summaryrefslogtreecommitdiff
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.cpu73
-rw-r--r--arch/x86/Makefile_32.cpu1
-rw-r--r--arch/x86/boot/.gitignore1
-rw-r--r--arch/x86/boot/compressed/eboot.c120
-rw-r--r--arch/x86/boot/header.S3
-rw-r--r--arch/x86/ia32/ia32_aout.c5
-rw-r--r--arch/x86/ia32/ia32entry.S7
-rw-r--r--arch/x86/ia32/sys_ia32.c11
-rw-r--r--arch/x86/include/asm/Kbuild3
-rw-r--r--arch/x86/include/asm/atomic.h16
-rw-r--r--arch/x86/include/asm/bootparam.h1
-rw-r--r--arch/x86/include/asm/cmpxchg_32.h55
-rw-r--r--arch/x86/include/asm/context_tracking.h (renamed from arch/x86/include/asm/rcu.h)15
-rw-r--r--arch/x86/include/asm/cpu.h4
-rw-r--r--arch/x86/include/asm/cpufeature.h7
-rw-r--r--arch/x86/include/asm/device.h3
-rw-r--r--arch/x86/include/asm/elf.h6
-rw-r--r--arch/x86/include/asm/fpu-internal.h15
-rw-r--r--arch/x86/include/asm/futex.h12
-rw-r--r--arch/x86/include/asm/local.h18
-rw-r--r--arch/x86/include/asm/mman.h3
-rw-r--r--arch/x86/include/asm/module.h2
-rw-r--r--arch/x86/include/asm/msr-index.h2
-rw-r--r--arch/x86/include/asm/numachip/numachip.h19
-rw-r--r--arch/x86/include/asm/pci.h12
-rw-r--r--arch/x86/include/asm/percpu.h3
-rw-r--r--arch/x86/include/asm/processor.h37
-rw-r--r--arch/x86/include/asm/ptrace.h24
-rw-r--r--arch/x86/include/asm/signal.h2
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/swab.h29
-rw-r--r--arch/x86/include/asm/sys_ia32.h2
-rw-r--r--arch/x86/include/asm/syscalls.h9
-rw-r--r--arch/x86/include/asm/tlbflush.h3
-rw-r--r--arch/x86/include/asm/trace_clock.h20
-rw-r--r--arch/x86/include/asm/uaccess.h42
-rw-r--r--arch/x86/include/asm/unistd.h3
-rw-r--r--arch/x86/include/asm/xen/hypercall.h21
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h1
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c6
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/apic/apic.c73
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c35
-rw-r--r--arch/x86/kernel/cpu/amd.c26
-rw-r--r--arch/x86/kernel/cpu/bugs.c41
-rw-r--r--arch/x86/kernel/cpu/common.c14
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c75
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c31
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c11
-rw-r--r--arch/x86/kernel/cpu/perf_event.c121
-rw-r--r--arch/x86/kernel/cpu/perf_event.h5
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c2
-rw-r--r--arch/x86/kernel/entry_32.S18
-rw-r--r--arch/x86/kernel/entry_64.S79
-rw-r--r--arch/x86/kernel/head_32.S22
-rw-r--r--arch/x86/kernel/head_64.S16
-rw-r--r--arch/x86/kernel/hpet.c4
-rw-r--r--arch/x86/kernel/i387.c6
-rw-r--r--arch/x86/kernel/microcode_amd.c8
-rw-r--r--arch/x86/kernel/process.c69
-rw-r--r--arch/x86/kernel/process_32.c12
-rw-r--r--arch/x86/kernel/process_64.c10
-rw-r--r--arch/x86/kernel/ptrace.c42
-rw-r--r--arch/x86/kernel/rtc.c6
-rw-r--r--arch/x86/kernel/setup.c4
-rw-r--r--arch/x86/kernel/signal.c5
-rw-r--r--arch/x86/kernel/smpboot.c156
-rw-r--r--arch/x86/kernel/sys_x86_64.c151
-rw-r--r--arch/x86/kernel/topology.c101
-rw-r--r--arch/x86/kernel/trace_clock.c21
-rw-r--r--arch/x86/kernel/traps.c2
-rw-r--r--arch/x86/kernel/tsc.c6
-rw-r--r--arch/x86/kernel/uprobes.c54
-rw-r--r--arch/x86/kernel/vm86_32.c2
-rw-r--r--arch/x86/kvm/cpuid.h3
-rw-r--r--arch/x86/kvm/emulate.c3
-rw-r--r--arch/x86/kvm/vmx.c11
-rw-r--r--arch/x86/kvm/x86.c63
-rw-r--r--arch/x86/lib/Makefile1
-rw-r--r--arch/x86/lib/cmpxchg.c54
-rw-r--r--arch/x86/lib/copy_page_64.S120
-rw-r--r--arch/x86/lib/usercopy_32.c57
-rw-r--r--arch/x86/mm/fault.c25
-rw-r--r--arch/x86/mm/hugetlbpage.c130
-rw-r--r--arch/x86/mm/init_32.c5
-rw-r--r--arch/x86/mm/init_64.c4
-rw-r--r--arch/x86/mm/pgtable.c2
-rw-r--r--arch/x86/mm/tlb.c10
-rw-r--r--arch/x86/net/bpf_jit_comp.c21
-rw-r--r--arch/x86/pci/Makefile1
-rw-r--r--arch/x86/pci/acpi.c46
-rw-r--r--arch/x86/pci/ce4100.c13
-rw-r--r--arch/x86/pci/common.c32
-rw-r--r--arch/x86/pci/numachip.c129
-rw-r--r--arch/x86/platform/ce4100/ce4100.c27
-rw-r--r--arch/x86/power/cpu.c82
-rw-r--r--arch/x86/syscalls/syscall_32.tbl6
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk6
-rw-r--r--arch/x86/um/Kconfig3
-rw-r--r--arch/x86/um/shared/sysdep/syscalls.h2
-rw-r--r--arch/x86/um/sys_call_table_32.c3
-rw-r--r--arch/x86/um/syscalls_32.c15
-rw-r--r--arch/x86/vdso/vma.c2
-rw-r--r--arch/x86/xen/Kconfig2
-rw-r--r--arch/x86/xen/mmu.c21
112 files changed, 1653 insertions, 1182 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 46c3bff..65a872b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -69,8 +69,8 @@ config X86
select HAVE_PERF_USER_STACK_DUMP
select HAVE_DEBUG_KMEMLEAK
select ANON_INODES
- select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
- select HAVE_CMPXCHG_LOCAL if !M386
+ select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+ select HAVE_CMPXCHG_LOCAL
select HAVE_CMPXCHG_DOUBLE
select HAVE_ARCH_KMEMCHECK
select HAVE_USER_RETURN_NOTIFIER
@@ -106,12 +106,13 @@ config X86
select KTIME_SCALAR if X86_32
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
- select HAVE_RCU_USER_QS if X86_64
+ select HAVE_CONTEXT_TRACKING if X86_64
select HAVE_IRQ_TIME_ACCOUNTING
select GENERIC_KERNEL_THREAD
select GENERIC_KERNEL_EXECVE
select MODULES_USE_ELF_REL if X86_32
select MODULES_USE_ELF_RELA if X86_64
+ select CLONE_BACKWARDS if X86_32
config INSTRUCTION_DECODER
def_bool y
@@ -171,13 +172,8 @@ config ARCH_MAY_HAVE_PC_FDC
def_bool y
depends on ISA_DMA_API
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
- depends on !X86_XADD
-
config RWSEM_XCHGADD_ALGORITHM
def_bool y
- depends on X86_XADD
config GENERIC_CALIBRATE_DELAY
def_bool y
@@ -310,7 +306,7 @@ config X86_X2APIC
If you don't know what to do here, say N.
config X86_MPPARSE
- bool "Enable MPS table" if ACPI
+ bool "Enable MPS table" if ACPI || SFI
default y
depends on X86_LOCAL_APIC
---help---
@@ -374,6 +370,7 @@ config X86_NUMACHIP
depends on NUMA
depends on SMP
depends on X86_X2APIC
+ depends on PCI_MMCONFIG
---help---
Adds support for Numascale NumaChip large-SMP systems. Needed to
enable more than ~168 cores.
@@ -1100,7 +1097,7 @@ config HIGHMEM4G
config HIGHMEM64G
bool "64GB"
- depends on !M386 && !M486
+ depends on !M486
select X86_PAE
---help---
Select this if you have a 32-bit processor and more than 4
@@ -1698,6 +1695,50 @@ config HOTPLUG_CPU
automatically on SMP systems. )
Say N if you want to disable CPU hotplug.
+config BOOTPARAM_HOTPLUG_CPU0
+ bool "Set default setting of cpu0_hotpluggable"
+ default n
+ depends on HOTPLUG_CPU && EXPERIMENTAL
+ ---help---
+ Set whether default state of cpu0_hotpluggable is on or off.
+
+ Say Y here to enable CPU0 hotplug by default. If this switch
+ is turned on, there is no need to give cpu0_hotplug kernel
+ parameter and the CPU0 hotplug feature is enabled by default.
+
+ Please note: there are two known CPU0 dependencies if you want
+ to enable the CPU0 hotplug feature either by this switch or by
+ cpu0_hotplug kernel parameter.
+
+ First, resume from hibernate or suspend always starts from CPU0.
+ So hibernate and suspend are prevented if CPU0 is offline.
+
+ Second dependency is PIC interrupts always go to CPU0. CPU0 can not
+ offline if any interrupt can not migrate out of CPU0. There may
+ be other CPU0 dependencies.
+
+ Please make sure the dependencies are under your control before
+ you enable this feature.
+
+ Say N if you don't want to enable CPU0 hotplug feature by default.
+ You still can enable the CPU0 hotplug feature at boot by kernel
+ parameter cpu0_hotplug.
+
+config DEBUG_HOTPLUG_CPU0
+ def_bool n
+ prompt "Debug CPU0 hotplug"
+ depends on HOTPLUG_CPU && EXPERIMENTAL
+ ---help---
+ Enabling this option offlines CPU0 (if CPU0 can be offlined) as
+ soon as possible and boots up userspace with CPU0 offlined. User
+ can online CPU0 back after boot time.
+
+ To debug CPU0 hotplug, you need to enable CPU0 offline/online
+ feature by either turning on CONFIG_BOOTPARAM_HOTPLUG_CPU0 during
+ compilation or giving cpu0_hotplug kernel parameter at boot.
+
+ If unsure, say N.
+
config COMPAT_VDSO
def_bool y
prompt "Compat VDSO support"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index f3b86d0..c026cca 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -4,23 +4,24 @@ choice
default M686 if X86_32
default GENERIC_CPU if X86_64
-config M386
- bool "386"
- depends on X86_32 && !UML
+config M486
+ bool "486"
+ depends on X86_32
---help---
- This is the processor type of your CPU. This information is used for
- optimizing purposes. In order to compile a kernel that can run on
- all x86 CPU types (albeit not optimally fast), you can specify
- "386" here.
+ This is the processor type of your CPU. This information is
+ used for optimizing purposes. In order to compile a kernel
+ that can run on all supported x86 CPU types (albeit not
+ optimally fast), you can specify "486" here.
+
+ Note that the 386 is no longer supported, this includes
+ AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI 486DLC/DLC2,
+ UMC 486SX-S and the NexGen Nx586.
The kernel will not necessarily run on earlier architectures than
the one you have chosen, e.g. a Pentium optimized kernel will run on
a PPro, but not necessarily on a i486.
Here are the settings recommended for greatest speed:
- - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI
- 486DLC/DLC2, and UMC 486SX-S. Only "386" kernels will run on a 386
- class machine.
- "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or
SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
- "586" for generic Pentium CPUs lacking the TSC
@@ -43,16 +44,7 @@ config M386
- "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
- "VIA C7" for VIA C7.
- If you don't know what to do, choose "386".
-
-config M486
- bool "486"
- depends on X86_32
- ---help---
- Select this for a 486 series processor, either Intel or one of the
- compatible processors from AMD, Cyrix, IBM, or Intel. Includes DX,
- DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or
- U5S.
+ If you don't know what to do, choose "486".
config M586
bool "586/K5/5x86/6x86/6x86MX"
@@ -305,24 +297,16 @@ config X86_INTERNODE_CACHE_SHIFT
default "12" if X86_VSMP
default X86_L1_CACHE_SHIFT
-config X86_CMPXCHG
- def_bool y
- depends on X86_64 || (X86_32 && !M386)
-
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 MELAN || M486 || M386 || MGEODEGX1
+ default "4" if MELAN || M486 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-config X86_XADD
- def_bool y
- depends on !M386
-
config X86_PPRO_FENCE
bool "PentiumPro memory ordering errata workaround"
- depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1
+ depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1
---help---
Old PentiumPro multiprocessor systems had errata that could cause
memory operations to violate the x86 ordering standard in rare cases.
@@ -335,27 +319,11 @@ config X86_PPRO_FENCE
config X86_F00F_BUG
def_bool y
- depends on M586MMX || M586TSC || M586 || M486 || M386
+ depends on M586MMX || M586TSC || M586 || M486
config X86_INVD_BUG
def_bool y
- depends on M486 || M386
-
-config X86_WP_WORKS_OK
- def_bool y
- depends on !M386
-
-config X86_INVLPG
- def_bool y
- depends on X86_32 && !M386
-
-config X86_BSWAP
- def_bool y
- depends on X86_32 && !M386
-
-config X86_POPAD_OK
- def_bool y
- depends on X86_32 && !M386
+ depends on M486
config X86_ALIGNMENT_16
def_bool y
@@ -412,12 +380,11 @@ config X86_MINIMUM_CPU_FAMILY
default "64" if X86_64
default "6" if X86_32 && X86_P6_NOP
default "5" if X86_32 && X86_CMPXCHG64
- default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK)
- default "3"
+ default "4"
config X86_DEBUGCTLMSR
def_bool y
- depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386) && !UML
+ depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486) && !UML
menuconfig PROCESSOR_SELECT
bool "Supported processor vendors" if EXPERT
@@ -441,7 +408,7 @@ config CPU_SUP_INTEL
config CPU_SUP_CYRIX_32
default y
bool "Support Cyrix processors" if PROCESSOR_SELECT
- depends on M386 || M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
+ depends on M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
---help---
This enables detection, tunings and quirks for Cyrix processors
@@ -495,7 +462,7 @@ config CPU_SUP_TRANSMETA_32
config CPU_SUP_UMC_32
default y
bool "Support UMC processors" if PROCESSOR_SELECT
- depends on M386 || M486 || (EXPERT && !64BIT)
+ depends on M486 || (EXPERT && !64BIT)
---help---
This enables detection, tunings and quirks for UMC processors
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 86cee7b..6647ed4 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -10,7 +10,6 @@ tune = $(call cc-option,-mcpu=$(1),$(2))
endif
align := $(cc-option-align)
-cflags-$(CONFIG_M386) += -march=i386
cflags-$(CONFIG_M486) += -march=i486
cflags-$(CONFIG_M586) += -march=i586
cflags-$(CONFIG_M586TSC) += -march=i586
diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore
index 851fe93..e3cf9f6 100644
--- a/arch/x86/boot/.gitignore
+++ b/arch/x86/boot/.gitignore
@@ -2,7 +2,6 @@ bootsect
bzImage
cpustr.h
mkcpustr
-offsets.h
voffset.h
zoffset.h
setup
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c760e07..b1942e2 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -8,10 +8,13 @@
* ----------------------------------------------------------------------- */
#include <linux/efi.h>
+#include <linux/pci.h>
#include <asm/efi.h>
#include <asm/setup.h>
#include <asm/desc.h>
+#undef memcpy /* Use memcpy from misc.c */
+
#include "eboot.h"
static efi_system_table_t *sys_table;
@@ -243,6 +246,121 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
*size = len;
}
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+ efi_pci_io_protocol *pci;
+ efi_status_t status;
+ void **pci_handle;
+ efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ unsigned long nr_pci, size = 0;
+ int i;
+ struct setup_data *data;
+
+ data = (struct setup_data *)params->hdr.setup_data;
+
+ while (data && data->next)
+ data = (struct setup_data *)data->next;
+
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+ NULL, &size, pci_handle);
+
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, size, &pci_handle);
+
+ if (status != EFI_SUCCESS)
+ return status;
+
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+ NULL, &size, pci_handle);
+ }
+
+ if (status != EFI_SUCCESS)
+ goto free_handle;
+
+ nr_pci = size / sizeof(void *);
+ for (i = 0; i < nr_pci; i++) {
+ void *h = pci_handle[i];
+ uint64_t attributes;
+ struct pci_setup_rom *rom;
+
+ status = efi_call_phys3(sys_table->boottime->handle_protocol,
+ h, &pci_proto, &pci);
+
+ if (status != EFI_SUCCESS)
+ continue;
+
+ if (!pci)
+ continue;
+
+ status = efi_call_phys4(pci->attributes, pci,
+ EfiPciIoAttributeOperationGet, 0,
+ &attributes);
+
+ if (status != EFI_SUCCESS)
+ continue;
+
+ if (!attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM)
+ continue;
+
+ if (!pci->romimage || !pci->romsize)
+ continue;
+
+ size = pci->romsize + sizeof(*rom);
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, size, &rom);
+
+ if (status != EFI_SUCCESS)
+ continue;
+
+ rom->data.type = SETUP_PCI;
+ rom->data.len = size - sizeof(struct setup_data);
+ rom->data.next = 0;
+ rom->pcilen = pci->romsize;
+
+ status = efi_call_phys5(pci->pci.read, pci,
+ EfiPciIoWidthUint16, PCI_VENDOR_ID,
+ 1, &(rom->vendor));
+
+ if (status != EFI_SUCCESS)
+ goto free_struct;
+
+ status = efi_call_phys5(pci->pci.read, pci,
+ EfiPciIoWidthUint16, PCI_DEVICE_ID,
+ 1, &(rom->devid));
+
+ if (status != EFI_SUCCESS)
+ goto free_struct;
+
+ status = efi_call_phys5(pci->get_location, pci,
+ &(rom->segment), &(rom->bus),
+ &(rom->device), &(rom->function));
+
+ if (status != EFI_SUCCESS)
+ goto free_struct;
+
+ memcpy(rom->romdata, pci->romimage, pci->romsize);
+
+ if (data)
+ data->next = (uint64_t)rom;
+ else
+ params->hdr.setup_data = (uint64_t)rom;
+
+ data = (struct setup_data *)rom;
+
+ continue;
+ free_struct:
+ efi_call_phys1(sys_table->boottime->free_pool, rom);
+ }
+
+free_handle:
+ efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
+ return status;
+}
+
/*
* See if we have Graphics Output Protocol
*/
@@ -1026,6 +1144,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
setup_graphics(boot_params);
+ setup_efi_pci(boot_params);
+
status = efi_call_phys3(sys_table->boottime->allocate_pool,
EFI_LOADER_DATA, sizeof(*gdt),
(void **)&gdt);
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 2a01744..8c132a6 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -476,6 +476,3 @@ die:
setup_corrupt:
.byte 7
.string "No setup signature found...\n"
-
- .data
-dummy: .long 0
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 07b3a68..a703af1 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -35,7 +35,7 @@
#undef WARN_OLD
#undef CORE_DUMP /* definitely broken */
-static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs);
+static int load_aout_binary(struct linux_binprm *);
static int load_aout_library(struct file *);
#ifdef CORE_DUMP
@@ -260,9 +260,10 @@ static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
* These are the functions used to load a.out style executables and shared
* libraries. There is no binary dependent code anywhere else.
