summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig61
-rw-r--r--arch/x86/Kconfig.cpu16
-rw-r--r--arch/x86/Makefile_32.cpu2
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/alternative-asm.h9
-rw-r--r--arch/x86/include/asm/alternative.h9
-rw-r--r--arch/x86/include/asm/amd_iommu_proto.h13
-rw-r--r--arch/x86/include/asm/amd_iommu_types.h28
-rw-r--r--arch/x86/include/asm/amd_nb.h1
-rw-r--r--arch/x86/include/asm/apic.h9
-rw-r--r--arch/x86/include/asm/apicdef.h1
-rw-r--r--arch/x86/include/asm/bios_ebda.h28
-rw-r--r--arch/x86/include/asm/cpufeature.h15
-rw-r--r--arch/x86/include/asm/dma.h12
-rw-r--r--arch/x86/include/asm/efi.h1
-rw-r--r--arch/x86/include/asm/ftrace.h7
-rw-r--r--arch/x86/include/asm/i8253.h2
-rw-r--r--arch/x86/include/asm/jump_label.h27
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mmzone_32.h20
-rw-r--r--arch/x86/include/asm/mmzone_64.h23
-rw-r--r--arch/x86/include/asm/module.h2
-rw-r--r--arch/x86/include/asm/nops.h146
-rw-r--r--arch/x86/include/asm/numa.h32
-rw-r--r--arch/x86/include/asm/numa_32.h10
-rw-r--r--arch/x86/include/asm/numa_64.h36
-rw-r--r--arch/x86/include/asm/numaq.h7
-rw-r--r--arch/x86/include/asm/olpc_ofw.h9
-rw-r--r--arch/x86/include/asm/percpu.h29
-rw-r--r--arch/x86/include/asm/pgtable_types.h1
-rw-r--r--arch/x86/include/asm/probe_roms.h8
-rw-r--r--arch/x86/include/asm/processor-flags.h1
-rw-r--r--arch/x86/include/asm/setup.h4
-rw-r--r--arch/x86/include/asm/srat.h39
-rw-r--r--arch/x86/include/asm/stacktrace.h3
-rw-r--r--arch/x86/include/asm/system.h85
-rw-r--r--arch/x86/include/asm/topology.h8
-rw-r--r--arch/x86/include/asm/uaccess.h2
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h17
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h2
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h16
-rw-r--r--arch/x86/include/asm/x86_init.h12
-rw-r--r--arch/x86/include/asm/xen/page.h5
-rw-r--r--arch/x86/include/asm/xen/pci.h16
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/acpi/sleep.c5
-rw-r--r--arch/x86/kernel/alternative.c203
-rw-r--r--arch/x86/kernel/amd_gart_64.c (renamed from arch/x86/kernel/pci-gart_64.c)0
-rw-r--r--arch/x86/kernel/amd_iommu.c526
-rw-r--r--arch/x86/kernel/amd_iommu_init.c48
-rw-r--r--arch/x86/kernel/apb_timer.c10
-rw-r--r--arch/x86/kernel/aperture_64.c34
-rw-r--r--arch/x86/kernel/apic/apic.c69
-rw-r--r--arch/x86/kernel/apic/apic_noop.c9
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c1
-rw-r--r--arch/x86/kernel/apic/es7000_32.c7
-rw-r--r--arch/x86/kernel/apic/numaq_32.c34
-rw-r--r--arch/x86/kernel/apic/probe_32.c1
-rw-r--r--arch/x86/kernel/apic/summit_32.c1
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c48
-rw-r--r--arch/x86/kernel/apm_32.c4
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/common.c26
-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.c624
-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.c1607
-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.c29
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c20
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c25
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c22
-rw-r--r--arch/x86/kernel/cpu/perf_event.c28
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c14
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c124
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c7
-rw-r--r--arch/x86/kernel/dumpstack.c17
-rw-r--r--arch/x86/kernel/ftrace.c4
-rw-r--r--arch/x86/kernel/head32.c1
-rw-r--r--arch/x86/kernel/hpet.c72
-rw-r--r--arch/x86/kernel/i8253.c86
-rw-r--r--arch/x86/kernel/irq.c5
-rw-r--r--arch/x86/kernel/jump_label.c5
-rw-r--r--arch/x86/kernel/kprobes.c5
-rw-r--r--arch/x86/kernel/kvmclock.c6
-rw-r--r--arch/x86/kernel/module.c1
-rw-r--r--arch/x86/kernel/mpparse.c6
-rw-r--r--arch/x86/kernel/pci-iommu_table.c18
-rw-r--r--arch/x86/kernel/probe_roms.c (renamed from arch/x86/kernel/probe_roms_32.c)101
-rw-r--r--arch/x86/kernel/process.c4
-rw-r--r--arch/x86/kernel/ptrace.c36
-rw-r--r--arch/x86/kernel/reboot.c24
-rw-r--r--arch/x86/kernel/reboot_32.S12
-rw-r--r--arch/x86/kernel/setup.c6
-rw-r--r--arch/x86/kernel/smp.c5
-rw-r--r--arch/x86/kernel/smpboot.c4
-rw-r--r--arch/x86/kernel/stacktrace.c13
-rw-r--r--arch/x86/kernel/x86_init.c6
-rw-r--r--arch/x86/lguest/boot.c6
-rw-r--r--arch/x86/lib/clear_page_64.S33
-rw-r--r--arch/x86/lib/copy_user_64.S69
-rw-r--r--arch/x86/lib/memcpy_64.S47
-rw-r--r--arch/x86/lib/memmove_64.S29
-rw-r--r--arch/x86/lib/memset_64.S54
-rw-r--r--arch/x86/mm/Makefile4
-rw-r--r--arch/x86/mm/amdtopology.c (renamed from arch/x86/mm/amdtopology_64.c)21
-rw-r--r--arch/x86/mm/init.c24
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c10
-rw-r--r--arch/x86/mm/ioremap.c14
-rw-r--r--arch/x86/mm/numa.c550
-rw-r--r--arch/x86/mm/numa_32.c398
-rw-r--r--arch/x86/mm/numa_64.c644
-rw-r--r--arch/x86/mm/numa_emulation.c16
-rw-r--r--arch/x86/mm/numa_internal.h8
-rw-r--r--arch/x86/mm/srat.c (renamed from arch/x86/mm/srat_64.c)82
-rw-r--r--arch/x86/mm/srat_32.c288
-rw-r--r--arch/x86/oprofile/backtrace.c13
-rw-r--r--arch/x86/pci/xen.c96
-rw-r--r--arch/x86/platform/efi/efi.c78
-rw-r--r--arch/x86/platform/efi/efi_64.c34
-rw-r--r--arch/x86/platform/mrst/mrst.c4
-rw-r--r--arch/x86/platform/olpc/Makefile4
-rw-r--r--arch/x86/platform/olpc/olpc.c51
-rw-r--r--arch/x86/platform/olpc/olpc_dt.c19
-rw-r--r--arch/x86/platform/uv/tlb_uv.c92
-rw-r--r--arch/x86/platform/uv/uv_time.c6
-rw-r--r--arch/x86/xen/enlighten.c20
-rw-r--r--arch/x86/xen/irq.c2
-rw-r--r--arch/x86/xen/mmu.c53
-rw-r--r--arch/x86/xen/p2m.c43
-rw-r--r--arch/x86/xen/setup.c10
-rw-r--r--arch/x86/xen/smp.c13
-rw-r--r--arch/x86/xen/time.c14
-rw-r--r--arch/x86/xen/xen-ops.h2
157 files changed, 2669 insertions, 13295 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc6c53a95bf..4168e5d8632 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -8,6 +8,7 @@ config 64BIT
config X86_32
def_bool !64BIT
+ select CLKSRC_I8253
config X86_64
def_bool 64BIT
@@ -71,7 +72,6 @@ config X86
select GENERIC_IRQ_SHOW
select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
- select ARCH_NO_SYSDEV_OPS
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
@@ -112,7 +112,14 @@ config MMU
def_bool y
config ZONE_DMA
- def_bool y
+ bool "DMA memory allocation support" if EXPERT
+ default y
+ help
+ DMA memory allocation support allows devices with less than 32-bit
+ addressing to allocate within the first 16MB of address space.
+ Disable if no such devices will be used.
+
+ If unsure, say Y.
config SBUS
bool
@@ -365,17 +372,6 @@ config X86_UV
# Following is an alphabetically sorted list of 32 bit extended platforms
# Please maintain the alphabetic order if and when there are additions
-config X86_ELAN
- bool "AMD Elan"
- depends on X86_32
- depends on X86_EXTENDED_PLATFORM
- ---help---
- Select this for an AMD Elan processor.
-
- Do not use this option for K6/Athlon/Opteron processors!
-
- If unsure, choose "PC-compatible" instead.
-
config X86_INTEL_CE
bool "CE4100 TV platform"
depends on PCI
@@ -690,6 +686,7 @@ config AMD_IOMMU
bool "AMD IOMMU support"
select SWIOTLB
select PCI_MSI
+ select PCI_IOV
depends on X86_64 && PCI && ACPI
---help---
With this option you can enable support for AMD IOMMU hardware in
@@ -1174,7 +1171,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
config AMD_NUMA
def_bool y
prompt "Old style AMD Opteron NUMA detection"
- depends on X86_64 && NUMA && PCI
+ depends on NUMA && PCI
---help---
Enable AMD NUMA node topology detection. You should say Y here if
you have a multi processor AMD system. This uses an old method to
@@ -1201,7 +1198,7 @@ config NODES_SPAN_OTHER_NODES
config NUMA_EMU
bool "NUMA emulation"
- depends on X86_64 && NUMA
+ depends on NUMA
---help---
Enable NUMA emulation. A flat machine will be split
into virtual nodes when booted with "numa=fake=N", where N is the
@@ -1223,6 +1220,10 @@ config HAVE_ARCH_BOOTMEM
def_bool y
depends on X86_32 && NUMA
+config HAVE_ARCH_ALLOC_REMAP
+ def_bool y
+ depends on X86_32 && NUMA
+
config ARCH_HAVE_MEMORY_PRESENT
def_bool y
depends on X86_32 && DISCONTIGMEM
@@ -1231,13 +1232,9 @@ config NEED_NODE_MEMMAP_SIZE
def_bool y
depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
-config HAVE_ARCH_ALLOC_REMAP
- def_bool y
- depends on X86_32 && NUMA
-
config ARCH_FLATMEM_ENABLE
def_bool y
- depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
+ depends on X86_32 && !NUMA
config ARCH_DISCONTIGMEM_ENABLE
def_bool y
@@ -1247,20 +1244,16 @@ config ARCH_DISCONTIGMEM_DEFAULT
def_bool y
depends on NUMA && X86_32
-config ARCH_PROC_KCORE_TEXT
- def_bool y
- depends on X86_64 && PROC_KCORE
-
-config ARCH_SPARSEMEM_DEFAULT
- def_bool y
- depends on X86_64
-
config ARCH_SPARSEMEM_ENABLE
def_bool y
depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
select SPARSEMEM_STATIC if X86_32
select SPARSEMEM_VMEMMAP_ENABLE if X86_64
+config ARCH_SPARSEMEM_DEFAULT
+ def_bool y
+ depends on X86_64
+
config ARCH_SELECT_MEMORY_MODEL
def_bool y
depends on ARCH_SPARSEMEM_ENABLE
@@ -1269,6 +1262,10 @@ config ARCH_MEMORY_PROBE
def_bool X86_64
depends on MEMORY_HOTPLUG
+config ARCH_PROC_KCORE_TEXT
+ def_bool y
+ depends on X86_64 && PROC_KCORE
+
config ILLEGAL_POINTER_VALUE
hex
default 0 if X86_32
@@ -1703,10 +1700,6 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
def_bool y
depends on MEMORY_HOTPLUG
-config HAVE_ARCH_EARLY_PFN_TO_NID
- def_bool X86_64
- depends on NUMA
-
config USE_PERCPU_NUMA_NODE_ID
def_bool y
depends on NUMA
@@ -1848,7 +1841,7 @@ config APM_ALLOW_INTS
endif # APM
-source "arch/x86/kernel/cpu/cpufreq/Kconfig"
+source "drivers/cpufreq/Kconfig"
source "drivers/cpuidle/Kconfig"
@@ -2076,7 +2069,7 @@ config OLPC
depends on !X86_PAE
select GPIOLIB
select OF
- select OF_PROMTREE if PROC_DEVICETREE
+ select OF_PROMTREE
---help---
Add support for detecting the unique features of the OLPC
XO hardware.
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index d161e939df6..6a7cfdf8ff6 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -1,6 +1,4 @@
# Put here option for CPU selection and depending optimization
-if !X86_ELAN
-
choice
prompt "Processor family"
default M686 if X86_32
@@ -203,6 +201,14 @@ config MWINCHIP3D
stores for this CPU, which can increase performance of some
operations.
+config MELAN
+ bool "AMD Elan"
+ depends on X86_32
+ ---help---
+ Select this for an AMD Elan processor.
+
+ Do not use this option for K6/Athlon/Opteron processors!
+
config MGEODEGX1
bool "GeodeGX1"
depends on X86_32
@@ -292,8 +298,6 @@ config X86_GENERIC
This is really intended for distributors who need more
generic optimizations.
-endif
-
#
# Define implied options from the CPU selection here
config X86_INTERNODE_CACHE_SHIFT
@@ -312,7 +316,7 @@ config X86_L1_CACHE_SHIFT
int
default "7" if MPENTIUM4 || MPSC
default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
- default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
+ default "4" if MELAN || M486 || M386 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
config X86_XADD
@@ -358,7 +362,7 @@ config X86_POPAD_OK
config X86_ALIGNMENT_16
def_bool y
- depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
+ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
config X86_INTEL_USERCOPY
def_bool y
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index f2ee1abb1df..86cee7b749e 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -37,7 +37,7 @@ cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=
$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
# AMD Elan support
-cflags-$(CONFIG_X86_ELAN) += -march=i486
+cflags-$(CONFIG_MELAN) += -march=i486
# Geode GX1 support
cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 12e0e7dd869..416d865eae3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -183,8 +183,6 @@ static inline void disable_acpi(void) { }
#define ARCH_HAS_POWER_INIT 1
-struct bootnode;
-
#ifdef CONFIG_ACPI_NUMA
extern int acpi_numa;
extern int x86_acpi_numa_init(void);
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index a63a68be1cc..94d420b360d 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -15,4 +15,13 @@
.endm
#endif
+.macro altinstruction_entry orig alt feature orig_len alt_len
+ .align 8
+ .quad \orig
+ .quad \alt
+ .word \feature
+ .byte \orig_len
+ .byte \alt_len
+.endm
+
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 13009d1af99..bf535f947e8 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -4,7 +4,6 @@
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/stringify.h>
-#include <linux/jump_label.h>
#include <asm/asm.h>
/*
@@ -191,12 +190,4 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
extern void text_poke_smp_batch(struct text_poke_param *params, int n);
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
-#define IDEAL_NOP_SIZE_5 5
-extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
-extern void arch_init_ideal_nop5(void);
-#else
-static inline void arch_init_ideal_nop5(void) {}
-#endif
-
#endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index 916bc8111a0..55d95eb789b 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -19,13 +19,12 @@
#ifndef _ASM_X86_AMD_IOMMU_PROTO_H
#define _ASM_X86_AMD_IOMMU_PROTO_H
-struct amd_iommu;
+#include <asm/amd_iommu_types.h>
extern int amd_iommu_init_dma_ops(void);
extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_flush_all_domains(void);
-extern void amd_iommu_flush_all_devices(void);
extern void amd_iommu_apply_erratum_63(u16 devid);
extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
extern int amd_iommu_init_devices(void);
@@ -44,4 +43,12 @@ static inline bool is_rd890_iommu(struct pci_dev *pdev)
(pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
}
+static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
+{
+ if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+ return false;
+
+ return !!(iommu->features & f);
+}
+
#endif /* _ASM_X86_AMD_IOMMU_PROTO_H */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index e3509fc303b..4c998299541 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -68,12 +68,25 @@
#define MMIO_CONTROL_OFFSET 0x0018
#define MMIO_EXCL_BASE_OFFSET 0x0020
#define MMIO_EXCL_LIMIT_OFFSET 0x0028
+#define MMIO_EXT_FEATURES 0x0030
#define MMIO_CMD_HEAD_OFFSET 0x2000
#define MMIO_CMD_TAIL_OFFSET 0x2008
#define MMIO_EVT_HEAD_OFFSET 0x2010
#define MMIO_EVT_TAIL_OFFSET 0x2018
#define MMIO_STATUS_OFFSET 0x2020
+
+/* Extended Feature Bits */
+#define FEATURE_PREFETCH (1ULL<<0)
+#define FEATURE_PPR (1ULL<<1)
+#define FEATURE_X2APIC (1ULL<<2)
+#define FEATURE_NX (1ULL<<3)
+#define FEATURE_GT (1ULL<<4)
+#define FEATURE_IA (1ULL<<6)
+#define FEATURE_GA (1ULL<<7)
+#define FEATURE_HE (1ULL<<8)
+#define FEATURE_PC (1ULL<<9)
+
/* MMIO status bits */
#define MMIO_STATUS_COM_WAIT_INT_MASK 0x04
@@ -113,7 +126,9 @@
/* command specific defines */
#define CMD_COMPL_WAIT 0x01
#define CMD_INV_DEV_ENTRY 0x02
-#define CMD_INV_IOMMU_PAGES 0x03
+#define CMD_INV_IOMMU_PAGES 0x03
+#define CMD_INV_IOTLB_PAGES 0x04
+#define CMD_INV_ALL 0x08
#define CMD_COMPL_WAIT_STORE_MASK 0x01
#define CMD_COMPL_WAIT_INT_MASK 0x02
@@ -215,6 +230,8 @@
#define IOMMU_PTE_IR (1ULL << 61)
#define IOMMU_PTE_IW (1ULL << 62)
+#define DTE_FLAG_IOTLB 0x01
+
#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
@@ -227,6 +244,7 @@
/* IOMMU capabilities */
#define IOMMU_CAP_IOTLB 24
#define IOMMU_CAP_NPCACHE 26
+#define IOMMU_CAP_EFR 27
#define MAX_DOMAIN_ID 65536
@@ -249,6 +267,8 @@ extern bool amd_iommu_dump;
/* global flag if IOMMUs cache non-present entries */
extern bool amd_iommu_np_cache;
+/* Only true if all IOMMUs support device IOTLBs */
+extern bool amd_iommu_iotlb_sup;
/*
* Make iterating over all IOMMUs easier
@@ -371,6 +391,9 @@ struct amd_iommu {
/* flags read from acpi table */
u8 acpi_flags;
+ /* Extended features */
+ u64 features;
+
/*
* Capability pointer. There could be more than one IOMMU per PCI
* device function if there are more than one AMD IOMMU capability
@@ -409,9 +432,6 @@ struct amd_iommu {
/* if one, we need to send a completion wait command */
bool need_sync;
- /* becomes true if a command buffer reset is running */
- bool reset_in_progress;
-
/* default dma_ops domain for that IOMMU */
struct dma_ops_domain *default_dom;
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 331682231bb..67f87f25761 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -11,7 +11,6 @@ struct amd_nb_bus_dev_range {
extern const struct pci_device_id amd_nb_misc_ids[];
extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
-struct bootnode;
extern bool early_is_amd_nb(u32 value);
extern int amd_cache_northbridges(void);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 2b7d573be54..a0c46f06121 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -363,7 +363,12 @@ struct apic {
*/
int (*x86_32_early_logical_apicid)(int cpu);
- /* determine CPU -> NUMA node mapping */
+ /*
+ * Optional method called from setup_local_APIC() after logical
+ * apicid is guaranteed to be known to initialize apicid -> node
+ * mapping if NUMA initialization hasn't done so already. Don't
+ * add new users.
+ */
int (*x86_32_numa_cpu_node)(int cpu);
#endif
};
@@ -537,8 +542,6 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
return cpuid_apic >> index_msb;
}
-extern int default_x86_32_numa_cpu_node(int cpu);
-
#endif
static inline unsigned int
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index d87988bacf3..34595d5e103 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -78,6 +78,7 @@
#define APIC_DEST_LOGICAL 0x00800
#define APIC_DEST_PHYSICAL 0x00000
#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
#define APIC_DM_LOWEST 0x00100
#define APIC_DM_SMI 0x00200
#define APIC_DM_REMRD 0x00300
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
index 3c7521063d3..aa6a3170ab5 100644
--- a/arch/x86/include/asm/bios_ebda.h
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -4,16 +4,40 @@
#include <asm/io.h>
/*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E.
+ * Returns physical address of EBDA. Returns 0 if there is no EBDA.
*/
static inline unsigned int get_bios_ebda(void)
{
+ /*
+ * There is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E.
+ */
unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
address <<= 4;
return address; /* 0 means none */
}
+/*
+ * Return the sanitized length of the EBDA in bytes, if it exists.
+ */
+static inline unsigned int get_bios_ebda_length(void)
+{
+ unsigned int address;
+ unsigned int length;
+
+ address = get_bios_ebda();
+ if (!address)
+ return 0;
+
+ /* EBDA length is byte 0 of the EBDA (stored in KiB) */
+ length = *(unsigned char *)phys_to_virt(address);
+ length <<= 10;
+
+ /* Trim the length if it extends beyond 640KiB */
+ length = min_t(unsigned int, (640 * 1024) - address, length);
+ return length;
+}
+
void reserve_ebda_region(void);
#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 91f3e087cf2..5dc6acc98db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -195,6 +195,8 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
@@ -207,8 +209,7 @@ extern const char * const x86_power_flags[32];
#define test_cpu_cap(c, bit) \
test_bit(bit, (unsigned long *)((c)->x86_capability))
-#define cpu_has(c, bit) \
- (__builtin_constant_p(bit) && \
+#define REQUIRED_MASK_BIT_SET(bit) \
( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) || \
(((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) || \
(((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) || \
@@ -218,10 +219,16 @@ extern const char * const x86_power_flags[32];
(((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \
(((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \
(((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \
- (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \
- ? 1 : \
+ (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+#define cpu_has(c, bit) \
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
test_cpu_cap(c, bit))
+#define this_cpu_has(bit) \
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
+ x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit)
#define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability))
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 057099e5fab..0bdb0c54d9a 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -69,22 +69,18 @@
#define MAX_DMA_CHANNELS 8
-#ifdef CONFIG_X86_32
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000)
-
-#else
-
/* 16MB ISA DMA zone */
#define MAX_DMA_PFN ((16 * 1024 * 1024) >> PAGE_SHIFT)
/* 4GB broken PCI/AGP hardware bus master zone */
#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#ifdef CONFIG_X86_32
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000)
+#else
/* Compat define for old dma zone */
#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
-
#endif
/* 8237 DMA controllers */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8e4a16508d4..7093e4a6a0b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,6 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
#endif /* CONFIG_X86_32 */
extern int add_efi_memmap;
+extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
extern void efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
extern void efi_call_phys_epilog(void);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c2278be..268c783ab1c 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -38,11 +38,10 @@ extern void mcount(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
/*
- * call mcount is "e8 <4 byte offset>"
- * The addr points to the 4 byte offset and the caller of this
- * function wants the pointer to e8. Simply subtract one.
+ * addr is the address of the mcount call instruction.
+ * recordmcount does the necessary offset calculation.
*/
- return addr - 1;
+ return addr;
}
#ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h
index fc1f579fb96..65aaa91d585 100644
--- a/arch/x86/include/asm/i8253.h
+++ b/arch/x86/include/asm/i8253.h
@@ -6,6 +6,8 @@
#define PIT_CH0 0x40
#define PIT_CH2 0x42
+#define PIT_LATCH LATCH
+
extern raw_spinlock_t i8253_lock;
extern struct clock_event_device *global_clock_event;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 574dbc22893..a32b18ce6ea 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -5,20 +5,25 @@
#include <linux/types.h>
#include <asm/nops.h>
+#include <asm/asm.h>
#define JUMP_LABEL_NOP_SIZE 5
-# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
-
-# define JUMP_LABEL(key, label) \
- do { \
- asm goto("1:" \
- JUMP_LABEL_INITIAL_NOP \
- ".pushsection __jump_table, \"aw\" \n\t"\
- _ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
- ".popsection \n\t" \
- : : "i" (key) : : label); \
- } while (0)
+#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+ asm goto("1:"
+ JUMP_LABEL_INITIAL_NOP
+ ".pushsection __jump_table, \"aw\" \n\t"
+ _ASM_ALIGN "\n\t"
+ _ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+ ".popsection \n\t"
+ : : "i" (key) : : l_yes);
+ return false;
+l_yes:
+ return true;
+}
#endif /* __KERNEL__ */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index eb16e94ae04..021979a6e23 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -142,8 +142,6 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
static inline void enable_p5_mce(void) {}
#endif
-extern void (*x86_mce_decode_callback)(struct mce *m);
-
void mce_setup(struct mce *m);
void mce_log(struct mce *m);
DECLARE_PER_CPU(struct sys_device, mce_dev);
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 91df7c51806..5e83a416eca 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -13,31 +13,11 @@ extern struct pglist_data *node_data[];
#define NODE_DATA(nid) (node_data[nid])
#include <asm/numaq.h>
-/* summit or generic arch */
-#include <asm/srat.h>
-
-extern int get_memcfg_numa_flat(void);
-/*
- * This allows any one NUMA architecture to be compiled
- * for, and still fall back to the flat function if it
- * fails.
- */
-static inline void get_memcfg_numa(void)
-{
-
- if (get_memcfg_numaq())
- return;
- if (get_memcfg_from_srat())
- return;
- get_memcfg_numa_flat();
-}
extern void resume_map_numa_kva(pgd_t *pgd);
#else /* !CONFIG_NUMA */
-#define get_memcfg_numa get_memcfg_numa_flat
-
static inline void resume_map_numa_kva(pgd_t *pgd) {}
#endif /* CONFIG_NUMA */
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index 288b96f815a..b3f88d7867c 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -4,36 +4,13 @@
#ifndef _ASM_X86_MMZONE_64_H
#define _ASM_X86_MMZONE_64_H
-
#ifdef CONFIG_NUMA
#include <linux/mmdebug.h>
-
#include <asm/smp.h>
-/* Simple perfect hash to map physical addresses to node numbers */
-struct memnode {
- int shift;
- unsigned int mapsize;
- s16 *map;
- s16 embedded_map[64 - 8];
-} ____cacheline_aligned; /* total size = 128 bytes */
-extern struct memnode memnode;
-#define memnode_shift memnode.shift
-#define memnodemap memnode.map
-#define memnodemapsize memnode.mapsize
-
extern struct pglist_data *node_data[];
-static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
-{
- unsigned nid;
- VIRTUAL_BUG_ON(!memnodemap);
- nid = memnodemap[addr >> memnode_shift];
- VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
- return nid;
-}
-
#define NODE_DATA(nid) (node_data[nid])
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 67763c5d8b4..9eae7752ae9 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -35,7 +35,7 @@
#define MODULE_PROC_FAMILY "K7 "
#elif defined CONFIG_MK8
#define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_X86_ELAN
+#elif defined CONFIG_MELAN
#define MODULE_PROC_FAMILY "ELAN "
#elif defined CONFIG_MCRUSOE
#define MODULE_PROC_FAMILY "CRUSOE "
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index af788496020..405b4032a60 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -1,7 +1,13 @@
#ifndef _ASM_X86_NOPS_H
#define _ASM_X86_NOPS_H
-/* Define nops for use with alternative() */
+/*
+ * Define nops for use with alternative() and for tracing.
+ *
+ * *_NOP5_ATOMIC must be a single instruction.
+ */
+
+#define NOP_DS_PREFIX 0x3e
/* generic versions from gas
1: nop
@@ -13,14 +19,15 @@
6: leal 0x00000000(%esi),%esi
7: leal 0x00000000(,%esi,1),%esi
*/
-#define GENERIC_NOP1 ".byte 0x90\n"
-#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
-#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
-#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
-#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
-#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
+#define GENERIC_NOP1 0x90
+#define GENERIC_NOP2 0x89,0xf6
+#define GENERIC_NOP3 0x8d,0x76,0x00
+#define GENERIC_NOP4 0x8d,0x74,0x26,0x00
+#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4
+#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00
+#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
+#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7
+#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4
/* Opteron 64bit nops
1: nop
@@ -29,13 +36,14 @@
4: osp osp osp nop
*/
#define K8_NOP1 GENERIC_NOP1
-#define K8_NOP2 ".byte 0x66,0x90\n"
-#define K8_NOP3 ".byte 0x66,0x66,0x90\n"
-#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n"
-#define K8_NOP5 K8_NOP3 K8_NOP2
-#define K8_NOP6 K8_NOP3 K8_NOP3
-#define K8_NOP7 K8_NOP4 K8_NOP3
-#define K8_NOP8 K8_NOP4 K8_NOP4
+#define K8_NOP2 0x66,K8_NOP1
+#define K8_NOP3 0x66,K8_NOP2
+#define K8_NOP4 0x66,K8_NOP3
+#define K8_NOP5 K8_NOP3,K8_NOP2
+#define K8_NOP6 K8_NOP3,K8_NOP3
+#define K8_NOP7 K8_NOP4,K8_NOP3
+#define K8_NOP8 K8_NOP4,K8_NOP4
+#define K8_NOP5_ATOMIC 0x66,K8_NOP4
/* K7 nops
uses eax dependencies (arbitrary choice)
@@ -47,13 +55,14 @@
7: leal 0x00000000(,%eax,1),%eax
*/
#define K7_NOP1 GENERIC_NOP1
-#define K7_NOP2 ".byte 0x8b,0xc0\n"
-#define K7_NOP3 ".byte 0x8d,0x04,0x20\n"
-#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n"
-#define K7_NOP5 K7_NOP4 ASM_NOP1
-#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n"
-#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n"
-#define K7_NOP8 K7_NOP7 ASM_NOP1
+#define K7_NOP2 0x8b,0xc0
+#define K7_NOP3 0x8d,0x04,0x20
+#define K7_NOP4 0x8d,0x44,0x20,0x00
+#define K7_NOP5 K7_NOP4,K7_NOP1
+#define K7_NOP6 0x8d,0x80,0,0,0,0
+#define K7_NOP7 0x8D,0x04,0x05,0,0,0,0
+#define K7_NOP8 K7_NOP7,K7_NOP1
+#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4
/* P6 nops
uses eax dependencies (Intel-recommended choice)
@@ -69,52 +78,65 @@
There is kernel code that depends on this.
