned long bp, char *log_lvl)
{
unsigned long *irq_stack_end;
unsigned long *irq_stack;
@@ -269,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
preempt_enable();
printk(KERN_CONT "\n");
- show_trace_log_lvl(task, regs, sp, log_lvl);
+ show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
void show_registers(struct pt_regs *regs)
@@ -298,7 +298,7 @@ void show_registers(struct pt_regs *regs)
printk(KERN_EMERG "Stack:\n");
show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
- KERN_EMERG);
+ 0, KERN_EMERG);
printk(KERN_EMERG "Code: ");
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 294f26da0c0..3e2ef842531 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
+#include <linux/crash_dump.h>
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
@@ -667,21 +668,15 @@ __init void e820_setup_gap(void)
* boot_params.e820_map, others are passed via SETUP_E820_EXT node of
* linked list of struct setup_data, which is parsed here.
*/
-void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data)
+void __init parse_e820_ext(struct setup_data *sdata)
{
- u32 map_len;
int entries;
struct e820entry *extmap;
entries = sdata->len / sizeof(struct e820entry);
- map_len = sdata->len + sizeof(struct setup_data);
- if (map_len > PAGE_SIZE)
- sdata = early_ioremap(pa_data, map_len);
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
- if (map_len > PAGE_SIZE)
- early_iounmap(sdata, map_len);
printk(KERN_INFO "extended physical RAM map:\n");
e820_print_map("extended");
}
@@ -847,15 +842,21 @@ static int __init parse_memopt(char *p)
if (!p)
return -EINVAL;
-#ifdef CONFIG_X86_32
if (!strcmp(p, "nopentium")) {
+#ifdef CONFIG_X86_32
setup_clear_cpu_cap(X86_FEATURE_PSE);
return 0;
- }
+#else
+ printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
+ return -EINVAL;
#endif
+ }
userdef = 1;
mem_size = memparse(p, &p);
+ /* don't remove all of memory when handling "mem={invalid}" param */
+ if (mem_size == 0)
+ return -EINVAL;
e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
return 0;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 76b8cd953de..3755ef49439 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -143,15 +143,10 @@ static void __init ati_bugs(int num, int slot, int func)
static u32 __init ati_sbx00_rev(int num, int slot, int func)
{
- u32 old, d;
+ u32 d;
- d = read_pci_config(num, slot, func, 0x70);
- old = d;
- d &= ~(1<<8);
- write_pci_config(num, slot, func, 0x70, d);
d = read_pci_config(num, slot, func, 0x8);
d &= 0xff;
- write_pci_config(num, slot, func, 0x70, old);
return d;
}
@@ -160,11 +155,19 @@ static void __init ati_bugs_contd(int num, int slot, int func)
{
u32 d, rev;
- if (acpi_use_timer_override)
+ rev = ati_sbx00_rev(num, slot, func);
+ if (rev >= 0x40)
+ acpi_fix_pin2_polarity = 1;
+
+ /*
+ * SB600: revisions 0x11, 0x12, 0x13, 0x14, ...
+ * SB700: revisions 0x39, 0x3a, ...
+ * SB800: revisions 0x40, 0x41, ...
+ */
+ if (rev >= 0x39)
return;
- rev = ati_sbx00_rev(num, slot, func);
- if (rev > 0x13)
+ if (acpi_use_timer_override)
return;
/* check for IRQ0 interrupt swap */
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c8b4efad7eb..5c1a9197491 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -65,6 +65,8 @@
#define sysexit_audit syscall_exit_work
#endif
+ .section .entry.text, "ax"
+
/*
* We use macros for low-level operations which need to be overridden
* for paravirtualization. The following will never clobber any registers:
@@ -395,7 +397,7 @@ sysenter_past_esp:
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
* pushed above; +8 corresponds to copy_thread's esp0 setting.
*/
- pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp)
+ pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp)
CFI_REL_OFFSET eip, 0
pushl_cfi %eax
@@ -788,7 +790,7 @@ ENDPROC(ptregs_clone)
*/
.section .init.rodata,"a"
ENTRY(interrupt)
-.text
+.section .entry.text, "ax"
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
@@ -807,7 +809,7 @@ vector=FIRST_EXTERNAL_VECTOR
.endif
.previous
.long 1b
- .text
+ .section .entry.text, "ax"
vector=vector+1
.endif
.endr
@@ -1409,11 +1411,10 @@ END(general_protection)
#ifdef CONFIG_KVM_GUEST
ENTRY(async_page_fault)
RING0_EC_FRAME
- pushl $do_async_page_fault
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi $do_async_page_fault
jmp error_code
CFI_ENDPROC
-END(apf_page_fault)
+END(async_page_fault)
#endif
/*
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index aed1ffbeb0c..8a445a0c989 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -18,7 +18,7 @@
* A note on terminology:
* - top of stack: Architecture defined interrupt frame from SS to RIP
* at the top of the kernel process stack.
- * - partial stack frame: partially saved registers upto R11.
+ * - partial stack frame: partially saved registers up to R11.
* - full stack frame: Like partial stack frame, but all register saved.
*
* Some macro usage:
@@ -61,6 +61,8 @@
#define __AUDIT_ARCH_LE 0x40000000
.code64
+ .section .entry.text, "ax"
+
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(mcount)
@@ -420,7 +422,7 @@ ENTRY(ret_from_fork)
END(ret_from_fork)
/*
- * System call entry. Upto 6 arguments in registers are supported.
+ * System call entry. Up to 6 arguments in registers are supported.
*
* SYSCALL does not save anything on the stack and does not change the
* stack pointer.
@@ -744,7 +746,7 @@ END(stub_rt_sigreturn)
*/
.section .init.rodata,"a"
ENTRY(interrupt)
- .text
+ .section .entry.text
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
@@ -763,7 +765,7 @@ vector=FIRST_EXTERNAL_VECTOR
.endif
.previous
.quad 1b
- .text
+ .section .entry.text
vector=vector+1
.endif
.endr
@@ -975,9 +977,12 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
x86_platform_ipi smp_x86_platform_ipi
#ifdef CONFIG_SMP
-.irpc idx, "01234567"
+.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
+ 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+.if NUM_INVALIDATE_TLB_VECTORS > \idx
apicinterrupt (INVALIDATE_TLB_VECTOR_START)+\idx \
invalidate_interrupt\idx smp_invalidate_interrupt
+.endif
.endr
#endif
@@ -1248,7 +1253,7 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
decl PER_CPU_VAR(irq_count)
jmp error_exit
CFI_ENDPROC
-END(do_hypervisor_callback)
+END(xen_do_hypervisor_callback)
/*
* Hypervisor uses this for application faults while it executes.
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 382eb2936d4..a93742a5746 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
return;
}
- if (ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer) == -EBUSY) {
- *parent = old;
- return;
- }
-
trace.func = self_addr;
+ trace.depth = current->curr_ret_stack + 1;
/* Only trace if the calling function expects to */
if (!ftrace_graph_entry(&trace)) {
- current->curr_ret_stack--;
*parent = old;
+ return;
+ }
+
+ if (ftrace_push_return_trace(old, self_addr, &trace.depth,
+ frame_pointer) == -EBUSY) {
+ *parent = old;
+ return;
}
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 7f138b3c3c5..d6d6bb36193 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -34,15 +34,6 @@ void __init i386_start_kernel(void)
{
memblock_init();
-#ifdef CONFIG_X86_TRAMPOLINE
- /*
- * But first pinch a few for the stack/trampoline stuff
- * FIXME: Don't need the extra page at 4K, but need to fix
- * trampoline before removing it. (see the GDT stuff)
- */
- memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
-#endif
-
memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
#ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2d2673c28af..5655c2272ad 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -77,9 +77,6 @@ void __init x86_64_start_kernel(char * real_mode_data)
/* Make NULL pointers segfault */
zap_identity_mappings();
- /* Cleanup the over mapped high alias */
- cleanup_highmap();
-
max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 767d6c43de3..ce0be7cd085 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -73,7 +73,7 @@ MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
*/
KERNEL_PAGES = LOWMEM_PAGES
-INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
+INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE
RESERVE_BRK(pagetables, INIT_MAP_SIZE)
/*
@@ -137,7 +137,7 @@ ENTRY(startup_32)
movsl
1:
-#ifdef CONFIG_OLPC_OPENFIRMWARE
+#ifdef CONFIG_OLPC
/* save OFW's pgdir table for later use when calling into OFW */
movl %cr3, %eax
movl %eax, pa(olpc_ofw_pgd)
@@ -623,7 +623,7 @@ ENTRY(initial_code)
* BSS section
*/
__PAGE_ALIGNED_BSS
- .align PAGE_SIZE_asm
+ .align PAGE_SIZE
#ifdef CONFIG_X86_PAE
initial_pg_pmd:
.fill 1024*KPMDS,4,0
@@ -644,7 +644,7 @@ ENTRY(swapper_pg_dir)
#ifdef CONFIG_X86_PAE
__PAGE_ALIGNED_DATA
/* Page-aligned for the benefit of paravirt? */
- .align PAGE_SIZE_asm
+ .align PAGE_SIZE
ENTRY(initial_page_table)
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */
# if KPMDS == 3
@@ -662,7 +662,7 @@ ENTRY(initial_page_table)
# else
# error "Kernel PMDs should be 1, 2 or 3"
# endif
- .align PAGE_SIZE_asm /* needs to be page-sized too */
+ .align PAGE_SIZE /* needs to be page-sized too */
#endif
.data
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 239046bd447..e11e39478a4 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -136,10 +136,9 @@ ident_complete:
/* Fixup phys_base */
addq %rbp, phys_base(%rip)
-#ifdef CONFIG_X86_TRAMPOLINE
+ /* Fixup trampoline */
addq %rbp, trampoline_level4_pgt + 0(%rip)
addq %rbp, trampoline_level4_pgt + (511*8)(%rip)
-#endif
/* Due to ENTRY(), sometimes the empty space gets filled with
* zeros. Better take a jmp than relying on empty space being
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 4ff5968f12d..bfe8f729e08 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -503,7 +503,7 @@ static int hpet_assign_irq(struct hpet_dev *dev)
if (!irq)
return -EINVAL;
- set_irq_data(irq, dev);
+ irq_set_handler_data(irq, dev);
if (hpet_setup_msi_irq(irq))
return -EINVAL;
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e60c38cc0ee..12aff253768 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -145,7 +145,7 @@ EXPORT_SYMBOL_GPL(fpu_finit);
* The _current_ task is using the FPU for the first time
* so initialize it and set the mxcsr to its default
* value at reset if we support XMM instructions and then
- * remeber the current task has used the FPU.