*/
-static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+static int load_aout_binary(struct linux_binprm *bprm)
{
unsigned long error, fd_offset, rlim;
+ struct pt_regs *regs = current_pt_regs();
struct exec ex;
int retval;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 076745f..32e6f05 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -467,11 +467,16 @@ GLOBAL(\label)
PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
PTREGSCALL stub32_execve, compat_sys_execve, %rcx
PTREGSCALL stub32_fork, sys_fork, %rdi
- PTREGSCALL stub32_clone, sys32_clone, %rdx
PTREGSCALL stub32_vfork, sys_vfork, %rdi
PTREGSCALL stub32_iopl, sys_iopl, %rsi
ALIGN
+GLOBAL(stub32_clone)
+ leaq sys_clone(%rip),%rax
+ mov %r8, %rcx
+ jmp ia32_ptregs_common
+
+ ALIGN
ia32_ptregs_common:
popq %r11
CFI_ENDPROC
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 86d68d1..d0b689b 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -385,17 +385,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd,
return ret;
}
-asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp,
- struct pt_regs *regs)
-{
- void __user *parent_tid = (void __user *)regs->dx;
- void __user *child_tid = (void __user *)regs->di;
-
- if (!newsp)
- newsp = regs->sp;
- return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
-}
-
/*
* Some system calls that need sign extended arguments. This could be
* done by a generic wrapper.
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 66e5f0e..79fd8a3 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += mce.h
header-y += msr-index.h
header-y += msr.h
header-y += mtrr.h
+header-y += perf_regs.h
header-y += posix_types_32.h
header-y += posix_types_64.h
header-y += posix_types_x32.h
@@ -19,8 +20,10 @@ header-y += prctl.h
header-y += processor-flags.h
header-y += ptrace-abi.h
header-y += sigcontext32.h
+header-y += svm.h
header-y += ucontext.h
header-y += vm86.h
+header-y += vmx.h
header-y += vsyscall.h
genhdr-y += unistd_32.h
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index b6c3b82..722aa3b 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -172,23 +172,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
*/
static inline int atomic_add_return(int i, atomic_t *v)
{
-#ifdef CONFIG_M386
- int __i;
- unsigned long flags;
- if (unlikely(boot_cpu_data.x86 <= 3))
- goto no_xadd;
-#endif
- /* Modern 486+ processor */
return i + xadd(&v->counter, i);
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
- raw_local_irq_save(flags);
- __i = atomic_read(v);
- atomic_set(v, i + __i);
- raw_local_irq_restore(flags);
- return i + __i;
-#endif
}
/**
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 2ad874c..92862cd 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -13,6 +13,7 @@
#define SETUP_NONE 0
#define SETUP_E820_EXT 1
#define SETUP_DTB 2
+#define SETUP_PCI 3
/* extensible setup data list node */
struct setup_data {
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 53f4b21..f8bf2ee 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -34,9 +34,7 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
: "memory");
}
-#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
-#endif
#ifdef CONFIG_X86_CMPXCHG64
#define cmpxchg64(ptr, o, n) \
@@ -73,59 +71,6 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
return prev;
}
-#ifndef CONFIG_X86_CMPXCHG
-/*
- * Building a kernel capable running on 80386. It may be necessary to
- * simulate the cmpxchg on the 80386 CPU. For that purpose we define
- * a function for each of the sizes we support.
- */
-
-extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
-extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
-extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
-
-static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
- unsigned long new, int size)
-{
- switch (size) {
- case 1:
- return cmpxchg_386_u8(ptr, old, new);
- case 2:
- return cmpxchg_386_u16(ptr, old, new);
- case 4:
- return cmpxchg_386_u32(ptr, old, new);
- }
- return old;
-}
-
-#define cmpxchg(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- if (likely(boot_cpu_data.x86 > 3)) \
- __ret = (__typeof__(*(ptr)))__cmpxchg((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- else \
- __ret = (__typeof__(*(ptr)))cmpxchg_386((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- __ret; \
-})
-#define cmpxchg_local(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- if (likely(boot_cpu_data.x86 > 3)) \
- __ret = (__typeof__(*(ptr)))__cmpxchg_local((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- else \
- __ret = (__typeof__(*(ptr)))cmpxchg_386((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- __ret; \
-})
-#endif
-
#ifndef CONFIG_X86_CMPXCHG64
/*
* Building a kernel capable running on 80386 and 80486. It may be necessary
diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/context_tracking.h
index d1ac07a..1616562 100644
--- a/arch/x86/include/asm/rcu.h
+++ b/arch/x86/include/asm/context_tracking.h
@@ -1,27 +1,26 @@
-#ifndef _ASM_X86_RCU_H
-#define _ASM_X86_RCU_H
+#ifndef _ASM_X86_CONTEXT_TRACKING_H
+#define _ASM_X86_CONTEXT_TRACKING_H
#ifndef __ASSEMBLY__
-
-#include <linux/rcupdate.h>
+#include <linux/context_tracking.h>
#include <asm/ptrace.h>
static inline void exception_enter(struct pt_regs *regs)
{
- rcu_user_exit();
+ user_exit();
}
static inline void exception_exit(struct pt_regs *regs)
{
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
if (user_mode(regs))
- rcu_user_enter();
+ user_enter();
#endif
}
#else /* __ASSEMBLY__ */
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
# define SCHEDULE_USER call schedule_user
#else
# define SCHEDULE_USER call schedule
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 4564c8e..5f9a124 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,6 +28,10 @@ struct x86_cpu {
#ifdef CONFIG_HOTPLUG_CPU
extern int arch_register_cpu(int num);
extern void arch_unregister_cpu(int);
+extern void __cpuinit start_cpu0(void);
+#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
+extern int _debug_hotplug_cpu(int cpu, int action);
+#endif
#endif
DECLARE_PER_CPU(int, cpu_state);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 8c297aa..da40b1e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -311,12 +311,7 @@ extern const char * const x86_power_flags[32];
#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8)
#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16)
#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU)
-
-#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
-# define cpu_has_invlpg 1
-#else
-# define cpu_has_invlpg (boot_cpu_data.x86 > 3)
-#endif
+#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT)
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 93e1c55..03dd729 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -2,9 +2,6 @@
#define _ASM_X86_DEVICE_H
struct dev_archdata {
-#ifdef CONFIG_ACPI
- void *acpi_handle;
-#endif
#ifdef CONFIG_X86_DEV_DMA_OPS
struct dma_map_ops *dma_ops;
#endif
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 5939f44..9c999c1 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -354,12 +354,10 @@ static inline int mmap_is_ia32(void)
return 0;
}
-/* The first two values are special, do not change. See align_addr() */
+/* Do not change the values. See get_align_mask() */
enum align_flags {
ALIGN_VA_32 = BIT(0),
ALIGN_VA_64 = BIT(1),
- ALIGN_VDSO = BIT(2),
- ALIGN_TOPDOWN = BIT(3),
};
struct va_alignment {
@@ -368,5 +366,5 @@ struct va_alignment {
} ____cacheline_aligned;
extern struct va_alignment va_align;
-extern unsigned long align_addr(unsigned long, struct file *, enum align_flags);
+extern unsigned long align_vdso_addr(unsigned long);
#endif /* _ASM_X86_ELF_H */
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 831dbb9..41ab26e 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -399,14 +399,17 @@ static inline void drop_init_fpu(struct task_struct *tsk)
typedef struct { int preload; } fpu_switch_t;
/*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
*
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
*/
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+ per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
{
return new == this_cpu_read_stable(fpu_owner_task) &&
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index f373046..be27ba1 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -55,12 +55,6 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
- /* Real i386 machines can only support FUTEX_OP_SET */
- if (op != FUTEX_OP_SET && boot_cpu_data.x86 == 3)
- return -ENOSYS;
-#endif
-
pagefault_disable();
switch (op) {
@@ -118,12 +112,6 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
{
int ret = 0;
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
- /* Real i386 machines have no cmpxchg instruction */
- if (boot_cpu_data.x86 == 3)
- return -ENOSYS;
-#endif
-
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index c8bed0d..2d89e39 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -124,27 +124,11 @@ static inline int local_add_negative(long i, local_t *l)
*/
static inline long local_add_return(long i, local_t *l)
{
- long __i;
-#ifdef CONFIG_M386
- unsigned long flags;
- if (unlikely(boot_cpu_data.x86 <= 3))
- goto no_xadd;
-#endif
- /* Modern 486+ processor */
- __i = i;
+ long __i = i;
asm volatile(_ASM_XADD "%0, %1;"
: "+r" (i), "+m" (l->a.counter)
: : "memory");
return i + __i;
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
- local_irq_save(flags);
- __i = local_read(l);
- local_set(l, i + __i);
- local_irq_restore(flags);
- return i + __i;
-#endif
}
static inline long local_sub_return(long i, local_t *l)
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 593e51d..513b05f 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -3,6 +3,9 @@
#define MAP_32BIT 0x40 /* only give out 32bit addresses */
+#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT)
+#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT)
+
#include <asm-generic/mman.h>
#endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 9eae775..e3b7819 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,8 +5,6 @@
#ifdef CONFIG_X86_64
/* X86_64 does not define MODULE_PROC_FAMILY */
-#elif defined CONFIG_M386
-#define MODULE_PROC_FAMILY "386 "
#elif defined CONFIG_M486
#define MODULE_PROC_FAMILY "486 "
#elif defined CONFIG_M586
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7f0edce..e400cdb 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -337,6 +337,8 @@
#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << 38)
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << 39)
+#define MSR_IA32_TSC_DEADLINE 0x000006E0
+
/* P4/Xeon+ specific */
#define MSR_IA32_MCG_EAX 0x00000180
#define MSR_IA32_MCG_EBX 0x00000181
diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h
new file mode 100644
index 0000000..1c6f7f6
--- /dev/null
+++ b/arch/x86/include/asm/numachip/numachip.h
@@ -0,0 +1,19 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-specific header file
+ *
+ * Copyright (C) 2012 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ */
+
+#ifndef _ASM_X86_NUMACHIP_NUMACHIP_H
+#define _ASM_X86_NUMACHIP_NUMACHIP_H
+
+extern int __init pci_numachip_init(void);
+
+#endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 6e41b93..dba7805 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -171,4 +171,16 @@ cpumask_of_pcibus(const struct pci_bus *bus)
}
#endif
+struct pci_setup_rom {
+ struct setup_data data;
+ uint16_t vendor;
+ uint16_t devid;
+ uint64_t pcilen;
+ unsigned long segment;
+ unsigned long bus;
+ unsigned long device;
+ unsigned long function;
+ uint8_t romdata[0];
+};
+
#endif /* _ASM_X86_PCI_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 1104afa..0da5200 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -406,7 +406,6 @@ do { \
#define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(pcp, nval)
#define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(pcp, nval)
-#ifndef CONFIG_M386
#define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val)
#define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val)
#define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val)
@@ -421,8 +420,6 @@ do { \
#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
-#endif /* !CONFIG_M386 */
-
#ifdef CONFIG_X86_CMPXCHG64
#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2) \
({ \
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ad1fc85..888184b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -178,8 +178,6 @@ static inline int hlt_works(int cpu)
extern void cpu_detect(struct cpuinfo_x86 *c);
-extern struct pt_regs *idle_regs(struct pt_regs *);
-
extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
@@ -187,7 +185,7 @@ extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern unsigned short num_cache_leaves;
+extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
extern void detect_extended_topology(struct cpuinfo_x86 *c);
extern void detect_ht(struct cpuinfo_x86 *c);
@@ -672,18 +670,29 @@ static inline void sync_core(void)
{
int tmp;
-#if defined(CONFIG_M386) || defined(CONFIG_M486)
- if (boot_cpu_data.x86 < 5)
- /* There is no speculative execution.
- * jmp is a barrier to prefetching. */
- asm volatile("jmp 1f\n1:\n" ::: "memory");
- else
+#ifdef CONFIG_M486
+ /*
+ * Do a CPUID if available, otherwise do a jump. The jump
+ * can conveniently enough be the jump around CPUID.
+ */
+ asm volatile("cmpl %2,%1\n\t"
+ "jl 1f\n\t"
+ "cpuid\n"
+ "1:"
+ : "=a" (tmp)
+ : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
+ : "ebx", "ecx", "edx", "memory");
+#else
+ /*
+ * CPUID is a barrier to speculative execution.
+ * Prefetched instructions are automatically
+ * invalidated when modified.
+ */
+ asm volatile("cpuid"
+ : "=a" (tmp)
+ : "0" (1)
+ : "ebx", "ecx", "edx", "memory");
#endif
- /* cpuid is a barrier to speculative execution.
- * Prefetched instructions are automatically
- * invalidated when modified. */
- asm volatile("cpuid" : "=a" (tmp) : "0" (1)
- : "ebx", "ecx", "edx", "memory");
}
static inline void __monitor(const void *eax, unsigned long ecx,
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index dcfde52..54d80fd 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -205,21 +205,14 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
}
#endif
-/*
- * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps. The previous stack will be directly underneath the saved
- * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
- *
- * This is valid only for kernel mode traps.
- */
-static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
-{
#ifdef CONFIG_X86_32
- return (unsigned long)(&regs->sp);
+extern unsigned long kernel_stack_pointer(struct pt_regs *regs);
#else
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
return regs->sp;
-#endif
}
+#endif
#define GET_IP(regs) ((regs)->ip)
#define GET_FP(regs) ((regs)->bp)
@@ -246,6 +239,15 @@ static inline unsigned long regs_get_register(struct pt_regs *regs,
{
if (unlikely(offset > MAX_REG_OFFSET))
return 0;
+#ifdef CONFIG_X86_32
+ /*
+ * Traps from the kernel do not save sp and ss.
+ * Use the helper function to retrieve sp.