*/
#define P6_NOP1 GENERIC_NOP1
-#define P6_NOP2 ".byte 0x66,0x90\n"
-#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n"
-#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n"
-#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n"
-#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+#define P6_NOP2 0x66,0x90
+#define P6_NOP3 0x0f,0x1f,0x00
+#define P6_NOP4 0x0f,0x1f,0x40,0
+#define P6_NOP5 0x0f,0x1f,0x44,0x00,0
+#define P6_NOP6 0x66,0x0f,0x1f,0x44,0x00,0
+#define P6_NOP7 0x0f,0x1f,0x80,0,0,0,0
+#define P6_NOP8 0x0f,0x1f,0x84,0x00,0,0,0,0
+#define P6_NOP5_ATOMIC P6_NOP5
+
+#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
#if defined(CONFIG_MK7)
-#define ASM_NOP1 K7_NOP1
-#define ASM_NOP2 K7_NOP2
-#define ASM_NOP3 K7_NOP3
-#define ASM_NOP4 K7_NOP4
-#define ASM_NOP5 K7_NOP5
-#define ASM_NOP6 K7_NOP6
-#define ASM_NOP7 K7_NOP7
-#define ASM_NOP8 K7_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC)
#elif defined(CONFIG_X86_P6_NOP)
-#define ASM_NOP1 P6_NOP1
-#define ASM_NOP2 P6_NOP2
-#define ASM_NOP3 P6_NOP3
-#define ASM_NOP4 P6_NOP4
-#define ASM_NOP5 P6_NOP5
-#define ASM_NOP6 P6_NOP6
-#define ASM_NOP7 P6_NOP7
-#define ASM_NOP8 P6_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC)
#elif defined(CONFIG_X86_64)
-#define ASM_NOP1 K8_NOP1
-#define ASM_NOP2 K8_NOP2
-#define ASM_NOP3 K8_NOP3
-#define ASM_NOP4 K8_NOP4
-#define ASM_NOP5 K8_NOP5
-#define ASM_NOP6 K8_NOP6
-#define ASM_NOP7 K8_NOP7
-#define ASM_NOP8 K8_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC)
#else
-#define ASM_NOP1 GENERIC_NOP1
-#define ASM_NOP2 GENERIC_NOP2
-#define ASM_NOP3 GENERIC_NOP3
-#define ASM_NOP4 GENERIC_NOP4
-#define ASM_NOP5 GENERIC_NOP5
-#define ASM_NOP6 GENERIC_NOP6
-#define ASM_NOP7 GENERIC_NOP7
-#define ASM_NOP8 GENERIC_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC)
#endif
#define ASM_NOP_MAX 8
+#define NOP_ATOMIC5 (ASM_NOP_MAX+1) /* Entry for the 5-byte atomic NOP */
+
+#ifndef __ASSEMBLY__
+extern const unsigned char * const *ideal_nops;
+extern void arch_init_ideal_nops(void);
+#endif
#endif /* _ASM_X86_NOPS_H */
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index a50fc9f493b..bfacd2ccf65 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -1,12 +1,24 @@
#ifndef _ASM_X86_NUMA_H
#define _ASM_X86_NUMA_H
+#include <linux/nodemask.h>
+
#include <asm/topology.h>
#include <asm/apicdef.h>
#ifdef CONFIG_NUMA
#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
+
+/*
+ * Too small node sizes may confuse the VM badly. Usually they
+ * result from BIOS bugs. So dont recognize nodes as standalone
+ * NUMA entities that have less than this amount of RAM listed:
+ */
+#define NODE_MIN_SIZE (4*1024*1024)
+
+extern int numa_off;
/*
* __apicid_to_node[] stores the raw mapping between physical apicid and
@@ -17,15 +29,27 @@
* numa_cpu_node().
*/
extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+extern nodemask_t numa_nodes_parsed __initdata;
+
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern void __init numa_set_distance(int from, int to, int distance);
static inline void set_apicid_to_node(int apicid, s16 node)
{
__apicid_to_node[apicid] = node;
}
+
+extern int __cpuinit numa_cpu_node(int cpu);
+
#else /* CONFIG_NUMA */
static inline void set_apicid_to_node(int apicid, s16 node)
{
}
+
+static inline int numa_cpu_node(int cpu)
+{
+ return NUMA_NO_NODE;
+}
#endif /* CONFIG_NUMA */
#ifdef CONFIG_X86_32
@@ -37,14 +61,12 @@ static inline void set_apicid_to_node(int apicid, s16 node)
#ifdef CONFIG_NUMA
extern void __cpuinit numa_set_node(int cpu, int node);
extern void __cpuinit numa_clear_node(int cpu);
-extern void __init numa_init_array(void);
extern void __init init_cpu_to_node(void);
extern void __cpuinit numa_add_cpu(int cpu);
extern void __cpuinit numa_remove_cpu(int cpu);
#else /* CONFIG_NUMA */
static inline void numa_set_node(int cpu, int node) { }
static inline void numa_clear_node(int cpu) { }
-static inline void numa_init_array(void) { }
static inline void init_cpu_to_node(void) { }
static inline void numa_add_cpu(int cpu) { }
static inline void numa_remove_cpu(int cpu) { }
@@ -54,4 +76,10 @@ static inline void numa_remove_cpu(int cpu) { }
void debug_cpumask_set_cpu(int cpu, int node, bool enable);
#endif
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE ((u64)32 << 20)
+#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
+void numa_emu_cmdline(char *);
+#endif /* CONFIG_NUMA_EMU */
+
#endif /* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index c6beed1ef10..e7d6b825474 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -1,16 +1,6 @@
#ifndef _ASM_X86_NUMA_32_H
#define _ASM_X86_NUMA_32_H
-extern int numa_off;
-
-extern int pxm_to_nid(int pxm);
-
-#ifdef CONFIG_NUMA
-extern int __cpuinit numa_cpu_node(int cpu);
-#else /* CONFIG_NUMA */
-static inline int numa_cpu_node(int cpu) { return NUMA_NO_NODE; }
-#endif /* CONFIG_NUMA */
-
#ifdef CONFIG_HIGHMEM
extern void set_highmem_pages_init(void);
#else
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 344eb1790b4..0c05f7ae46e 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -1,42 +1,6 @@
#ifndef _ASM_X86_NUMA_64_H
#define _ASM_X86_NUMA_64_H
-#include <linux/nodemask.h>
-
-struct bootnode {
- u64 start;
- u64 end;
-};
-
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
-
-extern int numa_off;
-
extern unsigned long numa_free_all_bootmem(void);
-extern void setup_node_bootmem(int nodeid, unsigned long start,
- unsigned long end);
-
-#ifdef CONFIG_NUMA
-/*
- * Too small node sizes may confuse the VM badly. Usually they
- * result from BIOS bugs. So dont recognize nodes as standalone
- * NUMA entities that have less than this amount of RAM listed:
- */
-#define NODE_MIN_SIZE (4*1024*1024)
-
-extern nodemask_t numa_nodes_parsed __initdata;
-
-extern int __cpuinit numa_cpu_node(int cpu);
-extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
-extern void __init numa_set_distance(int from, int to, int distance);
-
-#ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE ((u64)32 << 20)
-#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
-void numa_emu_cmdline(char *);
-#endif /* CONFIG_NUMA_EMU */
-#else
-static inline int numa_cpu_node(int cpu) { return NUMA_NO_NODE; }
-#endif
#endif /* _ASM_X86_NUMA_64_H */
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
index 37c516545ec..c3b3c322fd8 100644
--- a/arch/x86/include/asm/numaq.h
+++ b/arch/x86/include/asm/numaq.h
@@ -29,7 +29,7 @@
#ifdef CONFIG_X86_NUMAQ
extern int found_numaq;
-extern int get_memcfg_numaq(void);
+extern int numaq_numa_init(void);
extern int pci_numaq_init(void);
extern void *xquad_portio;
@@ -166,11 +166,6 @@ struct sys_cfg_data {
void numaq_tsc_disable(void);
-#else
-static inline int get_memcfg_numaq(void)
-{
- return 0;
-}
#endif /* CONFIG_X86_NUMAQ */
#endif /* _ASM_X86_NUMAQ_H */
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index c5d3a5abbb9..24487712e0b 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -26,15 +26,12 @@ extern void setup_olpc_ofw_pgd(void);
/* check if OFW was detected during boot */
extern bool olpc_ofw_present(void);
+extern void olpc_dt_build_devicetree(void);
+
#else /* !CONFIG_OLPC */
static inline void olpc_ofw_detect(void) { }
static inline void setup_olpc_ofw_pgd(void) { }
-#endif /* !CONFIG_OLPC */
-
-#ifdef CONFIG_OF_PROMTREE
-extern void olpc_dt_build_devicetree(void);
-#else
static inline void olpc_dt_build_devicetree(void) { }
-#endif
+#endif /* !CONFIG_OLPC */
#endif /* _ASM_X86_OLPC_OFW_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index d475b4398d8..53278b0dfdf 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -517,7 +517,7 @@ do { \
typeof(o2) __o2 = o2; \
typeof(o2) __n2 = n2; \
typeof(o2) __dummy; \
- alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4, \
+ alternative_io("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4, \
"cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \
X86_FEATURE_CX16, \
ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \
@@ -542,6 +542,33 @@ do { \
old__; \
})
+static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+ const unsigned long __percpu *addr)
+{
+ unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+
+ return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0;
+}
+
+static inline int x86_this_cpu_variable_test_bit(int nr,
+ const unsigned long __percpu *addr)
+{
+ int oldbit;
+
+ asm volatile("bt "__percpu_arg(2)",%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit)
+ : "m" (*(unsigned long *)addr), "Ir" (nr));
+
+ return oldbit;
+}
+
+#define x86_this_cpu_test_bit(nr, addr) \
+ (__builtin_constant_p((nr)) \
+ ? x86_this_cpu_constant_test_bit((nr), (addr)) \
+ : x86_this_cpu_variable_test_bit((nr), (addr)))
+
+
#include <asm-generic/percpu.h>
/* We can use this directly for local CPU (faster). */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7db7723d1f3..d56187c6b83 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -299,6 +299,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
/* Install a pte for a particular vaddr in kernel space. */
void set_pte_vaddr(unsigned long vaddr, pte_t pte);
+extern void native_pagetable_reserve(u64 start, u64 end);
#ifdef CONFIG_X86_32
extern void native_pagetable_setup_start(pgd_t *base);
extern void native_pagetable_setup_done(pgd_t *base);
diff --git a/arch/x86/include/asm/probe_roms.h b/arch/x86/include/asm/probe_roms.h
new file mode 100644
index 00000000000..4950a0b1d09
--- /dev/null
+++ b/arch/x86/include/asm/probe_roms.h
@@ -0,0 +1,8 @@
+#ifndef _PROBE_ROMS_H_
+#define _PROBE_ROMS_H_
+struct pci_dev;
+
+extern void __iomem *pci_map_biosrom(struct pci_dev *pdev);
+extern void pci_unmap_biosrom(void __iomem *rom);
+extern size_t pci_biosrom_size(struct pci_dev *pdev);
+#endif
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index a898a2b6e10..59ab4dffa37 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -60,6 +60,7 @@
#define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
#define X86_CR4_VMXE 0x00002000 /* enable VMX virtualization */
#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
+#define X86_CR4_SMEP 0x00100000 /* enable SMEP support */
/*
* x86-64 Task Priority Register, CR8
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index db8aa19a08a..9756551ec76 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -88,7 +88,7 @@ void *extend_brk(size_t size, size_t align);
* executable.)
*/
#define RESERVE_BRK(name,sz) \
- static void __section(.discard.text) __used \
+ static void __section(.discard.text) __used notrace \
__brk_reservation_fn_##name##__(void) { \
asm volatile ( \
".pushsection .brk_reservation,\"aw\",@nobits;" \
@@ -104,10 +104,10 @@ void *extend_brk(size_t size, size_t align);
type *name; \
RESERVE_BRK(name, sizeof(type) * entries)
+extern void probe_roms(void);
#ifdef __i386__
void __init i386_start_kernel(void);
-extern void probe_roms(void);
#else
void __init x86_64_start_kernel(char *real_mode);
diff --git a/arch/x86/include/asm/srat.h b/arch/x86/include/asm/srat.h
deleted file mode 100644
index b508d639d1a..00000000000
--- a/arch/x86/include/asm/srat.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Some of the code in this file has been gleaned from the 64 bit
- * discontigmem support code base.
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * 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.
- *
- * 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.
- *
- * Send feedback to Pat Gaughen <gone@us.ibm.com>
- */
-
-#ifndef _ASM_X86_SRAT_H
-#define _ASM_X86_SRAT_H
-
-#ifdef CONFIG_ACPI_NUMA
-extern int get_memcfg_from_srat(void);
-#else
-static inline int get_memcfg_from_srat(void)
-{
- return 0;
-}
-#endif
-
-#endif /* _ASM_X86_SRAT_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index d7e89c83645..70bbe39043a 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -37,9 +37,6 @@ print_context_stack_bp(struct thread_info *tinfo,
/* Generic stack tracer with callbacks */
struct stacktrace_ops {
- void (*warning)(void *data, char *msg);
- /* msg must contain %s for the symbol */
- void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
void (*address)(void *data, unsigned long address, int reliable);
/* On negative return stop dumping */
int (*stack)(void *data, char *name);
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 12569e691ce..c2ff2a1d845 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -303,24 +303,81 @@ static inline void native_wbinvd(void)
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
-#define read_cr0() (native_read_cr0())
-#define write_cr0(x) (native_write_cr0(x))
-#define read_cr2() (native_read_cr2())
-#define write_cr2(x) (native_write_cr2(x))
-#define read_cr3() (native_read_cr3())
-#define write_cr3(x) (native_write_cr3(x))
-#define read_cr4() (native_read_cr4())
-#define read_cr4_safe() (native_read_cr4_safe())
-#define write_cr4(x) (native_write_cr4(x))
-#define wbinvd() (native_wbinvd())
+
+static inline unsigned long read_cr0(void)
+{
+ return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+ native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+ return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+ native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+ return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+ native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+ return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+ return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+ native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+ native_wbinvd();
+}
+
#ifdef CONFIG_X86_64
-#define read_cr8() (native_read_cr8())
-#define write_cr8(x) (native_write_cr8(x))
-#define load_gs_index native_load_gs_index
+
+static inline unsigned long read_cr8(void)
+{
+ return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+ native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+ native_load_gs_index(selector);
+}
+
#endif
/* Clear the 'TS' bit */
-#define clts() (native_clts())
+static inline void clts(void)
+{
+ native_clts();
+}
#endif/* CONFIG_PARAVIRT */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 910a7084f7f..c00692476e9 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -93,19 +93,11 @@ extern void setup_node_to_cpumask_map(void);
#define pcibus_to_node(bus) __pcibus_to_node(bus)
#ifdef CONFIG_X86_32
-extern unsigned long node_start_pfn[];
-extern unsigned long node_end_pfn[];
-extern unsigned long node_remap_size[];
-#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
-
# define SD_CACHE_NICE_TRIES 1
# define SD_IDLE_IDX 1
-
#else
-
# define SD_CACHE_NICE_TRIES 2
# define SD_IDLE_IDX 2
-
#endif
/* sched_domains SD_NODE_INIT for NUMA machines */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index abd3e0ea762..99f0ad753f3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -42,7 +42,7 @@
* Returns 0 if the range is valid, nonzero otherwise.
*
* This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
*
* This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
*/
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 3e094af443c..130f1eeee5f 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -94,6 +94,8 @@
/* after this # consecutive successes, bump up the throttle if it was lowered */
#define COMPLETE_THRESHOLD 5
+#define UV_LB_SUBNODEID 0x10
+
/*
* number of entries in the destination side payload queue
*/
@@ -124,7 +126,7 @@
* The distribution specification (32 bytes) is interpreted as a 256-bit
* distribution vector. Adjacent bits correspond to consecutive even numbered
* nodeIDs. The result of adding the index of a given bit to the 15-bit
- * 'base_dest_nodeid' field of the header corresponds to the
+ * 'base_dest_nasid' field of the header corresponds to the
* destination nodeID associated with that specified bit.
*/
struct bau_target_uvhubmask {
@@ -176,7 +178,7 @@ struct bau_msg_payload {
struct bau_msg_header {
unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */
/* bits 5:0 */
- unsigned int base_dest_nodeid:15; /* nasid of the */
+ unsigned int base_dest_nasid:15; /* nasid of the */
/* bits 20:6 */ /* first bit in uvhub map */
unsigned int command:8; /* message type */
/* bits 28:21 */
@@ -378,6 +380,10 @@ struct ptc_stats {
unsigned long d_rcanceled; /* number of messages canceled by resets */
};
+struct hub_and_pnode {
+ short uvhub;
+ short pnode;
+};
/*
* one per-cpu; to locate the software tables
*/
@@ -399,10 +405,12 @@ struct bau_control {
int baudisabled;
int set_bau_off;
short cpu;
+ short osnode;
short uvhub_cpu;
short uvhub;
short cpus_in_socket;
short cpus_in_uvhub;
+ short partition_base_pnode;
unsigned short message_number;
unsigned short uvhub_quiesce;
short socket_acknowledge_count[DEST_Q_SIZE];
@@ -422,15 +430,16 @@ struct bau_control {
int congested_period;
cycles_t period_time;
long period_requests;
+ struct hub_and_pnode *target_hub_and_pnode;
};
static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
{
return constant_test_bit(uvhub, &dstp->bits[0]);
}
-static inline void bau_uvhub_set(int uvhub, struct bau_target_uvhubmask *dstp)
+static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp)
{
- __set_bit(uvhub, &dstp->bits[0]);
+ __set_bit(pnode, &dstp->bits[0]);
}
static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
int nbits)
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index a501741c233..4298002d0c8 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -398,6 +398,8 @@ struct uv_blade_info {
unsigned short nr_online_cpus;
unsigned short pnode;
short memory_nid;
+ spinlock_t nmi_lock;
+ unsigned long nmi_count;
};
extern struct uv_blade_info *uv_blade_info;
extern short *uv_node_to_blade;
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 20cafeac745..f5bb64a823d 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -5,7 +5,7 @@
*
* SGI UV MMR definitions
*
- * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved.
*/
#ifndef _ASM_X86_UV_UV_MMRS_H
@@ -1099,5 +1099,19 @@ union uvh_rtc1_int_config_u {
} s;
};
+/* ========================================================================= */
+/* UVH_SCRATCH5 */
+/* ========================================================================= */
+#define UVH_SCRATCH5 0x2d0200UL
+#define UVH_SCRATCH5_32 0x00778
+
+#define UVH_SCRATCH5_SCRATCH5_SHFT 0
+#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
+union uvh_scratch5_u {
+ unsigned long v;
+ struct uvh_scratch5_s {
+ unsigned long scratch5 : 64; /* RW, W1CS */
+ } s;
+};
#endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 643ebf2e2ad..d3d859035af 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -68,6 +68,17 @@ struct x86_init_oem {
};
/**
+ * struct x86_init_mapping - platform specific initial kernel pagetable setup
+ * @pagetable_reserve: reserve a range of addresses for kernel pagetable usage
+ *
+ * For more details on the purpose of this hook, look in
+ * init_memory_mapping and the commit that added it.
+ */
+struct x86_init_mapping {
+ void (*pagetable_reserve)(u64 start, u64 end);
+};
+
+/**
* struct x86_init_paging - platform specific paging functions
* @pagetable_setup_start: platform specific pre paging_init() call
* @pagetable_setup_done: platform specific post paging_init() call
@@ -123,6 +134,7 @@ struct x86_init_ops {
struct x86_init_mpparse mpparse;
struct x86_init_irqs irqs;
struct x86_init_oem oem;
+ struct x86_init_mapping mapping;
struct x86_init_paging paging;
struct x86_init_timers timers;
struct x86_init_iommu iommu;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c61934fbf22..64a619d47d3 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -47,8 +47,9 @@ extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern unsigned long set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e);
-extern int m2p_add_override(unsigned long mfn, struct page *page);
-extern int m2p_remove_override(struct page *page);
+extern int m2p_add_override(unsigned long mfn, struct page *page,
+ bool clear_pte);
+extern int m2p_remove_override(struct page *page, bool clear_pte);
extern struct page *m2p_find_override(unsigned long mfn);
extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index aa862098916..4fbda9a3f33 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -15,10 +15,26 @@ static inline int pci_xen_hvm_init(void)
#endif
#if defined(CONFIG_XEN_DOM0)
void __init xen_setup_pirqs(void);
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
#else
static inline void __init xen_setup_pirqs(void)
{
}
+static inline int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+ return -1;
+}
+static inline int xen_register_device_domain_owner(struct pci_dev *dev,
+ uint16_t domain)
+{
+ return -1;
+}
+static inline int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+ return -1;
+}
#endif
#if defined(CONFIG_PCI_MSI)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7338ef2218b..250806472a7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -36,7 +36,7 @@ obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o
obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o
obj-$(CONFIG_IRQ_WORK) += irq_work.o
-obj-$(CONFIG_X86_32) += probe_roms_32.o
+obj-y += probe_roms.o
obj-$(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
@@ -117,7 +117,7 @@ obj-$(CONFIG_OF) += devicetree.o
ifeq ($(CONFIG_X86_64),y)
obj-$(CONFIG_AUDIT) += audit_64.o
- obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o
+ obj-$(CONFIG_GART_IOMMU) += amd_gart_64.o aperture_64.o
obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index ff93bc1b09c..18a857ba7a2 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -112,11 +112,6 @@ static int __init acpi_sleep_setup(char *str)
#ifdef CONFIG_HIBERNATION
if (strncmp(str, "s4_nohwsig", 10) == 0)
acpi_no_s4_hw_signature();
- if (strncmp(str, "s4_nonvs", 8) == 0) {
- pr_warning("ACPI: acpi_sleep=s4_nonvs is deprecated, "
- "please use acpi_sleep=nonvs instead");
- acpi_nvs_nosave();
- }
#endif
if (strncmp(str, "nonvs", 5) == 0)
acpi_nvs_nosave();
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4a234677e21..a81f2d52f86 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -67,17 +67,30 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
#define DPRINTK(fmt, args...) if (debug_alternative) \
printk(KERN_DEBUG fmt, args)
+/*
+ * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
+ * that correspond to that nop. Getting from one nop to the next, we
+ * add to the array the offset that is equal to the sum of all sizes of
+ * nops preceding the one we are after.
+ *
+ * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
+ * nice symmetry of sizes of the previous nops.
+ */
#if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
-/* Use inline assembly to define this because the nops are defined
- as inline assembly strings in the include files and we cannot
- get them easily into strings. */
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nintelnops: "
- GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
- GENERIC_NOP7 GENERIC_NOP8
- "\t.previous");
-extern const unsigned char intelnops[];
-static const unsigned char *const __initconst_or_module
-intel_nops[ASM_NOP_MAX+1] = {
+static const unsigned char intelnops[] =
+{
+ GENERIC_NOP1,
+ GENERIC_NOP2,
+ GENERIC_NOP3,
+ GENERIC_NOP4,
+ GENERIC_NOP5,
+ GENERIC_NOP6,
+ GENERIC_NOP7,
+ GENERIC_NOP8,
+ GENERIC_NOP5_ATOMIC
+};
+static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
+{
NULL,
intelnops,
intelnops + 1,
@@ -87,17 +100,25 @@ intel_nops[ASM_NOP_MAX+1] = {
intelnops + 1 + 2 + 3 + 4 + 5,
intelnops + 1 + 2 + 3 + 4 + 5 + 6,
intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+ intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
#ifdef K8_NOP1
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk8nops: "
- K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
- K8_NOP7 K8_NOP8
- "\t.previous");
-extern const unsigned char k8nops[];
-static const unsigned char *const __initconst_or_module
-k8_nops[ASM_NOP_MAX+1] = {
+static const unsigned char k8nops[] =
+{
+ K8_NOP1,
+ K8_NOP2,
+ K8_NOP3,
+ K8_NOP4,
+ K8_NOP5,
+ K8_NOP6,
+ K8_NOP7,
+ K8_NOP8,
+ K8_NOP5_ATOMIC
+};
+static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
+{
NULL,
k8nops,
k8nops + 1,
@@ -107,17 +128,25 @@ k8_nops[ASM_NOP_MAX+1] = {
k8nops + 1 + 2 + 3 + 4 + 5,
k8nops + 1 + 2 + 3 + 4 + 5 + 6,
k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+ k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
#if defined(K7_NOP1) && !defined(CONFIG_X86_64)
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk7nops: "
- K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
- K7_NOP7 K7_NOP8
- "\t.previous");
-extern const unsigned char k7nops[];
-static const unsigned char *const __initconst_or_module
-k7_nops[ASM_NOP_MAX+1] = {
+static const unsigned char k7nops[] =
+{
+ K7_NOP1,
+ K7_NOP2,
+ K7_NOP3,
+ K7_NOP4,
+ K7_NOP5,
+ K7_NOP6,
+ K7_NOP7,
+ K7_NOP8,
+ K7_NOP5_ATOMIC
+};
+static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
+{
NULL,
k7nops,
k7nops + 1,
@@ -127,17 +156,25 @@ k7_nops[ASM_NOP_MAX+1] = {
k7nops + 1 + 2 + 3 + 4 + 5,
k7nops + 1 + 2 + 3 + 4 + 5 + 6,
k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+ k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
#ifdef P6_NOP1
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\np6nops: "
- P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
- P6_NOP7 P6_NOP8
- "\t.previous");
-extern const unsigned char p6nops[];
-static const unsigned char *const __initconst_or_module
-p6_nops[ASM_NOP_MAX+1] = {
+static const unsigned char __initconst_or_module p6nops[] =
+{
+ P6_NOP1,
+ P6_NOP2,
+ P6_NOP3,
+ P6_NOP4,
+ P6_NOP5,
+ P6_NOP6,
+ P6_NOP7,
+ P6_NOP8,
+ P6_NOP5_ATOMIC
+};
+static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
+{
NULL,
p6nops,
p6nops + 1,
@@ -147,47 +184,65 @@ p6_nops[ASM_NOP_MAX+1] = {
p6nops + 1 + 2 + 3 + 4 + 5,
p6nops + 1 + 2 + 3 + 4 + 5 + 6,
p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+ p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
+/* Initialize these to a safe default */
#ifdef CONFIG_X86_64
+const unsigned char * const *ideal_nops = p6_nops;
+#else
+const unsigned char * const *ideal_nops = intel_nops;
+#endif
-extern char __vsyscall_0;
-static const unsigned char *const *__init_or_module find_nop_table(void)
+void __init arch_init_ideal_nops(void)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
- boot_cpu_has(X86_FEATURE_NOPL))
- return p6_nops;
- else
- return k8_nops;
-}
-
-#else /* CONFIG_X86_64 */
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ /*
+ * Due to a decoder implementation quirk, some
+ * specific Intel CPUs actually perform better with
+ * the "k8_nops" than with the SDM-recommended NOPs.
+ */
+ if (boot_cpu_data.x86 == 6 &&
+ boot_cpu_data.x86_model >= 0x0f &&
+ boot_cpu_data.x86_model != 0x1c &&
+ boot_cpu_data.x86_model != 0x26 &&
+ boot_cpu_data.x86_model != 0x27 &&
+ boot_cpu_data.x86_model < 0x30) {
+ ideal_nops = k8_nops;
+ } else if (boot_cpu_has(X86_FEATURE_NOPL)) {
+ ideal_nops = p6_nops;
+ } else {
+#ifdef CONFIG_X86_64
+ ideal_nops = k8_nops;
+#else
+ ideal_nops = intel_nops;
+#endif
+ }
-static const unsigned char *const *__init_or_module find_nop_table(void)
-{
- if (boot_cpu_has(X86_FEATURE_K8))
- return k8_nops;
- else if (boot_cpu_has(X86_FEATURE_K7))
- return k7_nops;
- else if (boot_cpu_has(X86_FEATURE_NOPL))
- return p6_nops;
- else
- return intel_nops;
+ default:
+#ifdef CONFIG_X86_64
+ ideal_nops = k8_nops;
+#else
+ if (boot_cpu_has(X86_FEATURE_K8))
+ ideal_nops = k8_nops;
+ else if (boot_cpu_has(X86_FEATURE_K7))
+ ideal_nops = k7_nops;
+ else
+ ideal_nops = intel_nops;
+#endif
+ }
}
-#endif /* CONFIG_X86_64 */
-
/* Use this to add nops to a buffer, then text_poke the whole buffer. */
static void __init_or_module add_nops(void *insns, unsigned int len)
{
- const unsigned char *const *noptable = find_nop_table();
-
while (len > 0) {
unsigned int noplen = len;
if (noplen > ASM_NOP_MAX)
noplen = ASM_NOP_MAX;
- memcpy(insns, noptable[noplen], noplen);
+ memcpy(insns, ideal_nops[noplen], noplen);
insns += noplen;
len -= noplen;
}
@@ -195,6 +250,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
+extern char __vsyscall_0;
void *text_poke_early(void *addr, const void *opcode, size_t len);
/* Replace instructions with better alternatives for this CPU type.
@@ -210,6 +266,15 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
u8 insnbuf[MAX_PATCH_LEN];
DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+ /*
+ * The scan order should be from start to end. A later scanned
+ * alternative code can overwrite a previous scanned alternative code.
+ * Some kernel functions (e.g. memcpy, memset, etc) use this order to
+ * patch code.
+ *
+ * So be careful if you want to change the scan order to any other
+ * order.
+ */
for (a = start; a < end; a++) {
u8 *instr = a->instr;
BUG_ON(a->replacementlen > a->instrlen);
@@ -678,29 +743,3 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
wrote_text = 0;
__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
}
-
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
-
-#ifdef CONFIG_X86_64
-unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
-#else
-unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
-#endif
-
-void __init arch_init_ideal_nop5(void)
-{
- /*
- * There is no good nop for all x86 archs. This selection
- * algorithm should be unified with the one in find_nop_table(),
- * but this should be good enough for now.
- *
- * For cases other than the ones below, use the safe (as in
- * always functional) defaults above.
- */
-#ifdef CONFIG_X86_64
- /* Don't use these on 32 bits due to broken virtualizers */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- memcpy(ideal_nop5, p6_nops[5], 5);
-#endif
-}
-#endif
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b117efd24f7..b117efd24f7 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 57ca7778722..873e7e1ead7 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -18,6 +18,7 @@
*/
#include <linux/pci.h>
+#include <linux/pci-ats.h>
#include <linux/bitmap.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
@@ -25,6 +26,7 @@
#include <linux/dma-mapping.h>
#include <linux/iommu-helper.h>
#include <linux/iommu.h>
+#include <linux/delay.h>
#include <asm/proto.h>
#include <asm/iommu.h>
#include <asm/gart.h>
@@ -34,7 +36,7 @@
#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
-#define EXIT_LOOP_COUNT 10000000
+#define LOOP_TIMEOUT 100000
static DEFINE_RWLOCK(amd_iommu_devtable_lock);
@@ -57,7 +59,6 @@ struct iommu_cmd {
u32 data[4];
};
-static void reset_iommu_command_buffer(struct amd_iommu *iommu);
static void update_domain(struct protection_domain *domain);
/****************************************************************************
@@ -322,8 +323,6 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
break;
case EVENT_TYPE_ILL_CMD:
printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
- iommu->reset_in_progress = true;
- reset_iommu_command_buffer(iommu);
dump_command(address);
break;
case EVENT_TYPE_CMD_HARD_ERR:
@@ -367,7 +366,7 @@ static void iommu_poll_events(struct amd_iommu *iommu)
spin_unlock_irqrestore(&iommu->lock, flags);
}
-irqreturn_t amd_iommu_int_handler(int irq, void *data)
+irqreturn_t amd_iommu_int_thread(int irq, void *data)
{
struct amd_iommu *iommu;
@@ -377,192 +376,300 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
return IRQ_HANDLED;
}
+irqreturn_t amd_iommu_int_handler(int irq, void *data)
+{
+ return IRQ_WAKE_THREAD;
+}
+
/****************************************************************************
*
* IOMMU command queuing functions
*
****************************************************************************/
-/*
- * Writes the command to the IOMMUs command buffer and informs the
- * hardware about the new command. Must be called with iommu->lock held.