+ * remember the current task has used the FPU.
*/
int init_fpu(struct task_struct *tsk)
{
diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c
index b42ca694dc6..8eeaa81de06 100644
--- a/arch/x86/kernel/i8237.c
+++ b/arch/x86/kernel/i8237.c
@@ -10,7 +10,7 @@
*/
#include <linux/init.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <asm/dma.h>
@@ -21,7 +21,7 @@
* in asm/dma.h.
*/
-static int i8237A_resume(struct sys_device *dev)
+static void i8237A_resume(void)
{
unsigned long flags;
int i;
@@ -41,31 +41,15 @@ static int i8237A_resume(struct sys_device *dev)
enable_dma(4);
release_dma_lock(flags);
-
- return 0;
}
-static int i8237A_suspend(struct sys_device *dev, pm_message_t state)
-{
- return 0;
-}
-
-static struct sysdev_class i8237_sysdev_class = {
- .name = "i8237",
- .suspend = i8237A_suspend,
+static struct syscore_ops i8237_syscore_ops = {
.resume = i8237A_resume,
};
-static struct sys_device device_i8237A = {
- .id = 0,
- .cls = &i8237_sysdev_class,
-};
-
-static int __init i8237A_init_sysfs(void)
+static int __init i8237A_init_ops(void)
{
- int error = sysdev_class_register(&i8237_sysdev_class);
- if (!error)
- error = sysdev_register(&device_i8237A);
- return error;
+ register_syscore_ops(&i8237_syscore_ops);
+ return 0;
}
-device_initcall(i8237A_init_sysfs);
+device_initcall(i8237A_init_ops);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 20757cb2efa..65b8f5c2eeb 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -8,7 +8,7 @@
#include <linux/random.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/bitops.h>
#include <linux/acpi.h>
#include <linux/io.h>
@@ -112,7 +112,7 @@ static void make_8259A_irq(unsigned int irq)
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
- set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+ irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
i8259A_chip.name);
enable_irq(irq);
}
@@ -245,20 +245,19 @@ static void save_ELCR(char *trigger)
trigger[1] = inb(0x4d1) & 0xDE;
}
-static int i8259A_resume(struct sys_device *dev)
+static void i8259A_resume(void)
{
init_8259A(i8259A_auto_eoi);
restore_ELCR(irq_trigger);
- return 0;
}
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
+static int i8259A_suspend(void)
{
save_ELCR(irq_trigger);
return 0;
}
-static int i8259A_shutdown(struct sys_device *dev)
+static void i8259A_shutdown(void)
{
/* Put the i8259A into a quiescent state that
* the kernel initialization code can get it
@@ -266,21 +265,14 @@ static int i8259A_shutdown(struct sys_device *dev)
*/
outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */
- return 0;
}
-static struct sysdev_class i8259_sysdev_class = {
- .name = "i8259",
+static struct syscore_ops i8259_syscore_ops = {
.suspend = i8259A_suspend,
.resume = i8259A_resume,
.shutdown = i8259A_shutdown,
};
-static struct sys_device device_i8259A = {
- .id = 0,
- .cls = &i8259_sysdev_class,
-};
-
static void mask_8259A(void)
{
unsigned long flags;
@@ -399,17 +391,12 @@ struct legacy_pic default_legacy_pic = {
struct legacy_pic *legacy_pic = &default_legacy_pic;
-static int __init i8259A_init_sysfs(void)
+static int __init i8259A_init_ops(void)
{
- int error;
-
- if (legacy_pic != &default_legacy_pic)
- return 0;
+ if (legacy_pic == &default_legacy_pic)
+ register_syscore_ops(&i8259_syscore_ops);
- error = sysdev_class_register(&i8259_sysdev_class);
- if (!error)
- error = sysdev_register(&device_i8259A);
- return error;
+ return 0;
}
-device_initcall(i8259A_init_sysfs);
+device_initcall(i8259A_init_ops);
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 8eec0ec59af..8c968974253 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -14,22 +14,9 @@
#include <linux/slab.h>
#include <linux/thread_info.h>
#include <linux/syscalls.h>
+#include <linux/bitmap.h>
#include <asm/syscalls.h>
-/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
-static void set_bitmap(unsigned long *bitmap, unsigned int base,
- unsigned int extent, int new_value)
-{
- unsigned int i;
-
- for (i = base; i < base + extent; i++) {
- if (new_value)
- __set_bit(i, bitmap);
- else
- __clear_bit(i, bitmap);
- }
-}
-
/*
* this changes the io permissions bitmap in the current task.
*/
@@ -69,7 +56,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
*/
tss = &per_cpu(init_tss, get_cpu());
- set_bitmap(t->io_bitmap_ptr, from, num, !turn_on);
+ if (turn_on)
+ bitmap_clear(t->io_bitmap_ptr, from, num);
+ else
+ bitmap_set(t->io_bitmap_ptr, from, num);
/*
* Search for a (possibly new) maximum. This is simple and stupid,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 52945da52a9..1cb0b9fc78d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -8,6 +8,7 @@
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/ftrace.h>
+#include <linux/delay.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
@@ -44,9 +45,9 @@ void ack_bad_irq(unsigned int irq)
#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
- * /proc/interrupts printing:
+ * /proc/interrupts printing for arch specific interrupts
*/
-static int show_other_interrupts(struct seq_file *p, int prec)
+int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
@@ -122,59 +123,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
return 0;
}
-int show_interrupts(struct seq_file *p, void *v)
-{
- unsigned long flags, any_count = 0;
- int i = *(loff_t *) v, j, prec;
- struct irqaction *action;
- struct irq_desc *desc;
-
- if (i > nr_irqs)
- return 0;
-
- for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
- j *= 10;
-
- if (i == nr_irqs)
- return show_other_interrupts(p, prec);
-
- /* print header */
- if (i == 0) {
- seq_printf(p, "%*s", prec + 8, "");
- for_each_online_cpu(j)
- seq_printf(p, "CPU%-8d", j);
- seq_putc(p, '\n');
- }
-
- desc = irq_to_desc(i);
- if (!desc)
- return 0;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- for_each_online_cpu(j)
- any_count |= kstat_irqs_cpu(i, j);
- action = desc->action;
- if (!action && !any_count)
- goto out;
-
- seq_printf(p, "%*d: ", prec, i);
- for_each_online_cpu(j)
- seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
- seq_printf(p, " %8s", desc->irq_data.chip->name);
- seq_printf(p, "-%-8s", desc->name);
-
- if (action) {
- seq_printf(p, " %s", action->name);
- while ((action = action->next) != NULL)
- seq_printf(p, ", %s", action->name);
- }
-
- seq_putc(p, '\n');
-out:
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- return 0;
-}
-
/*
* /proc/stat helpers
*/
@@ -276,15 +224,6 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
-#ifdef CONFIG_OF
-unsigned int irq_create_of_mapping(struct device_node *controller,
- const u32 *intspec, unsigned int intsize)
-{
- return intspec[0];
-}
-EXPORT_SYMBOL_GPL(irq_create_of_mapping);
-#endif
-
#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
@@ -293,6 +232,7 @@ void fixup_irqs(void)
static int warned;
struct irq_desc *desc;
struct irq_data *data;
+ struct irq_chip *chip;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
@@ -307,10 +247,10 @@ void fixup_irqs(void)
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
- data = &desc->irq_data;
+ data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
if (!irq_has_action(irq) ||
- cpumask_equal(affinity, cpu_online_mask)) {
+ cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
@@ -327,16 +267,17 @@ void fixup_irqs(void)
affinity = cpu_all_mask;
}
- if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
- data->chip->irq_mask(data);
+ chip = irq_data_get_irq_chip(data);
+ if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
+ chip->irq_mask(data);
- if (data->chip->irq_set_affinity)
- data->chip->irq_set_affinity(data, affinity, true);
+ if (chip->irq_set_affinity)
+ chip->irq_set_affinity(data, affinity, true);
else if (!(warned++))
set_affinity = 0;
- if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
- data->chip->irq_unmask(data);
+ if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
+ chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
@@ -367,10 +308,12 @@ void fixup_irqs(void)
if (irr & (1 << (vector % 32))) {
irq = __this_cpu_read(vector_irq[vector]);
- data = irq_get_irq_data(irq);
+ desc = irq_to_desc(irq);
+ data = irq_desc_get_irq_data(desc);
+ chip = irq_data_get_irq_chip(data);
raw_spin_lock(&desc->lock);
- if (data->chip->irq_retrigger)
- data->chip->irq_retrigger(data);
+ if (chip->irq_retrigger)
+ chip->irq_retrigger(data);
raw_spin_unlock(&desc->lock);
}
}
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 9974d21048f..72090705a65 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -172,7 +172,7 @@ asmlinkage void do_softirq(void)
call_on_stack(__do_softirq, isp);
/*
- * Shouldnt happen, we returned above if in_interrupt():
+ * Shouldn't happen, we returned above if in_interrupt():
*/
WARN_ON_ONCE(softirq_count());
}
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index c752e973958..f470e4ef993 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -25,6 +25,7 @@
#include <asm/setup.h>
#include <asm/i8259.h>
#include <asm/traps.h>
+#include <asm/prom.h>
/*
* ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
@@ -71,6 +72,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
static struct irqaction fpu_irq = {
.handler = math_error_irq,
.name = "fpu",
+ .flags = IRQF_NO_THREAD,
};
#endif
@@ -80,6 +82,7 @@ static struct irqaction fpu_irq = {
static struct irqaction irq2 = {
.handler = no_action,
.name = "cascade",
+ .flags = IRQF_NO_THREAD,
};
DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
@@ -110,7 +113,7 @@ void __init init_ISA_irqs(void)
legacy_pic->init(0);
for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
- set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
+ irq_set_chip_and_handler_name(i, chip, handle_level_irq, name);
}
void __init init_IRQ(void)
@@ -118,6 +121,12 @@ void __init init_IRQ(void)
int i;
/*
+ * We probably need a better place for this, but it works for
+ * now ...