+ */
+ if (offset == offsetof(struct pt_regs, sp) &&
+ regs->cs == __KERNEL_CS)
+ return kernel_stack_pointer(regs);
+#endif
return *(unsigned long *)((unsigned long)regs + offset);
}
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 323973f..0dba8b7 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -260,8 +260,6 @@ struct pt_regs;
#endif /* !__i386__ */
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
#endif /* __KERNEL__ */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4f19a15..b073aae 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -166,6 +166,7 @@ void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle);
+void smp_store_boot_cpu_info(void);
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h
index 557cd9f..7f235c7 100644
--- a/arch/x86/include/asm/swab.h
+++ b/arch/x86/include/asm/swab.h
@@ -6,22 +6,7 @@
static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
{
-#ifdef __i386__
-# ifdef CONFIG_X86_BSWAP
- asm("bswap %0" : "=r" (val) : "0" (val));
-# else
- asm("xchgb %b0,%h0\n\t" /* swap lower bytes */
- "rorl $16,%0\n\t" /* swap words */
- "xchgb %b0,%h0" /* swap higher bytes */
- : "=q" (val)
- : "0" (val));
-# endif
-
-#else /* __i386__ */
- asm("bswapl %0"
- : "=r" (val)
- : "0" (val));
-#endif
+ asm("bswapl %0" : "=r" (val) : "0" (val));
return val;
}
#define __arch_swab32 __arch_swab32
@@ -37,22 +22,12 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
__u64 u;
} v;
v.u = val;
-# ifdef CONFIG_X86_BSWAP
asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
: "=r" (v.s.a), "=r" (v.s.b)
: "0" (v.s.a), "1" (v.s.b));
-# else
- v.s.a = __arch_swab32(v.s.a);
- v.s.b = __arch_swab32(v.s.b);
- asm("xchgl %0,%1"
- : "=r" (v.s.a), "=r" (v.s.b)
- : "0" (v.s.a), "1" (v.s.b));
-# endif
return v.u;
#else /* __i386__ */
- asm("bswapq %0"
- : "=r" (val)
- : "0" (val));
+ asm("bswapq %0" : "=r" (val) : "0" (val));
return val;
#endif
}
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index a9a8cf3..c76fae4 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -54,8 +54,6 @@ asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
asmlinkage long sys32_personality(unsigned long);
asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32);
-asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *);
-
long sys32_lseek(unsigned int, int, unsigned int);
long sys32_kill(int, int);
long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int);
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 2be0b88..2f83747 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -20,15 +20,6 @@
asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
long sys_iopl(unsigned int, struct pt_regs *);
-/* kernel/process.c */
-int sys_fork(struct pt_regs *);
-int sys_vfork(struct pt_regs *);
-long sys_execve(const char __user *,
- const char __user *const __user *,
- const char __user *const __user *);
-long sys_clone(unsigned long, unsigned long, void __user *,
- void __user *, struct pt_regs *);
-
/* kernel/ldt.c */
asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 74a4433..0fee48e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -56,10 +56,7 @@ static inline void __flush_tlb_all(void)
static inline void __flush_tlb_one(unsigned long addr)
{
- if (cpu_has_invlpg)
__flush_tlb_single(addr);
- else
- __flush_tlb();
}
#define TLB_FLUSH_ALL -1UL
diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h
new file mode 100644
index 0000000..beab86c
--- /dev/null
+++ b/arch/x86/include/asm/trace_clock.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_TRACE_CLOCK_H
+#define _ASM_X86_TRACE_CLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_X86_TSC
+
+extern u64 notrace trace_clock_x86_tsc(void);
+
+# define ARCH_TRACE_CLOCKS \
+ { trace_clock_x86_tsc, "x86-tsc", .in_ns = 0 },
+
+#else /* !CONFIG_X86_TSC */
+
+#define ARCH_TRACE_CLOCKS
+
+#endif
+
+#endif /* _ASM_X86_TRACE_CLOCK_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 7ccf8d1..1709801 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -237,8 +237,6 @@ extern void __put_user_2(void);
extern void __put_user_4(void);
extern void __put_user_8(void);
-#ifdef CONFIG_X86_WP_WORKS_OK
-
/**
* put_user: - Write a simple value into user space.
* @x: Value to copy to user space.
@@ -326,29 +324,6 @@ do { \
} \
} while (0)
-#else
-
-#define __put_user_size(x, ptr, size, retval, errret) \
-do { \
- __typeof__(*(ptr))__pus_tmp = x; \
- retval = 0; \
- \
- if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0)) \
- retval = errret; \
-} while (0)
-
-#define put_user(x, ptr) \
-({ \
- int __ret_pu; \
- __typeof__(*(ptr))__pus_tmp = x; \
- __ret_pu = 0; \
- if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, \
- sizeof(*(ptr))) != 0)) \
- __ret_pu = -EFAULT; \
- __ret_pu; \
-})
-#endif
-
#ifdef CONFIG_X86_32
#define __get_user_asm_u64(x, ptr, retval, errret) (x) = __get_user_bad()
#define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad()
@@ -543,29 +518,12 @@ struct __large_struct { unsigned long buf[100]; };
(x) = (__force __typeof__(*(ptr)))__gue_val; \
} while (0)
-#ifdef CONFIG_X86_WP_WORKS_OK
-
#define put_user_try uaccess_try
#define put_user_catch(err) uaccess_catch(err)
#define put_user_ex(x, ptr) \
__put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-#else /* !CONFIG_X86_WP_WORKS_OK */
-
-#define put_user_try do { \
- int __uaccess_err = 0;
-
-#define put_user_catch(err) \
- (err) |= __uaccess_err; \
-} while (0)
-
-#define put_user_ex(x, ptr) do { \
- __uaccess_err |= __put_user(x, ptr); \
-} while (0)
-
-#endif /* CONFIG_X86_WP_WORKS_OK */
-
extern unsigned long
copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
extern __must_check long
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 16f3fc6..0e7dea7 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -51,6 +51,9 @@
# define __ARCH_WANT_SYS_UTIME
# define __ARCH_WANT_SYS_WAITPID
# define __ARCH_WANT_SYS_EXECVE
+# define __ARCH_WANT_SYS_FORK
+# define __ARCH_WANT_SYS_VFORK
+# define __ARCH_WANT_SYS_CLONE
/*
* "Conditional" syscalls
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 59c226d..c20d1ce 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -359,18 +359,14 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
return _hypercall4(int, update_va_mapping, va,
new_val.pte, new_val.pte >> 32, flags);
}
+extern int __must_check xen_event_channel_op_compat(int, void *);
static inline int
HYPERVISOR_event_channel_op(int cmd, void *arg)
{
int rc = _hypercall2(int, event_channel_op, cmd, arg);
- if (unlikely(rc == -ENOSYS)) {
- struct evtchn_op op;
- op.cmd = cmd;
- memcpy(&op.u, arg, sizeof(op.u));
- rc = _hypercall1(int, event_channel_op_compat, &op);
- memcpy(arg, &op.u, sizeof(op.u));
- }
+ if (unlikely(rc == -ENOSYS))
+ rc = xen_event_channel_op_compat(cmd, arg);
return rc;
}
@@ -386,17 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
return _hypercall3(int, console_io, cmd, count, str);
}
+extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+
static inline int
HYPERVISOR_physdev_op(int cmd, void *arg)
{
int rc = _hypercall2(int, physdev_op, cmd, arg);
- if (unlikely(rc == -ENOSYS)) {
- struct physdev_op op;
- op.cmd = cmd;
- memcpy(&op.u, arg, sizeof(op.u));
- rc = _hypercall1(int, physdev_op_compat, &op);
- memcpy(arg, &op.u, sizeof(op.u));
- }
+ if (unlikely(rc == -ENOSYS))
+ rc = HYPERVISOR_physdev_op_compat(cmd, arg);
return rc;
}
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 66d0fff..125f344 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,7 +33,6 @@
#ifndef _ASM_X86_XEN_HYPERVISOR_H
#define _ASM_X86_XEN_HYPERVISOR_H
-/* arch/i386/kernel/setup.c */
extern struct shared_info *HYPERVISOR_shared_info;
extern struct start_info *xen_start_info;
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 91ce48f..34e923a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -9,7 +9,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
ifdef CONFIG_FUNCTION_TRACER
# Do not profile debug and lowlevel utilities
CFLAGS_REMOVE_tsc.o = -pg
-CFLAGS_REMOVE_rtc.o = -pg
CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
CFLAGS_REMOVE_pvclock.o = -pg
CFLAGS_REMOVE_kvmclock.o = -pg
@@ -62,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
+obj-$(CONFIG_X86_TSC) += trace_clock.o
obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e651f7a..e48cafc 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -574,6 +574,12 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
return irq;
}
+EXPORT_SYMBOL_GPL(acpi_register_gsi);
+
+void acpi_unregister_gsi(u32 gsi)
+{
+}
+EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
void __init acpi_set_irq_model_pic(void)
{
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 11676cf..d5e0d71 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,8 @@ static int __init acpi_sleep_setup(char *str)
#endif
if (strncmp(str, "nonvs", 5) == 0)
acpi_nvs_nosave();
+ if (strncmp(str, "nonvs_s3", 8) == 0)
+ acpi_nvs_nosave_s3();
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
str = strchr(str, ',');
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b17416e..b994cc8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -90,21 +90,6 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
*/
DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
-/*
- * Knob to control our willingness to enable the local APIC.
- *
- * +1=force-enable
- */
-static int force_enable_local_apic __initdata;
-/*
- * APIC command line parameters
- */
-static int __init parse_lapic(char *arg)
-{
- force_enable_local_apic = 1;
- return 0;
-}
-early_param("lapic", parse_lapic);
/* Local APIC was disabled by the BIOS and enabled by the kernel */
static int enabled_via_apicbase;
@@ -133,6 +118,25 @@ static inline void imcr_apic_to_pic(void)
}
#endif
+/*
+ * Knob to control our willingness to enable the local APIC.
+ *
+ * +1=force-enable
+ */
+static int force_enable_local_apic __initdata;
+/*
+ * APIC command line parameters
+ */
+static int __init parse_lapic(char *arg)
+{
+ if (config_enabled(CONFIG_X86_32) && !arg)
+ force_enable_local_apic = 1;
+ else if (!strncmp(arg, "notscdeadline", 13))
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+ return 0;
+}
+early_param("lapic", parse_lapic);
+
#ifdef CONFIG_X86_64
static int apic_calibrate_pmtmr __initdata;
static __init int setup_apicpmtimer(char *s)
@@ -315,6 +319,7 @@ int lapic_get_maxlvt(void)
/* Clock divisor */
#define APIC_DIVISOR 16
+#define TSC_DIVISOR 32
/*
* This function sets up the local APIC timer, with a timeout of
@@ -333,6 +338,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
lvtt_value = LOCAL_TIMER_VECTOR;
if (!oneshot)
lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+ else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE;
+
if (!lapic_is_integrated())
lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
@@ -341,6 +349,11 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
apic_write(APIC_LVTT, lvtt_value);
+ if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) {
+ printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
+ return;
+ }
+
/*
* Divide PICLK by 16
*/
@@ -453,6 +466,16 @@ static int lapic_next_event(unsigned long delta,
return 0;
}
+static int lapic_next_deadline(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ u64 tsc;
+
+ rdtscll(tsc);
+ wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
+ return 0;
+}
+
/*
* Setup the lapic timer in periodic or oneshot mode
*/
@@ -533,7 +556,15 @@ static void __cpuinit setup_APIC_timer(void)
memcpy(levt, &lapic_clockevent, sizeof(*levt));
levt->cpumask = cpumask_of(smp_processor_id());
- clockevents_register_device(levt);
+ if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
+ levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_DUMMY);
+ levt->set_next_event = lapic_next_deadline;
+ clockevents_config_and_register(levt,
+ (tsc_khz / TSC_DIVISOR) * 1000,
+ 0xF, ~0UL);
+ } else
+ clockevents_register_device(levt);
}
/*
@@ -661,7 +692,9 @@ static int __init calibrate_APIC_clock(void)
* in the clockevent structure and return.
*/
- if (lapic_timer_frequency) {
+ if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
+ return 0;
+ } else if (lapic_timer_frequency) {
apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
lapic_timer_frequency);
lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
@@ -674,6 +707,9 @@ static int __init calibrate_APIC_clock(void)
return 0;
}
+ apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
+ "calibrating APIC timer ...\n");
+
local_irq_disable();
/* Replace the global interrupt handler */
@@ -811,9 +847,6 @@ void __init setup_boot_APIC_clock(void)
return;
}
- apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
- "calibrating APIC timer ...\n");
-
if (calibrate_APIC_clock()) {
/* No broadcast on UP ! */
if (num_possible_cpus() > 1)
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index a65829a..9c2aa89 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -22,6 +22,7 @@
#include <linux/hardirq.h>
#include <linux/delay.h>
+#include <asm/numachip/numachip.h>
#include <asm/numachip/numachip_csr.h>
#include <asm/smp.h>
#include <asm/apic.h>
@@ -179,6 +180,7 @@ static int __init numachip_system_init(void)
return 0;
x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
+ x86_init.pci.arch_init = pci_numachip_init;
map_csrs();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1817fa9..b739d39 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -234,11 +234,11 @@ int __init arch_early_irq_init(void)
zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
/*
* For legacy IRQ's, start with assigning irq0 to irq15 to
- * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
+ * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
*/
if (i < legacy_pic->nr_legacy_irqs) {
cfg[i].vector = IRQ0_VECTOR + i;
- cpumask_set_cpu(0, cfg[i].domain);
+ cpumask_setall(cfg[i].domain);
}
}
@@ -1141,7 +1141,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
* allocation for the members that are not used anymore.
*/
cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
- cfg->move_in_progress = 1;
+ cfg->move_in_progress =
+ cpumask_intersects(cfg->old_domain, cpu_online_mask);
cpumask_and(cfg->domain, cfg->domain, tmp_mask);
break;
}
@@ -1172,8 +1173,9 @@ next:
current_vector = vector;
current_offset = offset;
if (cfg->vector) {
- cfg->move_in_progress = 1;
cpumask_copy(cfg->old_domain, cfg->domain);
+ cfg->move_in_progress =
+ cpumask_intersects(cfg->old_domain, cpu_online_mask);
}
for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
per_cpu(vector_irq, new_cpu)[vector] = irq;
@@ -1241,12 +1243,6 @@ void __setup_vector_irq(int cpu)
cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
- /*
- * If it is a legacy IRQ handled by the legacy PIC, this cpu
- * will be part of the irq_cfg's domain.
- */
- if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
- cpumask_set_cpu(cpu, cfg->domain);
if (!cpumask_test_cpu(cpu, cfg->domain))
continue;
@@ -1356,16 +1352,6 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
if (!IO_APIC_IRQ(irq))
return;
- /*
- * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC
- * can handle this irq and the apic driver is finialized at this point,
- * update the cfg->domain.
- */
- if (irq < legacy_pic->nr_legacy_irqs &&
- cpumask_equal(cfg->domain, cpumask_of(0)))
- apic->vector_allocation_domain(0, cfg->domain,
- apic->target_cpus());
-
if (assign_irq_vector(irq, cfg, apic->target_cpus()))
return;
@@ -2199,9 +2185,11 @@ static int ioapic_retrigger_irq(struct irq_data *data)
{
struct irq_cfg *cfg = data->chip_data;
unsigned long flags;
+ int cpu;
raw_spin_lock_irqsave(&vector_lock, flags);
- apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
+ cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
+ apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return 1;
@@ -3317,8 +3305,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
int ret;
if (irq_remapping_enabled) {
- if (!setup_hpet_msi_remapped(irq, id))
- return -1;
+ ret = setup_hpet_msi_remapped(irq, id);
+ if (ret)
+ return ret;
}
ret = msi_compose_msg(NULL, irq, &msg, id);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f7e98a2..15239ff 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -304,7 +304,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
int cpu = smp_processor_id();
/* get information required for multi-node processors */
- if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+ if (cpu_has_topoext) {
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
+ /*
+ * The way access filter has a performance penalty on some workloads.
+ * Disable it on the affected CPUs.
+ */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+ u64 val;
+
+ if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+ val |= 0x1E;
+ wrmsrl_safe(0xc0011021, val);
+ }
+ }
+
cpu_detect_cache_sizes(c);
/* Multi core CPU? */
@@ -643,12 +657,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
detect_ht(c);
#endif
- if (c->extended_cpuid_level >= 0x80000006) {
- if (cpuid_edx(0x80000006) & 0xf000)
- num_cache_leaves = 4;
- else
- num_cache_leaves = 3;
- }
+ init_amd_cacheinfo(c);
if (c->x86 >= 0xf)
set_cpu_cap(c, X86_FEATURE_K8);
@@ -739,9 +748,6 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c,
static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
{
- if (!cpu_has_invlpg)
- return;
-
tlb_flushall_shift = 5;
if (c->x86 <= 0x11)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d0e910d..92dfec9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -107,53 +107,17 @@ static void __init check_hlt(void)
}
/*
- * Most 386 processors have a bug where a POPAD can lock the
- * machine even from user space.
- */
-
-static void __init check_popad(void)
-{
-#ifndef CONFIG_X86_POPAD_OK
- int res, inp = (int) &res;
-
- pr_info("Checking for popad bug... ");
- __asm__ __volatile__(
- "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx "
- : "=&a" (res)
- : "d" (inp)
- : "ecx", "edi");
- /*
- * If this fails, it means that any user program may lock the
- * CPU hard. Too bad.
- */
- if (res != 12345678)
- pr_cont("Buggy\n");
- else
- pr_cont("OK\n");
-#endif
-}
-
-/*
* Check whether we are able to run this kernel safely on SMP.
*
- * - In order to run on a i386, we need to be compiled for i386
- * (for due to lack of "invlpg" and working WP on a i386)
+ * - i386 is no longer supported.
* - In order to run on anything without a TSC, we need to be
* compiled for a i486.