- */
-static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
+static int wait_on_sem(volatile u64 *sem)
+{
+ int i = 0;
+
+ while (*sem == 0 && i < LOOP_TIMEOUT) {
+ udelay(1);
+ i += 1;
+ }
+
+ if (i == LOOP_TIMEOUT) {
+ pr_alert("AMD-Vi: Completion-Wait loop timed out\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static void copy_cmd_to_buffer(struct amd_iommu *iommu,
+ struct iommu_cmd *cmd,
+ u32 tail)
{
- u32 tail, head;
u8 *target;
- WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
- tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
target = iommu->cmd_buf + tail;
- memcpy_toio(target, cmd, sizeof(*cmd));
- tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
- head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
- if (tail == head)
- return -ENOMEM;
+ tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
+
+ /* Copy command to buffer */
+ memcpy(target, cmd, sizeof(*cmd));
+
+ /* Tell the IOMMU about it */
writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+}
- return 0;
+static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
+{
+ WARN_ON(address & 0x7ULL);
+
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->data[0] = lower_32_bits(__pa(address)) | CMD_COMPL_WAIT_STORE_MASK;
+ cmd->data[1] = upper_32_bits(__pa(address));
+ cmd->data[2] = 1;
+ CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
+}
+
+static void build_inv_dte(struct iommu_cmd *cmd, u16 devid)
+{
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->data[0] = devid;
+ CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY);
+}
+
+static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
+ size_t size, u16 domid, int pde)
+{
+ u64 pages;
+ int s;
+
+ pages = iommu_num_pages(address, size, PAGE_SIZE);
+ s = 0;
+
+ if (pages > 1) {
+ /*
+ * If we have to flush more than one page, flush all
+ * TLB entries for this domain
+ */
+ address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+ s = 1;
+ }
+
+ address &= PAGE_MASK;
+
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->data[1] |= domid;
+ cmd->data[2] = lower_32_bits(address);
+ cmd->data[3] = upper_32_bits(address);
+ CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
+ if (s) /* size bit - we flush more than one 4kb page */
+ cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+ if (pde) /* PDE bit - we wan't flush everything not only the PTEs */
+ cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+}
+
+static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
+ u64 address, size_t size)
+{
+ u64 pages;
+ int s;
+
+ pages = iommu_num_pages(address, size, PAGE_SIZE);
+ s = 0;
+
+ if (pages > 1) {
+ /*
+ * If we have to flush more than one page, flush all
+ * TLB entries for this domain
+ */
+ address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+ s = 1;
+ }
+
+ address &= PAGE_MASK;
+
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->data[0] = devid;
+ cmd->data[0] |= (qdep & 0xff) << 24;
+ cmd->data[1] = devid;
+ cmd->data[2] = lower_32_bits(address);
+ cmd->data[3] = upper_32_bits(address);
+ CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
+ if (s)
+ cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+}
+
+static void build_inv_all(struct iommu_cmd *cmd)
+{
+ memset(cmd, 0, sizeof(*cmd));
+ CMD_SET_TYPE(cmd, CMD_INV_ALL);
}
/*
- * General queuing function for commands. Takes iommu->lock and calls
- * __iommu_queue_command().
+ * Writes the command to the IOMMUs command buffer and informs the
+ * hardware about the new command.
*/
static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
{
+ u32 left, tail, head, next_tail;
unsigned long flags;
- int ret;
+ WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
+
+again:
spin_lock_irqsave(&iommu->lock, flags);
- ret = __iommu_queue_command(iommu, cmd);
- if (!ret)
- iommu->need_sync = true;
- spin_unlock_irqrestore(&iommu->lock, flags);
- return ret;
-}
+ head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+ tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+ next_tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
+ left = (head - next_tail) % iommu->cmd_buf_size;
-/*
- * This function waits until an IOMMU has completed a completion
- * wait command
- */
-static void __iommu_wait_for_completion(struct amd_iommu *iommu)
-{
- int ready = 0;
- unsigned status = 0;
- unsigned long i = 0;
+ if (left <= 2) {
+ struct iommu_cmd sync_cmd;
+ volatile u64 sem = 0;
+ int ret;
- INC_STATS_COUNTER(compl_wait);
+ build_completion_wait(&sync_cmd, (u64)&sem);
+ copy_cmd_to_buffer(iommu, &sync_cmd, tail);
- while (!ready && (i < EXIT_LOOP_COUNT)) {
- ++i;
- /* wait for the bit to become one */
- status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
- ready = status & MMIO_STATUS_COM_WAIT_INT_MASK;
+ spin_unlock_irqrestore(&iommu->lock, flags);
+
+ if ((ret = wait_on_sem(&sem)) != 0)
+ return ret;
+
+ goto again;
}
- /* set bit back to zero */
- status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
- writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
+ copy_cmd_to_buffer(iommu, cmd, tail);
+
+ /* We need to sync now to make sure all commands are processed */
+ iommu->need_sync = true;
+
+ spin_unlock_irqrestore(&iommu->lock, flags);
- if (unlikely(i == EXIT_LOOP_COUNT))
- iommu->reset_in_progress = true;
+ return 0;
}
/*
* This function queues a completion wait command into the command
* buffer of an IOMMU
*/
-static int __iommu_completion_wait(struct amd_iommu *iommu)
+static int iommu_completion_wait(struct amd_iommu *iommu)
{
struct iommu_cmd cmd;
+ volatile u64 sem = 0;
+ int ret;
- memset(&cmd, 0, sizeof(cmd));
- cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
- CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
+ if (!iommu->need_sync)
+ return 0;
- return __iommu_queue_command(iommu, &cmd);
+ build_completion_wait(&cmd, (u64)&sem);
+
+ ret = iommu_queue_command(iommu, &cmd);
+ if (ret)
+ return ret;
+
+ return wait_on_sem(&sem);
}
-/*
- * This function is called whenever we need to ensure that the IOMMU has
- * completed execution of all commands we sent. It sends a
- * COMPLETION_WAIT command and waits for it to finish. The IOMMU informs
- * us about that by writing a value to a physical address we pass with
- * the command.
- */
-static int iommu_completion_wait(struct amd_iommu *iommu)
+static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
{
- int ret = 0;
- unsigned long flags;
+ struct iommu_cmd cmd;
- spin_lock_irqsave(&iommu->lock, flags);
+ build_inv_dte(&cmd, devid);
- if (!iommu->need_sync)
- goto out;
+ return iommu_queue_command(iommu, &cmd);
+}
- ret = __iommu_completion_wait(iommu);
+static void iommu_flush_dte_all(struct amd_iommu *iommu)
+{
+ u32 devid;
- iommu->need_sync = false;
+ for (devid = 0; devid <= 0xffff; ++devid)
+ iommu_flush_dte(iommu, devid);
- if (ret)
- goto out;
-
- __iommu_wait_for_completion(iommu);
+ iommu_completion_wait(iommu);
+}
-out:
- spin_unlock_irqrestore(&iommu->lock, flags);
+/*
+ * This function uses heavy locking and may disable irqs for some time. But
+ * this is no issue because it is only called during resume.
+ */
+static void iommu_flush_tlb_all(struct amd_iommu *iommu)
+{
+ u32 dom_id;
- if (iommu->reset_in_progress)
- reset_iommu_command_buffer(iommu);
+ for (dom_id = 0; dom_id <= 0xffff; ++dom_id) {
+ struct iommu_cmd cmd;
+ build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+ dom_id, 1);
+ iommu_queue_command(iommu, &cmd);
+ }
- return 0;
+ iommu_completion_wait(iommu);
}
-static void iommu_flush_complete(struct protection_domain *domain)
+static void iommu_flush_all(struct amd_iommu *iommu)
{
- int i;
+ struct iommu_cmd cmd;
- for (i = 0; i < amd_iommus_present; ++i) {
- if (!domain->dev_iommu[i])
- continue;
+ build_inv_all(&cmd);
- /*
- * Devices of this domain are behind this IOMMU
- * We need to wait for completion of all commands.
- */
- iommu_completion_wait(amd_iommus[i]);
+ iommu_queue_command(iommu, &cmd);
+ iommu_completion_wait(iommu);
+}
+
+void iommu_flush_all_caches(struct amd_iommu *iommu)
+{
+ if (iommu_feature(iommu, FEATURE_IA)) {
+ iommu_flush_all(iommu);
+ } else {
+ iommu_flush_dte_all(iommu);
+ iommu_flush_tlb_all(iommu);
}
}
/*
- * Command send function for invalidating a device table entry
+ * Command send function for flushing on-device TLB
*/
-static int iommu_flush_device(struct device *dev)
+static int device_flush_iotlb(struct device *dev, u64 address, size_t size)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct amd_iommu *iommu;
struct iommu_cmd cmd;
u16 devid;
+ int qdep;
+ qdep = pci_ats_queue_depth(pdev);
devid = get_device_id(dev);
iommu = amd_iommu_rlookup_table[devid];
- /* Build command */
- memset(&cmd, 0, sizeof(cmd));
- CMD_SET_TYPE(&cmd, CMD_INV_DEV_ENTRY);
- cmd.data[0] = devid;
+ build_inv_iotlb_pages(&cmd, devid, qdep, address, size);
return iommu_queue_command(iommu, &cmd);
}
-static void __iommu_build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
- u16 domid, int pde, int s)
-{
- memset(cmd, 0, sizeof(*cmd));
- address &= PAGE_MASK;
- CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
- cmd->data[1] |= domid;
- cmd->data[2] = lower_32_bits(address);
- cmd->data[3] = upper_32_bits(address);
- if (s) /* size bit - we flush more than one 4kb page */
- cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
- if (pde) /* PDE bit - we wan't flush everything not only the PTEs */
- cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-}
-
/*
- * Generic command send function for invalidaing TLB entries
+ * Command send function for invalidating a device table entry
*/
-static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
- u64 address, u16 domid, int pde, int s)
+static int device_flush_dte(struct device *dev)
{
- struct iommu_cmd cmd;
+ struct amd_iommu *iommu;
+ struct pci_dev *pdev;
+ u16 devid;
int ret;
- __iommu_build_inv_iommu_pages(&cmd, address, domid, pde, s);
+ pdev = to_pci_dev(dev);
+ devid = get_device_id(dev);
+ iommu = amd_iommu_rlookup_table[devid];
- ret = iommu_queue_command(iommu, &cmd);
+ ret = iommu_flush_dte(iommu, devid);
+ if (ret)
+ return ret;
+
+ if (pci_ats_enabled(pdev))
+ ret = device_flush_iotlb(dev, 0, ~0UL);
return ret;
}
@@ -572,23 +679,14 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
* It invalidates a single PTE if the range to flush is within a single
* page. Otherwise it flushes the whole TLB of the IOMMU.
*/
-static void __iommu_flush_pages(struct protection_domain *domain,
- u64 address, size_t size, int pde)
+static void __domain_flush_pages(struct protection_domain *domain,
+ u64 address, size_t size, int pde)
{
- int s = 0, i;
- unsigned long pages = iommu_num_pages(address, size, PAGE_SIZE);
-
- address &= PAGE_MASK;
-
- if (pages > 1) {
- /*
- * If we have to flush more than one page, flush all
- * TLB entries for this domain
- */
- address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
- s = 1;
- }
+ struct iommu_dev_data *dev_data;
+ struct iommu_cmd cmd;
+ int ret = 0, i;
+ build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
for (i = 0; i < amd_iommus_present; ++i) {
if (!domain->dev_iommu[i])
@@ -598,101 +696,70 @@ static void __iommu_flush_pages(struct protection_domain *domain,
* Devices of this domain are behind this IOMMU
* We need a TLB flush
*/
- iommu_queue_inv_iommu_pages(amd_iommus[i], address,
- domain->id, pde, s);
+ ret |= iommu_queue_command(amd_iommus[i], &cmd);
+ }
+
+ list_for_each_entry(dev_data, &domain->dev_list, list) {
+ struct pci_dev *pdev = to_pci_dev(dev_data->dev);
+
+ if (!pci_ats_enabled(pdev))
+ continue;
+
+ ret |= device_flush_iotlb(dev_data->dev, address, size);
}
- return;
+ WARN_ON(ret);
}
-static void iommu_flush_pages(struct protection_domain *domain,
- u64 address, size_t size)
+static void domain_flush_pages(struct protection_domain *domain,
+ u64 address, size_t size)
{
- __iommu_flush_pages(domain, address, size, 0);
+ __domain_flush_pages(domain, address, size, 0);
}
/* Flush the whole IO/TLB for a given protection domain */
-static void iommu_flush_tlb(struct protection_domain *domain)
+static void domain_flush_tlb(struct protection_domain *domain)
{
- __iommu_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0);
+ __domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0);
}
/* Flush the whole IO/TLB for a given protection domain - including PDE */
-static void iommu_flush_tlb_pde(struct protection_domain *domain)
+static void domain_flush_tlb_pde(struct protection_domain *domain)
{
- __iommu_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
-}
-
-
-/*
- * This function flushes the DTEs for all devices in domain
- */
-static void iommu_flush_domain_devices(struct protection_domain *domain)
-{
- struct iommu_dev_data *dev_data;
- unsigned long flags;
-
- spin_lock_irqsave(&domain->lock, flags);
-
- list_for_each_entry(dev_data, &domain->dev_list, list)
- iommu_flush_device(dev_data->dev);
-
- spin_unlock_irqrestore(&domain->lock, flags);
+ __domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
}
-static void iommu_flush_all_domain_devices(void)
+static void domain_flush_complete(struct protection_domain *domain)
{
- struct protection_domain *domain;
- unsigned long flags;
+ int i;
- spin_lock_irqsave(&amd_iommu_pd_lock, flags);
+ for (i = 0; i < amd_iommus_present; ++i) {
+ if (!domain->dev_iommu[i])
+ continue;
- list_for_each_entry(domain, &amd_iommu_pd_list, list) {
- iommu_flush_domain_devices(domain);
- iommu_flush_complete(domain);
+ /*
+ * Devices of this domain are behind this IOMMU
+ * We need to wait for completion of all commands.
+ */
+ iommu_completion_wait(amd_iommus[i]);
}
-
- spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
}
-void amd_iommu_flush_all_devices(void)
-{
- iommu_flush_all_domain_devices();
-}
/*
- * This function uses heavy locking and may disable irqs for some time. But
- * this is no issue because it is only called during resume.
+ * This function flushes the DTEs for all devices in domain
*/
-void amd_iommu_flush_all_domains(void)
+static void domain_flush_devices(struct protection_domain *domain)
{
- struct protection_domain *domain;
+ struct iommu_dev_data *dev_data;
unsigned long flags;
- spin_lock_irqsave(&amd_iommu_pd_lock, flags);
-
- list_for_each_entry(domain, &amd_iommu_pd_list, list) {
- spin_lock(&domain->lock);
- iommu_flush_tlb_pde(domain);
- iommu_flush_complete(domain);
- spin_unlock(&domain->lock);
- }
-
- spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
-}
-
-static void reset_iommu_command_buffer(struct amd_iommu *iommu)
-{
- pr_err("AMD-Vi: Resetting IOMMU command buffer\n");
-
- if (iommu->reset_in_progress)
- panic("AMD-Vi: ILLEGAL_COMMAND_ERROR while resetting command buffer\n");
+ spin_lock_irqsave(&domain->lock, flags);
- amd_iommu_reset_cmd_buffer(iommu);
- amd_iommu_flush_all_devices();
- amd_iommu_flush_all_domains();
+ list_for_each_entry(dev_data, &domain->dev_list, list)
+ device_flush_dte(dev_data->dev);
- iommu->reset_in_progress = false;
+ spin_unlock_irqrestore(&domain->lock, flags);
}
/****************************************************************************
@@ -1410,17 +1477,22 @@ static bool dma_ops_domain(struct protection_domain *domain)
return domain->flags & PD_DMA_OPS_MASK;
}
-static void set_dte_entry(u16 devid, struct protection_domain *domain)
+static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
{
u64 pte_root = virt_to_phys(domain->pt_root);
+ u32 flags = 0;
pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
<< DEV_ENTRY_MODE_SHIFT;
pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
- amd_iommu_dev_table[devid].data[2] = domain->id;
- amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
- amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
+ if (ats)
+ flags |= DTE_FLAG_IOTLB;
+
+ amd_iommu_dev_table[devid].data[3] |= flags;
+ amd_iommu_dev_table[devid].data[2] = domain->id;
+ amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
+ amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
}
static void clear_dte_entry(u16 devid)
@@ -1437,34 +1509,42 @@ static void do_attach(struct device *dev, struct protection_domain *domain)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu;
+ struct pci_dev *pdev;
+ bool ats = false;
u16 devid;
devid = get_device_id(dev);
iommu = amd_iommu_rlookup_table[devid];
dev_data = get_dev_data(dev);
+ pdev = to_pci_dev(dev);
+
+ if (amd_iommu_iotlb_sup)
+ ats = pci_ats_enabled(pdev);
/* Update data structures */
dev_data->domain = domain;
list_add(&dev_data->list, &domain->dev_list);
- set_dte_entry(devid, domain);
+ set_dte_entry(devid, domain, ats);
/* Do reference counting */
domain->dev_iommu[iommu->index] += 1;
domain->dev_cnt += 1;
/* Flush the DTE entry */
- iommu_flush_device(dev);
+ device_flush_dte(dev);
}
static void do_detach(struct device *dev)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu;
+ struct pci_dev *pdev;
u16 devid;
devid = get_device_id(dev);
iommu = amd_iommu_rlookup_table[devid];
dev_data = get_dev_data(dev);
+ pdev = to_pci_dev(dev);
/* decrease reference counters */
dev_data->domain->dev_iommu[iommu->index] -= 1;
@@ -1476,7 +1556,7 @@ static void do_detach(struct device *dev)
clear_dte_entry(devid);
/* Flush the DTE entry */
- iommu_flush_device(dev);
+ device_flush_dte(dev);
}
/*
@@ -1539,9 +1619,13 @@ out_unlock:
static int attach_device(struct device *dev,
struct protection_domain *domain)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
unsigned long flags;
int ret;
+ if (amd_iommu_iotlb_sup)
+ pci_enable_ats(pdev, PAGE_SHIFT);
+
write_lock_irqsave(&amd_iommu_devtable_lock, flags);
ret = __attach_device(dev, domain);
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -1551,7 +1635,7 @@ static int attach_device(struct device *dev,
* left the caches in the IOMMU dirty. So we have to flush
* here to evict all dirty stuff.
*/
- iommu_flush_tlb_pde(domain);
+ domain_flush_tlb_pde(domain);
return ret;
}
@@ -1598,12 +1682,16 @@ static void __detach_device(struct device *dev)
*/
static void detach_device(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
unsigned long flags;
/* lock device table */
write_lock_irqsave(&amd_iommu_devtable_lock, flags);
__detach_device(dev);
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+ if (amd_iommu_iotlb_sup && pci_ats_enabled(pdev))
+ pci_disable_ats(pdev);
}
/*
@@ -1692,7 +1780,7 @@ static int device_change_notifier(struct notifier_block *nb,
goto out;
}
- iommu_flush_device(dev);
+ device_flush_dte(dev);
iommu_completion_wait(iommu);
out:
@@ -1753,8 +1841,9 @@ static void update_device_table(struct protection_domain *domain)
struct iommu_dev_data *dev_data;
list_for_each_entry(dev_data, &domain->dev_list, list) {
+ struct pci_dev *pdev = to_pci_dev(dev_data->dev);
u16 devid = get_device_id(dev_data->dev);
- set_dte_entry(devid, domain);
+ set_dte_entry(devid, domain, pci_ats_enabled(pdev));
}
}
@@ -1764,8 +1853,9 @@ static void update_domain(struct protection_domain *domain)
return;
update_device_table(domain);
- iommu_flush_domain_devices(domain);
- iommu_flush_tlb_pde(domain);
+
+ domain_flush_devices(domain);
+ domain_flush_tlb_pde(domain);
domain->updated = false;
}
@@ -1924,10 +2014,10 @@ retry:
ADD_STATS_COUNTER(alloced_io_mem, size);
if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) {
- iommu_flush_tlb(&dma_dom->domain);
+ domain_flush_tlb(&dma_dom->domain);
dma_dom->need_flush = false;
} else if (unlikely(amd_iommu_np_cache))
- iommu_flush_pages(&dma_dom->domain, address, size);
+ domain_flush_pages(&dma_dom->domain, address, size);
out:
return address;
@@ -1976,7 +2066,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
dma_ops_free_addresses(dma_dom, dma_addr, pages);
if (amd_iommu_unmap_flush || dma_dom->need_flush) {
- iommu_flush_pages(&dma_dom->domain, flush_addr, size);
+ domain_flush_pages(&dma_dom->domain, flush_addr, size);
dma_dom->need_flush = false;
}
}
@@ -2012,7 +2102,7 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
if (addr == DMA_ERROR_CODE)
goto out;
- iommu_flush_complete(domain);
+ domain_flush_complete(domain);
out:
spin_unlock_irqrestore(&domain->lock, flags);
@@ -2039,7 +2129,7 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
__unmap_single(domain->priv, dma_addr, size, dir);
- iommu_flush_complete(domain);
+ domain_flush_complete(domain);
spin_unlock_irqrestore(&domain->lock, flags);
}
@@ -2104,7 +2194,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
goto unmap;
}
- iommu_flush_complete(domain);
+ domain_flush_complete(domain);
out:
spin_unlock_irqrestore(&domain->lock, flags);
@@ -2150,7 +2240,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
s->dma_address = s->dma_length = 0;
}
- iommu_flush_complete(domain);
+ domain_flush_complete(domain);
spin_unlock_irqrestore(&domain->lock, flags);
}
@@ -2200,7 +2290,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
goto out_free;
}
- iommu_flush_complete(domain);
+ domain_flush_complete(domain);
spin_unlock_irqrestore(&domain->lock, flags);
@@ -2232,7 +2322,7 @@ static void free_coherent(struct device *dev, size_t size,
__unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
- iommu_flush_complete(domain);
+ domain_flush_complete(domain);
spin_unlock_irqrestore(&domain->lock, flags);
@@ -2476,7 +2566,7 @@ static void amd_iommu_detach_device(struct iommu_domain *dom,
if (!iommu)
return;
- iommu_flush_device(dev);
+ device_flush_dte(dev);
iommu_completion_wait(iommu);
}
@@ -2542,7 +2632,7 @@ static int amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
unmap_size = iommu_unmap_page(domain, iova, page_size);
mutex_unlock(&domain->api_lock);
- iommu_flush_tlb_pde(domain);
+ domain_flush_tlb_pde(domain);
return get_order(unmap_size);
}
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 246d727b65b..9179c21120a 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -137,6 +137,7 @@ int amd_iommus_present;
/* IOMMUs have a non-present cache? */
bool amd_iommu_np_cache __read_mostly;
+bool amd_iommu_iotlb_sup __read_mostly = true;
/*
* The ACPI table parsing functions set this variable on an error
@@ -180,6 +181,12 @@ static u32 dev_table_size; /* size of the device table */
static u32 alias_table_size; /* size of the alias table */
static u32 rlookup_table_size; /* size if the rlookup table */
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+extern void iommu_flush_all_caches(struct amd_iommu *iommu);
+
static inline void update_last_devid(u16 devid)
{
if (devid > amd_iommu_last_bdf)
@@ -293,9 +300,23 @@ static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
/* Function to enable the hardware */
static void iommu_enable(struct amd_iommu *iommu)
{
- printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx\n",
+ static const char * const feat_str[] = {
+ "PreF", "PPR", "X2APIC", "NX", "GT", "[5]",
+ "IA", "GA", "HE", "PC", NULL
+ };
+ int i;
+
+ printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx",
dev_name(&iommu->dev->dev), iommu->cap_ptr);
+ if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
+ printk(KERN_CONT " extended features: ");
+ for (i = 0; feat_str[i]; ++i)
+ if (iommu_feature(iommu, (1ULL << i)))
+ printk(KERN_CONT " %s", feat_str[i]);
+ }
+ printk(KERN_CONT "\n");
+
iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
}
@@ -651,7 +672,7 @@ static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
static void __init init_iommu_from_pci(struct amd_iommu *iommu)
{
int cap_ptr = iommu->cap_ptr;
- u32 range, misc;
+ u32 range, misc, low, high;
int i, j;
pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
@@ -667,6 +688,15 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
MMIO_GET_LD(range));
iommu->evt_msi_num = MMIO_MSI_NUM(misc);
+ if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
+ amd_iommu_iotlb_sup = false;
+
+ /* read extended feature bits */
+ low = readl(iommu->mmio_base + MMIO_EXT_FEATURES);
+ high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4);
+
+ iommu->features = ((u64)high << 32) | low;
+
if (!is_rd890_iommu(iommu->dev))
return;
@@ -1004,10 +1034,11 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
if (pci_enable_msi(iommu->dev))
return 1;
- r = request_irq(iommu->dev->irq, amd_iommu_int_handler,
- IRQF_SAMPLE_RANDOM,
- "AMD-Vi",
- NULL);
+ r = request_threaded_irq(iommu->dev->irq,
+ amd_iommu_int_handler,
+ amd_iommu_int_thread,
+ 0, "AMD-Vi",
+ iommu->dev);
if (r) {
pci_disable_msi(iommu->dev);
@@ -1244,6 +1275,7 @@ static void enable_iommus(void)
iommu_set_exclusion_range(iommu);
iommu_init_msi(iommu);
iommu_enable(iommu);
+ iommu_flush_all_caches(iommu);
}
}
@@ -1274,8 +1306,8 @@ static void amd_iommu_resume(void)
* we have to flush after the IOMMUs are enabled because a
* disabled IOMMU will never execute the commands we send
*/
- amd_iommu_flush_all_devices();
- amd_iommu_flush_all_domains();
+ for_each_iommu(iommu)
+ iommu_flush_all_caches(iommu);
}
static int amd_iommu_suspend(void)
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index cd1ffed4ee2..289e92862fd 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -177,7 +177,6 @@ static struct clocksource clocksource_apbt = {
.rating = APBT_CLOCKSOURCE_RATING,
.read = apbt_read_clocksource,
.mask = APBT_MASK,
- .shift = APBT_SHIFT,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.resume = apbt_restart_clocksource,
};
@@ -543,14 +542,7 @@ static int apbt_clocksource_register(void)
if (t1 == apbt_read_clocksource(&clocksource_apbt))
panic("APBT counter not counting. APBT disabled\n");
- /*
- * initialize and register APBT clocksource
- * convert that to ns/clock cycle
- * mult = (ns/c) * 2^APBT_SHIFT
- */
- clocksource_apbt.mult = div_sc(MSEC_PER_SEC,
- (unsigned long) apbt_freq, APBT_SHIFT);
- clocksource_register(&clocksource_apbt);
+ clocksource_register_khz(&clocksource_apbt, (u32)apbt_freq*1000);
return 0;
}
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 73fb469908c..3d2661ca654 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -30,6 +30,22 @@
#include <asm/amd_nb.h>
#include <asm/x86_init.h>
+/*
+ * Using 512M as goal, in case kexec will load kernel_big
+ * that will do the on-position decompress, and could overlap with
+ * with the gart aperture that is used.
+ * Sequence:
+ * kernel_small
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kernel_small (gart area become e820_reserved)
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+ * So don't use 512M below as gart iommu, leave the space for kernel
+ * code for safe.
+ */
+#define GART_MIN_ADDR (512ULL << 20)
+#define GART_MAX_ADDR (1ULL << 32)
+
int gart_iommu_aperture;
int gart_iommu_aperture_disabled __initdata;
int gart_iommu_aperture_allowed __initdata;
@@ -70,21 +86,9 @@ static u32 __init allocate_aperture(void)
* memory. Unfortunately we cannot move it up because that would
* make the IOMMU useless.
*/
- /*
- * using 512M as goal, in case kexec will load kernel_big
- * that will do the on position decompress, and could overlap with
- * that position with gart that is used.
- * sequende:
- * kernel_small
- * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
- * ==> kernel_small(gart area become e820_reserved)
- * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
- * ==> kerne_big (uncompressed size will be big than 64M or 128M)
- * so don't use 512M below as gart iommu, leave the space for kernel
- * code for safe
- */
- addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20);
- if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) {
+ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
+ aper_size, aper_size);
+ if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) {
printk(KERN_ERR
"Cannot allocate aperture memory hole (%lx,%uK)\n",
addr, aper_size>>10);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index fabf01eff77..f92a8e5d1e2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -505,7 +505,7 @@ static void __cpuinit setup_APIC_timer(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
- if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_ARAT)) {
+ if (this_cpu_has(X86_FEATURE_ARAT)) {
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
/* Make LAPIC timer preferrable over percpu HPET */
lapic_clockevent.rating = 150;
@@ -1237,6 +1237,17 @@ void __cpuinit setup_local_APIC(void)
/* always use the value from LDR */
early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
logical_smp_processor_id();
+
+ /*
+ * Some NUMA implementations (NUMAQ) don't initialize apicid to
+ * node mapping during NUMA init. Now that logical apicid is
+ * guaranteed to be known, give it another chance. This is already
+ * a bit too late - percpu allocation has already happened without
+ * proper NUMA affinity.
+ */
+ if (apic->x86_32_numa_cpu_node)
+ set_apicid_to_node(early_per_cpu(x86_cpu_to_apicid, cpu),
+ apic->x86_32_numa_cpu_node(cpu));
#endif
/*
@@ -1812,30 +1823,41 @@ void smp_spurious_interrupt(struct pt_regs *regs)
*/
void smp_error_interrupt(struct pt_regs *regs)
{
- u32 v, v1;
+ u32 v0, v1;
+ u32 i = 0;
+ static const char * const error_interrupt_reason[] = {
+ "Send CS error", /* APIC Error Bit 0 */
+ "Receive CS error", /* APIC Error Bit 1 */
+ "Send accept error", /* APIC Error Bit 2 */
+ "Receive accept error", /* APIC Error Bit 3 */
+ "Redirectable IPI", /* APIC Error Bit 4 */
+ "Send illegal vector", /* APIC Error Bit 5 */
+ "Received illegal vector", /* APIC Error Bit 6 */
+ "Illegal register address", /* APIC Error Bit 7 */
+ };
exit_idle();
irq_enter();
/* First tickle the hardware, only then report what went on. -- REW */
- v = apic_read(APIC_ESR);
+ v0 = apic_read(APIC_ESR);
apic_write(APIC_ESR, 0);
v1 = apic_read(APIC_ESR);
ack_APIC_irq();
atomic_inc(&irq_err_count);
- /*
- * Here is what the APIC error bits mean:
- * 0: Send CS error
- * 1: Receive CS error
- * 2: Send accept error
- * 3: Receive accept error
- * 4: Reserved
- * 5: Send illegal vector
- * 6: Received illegal vector
- * 7: Illegal register address
- */
- pr_debug("APIC error on CPU%d: %02x(%02x)\n",
- smp_processor_id(), v , v1);
+ apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)",
+ smp_processor_id(), v0 , v1);
+
+ v1 = v1 & 0xff;
+ while (v1) {
+ if (v1 & 0x1)
+ apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
+ i++;
+ v1 >>= 1;
+ };
+
+ apic_printk(APIC_DEBUG, KERN_CONT "\n");
+
irq_exit();
}
@@ -2003,21 +2025,6 @@ void default_init_apic_ldr(void)
apic_write(APIC_LDR, val);
}
-#ifdef CONFIG_X86_32
-int default_x86_32_numa_cpu_node(int cpu)
-{
-#ifdef CONFIG_NUMA
- int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-
- if (apicid != BAD_APICID)
- return __apicid_to_node[apicid];
- return NUMA_NO_NODE;
-#else
- return 0;
-#endif
-}
-#endif
-
/*
* Power management
*/
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index f1baa2dc087..775b82bc655 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -119,14 +119,6 @@ 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,
@@ -195,6 +187,5 @@ struct apic apic_noop = {
#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 541a2e43165..d84ac5a584b 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -253,5 +253,4 @@ struct apic apic_bigsmp = {
.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 3e9de4854c5..70533de5bd2 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -510,11 +510,6 @@ static void es7000_setup_apic_routing(void)
nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
}
-static int es7000_numa_cpu_node(int cpu)
-{
- return 0;
-}
-
static int es7000_cpu_present_to_apicid(int mps_cpu)
{
if (!mps_cpu)
@@ -688,7 +683,6 @@ struct apic __refdata apic_es7000_cluster = {
.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 = {
@@ -752,5 +746,4 @@ struct apic __refdata apic_es7000 = {
.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/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 6273eee5134..30f13319e24 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -48,8 +48,6 @@
#include <asm/e820.h>
#include <asm/ipi.h>
-#define MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT))
-
int found_numaq;
/*
@@ -79,31 +77,20 @@ int quad_local_to_mp_bus_id[NR_CPUS/4][4];
static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
{
struct eachquadmem *eq = scd->eq + node;
+ u64 start = (u64)(eq->hi_shrd_mem_start - eq->priv_mem_size) << 20;
+ u64 end = (u64)(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size) << 20;
+ int ret;
- node_set_online(node);
-
- /* Convert to pages */
- node_start_pfn[node] =
- MB_TO_PAGES(eq->hi_shrd_mem_start - eq->priv_mem_size);
-
- node_end_pfn[node] =
- MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
-
- memblock_x86_register_active_regions(node, node_start_pfn[node],
- node_end_pfn[node]);
-
- memory_present(node, node_start_pfn[node], node_end_pfn[node]);
-
- node_remap_size[node] = node_memmap_size_bytes(node,
- node_start_pfn[node],
- node_end_pfn[node]);
+ node_set(node, numa_nodes_parsed);
+ ret = numa_add_memblk(node, start, end);
+ BUG_ON(ret < 0);
}
/*
* Function: smp_dump_qct()
*
* Description: gets memory layout from the quad config table. This
- * function also updates node_online_map with the nodes (quads) present.