+ */
+ x86_add_irq_domains();
+
+ /*
* On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
* If these IRQ's are handled by legacy interrupt-controllers like PIC,
* then this configuration will likely be static after the boot. If
@@ -164,14 +173,77 @@ static void __init smp_intr_init(void)
alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
/* IPIs for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+#define ALLOC_INVTLB_VEC(NR) \
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+NR, \
+ invalidate_interrupt##NR)
+
+ switch (NUM_INVALIDATE_TLB_VECTORS) {
+ default:
+ ALLOC_INVTLB_VEC(31);
+ case 31:
+ ALLOC_INVTLB_VEC(30);
+ case 30:
+ ALLOC_INVTLB_VEC(29);
+ case 29:
+ ALLOC_INVTLB_VEC(28);
+ case 28:
+ ALLOC_INVTLB_VEC(27);
+ case 27:
+ ALLOC_INVTLB_VEC(26);
+ case 26:
+ ALLOC_INVTLB_VEC(25);
+ case 25:
+ ALLOC_INVTLB_VEC(24);
+ case 24:
+ ALLOC_INVTLB_VEC(23);
+ case 23:
+ ALLOC_INVTLB_VEC(22);
+ case 22:
+ ALLOC_INVTLB_VEC(21);
+ case 21:
+ ALLOC_INVTLB_VEC(20);
+ case 20:
+ ALLOC_INVTLB_VEC(19);
+ case 19:
+ ALLOC_INVTLB_VEC(18);
+ case 18:
+ ALLOC_INVTLB_VEC(17);
+ case 17:
+ ALLOC_INVTLB_VEC(16);
+ case 16:
+ ALLOC_INVTLB_VEC(15);
+ case 15:
+ ALLOC_INVTLB_VEC(14);
+ case 14:
+ ALLOC_INVTLB_VEC(13);
+ case 13:
+ ALLOC_INVTLB_VEC(12);
+ case 12:
+ ALLOC_INVTLB_VEC(11);
+ case 11:
+ ALLOC_INVTLB_VEC(10);
+ case 10:
+ ALLOC_INVTLB_VEC(9);
+ case 9:
+ ALLOC_INVTLB_VEC(8);
+ case 8:
+ ALLOC_INVTLB_VEC(7);
+ case 7:
+ ALLOC_INVTLB_VEC(6);
+ case 6:
+ ALLOC_INVTLB_VEC(5);
+ case 5:
+ ALLOC_INVTLB_VEC(4);
+ case 4:
+ ALLOC_INVTLB_VEC(3);
+ case 3:
+ ALLOC_INVTLB_VEC(2);
+ case 2:
+ ALLOC_INVTLB_VEC(1);
+ case 1:
+ ALLOC_INVTLB_VEC(0);
+ break;
+ }
/* IPI for generic function call */
alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
@@ -243,7 +315,7 @@ void __init native_init_IRQ(void)
set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
}
- if (!acpi_ioapic)
+ if (!acpi_ioapic && !of_ioapic)
setup_irq(2, &irq2);
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index a4130005028..5f9ecff328b 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -121,8 +121,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
dbg_reg_def[regno].size);
- switch (regno) {
#ifdef CONFIG_X86_32
+ switch (regno) {
case GDB_SS:
if (!user_mode_vm(regs))
*(unsigned long *)mem = __KERNEL_DS;
@@ -135,8 +135,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
case GDB_FS:
*(unsigned long *)mem = 0xFFFF;
break;
-#endif
}
+#endif
return dbg_reg_def[regno].name;
}
@@ -278,7 +278,7 @@ static int hw_break_release_slot(int breakno)
pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
if (dbg_release_bp_slot(*pevent))
/*
- * The debugger is responisble for handing the retry on
+ * The debugger is responsible for handing the retry on
* remove failure.
*/
return -1;
@@ -533,15 +533,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
}
return NOTIFY_DONE;
- case DIE_NMIWATCHDOG:
- if (atomic_read(&kgdb_active) != -1) {
- /* KGDB CPU roundup: */
- kgdb_nmicallback(raw_smp_processor_id(), regs);
- return NOTIFY_STOP;
- }
- /* Enter debugger: */
- break;
-
case DIE_DEBUG:
if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
if (user_mode(regs))
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index d91c477b3f6..f1a6244d7d9 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1183,12 +1183,13 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ unsigned long flags;
/* This is possible if op is under delayed unoptimizing */
if (kprobe_disabled(&op->kp))
return;
- preempt_disable();
+ local_irq_save(flags);
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
} else {
@@ -1207,7 +1208,7 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
opt_pre_handler(&op->kp, regs);
__this_cpu_write(current_kprobe, NULL);
}
- preempt_enable_no_resched();
+ local_irq_restore(flags);
}
static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
@@ -1276,6 +1277,14 @@ static int __kprobes can_optimize(unsigned long paddr)
if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
return 0;
+ /*
+ * Do not optimize in the entry code due to the unstable
+ * stack handling.
+ */
+ if ((paddr >= (unsigned long )__entry_text_start) &&
+ (paddr < (unsigned long )__entry_text_end))
+ return 0;
+
/* Check there is enough space for a relative jump. */
if (size - offset < RELATIVEJUMP_SIZE)
return 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8dc44662394..33c07b0b122 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -493,7 +493,7 @@ static void __init kvm_smp_prepare_boot_cpu(void)
native_smp_prepare_boot_cpu();
}
-static void kvm_guest_cpu_online(void *dummy)
+static void __cpuinit kvm_guest_cpu_online(void *dummy)
{
kvm_guest_cpu_init();
}
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 63eaf659623..177183cbb6a 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -259,7 +259,7 @@ static int __init mca_init(void)
/*
* WARNING: Be careful when making changes here. Putting an adapter
* and the motherboard simultaneously into setup mode may result in
- * damage to chips (according to The Indispensible PC Hardware Book
+ * damage to chips (according to The Indispensable PC Hardware Book
* by Hans-Peter Messmer). Also, we disable system interrupts (so
* that we are not disturbed in the middle of this).
*/
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 0fe6d1a66c3..c5610384ab1 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -66,7 +66,6 @@ struct microcode_amd {
unsigned int mpb[0];
};
-#define UCODE_MAX_SIZE 2048
#define UCODE_CONTAINER_SECTION_HDR 8
#define UCODE_CONTAINER_HEADER_SIZE 12
@@ -77,20 +76,20 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
struct cpuinfo_x86 *c = &cpu_data(cpu);
u32 dummy;
- memset(csig, 0, sizeof(*csig));
if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
- pr_warning("microcode: CPU%d: AMD CPU family 0x%x not "
- "supported\n", cpu, c->x86);
+ pr_warning("CPU%d: family %d not supported\n", cpu, c->x86);
return -1;
}
+
rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
- pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev);
+ pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
+
return 0;
}
-static int get_matching_microcode(int cpu, void *mc, int rev)
+static int get_matching_microcode(int cpu, struct microcode_header_amd *mc_hdr,
+ int rev)
{
- struct microcode_header_amd *mc_header = mc;
unsigned int current_cpu_id;
u16 equiv_cpu_id = 0;
unsigned int i = 0;
@@ -109,17 +108,17 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
if (!equiv_cpu_id)
return 0;
- if (mc_header->processor_rev_id != equiv_cpu_id)
+ if (mc_hdr->processor_rev_id != equiv_cpu_id)
return 0;
/* ucode might be chipset specific -- currently we don't support this */
- if (mc_header->nb_dev_id || mc_header->sb_dev_id) {
- pr_err("CPU%d: loading of chipset specific code not yet supported\n",
+ if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+ pr_err("CPU%d: chipset specific code not yet supported\n",
cpu);
return 0;
}
- if (mc_header->patch_id <= rev)
+ if (mc_hdr->patch_id <= rev)
return 0;
return 1;
@@ -144,71 +143,93 @@ static int apply_microcode_amd(int cpu)
/* check current patch id and patch's id for match */
if (rev != mc_amd->hdr.patch_id) {
- pr_err("CPU%d: update failed (for patch_level=0x%x)\n",
+ pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
return -1;
}
- pr_info("CPU%d: updated (new patch_level=0x%x)\n", cpu, rev);
+ pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
uci->cpu_sig.rev = rev;
return 0;
}
-static void *
-get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
+static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size)
{
- unsigned int total_size;
- u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
- void *mc;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ unsigned int max_size, actual_size;
+
+#define F1XH_MPB_MAX_SIZE 2048
+#define F14H_MPB_MAX_SIZE 1824
+#define F15H_MPB_MAX_SIZE 4096
+
+ switch (c->x86) {
+ case 0x14:
+ max_size = F14H_MPB_MAX_SIZE;
+ break;
+ case 0x15:
+ max_size = F15H_MPB_MAX_SIZE;
+ break;
+ default:
+ max_size = F1XH_MPB_MAX_SIZE;
+ break;
+ }
- get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
+ actual_size = buf[4] + (buf[5] << 8);
- if (section_hdr[0] != UCODE_UCODE_TYPE) {
- pr_err("error: invalid type field in container file section header\n");
- return NULL;
+ if (actual_size > size || actual_size > max_size) {
+ pr_err("section size mismatch\n");
+ return 0;
}
- total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8));
+ return actual_size;
+}
- if (total_size > size || total_size > UCODE_MAX_SIZE) {
- pr_err("error: size mismatch\n");
- return NULL;
+static struct microcode_header_amd *
+get_next_ucode(int cpu, const u8 *buf, unsigned int size, unsigned int *mc_size)
+{
+ struct microcode_header_amd *mc = NULL;
+ unsigned int actual_size = 0;
+
+ if (buf[0] != UCODE_UCODE_TYPE) {
+ pr_err("invalid type field in container file section header\n");
+ goto out;
}
- mc = vzalloc(UCODE_MAX_SIZE);
+ actual_size = verify_ucode_size(cpu, buf, size);
+ if (!actual_size)
+ goto out;
+
+ mc = vzalloc(actual_size);
if (!mc)
- return NULL;
+ goto out;
- get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
- *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
+ get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, actual_size);
+ *mc_size = actual_size + UCODE_CONTAINER_SECTION_HDR;
+out:
return mc;
}
static int install_equiv_cpu_table(const u8 *buf)
{
- u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE];
- unsigned int *buf_pos = (unsigned int *)container_hdr;
- unsigned long size;
-
- get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
-
- size = buf_pos[2];
-
- if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
- pr_err("error: invalid type field in container file section header\n");
- return 0;
+ unsigned int *ibuf = (unsigned int *)buf;
+ unsigned int type = ibuf[1];
+ unsigned int size = ibuf[2];
+