*/
static void __init check_config(void)
{
-/*
- * We'd better not be a i386 if we're configured to use some
- * i486+ only features! (WP works in supervisor mode and the
- * new "invlpg" and "bswap" instructions)
- */
-#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \
- defined(CONFIG_X86_BSWAP)
- if (boot_cpu_data.x86 == 3)
+ if (boot_cpu_data.x86 < 4)
panic("Kernel requires i486+ for 'invlpg' and other features");
-#endif
}
@@ -166,7 +130,6 @@ void __init check_bugs(void)
#endif
check_config();
check_hlt();
- check_popad();
init_utsname()->machine[1] =
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7505f7b..9c3ab43 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1173,15 +1173,6 @@ DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
#endif
-/* Make sure %fs and %gs are initialized properly in idle threads */
-struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
-{
- memset(regs, 0, sizeof(struct pt_regs));
- regs->fs = __KERNEL_PERCPU;
- regs->gs = __KERNEL_STACK_CANARY;
-
- return regs;
-}
#endif /* CONFIG_X86_64 */
/*
@@ -1237,7 +1228,7 @@ void __cpuinit cpu_init(void)
oist = &per_cpu(orig_ist, cpu);
#ifdef CONFIG_NUMA
- if (cpu != 0 && this_cpu_read(numa_node) == 0 &&
+ if (this_cpu_read(numa_node) == 0 &&
early_cpu_to_node(cpu) != NUMA_NO_NODE)
set_numa_node(early_cpu_to_node(cpu));
#endif
@@ -1269,8 +1260,7 @@ void __cpuinit cpu_init(void)
barrier();
x86_configure_nx();
- if (cpu != 0)
- enable_x2apic();
+ enable_x2apic();
/*
* set up and load the per-CPU TSS
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 198e019..fcaabd0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -612,10 +612,6 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc)
static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
{
- if (!cpu_has_invlpg) {
- tlb_flushall_shift = -1;
- return;
- }
switch ((c->x86 << 8) + c->x86_model) {
case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 93c5451..fe9edec 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -538,7 +538,11 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
unsigned edx;
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
- amd_cpuid4(index, &eax, &ebx, &ecx);
+ if (cpu_has_topoext)
+ cpuid_count(0x8000001d, index, &eax.full,
+ &ebx.full, &ecx.full, &edx);
+ else
+ amd_cpuid4(index, &eax, &ebx, &ecx);
amd_init_l3_cache(this_leaf, index);
} else {
cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
@@ -557,21 +561,39 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
return 0;
}
-static int __cpuinit find_num_cache_leaves(void)
+static int __cpuinit find_num_cache_leaves(struct cpuinfo_x86 *c)
{
- unsigned int eax, ebx, ecx, edx;
+ unsigned int eax, ebx, ecx, edx, op;
union _cpuid4_leaf_eax cache_eax;
int i = -1;
+ if (c->x86_vendor == X86_VENDOR_AMD)
+ op = 0x8000001d;
+ else
+ op = 4;
+
do {
++i;
- /* Do cpuid(4) loop to find out num_cache_leaves */
- cpuid_count(4, i, &eax, &ebx, &ecx, &edx);
+ /* Do cpuid(op) loop to find out num_cache_leaves */
+ cpuid_count(op, i, &eax, &ebx, &ecx, &edx);
cache_eax.full = eax;
} while (cache_eax.split.type != CACHE_TYPE_NULL);
return i;
}
+void __cpuinit init_amd_cacheinfo(struct cpuinfo_x86 *c)
+{
+
+ if (cpu_has_topoext) {
+ num_cache_leaves = find_num_cache_leaves(c);
+ } else if (c->extended_cpuid_level >= 0x80000006) {
+ if (cpuid_edx(0x80000006) & 0xf000)
+ num_cache_leaves = 4;
+ else
+ num_cache_leaves = 3;
+ }
+}
+
unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
{
/* Cache sizes */
@@ -588,7 +610,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
if (is_initialized == 0) {
/* Init num_cache_leaves from boot CPU */
- num_cache_leaves = find_num_cache_leaves();
+ num_cache_leaves = find_num_cache_leaves(c);
is_initialized++;
}
@@ -728,37 +750,50 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
{
struct _cpuid4_info *this_leaf;
- int ret, i, sibling;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
+ int i, sibling;
- ret = 0;
- if (index == 3) {
- ret = 1;
- for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
+ if (cpu_has_topoext) {
+ unsigned int apicid, nshared, first, last;
+
+ if (!per_cpu(ici_cpuid4_info, cpu))
+ return 0;
+
+ this_leaf = CPUID4_INFO_IDX(cpu, index);
+ nshared = this_leaf->base.eax.split.num_threads_sharing + 1;
+ apicid = cpu_data(cpu).apicid;
+ first = apicid - (apicid % nshared);
+ last = first + nshared - 1;
+
+ for_each_online_cpu(i) {
+ apicid = cpu_data(i).apicid;
+ if ((apicid < first) || (apicid > last))
+ continue;
if (!per_cpu(ici_cpuid4_info, i))
continue;
this_leaf = CPUID4_INFO_IDX(i, index);
- for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
- if (!cpu_online(sibling))
+
+ for_each_online_cpu(sibling) {
+ apicid = cpu_data(sibling).apicid;
+ if ((apicid < first) || (apicid > last))
continue;
set_bit(sibling, this_leaf->shared_cpu_map);
}
}
- } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) {
- ret = 1;
- for_each_cpu(i, cpu_sibling_mask(cpu)) {
+ } else if (index == 3) {
+ for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
if (!per_cpu(ici_cpuid4_info, i))
continue;
this_leaf = CPUID4_INFO_IDX(i, index);
- for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+ for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
if (!cpu_online(sibling))
continue;
set_bit(sibling, this_leaf->shared_cpu_map);
}
}
- }
+ } else
+ return 0;
- return ret;
+ return 1;
}
static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 698b6ec..1ac581f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -6,7 +6,7 @@
*
* Written by Jacob Shin - AMD, Inc.
*
- * Support: borislav.petkov@amd.com
+ * Maintained by: Borislav Petkov <bp@alien8.de>
*
* April 2006
* - added support for AMD Family 0x10 processors
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 5f88abf..4f9a3cb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,34 +285,39 @@ void cmci_clear(void)
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
+static long cmci_rediscover_work_func(void *arg)
+{
+ int banks;
+
+ /* Recheck banks in case CPUs don't all have the same */
+ if (cmci_supported(&banks))
+ cmci_discover(banks);
+
+ return 0;
+}
+
/*
* After a CPU went down cycle through all the others and rediscover
* Must run in process context.
*/
void cmci_rediscover(int dying)
{
- int banks;
- int cpu;
- cpumask_var_t old;
+ int cpu, banks;
if (!cmci_supported(&banks))
return;
- if (!alloc_cpumask_var(&old, GFP_KERNEL))
- return;
- cpumask_copy(old, &current->cpus_allowed);
for_each_online_cpu(cpu) {
if (cpu == dying)
continue;
- if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
+
+ if (cpu == smp_processor_id()) {
+ cmci_rediscover_work_func(NULL);
continue;
- /* Recheck banks in case CPUs don't all have the same */
- if (cmci_supported(&banks))
- cmci_discover(banks);
- }
+ }
- set_cpus_allowed_ptr(current, old);
- free_cpumask_var(old);
+ work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
+ }
}
/*
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 6b96110..726bf96 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -606,7 +606,7 @@ void __init mtrr_bp_init(void)
/*
* This is an AMD specific MSR, but we assume(hope?) that
- * Intel will implement it to when they extend the address
+ * Intel will implement it too when they extend the address
* bus of the Xeon.
*/
if (cpuid_eax(0x80000000) >= 0x80000008) {
@@ -695,11 +695,16 @@ void mtrr_ap_init(void)
}
/**
- * Save current fixed-range MTRR state of the BSP
+ * Save current fixed-range MTRR state of the first cpu in cpu_online_mask.
*/
void mtrr_save_state(void)
{
- smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1);
+ int first_cpu;
+
+ get_online_cpus();
+ first_cpu = cpumask_first(cpu_online_mask);
+ smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
+ put_online_cpus();
}
void set_mtrr_aps_delayed_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4a3374e..4428fd1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1316,6 +1316,121 @@ static struct attribute_group x86_pmu_format_group = {
.attrs = NULL,
};
+struct perf_pmu_events_attr {
+ struct device_attribute attr;
+ u64 id;
+};
+
+/*
+ * Remove all undefined events (x86_pmu.event_map(id) == 0)
+ * out of events_attr attributes.
+ */
+static void __init filter_events(struct attribute **attrs)
+{
+ int i, j;
+
+ for (i = 0; attrs[i]; i++) {
+ if (x86_pmu.event_map(i))
+ continue;
+
+ for (j = i; attrs[j]; j++)
+ attrs[j] = attrs[j + 1];
+
+ /* Check the shifted attr. */
+ i--;
+ }
+}
+
+static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr = \
+ container_of(attr, struct perf_pmu_events_attr, attr);
+
+ u64 config = x86_pmu.event_map(pmu_attr->id);
+ return x86_pmu.events_sysfs_show(page, config);
+}
+
+#define EVENT_VAR(_id) event_attr_##_id
+#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+
+#define EVENT_ATTR(_name, _id) \
+static struct perf_pmu_events_attr EVENT_VAR(_id) = { \
+ .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \
+ .id = PERF_COUNT_HW_##_id, \
+};
+
+EVENT_ATTR(cpu-cycles, CPU_CYCLES );
+EVENT_ATTR(instructions, INSTRUCTIONS );
+EVENT_ATTR(cache-references, CACHE_REFERENCES );
+EVENT_ATTR(cache-misses, CACHE_MISSES );
+EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS );
+EVENT_ATTR(branch-misses, BRANCH_MISSES );
+EVENT_ATTR(bus-cycles, BUS_CYCLES );
+EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND );
+EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND );
+EVENT_ATTR(ref-cycles, REF_CPU_CYCLES );
+
+static struct attribute *empty_attrs;
+
+static struct attribute *events_attr[] = {
+ EVENT_PTR(CPU_CYCLES),
+ EVENT_PTR(INSTRUCTIONS),
+ EVENT_PTR(CACHE_REFERENCES),
+ EVENT_PTR(CACHE_MISSES),
+ EVENT_PTR(BRANCH_INSTRUCTIONS),
+ EVENT_PTR(BRANCH_MISSES),
+ EVENT_PTR(BUS_CYCLES),
+ EVENT_PTR(STALLED_CYCLES_FRONTEND),
+ EVENT_PTR(STALLED_CYCLES_BACKEND),
+ EVENT_PTR(REF_CPU_CYCLES),
+ NULL,
+};
+
+static struct attribute_group x86_pmu_events_group = {
+ .name = "events",
+ .attrs = events_attr,
+};
+
+ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
+{
+ u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
+ u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24;
+ bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE);
+ bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL);
+ bool any = (config & ARCH_PERFMON_EVENTSEL_ANY);
+ bool inv = (config & ARCH_PERFMON_EVENTSEL_INV);
+ ssize_t ret;
+
+ /*
+ * We have whole page size to spend and just little data
+ * to write, so we can safely use sprintf.
+ */
+ ret = sprintf(page, "event=0x%02llx", event);
+
+ if (umask)
+ ret += sprintf(page + ret, ",umask=0x%02llx", umask);
+
+ if (edge)
+ ret += sprintf(page + ret, ",edge");
+
+ if (pc)
+ ret += sprintf(page + ret, ",pc");
+
+ if (any)
+ ret += sprintf(page + ret, ",any");
+
+ if (inv)
+ ret += sprintf(page + ret, ",inv");
+
+ if (cmask)
+ ret += sprintf(page + ret, ",cmask=0x%02llx", cmask);
+
+ ret += sprintf(page + ret, "\n");
+
+ return ret;
+}
+
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
@@ -1362,6 +1477,11 @@ static int __init init_hw_perf_events(void)
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
+ if (!x86_pmu.events_sysfs_show)
+ x86_pmu_events_group.attrs = &empty_attrs;
+ else
+ filter_events(x86_pmu_events_group.attrs);
+
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
pr_info("... generic registers: %d\n", x86_pmu.num_counters);
@@ -1651,6 +1771,7 @@ static struct attribute_group x86_pmu_attr_group = {
static const struct attribute_group *x86_pmu_attr_groups[] = {
&x86_pmu_attr_group,
&x86_pmu_format_group,
+ &x86_pmu_events_group,
NULL,
};
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 271d257..115c1ea 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -354,6 +354,8 @@ struct x86_pmu {
int attr_rdpmc;
struct attribute **format_attrs;
+ ssize_t (*events_sysfs_show)(char *page, u64 config);
+
/*
* CPU Hotplug hooks
*/
@@ -536,6 +538,9 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
regs->ip = ip;
}
+ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
+ssize_t intel_event_sysfs_show(char *page, u64 config);
+
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 4528ae7..c93bc4e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -568,6 +568,14 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
}
}
+static ssize_t amd_event_sysfs_show(char *page, u64 config)
+{
+ u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) |
+ (config & AMD64_EVENTSEL_EVENT) >> 24;
+
+ return x86_event_sysfs_show(page, config, event);
+}
+
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
.handle_irq = x86_pmu_handle_irq,
@@ -591,6 +599,7 @@ static __initconst const struct x86_pmu amd_pmu = {
.put_event_constraints = amd_put_event_constraints,
.format_attrs = amd_format_attr,
+ .events_sysfs_show = amd_event_sysfs_show,
.cpu_prepare = amd_pmu_cpu_prepare,
.cpu_starting = amd_pmu_cpu_starting,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 324bb52..93b9e11 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1603,6 +1603,13 @@ static struct attribute *intel_arch_formats_attr[] = {
NULL,
};
+ssize_t intel_event_sysfs_show(char *page, u64 config)
+{
+ u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT);
+
+ return x86_event_sysfs_show(page, config, event);
+}
+
static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
@@ -1628,6 +1635,7 @@ static __initconst const struct x86_pmu core_pmu = {
.event_constraints = intel_core_event_constraints,
.guest_get_msrs = core_guest_get_msrs,
.format_attrs = intel_arch_formats_attr,
+ .events_sysfs_show = intel_event_sysfs_show,
};
struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1766,6 +1774,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.pebs_aliases = intel_pebs_aliases_core2,
.format_attrs = intel_arch3_formats_attr,
+ .events_sysfs_show = intel_event_sysfs_show,
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 7d0270b..f2af39f 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -227,6 +227,8 @@ static __initconst const struct x86_pmu p6_pmu = {
.event_constraints = p6_event_constraints,
.format_attrs = intel_p6_formats_attr,
+ .events_sysfs_show = intel_event_sysfs_show,
+
};
__init int p6_pmu_init(void)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 88b725a..c763116 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -739,30 +739,12 @@ ENTRY(ptregs_##name) ; \
ENDPROC(ptregs_##name)
PTREGSCALL1(iopl)
-PTREGSCALL0(fork)
-PTREGSCALL0(vfork)
PTREGSCALL2(sigaltstack)
PTREGSCALL0(sigreturn)
PTREGSCALL0(rt_sigreturn)
PTREGSCALL2(vm86)
PTREGSCALL1(vm86old)
-/* Clone is an oddball. The 4th arg is in %edi */
-ENTRY(ptregs_clone)
- CFI_STARTPROC
- leal 4(%esp),%eax
- pushl_cfi %eax
- pushl_cfi PT_EDI(%eax)
- movl PT_EDX(%eax),%ecx
- movl PT_ECX(%eax),%edx
- movl PT_EBX(%eax),%eax
- call sys_clone
- addl $8,%esp
- CFI_ADJUST_CFA_OFFSET -8
- ret
- CFI_ENDPROC
-ENDPROC(ptregs_clone)
-
.macro FIXUP_ESPFIX_STACK
/*
* Switch back for ESPFIX stack to the normal zerobased stack
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b51b2c7..70641af 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,7 +56,7 @@
#include <asm/ftrace.h>
#include <asm/percpu.h>
#include <asm/asm.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
#include <asm/smap.h>
#include <linux/err.h>
@@ -845,9 +845,25 @@ ENTRY(\label)
END(\label)
.endm
- PTREGSCALL stub_clone, sys_clone, %r8
- PTREGSCALL stub_fork, sys_fork, %rdi
- PTREGSCALL stub_vfork, sys_vfork, %rdi
+ .macro FORK_LIKE func
+ENTRY(stub_\func)
+ CFI_STARTPROC
+ popq %r11 /* save return address */
+ PARTIAL_FRAME 0
+ SAVE_REST
+ pushq %r11 /* put it back on stack */
+ FIXUP_TOP_OF_STACK %r11, 8
+ DEFAULT_FRAME 0 8 /* offset 8: return address */
+ call sys_\func
+ RESTORE_TOP_OF_STACK %r11, 8
+ ret $REST_SKIP /* pop extended registers */
+ CFI_ENDPROC
+END(stub_\func)
+ .endm
+
+ FORK_LIKE clone
+ FORK_LIKE fork
+ FORK_LIKE vfork
PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
PTREGSCALL stub_iopl, sys_iopl, %rsi
@@ -995,8 +1011,8 @@ END(interrupt)
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
- ASM_CLAC
XCPT_FRAME
+ ASM_CLAC
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
/* 0(%rsp): old_rsp-ARGOFFSET */
@@ -1135,8 +1151,8 @@ END(common_interrupt)
*/
.macro apicinterrupt num sym do_sym
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
pushq_cfi $~(\num)
.Lcommon_\sym:
interrupt \do_sym
@@ -1190,8 +1206,8 @@ apicinterrupt IRQ_WORK_VECTOR \
*/
.macro zeroentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
@@ -1208,8 +1224,8 @@ END(\sym)
.macro paranoidzeroentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
@@ -1227,8 +1243,8 @@ END(\sym)
#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
.macro paranoidzeroentry_ist sym do_sym ist
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
@@ -1247,8 +1263,8 @@ END(\sym)
.macro errorentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
XCPT_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1266,8 +1282,8 @@ END(\sym)
/* error code is on the stack already */
.macro paranoiderrorentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
XCPT_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1699,9 +1715,10 @@ nested_nmi:
1:
/* Set up the interrupted NMIs stack to jump to repeat_nmi */
- leaq -6*8(%rsp), %rdx
+ leaq -1*8(%rsp), %rdx
movq %rdx, %rsp
- CFI_ADJUST_CFA_OFFSET 6*8
+ CFI_ADJUST_CFA_OFFSET 1*8
+ leaq -10*8(%rsp), %rdx
pushq_cfi $__KERNEL_DS
pushq_cfi %rdx
pushfq_cfi
@@ -1709,8 +1726,8 @@ nested_nmi:
pushq_cfi $repeat_nmi
/* Put stack back */
- addq $(11*8), %rsp
- CFI_ADJUST_CFA_OFFSET -11*8
+ addq $(6*8), %rsp
+ CFI_ADJUST_CFA_OFFSET -6*8
nested_nmi_out:
popq_cfi %rdx
@@ -1736,18 +1753,18 @@ first_nmi:
* +-------------------------+
* | NMI executing variable |
* +-------------------------+
- * | Saved SS |
- * | Saved Return RSP |
- * | Saved RFLAGS |
- * | Saved CS |
- * | Saved RIP |
- * +-------------------------+
* | copied SS |
* | copied Return RSP |
* | copied RFLAGS |
* | copied CS |
* | copied RIP |
* +-------------------------+
+ * | Saved SS |
+ * | Saved Return RSP |
+ * | Saved RFLAGS |
+ * | Saved CS |
+ * | Saved RIP |
+ * +-------------------------+
* | pt_regs |
* +-------------------------+
*
@@ -1763,9 +1780,14 @@ first_nmi:
/* Set the NMI executing variable on the stack. */
pushq_cfi $1
+ /*
+ * Leave room for the "copied" frame
+ */
+ subq $(5*8), %rsp
+
/* Copy the stack frame to the Saved frame */
.rept 5
- pushq_cfi 6*8(%rsp)
+ pushq_cfi 11*8(%rsp)
.endr
CFI_DEF_CFA_OFFSET SS+8-RIP
@@ -1786,12 +1808,15 @@ repeat_nmi:
* is benign for the non-repeat case, where 1 was pushed just above
* to this very stack slot).