+ * function also updates numa_nodes_parsed with the nodes (quads) present.
*/
static void __init smp_dump_qct(void)
{
@@ -112,7 +99,6 @@ static void __init smp_dump_qct(void)
scd = (void *)__va(SYS_CFG_DATA_PRIV_ADDR);
- nodes_clear(node_online_map);
for_each_node(node) {
if (scd->quads_present31_0 & (1 << node))
numaq_register_node(node, scd);
@@ -282,14 +268,14 @@ static __init void early_check_numaq(void)
}
}
-int __init get_memcfg_numaq(void)
+int __init numaq_numa_init(void)
{
early_check_numaq();
if (!found_numaq)
- return 0;
+ return -ENOENT;
smp_dump_qct();
- return 1;
+ return 0;
}
#define NUMAQ_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index fc84c7b6110..6541e471fd9 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -172,7 +172,6 @@ struct apic apic_default = {
.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 e4b8059b414..35bcd7d995a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -551,5 +551,4 @@ struct apic apic_summit = {
.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_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 33b10a0fc09..7acd2d2ac96 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -37,6 +37,13 @@
#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);
@@ -642,18 +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;
+
/*
- * Use a lock so only one cpu prints at a time
- * to prevent intermixed output.
+ * 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.
+ * 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);
@@ -661,7 +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)
@@ -720,8 +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;
@@ -747,6 +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++;
}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index adee12e0da1..3bfa0223596 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1238,7 +1238,6 @@ static int suspend(int vetoable)
dpm_suspend_noirq(PMSG_SUSPEND);
local_irq_disable();
- sysdev_suspend(PMSG_SUSPEND);
syscore_suspend();
local_irq_enable();
@@ -1258,7 +1257,6 @@ static int suspend(int vetoable)
err = (err == APM_SUCCESS) ? 0 : -EIO;
syscore_resume();
- sysdev_resume();
local_irq_enable();
dpm_resume_noirq(PMSG_RESUME);
@@ -1282,7 +1280,6 @@ static void standby(void)
dpm_suspend_noirq(PMSG_SUSPEND);
local_irq_disable();
- sysdev_suspend(PMSG_SUSPEND);
syscore_suspend();
local_irq_enable();
@@ -1292,7 +1289,6 @@ static void standby(void)
local_irq_disable();
syscore_resume();
- sysdev_resume();
local_irq_enable();
dpm_resume_noirq(PMSG_RESUME);
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 3532d3bf810..6f9d1f6063e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -613,7 +613,7 @@ 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))
+ if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
set_cpu_cap(c, X86_FEATURE_ARAT);
/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e2ced0074a4..cbc70a27430 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -254,6 +254,25 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
}
#endif
+static int disable_smep __initdata;
+static __init int setup_disable_smep(char *arg)
+{
+ disable_smep = 1;
+ return 1;
+}
+__setup("nosmep", setup_disable_smep);
+
+static __init void setup_smep(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_SMEP)) {
+ if (unlikely(disable_smep)) {
+ setup_clear_cpu_cap(X86_FEATURE_SMEP);
+ clear_in_cr4(X86_CR4_SMEP);
+ } else
+ set_in_cr4(X86_CR4_SMEP);
+ }
+}
+
/*
* Some CPU features depend on higher CPUID levels, which may not always
* be available due to CPUID level capping or broken virtualization
@@ -565,8 +584,7 @@ void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
- if (eax > 0)
- c->x86_capability[9] = ebx;
+ c->x86_capability[9] = ebx;
}
/* AMD-defined flags: level 0x80000001 */
@@ -668,6 +686,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
c->cpu_index = 0;
#endif
filter_cpuid_features(c, false);
+
+ setup_smep(c);
}
void __init early_cpu_init(void)
@@ -753,6 +773,8 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
#endif
}
+ setup_smep(c);
+
get_model_name(c); /* Default name */
detect_nopl(c);
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 cf48cdd6907..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 useful 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 useful 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 52c93648e49..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_once(KERN_WARNING PFX "Warning: EST-capable "
- "CPU detected. The acpi-cpufreq module offers "
- "voltage scaling in addition to 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 755a31e0f5b..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ /dev/null
@@ -1,624 +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 0;
-}
-
-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;
- 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 2368e38327b..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ /dev/null
@@ -1,1607 +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
- "fid 0x%x (%d MHz), vid 0x%x\n",
- 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 available 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;
- int rv;
-
- 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;
-
- msrs = msrs_alloc();
- if (!msrs) {
- printk(KERN_ERR "%s: Error allocating msrs!\n", __func__);
- return -ENOMEM;
- }
-
- register_cpu_notifier(&cpb_nb);
-
- 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"));
- }
-
- rv = cpufreq_register_driver(&cpufreq_amd64_driver);
- if (rv < 0 && boot_cpu_has(X86_FEATURE_CPB)) {
- unregister_cpu_notifier(&cpb_nb);
- msrs_free(msrs);
- msrs = NULL;
- }
- return rv;
-}
-
-/* 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 91bc25b67bc..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 acquiring 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-acquiring 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 df86bc8c859..1edf5ba4fb2 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -29,10 +29,10 @@
static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
{
+ u64 misc_enable;
+
/* Unmask CPUID levels if masked: */
if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
- u64 misc_enable;
-
rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
@@ -118,8 +118,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
* (model 2) with the same problem.
*/
if (c->x86 == 15) {
- u64 misc_enable;
-
rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
@@ -130,6 +128,19 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
}
}
#endif
+
+ /*
+ * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
+ * clear the fast string and enhanced fast string CPU capabilities.
+ */
+ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+ rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+ if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
+ printk(KERN_INFO "Disabled fast string operations\n");
+ setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
+ setup_clear_cpu_cap(X86_FEATURE_ERMS);
+ }
+ }
}
#ifdef CONFIG_X86_32
@@ -400,12 +411,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
switch (c->x86_model) {
case 5:
- if (c->x86_mask == 0) {
- if (l2 == 0)
- p = "Celeron (Covington)";
- else if (l2 == 256)
- p = "Mobile Pentium II (Dixon)";
- }
+ if (l2 == 0)
+ p = "Celeron (Covington)";
+ else if (l2 == 256)
+ p = "Mobile Pentium II (Dixon)";
break;
case 6:
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 1ce1af2899d..c105c533ed9 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -327,7 +327,6 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9));
l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
- l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
}
@@ -454,27 +453,16 @@ int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot,
{
int ret = 0;
-#define SUBCACHE_MASK (3UL << 20)
-#define SUBCACHE_INDEX 0xfff
-
- /*
- * check whether this slot is already used or
- * the index is already disabled
- */
+ /* check if @slot is already used or the index is already disabled */
ret = amd_get_l3_disable_slot(l3, slot);
if (ret >= 0)
return -EINVAL;
- /*
- * check whether the other slot has disabled the
- * same index already
- */
- if (index == amd_get_l3_disable_slot(l3, !slot))
+ if (index > l3->indices)
return -EINVAL;
- /* do not allow writes outside of allowed bits */
- if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
- ((index & SUBCACHE_INDEX) > l3->indices))
+ /* check whether the other slot has disabled the same index already */
+ if (index == amd_get_l3_disable_slot(l3, !slot))
return -EINVAL;
amd_l3_disable_index(l3, cpu, slot, index);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3385ea26f68..ff1ae9b6464 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -105,20 +105,6 @@ static int cpu_missing;
ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
-static int default_decode_mce(struct notifier_block *nb, unsigned long val,
- void *data)
-{
- pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
- pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
-
- return NOTIFY_STOP;
-}
-
-static struct notifier_block mce_dec_nb = {
- .notifier_call = default_decode_mce,
- .priority = -1,
-};
-
/* MCA banks polled by the period polling timer for corrected events */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -212,6 +198,8 @@ void mce_log(struct mce *mce)
static void print_mce(struct mce *m)
{
+ int ret = 0;
+
pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
m->extcpu, m->mcgstatus, m->bank, m->status);
@@ -239,7 +227,11 @@ static void print_mce(struct mce *m)
* Print out human-readable details about the MCE error,
* (if the CPU has an implementation for that)
*/
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+ ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+ if (ret == NOTIFY_STOP)
+ return;
+
+ pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -590,7 +582,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
mce_log(&m);
atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
- add_taint(TAINT_MACHINE_CHECK);
}
/*
@@ -1722,8 +1713,6 @@ __setup("mce", mcheck_enable);
int __init mcheck_init(void)
{
- atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
-
mcheck_intel_therm_init();
return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 167f97b5596..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;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9da97..27c625178bf 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -187,8 +187,6 @@ static int therm_throt_process(bool new_event, int event, int level)
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
-
- add_taint(TAINT_MACHINE_CHECK);
return 1;
}
if (old_event) {
@@ -355,7 +353,6 @@ static void notify_thresholds(__u64 msr_val)
static void intel_thermal_interrupt(void)
{
__u64 msr_val;
- struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
@@ -367,19 +364,19 @@ static void intel_thermal_interrupt(void)
CORE_LEVEL) != 0)
mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
- if (cpu_has(c, X86_FEATURE_PLN))
+ if (this_cpu_has(X86_FEATURE_PLN))
if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
POWER_LIMIT_EVENT,
CORE_LEVEL) != 0)
mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
- if (cpu_has(c, X86_FEATURE_PTS)) {
+ if (this_cpu_has(X86_FEATURE_PTS)) {
rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
THERMAL_THROTTLING_EVENT,
PACKAGE_LEVEL) != 0)
mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
- if (cpu_has(c, X86_FEATURE_PLN))
+ if (this_cpu_has(X86_FEATURE_PLN))
if (therm_throt_process(msr_val &
PACKAGE_THERM_STATUS_POWER_LIMIT,
POWER_LIMIT_EVENT,
@@ -393,7 +390,6 @@ static void unexpected_thermal_interrupt(void)
{
printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
smp_processor_id());
- add_taint(TAINT_MACHINE_CHECK);
}
static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
@@ -446,18 +442,20 @@ 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/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e638689279d..3a0338b4b17 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,6 +31,7 @@
#include <asm/nmi.h>
#include <asm/compat.h>
#include <asm/smp.h>
+#include <asm/alternative.h>
#if 0
#undef wrmsrl
@@ -363,12 +364,18 @@ 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;
+ int offset;
+
+ /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */
+ alternative_io(ASM_NOP2,
+ "shll $1, %%eax",
+ X86_FEATURE_PERFCTR_CORE,
+ "=a" (offset),
+ "a" (index));
+
+ return offset;
}
static inline unsigned int x86_pmu_config_addr(int index)
@@ -1766,17 +1773,6 @@ static struct pmu pmu = {
* callchain support
*/
-static void
-backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
- /* Ignore warnings */
-}
-
-static void backtrace_warning(void *data, char *msg)
-{
- /* Ignore warnings */
-}
-
static int backtrace_stack(void *data, char *name)
{
return 0;
@@ -1790,8 +1786,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
}
static const struct stacktrace_ops backtrace_ops = {
- .warning = backtrace_warning,
- .warning_symbol = backtrace_warning_symbol,
.stack = backtrace_stack,
.address = backtrace_address,
.walk_stack = print_context_stack_bp,
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index cf4e369cea6..fe29c1d2219 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -96,12 +96,14 @@ static __initconst const u64 amd_hw_cache_event_ids
*/
static const u64 amd_perfmon_event_map[] =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
};
static u64 amd_pmu_event_map(int hw_event)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e61539b07d2..41178c826c4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -36,7 +36,7 @@ static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
[PERF_COUNT_HW_BUS_CYCLES] = 0x013c,
};
-static struct event_constraint intel_core_event_constraints[] =
+static struct event_constraint intel_core_event_constraints[] __read_mostly =
{
INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
@@ -47,7 +47,7 @@ static struct event_constraint intel_core_event_constraints[] =
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_core2_event_constraints[] =
+static struct event_constraint intel_core2_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -70,7 +70,7 @@ static struct event_constraint intel_core2_event_constraints[] =
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_nehalem_event_constraints[] =
+static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -86,19 +86,19 @@ static struct event_constraint intel_nehalem_event_constraints[] =
EVENT_CONSTRAINT_END
};
-static struct extra_reg intel_nehalem_extra_regs[] =
+static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
{
INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
EVENT_EXTRA_END
};
-static struct event_constraint intel_nehalem_percore_constraints[] =
+static struct event_constraint intel_nehalem_percore_constraints[] __read_mostly =
{
INTEL_EVENT_CONSTRAINT(0xb7, 0),
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_westmere_event_constraints[] =
+static struct event_constraint intel_westmere_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -110,7 +110,7 @@ static struct event_constraint intel_westmere_event_constraints[] =
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_snb_event_constraints[] =
+static struct event_constraint intel_snb_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -123,21 +123,21 @@ static struct event_constraint intel_snb_event_constraints[] =
EVENT_CONSTRAINT_END
};
-static struct extra_reg intel_westmere_extra_regs[] =
+static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
{
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[] =
+static struct event_constraint intel_westmere_percore_constraints[] __read_mostly =
{
INTEL_EVENT_CONSTRAINT(0xb7, 0),
INTEL_EVENT_CONSTRAINT(0xbb, 0),
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_gen_event_constraints[] =
+static struct event_constraint intel_gen_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -184,26 +184,23 @@ static __initconst const u64 snb_hw_cache_event_ids
},
},
[ C(LL ) ] = {
- /*
- * TBD: Need Off-core Response Performance Monitoring support
- */
[ C(OP_READ) ] = {
- /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
- /* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -285,26 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* 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) ] = {
- /* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
- [ C(RESULT_ACCESS) ] = 0x01bb,
- /* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_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) ] = {
- /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -352,16 +349,36 @@ static __initconst const u64 westmere_hw_cache_event_ids
};
/*
- * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
*/
-#define DMND_DATA_RD (1 << 0)
-#define DMND_RFO (1 << 1)
-#define DMND_WB (1 << 3)
-#define PF_DATA_RD (1 << 4)
-#define PF_DATA_RFO (1 << 5)
-#define RESP_UNCORE_HIT (1 << 8)
-#define RESP_MISS (0xf600) /* non uncore hit */
+#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]
@@ -370,16 +387,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = DMND_DATA_RD|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_L3_MISS,
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = DMND_RFO|DMND_WB|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_L3_MISS,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
},
}
};
@@ -1423,6 +1440,11 @@ static __init int intel_pmu_init(void)
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
+ /* UOPS_ISSUED.STALLED_CYCLES */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+ /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+
if (ebx & 0x40) {
/*
* Erratum AAJ80 detected, we work it around by using
@@ -1463,6 +1485,12 @@ static __init int intel_pmu_init(void)
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;
+
+ /* UOPS_ISSUED.STALLED_CYCLES */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+ /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+
pr_cont("Westmere events, ");
break;
@@ -1474,6 +1502,12 @@ static __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_events;
+
+ /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+ /* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1;
+
pr_cont("SandyBridge events, ");
break;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index e93fcd55fae..ead584fb6a7 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -468,7 +468,7 @@ static struct p4_event_bind p4_event_bind_map[] = {
.opcode = P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
.escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
.escr_emask =
- P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
+ P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
.cntr = { {12, 13, 16}, {14, 15, 17} },
},
[P4_EVENT_X87_ASSIST] = {
@@ -912,8 +912,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
int idx, handled = 0;
u64 val;
- data.addr = 0;
- data.raw = NULL;
+ perf_sample_data_init(&data, 0);
cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1197,7 +1196,7 @@ static __init int p4_pmu_init(void)
{
unsigned int low, high;
- /* If we get stripped -- indexig fails */
+ /* If we get stripped -- indexing fails */
BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC);
rdmsr(MSR_IA32_MISC_ENABLE, low, high);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index e2a3f0606da..1aae78f775f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -135,20 +135,6 @@ print_context_stack_bp(struct thread_info *tinfo,
}
EXPORT_SYMBOL_GPL(print_context_stack_bp);
-
-static void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
- printk(data);
- print_symbol(msg, symbol);
- printk("\n");
-}
-
-static void print_trace_warning(void *data, char *msg)
-{
- printk("%s%s\n", (char *)data, msg);
-}
-
static int print_trace_stack(void *data, char *name)
{
printk("%s <%s> ", (char *)data, name);
@@ -166,8 +152,6 @@ static void print_trace_address(void *data, unsigned long addr, int reliable)
}
static const struct stacktrace_ops print_trace_ops = {
- .warning = print_trace_warning,
- .warning_symbol = print_trace_warning_symbol,
.stack = print_trace_stack,
.address = print_trace_address,
.walk_stack = print_context_stack,
@@ -279,7 +263,6 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
printk("DEBUG_PAGEALLOC");
#endif
printk("\n");
- sysfs_printk_last_file();
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
return 1;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index a93742a5746..0ba15a6cc57 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -260,9 +260,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
return mod_code_status;
}
-static unsigned char *ftrace_nop_replace(void)
+static const unsigned char *ftrace_nop_replace(void)
{
- return ideal_nop5;
+ return ideal_nops[NOP_ATOMIC5];
}
static int
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index d6d6bb36193..3bb08509a7a 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -23,7 +23,6 @@
static void __init i386_default_early_setup(void)
{
/* Initialize 32bit specific setup functions */
- x86_init.resources.probe_roms = probe_roms;
x86_init.resources.reserve_resources = i386_reserve_resources;
x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index bfe8f729e08..6781765b3a0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -217,7 +217,7 @@ static void hpet_reserve_platform_timers(unsigned int id) { }
/*
* Common hpet info
*/
-static unsigned long hpet_period;
+static unsigned long hpet_freq;
static void hpet_legacy_set_mode(enum clock_event_mode mode,
struct clock_event_device *evt);
@@ -232,7 +232,6 @@ static struct clock_event_device hpet_clockevent = {
.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
.set_mode = hpet_legacy_set_mode,
.set_next_event = hpet_legacy_next_event,
- .shift = 32,
.irq = 0,
.rating = 50,
};
@@ -290,28 +289,12 @@ static void hpet_legacy_clockevent_register(void)
hpet_enable_legacy_int();
/*
- * The mult factor is defined as (include/linux/clockchips.h)
- * mult/2^shift = cyc/ns (in contrast to ns/cyc in clocksource.h)
- * hpet_period is in units of femtoseconds (per cycle), so
- * mult/2^shift = cyc/ns = 10^6/hpet_period
- * mult = (10^6 * 2^shift)/hpet_period
- * mult = (FSEC_PER_NSEC << hpet_clockevent.shift)/hpet_period
- */
- hpet_clockevent.mult = div_sc((unsigned long) FSEC_PER_NSEC,
- hpet_period, hpet_clockevent.shift);
- /* Calculate the min / max delta */
- hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
- &hpet_clockevent);
- /* Setup minimum reprogramming delta. */
- hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA,
- &hpet_clockevent);
-
- /*
* Start hpet with the boot cpu mask and make it
* global after the IO_APIC has been initialized.
*/
hpet_clockevent.cpumask = cpumask_of(smp_processor_id());
- clockevents_register_device(&hpet_clockevent);
+ clockevents_config_and_register(&hpet_clockevent, hpet_freq,
+ HPET_MIN_PROG_DELTA, 0x7FFFFFFF);
global_clock_event = &hpet_clockevent;
printk(KERN_DEBUG "hpet clockevent registered\n");
}
@@ -549,7 +532,6 @@ static int hpet_setup_irq(struct hpet_dev *dev)
static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
{
struct clock_event_device *evt = &hdev->evt;
- uint64_t hpet_freq;
WARN_ON(cpu != smp_processor_id());
if (!(hdev->flags & HPET_DEV_VALID))
@@ -571,24 +553,10 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
evt->set_mode = hpet_msi_set_mode;
evt->set_next_event = hpet_msi_next_event;
- evt->shift = 32;
-
- /*
- * The period is a femto seconds value. We need to calculate the
- * scaled math multiplication factor for nanosecond to hpet tick
- * conversion.
- */
- hpet_freq = FSEC_PER_SEC;
- do_div(hpet_freq, hpet_period);
- evt->mult = div_sc((unsigned long) hpet_freq,
- NSEC_PER_SEC, evt->shift);
- /* Calculate the max delta */
- evt->max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, evt);
- /* 5 usec minimum reprogramming delta. */
- evt->min_delta_ns = 5000;
-
evt->cpumask = cpumask_of(hdev->cpu);
- clockevents_register_device(evt);
+
+ clockevents_config_and_register(evt, hpet_freq, HPET_MIN_PROG_DELTA,
+ 0x7FFFFFFF);
}
#ifdef CONFIG_HPET
@@ -792,7 +760,6 @@ static struct clocksource clocksource_hpet = {
static int hpet_clocksource_register(void)
{
u64 start, now;
- u64 hpet_freq;
cycle_t t1;
/* Start the counter */
@@ -819,24 +786,7 @@ static int hpet_clocksource_register(void)
return -ENODEV;
}
- /*
- * The definition of mult is (include/linux/clocksource.h)
- * mult/2^shift = ns/cyc and hpet_period is in units of fsec/cyc
- * so we first need to convert hpet_period to ns/cyc units:
- * mult/2^shift = ns/cyc = hpet_period/10^6
- * mult = (hpet_period * 2^shift)/10^6
- * mult = (hpet_period << shift)/FSEC_PER_NSEC
- */
-
- /* Need to convert hpet_period (fsec/cyc) to cyc/sec:
- *
- * cyc/sec = FSEC_PER_SEC/hpet_period(fsec/cyc)
- * cyc/sec = (FSEC_PER_NSEC * NSEC_PER_SEC)/hpet_period
- */
- hpet_freq = FSEC_PER_SEC;
- do_div(hpet_freq, hpet_period);
clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
-
return 0;
}
@@ -845,7 +795,9 @@ static int hpet_clocksource_register(void)
*/
int __init hpet_enable(void)
{
+ unsigned long hpet_period;
unsigned int id;
+ u64 freq;
int i;
if (!is_hpet_capable())
@@ -884,6 +836,14 @@ int __init hpet_enable(void)
goto out_nohpet;
/*
+ * The period is a femto seconds value. Convert it to a
+ * frequency.
+ */
+ freq = FSEC_PER_SEC;
+ do_div(freq, hpet_period);
+ hpet_freq = freq;
+
+ /*
* Read the HPET ID register to retrieve the IRQ routing
* information and the number of channels
*/
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 2dfd3159744..fb66dc9e36c 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -93,7 +93,6 @@ static struct clock_event_device pit_ce = {
.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
.set_mode = init_pit_timer,
.set_next_event = pit_next_event,
- .shift = 32,
.irq = 0,
};
@@ -108,90 +107,12 @@ void __init setup_pit_timer(void)
* IO_APIC has been initialized.
*/
pit_ce.cpumask = cpumask_of(smp_processor_id());
- pit_ce.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, pit_ce.shift);
- pit_ce.max_delta_ns = clockevent_delta2ns(0x7FFF, &pit_ce);
- pit_ce.min_delta_ns = clockevent_delta2ns(0xF, &pit_ce);
- clockevents_register_device(&pit_ce);
+ clockevents_config_and_register(&pit_ce, CLOCK_TICK_RATE, 0xF, 0x7FFF);
global_clock_event = &pit_ce;
}
#ifndef CONFIG_X86_64
-/*
- * Since the PIT overflows every tick, its not very useful
- * to just read by itself. So use jiffies to emulate a free
- * running counter:
- */
-static cycle_t pit_read(struct clocksource *cs)
-{
- static int old_count;
- static u32 old_jifs;
- unsigned long flags;
- int count;
- u32 jifs;
-
- raw_spin_lock_irqsave(&i8253_lock, flags);
- /*
- * Although our caller may have the read side of xtime_lock,
- * this is now a seqlock, and we are cheating in this routine
- * by having side effects on state that we cannot undo if
- * there is a collision on the seqlock and our caller has to
- * retry. (Namely, old_jifs and old_count.) So we must treat
- * jiffies as volatile despite the lock. We read jiffies
- * before latching the timer count to guarantee that although
- * the jiffies value might be older than the count (that is,
- * the counter may underflow between the last point where
- * jiffies was incremented and the point where we latch the
- * count), it cannot be newer.
- */
- jifs = jiffies;
- outb_pit(0x00, PIT_MODE); /* latch the count ASAP */
- count = inb_pit(PIT_CH0); /* read the latched count */
- count |= inb_pit(PIT_CH0) << 8;
-
- /* VIA686a test code... reset the latch if count > max + 1 */
- if (count > LATCH) {
- outb_pit(0x34, PIT_MODE);
- outb_pit(LATCH & 0xff, PIT_CH0);
- outb_pit(LATCH >> 8, PIT_CH0);
- count = LATCH - 1;
- }
-
- /*
- * It's possible for count to appear to go the wrong way for a
- * couple of reasons:
- *
- * 1. The timer counter underflows, but we haven't handled the
- * resulting interrupt and incremented jiffies yet.
- * 2. Hardware problem with the timer, not giving us continuous time,
- * the counter does small "jumps" upwards on some Pentium systems,
- * (see c't 95/10 page 335 for Neptun bug.)
- *
- * Previous attempts to handle these cases intelligently were
- * buggy, so we just do the simple thing now.
- */
- if (count > old_count && jifs == old_jifs)
- count = old_count;
-
- old_count = count;
- old_jifs = jifs;
-
- raw_spin_unlock_irqrestore(&i8253_lock, flags);
-
- count = (LATCH - 1) - count;
-
- return (cycle_t)(jifs * LATCH) + count;
-}
-
-static struct clocksource pit_cs = {
- .name = "pit",
- .rating = 110,
- .read = pit_read,
- .mask = CLOCKSOURCE_MASK(32),
- .mult = 0,
- .shift = 20,
-};
-
static int __init init_pit_clocksource(void)
{
/*
@@ -205,10 +126,7 @@ static int __init init_pit_clocksource(void)
pit_ce.mode != CLOCK_EVT_MODE_PERIODIC)
return 0;
- pit_cs.mult = clocksource_hz2mult(CLOCK_TICK_RATE, pit_cs.shift);
-
- return clocksource_register(&pit_cs);
+ return clocksource_i8253_init();
}
arch_initcall(init_pit_clocksource);
-
#endif /* !CONFIG_X86_64 */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 1cb0b9fc78d..6c0802eb2f7 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -249,7 +249,7 @@ void fixup_irqs(void)
data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
- if (!irq_has_action(irq) ||
+ if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
@@ -276,7 +276,8 @@ void fixup_irqs(void)
else if (!(warned++))
set_affinity = 0;
- if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
+ if (!irqd_can_move_in_process_context(data) &&
+ !irqd_irq_disabled(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 961b6b30ba9..3fee346ef54 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -34,7 +34,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
code.offset = entry->target -
(entry->code + JUMP_LABEL_NOP_SIZE);
} else
- memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+ memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
get_online_cpus();
mutex_lock(&text_mutex);
text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
@@ -44,7 +44,8 @@ void arch_jump_label_transform(struct jump_entry *entry,
void arch_jump_label_text_poke_early(jump_label_t addr)
{
- text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+ text_poke_early((void *)addr, ideal_nops[NOP_ATOMIC5],
+ JUMP_LABEL_NOP_SIZE);
}
#endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index c969fd9d156..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)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index f98d3eafe07..6389a6bca11 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -26,8 +26,6 @@
#include <asm/x86_init.h>
#include <asm/reboot.h>
-#define KVM_SCALE 22
-
static int kvmclock = 1;
static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
@@ -120,8 +118,6 @@ static struct clocksource kvm_clock = {
.read = kvm_clock_get_cycles,
.rating = 400,
.mask = CLOCKSOURCE_MASK(64),
- .mult = 1 << KVM_SCALE,
- .shift = KVM_SCALE,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
@@ -203,7 +199,7 @@ void __init kvmclock_init(void)
machine_ops.crash_shutdown = kvm_crash_shutdown;
#endif
kvm_get_preset_lpj();
- clocksource_register(&kvm_clock);
+ clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
pv_info.paravirt_enabled = 1;
pv_info.name = "KVM";
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index ab23f1ad4bf..52f256f2cc8 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -24,6 +24,7 @@
#include <linux/bug.h>
#include <linux/mm.h>
#include <linux/gfp.h>
+#include <linux/jump_label.h>
#include <asm/system.h>
#include <asm/page.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 5a532ce646b..6f9bfffb272 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -715,17 +715,15 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
}
}
-static int
+static int __init
check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
{
- int ret = 0;
-
if (!mpc_new_phys || count <= mpc_new_length) {
WARN(1, "update_mptable: No spare slots (length: %x)\n", count);
return -1;
}
- return ret;
+ return 0;
}
#else /* CONFIG_X86_IO_APIC */
static
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 55d745ec118..35ccf75696e 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -50,20 +50,14 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
struct iommu_table_entry *finish)
{
struct iommu_table_entry *p, *q, *x;
- char sym_p[KSYM_SYMBOL_LEN];
- char sym_q[KSYM_SYMBOL_LEN];
/* Simple cyclic dependency checker. */
for (p = start; p < finish; p++) {
q = find_dependents_of(start, finish, p);
x = find_dependents_of(start, finish, q);
if (p == x) {
- sprint_symbol(sym_p, (unsigned long)p->detect);
- sprint_symbol(sym_q, (unsigned long)q->detect);
-
- printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %s depends" \
- " on %s and vice-versa. BREAKING IT.\n",
- sym_p, sym_q);
+ printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
+ p->detect, q->detect);
/* Heavy handed way..*/
x->depend = 0;
}
@@ -72,12 +66,8 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
for (p = start; p < finish; p++) {
q = find_dependents_of(p, finish, p);
if (q && q > p) {
- sprint_symbol(sym_p, (unsigned long)p->detect);
- sprint_symbol(sym_q, (unsigned long)q->detect);
-
- printk(KERN_ERR "EXECUTION ORDER INVALID! %s "\
- "should be called before %s!\n",
- sym_p, sym_q);
+ printk(KERN_ERR "EXECUTION ORDER INVALID! %pS should be called before %pS!\n",
+ p->detect, q->detect);
}
}
}
diff --git a/arch/x86/kernel/probe_roms_32.c b/arch/x86/kernel/probe_roms.c
index 071e7fea42e..ba0a4cce53b 100644
--- a/arch/x86/kernel/probe_roms_32.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -73,6 +73,107 @@ static struct resource video_rom_resource = {
.flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
};
+/* does this oprom support the given pci device, or any of the devices
+ * that the driver supports?