+ if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
+ pr_err("empty section/"
+ "invalid type field in container file section header\n");
+ return -EINVAL;
}
equiv_cpu_table = vmalloc(size);
if (!equiv_cpu_table) {
pr_err("failed to allocate equivalent CPU table\n");
- return 0;
+ return -ENOMEM;
}
- buf += UCODE_CONTAINER_HEADER_SIZE;
- get_ucode_data(equiv_cpu_table, buf, size);
+ get_ucode_data(equiv_cpu_table, buf + UCODE_CONTAINER_HEADER_SIZE, size);
return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
}
@@ -223,16 +244,16 @@ static enum ucode_state
generic_load_microcode(int cpu, const u8 *data, size_t size)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ struct microcode_header_amd *mc_hdr = NULL;
+ unsigned int mc_size, leftover;
+ int offset;
const u8 *ucode_ptr = data;
void *new_mc = NULL;
- void *mc;
- int new_rev = uci->cpu_sig.rev;
- unsigned int leftover;
- unsigned long offset;
+ unsigned int new_rev = uci->cpu_sig.rev;
enum ucode_state state = UCODE_OK;
offset = install_equiv_cpu_table(ucode_ptr);
- if (!offset) {
+ if (offset < 0) {
pr_err("failed to create equivalent cpu table\n");
return UCODE_ERROR;
}
@@ -241,64 +262,65 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
leftover = size - offset;
while (leftover) {
- unsigned int uninitialized_var(mc_size);
- struct microcode_header_amd *mc_header;
-
- mc = get_next_ucode(ucode_ptr, leftover, &mc_size);
- if (!mc)
+ mc_hdr = get_next_ucode(cpu, ucode_ptr, leftover, &mc_size);
+ if (!mc_hdr)
break;
- mc_header = (struct microcode_header_amd *)mc;
- if (get_matching_microcode(cpu, mc, new_rev)) {
+ if (get_matching_microcode(cpu, mc_hdr, new_rev)) {
vfree(new_mc);
- new_rev = mc_header->patch_id;
- new_mc = mc;
+ new_rev = mc_hdr->patch_id;
+ new_mc = mc_hdr;
} else
- vfree(mc);
+ vfree(mc_hdr);
ucode_ptr += mc_size;
leftover -= mc_size;
}
- if (new_mc) {
- if (!leftover) {
- vfree(uci->mc);
- uci->mc = new_mc;
- pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
- cpu, new_rev, uci->cpu_sig.rev);
- } else {
- vfree(new_mc);
- state = UCODE_ERROR;
- }
- } else
+ if (!new_mc) {
state = UCODE_NFOUND;
+ goto free_table;
+ }
+ if (!leftover) {
+ vfree(uci->mc);
+ uci->mc = new_mc;
+ pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n",
+ cpu, uci->cpu_sig.rev, new_rev);
+ } else {
+ vfree(new_mc);
+ state = UCODE_ERROR;
+ }
+
+free_table:
free_equiv_cpu_table();
return state;
}
-static enum ucode_state request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_amd(int cpu, struct device *device)
{
const char *fw_name = "amd-ucode/microcode_amd.bin";
- const struct firmware *firmware;
- enum ucode_state ret;
+ const struct firmware *fw;
+ enum ucode_state ret = UCODE_NFOUND;
- if (request_firmware(&firmware, fw_name, device)) {
- printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
- return UCODE_NFOUND;
+ if (request_firmware(&fw, fw_name, device)) {
+ pr_err("failed to load file %s\n", fw_name);
+ goto out;
}
- if (*(u32 *)firmware->data != UCODE_MAGIC) {
- pr_err("invalid UCODE_MAGIC (0x%08x)\n",
- *(u32 *)firmware->data);
- return UCODE_ERROR;
+ ret = UCODE_ERROR;
+ if (*(u32 *)fw->data != UCODE_MAGIC) {
+ pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
+ goto fw_release;
}
- ret = generic_load_microcode(cpu, firmware->data, firmware->size);
+ ret = generic_load_microcode(cpu, fw->data, fw->size);
- release_firmware(firmware);
+fw_release:
+ release_firmware(fw);
+out:
return ret;
}
@@ -319,7 +341,7 @@ static void microcode_fini_cpu_amd(int cpu)
static struct microcode_ops microcode_amd_ops = {
.request_microcode_user = request_microcode_user,
- .request_microcode_fw = request_microcode_fw,
+ .request_microcode_fw = request_microcode_amd,
.collect_cpu_info = collect_cpu_info_amd,
.apply_microcode = apply_microcode_amd,
.microcode_fini_cpu = microcode_fini_cpu_amd,
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 1cca374a2ba..f9242800bc8 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -82,6 +82,7 @@
#include <linux/cpu.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/syscore_ops.h>
#include <asm/microcode.h>
#include <asm/processor.h>
@@ -417,8 +418,10 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
if (err)
return err;
- if (microcode_init_cpu(cpu) == UCODE_ERROR)
- err = -EINVAL;
+ if (microcode_init_cpu(cpu) == UCODE_ERROR) {
+ sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
+ return -EINVAL;
+ }
return err;
}
@@ -436,33 +439,25 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
return 0;
}
-static int mc_sysdev_resume(struct sys_device *dev)
+static struct sysdev_driver mc_sysdev_driver = {
+ .add = mc_sysdev_add,
+ .remove = mc_sysdev_remove,
+};
+
+/**
+ * mc_bp_resume - Update boot CPU microcode during resume.
+ */
+static void mc_bp_resume(void)
{
- int cpu = dev->id;
+ int cpu = smp_processor_id();
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- if (!cpu_online(cpu))
- return 0;
-
- /*
- * All non-bootup cpus are still disabled,
- * so only CPU 0 will apply ucode here.
- *
- * Moreover, there can be no concurrent
- * updates from any other places at this point.
- */
- WARN_ON(cpu != 0);
-
if (uci->valid && uci->mc)
microcode_ops->apply_microcode(cpu);
-
- return 0;
}
-static struct sysdev_driver mc_sysdev_driver = {
- .add = mc_sysdev_add,
- .remove = mc_sysdev_remove,
- .resume = mc_sysdev_resume,
+static struct syscore_ops mc_syscore_ops = {
+ .resume = mc_bp_resume,
};
static __cpuinit int
@@ -540,6 +535,7 @@ static int __init microcode_init(void)
if (error)
return error;
+ register_syscore_ops(&mc_syscore_ops);
register_hotcpu_notifier(&mc_cpu_notifier);
pr_info("Microcode Update Driver: v" MICROCODE_VERSION
@@ -554,6 +550,7 @@ static void __exit microcode_exit(void)
microcode_dev_exit();
unregister_hotcpu_notifier(&mc_cpu_notifier);
+ unregister_syscore_ops(&mc_syscore_ops);
get_online_cpus();
mutex_lock(&microcode_mutex);
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 01b0f6d0645..5a532ce646b 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -714,10 +714,6 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
*nr_m_spare += 1;
}
}
-#else /* CONFIG_X86_IO_APIC */
-static
-inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
-#endif /* CONFIG_X86_IO_APIC */
static int
check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
@@ -731,6 +727,10 @@ check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
return ret;
}
+#else /* CONFIG_X86_IO_APIC */
+static
+inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
+#endif /* CONFIG_X86_IO_APIC */
static int __init replace_intsrc_all(struct mpc_table *mpc,
unsigned long mpc_new_phys,
@@ -883,7 +883,7 @@ static int __init update_mp_table(void)
if (!mpc_new_phys) {
unsigned char old, new;
- /* check if we can change the postion */
+ /* check if we can change the position */
mpc->checksum = 0;
old = mpf_checksum((unsigned char *)mpc, mpc->length);
mpc->checksum = 0xff;
@@ -892,7 +892,7 @@ static int __init update_mp_table(void)
printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n");
return 0;
}
- printk(KERN_INFO "use in-positon replacing\n");
+ printk(KERN_INFO "use in-position replacing\n");
} else {
mpf->physptr = mpc_new_phys;
mpc_new = phys_to_virt(mpc_new_phys);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index f56a117cef6..e8c33a30200 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1279,7 +1279,7 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
if (pci_dev == PCI_DEVICE_ID_IBM_CALIOC2) {
/*
- * FIXME: properly scan for devices accross the
+ * FIXME: properly scan for devices across the
* PCI-to-PCI bridge on every CalIOC2 port.
*/
return 1;
@@ -1295,7 +1295,7 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
/*
* calgary_init_bitmap_from_tce_table():
- * Funtion for kdump case. In the second/kdump kernel initialize
+ * Function for kdump case. In the second/kdump kernel initialize
* the bitmap based on the tce table entries obtained from first kernel
*/
static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c01ffa5b9b8..b117efd24f7 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -27,7 +27,7 @@
#include <linux/kdebug.h>
#include <linux/scatterlist.h>
#include <linux/iommu-helper.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/io.h>
#include <linux/gfp.h>
#include <asm/atomic.h>
@@ -81,6 +81,9 @@ static u32 gart_unmapped_entry;
#define AGPEXTERN
#endif
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR (1ULL << 40)
+
/* backdoor interface to AGP driver */
AGPEXTERN int agp_memory_reserved;
AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
size_t size, int dir, unsigned long align_mask)
{
unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
- unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+ unsigned long iommu_page;
int i;
+ if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+ return bad_dma_addr;
+
+ iommu_page = alloc_iommu(dev, npages, align_mask);
if (iommu_page == -1) {
if (!nonforced_iommu(dev, phys_mem, size))
return phys_mem;
@@ -589,7 +596,7 @@ void set_up_gart_resume(u32 aper_order, u32 aper_alloc)
aperture_alloc = aper_alloc;
}
-static void gart_fixup_northbridges(struct sys_device *dev)
+static void gart_fixup_northbridges(void)
{
int i;
@@ -613,33 +620,20 @@ static void gart_fixup_northbridges(struct sys_device *dev)
}
}
-static int gart_resume(struct sys_device *dev)
+static void gart_resume(void)
{
pr_info("PCI-DMA: Resuming GART IOMMU\n");
- gart_fixup_northbridges(dev);
+ gart_fixup_northbridges();
enable_gart_translations();
-
- return 0;
}
-static int gart_suspend(struct sys_device *dev, pm_message_t state)
-{
- return 0;
-}
-
-static struct sysdev_class gart_sysdev_class = {
- .name = "gart",
- .suspend = gart_suspend,
+static struct syscore_ops gart_syscore_ops = {
.resume = gart_resume,
};
-static struct sys_device device_gart = {
- .cls = &gart_sysdev_class,
-};
-
/*
* Private Northbridge GATT initialization in case we cannot use the
* AGP driver for some reason.