*/
- movq $1, 5*8(%rsp)
+ movq $1, 10*8(%rsp)
/* Make another copy, this one may be modified by nested NMIs */
+ addq $(10*8), %rsp
+ CFI_ADJUST_CFA_OFFSET -10*8
.rept 5
- pushq_cfi 4*8(%rsp)
+ pushq_cfi -6*8(%rsp)
.endr
+ subq $(5*8), %rsp
CFI_DEF_CFA_OFFSET SS+8-RIP
end_repeat_nmi:
@@ -1842,8 +1867,12 @@ nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
RESTORE_ALL 8
+
+ /* Pop the extra iret frame */
+ addq $(5*8), %rsp
+
/* Clear the NMI executing stack variable */
- movq $0, 10*8(%rsp)
+ movq $0, 5*8(%rsp)
jmp irq_return
CFI_ENDPROC
END(nmi)
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 957a47a..8e7f655 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -266,6 +266,19 @@ num_subarch_entries = (. - subarch_entries) / 4
jmp default_entry
#endif /* CONFIG_PARAVIRT */
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
+ * up already except stack. We just set up stack here. Then call
+ * start_secondary().
+ */
+ENTRY(start_cpu0)
+ movl stack_start, %ecx
+ movl %ecx, %esp
+ jmp *(initial_code)
+ENDPROC(start_cpu0)
+#endif
+
/*
* Non-boot CPU entry point; entered from trampoline.S
* We can't lgdt here, because lgdt itself uses a data segment, but
@@ -292,8 +305,8 @@ default_entry:
* be using the global pages.
*
* NOTE! If we are on a 486 we may have no cr4 at all!
- * Specifically, cr4 exists if and only if CPUID exists,
- * which in turn exists if and only if EFLAGS.ID exists.
+ * Specifically, cr4 exists if and only if CPUID exists
+ * and has flags other than the FPU flag set.
*/
movl $X86_EFLAGS_ID,%ecx
pushl %ecx
@@ -308,6 +321,11 @@ default_entry:
testl %ecx,%eax
jz 6f # No ID flag = no CPUID = no CR4
+ movl $1,%eax
+ cpuid
+ andl $~1,%edx # Ignore CPUID.FPU
+ jz 6f # No flags or only CPUID.FPU = no CR4
+
movl pa(mmu_cr4_features),%eax
movl %eax,%cr4
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 94bf9cc..980053c 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -252,6 +252,22 @@ ENTRY(secondary_startup_64)
pushq %rax # target address in negative space
lretq
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
+ * up already except stack. We just set up stack here. Then call
+ * start_secondary().
+ */
+ENTRY(start_cpu0)
+ movq stack_start(%rip),%rsp
+ movq initial_code(%rip),%rax
+ pushq $0 # fake return address to stop unwinder
+ pushq $__KERNEL_CS # set correct cs
+ pushq %rax # target address in negative space
+ lretq
+ENDPROC(start_cpu0)
+#endif
+
/* SMP bootup changes these two */
__REFDATA
.align 8
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 1460a5d..e28670f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -434,7 +434,7 @@ void hpet_msi_unmask(struct irq_data *data)
/* unmask it */
cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
- cfg |= HPET_TN_FSB;
+ cfg |= HPET_TN_ENABLE | HPET_TN_FSB;
hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
}
@@ -445,7 +445,7 @@ void hpet_msi_mask(struct irq_data *data)
/* mask it */
cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
- cfg &= ~HPET_TN_FSB;
+ cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB);
hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
}
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 675a050..245a71d 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -175,7 +175,11 @@ void __cpuinit fpu_init(void)
cr0 |= X86_CR0_EM;
write_cr0(cr0);
- if (!smp_processor_id())
+ /*
+ * init_thread_xstate is only called once to avoid overriding
+ * xstate_size during boot time or during CPU hotplug.
+ */
+ if (xstate_size == 0)
init_thread_xstate();
mxcsr_feature_mask_init();
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7720ff5..efdec7c 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -8,8 +8,8 @@
* Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
*
* Maintainers:
- * Andreas Herrmann <andreas.herrmann3@amd.com>
- * Borislav Petkov <borislav.petkov@amd.com>
+ * Andreas Herrmann <herrmann.der.user@googlemail.com>
+ * Borislav Petkov <bp@alien8.de>
*
* This driver allows to upgrade microcode on F10h AMD
* CPUs and later.
@@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
#define F1XH_MPB_MAX_SIZE 2048
#define F14H_MPB_MAX_SIZE 1824
#define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
switch (c->x86) {
case 0x14:
@@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
case 0x15:
max_size = F15H_MPB_MAX_SIZE;
break;
+ case 0x16:
+ max_size = F16H_MPB_MAX_SIZE;
+ break;
default:
max_size = F1XH_MPB_MAX_SIZE;
break;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b644e1c..2ed787f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -262,36 +262,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
propagate_user_return_notify(prev_p, next_p);
}
-int sys_fork(struct pt_regs *regs)
-{
- return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-int sys_vfork(struct pt_regs *regs)
-{
- return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0,
- NULL, NULL);
-}
-
-long
-sys_clone(unsigned long clone_flags, unsigned long newsp,
- void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
-{
- if (!newsp)
- newsp = regs->sp;
- return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
-}
-
/*
* Idle related variables and functions
*/
@@ -306,11 +276,6 @@ void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);
#endif
-static inline int hlt_use_halt(void)
-{
- return 1;
-}
-
#ifndef CONFIG_SMP
static inline void play_dead(void)
{
@@ -410,28 +375,22 @@ void cpu_idle(void)
*/
void default_idle(void)
{
- if (hlt_use_halt()) {
- trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
- trace_cpu_idle_rcuidle(1, smp_processor_id());
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we
- * test NEED_RESCHED:
- */
- smp_mb();
+ trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+ trace_cpu_idle_rcuidle(1, smp_processor_id());
+ current_thread_info()->status &= ~TS_POLLING;
+ /*
+ * TS_POLLING-cleared state must be visible before we
+ * test NEED_RESCHED:
+ */
+ smp_mb();
- if (!need_resched())
- safe_halt(); /* enables interrupts racelessly */
- else
- local_irq_enable();
- current_thread_info()->status |= TS_POLLING;
- trace_power_end_rcuidle(smp_processor_id());
- trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
- } else {
+ if (!need_resched())
+ safe_halt(); /* enables interrupts racelessly */
+ else
local_irq_enable();
- /* loop is done by the caller */
- cpu_relax();
- }
+ current_thread_info()->status |= TS_POLLING;
+ trace_power_end_rcuidle(smp_processor_id());
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(default_idle);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 44e0bff..b5a8905 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,8 +128,7 @@ void release_thread(struct task_struct *dead_task)
}
int copy_thread(unsigned long clone_flags, unsigned long sp,
- unsigned long arg,
- struct task_struct *p, struct pt_regs *regs)
+ unsigned long arg, struct task_struct *p)
{
struct pt_regs *childregs = task_pt_regs(p);
struct task_struct *tsk;
@@ -138,7 +137,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
- if (unlikely(!regs)) {
+ if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
p->thread.ip = (unsigned long) ret_from_kernel_thread;
@@ -156,12 +155,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
return 0;
}
- *childregs = *regs;
+ *childregs = *current_pt_regs();
childregs->ax = 0;
- childregs->sp = sp;
+ if (sp)
+ childregs->sp = sp;
p->thread.ip = (unsigned long) ret_from_fork;
- task_user_gs(p) = get_user_gs(regs);
+ task_user_gs(p) = get_user_gs(current_pt_regs());
p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 16c6365..6e68a61 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -146,8 +146,7 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls)
}
int copy_thread(unsigned long clone_flags, unsigned long sp,
- unsigned long arg,
- struct task_struct *p, struct pt_regs *regs)
+ unsigned long arg, struct task_struct *p)
{
int err;
struct pt_regs *childregs;
@@ -169,7 +168,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
savesegment(ds, p->thread.ds);
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
- if (unlikely(!regs)) {
+ if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
childregs->sp = (unsigned long)childregs;
@@ -181,10 +180,11 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
return 0;
}
- *childregs = *regs;
+ *childregs = *current_pt_regs();
childregs->ax = 0;
- childregs->sp = sp;
+ if (sp)
+ childregs->sp = sp;
err = -ENOMEM;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index b00b33a..b629bbe 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -22,6 +22,8 @@
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/rcupdate.h>
+#include <linux/module.h>
+#include <linux/context_tracking.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -166,6 +168,35 @@ static inline bool invalid_selector(u16 value)
#define FLAG_MASK FLAG_MASK_32
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps. The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+ unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+ unsigned long sp = (unsigned long)&regs->sp;
+ struct thread_info *tinfo;
+
+ if (context == (sp & ~(THREAD_SIZE - 1)))
+ return sp;
+
+ tinfo = (struct thread_info *)context;
+ if (tinfo->previous_esp)
+ return tinfo->previous_esp;
+
+ return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
{
BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
@@ -1461,7 +1492,7 @@ long syscall_trace_enter(struct pt_regs *regs)
{
long ret = 0;
- rcu_user_exit();
+ user_exit();
/*
* If we stepped into a sysenter/syscall insn, it trapped in
@@ -1511,6 +1542,13 @@ void syscall_trace_leave(struct pt_regs *regs)
{
bool step;
+ /*
+ * We may come here right after calling schedule_user()
+ * or do_notify_resume(), in which case we can be in RCU
+ * user mode.
+ */
+ user_exit();
+
audit_syscall_exit(regs);
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
@@ -1527,5 +1565,5 @@ void syscall_trace_leave(struct pt_regs *regs)
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
- rcu_user_enter();
+ user_enter();
}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 4929c1b..801602b 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -195,12 +195,6 @@ void read_persistent_clock(struct timespec *ts)
ts->tv_nsec = 0;
}
-unsigned long long native_read_tsc(void)
-{
- return __native_read_tsc();
-}
-EXPORT_SYMBOL(native_read_tsc);
-
static struct resource rtc_resources[] = {
[0] = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ca45696..c228322 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -143,11 +143,7 @@ int default_check_phys_apicid_present(int phys_apicid)
}
#endif
-#ifndef CONFIG_DEBUG_BOOT_PARAMS
-struct boot_params __initdata boot_params;
-#else
struct boot_params boot_params;
-#endif
/*
* Machine setup..
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 70b27ee..fbbb604 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -22,6 +22,7 @@
#include <linux/uaccess.h>
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
+#include <linux/context_tracking.h>
#include <asm/processor.h>
#include <asm/ucontext.h>
@@ -816,7 +817,7 @@ static void do_signal(struct pt_regs *regs)
void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
- rcu_user_exit();
+ user_exit();
#ifdef CONFIG_X86_MCE
/* notify userspace of pending MCEs */
@@ -838,7 +839,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
fire_user_return_notifiers();
- rcu_user_enter();
+ user_enter();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33b..ed0fe38 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,6 +68,8 @@
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
@@ -125,8 +127,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
atomic_t init_deasserted;
/*
- * Report back to the Boot Processor.
- * Running on AP.
+ * Report back to the Boot Processor during boot time or to the caller processor
+ * during CPU online.
*/
static void __cpuinit smp_callin(void)
{
@@ -138,15 +140,17 @@ static void __cpuinit smp_callin(void)
* we may get here before an INIT-deassert IPI reaches
* our local APIC. We have to wait for the IPI or we'll
* lock up on an APIC access.
+ *
+ * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
*/
- if (apic->wait_for_init_deassert)
+ cpuid = smp_processor_id();
+ if (apic->wait_for_init_deassert && cpuid != 0)
apic->wait_for_init_deassert(&init_deasserted);
/*
* (This works even if the APIC is not enabled.)
*/
phys_id = read_apic_id();
- cpuid = smp_processor_id();
if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
phys_id, cpuid);
@@ -228,6 +232,8 @@ static void __cpuinit smp_callin(void)
cpumask_set_cpu(cpuid, cpu_callin_mask);
}
+static int cpu0_logical_apicid;
+static int enable_start_cpu0;
/*
* Activate a secondary processor.
*/
@@ -243,6 +249,8 @@ notrace static void __cpuinit start_secondary(void *unused)
preempt_disable();
smp_callin();
+ enable_start_cpu0 = 0;
+
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
load_cr3(swapper_pg_dir);
@@ -279,19 +287,30 @@ notrace static void __cpuinit start_secondary(void *unused)
cpu_idle();
}
+void __init smp_store_boot_cpu_info(void)
+{
+ int id = 0; /* CPU 0 */
+ struct cpuinfo_x86 *c = &cpu_data(id);
+
+ *c = boot_cpu_data;
+ c->cpu_index = id;
+}
+
/*
* The bootstrap kernel entry code has set these up. Save them for
* a given CPU
*/
-
void __cpuinit smp_store_cpu_info(int id)
{
struct cpuinfo_x86 *c = &cpu_data(id);
*c = boot_cpu_data;
c->cpu_index = id;
- if (id != 0)
- identify_secondary_cpu(c);
+ /*
+ * During boot time, CPU0 has this setup already. Save the info when
+ * bringing up AP or offlined CPU0.
+ */
+ identify_secondary_cpu(c);
}
static bool __cpuinit
@@ -313,7 +332,7 @@ do { \
static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+ if (cpu_has_topoext) {
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
if (c->phys_proc_id == o->phys_proc_id &&
@@ -481,7 +500,7 @@ void __inquire_remote_apic(int apicid)
* won't ... remember to clear down the APIC, etc later.
*/
int __cpuinit
-wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
+wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
int maxlvt;
@@ -489,7 +508,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
/* Target chip */
/* Boot on the stack */
/* Kick the second */
- apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid);
+ apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid);
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -649,6 +668,63 @@ static void __cpuinit announce_cpu(int cpu, int apicid)
node, cpu, apicid);
}
+static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs)
+{
+ int cpu;
+
+ cpu = smp_processor_id();
+ if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0)
+ return NMI_HANDLED;
+
+ return NMI_DONE;
+}
+
+/*
+ * Wake up AP by INIT, INIT, STARTUP sequence.
+ *
+ * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS
+ * boot-strap code which is not a desired behavior for waking up BSP. To
+ * void the boot-strap code, wake up CPU0 by NMI instead.
+ *
+ * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined
+ * (i.e. physically hot removed and then hot added), NMI won't wake it up.
+ * We'll change this code in the future to wake up hard offlined CPU0 if
+ * real platform and request are available.
+ */
+static int __cpuinit
+wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
+ int *cpu0_nmi_registered)
+{
+ int id;
+ int boot_error;
+
+ /*
+ * Wake up AP by INIT, INIT, STARTUP sequence.