+ */
+static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short device)
+{
+ struct pci_driver *drv = pdev->driver;
+ const struct pci_device_id *id;
+
+ if (pdev->vendor == vendor && pdev->device == device)
+ return true;
+
+ for (id = drv ? drv->id_table : NULL; id && id->vendor; id++)
+ if (id->vendor == vendor && id->device == device)
+ break;
+
+ return id && id->vendor;
+}
+
+static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
+ const unsigned char *rom_list)
+{
+ unsigned short device;
+
+ do {
+ if (probe_kernel_address(rom_list, device) != 0)
+ device = 0;
+
+ if (device && match_id(pdev, vendor, device))
+ break;
+
+ rom_list += 2;
+ } while (device);
+
+ return !!device;
+}
+
+static struct resource *find_oprom(struct pci_dev *pdev)
+{
+ struct resource *oprom = NULL;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) {
+ struct resource *res = &adapter_rom_resources[i];
+ unsigned short offset, vendor, device, list, rev;
+ const unsigned char *rom;
+
+ if (res->end == 0)
+ break;
+
+ rom = isa_bus_to_virt(res->start);
+ if (probe_kernel_address(rom + 0x18, offset) != 0)
+ continue;
+
+ if (probe_kernel_address(rom + offset + 0x4, vendor) != 0)
+ continue;
+
+ if (probe_kernel_address(rom + offset + 0x6, device) != 0)
+ continue;
+
+ if (match_id(pdev, vendor, device)) {
+ oprom = res;
+ break;
+ }
+
+ if (probe_kernel_address(rom + offset + 0x8, list) == 0 &&
+ probe_kernel_address(rom + offset + 0xc, rev) == 0 &&
+ rev >= 3 && list &&
+ probe_list(pdev, vendor, rom + offset + list)) {
+ oprom = res;
+ break;
+ }
+ }
+
+ return oprom;
+}
+
+void *pci_map_biosrom(struct pci_dev *pdev)
+{
+ struct resource *oprom = find_oprom(pdev);
+
+ if (!oprom)
+ return NULL;
+
+ return ioremap(oprom->start, resource_size(oprom));
+}
+EXPORT_SYMBOL(pci_map_biosrom);
+
+void pci_unmap_biosrom(void __iomem *image)
+{
+ iounmap(image);
+}
+EXPORT_SYMBOL(pci_unmap_biosrom);
+
+size_t pci_biosrom_size(struct pci_dev *pdev)
+{
+ struct resource *oprom = find_oprom(pdev);
+
+ return oprom ? resource_size(oprom) : 0;
+}
+EXPORT_SYMBOL(pci_biosrom_size);
+
#define ROMSIGNATURE 0xaa55
static int __init romsignature(const unsigned char *rom)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d46cbe46b7a..88a90a977f8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -449,7 +449,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
{
if (!need_resched()) {
- if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
+ if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)&current_thread_info()->flags);
__monitor((void *)&current_thread_info()->flags, 0, 0);
@@ -465,7 +465,7 @@ static void mwait_idle(void)
if (!need_resched()) {
trace_power_start(POWER_CSTATE, 1, smp_processor_id());
trace_cpu_idle(1, smp_processor_id());
- if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
+ if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)&current_thread_info()->flags);
__monitor((void *)&current_thread_info()->flags, 0, 0);
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 08c44b08bf5..0c016f72769 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL(pm_power_off);
static const struct desc_ptr no_idt = {};
static int reboot_mode;
-enum reboot_type reboot_type = BOOT_KBD;
+enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;
#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
@@ -478,9 +478,24 @@ void __attribute__((weak)) mach_reboot_fixups(void)
{
}
+/*
+ * Windows compatible x86 hardware expects the following on reboot:
+ *
+ * 1) If the FADT has the ACPI reboot register flag set, try it
+ * 2) If still alive, write to the keyboard controller
+ * 3) If still alive, write to the ACPI reboot register again
+ * 4) If still alive, write to the keyboard controller again
+ *
+ * If the machine is still alive at this stage, it gives up. We default to
+ * following the same pattern, except that if we're still alive after (4) we'll
+ * try to force a triple fault and then cycle between hitting the keyboard
+ * controller and doing that
+ */
static void native_machine_emergency_restart(void)
{
int i;
+ int attempt = 0;
+ int orig_reboot_type = reboot_type;
if (reboot_emergency)
emergency_vmx_disable_all();
@@ -502,6 +517,13 @@ static void native_machine_emergency_restart(void)
outb(0xfe, 0x64); /* pulse reset low */
udelay(50);
}
+ if (attempt == 0 && orig_reboot_type == BOOT_ACPI) {
+ attempt = 1;
+ reboot_type = BOOT_ACPI;
+ } else {
+ reboot_type = BOOT_TRIPLE;
+ }
+ break;
case BOOT_TRIPLE:
load_idt(&no_idt);
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S
index 29092b38d81..1d5c46df0d7 100644
--- a/arch/x86/kernel/reboot_32.S
+++ b/arch/x86/kernel/reboot_32.S
@@ -21,26 +21,26 @@ r_base = .
/* Get our own relocated address */
call 1f
1: popl %ebx
- subl $1b, %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(%ebx,%eax,2),%ax
- movw %ax, 101f(%ebx)
- movw %cx, 102f(%ebx)
+ 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(%ebx)
+ 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(%ebx)
+ lgdtl (machine_real_restart_gdt - r_base)(%ebx)
/*
* Load the data segment registers with 16-bit compatible values
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4be9b398470..c3050af9306 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -691,8 +691,6 @@ early_param("reservelow", parse_reservelow);
void __init setup_arch(char **cmdline_p)
{
- unsigned long flags;
-
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
@@ -1041,9 +1039,7 @@ void __init setup_arch(char **cmdline_p)
mcheck_init();
- local_irq_save(flags);
- arch_init_ideal_nop5();
- local_irq_restore(flags);
+ arch_init_ideal_nops();
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 513deac7228..013e7eba83b 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait)
}
/*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
*/
void smp_reschedule_interrupt(struct pt_regs *regs)
{
ack_APIC_irq();
inc_irq_stat(irq_resched_count);
+ scheduler_ipi();
/*
* KVM uses this interrupt to force a cpu out of guest mode
*/
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2871d3c71b..a3c430bdfb6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1332,9 +1332,9 @@ static inline void mwait_play_dead(void)
void *mwait_ptr;
struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
- if (!(cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)))
+ if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
return;
- if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLSH))
+ if (!this_cpu_has(X86_FEATURE_CLFLSH))
return;
if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
return;
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6515733a289..55d9bc03f69 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -9,15 +9,6 @@
#include <linux/uaccess.h>
#include <asm/stacktrace.h>
-static void save_stack_warning(void *data, char *msg)
-{
-}
-
-static void
-save_stack_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-}
-
static int save_stack_stack(void *data, char *name)
{
return 0;
@@ -53,16 +44,12 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable)
}
static const struct stacktrace_ops save_stack_ops = {
- .warning = save_stack_warning,
- .warning_symbol = save_stack_warning_symbol,
.stack = save_stack_stack,
.address = save_stack_address,
.walk_stack = print_context_stack,
};
static const struct stacktrace_ops save_stack_ops_nosched = {
- .warning = save_stack_warning,
- .warning_symbol = save_stack_warning_symbol,
.stack = save_stack_stack,
.address = save_stack_address_nosched,
.walk_stack = print_context_stack,
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index c11514e9128..6f164bd5e14 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -35,7 +35,7 @@ void iommu_shutdown_noop(void) { }
struct x86_init_ops x86_init __initdata = {
.resources = {
- .probe_roms = x86_init_noop,
+ .probe_roms = probe_roms,
.reserve_resources = reserve_standard_io_resources,
.memory_setup = default_machine_specific_memory_setup,
},
@@ -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,
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 1cd608973ce..e191c096ab9 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -7,7 +7,7 @@
* kernel and insert a module (lg.ko) which allows us to run other Linux
* kernels the same way we'd run processes. We call the first kernel the Host,
* and the others the Guests. The program which sets up and configures Guests
- * (such as the example in Documentation/lguest/lguest.c) is called the
+ * (such as the example in Documentation/virtual/lguest/lguest.c) is called the
* Launcher.
*
* Secondly, we only run specially modified Guests, not normal kernels: setting
@@ -913,8 +913,6 @@ static struct clocksource lguest_clock = {
.rating = 200,
.read = lguest_clock_read,
.mask = CLOCKSOURCE_MASK(64),
- .mult = 1 << 22,
- .shift = 22,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
@@ -997,7 +995,7 @@ static void lguest_time_init(void)
/* Set up the timer interrupt (0) to go to our simple timer routine */
irq_set_handler(0, lguest_time_irq);
- clocksource_register(&lguest_clock);
+ clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);
/* We can't set cpumask in the initializer: damn C limitations! Set it
* here and register our timer device. */
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index aa4326bfb24..f2145cfa12a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,6 @@
#include <linux/linkage.h>
#include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
/*
* Zero a page.
@@ -14,6 +15,15 @@ ENTRY(clear_page_c)
CFI_ENDPROC
ENDPROC(clear_page_c)
+ENTRY(clear_page_c_e)
+ CFI_STARTPROC
+ movl $4096,%ecx
+ xorl %eax,%eax
+ rep stosb
+ ret
+ CFI_ENDPROC
+ENDPROC(clear_page_c_e)
+
ENTRY(clear_page)
CFI_STARTPROC
xorl %eax,%eax
@@ -38,21 +48,26 @@ ENTRY(clear_page)
.Lclear_page_end:
ENDPROC(clear_page)
- /* Some CPUs run faster using the string instructions.
- It is also a lot simpler. Use this when possible */
+ /*
+ * Some CPUs support enhanced REP MOVSB/STOSB instructions.
+ * It is recommended to use this when possible.
+ * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
+ * Otherwise, use original function.
+ *
+ */
#include <asm/cpufeature.h>
.section .altinstr_replacement,"ax"
1: .byte 0xeb /* jmp <disp8> */
.byte (clear_page_c - clear_page) - (2f - 1b) /* offset */
-2:
+2: .byte 0xeb /* jmp <disp8> */
+ .byte (clear_page_c_e - clear_page) - (3f - 2b) /* offset */
+3:
.previous
.section .altinstructions,"a"
- .align 8
- .quad clear_page
- .quad 1b
- .word X86_FEATURE_REP_GOOD
- .byte .Lclear_page_end - clear_page
- .byte 2b - 1b
+ altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\
+ .Lclear_page_end-clear_page, 2b-1b
+ altinstruction_entry clear_page,2b,X86_FEATURE_ERMS, \
+ .Lclear_page_end-clear_page,3b-2b
.previous
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 99e48261519..024840266ba 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -15,23 +15,30 @@
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
- .macro ALTERNATIVE_JUMP feature,orig,alt
+/*
+ * By placing feature2 after feature1 in altinstructions section, we logically
+ * implement:
+ * If CPU has feature2, jmp to alt2 is used
+ * else if CPU has feature1, jmp to alt1 is used
+ * else jmp to orig is used.
+ */
+ .macro ALTERNATIVE_JUMP feature1,feature2,orig,alt1,alt2
0:
.byte 0xe9 /* 32bit jump */
.long \orig-1f /* by default jump to orig */
1:
.section .altinstr_replacement,"ax"
2: .byte 0xe9 /* near jump with 32bit immediate */
- .long \alt-1b /* offset */ /* or alternatively to alt */
+ .long \alt1-1b /* offset */ /* or alternatively to alt1 */
+3: .byte 0xe9 /* near jump with 32bit immediate */
+ .long \alt2-1b /* offset */ /* or alternatively to alt2 */
.previous
+
.section .altinstructions,"a"
- .align 8
- .quad 0b
- .quad 2b
- .word \feature /* when feature is set */
- .byte 5
- .byte 5
+ altinstruction_entry 0b,2b,\feature1,5,5
+ altinstruction_entry 0b,3b,\feature2,5,5
.previous
.endm
@@ -72,8 +79,10 @@ ENTRY(_copy_to_user)
addq %rdx,%rcx
jc bad_to_user
cmpq TI_addr_limit(%rax),%rcx
- jae bad_to_user
- ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
+ ja bad_to_user
+ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS, \
+ copy_user_generic_unrolled,copy_user_generic_string, \
+ copy_user_enhanced_fast_string
CFI_ENDPROC
ENDPROC(_copy_to_user)
@@ -85,8 +94,10 @@ ENTRY(_copy_from_user)
addq %rdx,%rcx
jc bad_from_user
cmpq TI_addr_limit(%rax),%rcx
- jae bad_from_user
- ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
+ ja bad_from_user
+ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS, \
+ copy_user_generic_unrolled,copy_user_generic_string, \
+ copy_user_enhanced_fast_string
CFI_ENDPROC
ENDPROC(_copy_from_user)
@@ -255,3 +266,37 @@ ENTRY(copy_user_generic_string)
.previous
CFI_ENDPROC
ENDPROC(copy_user_generic_string)
+
+/*
+ * Some CPUs are adding enhanced REP MOVSB/STOSB instructions.
+ * It's recommended to use enhanced REP MOVSB/STOSB if it's enabled.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ENTRY(copy_user_enhanced_fast_string)
+ CFI_STARTPROC
+ andl %edx,%edx
+ jz 2f
+ movl %edx,%ecx
+1: rep
+ movsb
+2: xorl %eax,%eax
+ ret
+
+ .section .fixup,"ax"
+12: movl %ecx,%edx /* ecx is zerorest also */
+ jmp copy_user_handle_tail
+ .previous
+
+ .section __ex_table,"a"
+ .align 8
+ .quad 1b,12b
+ .previous
+ CFI_ENDPROC
+ENDPROC(copy_user_enhanced_fast_string)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 75ef61e35e3..efbf2a0ecde 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,6 +4,7 @@
#include <asm/cpufeature.h>
#include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
/*
* memcpy - Copy a memory block.
@@ -37,6 +38,23 @@
.Lmemcpy_e:
.previous
+/*
+ * memcpy_c_e() - enhanced fast string memcpy. This is faster and simpler than
+ * memcpy_c. Use memcpy_c_e when possible.
+ *
+ * This gets patched over the unrolled variant (below) via the
+ * alternative instructions framework:
+ */
+ .section .altinstr_replacement, "ax", @progbits
+.Lmemcpy_c_e:
+ movq %rdi, %rax
+
+ movl %edx, %ecx
+ rep movsb
+ ret
+.Lmemcpy_e_e:
+ .previous
+
ENTRY(__memcpy)
ENTRY(memcpy)
CFI_STARTPROC
@@ -49,7 +67,7 @@ ENTRY(memcpy)
jb .Lhandle_tail
/*
- * We check whether memory false dependece could occur,
+ * We check whether memory false dependence could occur,
* then jump to corresponding copy mode.
*/
cmp %dil, %sil
@@ -171,21 +189,22 @@ ENDPROC(memcpy)
ENDPROC(__memcpy)
/*
- * Some CPUs run faster using the string copy instructions.
- * It is also a lot simpler. Use this when possible:
- */
-
- .section .altinstructions, "a"
- .align 8
- .quad memcpy
- .quad .Lmemcpy_c
- .word X86_FEATURE_REP_GOOD
-
- /*
+ * Some CPUs are adding enhanced REP MOVSB/STOSB feature
+ * If the feature is supported, memcpy_c_e() is the first choice.
+ * If enhanced rep movsb copy is not available, use fast string copy
+ * memcpy_c() when possible. This is faster and code is simpler than
+ * original memcpy().
+ * Otherwise, original memcpy() is used.
+ * In .altinstructions section, ERMS feature is placed after REG_GOOD
+ * feature to implement the right patch order.
+ *
* Replace only beginning, memcpy is used to apply alternatives,
* so it is silly to overwrite itself with nops - reboot is the
* only outcome...
*/
- .byte .Lmemcpy_e - .Lmemcpy_c
- .byte .Lmemcpy_e - .Lmemcpy_c
+ .section .altinstructions, "a"
+ altinstruction_entry memcpy,.Lmemcpy_c,X86_FEATURE_REP_GOOD,\
+ .Lmemcpy_e-.Lmemcpy_c,.Lmemcpy_e-.Lmemcpy_c
+ altinstruction_entry memcpy,.Lmemcpy_c_e,X86_FEATURE_ERMS, \
+ .Lmemcpy_e_e-.Lmemcpy_c_e,.Lmemcpy_e_e-.Lmemcpy_c_e
.previous
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0ecb8433e5a..d0ec9c2936d 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
#define _STRING_C
#include <linux/linkage.h>
#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
#undef memmove
@@ -24,6 +25,7 @@
*/
ENTRY(memmove)
CFI_STARTPROC
+
/* Handle more 32bytes in loop */
mov %rdi, %rax
cmp $0x20, %rdx
@@ -31,8 +33,13 @@ ENTRY(memmove)
/* Decide forward/backward copy mode */
cmp %rdi, %rsi
- jb 2f
+ jge .Lmemmove_begin_forward
+ mov %rsi, %r8
+ add %rdx, %r8
+ cmp %rdi, %r8
+ jg 2f
+.Lmemmove_begin_forward:
/*
* movsq instruction have many startup latency
* so we handle small size by general register.
@@ -78,6 +85,8 @@ ENTRY(memmove)
rep movsq
movq %r11, (%r10)
jmp 13f
+.Lmemmove_end_forward:
+
/*
* Handle data backward by movsq.
*/
@@ -194,4 +203,22 @@ ENTRY(memmove)
13:
retq
CFI_ENDPROC
+
+ .section .altinstr_replacement,"ax"
+.Lmemmove_begin_forward_efs:
+ /* Forward moving data. */
+ movq %rdx, %rcx
+ rep movsb
+ retq
+.Lmemmove_end_forward_efs:
+ .previous
+
+ .section .altinstructions,"a"
+ .align 8
+ .quad .Lmemmove_begin_forward
+ .quad .Lmemmove_begin_forward_efs
+ .word X86_FEATURE_ERMS
+ .byte .Lmemmove_end_forward-.Lmemmove_begin_forward
+ .byte .Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs
+ .previous
ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 09d34426965..79bd454b78a 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -2,9 +2,13 @@
#include <linux/linkage.h>
#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
/*
- * ISO C memset - set a memory block to a byte value.
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the orignal function as well.
*
* rdi destination
* rsi value (char)
@@ -31,6 +35,28 @@
.Lmemset_e:
.previous
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses
+ * enhanced rep stosb to override the fast string function.
+ * The code is simpler and shorter than the fast string function as well.
+ *
+ * rdi destination
+ * rsi value (char)
+ * rdx count (bytes)
+ *
+ * rax original destination
+ */
+ .section .altinstr_replacement, "ax", @progbits
+.Lmemset_c_e:
+ movq %rdi,%r9
+ movb %sil,%al
+ movl %edx,%ecx
+ rep stosb
+ movq %r9,%rax
+ ret
+.Lmemset_e_e:
+ .previous
+
ENTRY(memset)
ENTRY(__memset)
CFI_STARTPROC
@@ -112,16 +138,20 @@ ENTRY(__memset)
ENDPROC(memset)
ENDPROC(__memset)
- /* Some CPUs run faster using the string instructions.
- It is also a lot simpler. Use this when possible */
-
-#include <asm/cpufeature.h>
-
+ /* Some CPUs support enhanced REP MOVSB/STOSB feature.
+ * It is recommended to use this when possible.
+ *
+ * If enhanced REP MOVSB/STOSB feature is not available, use fast string
+ * instructions.
+ *
+ * Otherwise, use original memset function.
+ *
+ * In .altinstructions section, ERMS feature is placed after REG_GOOD
+ * feature to implement the right patch order.
+ */
.section .altinstructions,"a"
- .align 8
- .quad memset
- .quad .Lmemset_c
- .word X86_FEATURE_REP_GOOD
- .byte .Lfinal - memset
- .byte .Lmemset_e - .Lmemset_c
+ altinstruction_entry memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\
+ .Lfinal-memset,.Lmemset_e-.Lmemset_c
+ altinstruction_entry memset,.Lmemset_c_e,X86_FEATURE_ERMS, \
+ .Lfinal-memset,.Lmemset_e_e-.Lmemset_c_e
.previous
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 3e608edf995..3d11327c9ab 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -23,8 +23,8 @@ mmiotrace-y := kmmio.o pf_in.o mmio-mod.o
obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o
obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o
-obj-$(CONFIG_AMD_NUMA) += amdtopology_64.o
-obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o
+obj-$(CONFIG_AMD_NUMA) += amdtopology.o
+obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology.c
index 0919c26820d..5247d01329c 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology.c
@@ -12,6 +12,7 @@
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
+#include <linux/bootmem.h>
#include <asm/io.h>
#include <linux/pci_ids.h>
@@ -69,10 +70,10 @@ static __init void early_get_boot_cpu_id(void)
int __init amd_numa_init(void)
{
- unsigned long start = PFN_PHYS(0);
- unsigned long end = PFN_PHYS(max_pfn);
+ u64 start = PFN_PHYS(0);
+ u64 end = PFN_PHYS(max_pfn);
unsigned numnodes;
- unsigned long prevbase;
+ u64 prevbase;
int i, j, nb;
u32 nodeid, reg;
unsigned int bits, cores, apicid_base;
@@ -95,7 +96,7 @@ int __init amd_numa_init(void)
prevbase = 0;
for (i = 0; i < 8; i++) {
- unsigned long base, limit;
+ u64 base, limit;
base = read_pci_config(0, nb, 1, 0x40 + i*8);
limit = read_pci_config(0, nb, 1, 0x44 + i*8);
@@ -107,18 +108,18 @@ int __init amd_numa_init(void)
continue;
}
if (nodeid >= numnodes) {
- pr_info("Ignoring excess node %d (%lx:%lx)\n", nodeid,
+ pr_info("Ignoring excess node %d (%Lx:%Lx)\n", nodeid,
base, limit);
continue;
}
if (!limit) {
- pr_info("Skipping node entry %d (base %lx)\n",
+ pr_info("Skipping node entry %d (base %Lx)\n",
i, base);
continue;
}
if ((base >> 8) & 3 || (limit >> 8) & 3) {
- pr_err("Node %d using interleaving mode %lx/%lx\n",
+ pr_err("Node %d using interleaving mode %Lx/%Lx\n",
nodeid, (base >> 8) & 3, (limit >> 8) & 3);
return -EINVAL;
}
@@ -150,19 +151,19 @@ int __init amd_numa_init(void)
continue;
}
if (limit < base) {
- pr_err("Node %d bogus settings %lx-%lx.\n",
+ pr_err("Node %d bogus settings %Lx-%Lx.\n",
nodeid, base, limit);
continue;
}
/* Could sort here, but pun for now. Should not happen anyroads. */
if (prevbase > base) {
- pr_err("Node map not sorted %lx,%lx\n",
+ pr_err("Node map not sorted %Lx,%Lx\n",
prevbase, base);
return -EINVAL;
}
- pr_info("Node %d MemBase %016lx Limit %016lx\n",
+ pr_info("Node %d MemBase %016Lx Limit %016Lx\n",
nodeid, base, limit);
prevbase = base;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 286d289b039..37b8b0fe832 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -81,6 +81,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
}
+void __init native_pagetable_reserve(u64 start, u64 end)
+{
+ memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
struct map_range {
unsigned long start;
unsigned long end;
@@ -272,9 +277,24 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
__flush_tlb_all();
+ /*
+ * Reserve the kernel pagetable pages we used (pgt_buf_start -
+ * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+ * so that they can be reused for other purposes.
+ *
+ * On native it just means calling memblock_x86_reserve_range, on Xen it
+ * also means marking RW the pagetable pages that we allocated before
+ * but that haven't been used.
+ *
+ * In fact on xen we mark RO the whole range pgt_buf_start -
+ * pgt_buf_top, because we have to make sure that when
+ * init_memory_mapping reaches the pagetable pages area, it maps
+ * RO all the pagetable pages, including the ones that are beyond
+ * pgt_buf_end at that time.
+ */
if (!after_bootmem && pgt_buf_end > pgt_buf_start)
- memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
- pgt_buf_end << PAGE_SHIFT, "PGTABLE");
+ x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
+ PFN_PHYS(pgt_buf_end));
if (!after_bootmem)
early_memtest(start, end);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 80088f99419..29f7c6d9817 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -678,8 +678,10 @@ static void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
max_zone_pfns[ZONE_DMA] =
virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
@@ -716,6 +718,7 @@ void __init paging_init(void)
* NOTE: at this point the bootmem allocator is fully available.
*/
olpc_dt_build_devicetree();
+ sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
zone_sizes_init();
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 79423358728..d865c4aeec5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -616,7 +616,9 @@ void __init paging_init(void)
unsigned long max_zone_pfns[MAX_NR_ZONES];
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+#endif
max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
max_zone_pfns[ZONE_NORMAL] = max_pfn;
@@ -679,14 +681,6 @@ int arch_add_memory(int nid, u64 start, u64 size)
}
EXPORT_SYMBOL_GPL(arch_add_memory);
-#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
-int memory_add_physaddr_to_nid(u64 start)
-{
- return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
#endif /* CONFIG_MEMORY_HOTPLUG */
static struct kcore_list kcore_vsyscall;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0369843511d..be1ef574ce9 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -91,13 +91,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
return (__force void __iomem *)phys_to_virt(phys_addr);
/*
- * Check if the request spans more than any BAR in the iomem resource
- * tree.
- */
- WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
- KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
-
- /*
* Don't allow anybody to remap normal RAM that we're using..
*/
last_pfn = last_addr >> PAGE_SHIFT;
@@ -170,6 +163,13 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
ret_addr = (void __iomem *) (vaddr + offset);
mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
+ /*
+ * Check if the request spans more than any BAR in the iomem resource
+ * tree.
+ */
+ WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size),
+ KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
+
return ret_addr;
err_free_area:
free_vm_area(area);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 745258dfc4d..f5510d889a2 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -1,11 +1,39 @@
/* Common code for 32 and 64-bit NUMA */
-#include <linux/topology.h>
-#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/init.h>
#include <linux/bootmem.h>
-#include <asm/numa.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+#include <linux/topology.h>
+
+#include <asm/e820.h>
+#include <asm/proto.h>
+#include <asm/dma.h>
#include <asm/acpi.h>
+#include <asm/amd_nb.h>
+
+#include "numa_internal.h"
int __initdata numa_off;
+nodemask_t numa_nodes_parsed __initdata;
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+
+static struct numa_meminfo numa_meminfo
+#ifndef CONFIG_MEMORY_HOTPLUG
+__initdata
+#endif
+;
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
static __init int numa_setup(char *opt)
{
@@ -32,6 +60,15 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
+int __cpuinit numa_cpu_node(int cpu)
+{
+ int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+ if (apicid != BAD_APICID)
+ return __apicid_to_node[apicid];
+ return NUMA_NO_NODE;
+}
+
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
EXPORT_SYMBOL(node_to_cpumask_map);
@@ -95,6 +132,407 @@ void __init setup_node_to_cpumask_map(void)
pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
}
+static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
+ struct numa_meminfo *mi)
+{
+ /* ignore zero length blks */
+ if (start == end)
+ return 0;
+
+ /* whine about and ignore invalid blks */
+ if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
+ pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
+ nid, start, end);
+ return 0;
+ }
+
+ if (mi->nr_blks >= NR_NODE_MEMBLKS) {
+ pr_err("NUMA: too many memblk ranges\n");
+ return -EINVAL;
+ }
+
+ mi->blk[mi->nr_blks].start = start;
+ mi->blk[mi->nr_blks].end = end;
+ mi->blk[mi->nr_blks].nid = nid;
+ mi->nr_blks++;
+ return 0;
+}
+
+/**
+ * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
+ * @idx: Index of memblk to remove
+ * @mi: numa_meminfo to remove memblk from
+ *
+ * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
+ * decrementing @mi->nr_blks.
+ */
+void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
+{
+ mi->nr_blks--;
+ memmove(&mi->blk[idx], &mi->blk[idx + 1],
+ (mi->nr_blks - idx) * sizeof(mi->blk[0]));
+}
+
+/**
+ * numa_add_memblk - Add one numa_memblk to numa_meminfo
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @end: End address of the new memblk
+ *
+ * Add a new memblk to the default numa_meminfo.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 end)
+{
+ return numa_add_memblk_to(nid, start, end, &numa_meminfo);
+}
+
+/* Initialize NODE_DATA for a node on the local memory */
+static void __init setup_node_data(int nid, u64 start, u64 end)
+{
+ const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
+ const u64 nd_high = PFN_PHYS(max_pfn_mapped);
+ const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
+ bool remapped = false;
+ u64 nd_pa;
+ void *nd;
+ int tnid;
+
+ /*
+ * Don't confuse VM with a node that doesn't have the
+ * minimum amount of memory:
+ */
+ if (end && (end - start) < NODE_MIN_SIZE)
+ return;
+
+ /* initialize remap allocator before aligning to ZONE_ALIGN */
+ init_alloc_remap(nid, start, end);
+
+ start = roundup(start, ZONE_ALIGN);
+
+ printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
+ nid, start, end);
+
+ /*
+ * Allocate node data. Try remap allocator first, node-local
+ * memory and then any node. Never allocate in DMA zone.
+ */
+ nd = alloc_remap(nid, nd_size);
+ if (nd) {
+ nd_pa = __pa(nd);
+ remapped = true;
+ } else {
+ nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
+ nd_size, SMP_CACHE_BYTES);
+ if (nd_pa == MEMBLOCK_ERROR)
+ nd_pa = memblock_find_in_range(nd_low, nd_high,
+ nd_size, SMP_CACHE_BYTES);
+ if (nd_pa == MEMBLOCK_ERROR) {
+ pr_err("Cannot find %zu bytes in node %d\n",
+ nd_size, nid);
+ return;
+ }
+ memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
+ nd = __va(nd_pa);
+ }
+
+ /* report and initialize */
+ printk(KERN_INFO " NODE_DATA [%016Lx - %016Lx]%s\n",
+ nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
+ tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+ if (!remapped && tnid != nid)
+ printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid);
+
+ node_data[nid] = nd;
+ memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+ NODE_DATA(nid)->node_id = nid;
+ NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
+ NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
+
+ node_set_online(nid);
+}
+
+/**
+ * numa_cleanup_meminfo - Cleanup a numa_meminfo
+ * @mi: numa_meminfo to clean up
+ *
+ * Sanitize @mi by merging and removing unncessary memblks. Also check for
+ * conflicts and clear unused memblks.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
+{
+ const u64 low = 0;
+ const u64 high = PFN_PHYS(max_pfn);
+ int i, j, k;
+
+ /* first, trim all entries */
+ for (i = 0; i < mi->nr_blks; i++) {
+ struct numa_memblk *bi = &mi->blk[i];
+
+ /* make sure all blocks are inside the limits */
+ bi->start = max(bi->start, low);
+ bi->end = min(bi->end, high);
+
+ /* and there's no empty block */
+ if (bi->start >= bi->end)
+ numa_remove_memblk_from(i--, mi);
+ }
+
+ /* merge neighboring / overlapping entries */
+ for (i = 0; i < mi->nr_blks; i++) {
+ struct numa_memblk *bi = &mi->blk[i];
+
+ for (j = i + 1; j < mi->nr_blks; j++) {
+ struct numa_memblk *bj = &mi->blk[j];
+ u64 start, end;
+
+ /*
+ * See whether there are overlapping blocks. Whine
+ * about but allow overlaps of the same nid. They
+ * will be merged below.