@@ -650,7 +644,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
unsigned aper_base, new_aper_base;
struct pci_dev *dev;
void *gatt;
- int i, error;
+ int i;
pr_info("PCI-DMA: Disabling AGP.\n");
@@ -685,12 +679,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
agp_gatt_table = gatt;
- error = sysdev_class_register(&gart_sysdev_class);
- if (!error)
- error = sysdev_register(&device_gart);
- if (error)
- panic("Could not register gart_sysdev -- "
- "would corrupt data on next suspend");
+ register_syscore_ops(&gart_syscore_ops);
flush_gart();
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e764fc05d70..d46cbe46b7a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -87,26 +87,33 @@ void exit_thread(void)
void show_regs(struct pt_regs *regs)
{
show_registers(regs);
- show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
+ show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs), 0);
}
void show_regs_common(void)
{
- const char *board, *product;
+ const char *vendor, *product, *board;
- board = dmi_get_system_info(DMI_BOARD_NAME);
- if (!board)
- board = "";
+ vendor = dmi_get_system_info(DMI_SYS_VENDOR);
+ if (!vendor)
+ vendor = "";
product = dmi_get_system_info(DMI_PRODUCT_NAME);
if (!product)
product = "";
+ /* Board Name is optional */
+ board = dmi_get_system_info(DMI_BOARD_NAME);
+
printk(KERN_CONT "\n");
- printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
+ printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s",
current->pid, current->comm, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
- init_utsname()->version, board, product);
+ init_utsname()->version);
+ printk(KERN_CONT " %s %s", vendor, product);
+ if (board)
+ printk(KERN_CONT "/%s", board);
+ printk(KERN_CONT "\n");
}
void flush_thread(void)
@@ -506,7 +513,7 @@ static void poll_idle(void)
#define MWAIT_ECX_EXTENDED_INFO 0x01
#define MWAIT_EDX_C1 0xf0
-int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+int mwait_usable(const struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index bd387e8f73b..6c9dd922ac0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -501,6 +501,10 @@ void set_personality_64bit(void)
/* Make sure to be in 64bit mode */
clear_thread_flag(TIF_IA32);
+ /* Ensure the corresponding mm is not marked. */
+ if (current->mm)
+ current->mm->context.ia32_compat = 0;
+
/* TBD: overwrites user setup. Should have two bits.
But 64bit processes have always behaved this way,
so it's not too bad. The main problem is just that
@@ -516,6 +520,10 @@ void set_personality_ia32(void)
set_thread_flag(TIF_IA32);
current->personality |= force_personality32;
+ /* Mark the associated mm as containing 32-bit tasks. */
+ if (current->mm)
+ current->mm->context.ia32_compat = 1;
+
/* Prepare the first "return" to user space */
current_thread_info()->status |= TS_COMPAT;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 45892dc4b72..f65e5b521db 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -608,6 +608,9 @@ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
unsigned len, type;
struct perf_event *bp;
+ if (ptrace_get_breakpoints(tsk) < 0)
+ return -ESRCH;
+
data &= ~DR_CONTROL_RESERVED;
old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
restore:
@@ -655,6 +658,9 @@ restore:
}
goto restore;
}
+
+ ptrace_put_breakpoints(tsk);
+
return ((orig_ret < 0) ? orig_ret : rc);
}
@@ -668,10 +674,17 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
if (n < HBP_NUM) {
struct perf_event *bp;
+
+ if (ptrace_get_breakpoints(tsk) < 0)
+ return -ESRCH;
+
bp = thread->ptrace_bps[n];
if (!bp)
- return 0;
- val = bp->hw.info.address;
+ val = 0;
+ else
+ val = bp->hw.info.address;
+
+ ptrace_put_breakpoints(tsk);
} else if (n == 6) {
val = thread->debugreg6;
} else if (n == 7) {
@@ -686,6 +699,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
struct perf_event *bp;
struct thread_struct *t = &tsk->thread;
struct perf_event_attr attr;
+ int err = 0;
+
+ if (ptrace_get_breakpoints(tsk) < 0)
+ return -ESRCH;
if (!t->ptrace_bps[nr]) {
ptrace_breakpoint_init(&attr);
@@ -709,24 +726,23 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
* writing for the user. And anyway this is the previous
* behaviour.
*/
- if (IS_ERR(bp))
- return PTR_ERR(bp);
+ if (IS_ERR(bp)) {
+ err = PTR_ERR(bp);
+ goto put;
+ }
t->ptrace_bps[nr] = bp;
} else {
- int err;
-
bp = t->ptrace_bps[nr];
attr = bp->attr;
attr.bp_addr = addr;
err = modify_user_hw_breakpoint(bp, &attr);
- if (err)
- return err;
}
-
- return 0;
+put:
+ ptrace_put_breakpoints(tsk);
+ return err;
}
/*
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index fc7aae1e2bc..08c44b08bf5 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -6,6 +6,7 @@
#include <linux/dmi.h>
#include <linux/sched.h>
#include <linux/tboot.h>
+#include <linux/delay.h>
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
@@ -285,6 +286,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
+ { /* Handle problems with rebooting on VersaLogic Menlow boards */
+ .callback = set_bios_reboot,
+ .ident = "VersaLogic Menlow based board",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
+ DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
+ },
+ },
{ }
};
@@ -295,68 +304,16 @@ static int __init reboot_init(void)
}
core_initcall(reboot_init);
-/* The following code and data reboots the machine by switching to real
- mode and jumping to the BIOS reset entry point, as if the CPU has
- really been reset. The previous version asked the keyboard
- controller to pulse the CPU reset line, which is more thorough, but
- doesn't work with at least one type of 486 motherboard. It is easy
- to stop this code working; hence the copious comments. */
-static const unsigned long long
-real_mode_gdt_entries [3] =
-{
- 0x0000000000000000ULL, /* Null descriptor */
- 0x00009b000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */
- 0x000093000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */
-};
+extern const unsigned char machine_real_restart_asm[];
+extern const u64 machine_real_restart_gdt[3];
-static const struct desc_ptr
-real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries },
-real_mode_idt = { 0x3ff, 0 };
-
-/* This is 16-bit protected mode code to disable paging and the cache,
- switch to real mode and jump to the BIOS reset code.
-
- The instruction that switches to real mode by writing to CR0 must be
- followed immediately by a far jump instruction, which set CS to a
- valid value for real mode, and flushes the prefetch queue to avoid
- running instructions that have already been decoded in protected
- mode.
-
- Clears all the flags except ET, especially PG (paging), PE
- (protected-mode enable) and TS (task switch for coprocessor state
- save). Flushes the TLB after paging has been disabled. Sets CD and
- NW, to disable the cache on a 486, and invalidates the cache. This
- is more like the state of a 486 after reset. I don't know if
- something else should be done for other chips.
-
- More could be done here to set up the registers as if a CPU reset had
- occurred; hopefully real BIOSs don't assume much. */
-static const unsigned char real_mode_switch [] =
-{
- 0x66, 0x0f, 0x20, 0xc0, /* movl %cr0,%eax */
- 0x66, 0x83, 0xe0, 0x11, /* andl $0x00000011,%eax */
- 0x66, 0x0d, 0x00, 0x00, 0x00, 0x60, /* orl $0x60000000,%eax */
- 0x66, 0x0f, 0x22, 0xc0, /* movl %eax,%cr0 */
- 0x66, 0x0f, 0x22, 0xd8, /* movl %eax,%cr3 */
- 0x66, 0x0f, 0x20, 0xc3, /* movl %cr0,%ebx */
- 0x66, 0x81, 0xe3, 0x00, 0x00, 0x00, 0x60, /* andl $0x60000000,%ebx */
- 0x74, 0x02, /* jz f */
- 0x0f, 0x09, /* wbinvd */
- 0x24, 0x10, /* f: andb $0x10,al */
- 0x66, 0x0f, 0x22, 0xc0 /* movl %eax,%cr0 */
-};
-static const unsigned char jump_to_bios [] =
+void machine_real_restart(unsigned int type)
{
- 0xea, 0x00, 0x00, 0xff, 0xff /* ljmp $0xffff,$0x0000 */
-};
+ void *restart_va;
+ unsigned long restart_pa;
+ void (*restart_lowmem)(unsigned int);
+ u64 *lowmem_gdt;
-/*
- * Switch to real mode and then execute the code
- * specified by the code and length parameters.
- * We assume that length will aways be less that 100!
- */
-void machine_real_restart(const unsigned char *code, int length)
-{
local_irq_disable();
/* Write zero to CMOS register number 0x0f, which the BIOS POST
@@ -384,41 +341,23 @@ void machine_real_restart(const unsigned char *code, int length)
too. */
*((unsigned short *)0x472) = reboot_mode;
- /* For the switch to real mode, copy some code to low memory. It has
- to be in the first 64k because it is running in 16-bit mode, and it
- has to have the same physical and virtual address, because it turns
- off paging. Copy it near the end of the first page, out of the way
- of BIOS variables. */
- memcpy((void *)(0x1000 - sizeof(real_mode_switch) - 100),
- real_mode_switch, sizeof (real_mode_switch));
- memcpy((void *)(0x1000 - 100), code, length);
-
- /* Set up the IDT for real mode. */
- load_idt(&real_mode_idt);
-
- /* Set up a GDT from which we can load segment descriptors for real
- mode. The GDT is not used in real mode; it is just needed here to
- prepare the descriptors. */
- load_gdt(&real_mode_gdt);
-
- /* Load the data segment registers, and thus the descriptors ready for
- real mode. The base address of each segment is 0x100, 16 times the
- selector value being loaded here. This is so that the segment
- registers don't have to be reloaded after switching to real mode:
- the values are consistent for real mode operation already. */
- __asm__ __volatile__ ("movl $0x0010,%%eax\n"
- "\tmovl %%eax,%%ds\n"
- "\tmovl %%eax,%%es\n"
- "\tmovl %%eax,%%fs\n"
- "\tmovl %%eax,%%gs\n"
- "\tmovl %%eax,%%ss" : : : "eax");
-
- /* Jump to the 16-bit code that we copied earlier. It disables paging
- and the cache, switches to real mode, and jumps to the BIOS reset
- entry point. */
- __asm__ __volatile__ ("ljmp $0x0008,%0"
- :
- : "i" ((void *)(0x1000 - sizeof (real_mode_switch) - 100)));
+ /* Patch the GDT in the low memory trampoline */
+ lowmem_gdt = TRAMPOLINE_SYM(machine_real_restart_gdt);
+
+ restart_va = TRAMPOLINE_SYM(machine_real_restart_asm);
+ restart_pa = virt_to_phys(restart_va);
+ restart_lowmem = (void (*)(unsigned int))restart_pa;
+
+ /* GDT[0]: GDT self-pointer */
+ lowmem_gdt[0] =
+ (u64)(sizeof(machine_real_restart_gdt) - 1) +
+ ((u64)virt_to_phys(lowmem_gdt) << 16);
+ /* GDT[1]: 64K real mode code segment */
+ lowmem_gdt[1] =
+ GDT_ENTRY(0x009b, restart_pa, 0xffff);
+
+ /* Jump to the identity-mapped low memory code */
+ restart_lowmem(type);
}
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(machine_real_restart);
@@ -573,7 +512,7 @@ static void native_machine_emergency_restart(void)
#ifdef CONFIG_X86_32
case BOOT_BIOS:
- machine_real_restart(jump_to_bios, sizeof(jump_to_bios));
+ machine_real_restart(MRR_BIOS);
reboot_type = BOOT_KBD;
break;
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S
new file mode 100644
index 00000000000..1d5c46df0d7
--- /dev/null
+++ b/arch/x86/kernel/reboot_32.S
@@ -0,0 +1,135 @@
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/segment.h>
+#include <asm/page_types.h>
+
+/*
+ * The following code and data reboots the machine by switching to real
+ * mode and jumping to the BIOS reset entry point, as if the CPU has
+ * really been reset. The previous version asked the keyboard
+ * controller to pulse the CPU reset line, which is more thorough, but
+ * doesn't work with at least one type of 486 motherboard. It is easy
+ * to stop this code working; hence the copious comments.