+ */
+ if (cpu)
+ return wakeup_secondary_cpu_via_init(apicid, start_ip);
+
+ /*
+ * Wake up BSP by nmi.
+ *
+ * Register a NMI handler to help wake up CPU0.
+ */
+ boot_error = register_nmi_handler(NMI_LOCAL,
+ wakeup_cpu0_nmi, 0, "wake_cpu0");
+
+ if (!boot_error) {
+ enable_start_cpu0 = 1;
+ *cpu0_nmi_registered = 1;
+ if (apic->dest_logical == APIC_DEST_LOGICAL)
+ id = cpu0_logical_apicid;
+ else
+ id = apicid;
+ boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
+ }
+
+ return boot_error;
+}
+
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
* (ie clustered apic addressing mode), this is a LOGICAL apic ID.
@@ -664,6 +740,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
unsigned long boot_error = 0;
int timeout;
+ int cpu0_nmi_registered = 0;
/* Just in case we booted with a single CPU. */
alternatives_enable_smp();
@@ -711,13 +788,16 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
}
/*
- * Kick the secondary CPU. Use the method in the APIC driver
- * if it's defined - or use an INIT boot APIC message otherwise:
+ * Wake up a CPU in difference cases:
+ * - Use the method in the APIC driver if it's defined
+ * Otherwise,
+ * - Use an INIT boot APIC message for APs or NMI for BSP.
*/
if (apic->wakeup_secondary_cpu)
boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
else
- boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
+ boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
+ &cpu0_nmi_registered);
if (!boot_error) {
/*
@@ -782,6 +862,13 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
*/
smpboot_restore_warm_reset_vector();
}
+ /*
+ * Clean up the nmi handler. Do this after the callin and callout sync
+ * to avoid impact of possible long unregister time.
+ */
+ if (cpu0_nmi_registered)
+ unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+
return boot_error;
}
@@ -795,7 +882,7 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu);
- if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid ||
+ if (apicid == BAD_APICID ||
!physid_isset(apicid, phys_cpu_present_map) ||
!apic->apic_id_valid(apicid)) {
pr_err("%s: bad cpu %d\n", __func__, cpu);
@@ -818,6 +905,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+ /* the FPU context is blank, nobody can own it */
+ __cpu_disable_lazy_restore(cpu);
+
err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
pr_debug("do_boot_cpu failed %d\n", err);
@@ -990,7 +1080,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
/*
* Setup boot CPU information
*/
- smp_store_cpu_info(0); /* Final full version of the data */
+ smp_store_boot_cpu_info(); /* Final full version of the data */
cpumask_copy(cpu_callin_mask, cpumask_of(0));
mb();
@@ -1026,6 +1116,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
*/
setup_local_APIC();
+ if (x2apic_mode)
+ cpu0_logical_apicid = apic_read(APIC_LDR);
+ else
+ cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+
/*
* Enable IO APIC before setting up error vector
*/
@@ -1214,19 +1309,6 @@ void cpu_disable_common(void)
int native_cpu_disable(void)
{
- int cpu = smp_processor_id();
-
- /*
- * Perhaps use cpufreq to drop frequency, but that could go
- * into generic code.
- *
- * We won't take down the boot processor on i386 due to some
- * interrupts only being able to be serviced by the BSP.
- * Especially so if we're not using an IOAPIC -zwane
- */
- if (cpu == 0)
- return -EBUSY;
-
clear_local_APIC();
cpu_disable_common();
@@ -1266,6 +1348,14 @@ void play_dead_common(void)
local_irq_disable();
}
+static bool wakeup_cpu0(void)
+{
+ if (smp_processor_id() == 0 && enable_start_cpu0)
+ return true;
+
+ return false;
+}
+
/*
* We need to flush the caches before going to sleep, lest we have
* dirty data in our caches when we come back up.
@@ -1329,6 +1419,11 @@ static inline void mwait_play_dead(void)
__monitor(mwait_ptr, 0, 0);
mb();
__mwait(eax, 0);
+ /*
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+ if (wakeup_cpu0())
+ start_cpu0();
}
}
@@ -1339,6 +1434,11 @@ static inline void hlt_play_dead(void)
while (1) {
native_halt();
+ /*
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+ if (wakeup_cpu0())
+ start_cpu0();
}
}
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index b4d3c39..97ef74b 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -21,37 +21,23 @@
/*
* Align a virtual address to avoid aliasing in the I$ on AMD F15h.
- *
- * @flags denotes the allocation direction - bottomup or topdown -
- * or vDSO; see call sites below.
*/
-unsigned long align_addr(unsigned long addr, struct file *filp,
- enum align_flags flags)
+static unsigned long get_align_mask(void)
{
- unsigned long tmp_addr;
-
/* handle 32- and 64-bit case with a single conditional */
if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
- return addr;
+ return 0;
if (!(current->flags & PF_RANDOMIZE))
- return addr;
-
- if (!((flags & ALIGN_VDSO) || filp))
- return addr;
-
- tmp_addr = addr;
-
- /*
- * We need an address which is <= than the original
- * one only when in topdown direction.
- */
- if (!(flags & ALIGN_TOPDOWN))
- tmp_addr += va_align.mask;
+ return 0;
- tmp_addr &= ~va_align.mask;
+ return va_align.mask;
+}
- return tmp_addr;
+unsigned long align_vdso_addr(unsigned long addr)
+{
+ unsigned long align_mask = get_align_mask();
+ return (addr + align_mask) & ~align_mask;
}
static int __init control_va_addr_alignment(char *str)
@@ -126,7 +112,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- unsigned long start_addr;
+ struct vm_unmapped_area_info info;
unsigned long begin, end;
if (flags & MAP_FIXED)
@@ -144,50 +130,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
(!vma || addr + len <= vma->vm_start))
return addr;
}
- if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
- && len <= mm->cached_hole_size) {
- mm->cached_hole_size = 0;
- mm->free_area_cache = begin;
- }
- addr = mm->free_area_cache;
- if (addr < begin)
- addr = begin;
- start_addr = addr;
-
-full_search:
-
- addr = align_addr(addr, filp, 0);
-
- for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
- /* At this point: (!vma || addr < vma->vm_end). */
- if (end - len < addr) {
- /*
- * Start a new search - just in case we missed
- * some holes.
- */
- if (start_addr != begin) {
- start_addr = addr = begin;
- mm->cached_hole_size = 0;
- goto full_search;
- }
- return -ENOMEM;
- }
- if (!vma || addr + len <= vma->vm_start) {
- /*
- * Remember the place where we stopped the search:
- */
- mm->free_area_cache = addr + len;
- return addr;
- }
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - addr;
- addr = vma->vm_end;
- addr = align_addr(addr, filp, 0);
- }
+ info.flags = 0;
+ info.length = len;
+ info.low_limit = begin;
+ info.high_limit = end;
+ info.align_mask = filp ? get_align_mask() : 0;
+ info.align_offset = pgoff << PAGE_SHIFT;
+ return vm_unmapped_area(&info);
}
-
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
const unsigned long len, const unsigned long pgoff,
@@ -195,7 +147,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- unsigned long addr = addr0, start_addr;
+ unsigned long addr = addr0;
+ struct vm_unmapped_area_info info;
/* requested length too big for entire address space */
if (len > TASK_SIZE)
@@ -217,51 +170,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
return addr;
}
- /* check if free_area_cache is useful for us */
- if (len <= mm->cached_hole_size) {
- mm->cached_hole_size = 0;
- mm->free_area_cache = mm->mmap_base;
- }
-
-try_again:
- /* either no address requested or can't fit in requested address hole */
- start_addr = addr = mm->free_area_cache;
-
- if (addr < len)
- goto fail;
-
- addr -= len;
- do {
- addr = align_addr(addr, filp, ALIGN_TOPDOWN);
-
- /*
- * Lookup failure means no vma is above this address,
- * else if new region fits below vma->vm_start,
- * return with success:
- */
- vma = find_vma(mm, addr);
- if (!vma || addr+len <= vma->vm_start)
- /* remember the address as a hint for next time */
- return mm->free_area_cache = addr;
-
- /* remember the largest hole we saw so far */
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - addr;
-
- /* try just below the current vma->vm_start */
- addr = vma->vm_start-len;
- } while (len < vma->vm_start);
-
-fail:
- /*
- * if hint left us with no space for the requested
- * mapping then try again:
- */
- if (start_addr != mm->mmap_base) {
- mm->free_area_cache = mm->mmap_base;
- mm->cached_hole_size = 0;
- goto try_again;
- }
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = PAGE_SIZE;
+ info.high_limit = mm->mmap_base;
+ info.align_mask = filp ? get_align_mask() : 0;
+ info.align_offset = pgoff << PAGE_SHIFT;
+ addr = vm_unmapped_area(&info);
+ if (!(addr & ~PAGE_MASK))
+ return addr;
+ VM_BUG_ON(addr != -ENOMEM);
bottomup:
/*
@@ -270,14 +188,5 @@ bottomup:
* can happen with large stack limits and large mmap()
* allocations.
*/
- mm->cached_hole_size = ~0UL;
- mm->free_area_cache = TASK_UNMAPPED_BASE;
- addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
- /*
- * Restore the topdown base:
- */
- mm->free_area_cache = mm->mmap_base;
- mm->cached_hole_size = ~0UL;
-
- return addr;
+ return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 76ee977..6e60b5f 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -30,23 +30,110 @@
#include <linux/mmzone.h>
#include <linux/init.h>
#include <linux/smp.h>
+#include <linux/irq.h>
#include <asm/cpu.h>
static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
#ifdef CONFIG_HOTPLUG_CPU
+
+#ifdef CONFIG_BOOTPARAM_HOTPLUG_CPU0
+static int cpu0_hotpluggable = 1;
+#else
+static int cpu0_hotpluggable;
+static int __init enable_cpu0_hotplug(char *str)
+{
+ cpu0_hotpluggable = 1;
+ return 1;
+}
+
+__setup("cpu0_hotplug", enable_cpu0_hotplug);
+#endif
+
+#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
+/*
+ * This function offlines a CPU as early as possible and allows userspace to
+ * boot up without the CPU. The CPU can be onlined back by user after boot.
+ *
+ * This is only called for debugging CPU offline/online feature.
+ */
+int __ref _debug_hotplug_cpu(int cpu, int action)
+{
+ struct device *dev = get_cpu_device(cpu);
+ int ret;
+
+ if (!cpu_is_hotpluggable(cpu))
+ return -EINVAL;
+
+ cpu_hotplug_driver_lock();
+
+ switch (action) {
+ case 0:
+ ret = cpu_down(cpu);
+ if (!ret) {
+ pr_info("CPU %u is now offline\n", cpu);
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+ } else
+ pr_debug("Can't offline CPU%d.\n", cpu);
+ break;
+ case 1:
+ ret = cpu_up(cpu);
+ if (!ret)
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+ else
+ pr_debug("Can't online CPU%d.\n", cpu);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ cpu_hotplug_driver_unlock();
+
+ return ret;
+}
+
+static int __init debug_hotplug_cpu(void)
+{
+ _debug_hotplug_cpu(0, 0);
+ return 0;
+}
+
+late_initcall_sync(debug_hotplug_cpu);
+#endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */
+
int __ref arch_register_cpu(int num)
{
+ struct cpuinfo_x86 *c = &cpu_data(num);
+
+ /*
+ * Currently CPU0 is only hotpluggable on Intel platforms. Other
+ * vendors can add hotplug support later.
+ */
+ if (c->x86_vendor != X86_VENDOR_INTEL)
+ cpu0_hotpluggable = 0;
+
/*
- * CPU0 cannot be offlined due to several
- * restrictions and assumptions in kernel. This basically
- * doesn't add a control file, one cannot attempt to offline
- * BSP.
+ * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate
+ * depends on BSP. PIC interrupts depend on BSP.
*
- * Also certain PCI quirks require not to enable hotplug control
- * for all CPU's.
+ * If the BSP depencies are under control, one can tell kernel to
+ * enable BSP hotplug. This basically adds a control file and
+ * one can attempt to offline BSP.
*/
- if (num)
+ if (num == 0 && cpu0_hotpluggable) {
+ unsigned int irq;
+ /*
+ * We won't take down the boot processor on i386 if some
+ * interrupts only are able to be serviced by the BSP in PIC.
+ */
+ for_each_active_irq(irq) {
+ if (!IO_APIC_IRQ(irq) && irq_has_action(irq)) {
+ cpu0_hotpluggable = 0;
+ break;
+ }
+ }
+ }
+ if (num || cpu0_hotpluggable)
per_cpu(cpu_devices, num).cpu.hotpluggable = 1;
return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
new file mode 100644
index 0000000..25b9937
--- /dev/null
+++ b/arch/x86/kernel/trace_clock.c
@@ -0,0 +1,21 @@
+/*
+ * X86 trace clocks
+ */
+#include <asm/trace_clock.h>
+#include <asm/barrier.h>
+#include <asm/msr.h>
+
+/*
+ * trace_clock_x86_tsc(): A clock that is just the cycle counter.
+ *
+ * Unlike the other clocks, this is not in nanoseconds.
+ */
+u64 notrace trace_clock_x86_tsc(void)
+{
+ u64 ret;
+
+ rdtsc_barrier();
+ rdtscll(ret);
+
+ return ret;
+}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8276dc6..eb85866 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,7 +55,7 @@
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/mce.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
#include <asm/mach_traps.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfa5d4f..06ccb50 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -77,6 +77,12 @@ unsigned long long
sched_clock(void) __attribute__((alias("native_sched_clock")));
#endif
+unsigned long long native_read_tsc(void)
+{
+ return __native_read_tsc();
+}
+EXPORT_SYMBOL(native_read_tsc);
+
int check_tsc_unstable(void)
{
return tsc_unstable;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index aafa555..c71025b 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -478,6 +478,11 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
regs->ip = current->utask->xol_vaddr;
pre_xol_rip_insn(auprobe, regs, autask);
+ autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
+ regs->flags |= X86_EFLAGS_TF;
+ if (test_tsk_thread_flag(current, TIF_BLOCKSTEP))
+ set_task_blockstep(current, false);
+
return 0;
}
@@ -603,6 +608,16 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
if (auprobe->fixups & UPROBE_FIX_CALL)
result = adjust_ret_addr(regs->sp, correction);
+ /*
+ * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP
+ * so we can get an extra SIGTRAP if we do not clear TF. We need
+ * to examine the opcode to make it right.
+ */
+ if (utask->autask.saved_tf)
+ send_sig(SIGTRAP, current, 0);
+ else if (!(auprobe->fixups & UPROBE_FIX_SETF))
+ regs->flags &= ~X86_EFLAGS_TF;
+
return result;
}
@@ -647,6 +662,10 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
current->thread.trap_nr = utask->autask.saved_trap_nr;
handle_riprel_post_xol(auprobe, regs, NULL);
instruction_pointer_set(regs, utask->vaddr);
+
+ /* clear TF if it was set by us in arch_uprobe_pre_xol() */
+ if (!utask->autask.saved_tf)
+ regs->flags &= ~X86_EFLAGS_TF;
}
/*
@@ -676,38 +695,3 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
send_sig(SIGTRAP, current, 0);
return ret;
}
-
-void arch_uprobe_enable_step(struct arch_uprobe *auprobe)
-{
- struct task_struct *task = current;
- struct arch_uprobe_task *autask = &task->utask->autask;
- struct pt_regs *regs = task_pt_regs(task);
-
- autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
-
- regs->flags |= X86_EFLAGS_TF;
- if (test_tsk_thread_flag(task, TIF_BLOCKSTEP))
- set_task_blockstep(task, false);
-}
-
-void arch_uprobe_disable_step(struct arch_uprobe *auprobe)
-{
- struct task_struct *task = current;
- struct arch_uprobe_task *autask = &task->utask->autask;
- bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED);
- struct pt_regs *regs = task_pt_regs(task);
- /*
- * The state of TIF_BLOCKSTEP was not saved so we can get an extra
- * SIGTRAP if we do not clear TF. We need to examine the opcode to
- * make it right.