+ */
+ if (bi->end > bj->start && bi->start < bj->end) {
+ if (bi->nid != bj->nid) {
+ pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
+ bi->nid, bi->start, bi->end,
+ bj->nid, bj->start, bj->end);
+ return -EINVAL;
+ }
+ pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
+ bi->nid, bi->start, bi->end,
+ bj->start, bj->end);
+ }
+
+ /*
+ * Join together blocks on the same node, holes
+ * between which don't overlap with memory on other
+ * nodes.
+ */
+ if (bi->nid != bj->nid)
+ continue;
+ start = min(bi->start, bj->start);
+ end = max(bi->end, bj->end);
+ for (k = 0; k < mi->nr_blks; k++) {
+ struct numa_memblk *bk = &mi->blk[k];
+
+ if (bi->nid == bk->nid)
+ continue;
+ if (start < bk->end && end > bk->start)
+ break;
+ }
+ if (k < mi->nr_blks)
+ continue;
+ printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n",
+ bi->nid, bi->start, bi->end, bj->start, bj->end,
+ start, end);
+ bi->start = start;
+ bi->end = end;
+ numa_remove_memblk_from(j--, mi);
+ }
+ }
+
+ /* clear unused ones */
+ for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
+ mi->blk[i].start = mi->blk[i].end = 0;
+ mi->blk[i].nid = NUMA_NO_NODE;
+ }
+
+ return 0;
+}
+
+/*
+ * Set nodes, which have memory in @mi, in *@nodemask.
+ */
+static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
+ const struct numa_meminfo *mi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
+ if (mi->blk[i].start != mi->blk[i].end &&
+ mi->blk[i].nid != NUMA_NO_NODE)
+ node_set(mi->blk[i].nid, *nodemask);
+}
+
+/**
+ * numa_reset_distance - Reset NUMA distance table
+ *
+ * The current table is freed. The next numa_set_distance() call will
+ * create a new one.
+ */
+void __init numa_reset_distance(void)
+{
+ size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
+
+ /* numa_distance could be 1LU marking allocation failure, test cnt */
+ if (numa_distance_cnt)
+ memblock_x86_free_range(__pa(numa_distance),
+ __pa(numa_distance) + size);
+ numa_distance_cnt = 0;
+ numa_distance = NULL; /* enable table creation */
+}
+
+static int __init numa_alloc_distance(void)
+{
+ nodemask_t nodes_parsed;
+ size_t size;
+ int i, j, cnt = 0;
+ u64 phys;
+
+ /* size the new table and allocate it */
+ nodes_parsed = numa_nodes_parsed;
+ numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
+
+ for_each_node_mask(i, nodes_parsed)
+ cnt = i;
+ cnt++;
+ size = cnt * cnt * sizeof(numa_distance[0]);
+
+ phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+ size, PAGE_SIZE);
+ if (phys == MEMBLOCK_ERROR) {
+ pr_warning("NUMA: Warning: can't allocate distance table!\n");
+ /* don't retry until explicitly reset */
+ numa_distance = (void *)1LU;
+ return -ENOMEM;
+ }
+ memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
+
+ numa_distance = __va(phys);
+ numa_distance_cnt = cnt;
+
+ /* fill with the default distances */
+ for (i = 0; i < cnt; i++)
+ for (j = 0; j < cnt; j++)
+ numa_distance[i * cnt + j] = i == j ?
+ LOCAL_DISTANCE : REMOTE_DISTANCE;
+ printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
+
+ return 0;
+}
+
+/**
+ * numa_set_distance - Set NUMA distance from one NUMA to another
+ * @from: the 'from' node to set distance
+ * @to: the 'to' node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance. If distance table
+ * doesn't exist, one which is large enough to accommodate all the currently
+ * known nodes will be created.
+ *
+ * If such table cannot be allocated, a warning is printed and further
+ * calls are ignored until the distance table is reset with
+ * numa_reset_distance().
+ *
+ * If @from or @to is higher than the highest known node at the time of
+ * table creation or @distance doesn't make sense, the call is ignored.
+ * This is to allow simplification of specific NUMA config implementations.
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+ if (!numa_distance && numa_alloc_distance() < 0)
+ return;
+
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
+ printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
+ from, to, distance);
+ return;
+ }
+
+ if ((u8)distance != distance ||
+ (from == to && distance != LOCAL_DISTANCE)) {
+ pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+ from, to, distance);
+ return;
+ }
+
+ numa_distance[from * numa_distance_cnt + to] = distance;
+}
+
+int __node_distance(int from, int to)
+{
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+ return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+ return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+/*
+ * Sanity check to catch more bad NUMA configurations (they are amazingly
+ * common). Make sure the nodes cover all memory.
+ */
+static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
+{
+ u64 numaram, e820ram;
+ int i;
+
+ numaram = 0;
+ for (i = 0; i < mi->nr_blks; i++) {
+ u64 s = mi->blk[i].start >> PAGE_SHIFT;
+ u64 e = mi->blk[i].end >> PAGE_SHIFT;
+ numaram += e - s;
+ numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
+ if ((s64)numaram < 0)
+ numaram = 0;
+ }
+
+ e820ram = max_pfn - (memblock_x86_hole_size(0,
+ PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
+ /* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+ if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
+ printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
+ (numaram << PAGE_SHIFT) >> 20,
+ (e820ram << PAGE_SHIFT) >> 20);
+ return false;
+ }
+ return true;
+}
+
+static int __init numa_register_memblks(struct numa_meminfo *mi)
+{
+ int i, nid;
+
+ /* Account for nodes with cpus and no memory */
+ node_possible_map = numa_nodes_parsed;
+ numa_nodemask_from_meminfo(&node_possible_map, mi);
+ if (WARN_ON(nodes_empty(node_possible_map)))
+ return -EINVAL;
+
+ for (i = 0; i < mi->nr_blks; i++)
+ memblock_x86_register_active_regions(mi->blk[i].nid,
+ mi->blk[i].start >> PAGE_SHIFT,
+ mi->blk[i].end >> PAGE_SHIFT);
+
+ /* for out of order entries */
+ sort_node_map();
+ if (!numa_meminfo_cover_memory(mi))
+ return -EINVAL;
+
+ /* Finally register nodes. */
+ for_each_node_mask(nid, node_possible_map) {
+ u64 start = PFN_PHYS(max_pfn);
+ u64 end = 0;
+
+ for (i = 0; i < mi->nr_blks; i++) {
+ if (nid != mi->blk[i].nid)
+ continue;
+ start = min(mi->blk[i].start, start);
+ end = max(mi->blk[i].end, end);
+ }
+
+ if (start < end)
+ setup_node_data(nid, start, end);
+ }
+
+ return 0;
+}
+
/*
* There are unfortunately some poorly designed mainboards around that
* only connect memory to a single CPU. This breaks the 1:1 cpu->node
@@ -102,7 +540,7 @@ void __init setup_node_to_cpumask_map(void)
* as the number of CPUs is not known yet. We round robin the existing
* nodes.
*/
-void __init numa_init_array(void)
+static void __init numa_init_array(void)
{
int rr, i;
@@ -117,6 +555,95 @@ void __init numa_init_array(void)
}
}
+static int __init numa_init(int (*init_func)(void))
+{
+ int i;
+ int ret;
+
+ for (i = 0; i < MAX_LOCAL_APIC; i++)
+ set_apicid_to_node(i, NUMA_NO_NODE);
+
+ nodes_clear(numa_nodes_parsed);
+ nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
+ memset(&numa_meminfo, 0, sizeof(numa_meminfo));
+ remove_all_active_ranges();
+ numa_reset_distance();
+
+ ret = init_func();
+ if (ret < 0)
+ return ret;
+ ret = numa_cleanup_meminfo(&numa_meminfo);
+ if (ret < 0)
+ return ret;
+
+ numa_emulation(&numa_meminfo, numa_distance_cnt);
+
+ ret = numa_register_memblks(&numa_meminfo);
+ if (ret < 0)
+ return ret;
+
+ for (i = 0; i < nr_cpu_ids; i++) {
+ int nid = early_cpu_to_node(i);
+
+ if (nid == NUMA_NO_NODE)
+ continue;
+ if (!node_online(nid))
+ numa_clear_node(i);
+ }
+ numa_init_array();
+ return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node and add memory blocks that cover all
+ * allowed memory. This function must not fail.
+ */
+static int __init dummy_numa_init(void)
+{
+ printk(KERN_INFO "%s\n",
+ numa_off ? "NUMA turned off" : "No NUMA configuration found");
+ printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n",
+ 0LLU, PFN_PHYS(max_pfn));
+
+ node_set(0, numa_nodes_parsed);
+ numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
+
+ return 0;
+}
+
+/**
+ * x86_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds. The
+ * last fallback is dummy single node config encomapssing whole memory and
+ * never fails.
+ */
+void __init x86_numa_init(void)
+{
+ if (!numa_off) {
+#ifdef CONFIG_X86_NUMAQ
+ if (!numa_init(numaq_numa_init))
+ return;
+#endif
+#ifdef CONFIG_ACPI_NUMA
+ if (!numa_init(x86_acpi_numa_init))
+ return;
+#endif
+#ifdef CONFIG_AMD_NUMA
+ if (!numa_init(amd_numa_init))
+ return;
+#endif
+ }
+
+ numa_init(dummy_numa_init);
+}
+
static __init int find_near_online_node(int node)
{
int n, val;
@@ -282,3 +809,18 @@ const struct cpumask *cpumask_of_node(int node)
EXPORT_SYMBOL(cpumask_of_node);
#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int memory_add_physaddr_to_nid(u64 start)
+{
+ struct numa_meminfo *mi = &numa_meminfo;
+ int nid = mi->blk[0].nid;
+ int i;
+
+ for (i = 0; i < mi->nr_blks; i++)
+ if (mi->blk[i].start <= start && mi->blk[i].end > start)
+ nid = mi->blk[i].nid;
+ return nid;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index bde3906420d..849a975d3fa 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -22,39 +22,11 @@
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
-#include <linux/mmzone.h>
-#include <linux/highmem.h>
-#include <linux/initrd.h>
-#include <linux/nodemask.h>
#include <linux/module.h>
-#include <linux/kexec.h>
-#include <linux/pfn.h>
-#include <linux/swap.h>
-#include <linux/acpi.h>
-
-#include <asm/e820.h>
-#include <asm/setup.h>
-#include <asm/mmzone.h>
-#include <asm/bios_ebda.h>
-#include <asm/proto.h>
-
-struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
-EXPORT_SYMBOL(node_data);
-
-/*
- * numa interface - we expect the numa architecture specific code to have
- * populated the following initialisation.
- *
- * 1) node_online_map - the map of all nodes configured (online) in the system
- * 2) node_start_pfn - the starting page frame number for a node
- * 3) node_end_pfn - the ending page fram number for a node
- */
-unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly;
-unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly;
+#include "numa_internal.h"
#ifdef CONFIG_DISCONTIGMEM
/*
@@ -99,108 +71,46 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
}
#endif
-extern unsigned long find_max_low_pfn(void);
extern unsigned long highend_pfn, highstart_pfn;
#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
-unsigned long node_remap_size[MAX_NUMNODES];
static void *node_remap_start_vaddr[MAX_NUMNODES];
void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
-static unsigned long kva_start_pfn;
-static unsigned long kva_pages;
-
-int __cpuinit numa_cpu_node(int cpu)
-{
- return apic->x86_32_numa_cpu_node(cpu);
-}
-
-/*
- * FLAT - support for basic PC memory model with discontig enabled, essentially
- * a single node with all available processors in it with a flat
- * memory map.
- */
-int __init get_memcfg_numa_flat(void)
-{
- printk(KERN_DEBUG "NUMA - single node, flat memory mode\n");
-
- node_start_pfn[0] = 0;
- node_end_pfn[0] = max_pfn;
- memblock_x86_register_active_regions(0, 0, max_pfn);
- memory_present(0, 0, max_pfn);
- node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
-
- /* Indicate there is one node available. */
- nodes_clear(node_online_map);
- node_set_online(0);
- return 1;
-}
-
-/*
- * Find the highest page frame number we have available for the node
- */
-static void __init propagate_e820_map_node(int nid)
-{
- if (node_end_pfn[nid] > max_pfn)
- node_end_pfn[nid] = max_pfn;
- /*
- * if a user has given mem=XXXX, then we need to make sure
- * that the node _starts_ before that, too, not just ends
- */
- if (node_start_pfn[nid] > max_pfn)
- node_start_pfn[nid] = max_pfn;
- BUG_ON(node_start_pfn[nid] > node_end_pfn[nid]);
-}
-
-/*
- * Allocate memory for the pg_data_t for this node via a crude pre-bootmem
- * method. For node zero take this from the bottom of memory, for
- * subsequent nodes place them at node_remap_start_vaddr which contains
- * node local data in physically node local memory. See setup_memory()
- * for details.
- */
-static void __init allocate_pgdat(int nid)
-{
- char buf[16];
-
- if (node_has_online_mem(nid) && node_remap_start_vaddr[nid])
- NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
- else {
- unsigned long pgdat_phys;
- pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
- max_pfn_mapped<<PAGE_SHIFT,
- sizeof(pg_data_t),
- PAGE_SIZE);
- NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
- memset(buf, 0, sizeof(buf));
- sprintf(buf, "NODE_DATA %d", nid);
- memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
- }
- printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
- nid, (unsigned long)NODE_DATA(nid));
-}
-
/*
- * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel
- * virtual address space (KVA) is reserved and portions of nodes are mapped
- * using it. This is to allow node-local memory to be allocated for
- * structures that would normally require ZONE_NORMAL. The memory is
- * allocated with alloc_remap() and callers should be prepared to allocate
- * from the bootmem allocator instead.
+ * Remap memory allocator
*/
static unsigned long node_remap_start_pfn[MAX_NUMNODES];
static void *node_remap_end_vaddr[MAX_NUMNODES];
static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-static unsigned long node_remap_offset[MAX_NUMNODES];
+/**
+ * alloc_remap - Allocate remapped memory
+ * @nid: NUMA node to allocate memory from
+ * @size: The size of allocation
+ *
+ * Allocate @size bytes from the remap area of NUMA node @nid. The
+ * size of the remap area is predetermined by init_alloc_remap() and
+ * only the callers considered there should call this function. For
+ * more info, please read the comment on top of init_alloc_remap().
+ *
+ * The caller must be ready to handle allocation failure from this
+ * function and fall back to regular memory allocator in such cases.
+ *
+ * CONTEXT:
+ * Single CPU early boot context.
+ *
+ * RETURNS:
+ * Pointer to the allocated memory on success, %NULL on failure.
+ */
void *alloc_remap(int nid, unsigned long size)
{
void *allocation = node_remap_alloc_vaddr[nid];
size = ALIGN(size, L1_CACHE_BYTES);
- if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
+ if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
return NULL;
node_remap_alloc_vaddr[nid] += size;
@@ -209,26 +119,6 @@ void *alloc_remap(int nid, unsigned long size)
return allocation;
}
-static void __init remap_numa_kva(void)
-{
- void *vaddr;
- unsigned long pfn;
- int node;
-
- for_each_online_node(node) {
- printk(KERN_DEBUG "remap_numa_kva: node %d\n", node);
- for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
- vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
- printk(KERN_DEBUG "remap_numa_kva: %08lx to pfn %08lx\n",
- (unsigned long)vaddr,
- node_remap_start_pfn[node] + pfn);
- set_pmd_pfn((ulong) vaddr,
- node_remap_start_pfn[node] + pfn,
- PAGE_KERNEL_LARGE);
- }
- }
-}
-
#ifdef CONFIG_HIBERNATION
/**
* resume_map_numa_kva - add KVA mapping to the temporary page tables created
@@ -240,15 +130,16 @@ void resume_map_numa_kva(pgd_t *pgd_base)
int node;
for_each_online_node(node) {
- unsigned long start_va, start_pfn, size, pfn;
+ unsigned long start_va, start_pfn, nr_pages, pfn;
start_va = (unsigned long)node_remap_start_vaddr[node];
start_pfn = node_remap_start_pfn[node];
- size = node_remap_size[node];
+ nr_pages = (node_remap_end_vaddr[node] -
+ node_remap_start_vaddr[node]) >> PAGE_SHIFT;
printk(KERN_DEBUG "%s: node %d\n", __func__, node);
- for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+ for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
pgd_t *pgd = pgd_base + pgd_index(vaddr);
pud_t *pud = pud_offset(pgd, vaddr);
@@ -264,132 +155,89 @@ void resume_map_numa_kva(pgd_t *pgd_base)
}
#endif
-static __init unsigned long calculate_numa_remap_pages(void)
+/**
+ * init_alloc_remap - Initialize remap allocator for a NUMA node
+ * @nid: NUMA node to initizlie remap allocator for
+ *
+ * NUMA nodes may end up without any lowmem. As allocating pgdat and
+ * memmap on a different node with lowmem is inefficient, a special
+ * remap allocator is implemented which can be used by alloc_remap().
+ *
+ * For each node, the amount of memory which will be necessary for
+ * pgdat and memmap is calculated and two memory areas of the size are
+ * allocated - one in the node and the other in lowmem; then, the area
+ * in the node is remapped to the lowmem area.
+ *
+ * As pgdat and memmap must be allocated in lowmem anyway, this
+ * doesn't waste lowmem address space; however, the actual lowmem
+ * which gets remapped over is wasted. The amount shouldn't be
+ * problematic on machines this feature will be used.
+ *
+ * Initialization failure isn't fatal. alloc_remap() is used
+ * opportunistically and the callers will fall back to other memory
+ * allocation mechanisms on failure.
+ */
+void __init init_alloc_remap(int nid, u64 start, u64 end)
{
- int nid;
- unsigned long size, reserve_pages = 0;
-
- for_each_online_node(nid) {
- u64 node_kva_target;
- u64 node_kva_final;
-
- /*
- * The acpi/srat node info can show hot-add memroy zones
- * where memory could be added but not currently present.
- */
- printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
- nid, node_start_pfn[nid], node_end_pfn[nid]);
- if (node_start_pfn[nid] > max_pfn)
- continue;
- if (!node_end_pfn[nid])
- continue;
- if (node_end_pfn[nid] > max_pfn)
- node_end_pfn[nid] = max_pfn;
-
- /* ensure the remap includes space for the pgdat. */
- size = node_remap_size[nid] + sizeof(pg_data_t);
-
- /* convert size to large (pmd size) pages, rounding up */
- size = (size + LARGE_PAGE_BYTES - 1) / LARGE_PAGE_BYTES;
- /* now the roundup is correct, convert to PAGE_SIZE pages */
- size = size * PTRS_PER_PTE;
-
- node_kva_target = round_down(node_end_pfn[nid] - size,
- PTRS_PER_PTE);
- node_kva_target <<= PAGE_SHIFT;
- do {
- node_kva_final = memblock_find_in_range(node_kva_target,
- ((u64)node_end_pfn[nid])<<PAGE_SHIFT,
- ((u64)size)<<PAGE_SHIFT,
- LARGE_PAGE_BYTES);
- node_kva_target -= LARGE_PAGE_BYTES;
- } while (node_kva_final == MEMBLOCK_ERROR &&
- (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
-
- if (node_kva_final == MEMBLOCK_ERROR)
- panic("Can not get kva ram\n");
-
- node_remap_size[nid] = size;
- node_remap_offset[nid] = reserve_pages;
- reserve_pages += size;
- printk(KERN_DEBUG "Reserving %ld pages of KVA for lmem_map of"
- " node %d at %llx\n",
- size, nid, node_kva_final>>PAGE_SHIFT);
-
- /*
- * prevent kva address below max_low_pfn want it on system
- * with less memory later.
- * layout will be: KVA address , KVA RAM
- *
- * we are supposed to only record the one less then max_low_pfn
- * but we could have some hole in high memory, and it will only
- * check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
- * to use it as free.
- * So memblock_x86_reserve_range here, hope we don't run out of that array
- */
- memblock_x86_reserve_range(node_kva_final,
- node_kva_final+(((u64)size)<<PAGE_SHIFT),
- "KVA RAM");
-
- node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT;
- }
- printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n",
- reserve_pages);
- return reserve_pages;
-}
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long end_pfn = end >> PAGE_SHIFT;
+ unsigned long size, pfn;
+ u64 node_pa, remap_pa;
+ void *remap_va;
-static void init_remap_allocator(int nid)
-{
- node_remap_start_vaddr[nid] = pfn_to_kaddr(
- kva_start_pfn + node_remap_offset[nid]);
- node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] +
- (node_remap_size[nid] * PAGE_SIZE);
- node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] +
- ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-
- printk(KERN_DEBUG "node %d will remap to vaddr %08lx - %08lx\n", nid,
- (ulong) node_remap_start_vaddr[nid],
- (ulong) node_remap_end_vaddr[nid]);
+ /*
+ * The acpi/srat node info can show hot-add memroy zones where
+ * memory could be added but not currently present.
+ */
+ printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
+ nid, start_pfn, end_pfn);
+
+ /* calculate the necessary space aligned to large page size */
+ size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
+ size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
+ size = ALIGN(size, LARGE_PAGE_BYTES);
+
+ /* allocate node memory and the lowmem remap area */
+ node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
+ if (node_pa == MEMBLOCK_ERROR) {
+ pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
+ size, nid);
+ return;
+ }
+ memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
+
+ remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
+ max_low_pfn << PAGE_SHIFT,
+ size, LARGE_PAGE_BYTES);
+ if (remap_pa == MEMBLOCK_ERROR) {
+ pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
+ size, nid);
+ memblock_x86_free_range(node_pa, node_pa + size);
+ return;
+ }
+ memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
+ remap_va = phys_to_virt(remap_pa);
+
+ /* perform actual remap */
+ for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
+ set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
+ (node_pa >> PAGE_SHIFT) + pfn,
+ PAGE_KERNEL_LARGE);
+
+ /* initialize remap allocator parameters */
+ node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
+ node_remap_start_vaddr[nid] = remap_va;
+ node_remap_end_vaddr[nid] = remap_va + size;
+ node_remap_alloc_vaddr[nid] = remap_va;
+
+ printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
+ nid, node_pa, node_pa + size, remap_va, remap_va + size);
}
void __init initmem_init(void)
{
- int nid;
- long kva_target_pfn;
-
- /*
- * When mapping a NUMA machine we allocate the node_mem_map arrays
- * from node local memory. They are then mapped directly into KVA
- * between zone normal and vmalloc space. Calculate the size of
- * this space and use it to adjust the boundary between ZONE_NORMAL
- * and ZONE_HIGHMEM.
- */
-
- get_memcfg_numa();
- numa_init_array();
-
- kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
+ x86_numa_init();
- kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
- do {
- kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
- max_low_pfn<<PAGE_SHIFT,
- kva_pages<<PAGE_SHIFT,
- PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
- kva_target_pfn -= PTRS_PER_PTE;
- } while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
-
- if (kva_start_pfn == MEMBLOCK_ERROR)
- panic("Can not get kva space\n");
-
- printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
- kva_start_pfn, max_low_pfn);
- printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
-
- /* avoid clash with initrd */
- memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
- (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
- "KVA PG");
#ifdef CONFIG_HIGHMEM
highstart_pfn = highend_pfn = max_pfn;
if (max_pfn > max_low_pfn)
@@ -409,51 +257,9 @@ void __init initmem_init(void)
printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
(ulong) pfn_to_kaddr(max_low_pfn));
- for_each_online_node(nid) {
- init_remap_allocator(nid);
-
- allocate_pgdat(nid);
- }
- remap_numa_kva();
printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
(ulong) pfn_to_kaddr(highstart_pfn));
- for_each_online_node(nid)
- propagate_e820_map_node(nid);
-
- for_each_online_node(nid) {
- memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
- NODE_DATA(nid)->node_id = nid;
- }
setup_bootmem_allocator();
}
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int paddr_to_nid(u64 addr)
-{
- int nid;
- unsigned long pfn = PFN_DOWN(addr);
-
- for_each_node(nid)
- if (node_start_pfn[nid] <= pfn &&
- pfn < node_end_pfn[nid])
- return nid;
-
- return -1;
-}
-
-/*
- * This function is used to ask node id BEFORE memmap and mem_section's
- * initialization (pfn_to_nid() can't be used yet).
- * If _PXM is not defined on ACPI's DSDT, node id must be found by this.
- */
-int memory_add_physaddr_to_nid(u64 addr)
-{
- int nid = paddr_to_nid(addr);
- return (nid >= 0) ? nid : 0;
-}
-
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index e8c00cc7203..dd27f401f0a 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -2,646 +2,13 @@
* Generic VM initialization for x86-64 NUMA setups.
* Copyright 2002,2003 Andi Kleen, SuSE Labs.
*/
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/init.h>
#include <linux/bootmem.h>
-#include <linux/memblock.h>
-#include <linux/mmzone.h>
-#include <linux/ctype.h>
-#include <linux/module.h>
-#include <linux/nodemask.h>
-#include <linux/sched.h>
-#include <linux/acpi.h>
-
-#include <asm/e820.h>
-#include <asm/proto.h>
-#include <asm/dma.h>
-#include <asm/acpi.h>
-#include <asm/amd_nb.h>
#include "numa_internal.h"
-struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
-EXPORT_SYMBOL(node_data);
-
-nodemask_t numa_nodes_parsed __initdata;
-
-struct memnode memnode;
-
-static unsigned long __initdata nodemap_addr;
-static unsigned long __initdata nodemap_size;
-
-static struct numa_meminfo numa_meminfo __initdata;
-
-static int numa_distance_cnt;
-static u8 *numa_distance;
-
-/*
- * Given a shift value, try to populate memnodemap[]
- * Returns :
- * 1 if OK
- * 0 if memnodmap[] too small (of shift too small)
- * -1 if node overlap or lost ram (shift too big)
- */
-static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift)
-{
- unsigned long addr, end;
- int i, res = -1;
-
- memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
- for (i = 0; i < mi->nr_blks; i++) {
- addr = mi->blk[i].start;
- end = mi->blk[i].end;
- if (addr >= end)
- continue;
- if ((end >> shift) >= memnodemapsize)
- return 0;
- do {
- if (memnodemap[addr >> shift] != NUMA_NO_NODE)
- return -1;
- memnodemap[addr >> shift] = mi->blk[i].nid;
- addr += (1UL << shift);
- } while (addr < end);
- res = 1;
- }
- return res;
-}
-
-static int __init allocate_cachealigned_memnodemap(void)
-{
- unsigned long addr;
-
- memnodemap = memnode.embedded_map;
- if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map))
- return 0;
-
- addr = 0x8000;
- nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
- nodemap_addr = memblock_find_in_range(addr, get_max_mapped(),
- nodemap_size, L1_CACHE_BYTES);
- if (nodemap_addr == MEMBLOCK_ERROR) {
- printk(KERN_ERR
- "NUMA: Unable to allocate Memory to Node hash map\n");
- nodemap_addr = nodemap_size = 0;
- return -1;
- }
- memnodemap = phys_to_virt(nodemap_addr);
- memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
-
- printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
- nodemap_addr, nodemap_addr + nodemap_size);
- return 0;
-}
-
-/*
- * The LSB of all start and end addresses in the node map is the value of the
- * maximum possible shift.
- */
-static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi)
-{
- int i, nodes_used = 0;
- unsigned long start, end;
- unsigned long bitfield = 0, memtop = 0;
-
- for (i = 0; i < mi->nr_blks; i++) {
- start = mi->blk[i].start;
- end = mi->blk[i].end;
- if (start >= end)
- continue;
- bitfield |= start;
- nodes_used++;
- if (end > memtop)
- memtop = end;
- }
- if (nodes_used <= 1)
- i = 63;
- else
- i = find_first_bit(&bitfield, sizeof(unsigned long)*8);
- memnodemapsize = (memtop >> i)+1;
- return i;
-}
-
-static int __init compute_hash_shift(const struct numa_meminfo *mi)
-{
- int shift;
-
- shift = extract_lsb_from_nodes(mi);
- if (allocate_cachealigned_memnodemap())
- return -1;
- printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
- shift);
-
- if (populate_memnodemap(mi, shift) != 1) {
- printk(KERN_INFO "Your memory is not aligned you need to "
- "rebuild your kernel with a bigger NODEMAPSIZE "
- "shift=%d\n", shift);
- return -1;
- }
- return shift;
-}
-
-int __meminit __early_pfn_to_nid(unsigned long pfn)
-{
- return phys_to_nid(pfn << PAGE_SHIFT);
-}
-
-static void * __init early_node_mem(int nodeid, unsigned long start,
- unsigned long end, unsigned long size,
- unsigned long align)
-{
- unsigned long mem;
-
- /*
- * put it on high as possible
- * something will go with NODE_DATA
- */
- if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
- start = MAX_DMA_PFN<<PAGE_SHIFT;
- if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
- end > (MAX_DMA32_PFN<<PAGE_SHIFT))
- start = MAX_DMA32_PFN<<PAGE_SHIFT;
- mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
- if (mem != MEMBLOCK_ERROR)
- return __va(mem);
-
- /* extend the search scope */
- end = max_pfn_mapped << PAGE_SHIFT;
- start = MAX_DMA_PFN << PAGE_SHIFT;
- mem = memblock_find_in_range(start, end, size, align);
- if (mem != MEMBLOCK_ERROR)
- return __va(mem);
-
- printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
- size, nodeid);
-
- return NULL;
-}
-
-static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
- struct numa_meminfo *mi)
-{
- /* ignore zero length blks */
- if (start == end)
- return 0;
-
- /* whine about and ignore invalid blks */
- if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
- pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
- nid, start, end);
- return 0;
- }
-
- if (mi->nr_blks >= NR_NODE_MEMBLKS) {
- pr_err("NUMA: too many memblk ranges\n");
- return -EINVAL;
- }
-
- mi->blk[mi->nr_blks].start = start;
- mi->blk[mi->nr_blks].end = end;
- mi->blk[mi->nr_blks].nid = nid;
- mi->nr_blks++;
- return 0;
-}
-
-/**
- * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
- * @idx: Index of memblk to remove
- * @mi: numa_meminfo to remove memblk from
- *
- * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
- * decrementing @mi->nr_blks.
- */
-void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
-{
- mi->nr_blks--;
- memmove(&mi->blk[idx], &mi->blk[idx + 1],
- (mi->nr_blks - idx) * sizeof(mi->blk[0]));
-}
-
-/**
- * numa_add_memblk - Add one numa_memblk to numa_meminfo
- * @nid: NUMA node ID of the new memblk
- * @start: Start address of the new memblk
- * @end: End address of the new memblk
- *
- * Add a new memblk to the default numa_meminfo.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int __init numa_add_memblk(int nid, u64 start, u64 end)
-{
- return numa_add_memblk_to(nid, start, end, &numa_meminfo);
-}
-
-/* Initialize bootmem allocator for a node */
-void __init
-setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
-{
- unsigned long start_pfn, last_pfn, nodedata_phys;
- const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
- int nid;
-
- if (!end)
- return;
-
- /*
- * Don't confuse VM with a node that doesn't have the
- * minimum amount of memory:
- */
- if (end && (end - start) < NODE_MIN_SIZE)
- return;
-
- start = roundup(start, ZONE_ALIGN);
-
- printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
- start, end);
-
- start_pfn = start >> PAGE_SHIFT;
- last_pfn = end >> PAGE_SHIFT;
-
- node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size,
- SMP_CACHE_BYTES);
- if (node_data[nodeid] == NULL)
- return;
- nodedata_phys = __pa(node_data[nodeid]);
- memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
- printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
- nodedata_phys + pgdat_size - 1);
- nid = phys_to_nid(nodedata_phys);
- if (nid != nodeid)
- printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid);
-
- memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
- NODE_DATA(nodeid)->node_id = nodeid;
- NODE_DATA(nodeid)->node_start_pfn = start_pfn;
- NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
-
- node_set_online(nodeid);
-}
-
-/**
- * numa_cleanup_meminfo - Cleanup a numa_meminfo
- * @mi: numa_meminfo to clean up
- *
- * Sanitize @mi by merging and removing unncessary memblks. Also check for
- * conflicts and clear unused memblks.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
-{
- const u64 low = 0;
- const u64 high = (u64)max_pfn << PAGE_SHIFT;
- int i, j, k;
-
- for (i = 0; i < mi->nr_blks; i++) {
- struct numa_memblk *bi = &mi->blk[i];
-
- /* make sure all blocks are inside the limits */
- bi->start = max(bi->start, low);
- bi->end = min(bi->end, high);
-
- /* and there's no empty block */
- if (bi->start == bi->end) {
- numa_remove_memblk_from(i--, mi);
- continue;
- }
-
- for (j = i + 1; j < mi->nr_blks; j++) {
- struct numa_memblk *bj = &mi->blk[j];
- unsigned long start, end;
-
- /*
- * See whether there are overlapping blocks. Whine
- * about but allow overlaps of the same nid. They
- * will be merged below.