+ *
+ * This code is called with the restart type (0 = BIOS, 1 = APM) in %eax.
+ */
+ .section ".x86_trampoline","a"
+ .balign 16
+ .code32
+ENTRY(machine_real_restart_asm)
+r_base = .
+ /* Get our own relocated address */
+ call 1f
+1: popl %ebx
+ subl $(1b - r_base), %ebx
+
+ /* Compute the equivalent real-mode segment */
+ movl %ebx, %ecx
+ shrl $4, %ecx
+
+ /* Patch post-real-mode segment jump */
+ movw (dispatch_table - r_base)(%ebx,%eax,2),%ax
+ movw %ax, (101f - r_base)(%ebx)
+ movw %cx, (102f - r_base)(%ebx)
+
+ /* Set up the IDT for real mode. */
+ lidtl (machine_real_restart_idt - r_base)(%ebx)
+
+ /*
+ * Set up a GDT from which we can load segment descriptors for real
+ * mode. The GDT is not used in real mode; it is just needed here to
+ * prepare the descriptors.
+ */
+ lgdtl (machine_real_restart_gdt - r_base)(%ebx)
+
+ /*
+ * Load the data segment registers with 16-bit compatible values
+ */
+ movl $16, %ecx
+ movl %ecx, %ds
+ movl %ecx, %es
+ movl %ecx, %fs
+ movl %ecx, %gs
+ movl %ecx, %ss
+ ljmpl $8, $1f - r_base
+
+/*
+ * This is 16-bit protected mode code to disable paging and the cache,
+ * switch to real mode and jump to the BIOS reset code.
+ *
+ * The instruction that switches to real mode by writing to CR0 must be
+ * followed immediately by a far jump instruction, which set CS to a
+ * valid value for real mode, and flushes the prefetch queue to avoid
+ * running instructions that have already been decoded in protected
+ * mode.
+ *
+ * Clears all the flags except ET, especially PG (paging), PE
+ * (protected-mode enable) and TS (task switch for coprocessor state
+ * save). Flushes the TLB after paging has been disabled. Sets CD and
+ * NW, to disable the cache on a 486, and invalidates the cache. This
+ * is more like the state of a 486 after reset. I don't know if
+ * something else should be done for other chips.
+ *
+ * More could be done here to set up the registers as if a CPU reset had
+ * occurred; hopefully real BIOSs don't assume much. This is not the
+ * actual BIOS entry point, anyway (that is at 0xfffffff0).
+ *
+ * Most of this work is probably excessive, but it is what is tested.
+ */
+ .code16
+1:
+ xorl %ecx, %ecx
+ movl %cr0, %eax
+ andl $0x00000011, %eax
+ orl $0x60000000, %eax
+ movl %eax, %cr0
+ movl %ecx, %cr3
+ movl %cr0, %edx
+ andl $0x60000000, %edx /* If no cache bits -> no wbinvd */
+ jz 2f
+ wbinvd
+2:
+ andb $0x10, %al
+ movl %eax, %cr0
+ .byte 0xea /* ljmpw */
+101: .word 0 /* Offset */
+102: .word 0 /* Segment */
+
+bios:
+ ljmpw $0xf000, $0xfff0
+
+apm:
+ movw $0x1000, %ax
+ movw %ax, %ss
+ movw $0xf000, %sp
+ movw $0x5307, %ax
+ movw $0x0001, %bx
+ movw $0x0003, %cx
+ int $0x15
+
+END(machine_real_restart_asm)
+
+ .balign 16
+ /* These must match <asm/reboot.h */
+dispatch_table:
+ .word bios - r_base
+ .word apm - r_base
+END(dispatch_table)
+
+ .balign 16
+machine_real_restart_idt:
+ .word 0xffff /* Length - real mode default value */
+ .long 0 /* Base - real mode default value */
+END(machine_real_restart_idt)
+
+ .balign 16
+ENTRY(machine_real_restart_gdt)
+ .quad 0 /* Self-pointer, filled in by PM code */
+ .quad 0 /* 16-bit code segment, filled in by PM code */
+ /*
+ * 16-bit data segment with the selector value 16 = 0x10 and
+ * base value 0x100; since this is consistent with real mode
+ * semantics we don't have to reload the segments once CR0.PE = 0.
+ */
+ .quad GDT_ENTRY(0x0093, 0x100, 0xffff)
+END(machine_real_restart_gdt)
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 6f39cab052d..3f2ad2640d8 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -6,6 +6,7 @@
#include <linux/acpi.h>
#include <linux/bcd.h>
#include <linux/pnp.h>
+#include <linux/of.h>
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
@@ -236,6 +237,8 @@ static __init int add_rtc_cmos(void)
}
}
#endif
+ if (of_have_populated_dt())
+ return 0;
platform_device_register(&rtc_device);
dev_info(&rtc_device.dev,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d3cfe26c025..4be9b398470 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -113,6 +113,7 @@
#endif
#include <asm/mce.h>
#include <asm/alternative.h>
+#include <asm/prom.h>
/*
* end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -297,6 +298,9 @@ static void __init init_gbpages(void)
static inline void init_gbpages(void)
{
}
+static void __init cleanup_highmap(void)
+{
+}
#endif
static void __init reserve_brk(void)
@@ -429,16 +433,30 @@ static void __init parse_setup_data(void)
return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
- data = early_memremap(pa_data, PAGE_SIZE);
+ u32 data_len, map_len;
+
+ map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
+ (u64)sizeof(struct setup_data));
+ data = early_memremap(pa_data, map_len);
+ data_len = data->len + sizeof(struct setup_data);
+ if (data_len > map_len) {
+ early_iounmap(data, map_len);
+ data = early_memremap(pa_data, data_len);
+ map_len = data_len;
+ }
+
switch (data->type) {
case SETUP_E820_EXT:
- parse_e820_ext(data, pa_data);
+ parse_e820_ext(data);
+ break;
+ case SETUP_DTB:
+ add_dtb(pa_data);
break;
default:
break;
}
pa_data = data->next;
- early_iounmap(data, PAGE_SIZE);
+ early_iounmap(data, map_len);
}
}
@@ -601,28 +619,6 @@ void __init reserve_standard_io_resources(void)
}
-/*
- * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
- * is_kdump_kernel() to determine if we are booting after a panic. Hence
- * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
- */
-
-#ifdef CONFIG_CRASH_DUMP
-/* elfcorehdr= specifies the location of elf core header
- * stored by the crashed kernel. This option will be passed
- * by kexec loader to the capture kernel.
- */
-static int __init setup_elfcorehdr(char *arg)
-{
- char *end;
- if (!arg)
- return -EINVAL;
- elfcorehdr_addr = memparse(arg, &end);
- return end > arg ? 0 : -EINVAL;
-}
-early_param("elfcorehdr", setup_elfcorehdr);
-#endif
-
static __init void reserve_ibft_region(void)
{
unsigned long addr, size = 0;
@@ -680,15 +676,6 @@ static int __init parse_reservelow(char *p)
early_param("reservelow", parse_reservelow);
-static u64 __init get_max_mapped(void)
-{
- u64 end = max_pfn_mapped;
-
- end <<= PAGE_SHIFT;
-
- return end;
-}
-
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -704,8 +691,6 @@ static u64 __init get_max_mapped(void)
void __init setup_arch(char **cmdline_p)
{
- int acpi = 0;
- int amd = 0;
unsigned long flags;
#ifdef CONFIG_X86_32
@@ -922,6 +907,8 @@ void __init setup_arch(char **cmdline_p)
*/
reserve_brk();
+ cleanup_highmap();
+
memblock.current_limit = get_max_mapped();
memblock_x86_fill();
@@ -935,15 +922,8 @@ void __init setup_arch(char **cmdline_p)
printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
- reserve_trampoline_memory();
+ setup_trampolines();
-#ifdef CONFIG_ACPI_SLEEP
- /*
- * Reserve low memory region for sleep support.
- * even before init_memory_mapping
- */
- acpi_reserve_wakeup_memory();
-#endif
init_gbpages();
/* max_pfn_mapped is updated here */
@@ -984,19 +964,7 @@ void __init setup_arch(char **cmdline_p)
early_acpi_boot_init();
-#ifdef CONFIG_ACPI_NUMA
- /*
- * Parse SRAT to discover nodes.
- */
- acpi = acpi_numa_init();
-#endif
-
-#ifdef CONFIG_AMD_NUMA
- if (!acpi)
- amd = !amd_numa_init(0, max_pfn);
-#endif
-
- initmem_init(0, max_pfn, acpi, amd);
+ initmem_init();
memblock_find_dma_reserve();
dma32_reserve_bootmem();
@@ -1008,6 +976,11 @@ void __init setup_arch(char **cmdline_p)
paging_init();
x86_init.paging.pagetable_setup_done(swapper_pg_dir);
+ if (boot_cpu_data.cpuid_level >= 0) {
+ /* A CPU has %cr4 if and only if it has CPUID */
+ mmu_cr4_features = read_cr4();
+ }
+
#ifdef CONFIG_X86_32
/* sync back kernel address range */
clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
@@ -1029,8 +1002,8 @@ void __init setup_arch(char **cmdline_p)
* Read APIC and some other early information from ACPI tables.