- */
- if (unlikely(trapped)) {
- if (!autask->saved_tf)
- regs->flags &= ~X86_EFLAGS_TF;
- } else {
- if (autask->saved_tf)
- send_sig(SIGTRAP, task, 0);
- else if (!(auprobe->fixups & UPROBE_FIX_SETF))
- regs->flags &= ~X86_EFLAGS_TF;
- }
-}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5c9687b..1dfe69c 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
if (pud_none_or_clear_bad(pud))
goto out;
pmd = pmd_offset(pud, 0xA0000);
- split_huge_page_pmd(mm, pmd);
+ split_huge_page_pmd_mm(mm, 0xA0000, pmd);
if (pmd_none_or_clear_bad(pmd))
goto out;
pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a10e460..58fc514 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -24,6 +24,9 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
+ if (!static_cpu_has(X86_FEATURE_XSAVE))
+ return 0;
+
best = kvm_find_cpuid_entry(vcpu, 1, 0);
return best && (best->ecx & bit(X86_FEATURE_XSAVE));
}
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 39171cb..bba39bf 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -426,8 +426,7 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
_ASM_EXTABLE(1b, 3b) \
: "=m" ((ctxt)->eflags), "=&r" (_tmp), \
"+a" (*rax), "+d" (*rdx), "+qm"(_ex) \
- : "i" (EFLAGS_MASK), "m" ((ctxt)->src.val), \
- "a" (*rax), "d" (*rdx)); \
+ : "i" (EFLAGS_MASK), "m" ((ctxt)->src.val)); \
} while (0)
/* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ad6b1dd..f858159 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6549,19 +6549,22 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
}
}
- exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
/* Exposing INVPCID only when PCID is exposed */
best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
if (vmx_invpcid_supported() &&
best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
guest_cpuid_has_pcid(vcpu)) {
+ exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
exec_control);
} else {
- exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
- vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
- exec_control);
+ if (cpu_has_secondary_exec_ctrls()) {
+ exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+ exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+ vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+ exec_control);
+ }
if (best)
best->ebx &= ~bit(X86_FEATURE_INVPCID);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1eefebe..4f76417 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3779,7 +3779,7 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
{
struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
- memcpy(vcpu->run->mmio.data, frag->data, frag->len);
+ memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
return X86EMUL_CONTINUE;
}
@@ -3832,18 +3832,11 @@ mmio:
bytes -= handled;
val += handled;
- while (bytes) {
- unsigned now = min(bytes, 8U);
-
- frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
- frag->gpa = gpa;
- frag->data = val;
- frag->len = now;
-
- gpa += now;
- val += now;
- bytes -= now;
- }
+ WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS);
+ frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+ frag->gpa = gpa;
+ frag->data = val;
+ frag->len = bytes;
return X86EMUL_CONTINUE;
}
@@ -3890,7 +3883,7 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
vcpu->mmio_needed = 1;
vcpu->mmio_cur_fragment = 0;
- vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+ vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len);
vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
vcpu->run->exit_reason = KVM_EXIT_MMIO;
vcpu->run->mmio.phys_addr = gpa;
@@ -5522,28 +5515,44 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu)
*
* read:
* for each fragment
- * write gpa, len
- * exit
- * copy data
+ * for each mmio piece in the fragment
+ * write gpa, len
+ * exit
+ * copy data
* execute insn
*
* write:
* for each fragment
- * write gpa, len
- * copy data
- * exit
+ * for each mmio piece in the fragment
+ * write gpa, len
+ * copy data
+ * exit
*/
static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
struct kvm_mmio_fragment *frag;
+ unsigned len;
BUG_ON(!vcpu->mmio_needed);
/* Complete previous fragment */
- frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
+ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+ len = min(8u, frag->len);
if (!vcpu->mmio_is_write)
- memcpy(frag->data, run->mmio.data, frag->len);
+ memcpy(frag->data, run->mmio.data, len);
+
+ if (frag->len <= 8) {
+ /* Switch to the next fragment. */
+ frag++;
+ vcpu->mmio_cur_fragment++;
+ } else {
+ /* Go forward to the next mmio piece. */
+ frag->data += len;
+ frag->gpa += len;
+ frag->len -= len;
+ }
+
if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
if (vcpu->mmio_is_write)
@@ -5551,13 +5560,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
vcpu->mmio_read_completed = 1;
return complete_emulated_io(vcpu);
}
- /* Initiate next fragment */
- ++frag;
+
run->exit_reason = KVM_EXIT_MMIO;
run->mmio.phys_addr = frag->gpa;
if (vcpu->mmio_is_write)
- memcpy(run->mmio.data, frag->data, frag->len);
- run->mmio.len = frag->len;
+ memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+ run->mmio.len = min(8u, frag->len);
run->mmio.is_write = vcpu->mmio_is_write;
vcpu->arch.complete_userspace_io = complete_emulated_mmio;
return 0;
@@ -5773,6 +5781,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
int pending_vec, max_bits, idx;
struct desc_ptr dt;
+ if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+ return -EINVAL;
+
dt.size = sregs->idt.limit;
dt.address = sregs->idt.base;
kvm_x86_ops->set_idt(vcpu, &dt);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index b00f678..96b2c66 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -32,7 +32,6 @@ ifeq ($(CONFIG_X86_32),y)
lib-y += checksum_32.o
lib-y += strstr_32.o
lib-y += string_32.o
- lib-y += cmpxchg.o
ifneq ($(CONFIG_X86_CMPXCHG64),y)
lib-y += cmpxchg8b_emu.o atomic64_386_32.o
endif
diff --git a/arch/x86/lib/cmpxchg.c b/arch/x86/lib/cmpxchg.c
deleted file mode 100644
index 5d619f6d..0000000
--- a/arch/x86/lib/cmpxchg.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * cmpxchg*() fallbacks for CPU not supporting these instructions
- */
-
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-
-#ifndef CONFIG_X86_CMPXCHG
-unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
-{
- u8 prev;
- unsigned long flags;
-
- /* Poor man's cmpxchg for 386. Unsuitable for SMP */
- local_irq_save(flags);
- prev = *(u8 *)ptr;
- if (prev == old)
- *(u8 *)ptr = new;
- local_irq_restore(flags);
- return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u8);
-
-unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
-{
- u16 prev;
- unsigned long flags;
-
- /* Poor man's cmpxchg for 386. Unsuitable for SMP */
- local_irq_save(flags);
- prev = *(u16 *)ptr;
- if (prev == old)
- *(u16 *)ptr = new;
- local_irq_restore(flags);
- return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u16);
-
-unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
-{
- u32 prev;
- unsigned long flags;
-
- /* Poor man's cmpxchg for 386. Unsuitable for SMP */
- local_irq_save(flags);
- prev = *(u32 *)ptr;
- if (prev == old)
- *(u32 *)ptr = new;
- local_irq_restore(flags);
- return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u32);
-#endif
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 6b34d04..176cca6 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -5,91 +5,89 @@
#include <asm/alternative-asm.h>
ALIGN
-copy_page_c:
+copy_page_rep:
CFI_STARTPROC
- movl $4096/8,%ecx
- rep movsq
+ movl $4096/8, %ecx
+ rep movsq
ret
CFI_ENDPROC
-ENDPROC(copy_page_c)
+ENDPROC(copy_page_rep)
-/* Don't use streaming store because it's better when the target
- ends up in cache. */
-
-/* Could vary the prefetch distance based on SMP/UP */
+/*
+ * Don't use streaming copy unless the CPU indicates X86_FEATURE_REP_GOOD.
+ * Could vary the prefetch distance based on SMP/UP.
+*/
ENTRY(copy_page)
CFI_STARTPROC
- subq $2*8,%rsp
+ subq $2*8, %rsp
CFI_ADJUST_CFA_OFFSET 2*8
- movq %rbx,(%rsp)
+ movq %rbx, (%rsp)
CFI_REL_OFFSET rbx, 0
- movq %r12,1*8(%rsp)
+ movq %r12, 1*8(%rsp)
CFI_REL_OFFSET r12, 1*8
- movl $(4096/64)-5,%ecx
+ movl $(4096/64)-5, %ecx
.p2align 4
.Loop64:
- dec %rcx
-
- movq (%rsi), %rax
- movq 8 (%rsi), %rbx
- movq 16 (%rsi), %rdx
- movq 24 (%rsi), %r8
- movq 32 (%rsi), %r9
- movq 40 (%rsi), %r10
- movq 48 (%rsi), %r11
- movq 56 (%rsi), %r12
+ dec %rcx
+ movq 0x8*0(%rsi), %rax
+ movq 0x8*1(%rsi), %rbx
+ movq 0x8*2(%rsi), %rdx
+ movq 0x8*3(%rsi), %r8
+ movq 0x8*4(%rsi), %r9
+ movq 0x8*5(%rsi), %r10
+ movq 0x8*6(%rsi), %r11
+ movq 0x8*7(%rsi), %r12
prefetcht0 5*64(%rsi)
- movq %rax, (%rdi)
- movq %rbx, 8 (%rdi)
- movq %rdx, 16 (%rdi)
- movq %r8, 24 (%rdi)
- movq %r9, 32 (%rdi)
- movq %r10, 40 (%rdi)
- movq %r11, 48 (%rdi)
- movq %r12, 56 (%rdi)
+ movq %rax, 0x8*0(%rdi)
+ movq %rbx, 0x8*1(%rdi)
+ movq %rdx, 0x8*2(%rdi)
+ movq %r8, 0x8*3(%rdi)
+ movq %r9, 0x8*4(%rdi)
+ movq %r10, 0x8*5(%rdi)
+ movq %r11, 0x8*6(%rdi)
+ movq %r12, 0x8*7(%rdi)
- leaq 64 (%rsi), %rsi
- leaq 64 (%rdi), %rdi
+ leaq 64 (%rsi), %rsi
+ leaq 64 (%rdi), %rdi
- jnz .Loop64
+ jnz .Loop64
- movl $5,%ecx
+ movl $5, %ecx
.p2align 4
.Loop2:
- decl %ecx
-
- movq (%rsi), %rax
- movq 8 (%rsi), %rbx
- movq 16 (%rsi), %rdx
- movq 24 (%rsi), %r8
- movq 32 (%rsi), %r9
- movq 40 (%rsi), %r10
- movq 48 (%rsi), %r11
- movq 56 (%rsi), %r12
-
- movq %rax, (%rdi)
- movq %rbx, 8 (%rdi)
- movq %rdx, 16 (%rdi)
- movq %r8, 24 (%rdi)
- movq %r9, 32 (%rdi)
- movq %r10, 40 (%rdi)
- movq %r11, 48 (%rdi)
- movq %r12, 56 (%rdi)
-
- leaq 64(%rdi),%rdi
- leaq 64(%rsi),%rsi
-
+ decl %ecx
+
+ movq 0x8*0(%rsi), %rax
+ movq 0x8*1(%rsi), %rbx
+ movq 0x8*2(%rsi), %rdx
+ movq 0x8*3(%rsi), %r8
+ movq 0x8*4(%rsi), %r9
+ movq 0x8*5(%rsi), %r10
+ movq 0x8*6(%rsi), %r11
+ movq 0x8*7(%rsi), %r12
+
+ movq %rax, 0x8*0(%rdi)
+ movq %rbx, 0x8*1(%rdi)
+ movq %rdx, 0x8*2(%rdi)
+ movq %r8, 0x8*3(%rdi)
+ movq %r9, 0x8*4(%rdi)
+ movq %r10, 0x8*5(%rdi)
+ movq %r11, 0x8*6(%rdi)
+ movq %r12, 0x8*7(%rdi)
+
+ leaq 64(%rdi), %rdi
+ leaq 64(%rsi), %rsi
jnz .Loop2
- movq (%rsp),%rbx
+ movq (%rsp), %rbx
CFI_RESTORE rbx
- movq 1*8(%rsp),%r12
+ movq 1*8(%rsp), %r12
CFI_RESTORE r12
- addq $2*8,%rsp
+ addq $2*8, %rsp
CFI_ADJUST_CFA_OFFSET -2*8
ret
.Lcopy_page_end:
@@ -103,7 +101,7 @@ ENDPROC(copy_page)
.section .altinstr_replacement,"ax"
1: .byte 0xeb /* jmp <disp8> */
- .byte (copy_page_c - copy_page) - (2f - 1b) /* offset */
+ .byte (copy_page_rep - copy_page) - (2f - 1b) /* offset */
2:
.previous
.section .altinstructions,"a"
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 98f6d6b6..f0312d7 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,63 +570,6 @@ do { \
unsigned long __copy_to_user_ll(void __user *to, const void *from,
unsigned long n)
{
-#ifndef CONFIG_X86_WP_WORKS_OK
- if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
- ((unsigned long)to) < TASK_SIZE) {
- /*
- * When we are in an atomic section (see
- * mm/filemap.c:file_read_actor), return the full
- * length to take the slow path.
- */
- if (in_atomic())
- return n;
-
- /*
- * CPU does not honor the WP bit when writing
- * from supervisory mode, and due to preemption or SMP,
- * the page tables can change at any time.
- * Do it manually. Manfred <manfred@colorfullife.com>
- */
- while (n) {
- unsigned long offset = ((unsigned long)to)%PAGE_SIZE;
- unsigned long len = PAGE_SIZE - offset;
- int retval;
- struct page *pg;
- void *maddr;
-
- if (len > n)
- len = n;
-
-survive:
- down_read(&current->mm->mmap_sem);
- retval = get_user_pages(current, current->mm,
- (unsigned long)to, 1, 1, 0, &pg, NULL);
-
- if (retval == -ENOMEM && is_global_init(current)) {
- up_read(&current->mm->mmap_sem);
- congestion_wait(BLK_RW_ASYNC, HZ/50);
- goto survive;
- }
-
- if (retval != 1) {
- up_read(&current->mm->mmap_sem);
- break;
- }
-
- maddr = kmap_atomic(pg);
- memcpy(maddr + offset, from, len);
- kunmap_atomic(maddr);
- set_page_dirty_lock(pg);
- put_page(pg);
- up_read(&current->mm->mmap_sem);
-
- from += len;
- to += len;
- n -= len;
- }
- return n;
- }
-#endif
stac();
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8e13ecb..027088f 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,7 +18,7 @@
#include <asm/pgalloc.h> /* pgd_*(), ... */
#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
#include <asm/fixmap.h> /* VSYSCALL_START */
-#include <asm/rcu.h> /* exception_enter(), ... */
+#include <asm/context_tracking.h> /* exception_enter(), ... */
/*
* Page fault error code bits:
@@ -803,20 +803,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
__bad_area(regs, error_code, address, SEGV_ACCERR);
}
-/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
-static void
-out_of_memory(struct pt_regs *regs, unsigned long error_code,
- unsigned long address)
-{
- /*
- * We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed):
- */
- up_read(&current->mm->mmap_sem);
-
- pagefault_out_of_memory();
-}
-
static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
unsigned int fault)
@@ -879,7 +865,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
return 1;
}
- out_of_memory(regs, error_code, address);
+ up_read(&current->mm->mmap_sem);
+
+ /*
+ * We ran out of memory, call the OOM killer, and return the
+ * userspace (which will retry the fault, or kill us if we got
+ * oom-killed):
+ */
+ pagefault_out_of_memory();
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 937bff5..ae1aa71 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -274,42 +274,15 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- unsigned long start_addr;
-
- if (len > mm->cached_hole_size) {
- start_addr = mm->free_area_cache;
- } else {
- start_addr = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = 0;
- }
-
-full_search:
- addr = ALIGN(start_addr, huge_page_size(h));
-
- for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
- /* At this point: (!vma || addr < vma->vm_end). */
- if (TASK_SIZE - len < addr) {
- /*
- * Start a new search - just in case we missed
- * some holes.
- */
- if (start_addr != TASK_UNMAPPED_BASE) {
- start_addr = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = 0;
- goto full_search;
- }
- return -ENOMEM;
- }
- if (!vma || addr + len <= vma->vm_start) {
- mm->free_area_cache = addr + len;
- return addr;
- }
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - addr;
- addr = ALIGN(vma->vm_end, huge_page_size(h));
- }
+ struct vm_unmapped_area_info info;
+
+ info.flags = 0;
+ info.length = len;
+ info.low_limit = TASK_UNMAPPED_BASE;
+ info.high_limit = TASK_SIZE;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+ return vm_unmapped_area(&info);
}
static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
@@ -317,83 +290,30 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- unsigned long base = mm->mmap_base;
- unsigned long addr = addr0;
- unsigned long largest_hole = mm->cached_hole_size;
- unsigned long start_addr;
-
- /* don't allow allocations above current base */
- if (mm->free_area_cache > base)
- mm->free_area_cache = base;
-
- if (len <= largest_hole) {
- largest_hole = 0;
- mm->free_area_cache = base;
- }
-try_again:
- start_addr = mm->free_area_cache;
-
- /* make sure it can fit in the remaining address space */
- if (mm->free_area_cache < len)
- goto fail;
-
- /* either no address requested or can't fit in requested address hole */
- addr = (mm->free_area_cache - len) & huge_page_mask(h);
- do {
- /*
- * Lookup failure means no vma is above this address,
- * i.e. return with success:
- */
- vma = find_vma(mm, addr);
- if (!vma)
- return addr;
+ struct vm_unmapped_area_info info;
+ unsigned long addr;
- if (addr + len <= vma->vm_start) {
- /* remember the address as a hint for next time */
- mm->cached_hole_size = largest_hole;
- return (mm->free_area_cache = addr);
- } else if (mm->free_area_cache == vma->vm_end) {
- /* pull free_area_cache down to the first hole */
- mm->free_area_cache = vma->vm_start;
- mm->cached_hole_size = largest_hole;
- }
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = PAGE_SIZE;
+ info.high_limit = current->mm->mmap_base;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+ addr = vm_unmapped_area(&info);
- /* remember the largest hole we saw so far */
- if (addr + largest_hole < vma->vm_start)
- largest_hole = vma->vm_start - addr;
-
- /* try just below the current vma->vm_start */
- addr = (vma->vm_start - len) & huge_page_mask(h);
- } while (len <= vma->vm_start);
-
-fail:
- /*
- * if hint left us with no space for the requested
- * mapping then try again:
- */
- if (start_addr != base) {
- mm->free_area_cache = base;
- largest_hole = 0;
- goto try_again;
- }
/*
* A failed mmap() very likely causes application failure,
* so fall back to the bottom-up function here. This scenario
* can happen with large stack limits and large mmap()
* allocations.