- */
- if (bi->end > bj->start && bi->start < bj->end) {
- if (bi->nid != bj->nid) {
- pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
- bi->nid, bi->start, bi->end,
- bj->nid, bj->start, bj->end);
- return -EINVAL;
- }
- pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
- bi->nid, bi->start, bi->end,
- bj->start, bj->end);
- }
-
- /*
- * Join together blocks on the same node, holes
- * between which don't overlap with memory on other
- * nodes.
- */
- if (bi->nid != bj->nid)
- continue;
- start = max(min(bi->start, bj->start), low);
- end = min(max(bi->end, bj->end), high);
- for (k = 0; k < mi->nr_blks; k++) {
- struct numa_memblk *bk = &mi->blk[k];
-
- if (bi->nid == bk->nid)
- continue;
- if (start < bk->end && end > bk->start)
- break;
- }
- if (k < mi->nr_blks)
- continue;
- printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
- bi->nid, bi->start, bi->end, bj->start, bj->end,
- start, end);
- bi->start = start;
- bi->end = end;
- numa_remove_memblk_from(j--, mi);
- }
- }
-
- for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
- mi->blk[i].start = mi->blk[i].end = 0;
- mi->blk[i].nid = NUMA_NO_NODE;
- }
-
- return 0;
-}
-
-/*
- * Set nodes, which have memory in @mi, in *@nodemask.
- */
-static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
- const struct numa_meminfo *mi)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
- if (mi->blk[i].start != mi->blk[i].end &&
- mi->blk[i].nid != NUMA_NO_NODE)
- node_set(mi->blk[i].nid, *nodemask);
-}
-
-/**
- * numa_reset_distance - Reset NUMA distance table
- *
- * The current table is freed. The next numa_set_distance() call will
- * create a new one.
- */
-void __init numa_reset_distance(void)
-{
- size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
-
- /* numa_distance could be 1LU marking allocation failure, test cnt */
- if (numa_distance_cnt)
- memblock_x86_free_range(__pa(numa_distance),
- __pa(numa_distance) + size);
- numa_distance_cnt = 0;
- numa_distance = NULL; /* enable table creation */
-}
-
-static int __init numa_alloc_distance(void)
-{
- nodemask_t nodes_parsed;
- size_t size;
- int i, j, cnt = 0;
- u64 phys;
-
- /* size the new table and allocate it */
- nodes_parsed = numa_nodes_parsed;
- numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
-
- for_each_node_mask(i, nodes_parsed)
- cnt = i;
- cnt++;
- size = cnt * cnt * sizeof(numa_distance[0]);
-
- phys = memblock_find_in_range(0, (u64)max_pfn_mapped << PAGE_SHIFT,
- size, PAGE_SIZE);
- if (phys == MEMBLOCK_ERROR) {
- pr_warning("NUMA: Warning: can't allocate distance table!\n");
- /* don't retry until explicitly reset */
- numa_distance = (void *)1LU;
- return -ENOMEM;
- }
- memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
-
- numa_distance = __va(phys);
- numa_distance_cnt = cnt;
-
- /* fill with the default distances */
- for (i = 0; i < cnt; i++)
- for (j = 0; j < cnt; j++)
- numa_distance[i * cnt + j] = i == j ?
- LOCAL_DISTANCE : REMOTE_DISTANCE;
- printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
-
- return 0;
-}
-
-/**
- * numa_set_distance - Set NUMA distance from one NUMA to another
- * @from: the 'from' node to set distance
- * @to: the 'to' node to set distance
- * @distance: NUMA distance
- *
- * Set the distance from node @from to @to to @distance. If distance table
- * doesn't exist, one which is large enough to accommodate all the currently
- * known nodes will be created.
- *
- * If such table cannot be allocated, a warning is printed and further
- * calls are ignored until the distance table is reset with
- * numa_reset_distance().
- *
- * If @from or @to is higher than the highest known node at the time of
- * table creation or @distance doesn't make sense, the call is ignored.
- * This is to allow simplification of specific NUMA config implementations.
- */
-void __init numa_set_distance(int from, int to, int distance)
-{
- if (!numa_distance && numa_alloc_distance() < 0)
- return;
-
- if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
- printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
- from, to, distance);
- return;
- }
-
- if ((u8)distance != distance ||
- (from == to && distance != LOCAL_DISTANCE)) {
- pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
- from, to, distance);
- return;
- }
-
- numa_distance[from * numa_distance_cnt + to] = distance;
-}
-
-int __node_distance(int from, int to)
-{
- if (from >= numa_distance_cnt || to >= numa_distance_cnt)
- return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
- return numa_distance[from * numa_distance_cnt + to];
-}
-EXPORT_SYMBOL(__node_distance);
-
-/*
- * Sanity check to catch more bad NUMA configurations (they are amazingly
- * common). Make sure the nodes cover all memory.
- */
-static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
-{
- unsigned long numaram, e820ram;
- int i;
-
- numaram = 0;
- for (i = 0; i < mi->nr_blks; i++) {
- unsigned long s = mi->blk[i].start >> PAGE_SHIFT;
- unsigned long e = mi->blk[i].end >> PAGE_SHIFT;
- numaram += e - s;
- numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
- if ((long)numaram < 0)
- numaram = 0;
- }
-
- e820ram = max_pfn - (memblock_x86_hole_size(0,
- max_pfn << PAGE_SHIFT) >> PAGE_SHIFT);
- /* We seem to lose 3 pages somewhere. Allow 1M of slack. */
- if ((long)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
- printk(KERN_ERR "NUMA: nodes only cover %luMB of your %luMB e820 RAM. Not used.\n",
- (numaram << PAGE_SHIFT) >> 20,
- (e820ram << PAGE_SHIFT) >> 20);
- return false;
- }
- return true;
-}
-
-static int __init numa_register_memblks(struct numa_meminfo *mi)
-{
- int i, nid;
-
- /* Account for nodes with cpus and no memory */
- node_possible_map = numa_nodes_parsed;
- numa_nodemask_from_meminfo(&node_possible_map, mi);
- if (WARN_ON(nodes_empty(node_possible_map)))
- return -EINVAL;
-
- memnode_shift = compute_hash_shift(mi);
- if (memnode_shift < 0) {
- printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n");
- return -EINVAL;
- }
-
- for (i = 0; i < mi->nr_blks; i++)
- memblock_x86_register_active_regions(mi->blk[i].nid,
- mi->blk[i].start >> PAGE_SHIFT,
- mi->blk[i].end >> PAGE_SHIFT);
-
- /* for out of order entries */
- sort_node_map();
- if (!numa_meminfo_cover_memory(mi))
- return -EINVAL;
-
- /* Finally register nodes. */
- for_each_node_mask(nid, node_possible_map) {
- u64 start = (u64)max_pfn << PAGE_SHIFT;
- u64 end = 0;
-
- for (i = 0; i < mi->nr_blks; i++) {
- if (nid != mi->blk[i].nid)
- continue;
- start = min(mi->blk[i].start, start);
- end = max(mi->blk[i].end, end);
- }
-
- if (start < end)
- setup_node_bootmem(nid, start, end);
- }
-
- return 0;
-}
-
-/**
- * dummy_numma_init - Fallback dummy NUMA init
- *
- * Used if there's no underlying NUMA architecture, NUMA initialization
- * fails, or NUMA is disabled on the command line.
- *
- * Must online at least one node and add memory blocks that cover all
- * allowed memory. This function must not fail.
- */
-static int __init dummy_numa_init(void)
-{
- printk(KERN_INFO "%s\n",
- numa_off ? "NUMA turned off" : "No NUMA configuration found");
- printk(KERN_INFO "Faking a node at %016lx-%016lx\n",
- 0LU, max_pfn << PAGE_SHIFT);
-
- node_set(0, numa_nodes_parsed);
- numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT);
-
- return 0;
-}
-
-static int __init numa_init(int (*init_func)(void))
-{
- int i;
- int ret;
-
- for (i = 0; i < MAX_LOCAL_APIC; i++)
- set_apicid_to_node(i, NUMA_NO_NODE);
-
- nodes_clear(numa_nodes_parsed);
- nodes_clear(node_possible_map);
- nodes_clear(node_online_map);
- memset(&numa_meminfo, 0, sizeof(numa_meminfo));
- remove_all_active_ranges();
- numa_reset_distance();
-
- ret = init_func();
- if (ret < 0)
- return ret;
- ret = numa_cleanup_meminfo(&numa_meminfo);
- if (ret < 0)
- return ret;
-
- numa_emulation(&numa_meminfo, numa_distance_cnt);
-
- ret = numa_register_memblks(&numa_meminfo);
- if (ret < 0)
- return ret;
-
- for (i = 0; i < nr_cpu_ids; i++) {
- int nid = early_cpu_to_node(i);
-
- if (nid == NUMA_NO_NODE)
- continue;
- if (!node_online(nid))
- numa_clear_node(i);
- }
- numa_init_array();
- return 0;
-}
-
void __init initmem_init(void)
{
- int ret;
-
- if (!numa_off) {
-#ifdef CONFIG_ACPI_NUMA
- ret = numa_init(x86_acpi_numa_init);
- if (!ret)
- return;
-#endif
-#ifdef CONFIG_AMD_NUMA
- ret = numa_init(amd_numa_init);
- if (!ret)
- return;
-#endif
- }
-
- numa_init(dummy_numa_init);
+ x86_numa_init();
}
unsigned long __init numa_free_all_bootmem(void)
@@ -656,12 +23,3 @@ unsigned long __init numa_free_all_bootmem(void)
return pages;
}
-
-int __cpuinit numa_cpu_node(int cpu)
-{
- int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-
- if (apicid != BAD_APICID)
- return __apicid_to_node[apicid];
- return NUMA_NO_NODE;
-}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index de84cc14037..d0ed086b624 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -5,6 +5,7 @@
#include <linux/errno.h>
#include <linux/topology.h>
#include <linux/memblock.h>
+#include <linux/bootmem.h>
#include <asm/dma.h>
#include "numa_internal.h"
@@ -84,7 +85,13 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
nr_nodes = MAX_NUMNODES;
}
- size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
+ /*
+ * Calculate target node size. x86_32 freaks on __udivdi3() so do
+ * the division in ulong number of pages and convert back.
+ */
+ size = max_addr - addr - memblock_x86_hole_size(addr, max_addr);
+ size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
+
/*
* Calculate the number of big nodes that can be allocated as a result
* of consolidating the remainder.
@@ -226,7 +233,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
*/
while (nodes_weight(physnode_mask)) {
for_each_node_mask(i, physnode_mask) {
- u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+ u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
u64 start, limit, end;
int phys_blk;
@@ -298,7 +305,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
{
static struct numa_meminfo ei __initdata;
static struct numa_meminfo pi __initdata;
- const u64 max_addr = max_pfn << PAGE_SHIFT;
+ const u64 max_addr = PFN_PHYS(max_pfn);
u8 *phys_dist = NULL;
size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
int max_emu_nid, dfl_phys_nid;
@@ -342,8 +349,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
if (numa_dist_cnt) {
u64 phys;
- phys = memblock_find_in_range(0,
- (u64)max_pfn_mapped << PAGE_SHIFT,
+ phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
phys_size, PAGE_SIZE);
if (phys == MEMBLOCK_ERROR) {
pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index ef2d97377d7..7178c3afe05 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -19,6 +19,14 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi);
int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
void __init numa_reset_distance(void);
+void __init x86_numa_init(void);
+
+#ifdef CONFIG_X86_64
+static inline void init_alloc_remap(int nid, u64 start, u64 end) { }
+#else
+void __init init_alloc_remap(int nid, u64 start, u64 end);
+#endif
+
#ifdef CONFIG_NUMA_EMU
void __init numa_emulation(struct numa_meminfo *numa_meminfo,
int numa_dist_cnt);
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat.c
index 8e9d3394f6d..81dbfdeb080 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat.c
@@ -26,8 +26,6 @@
int acpi_numa __initdata;
-static struct bootnode nodes_add[MAX_NUMNODES];
-
static __init int setup_node(int pxm)
{
return acpi_map_pxm_to_node(pxm);
@@ -37,7 +35,6 @@ static __init void bad_srat(void)
{
printk(KERN_ERR "SRAT: SRAT not used.\n");
acpi_numa = -1;
- memset(nodes_add, 0, sizeof(nodes_add));
}
static __init inline int srat_disabled(void)
@@ -131,73 +128,17 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
pxm, apic_id, node);
}
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
static inline int save_add_info(void) {return 1;}
#else
static inline int save_add_info(void) {return 0;}
#endif
-/*
- * Update nodes_add[]
- * This code supports one contiguous hot add area per node
- */
-static void __init
-update_nodes_add(int node, unsigned long start, unsigned long end)
-{
- unsigned long s_pfn = start >> PAGE_SHIFT;
- unsigned long e_pfn = end >> PAGE_SHIFT;
- int changed = 0;
- struct bootnode *nd = &nodes_add[node];
-
- /* I had some trouble with strange memory hotadd regions breaking
- the boot. Be very strict here and reject anything unexpected.
- If you want working memory hotadd write correct SRATs.
-
- The node size check is a basic sanity check to guard against
- mistakes */
- if ((signed long)(end - start) < NODE_MIN_SIZE) {
- printk(KERN_ERR "SRAT: Hotplug area too small\n");
- return;
- }
-
- /* This check might be a bit too strict, but I'm keeping it for now. */
- if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) {
- printk(KERN_ERR
- "SRAT: Hotplug area %lu -> %lu has existing memory\n",
- s_pfn, e_pfn);
- return;
- }
-
- /* Looks good */
-
- if (nd->start == nd->end) {
- nd->start = start;
- nd->end = end;
- changed = 1;
- } else {
- if (nd->start == end) {
- nd->start = start;
- changed = 1;
- }
- if (nd->end == start) {
- nd->end = end;
- changed = 1;
- }
- if (!changed)
- printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
- }
-
- if (changed) {
- node_set(node, numa_nodes_parsed);
- printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
- nd->start, nd->end);
- }
-}
/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
void __init
acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
{
- unsigned long start, end;
+ u64 start, end;
int node, pxm;
if (srat_disabled())
@@ -226,11 +167,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
return;
}
- printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm,
+ printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
start, end);
-
- if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)
- update_nodes_add(node, start, end);
}
void __init acpi_numa_arch_fixup(void) {}
@@ -244,17 +182,3 @@ int __init x86_acpi_numa_init(void)
return ret;
return srat_disabled() ? -EINVAL : 0;
}
-
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY)
-int memory_add_physaddr_to_nid(u64 start)
-{
- int i, ret = 0;
-
- for_each_node(i)
- if (nodes_add[i].start <= start && nodes_add[i].end > start)
- ret = i;
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
deleted file mode 100644
index 364f36bdfad..00000000000
--- a/arch/x86/mm/srat_32.c
+++ /dev/null
@@ -1,288 +0,0 @@
-/*
- * Some of the code in this file has been gleaned from the 64 bit
- * discontigmem support code base.
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * 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.
- *
- * 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.
- *
- * Send feedback to Pat Gaughen <gone@us.ibm.com>
- */
-#include <linux/mm.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
-#include <linux/mmzone.h>
-#include <linux/acpi.h>
-#include <linux/nodemask.h>
-#include <asm/srat.h>
-#include <asm/topology.h>
-#include <asm/smp.h>
-#include <asm/e820.h>
-
-/*
- * proximity macros and definitions
- */
-#define NODE_ARRAY_INDEX(x) ((x) / 8) /* 8 bits/char */
-#define NODE_ARRAY_OFFSET(x) ((x) % 8) /* 8 bits/char */
-#define BMAP_SET(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] |= 1 << NODE_ARRAY_OFFSET(bit))
-#define BMAP_TEST(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] & (1 << NODE_ARRAY_OFFSET(bit)))
-/* bitmap length; _PXM is at most 255 */
-#define PXM_BITMAP_LEN (MAX_PXM_DOMAINS / 8)
-static u8 __initdata pxm_bitmap[PXM_BITMAP_LEN]; /* bitmap of proximity domains */
-
-#define MAX_CHUNKS_PER_NODE 3
-#define MAXCHUNKS (MAX_CHUNKS_PER_NODE * MAX_NUMNODES)
-struct node_memory_chunk_s {
- unsigned long start_pfn;
- unsigned long end_pfn;
- u8 pxm; // proximity domain of node
- u8 nid; // which cnode contains this chunk?
- u8 bank; // which mem bank on this node
-};
-static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS];
-
-static int __initdata num_memory_chunks; /* total number of memory chunks */
-static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC];
-
-int acpi_numa __initdata;
-
-static __init void bad_srat(void)
-{
- printk(KERN_ERR "SRAT: SRAT not used.\n");
- acpi_numa = -1;
- num_memory_chunks = 0;
-}
-
-static __init inline int srat_disabled(void)
-{
- return numa_off || acpi_numa < 0;
-}
-
-/* Identify CPU proximity domains */
-void __init
-acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity)
-{
- if (srat_disabled())
- return;
- if (cpu_affinity->header.length !=
- sizeof(struct acpi_srat_cpu_affinity)) {
- bad_srat();
- return;
- }
-
- if ((cpu_affinity->flags & ACPI_SRAT_CPU_ENABLED) == 0)
- return; /* empty entry */
-
- /* mark this node as "seen" in node bitmap */
- BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo);
-
- /* don't need to check apic_id here, because it is always 8 bits */
- apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo;
-
- printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n",
- cpu_affinity->apic_id, cpu_affinity->proximity_domain_lo);
-}
-
-/*
- * Identify memory proximity domains and hot-remove capabilities.
- * Fill node memory chunk list structure.
- */
-void __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *memory_affinity)
-{
- unsigned long long paddr, size;
- unsigned long start_pfn, end_pfn;
- u8 pxm;
- struct node_memory_chunk_s *p, *q, *pend;
-
- if (srat_disabled())
- return;
- if (memory_affinity->header.length !=
- sizeof(struct acpi_srat_mem_affinity)) {
- bad_srat();
- return;
- }
-
- if ((memory_affinity->flags & ACPI_SRAT_MEM_ENABLED) == 0)
- return; /* empty entry */
-
- pxm = memory_affinity->proximity_domain & 0xff;
-
- /* mark this node as "seen" in node bitmap */
- BMAP_SET(pxm_bitmap, pxm);
-
- /* calculate info for memory chunk structure */
- paddr = memory_affinity->base_address;
- size = memory_affinity->length;
-
- start_pfn = paddr >> PAGE_SHIFT;
- end_pfn = (paddr + size) >> PAGE_SHIFT;
-
-
- if (num_memory_chunks >= MAXCHUNKS) {
- printk(KERN_WARNING "Too many mem chunks in SRAT."
- " Ignoring %lld MBytes at %llx\n",
- size/(1024*1024), paddr);
- return;
- }
-
- /* Insertion sort based on base address */
- pend = &node_memory_chunk[num_memory_chunks];
- for (p = &node_memory_chunk[0]; p < pend; p++) {
- if (start_pfn < p->start_pfn)
- break;
- }
- if (p < pend) {
- for (q = pend; q >= p; q--)
- *(q + 1) = *q;
- }
- p->start_pfn = start_pfn;
- p->end_pfn = end_pfn;
- p->pxm = pxm;
-
- num_memory_chunks++;
-
- printk(KERN_DEBUG "Memory range %08lx to %08lx"
- " in proximity domain %02x %s\n",
- start_pfn, end_pfn,
- pxm,
- ((memory_affinity->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
- "enabled and removable" : "enabled" ) );
-}
-
-/* Callback for SLIT parsing */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
-{
-}
-
-void acpi_numa_arch_fixup(void)
-{
-}
-/*
- * The SRAT table always lists ascending addresses, so can always
- * assume that the first "start" address that you see is the real
- * start of the node, and that the current "end" address is after
- * the previous one.
- */
-static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
-{
- /*
- * Only add present memory as told by the e820.
- * There is no guarantee from the SRAT that the memory it
- * enumerates is present at boot time because it represents
- * *possible* memory hotplug areas the same as normal RAM.
- */
- if (memory_chunk->start_pfn >= max_pfn) {
- printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n",
- memory_chunk->start_pfn, memory_chunk->end_pfn);
- return -1;
- }
- if (memory_chunk->nid != nid)
- return -1;
-
- if (!node_has_online_mem(nid))
- node_start_pfn[nid] = memory_chunk->start_pfn;
-
- if (node_start_pfn[nid] > memory_chunk->start_pfn)
- node_start_pfn[nid] = memory_chunk->start_pfn;
-
- if (node_end_pfn[nid] < memory_chunk->end_pfn)
- node_end_pfn[nid] = memory_chunk->end_pfn;
-
- return 0;
-}
-
-int __init get_memcfg_from_srat(void)
-{
- int i, j, nid;
-
- if (srat_disabled())
- goto out_fail;
-
- if (acpi_numa_init() < 0)
- goto out_fail;
-
- if (num_memory_chunks == 0) {
- printk(KERN_DEBUG
- "could not find any ACPI SRAT memory areas.\n");
- goto out_fail;
- }
-
- /* Calculate total number of nodes in system from PXM bitmap and create
- * a set of sequential node IDs starting at zero. (ACPI doesn't seem
- * to specify the range of _PXM values.)
- */
- /*
- * MCD - we no longer HAVE to number nodes sequentially. PXM domain
- * numbers could go as high as 256, and MAX_NUMNODES for i386 is typically
- * 32, so we will continue numbering them in this manner until MAX_NUMNODES
- * approaches MAX_PXM_DOMAINS for i386.
- */
- nodes_clear(node_online_map);
- for (i = 0; i < MAX_PXM_DOMAINS; i++) {
- if (BMAP_TEST(pxm_bitmap, i)) {
- int nid = acpi_map_pxm_to_node(i);
- node_set_online(nid);
- }
- }
- BUG_ON(num_online_nodes() == 0);
-
- /* set cnode id in memory chunk structure */
- for (i = 0; i < num_memory_chunks; i++)
- node_memory_chunk[i].nid = pxm_to_node(node_memory_chunk[i].pxm);
-
- printk(KERN_DEBUG "pxm bitmap: ");
- for (i = 0; i < sizeof(pxm_bitmap); i++) {
- printk(KERN_CONT "%02x ", pxm_bitmap[i]);
- }
- printk(KERN_CONT "\n");
- printk(KERN_DEBUG "Number of logical nodes in system = %d\n",
- num_online_nodes());
- printk(KERN_DEBUG "Number of memory chunks in system = %d\n",
- num_memory_chunks);
-
- for (i = 0; i < MAX_LOCAL_APIC; i++)
- set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i]));
-
- for (j = 0; j < num_memory_chunks; j++){
- struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
- printk(KERN_DEBUG
- "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
- j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
- if (node_read_chunk(chunk->nid, chunk))
- continue;
-
- memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
- min(chunk->end_pfn, max_pfn));
- }
- /* for out of order entries in SRAT */
- sort_node_map();
-
- for_each_online_node(nid) {
- unsigned long start = node_start_pfn[nid];
- unsigned long end = min(node_end_pfn[nid], max_pfn);
-
- memory_present(nid, start, end);
- node_remap_size[nid] = node_memmap_size_bytes(nid, start, end);
- }
- return 1;
-out_fail:
- printk(KERN_DEBUG "failed to get NUMA memory information from SRAT"
- " table\n");
- return 0;
-}
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 2d49d4e19a3..a5b64ab4cd6 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -16,17 +16,6 @@
#include <asm/stacktrace.h>
#include <linux/compat.h>
-static void backtrace_warning_symbol(void *data, char *msg,
- unsigned long symbol)
-{
- /* Ignore warnings */
-}
-
-static void backtrace_warning(void *data, char *msg)
-{
- /* Ignore warnings */
-}
-
static int backtrace_stack(void *data, char *name)
{
/* Yes, we want all stacks */
@@ -42,8 +31,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
}
static struct stacktrace_ops backtrace_ops = {
- .warning = backtrace_warning,
- .warning_symbol = backtrace_warning_symbol,
.stack = backtrace_stack,
.address = backtrace_address,
.walk_stack = print_context_stack,
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e37b407a0ee..8214724ce54 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -108,7 +108,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
}
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
(type == PCI_CAP_ID_MSIX) ?
- "msi-x" : "msi");
+ "msi-x" : "msi",
+ DOMID_SELF);
if (irq < 0)
goto error;
dev_dbg(&dev->dev,
@@ -148,7 +149,8 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
(type == PCI_CAP_ID_MSIX) ?
"pcifront-msi-x" :
- "pcifront-msi");
+ "pcifront-msi",
+ DOMID_SELF);
if (irq < 0)
goto free;
i++;
@@ -190,9 +192,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
list_for_each_entry(msidesc, &dev->msi_list, list) {
struct physdev_map_pirq map_irq;
+ domid_t domid;
+
+ domid = ret = xen_find_device_domain_owner(dev);
+ /* N.B. Casting int's -ENODEV to uint16_t results in 0xFFED,
+ * hence check ret value for < 0. */
+ if (ret < 0)
+ domid = DOMID_SELF;
memset(&map_irq, 0, sizeof(map_irq));
- map_irq.domid = DOMID_SELF;
+ map_irq.domid = domid;
map_irq.type = MAP_PIRQ_TYPE_MSI;
map_irq.index = -1;
map_irq.pirq = -1;
@@ -215,14 +224,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
if (ret) {
- dev_warn(&dev->dev, "xen map irq failed %d\n", ret);
+ dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n",
+ ret, domid);
goto out;
}
ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
map_irq.pirq, map_irq.index,
(type == PCI_CAP_ID_MSIX) ?