*/
acpi_boot_init();
-
sfi_init();
+ x86_dtb_init();
/*
* get boot-time SMP configuration:
@@ -1040,9 +1013,7 @@ void __init setup_arch(char **cmdline_p)
prefill_possible_map();
-#ifdef CONFIG_X86_64
init_cpu_to_node();
-#endif
init_apic_mappings();
ioapic_and_gsi_init();
@@ -1066,6 +1037,8 @@ void __init setup_arch(char **cmdline_p)
#endif
x86_init.oem.banner();
+ x86_init.timers.wallclock_init();
+
mcheck_init();
local_irq_save(flags);
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 002b79685f7..71f4727da37 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -225,10 +225,15 @@ void __init setup_per_cpu_areas(void)
per_cpu(x86_bios_cpu_apicid, cpu) =
early_per_cpu_map(x86_bios_cpu_apicid, cpu);
#endif
+#ifdef CONFIG_X86_32
+ per_cpu(x86_cpu_to_logical_apicid, cpu) =
+ early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
+#endif
#ifdef CONFIG_X86_64
per_cpu(irq_stack_ptr, cpu) =
per_cpu(irq_stack_union.irq_stack, cpu) +
IRQ_STACK_SIZE - 64;
+#endif
#ifdef CONFIG_NUMA
per_cpu(x86_cpu_to_node_map, cpu) =
early_per_cpu_map(x86_cpu_to_node_map, cpu);
@@ -242,7 +247,6 @@ void __init setup_per_cpu_areas(void)
*/
set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
#endif
-#endif
/*
* Up to this point, the boot CPU has been using .init.data
* area. Reload any changed state for the boot CPU.
@@ -256,7 +260,10 @@ void __init setup_per_cpu_areas(void)
early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
#endif
-#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+#ifdef CONFIG_X86_32
+ early_per_cpu_ptr(x86_cpu_to_logical_apicid) = NULL;
+#endif
+#ifdef CONFIG_NUMA
early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
#endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 03273b6c272..c2871d3c71b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -64,6 +64,7 @@
#include <asm/mtrr.h>
#include <asm/mwait.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
@@ -71,10 +72,6 @@
#include <asm/smpboot_hooks.h>
#include <asm/i8259.h>
-#ifdef CONFIG_X86_32
-u8 apicid_2_node[MAX_APICID];
-#endif
-
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -130,68 +127,14 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
+
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
atomic_t init_deasserted;
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-/* which node each logical CPU is on */
-int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
-EXPORT_SYMBOL(cpu_to_node_map);
-
-/* set up a mapping between cpu and node. */
-static void map_cpu_to_node(int cpu, int node)
-{
- printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
- cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
- cpu_to_node_map[cpu] = node;
-}
-
-/* undo a mapping between cpu and node. */
-static void unmap_cpu_to_node(int cpu)
-{
- int node;
-
- printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
- for (node = 0; node < MAX_NUMNODES; node++)
- cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
- cpu_to_node_map[cpu] = 0;
-}
-#else /* !(CONFIG_NUMA && CONFIG_X86_32) */
-#define map_cpu_to_node(cpu, node) ({})
-#define unmap_cpu_to_node(cpu) ({})
-#endif
-
-#ifdef CONFIG_X86_32
-static int boot_cpu_logical_apicid;
-
-u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
- { [0 ... NR_CPUS-1] = BAD_APICID };
-
-static void map_cpu_to_logical_apicid(void)
-{
- int cpu = smp_processor_id();
- int apicid = logical_smp_processor_id();
- int node = apic->apicid_to_node(apicid);
-
- if (!node_online(node))
- node = first_online_node;
-
- cpu_2_logical_apicid[cpu] = apicid;
- map_cpu_to_node(cpu, node);
-}
-
-void numa_remove_cpu(int cpu)
-{
- cpu_2_logical_apicid[cpu] = BAD_APICID;
- unmap_cpu_to_node(cpu);
-}
-#else
-#define map_cpu_to_logical_apicid() do {} while (0)
-#endif
-
/*
* Report back to the Boot Processor.
* Running on AP.
@@ -259,7 +202,6 @@ static void __cpuinit smp_callin(void)
apic->smp_callin_clear_local_apic();
setup_local_APIC();
end_local_APIC_setup();
- map_cpu_to_logical_apicid();
/*
* Need to setup vector mappings before we enable interrupts.
@@ -355,23 +297,6 @@ notrace static void __cpuinit start_secondary(void *unused)
cpu_idle();
}
-#ifdef CONFIG_CPUMASK_OFFSTACK
-/* In this case, llc_shared_map is a pointer to a cpumask. */
-static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
- const struct cpuinfo_x86 *src)
-{
- struct cpumask *llc = dst->llc_shared_map;
- *dst = *src;
- dst->llc_shared_map = llc;
-}
-#else
-static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
- const struct cpuinfo_x86 *src)
-{
- *dst = *src;
-}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
-
/*
* The bootstrap kernel entry code has set these up. Save them for
* a given CPU
@@ -381,7 +306,7 @@ void __cpuinit smp_store_cpu_info(int id)
{
struct cpuinfo_x86 *c = &cpu_data(id);
- copy_cpuinfo_x86(c, &boot_cpu_data);
+ *c = boot_cpu_data;
c->cpu_index = id;
if (id != 0)
identify_secondary_cpu(c);
@@ -389,15 +314,12 @@ void __cpuinit smp_store_cpu_info(int id)
static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
{
- struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
- struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
-
cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
- cpumask_set_cpu(cpu1, c2->llc_shared_map);
- cpumask_set_cpu(cpu2, c1->llc_shared_map);
+ cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
+ cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
}
@@ -414,6 +336,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
if (c->phys_proc_id == o->phys_proc_id &&
+ per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
c->compute_unit_id == o->compute_unit_id)
link_thread_siblings(cpu, i);
} else if (c->phys_proc_id == o->phys_proc_id &&
@@ -425,7 +348,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
}
- cpumask_set_cpu(cpu, c->llc_shared_map);
+ cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
@@ -436,8 +359,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
for_each_cpu(i, cpu_sibling_setup_mask) {
if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
- cpumask_set_cpu(i, c->llc_shared_map);
- cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
+ cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
}
if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
cpumask_set_cpu(i, cpu_core_mask(cpu));
@@ -476,7 +399,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
!(cpu_has(c, X86_FEATURE_AMD_DCM)))
return cpu_core_mask(cpu);
else
- return c->llc_shared_map;
+ return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
@@ -788,7 +711,7 @@ do_rest:
stack_start = c_idle.idle->thread.sp;
/* start_ip had better be page-aligned! */
- start_ip = setup_trampoline();
+ start_ip = trampoline_address();
/* So we see what's up */
announce_cpu(cpu, apicid);
@@ -798,6 +721,8 @@ do_rest:
* the targeted processor.
*/
+ printk(KERN_DEBUG "smpboot cpu %d: start_ip = %lx\n", cpu, start_ip);
+
atomic_set(&init_deasserted, 0);
if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
@@ -851,8 +776,8 @@ do_rest:
pr_debug("CPU%d: has booted.\n", cpu);
else {
boot_error = 1;
- if (*((volatile unsigned char *)trampoline_base)
- == 0xA5)
+ if (*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status)
+ == 0xA5A5A5A5)
/* trampoline started but...? */
pr_err("CPU%d: Stuck ??\n", cpu);
else
@@ -878,7 +803,7 @@ do_rest:
}
/* mark "stuck" area as not stuck */
- *((volatile unsigned long *)trampoline_base) = 0;
+ *(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) = 0;
if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
/*
@@ -945,6 +870,14 @@ int __cpuinit native_cpu_up(unsigned int cpu)
return 0;
}
+/**
+ * arch_disable_smp_support() - disables SMP support for x86 at runtime
+ */
+void arch_disable_smp_support(void)
+{
+ disable_ioapic_support();
+}
+
/*
* Fall back to non SMP mode after errors.
*
@@ -960,7 +893,6 @@ static __init void disable_smp(void)
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
physid_set_mask_of_physid(0, &phys_cpu_present_map);
- map_cpu_to_logical_apicid();
cpumask_set_cpu(0, cpu_sibling_mask(0));
cpumask_set_cpu(0, cpu_core_mask(0));
}
@@ -1045,7 +977,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
"(tell your hw vendor)\n");
}
smpboot_clear_io_apic();
- arch_disable_smp_support();
+ disable_ioapic_support();
return -1;
}
@@ -1060,7 +992,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
connect_bsp_APIC();
setup_local_APIC();
- end_local_APIC_setup();
+ bsp_end_local_APIC_setup();
return -1;
}
@@ -1089,21 +1021,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
preempt_disable();
smp_cpu_index_default();
- memcpy(__this_cpu_ptr(&cpu_info), &boot_cpu_data, sizeof(cpu_info));
- cpumask_copy(cpu_callin_mask, cpumask_of(0));
- mb();
+
/*
* Setup boot CPU information
*/
smp_store_cpu_info(0); /* Final full version of the data */
-#ifdef CONFIG_X86_32
- boot_cpu_logical_apicid = logical_smp_processor_id();
-#endif
+ cpumask_copy(cpu_callin_mask, cpumask_of(0));
+ mb();
+
current_thread_info()->cpu = 0; /* needed? */
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
@@ -1137,9 +1067,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
if (!skip_ioapic_setup && nr_ioapics)
enable_IO_APIC();
- end_local_APIC_setup();
-
- map_cpu_to_logical_apicid();
+ bsp_end_local_APIC_setup();
if (apic->setup_portio_remap)
apic->setup_portio_remap();
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 938c8e10a19..6515733a289 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -73,7 +73,7 @@ static const struct stacktrace_ops save_stack_ops_nosched = {
*/
void save_stack_trace(struct stack_trace *trace)
{
- dump_trace(current, NULL, NULL, &save_stack_ops, trace);
+ dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
@@ -81,14 +81,14 @@ EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
{
- dump_trace(current, regs, NULL, &save_stack_ops, trace);
+ dump_trace(current, regs, NULL, 0, &save_stack_ops, trace);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
- dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace);
+ dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 58de45ee08b..7977f0cfe33 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -166,7 +166,7 @@ static void enable_step(struct task_struct *child, bool block)
* Make sure block stepping (BTF) is not enabled unless it should be.