- "msi-x" : "msi");
+ "msi-x" : "msi",
+ domid);
if (ret < 0)
goto out;
}
@@ -461,3 +472,78 @@ void __init xen_setup_pirqs(void)
}
}
#endif
+
+#ifdef CONFIG_XEN_DOM0
+struct xen_device_domain_owner {
+ domid_t domain;
+ struct pci_dev *dev;
+ struct list_head list;
+};
+
+static DEFINE_SPINLOCK(dev_domain_list_spinlock);
+static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list);
+
+static struct xen_device_domain_owner *find_device(struct pci_dev *dev)
+{
+ struct xen_device_domain_owner *owner;
+
+ list_for_each_entry(owner, &dev_domain_list, list) {
+ if (owner->dev == dev)
+ return owner;
+ }
+ return NULL;
+}
+
+int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+ struct xen_device_domain_owner *owner;
+ int domain = -ENODEV;
+
+ spin_lock(&dev_domain_list_spinlock);
+ owner = find_device(dev);
+ if (owner)
+ domain = owner->domain;
+ spin_unlock(&dev_domain_list_spinlock);
+ return domain;
+}
+EXPORT_SYMBOL_GPL(xen_find_device_domain_owner);
+
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain)
+{
+ struct xen_device_domain_owner *owner;
+
+ owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL);
+ if (!owner)
+ return -ENODEV;
+
+ spin_lock(&dev_domain_list_spinlock);
+ if (find_device(dev)) {
+ spin_unlock(&dev_domain_list_spinlock);
+ kfree(owner);
+ return -EEXIST;
+ }
+ owner->domain = domain;
+ owner->dev = dev;
+ list_add_tail(&owner->list, &dev_domain_list);
+ spin_unlock(&dev_domain_list_spinlock);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xen_register_device_domain_owner);
+
+int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+ struct xen_device_domain_owner *owner;
+
+ spin_lock(&dev_domain_list_spinlock);
+ owner = find_device(dev);
+ if (!owner) {
+ spin_unlock(&dev_domain_list_spinlock);
+ return -ENODEV;
+ }
+ list_del(&owner->list);
+ spin_unlock(&dev_domain_list_spinlock);
+ kfree(owner);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
+#endif
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0fe27d7c625..b30aa26a8df 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -145,17 +145,6 @@ static void virt_efi_reset_system(int reset_type,
data_size, data);
}
-static efi_status_t virt_efi_set_virtual_address_map(
- unsigned long memory_map_size,
- unsigned long descriptor_size,
- u32 descriptor_version,
- efi_memory_desc_t *virtual_map)
-{
- return efi_call_virt4(set_virtual_address_map,
- memory_map_size, descriptor_size,
- descriptor_version, virtual_map);
-}
-
static efi_status_t __init phys_efi_set_virtual_address_map(
unsigned long memory_map_size,
unsigned long descriptor_size,
@@ -468,11 +457,25 @@ void __init efi_init(void)
#endif
}
+void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
+{
+ u64 addr, npages;
+
+ addr = md->virt_addr;
+ npages = md->num_pages;
+
+ memrange_efi_to_native(&addr, &npages);
+
+ if (executable)
+ set_memory_x(addr, npages);
+ else
+ set_memory_nx(addr, npages);
+}
+
static void __init runtime_code_page_mkexec(void)
{
efi_memory_desc_t *md;
void *p;
- u64 addr, npages;
/* Make EFI runtime service code area executable */
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -481,10 +484,7 @@ static void __init runtime_code_page_mkexec(void)
if (md->type != EFI_RUNTIME_SERVICES_CODE)
continue;
- addr = md->virt_addr;
- npages = md->num_pages;
- memrange_efi_to_native(&addr, &npages);
- set_memory_x(addr, npages);
+ efi_set_executable(md, true);
}
}
@@ -498,13 +498,42 @@ static void __init runtime_code_page_mkexec(void)
*/
void __init efi_enter_virtual_mode(void)
{
- efi_memory_desc_t *md;
+ efi_memory_desc_t *md, *prev_md = NULL;
efi_status_t status;
unsigned long size;
u64 end, systab, addr, npages, end_pfn;
- void *p, *va;
+ void *p, *va, *new_memmap = NULL;
+ int count = 0;
efi.systab = NULL;
+
+ /* Merge contiguous regions of the same type and attribute */
+ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+ u64 prev_size;
+ md = p;
+
+ if (!prev_md) {
+ prev_md = md;
+ continue;
+ }
+
+ if (prev_md->type != md->type ||
+ prev_md->attribute != md->attribute) {
+ prev_md = md;
+ continue;
+ }
+
+ prev_size = prev_md->num_pages << EFI_PAGE_SHIFT;
+
+ if (md->phys_addr == (prev_md->phys_addr + prev_size)) {
+ prev_md->num_pages += md->num_pages;
+ md->type = EFI_RESERVED_TYPE;
+ md->attribute = 0;
+ continue;
+ }
+ prev_md = md;
+ }
+
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
md = p;
if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -541,15 +570,21 @@ void __init efi_enter_virtual_mode(void)
systab += md->virt_addr - md->phys_addr;
efi.systab = (efi_system_table_t *) (unsigned long) systab;
}
+ new_memmap = krealloc(new_memmap,
+ (count + 1) * memmap.desc_size,
+ GFP_KERNEL);
+ memcpy(new_memmap + (count * memmap.desc_size), md,
+ memmap.desc_size);
+ count++;
}
BUG_ON(!efi.systab);
status = phys_efi_set_virtual_address_map(
- memmap.desc_size * memmap.nr_map,
+ memmap.desc_size * count,
memmap.desc_size,
memmap.desc_version,
- memmap.phys_map);
+ (efi_memory_desc_t *)__pa(new_memmap));
if (status != EFI_SUCCESS) {
printk(KERN_ALERT "Unable to switch EFI into virtual mode "
@@ -572,11 +607,12 @@ void __init efi_enter_virtual_mode(void)
efi.set_variable = virt_efi_set_variable;
efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
efi.reset_system = virt_efi_reset_system;
- efi.set_virtual_address_map = virt_efi_set_virtual_address_map;
+ efi.set_virtual_address_map = NULL;
if (__supported_pte_mask & _PAGE_NX)
runtime_code_page_mkexec();
early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
memmap.map = NULL;
+ kfree(new_memmap);
}
/*
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac0621a7ac3..2649426a790 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -41,22 +41,7 @@
static pgd_t save_pgd __initdata;
static unsigned long efi_flags __initdata;
-static void __init early_mapping_set_exec(unsigned long start,
- unsigned long end,
- int executable)
-{
- unsigned long num_pages;
-
- start &= PMD_MASK;
- end = (end + PMD_SIZE - 1) & PMD_MASK;
- num_pages = (end - start) >> PAGE_SHIFT;
- if (executable)
- set_memory_x((unsigned long)__va(start), num_pages);
- else
- set_memory_nx((unsigned long)__va(start), num_pages);
-}
-
-static void __init early_runtime_code_mapping_set_exec(int executable)
+static void __init early_code_mapping_set_exec(int executable)
{
efi_memory_desc_t *md;
void *p;
@@ -67,11 +52,8 @@ static void __init early_runtime_code_mapping_set_exec(int executable)
/* Make EFI runtime service code area executable */
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
md = p;
- if (md->type == EFI_RUNTIME_SERVICES_CODE) {
- unsigned long end;
- end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
- early_mapping_set_exec(md->phys_addr, end, executable);
- }
+ if (md->type == EFI_RUNTIME_SERVICES_CODE)
+ efi_set_executable(md, executable);
}
}
@@ -79,7 +61,7 @@ void __init efi_call_phys_prelog(void)
{
unsigned long vaddress;
- early_runtime_code_mapping_set_exec(1);
+ early_code_mapping_set_exec(1);
local_irq_save(efi_flags);
vaddress = (unsigned long)__va(0x0UL);
save_pgd = *pgd_offset_k(0x0UL);
@@ -95,7 +77,7 @@ void __init efi_call_phys_epilog(void)
set_pgd(pgd_offset_k(0x0UL), save_pgd);
__flush_tlb_all();
local_irq_restore(efi_flags);
- early_runtime_code_mapping_set_exec(0);
+ early_code_mapping_set_exec(0);
}
void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
@@ -107,8 +89,10 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
return ioremap(phys_addr, size);
last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
- if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
- return NULL;
+ if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
+ unsigned long top = last_map_pfn << PAGE_SHIFT;
+ efi_ioremap(top, size - (top - phys_addr), type);
+ }
return (void __iomem *)__va(phys_addr);
}
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 275dbc19e2c..7000e74b308 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -194,7 +194,7 @@ static unsigned long __init mrst_calibrate_tsc(void)
return 0;
}
-void __init mrst_time_init(void)
+static void __init mrst_time_init(void)
{
sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
switch (mrst_timer_options) {
@@ -216,7 +216,7 @@ void __init mrst_time_init(void)
apbt_time_init();
}
-void __cpuinit mrst_arch_setup(void)
+static void __cpuinit mrst_arch_setup(void)
{
if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
__mrst_cpu_chip = MRST_CPU_CHIP_PENWELL;
diff --git a/arch/x86/platform/olpc/Makefile b/arch/x86/platform/olpc/Makefile
index c2a8cab65e5..81c5e2165c2 100644
--- a/arch/x86/platform/olpc/Makefile
+++ b/arch/x86/platform/olpc/Makefile
@@ -1,4 +1,2 @@
-obj-$(CONFIG_OLPC) += olpc.o
+obj-$(CONFIG_OLPC) += olpc.o olpc_ofw.o olpc_dt.o
obj-$(CONFIG_OLPC_XO1) += olpc-xo1.o
-obj-$(CONFIG_OLPC) += olpc_ofw.o
-obj-$(CONFIG_OF_PROMTREE) += olpc_dt.o
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index edaf3fe8dc5..0060fd59ea0 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -18,6 +18,7 @@
#include <linux/io.h>
#include <linux/string.h>
#include <linux/platform_device.h>
+#include <linux/of.h>
#include <asm/geode.h>
#include <asm/setup.h>
@@ -187,41 +188,43 @@ err:
}
EXPORT_SYMBOL_GPL(olpc_ec_cmd);
-static bool __init check_ofw_architecture(void)
+static bool __init check_ofw_architecture(struct device_node *root)
{
- size_t propsize;
- char olpc_arch[5];
- const void *args[] = { NULL, "architecture", olpc_arch, (void *)5 };
- void *res[] = { &propsize };
+ const char *olpc_arch;
+ int propsize;
- if (olpc_ofw("getprop", args, res)) {
- printk(KERN_ERR "ofw: getprop call failed!\n");
- return false;
- }
+ olpc_arch = of_get_property(root, "architecture", &propsize);
return propsize == 5 && strncmp("OLPC", olpc_arch, 5) == 0;
}
-static u32 __init get_board_revision(void)
+static u32 __init get_board_revision(struct device_node *root)
{
- size_t propsize;
- __be32 rev;
- const void *args[] = { NULL, "board-revision-int", &rev, (void *)4 };
- void *res[] = { &propsize };
-
- if (olpc_ofw("getprop", args, res) || propsize != 4) {
- printk(KERN_ERR "ofw: getprop call failed!\n");
- return cpu_to_be32(0);
- }
- return be32_to_cpu(rev);
+ int propsize;
+ const __be32 *rev;
+
+ rev = of_get_property(root, "board-revision-int", &propsize);
+ if (propsize != 4)
+ return 0;
+
+ return be32_to_cpu(*rev);
}
static bool __init platform_detect(void)
{
- if (!check_ofw_architecture())
+ struct device_node *root = of_find_node_by_path("/");
+ bool success;
+
+ if (!root)
return false;
- olpc_platform_info.flags |= OLPC_F_PRESENT;
- olpc_platform_info.boardrev = get_board_revision();
- return true;
+
+ success = check_ofw_architecture(root);
+ if (success) {
+ olpc_platform_info.boardrev = get_board_revision(root);
+ olpc_platform_info.flags |= OLPC_F_PRESENT;
+ }
+
+ of_node_put(root);
+ return success;
}
static int __init add_xo1_platform_devices(void)
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index 044bda5b317..d39f63d017d 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -19,7 +19,9 @@
#include <linux/kernel.h>
#include <linux/bootmem.h>
#include <linux/of.h>
+#include <linux/of_platform.h>
#include <linux/of_pdt.h>
+#include <asm/olpc.h>
#include <asm/olpc_ofw.h>
static phandle __init olpc_dt_getsibling(phandle node)
@@ -180,3 +182,20 @@ void __init olpc_dt_build_devicetree(void)
pr_info("PROM DT: Built device tree with %u bytes of memory.\n",
prom_early_allocated);
}
+
+/* A list of DT node/bus matches that we want to expose as platform devices */
+static struct of_device_id __initdata of_ids[] = {
+ { .compatible = "olpc,xo1-battery" },
+ { .compatible = "olpc,xo1-dcon" },
+ { .compatible = "olpc,xo1-rtc" },
+ {},
+};
+
+static int __init olpc_create_platform_devices(void)
+{
+ if (machine_is_olpc())
+ return of_platform_bus_probe(NULL, of_ids, NULL);
+ else
+ return 0;
+}
+device_initcall(olpc_create_platform_devices);
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 7cb6424317f..c58e0ea39ef 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -699,16 +699,17 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
unsigned long va, unsigned int cpu)
{
- int tcpu;
- int uvhub;
int locals = 0;
int remotes = 0;
int hubs = 0;
+ int tcpu;
+ int tpnode;
struct bau_desc *bau_desc;
struct cpumask *flush_mask;
struct ptc_stats *stat;
struct bau_control *bcp;
struct bau_control *tbcp;
+ struct hub_and_pnode *hpp;
/* kernel was booted 'nobau' */
if (nobau)
@@ -750,11 +751,18 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu;
bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
- /* cpu statistics */
for_each_cpu(tcpu, flush_mask) {
- uvhub = uv_cpu_to_blade_id(tcpu);
- bau_uvhub_set(uvhub, &bau_desc->distribution);
- if (uvhub == bcp->uvhub)
+ /*
+ * The distribution vector is a bit map of pnodes, relative
+ * to the partition base pnode (and the partition base nasid
+ * in the header).
+ * Translate cpu to pnode and hub using an array stored
+ * in local memory.
+ */
+ hpp = &bcp->socket_master->target_hub_and_pnode[tcpu];
+ tpnode = hpp->pnode - bcp->partition_base_pnode;
+ bau_uvhub_set(tpnode, &bau_desc->distribution);
+ if (hpp->uvhub == bcp->uvhub)
locals++;
else
remotes++;
@@ -855,7 +863,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
* an interrupt, but causes an error message to be returned to
* the sender.
*/
-static void uv_enable_timeouts(void)
+static void __init uv_enable_timeouts(void)
{
int uvhub;
int nuvhubs;
@@ -1326,10 +1334,10 @@ static int __init uv_ptc_init(void)
}
/*
- * initialize the sending side's sending buffers
+ * Initialize the sending side's sending buffers.
*/
static void
-uv_activation_descriptor_init(int node, int pnode)
+uv_activation_descriptor_init(int node, int pnode, int base_pnode)
{
int i;
int cpu;
@@ -1352,11 +1360,11 @@ uv_activation_descriptor_init(int node, int pnode)
n = pa >> uv_nshift;
m = pa & uv_mmask;
+ /* the 14-bit pnode */
uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
(n << UV_DESC_BASE_PNODE_SHIFT | m));
-
/*
- * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+ * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
* cpu even though we only use the first one; one descriptor can
* describe a broadcast to 256 uv hubs.
*/
@@ -1365,12 +1373,13 @@ uv_activation_descriptor_init(int node, int pnode)
memset(bd2, 0, sizeof(struct bau_desc));
bd2->header.sw_ack_flag = 1;
/*
- * base_dest_nodeid is the nasid of the first uvhub
- * in the partition. The bit map will indicate uvhub numbers,
- * which are 0-N in a partition. Pnodes are unique system-wide.
+ * The base_dest_nasid set in the message header is the nasid
+ * of the first uvhub in the partition. The bit map will
+ * indicate destination pnode numbers relative to that base.
+ * They may not be consecutive if nasid striding is being used.
*/
- bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode);
- bd2->header.dest_subnodeid = 0x10; /* the LB */
+ bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode);
+ bd2->header.dest_subnodeid = UV_LB_SUBNODEID;
bd2->header.command = UV_NET_ENDPOINT_INTD;
bd2->header.int_both = 1;
/*
@@ -1442,7 +1451,7 @@ uv_payload_queue_init(int node, int pnode)
/*
* Initialization of each UV hub's structures
*/
-static void __init uv_init_uvhub(int uvhub, int vector)
+static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
{
int node;
int pnode;
@@ -1450,11 +1459,11 @@ static void __init uv_init_uvhub(int uvhub, int vector)
node = uvhub_to_first_node(uvhub);
pnode = uv_blade_to_pnode(uvhub);
- uv_activation_descriptor_init(node, pnode);
+ uv_activation_descriptor_init(node, pnode, base_pnode);
uv_payload_queue_init(node, pnode);
/*
- * the below initialization can't be in firmware because the
- * messaging IRQ will be determined by the OS
+ * The below initialization can't be in firmware because the
+ * messaging IRQ will be determined by the OS.
*/
apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits;
uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
@@ -1491,10 +1500,11 @@ calculate_destination_timeout(void)
/*
* initialize the bau_control structure for each cpu
*/
-static int __init uv_init_per_cpu(int nuvhubs)
+static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
{
int i;
int cpu;
+ int tcpu;
int pnode;
int uvhub;
int have_hmaster;
@@ -1528,6 +1538,15 @@ static int __init uv_init_per_cpu(int nuvhubs)
bcp = &per_cpu(bau_control, cpu);
memset(bcp, 0, sizeof(struct bau_control));
pnode = uv_cpu_hub_info(cpu)->pnode;
+ if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) {
+ printk(KERN_EMERG
+ "cpu %d pnode %d-%d beyond %d; BAU disabled\n",
+ cpu, pnode, base_part_pnode,
+ UV_DISTRIBUTION_SIZE);
+ return 1;
+ }
+ bcp->osnode = cpu_to_node(cpu);
+ bcp->partition_base_pnode = uv_partition_base_pnode;
uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
*(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8));
bdp = &uvhub_descs[uvhub];
@@ -1536,7 +1555,7 @@ static int __init uv_init_per_cpu(int nuvhubs)
bdp->pnode = pnode;
/* kludge: 'assuming' one node per socket, and assuming that
disabling a socket just leaves a gap in node numbers */
- socket = (cpu_to_node(cpu) & 1);
+ socket = bcp->osnode & 1;
bdp->socket_mask |= (1 << socket);
sdp = &bdp->socket[socket];
sdp->cpu_number[sdp->num_cpus] = cpu;
@@ -1585,6 +1604,20 @@ static int __init uv_init_per_cpu(int nuvhubs)
nextsocket:
socket++;
socket_mask = (socket_mask >> 1);
+ /* each socket gets a local array of pnodes/hubs */
+ bcp = smaster;
+ bcp->target_hub_and_pnode = kmalloc_node(
+ sizeof(struct hub_and_pnode) *
+ num_possible_cpus(), GFP_KERNEL, bcp->osnode);
+ memset(bcp->target_hub_and_pnode, 0,
+ sizeof(struct hub_and_pnode) *
+ num_possible_cpus());
+ for_each_present_cpu(tcpu) {
+ bcp->target_hub_and_pnode[tcpu].pnode =
+ uv_cpu_hub_info(tcpu)->pnode;
+ bcp->target_hub_and_pnode[tcpu].uvhub =
+ uv_cpu_hub_info(tcpu)->numa_blade_id;
+ }
}
}
kfree(uvhub_descs);
@@ -1637,21 +1670,22 @@ static int __init uv_bau_init(void)
spin_lock_init(&disable_lock);
congested_cycles = microsec_2_cycles(congested_response_us);
- if (uv_init_per_cpu(nuvhubs)) {
- nobau = 1;
- return 0;
- }
-
uv_partition_base_pnode = 0x7fffffff;
- for (uvhub = 0; uvhub < nuvhubs; uvhub++)
+ for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
if (uv_blade_nr_possible_cpus(uvhub) &&
(uv_blade_to_pnode(uvhub) < uv_partition_base_pnode))
uv_partition_base_pnode = uv_blade_to_pnode(uvhub);
+ }
+
+ if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) {
+ nobau = 1;
+ return 0;
+ }
vector = UV_BAU_MESSAGE;
for_each_possible_blade(uvhub)
if (uv_blade_nr_possible_cpus(uvhub))
- uv_init_uvhub(uvhub, vector);
+ uv_init_uvhub(uvhub, vector, uv_partition_base_pnode);
uv_enable_timeouts();
alloc_intr_gate(vector, uv_bau_message_intr1);
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 9daf5d1af9f..0eb90184515 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -40,7 +40,6 @@ static struct clocksource clocksource_uv = {
.rating = 400,
.read = uv_read_rtc,
.mask = (cycle_t)UVH_RTC_REAL_TIME_CLOCK_MASK,
- .shift = 10,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
@@ -372,14 +371,11 @@ static __init int uv_rtc_setup_clock(void)
if (!is_uv_system())
return -ENODEV;
- clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second,
- clocksource_uv.shift);
-
/* If single blade, prefer tsc */
if (uv_num_possible_blades() == 1)
clocksource_uv.rating = 250;
- rc = clocksource_register(&clocksource_uv);
+ rc = clocksource_register_hz(&clocksource_uv, sn_rtc_cycles_per_second);
if (rc)
printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc);
else
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e3c6a06cf72..dd7b88f2ec7 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -235,7 +235,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
*dx &= maskedx;
}
-static __init void xen_init_cpuid_mask(void)
+static void __init xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
unsigned int xsave_mask;
@@ -400,7 +400,7 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
/*
* load_gdt for early boot, when the gdt is only mapped once
*/
-static __init void xen_load_gdt_boot(const struct desc_ptr *dtr)
+static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
@@ -662,7 +662,7 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
* Version of write_gdt_entry for use at early boot-time needed to
* update an entry as simply as possible.
*/
-static __init void xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
+static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
const void *desc, int type)
{
switch (type) {
@@ -933,18 +933,18 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
return ret;
}
-static const struct pv_info xen_info __initdata = {
+static const struct pv_info xen_info __initconst = {
.paravirt_enabled = 1,
.shared_kernel_pmd = 0,
.name = "Xen",
};
-static const struct pv_init_ops xen_init_ops __initdata = {
+static const struct pv_init_ops xen_init_ops __initconst = {
.patch = xen_patch,
};
-static const struct pv_cpu_ops xen_cpu_ops __initdata = {
+static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.cpuid = xen_cpuid,
.set_debugreg = xen_set_debugreg,
@@ -1004,7 +1004,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
.end_context_switch = xen_end_context_switch,
};
-static const struct pv_apic_ops xen_apic_ops __initdata = {
+static const struct pv_apic_ops xen_apic_ops __initconst = {
#ifdef CONFIG_X86_LOCAL_APIC
.startup_ipi_hook = paravirt_nop,
#endif
@@ -1055,7 +1055,7 @@ int xen_panic_handler_init(void)
return 0;
}
-static const struct machine_ops __initdata xen_machine_ops = {
+static const struct machine_ops xen_machine_ops __initconst = {
.restart = xen_restart,
.halt = xen_machine_halt,
.power_off = xen_machine_halt,
@@ -1332,7 +1332,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = {
+static struct notifier_block xen_hvm_cpu_notifier __cpuinitdata = {
.notifier_call = xen_hvm_cpu_notify,
};
@@ -1381,7 +1381,7 @@ bool xen_hvm_need_lapic(void)
}
EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
-const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = {
+const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
.name = "Xen HVM",
.detect = xen_hvm_platform,
.init_platform = xen_hvm_guest_init,
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 6a6fe893964..8bbb465b6f0 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -113,7 +113,7 @@ static void xen_halt(void)
xen_safe_halt();
}
-static const struct pv_irq_ops xen_irq_ops __initdata = {
+static const struct pv_irq_ops xen_irq_ops __initconst = {
.save_fl = PV_CALLEE_SAVE(xen_save_fl),
.restore_fl = PV_CALLEE_SAVE(xen_restore_fl),
.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index aef7af92b28..02d75246037 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1054,7 +1054,7 @@ void xen_mm_pin_all(void)
* that's before we have page structures to store the bits. So do all
* the book-keeping now.
*/
-static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page,
+static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
enum pt_level level)
{
SetPagePinned(page);
@@ -1187,7 +1187,7 @@ static void drop_other_mm_ref(void *info)
active_mm = percpu_read(cpu_tlbstate.active_mm);
- if (active_mm == mm)
+ if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
leave_mm(smp_processor_id());
/* If this cpu still has a stale cr3 reference, then make sure
@@ -1271,13 +1271,27 @@ void xen_exit_mmap(struct mm_struct *mm)
spin_unlock(&mm->page_table_lock);
}
-static __init void xen_pagetable_setup_start(pgd_t *base)
+static void __init xen_pagetable_setup_start(pgd_t *base)
{
}
+static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+{
+ /* reserve the range used */
+ native_pagetable_reserve(start, end);
+
+ /* set as RW the rest */
+ printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
+ PFN_PHYS(pgt_buf_top));
+ while (end < PFN_PHYS(pgt_buf_top)) {
+ make_lowmem_page_readwrite(__va(end));
+ end += PAGE_SIZE;
+ }
+}
+
static void xen_post_allocator_init(void);
-static __init void xen_pagetable_setup_done(pgd_t *base)
+static void __init xen_pagetable_setup_done(pgd_t *base)
{
xen_setup_shared_info();
xen_post_allocator_init();
@@ -1474,7 +1488,7 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
}
#ifdef CONFIG_X86_32
-static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
{
/* If there's an existing pte, then don't allow _PAGE_RW to be set */
if (pte_val_ma(*ptep) & _PAGE_PRESENT)
@@ -1484,7 +1498,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
return pte;
}
#else /* CONFIG_X86_64 */
-static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
@@ -1495,7 +1509,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
* it is RO.
*/
if (((!is_early_ioremap_ptep(ptep) &&
- pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+ pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
(is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
pte = pte_wrprotect(pte);
@@ -1505,7 +1519,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
/* Init-time set_pte while constructing initial pagetables, which
doesn't allow RO pagetable pages to be remapped RW */
-static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
{
pte = mask_rw_pte(ptep, pte);
@@ -1523,7 +1537,7 @@ static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
/* Early in boot, while setting up the initial pagetable, assume
everything is pinned. */
-static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
+static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
{
#ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */
@@ -1533,7 +1547,7 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
}
/* Used for pmd and pud */
-static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
+static void __init xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
{
#ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */
@@ -1543,13 +1557,13 @@ static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
/* Early release_pte assumes that all pts are pinned, since there's
only init_mm and anything attached to that is pinned. */
-static __init void xen_release_pte_init(unsigned long pfn)
+static void __init xen_release_pte_init(unsigned long pfn)
{
pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
-static __init void xen_release_pmd_init(unsigned long pfn)
+static void __init xen_release_pmd_init(unsigned long pfn)
{
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
@@ -1675,7 +1689,7 @@ static void set_page_prot(void *addr, pgprot_t prot)
BUG();
}
-static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
+static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
unsigned pmdidx, pteidx;
unsigned ident_pte;
@@ -1758,7 +1772,7 @@ static void convert_pfn_mfn(void *v)
* of the physical mapping once some sort of allocator has been set
* up.
*/
-__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
unsigned long max_pfn)
{
pud_t *l3;
@@ -1829,7 +1843,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
-static __init void xen_write_cr3_init(unsigned long cr3)
+static void __init xen_write_cr3_init(unsigned long cr3)
{
unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
@@ -1866,7 +1880,7 @@ static __init void xen_write_cr3_init(unsigned long cr3)
pv_mmu_ops.write_cr3 = &xen_write_cr3;
}
-__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
unsigned long max_pfn)
{
pmd_t *kernel_pmd;
@@ -1972,7 +1986,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
#endif
}
-__init void xen_ident_map_ISA(void)
+void __init xen_ident_map_ISA(void)
{
unsigned long pa;
@@ -1995,7 +2009,7 @@ __init void xen_ident_map_ISA(void)
xen_flush_tlb();
}
-static __init void xen_post_allocator_init(void)
+static void __init xen_post_allocator_init(void)
{
#ifdef CONFIG_XEN_DEBUG
pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
@@ -2032,7 +2046,7 @@ static void xen_leave_lazy_mmu(void)
preempt_enable();
}
-static const struct pv_mmu_ops xen_mmu_ops __initdata = {
+static const struct pv_mmu_ops xen_mmu_ops __initconst = {
.read_cr2 = xen_read_cr2,
.write_cr2 = xen_write_cr2,
@@ -2105,6 +2119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
void __init xen_init_mmu_ops(void)
{
+ x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
pv_mmu_ops = xen_mmu_ops;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 141eb0de8b0..58efeb9d544 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -522,11 +522,20 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
/* Boundary cross-over for the edges: */
if (idx) {
unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ unsigned long *mid_mfn_p;
p2m_init(p2m);
p2m_top[topidx][mididx] = p2m;
+ /* For save/restore we need to MFN of the P2M saved */
+
+ mid_mfn_p = p2m_top_mfn_p[topidx];
+ WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+ "P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+ topidx, mididx);
+ mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
}
return idx != 0;
}
@@ -549,12 +558,29 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
{
unsigned topidx = p2m_top_index(pfn);
- if (p2m_top[topidx] == p2m_mid_missing) {
- unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ unsigned long *mid_mfn_p;
+ unsigned long **mid;
+
+ mid = p2m_top[topidx];
+ mid_mfn_p = p2m_top_mfn_p[topidx];
+ if (mid == p2m_mid_missing) {
+ mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_init(mid);
p2m_top[topidx] = mid;
+
+ BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
+ }
+ /* And the save/restore P2M tables.. */
+ if (mid_mfn_p == p2m_mid_missing_mfn) {
+ mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_mfn_init(mid_mfn_p);
+
+ p2m_top_mfn_p[topidx] = mid_mfn_p;
+ p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
+ /* Note: we don't set mid_mfn_p[midix] here,
+ * look in __early_alloc_p2m */
}
}
@@ -650,7 +676,7 @@ static unsigned long mfn_hash(unsigned long mfn)
}
/* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page)
+int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
{
unsigned long flags;
unsigned long pfn;
@@ -662,7 +688,6 @@ int m2p_add_override(unsigned long mfn, struct page *page)
if (!PageHighMem(page)) {
address = (unsigned long)__va(pfn << PAGE_SHIFT);
ptep = lookup_address(address, &level);
-
if (WARN(ptep == NULL || level != PG_LEVEL_4K,
"m2p_add_override: pfn %lx not mapped", pfn))
return -EINVAL;
@@ -674,18 +699,17 @@ int m2p_add_override(unsigned long mfn, struct page *page)
if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
return -ENOMEM;
- if (!PageHighMem(page))
+ if (clear_pte && !PageHighMem(page))
/* Just zap old mapping for now */
pte_clear(&init_mm, address, ptep);
-
spin_lock_irqsave(&m2p_override_lock, flags);
list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]);
spin_unlock_irqrestore(&m2p_override_lock, flags);
return 0;
}
-
-int m2p_remove_override(struct page *page)
+EXPORT_SYMBOL_GPL(m2p_add_override);
+int m2p_remove_override(struct page *page, bool clear_pte)
{
unsigned long flags;
unsigned long mfn;
@@ -713,7 +737,7 @@ int m2p_remove_override(struct page *page)
spin_unlock_irqrestore(&m2p_override_lock, flags);
set_phys_to_machine(pfn, page->index);
- if (!PageHighMem(page))
+ if (clear_pte && !PageHighMem(page))
set_pte_at(&init_mm, address, ptep,
pfn_pte(pfn, PAGE_KERNEL));
/* No tlb flush necessary because the caller already
@@ -721,6 +745,7 @@ int m2p_remove_override(struct page *page)
return 0;
}
+EXPORT_SYMBOL_GPL(m2p_remove_override);
struct page *m2p_find_override(unsigned long mfn)
{
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 90bac0aac3a..be1a464f6d6 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -50,7 +50,7 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
*/
#define EXTRA_MEM_RATIO (10)
-static __init void xen_add_extra_mem(unsigned long pages)
+static void __init xen_add_extra_mem(unsigned long pages)
{
unsigned long pfn;
@@ -166,7 +166,7 @@ static unsigned long __init xen_set_identity(const struct e820entry *list,
if (last > end)
continue;
- if (entry->type == E820_RAM) {
+ if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) {
if (start > start_pci)
identity += set_phys_range_identity(
PFN_UP(start_pci), PFN_DOWN(start));
@@ -227,7 +227,11 @@ char * __init xen_memory_setup(void)
memcpy(map_raw, map, sizeof(map));
e820.nr_map = 0;
+#ifdef CONFIG_X86_32
+ xen_extra_mem_start = mem_end;
+#else
xen_extra_mem_start = max((1ULL << 32), mem_end);
+#endif
for (i = 0; i < memmap.nr_entries; i++) {
unsigned long long end;
@@ -336,7 +340,7 @@ static void __init fiddle_vdso(void)
#endif
}
-static __cpuinit int register_callback(unsigned type, const void *func)
+static int __cpuinit register_callback(unsigned type, const void *func)
{
struct callback_register callback = {
.type = type,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 30612441ed9..41038c01de4 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -46,18 +46,17 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
/*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
*/
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
inc_irq_stat(irq_resched_count);
+ scheduler_ipi();
return IRQ_HANDLED;
}
-static __cpuinit void cpu_bringup(void)
+static void __cpuinit cpu_bringup(void)
{
int cpu = smp_processor_id();
@@ -85,7 +84,7 @@ static __cpuinit void cpu_bringup(void)
wmb(); /* make sure everything is out */
}
-static __cpuinit void cpu_bringup_and_idle(void)
+static void __cpuinit cpu_bringup_and_idle(void)
{
cpu_bringup();
cpu_idle();
@@ -242,7 +241,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
}
}
-static __cpuinit int
+static int __cpuinit
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
struct vcpu_guest_context *ctxt;
@@ -486,7 +485,7 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}
-static const struct smp_ops xen_smp_ops __initdata = {
+static const struct smp_ops xen_smp_ops __initconst = {
.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
.smp_prepare_cpus = xen_smp_prepare_cpus,
.smp_cpus_done = xen_smp_cpus_done,
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 2e2d370a47b..5158c505bef 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -26,8 +26,6 @@
#include "xen-ops.h"
-#define XEN_SHIFT 22
-
/* Xen may fire a timer up to this many ns early */
#define TIMER_SLOP 100000
#define NS_PER_TICK (1000000000LL / HZ)
@@ -211,8 +209,6 @@ static struct clocksource xen_clocksource __read_mostly = {
.rating = 400,
.read = xen_clocksource_get_cycles,
.mask = ~0,
- .mult = 1<<XEN_SHIFT, /* time directly in nanoseconds */
- .shift = XEN_SHIFT,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
@@ -439,16 +435,16 @@ void xen_timer_resume(void)
}
}
-static const struct pv_time_ops xen_time_ops __initdata = {
+static const struct pv_time_ops xen_time_ops __initconst = {
.sched_clock = xen_clocksource_read,
};
-static __init void xen_time_init(void)
+static void __init xen_time_init(void)
{
int cpu = smp_processor_id();
struct timespec tp;
- clocksource_register(&xen_clocksource);
+ clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC);
if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {
/* Successfully turned off 100Hz tick, so we have the
@@ -468,7 +464,7 @@ static __init void xen_time_init(void)
xen_setup_cpu_clockevents();
}
-__init void xen_init_time_ops(void)
+void __init xen_init_time_ops(void)
{
pv_time_ops = xen_time_ops;
@@ -490,7 +486,7 @@ static void xen_hvm_setup_cpu_clockevents(void)
xen_setup_cpu_clockevents();
}
-__init void xen_hvm_init_time_ops(void)
+void __init xen_hvm_init_time_ops(void)
{
/* vector callback is needed otherwise we cannot receive interrupts
* on cpu > 0 and at this point we don't know how many cpus are
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 3112f55638c..97dfdc8757b 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -74,7 +74,7 @@ static inline void xen_hvm_smp_init(void) {}
#ifdef CONFIG_PARAVIRT_SPINLOCKS
void __init xen_init_spinlocks(void);
-__cpuinit void xen_init_lock_cpu(int cpu);
+void __cpuinit xen_init_lock_cpu(int cpu);
void xen_uninit_lock_cpu(int cpu);
#else
static inline void xen_init_spinlocks(void)