* Note that we don't try to worry about any is_setting_trap_flag()
* instructions after the first when using block stepping.
- * So noone should try to use debugger block stepping in a program
+ * So no one should try to use debugger block stepping in a program
* that uses user-mode single stepping itself.
*/
if (enable_single_step(child) && block) {
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index b35786dc9b8..abce34d5c79 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -340,3 +340,7 @@ ENTRY(sys_call_table)
.long sys_fanotify_init
.long sys_fanotify_mark
.long sys_prlimit64 /* 340 */
+ .long sys_name_to_handle_at
+ .long sys_open_by_handle_at
+ .long sys_clock_adjtime
+ .long sys_syncfs
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 7e4515957a1..8927486a464 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -39,7 +39,7 @@ int __ref arch_register_cpu(int num)
/*
* CPU0 cannot be offlined due to several
* restrictions and assumptions in kernel. This basically
- * doesnt add a control file, one cannot attempt to offline
+ * doesn't add a control file, one cannot attempt to offline
* BSP.
*
* Also certain PCI quirks require not to enable hotplug control
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index a375616d77f..a91ae7709b4 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -2,39 +2,41 @@
#include <linux/memblock.h>
#include <asm/trampoline.h>
+#include <asm/cacheflush.h>
#include <asm/pgtable.h>
-#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
-#define __trampinit
-#define __trampinitdata
-#else
-#define __trampinit __cpuinit
-#define __trampinitdata __cpuinitdata
-#endif
+unsigned char *x86_trampoline_base;
-/* ready for x86_64 and x86 */
-unsigned char *__trampinitdata trampoline_base;
-
-void __init reserve_trampoline_memory(void)
+void __init setup_trampolines(void)
{
phys_addr_t mem;
+ size_t size = PAGE_ALIGN(x86_trampoline_end - x86_trampoline_start);
/* Has to be in very low memory so we can execute real-mode AP code. */
- mem = memblock_find_in_range(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
if (mem == MEMBLOCK_ERROR)
panic("Cannot allocate trampoline\n");
- trampoline_base = __va(mem);
- memblock_x86_reserve_range(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
+ x86_trampoline_base = __va(mem);
+ memblock_x86_reserve_range(mem, mem + size, "TRAMPOLINE");
+
+ printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
+ x86_trampoline_base, (unsigned long long)mem, size);
+
+ memcpy(x86_trampoline_base, x86_trampoline_start, size);
}
/*
- * Currently trivial. Write the real->protected mode
- * bootstrap into the page concerned. The caller
- * has made sure it's suitably aligned.
+ * setup_trampolines() gets called very early, to guarantee the
+ * availability of low memory. This is before the proper kernel page
+ * tables are set up, so we cannot set page permissions in that
+ * function. Thus, we use an arch_initcall instead.
*/
-unsigned long __trampinit setup_trampoline(void)
+static int __init configure_trampolines(void)
{
- memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
- return virt_to_phys(trampoline_base);
+ size_t size = PAGE_ALIGN(x86_trampoline_end - x86_trampoline_start);
+
+ set_memory_x((unsigned long)x86_trampoline_base, size >> PAGE_SHIFT);
+ return 0;
}
+arch_initcall(configure_trampolines);
diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S
index 8508237e8e4..451c0a7ef7f 100644
--- a/arch/x86/kernel/trampoline_32.S
+++ b/arch/x86/kernel/trampoline_32.S
@@ -32,9 +32,11 @@
#include <asm/segment.h>
#include <asm/page_types.h>
-/* We can free up trampoline after bootup if cpu hotplug is not supported. */
-__CPUINITRODATA
-.code16
+#ifdef CONFIG_SMP
+
+ .section ".x86_trampoline","a"
+ .balign PAGE_SIZE
+ .code16
ENTRY(trampoline_data)
r_base = .
@@ -44,7 +46,7 @@ r_base = .
cli # We should be safe anyway
- movl $0xA5A5A5A5, trampoline_data - r_base
+ movl $0xA5A5A5A5, trampoline_status - r_base
# write marker for master knows we're running
/* GDT tables in non default location kernel can be beyond 16MB and
@@ -72,5 +74,10 @@ boot_idt_descr:
.word 0 # idt limit = 0
.long 0 # idt base = 0L
+ENTRY(trampoline_status)
+ .long 0
+
.globl trampoline_end
trampoline_end:
+
+#endif /* CONFIG_SMP */
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 075d130efcf..09ff51799e9 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -32,13 +32,9 @@
#include <asm/segment.h>
#include <asm/processor-flags.h>
-#ifdef CONFIG_ACPI_SLEEP
-.section .rodata, "a", @progbits
-#else
-/* We can free up the trampoline after bootup if cpu hotplug is not supported. */
-__CPUINITRODATA
-#endif
-.code16
+ .section ".x86_trampoline","a"
+ .balign PAGE_SIZE
+ .code16
ENTRY(trampoline_data)
r_base = .
@@ -50,7 +46,7 @@ r_base = .
mov %ax, %ss
- movl $0xA5A5A5A5, trampoline_data - r_base
+ movl $0xA5A5A5A5, trampoline_status - r_base
# write marker for master knows we're running
# Setup stack
@@ -64,10 +60,13 @@ r_base = .
movzx %ax, %esi # Find the 32bit trampoline location
shll $4, %esi
- # Fixup the vectors
- addl %esi, startup_32_vector - r_base
- addl %esi, startup_64_vector - r_base
- addl %esi, tgdt + 2 - r_base # Fixup the gdt pointer
+ # Fixup the absolute vectors
+ leal (startup_32 - r_base)(%esi), %eax
+ movl %eax, startup_32_vector - r_base
+ leal (startup_64 - r_base)(%esi), %eax
+ movl %eax, startup_64_vector - r_base
+ leal (tgdt - r_base)(%esi), %eax
+ movl %eax, (tgdt + 2 - r_base)
/*
* GDT tables in non default location kernel can be beyond 16MB and
@@ -129,6 +128,7 @@ no_longmode:
jmp no_longmode
#include "verify_cpu.S"
+ .balign 4
# Careful these need to be in the same 64K segment as the above;
tidt:
.word 0 # idt limit = 0
@@ -156,6 +156,10 @@ startup_64_vector:
.long startup_64 - r_base
.word __KERNEL_CS, 0
+ .balign 4
+ENTRY(trampoline_status)
+ .long 0
+
trampoline_stack:
.org 0x1000
trampoline_stack_end:
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ffe5755caa8..9335bf7dd2e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -427,7 +427,7 @@ unsigned long native_calibrate_tsc(void)
* the delta to the previous read. We keep track of the min
* and max values of that delta. The delta is mostly defined
* by the IO time of the PIT access, so we can detect when a
- * SMI/SMM disturbance happend between the two reads. If the
+ * SMI/SMM disturbance happened between the two reads. If the
* maximum time is significantly larger than the minimum time,
* then we discard the result and have another try.
*
@@ -900,7 +900,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
* timer based, instead of loop based, we don't block the boot
* process while this longer calibration is done.
*
- * If there are any calibration anomolies (too many SMIs, etc),
+ * If there are any calibration anomalies (too many SMIs, etc),
* or the refined calibration is off by 1% of the fast early
* calibration, we throw out the new calibration and use the
* early calibration.
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 0edefc19a11..b9242bacbe5 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -18,7 +18,7 @@
* This file is expected to run in 32bit code. Currently:
*
* arch/x86/boot/compressed/head_64.S: Boot cpu verification
- * arch/x86/kernel/trampoline_64.S: secondary processor verfication
+ * arch/x86/kernel/trampoline_64.S: secondary processor verification
* arch/x86/kernel/head_32.S: processor startup
*
* verify_cpu, returns the status of longmode and SSE in register %eax.
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bf470075518..624a2016198 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -105,6 +105,7 @@ SECTIONS
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ENTRY_TEXT
IRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
@@ -230,7 +231,7 @@ SECTIONS
* output PHDR, so the next output section - .init.text - should
* start another segment - init.
*/
- PERCPU_VADDR(0, :percpu)
+ PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
#endif
INIT_TEXT_SECTION(PAGE_SIZE)
@@ -240,6 +241,18 @@ SECTIONS
INIT_DATA_SECTION(16)
+ /*
+ * Code and data for a variety of lowlevel trampolines, to be
+ * copied into base memory (< 1 MiB) during initialization.
+ * Since it is copied early, the main copy can be discarded
+ * afterwards.
+ */
+ .x86_trampoline : AT(ADDR(.x86_trampoline) - LOAD_OFFSET) {
+ x86_trampoline_start = .;
+ *(.x86_trampoline)
+ x86_trampoline_end = .;
+ }
+
.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
__x86_cpu_dev_start = .;
*(.x86_cpu_dev.init)
@@ -291,6 +304,7 @@ SECTIONS
*(.iommu_table)
__iommu_table_end = .;
}
+
. = ALIGN(8);
/*
* .exit.text is discard at runtime, not link time, to deal with
@@ -305,7 +319,7 @@ SECTIONS
}
#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
- PERCPU(THREAD_SIZE)
+ PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE)
#endif
. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 1b950d151e5..9796c2f3d07 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -52,6 +52,7 @@ extern void *__memcpy(void *, const void *, __kernel_size_t);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(memmove);
EXPORT_SYMBOL(empty_zero_page);
#ifndef CONFIG_PARAVIRT
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index ceb2911aa43..75ef4b18e9b 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -61,6 +61,10 @@ struct x86_init_ops x86_init __initdata = {
.banner = default_banner,
},
+ .mapping = {
+ .pagetable_reserve = native_pagetable_reserve,
+ },
+
.paging = {
.pagetable_setup_start = native_pagetable_setup_start,
.pagetable_setup_done = native_pagetable_setup_done,
@@ -70,6 +74,7 @@ struct x86_init_ops x86_init __initdata = {
.setup_percpu_clockev = setup_boot_APIC_clock,
.tsc_pre_init = x86_init_noop,
.timer_init = hpet_time_init,
+ .wallclock_init = x86_init_noop,
},
.iommu = {
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 547128546cc..a3911343976 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -53,7 +53,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
/*
* None of the feature bits are in init state. So nothing else
- * to do for us, as the memory layout is upto date.
+ * to do for us, as the memory layout is up to date.
*/
if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
return;