*/
- mm->free_area_cache = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = ~0UL;
- addr = hugetlb_get_unmapped_area_bottomup(file, addr0,
- len, pgoff, flags);
-
- /*
- * Restore the topdown base:
- */
- mm->free_area_cache = base;
- mm->cached_hole_size = ~0UL;
+ if (addr & ~PAGE_MASK) {
+ VM_BUG_ON(addr != -ENOMEM);
+ info.flags = 0;
+ info.low_limit = TASK_UNMAPPED_BASE;
+ info.high_limit = TASK_SIZE;
+ addr = vm_unmapped_area(&info);
+ }
return addr;
}
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 11a5800..745d66b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -715,10 +715,7 @@ static void __init test_wp_bit(void)
if (!boot_cpu_data.wp_works_ok) {
printk(KERN_CONT "No.\n");
-#ifdef CONFIG_X86_WP_WORKS_OK
- panic(
- "This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
-#endif
+ panic("Linux doesn't support CPUs with broken WP.");
} else {
printk(KERN_CONT "Ok.\n");
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3baff25..2ead3c8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -630,7 +630,9 @@ void __init paging_init(void)
* numa support is not compiled in, and later node_set_state
* will not set it back.
*/
- node_clear_state(0, N_NORMAL_MEMORY);
+ node_clear_state(0, N_MEMORY);
+ if (N_MEMORY != N_NORMAL_MEMORY)
+ node_clear_state(0, N_NORMAL_MEMORY);
zone_sizes_init();
}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 8573b83..217eb70 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -137,7 +137,7 @@ static void pgd_dtor(pgd_t *pgd)
* against pageattr.c; it is the unique case in which a valid change
* of kernel pagetables can't be lazily synchronized by vmalloc faults.
* vmalloc faults work because attached pagetables are never freed.
- * -- wli
+ * -- nyc
*/
#ifdef CONFIG_X86_PAE
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0777f04..13a6b29 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -104,7 +104,7 @@ static void flush_tlb_func(void *info)
return;
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
- if (f->flush_end == TLB_FLUSH_ALL || !cpu_has_invlpg)
+ if (f->flush_end == TLB_FLUSH_ALL)
local_flush_tlb();
else if (!f->flush_end)
__flush_tlb_single(f->flush_start);
@@ -197,7 +197,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
}
if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
- || vmflag == VM_HUGETLB) {
+ || vmflag & VM_HUGETLB) {
local_flush_tlb();
goto flush_all;
}
@@ -337,10 +337,8 @@ static const struct file_operations fops_tlbflush = {
static int __cpuinit create_tlb_flushall_shift(void)
{
- if (cpu_has_invlpg) {
- debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
- arch_debugfs_dir, NULL, &fops_tlbflush);
- }
+ debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
+ arch_debugfs_dir, NULL, &fops_tlbflush);
return 0;
}
late_initcall(create_tlb_flushall_shift);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 520d2bd..d11a470 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@
#include <asm/cacheflush.h>
#include <linux/netdevice.h>
#include <linux/filter.h>
+#include <linux/if_vlan.h>
/*
* Conventions :
@@ -212,6 +213,8 @@ void bpf_jit_compile(struct sk_filter *fp)
case BPF_S_ANC_MARK:
case BPF_S_ANC_RXHASH:
case BPF_S_ANC_CPU:
+ case BPF_S_ANC_VLAN_TAG:
+ case BPF_S_ANC_VLAN_TAG_PRESENT:
case BPF_S_ANC_QUEUE:
case BPF_S_LD_W_ABS:
case BPF_S_LD_H_ABS:
@@ -515,6 +518,24 @@ void bpf_jit_compile(struct sk_filter *fp)
CLEAR_A();
#endif
break;
+ case BPF_S_ANC_VLAN_TAG:
+ case BPF_S_ANC_VLAN_TAG_PRESENT:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+ if (is_imm8(offsetof(struct sk_buff, vlan_tci))) {
+ /* movzwl off8(%rdi),%eax */
+ EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, vlan_tci));
+ } else {
+ EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
+ EMIT(offsetof(struct sk_buff, vlan_tci), 4);
+ }
+ BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+ if (filter[i].code == BPF_S_ANC_VLAN_TAG) {
+ EMIT3(0x80, 0xe4, 0xef); /* and $0xef,%ah */
+ } else {
+ EMIT3(0xc1, 0xe8, 0x0c); /* shr $0xc,%eax */
+ EMIT3(0x83, 0xe0, 0x01); /* and $0x1,%eax */
+ }
+ break;
case BPF_S_LD_W_ABS:
func = CHOOSE_LOAD_FUNC(K, sk_load_word);
common_load: seen |= SEEN_DATAREF;
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 3af5a1e..ee0af58 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_STA2X11) += sta2x11-fixup.o
obj-$(CONFIG_X86_VISWS) += visws.o
obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
+obj-$(CONFIG_X86_NUMACHIP) += numachip.o
obj-$(CONFIG_X86_INTEL_MID) += mrst.o
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 192397c..0c01261 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -12,6 +12,7 @@ struct pci_root_info {
char name[16];
unsigned int res_num;
struct resource *res;
+ resource_size_t *res_offset;
struct pci_sysdata sd;
#ifdef CONFIG_PCI_MMCONFIG
bool mcfg_added;
@@ -22,6 +23,7 @@ struct pci_root_info {
};
static bool pci_use_crs = true;
+static bool pci_ignore_seg = false;
static int __init set_use_crs(const struct dmi_system_id *id)
{
@@ -35,7 +37,14 @@ static int __init set_nouse_crs(const struct dmi_system_id *id)
return 0;
}
-static const struct dmi_system_id pci_use_crs_table[] __initconst = {
+static int __init set_ignore_seg(const struct dmi_system_id *id)
+{
+ printk(KERN_INFO "PCI: %s detected: ignoring ACPI _SEG\n", id->ident);
+ pci_ignore_seg = true;
+ return 0;
+}
+
+static const struct dmi_system_id pci_crs_quirks[] __initconst = {
/* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
{
.callback = set_use_crs,
@@ -98,6 +107,16 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = {
DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
},
},
+
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
+ {
+ .callback = set_ignore_seg,
+ .ident = "HP xw9300",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP xw9300 Workstation"),
+ },
+ },
{}
};
@@ -108,7 +127,7 @@ void __init pci_acpi_crs_quirks(void)
if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
pci_use_crs = false;
- dmi_check_system(pci_use_crs_table);
+ dmi_check_system(pci_crs_quirks);
/*
* If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that
@@ -305,6 +324,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
res->flags = flags;
res->start = start;
res->end = end;
+ info->res_offset[info->res_num] = addr.translation_offset;
if (!pci_use_crs) {
dev_printk(KERN_DEBUG, &info->bridge->dev,
@@ -374,7 +394,8 @@ static void add_resources(struct pci_root_info *info,
"ignoring host bridge window %pR (conflicts with %s %pR)\n",
res, conflict->name, conflict);
else
- pci_add_resource(resources, res);
+ pci_add_resource_offset(resources, res,
+ info->res_offset[i]);
}
}
@@ -382,6 +403,8 @@ static void free_pci_root_info_res(struct pci_root_info *info)
{
kfree(info->res);
info->res = NULL;
+ kfree(info->res_offset);
+ info->res_offset = NULL;
info->res_num = 0;
}
@@ -432,10 +455,20 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
return;
size = sizeof(*info->res) * info->res_num;
- info->res_num = 0;
info->res = kzalloc(size, GFP_KERNEL);
- if (!info->res)
+ if (!info->res) {
+ info->res_num = 0;
+ return;
+ }
+
+ size = sizeof(*info->res_offset) * info->res_num;
+ info->res_num = 0;
+ info->res_offset = kzalloc(size, GFP_KERNEL);
+ if (!info->res_offset) {
+ kfree(info->res);
+ info->res = NULL;
return;
+ }
acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
info);
@@ -455,6 +488,9 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
int pxm;
#endif
+ if (pci_ignore_seg)
+ domain = 0;
+
if (domain && !pci_domains_supported) {
printk(KERN_WARNING "pci_bus %04x:%02x: "
"ignored (multiple domains not supported)\n",
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 41bd2a2..b914e20 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -115,6 +115,16 @@ static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
reg_read(reg, value);
}
+static void reg_noirq_read(struct sim_dev_reg *reg, u32 *value)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+ /* force interrupt pin value to 0 */
+ *value = reg->sim_reg.value & 0xfff00ff;
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
static struct sim_dev_reg bus1_fixups[] = {
DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
@@ -144,6 +154,7 @@ static struct sim_dev_reg bus1_fixups[] = {
DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 7, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
@@ -161,8 +172,10 @@ static struct sim_dev_reg bus1_fixups[] = {
DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(16, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(18, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
};
static void __init init_sim_regs(void)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 720e973f..1b1dda9 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -17,6 +17,7 @@
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/pci_x86.h>
+#include <asm/setup.h>
unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
PCI_PROBE_MMCONF;
@@ -608,6 +609,35 @@ unsigned int pcibios_assign_all_busses(void)
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
+int pcibios_add_device(struct pci_dev *dev)
+{
+ struct setup_data *data;
+ struct pci_setup_rom *rom;
+ u64 pa_data;
+
+ pa_data = boot_params.hdr.setup_data;
+ while (pa_data) {
+ data = phys_to_virt(pa_data);
+
+ if (data->type == SETUP_PCI) {
+ rom = (struct pci_setup_rom *)data;
+
+ if ((pci_domain_nr(dev->bus) == rom->segment) &&
+ (dev->bus->number == rom->bus) &&
+ (PCI_SLOT(dev->devfn) == rom->device) &&
+ (PCI_FUNC(dev->devfn) == rom->function) &&
+ (dev->vendor == rom->vendor) &&
+ (dev->device == rom->devid)) {
+ dev->rom = pa_data +
+ offsetof(struct pci_setup_rom, romdata);
+ dev->romlen = rom->pcilen;
+ }
+ }
+ pa_data = data->next;
+ }
+ return 0;
+}
+
int pcibios_enable_device(struct pci_dev *dev, int mask)
{
int err;
@@ -626,7 +656,7 @@ void pcibios_disable_device (struct pci_dev *dev)
pcibios_disable_irq(dev);
}
-int pci_ext_cfg_avail(struct pci_dev *dev)
+int pci_ext_cfg_avail(void)
{
if (raw_pci_ext_ops)
return 1;
diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c
new file mode 100644
index 0000000..7307d9d
--- /dev/null
+++ b/arch/x86/pci/numachip.c
@@ -0,0 +1,129 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-specific PCI code
+ *
+ * Copyright (C) 2012 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ * PCI accessor functions derived from mmconfig_64.c
+ *
+ */
+
+#include <linux/pci.h>
+#include <asm/pci_x86.h>
+
+static u8 limit __read_mostly;
+
+static inline char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+{
+ struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
+
+ if (cfg && cfg->virt)
+ return cfg->virt + (PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12));
+ return NULL;
+}
+
+static int pci_mmcfg_read_numachip(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ char __iomem *addr;
+
+ /* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+ if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) {
+err: *value = -1;
+ return -EINVAL;
+ }
+
+ /* Ensure AMD Northbridges don't decode reads to other devices */
+ if (unlikely(bus == 0 && devfn >= limit)) {
+ *value = -1;
+ return 0;
+ }
+
+ rcu_read_lock();
+ addr = pci_dev_base(seg, bus, devfn);
+ if (!addr) {
+ rcu_read_unlock();
+ goto err;
+ }
+
+ switch (len) {
+ case 1:
+ *value = mmio_config_readb(addr + reg);
+ break;
+ case 2:
+ *value = mmio_config_readw(addr + reg);
+ break;
+ case 4:
+ *value = mmio_config_readl(addr + reg);
+ break;
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int pci_mmcfg_write_numachip(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ char __iomem *addr;
+
+ /* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+ if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
+ return -EINVAL;
+
+ /* Ensure AMD Northbridges don't decode writes to other devices */
+ if (unlikely(bus == 0 && devfn >= limit))
+ return 0;
+
+ rcu_read_lock();
+ addr = pci_dev_base(seg, bus, devfn);
+ if (!addr) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ switch (len) {
+ case 1:
+ mmio_config_writeb(addr + reg, value);
+ break;
+ case 2:
+ mmio_config_writew(addr + reg, value);
+ break;
+ case 4:
+ mmio_config_writel(addr + reg, value);
+ break;
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+const struct pci_raw_ops pci_mmcfg_numachip = {
+ .read = pci_mmcfg_read_numachip,
+ .write = pci_mmcfg_write_numachip,
+};
+
+int __init pci_numachip_init(void)
+{
+ int ret = 0;
+ u32 val;
+
+ /* For remote I/O, restrict bus 0 access to the actual number of AMD
+ Northbridges, which starts at device number 0x18 */
+ ret = raw_pci_read(0, 0, PCI_DEVFN(0x18, 0), 0x60, sizeof(val), &val);
+ if (ret)
+ goto out;
+
+ /* HyperTransport fabric size in bits 6:4 */
+ limit = PCI_DEVFN(0x18 + ((val >> 4) & 7) + 1, 0);
+
+ /* Use NumaChip PCI accessors for non-extended and extended access */
+ raw_pci_ops = raw_pci_ext_ops = &pci_mmcfg_numachip;
+out:
+ return ret;
+}
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 4c61b52..f8ab494 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -21,12 +21,25 @@
#include <asm/i8259.h>
#include <asm/io.h>
#include <asm/io_apic.h>
+#include <asm/emergency-restart.h>
static int ce4100_i8042_detect(void)
{
return 0;
}
+/*
+ * The CE4100 platform has an internal 8051 Microcontroller which is
+ * responsible for signaling to the external Power Management Unit the
+ * intention to reset, reboot or power off the system. This 8051 device has
+ * its command register mapped at I/O port 0xcf9 and the value 0x4 is used
+ * to power off the system.
+ */
+static void ce4100_power_off(void)
+{
+ outb(0x4, 0xcf9);
+}
+
#ifdef CONFIG_SERIAL_8250
static unsigned int mem_serial_in(struct uart_port *p, int offset)
@@ -92,8 +105,11 @@ static void ce4100_serial_fixup(int port, struct uart_port *up,
up->membase =
(void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
up->membase += up->mapbase & ~PAGE_MASK;
+ up->mapbase += port * 0x100;
+ up->membase += port * 0x100;
up->iotype = UPIO_MEM32;
up->regshift = 2;
+ up->irq = 4;
}
#endif
up->iobase = 0;
@@ -139,8 +155,19 @@ void __init x86_ce4100_early_setup(void)
x86_init.mpparse.find_smp_config = x86_init_noop;
x86_init.pci.init = ce4100_pci_init;
+ /*
+ * By default, the reboot method is ACPI which is supported by the
+ * CE4100 bootloader CEFDK using FADT.ResetReg Address and ResetValue
+ * the bootloader will however issue a system power off instead of
+ * reboot. By using BOOT_KBD we ensure proper system reboot as
+ * expected.
+ */
+ reboot_type = BOOT_KBD;
+
#ifdef CONFIG_X86_IO_APIC
x86_init.pci.init_irq = sdv_pci_init;
x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
#endif
+
+ pm_power_off = ce4100_power_off;
}
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 218cdb1..120cee1 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -21,6 +21,7 @@
#include <asm/suspend.h>
#include <asm/debugreg.h>
#include <asm/fpu-internal.h> /* pcntxt_mask */
+#include <asm/cpu.h>
#ifdef CONFIG_X86_32
static struct saved_context saved_context;
@@ -237,3 +238,84 @@ void restore_processor_state(void)
#ifdef CONFIG_X86_32
EXPORT_SYMBOL(restore_processor_state);
#endif
+
+/*
+ * When bsp_check() is called in hibernate and suspend, cpu hotplug
+ * is disabled already. So it's unnessary to handle race condition between
+ * cpumask query and cpu hotplug.
+ */
+static int bsp_check(void)
+{
+ if (cpumask_first(cpu_online_mask) != 0) {
+ pr_warn("CPU0 is offline.\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static int bsp_pm_callback(struct notifier_block *nb, unsigned long action,
+ void *ptr)
+{
+ int ret = 0;
+
+ switch (action) {
+ case PM_SUSPEND_PREPARE:
+ case PM_HIBERNATION_PREPARE:
+ ret = bsp_check();
+ break;
+#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
+ case PM_RESTORE_PREPARE:
+ /*
+ * When system resumes from hibernation, online CPU0 because
+ * 1. it's required for resume and
+ * 2. the CPU was online before hibernation
+ */
+ if (!cpu_online(0))
+ _debug_hotplug_cpu(0, 1);
+ break;
+ case PM_POST_RESTORE:
+ /*
+ * When a resume really happens, this code won't be called.
+ *
+ * This code is called only when user space hibernation software
+ * prepares for snapshot device during boot time. So we just
+ * call _debug_hotplug_cpu() to restore to CPU0's state prior to
+ * preparing the snapshot device.
+ *
+ * This works for normal boot case in our CPU0 hotplug debug
+ * mode, i.e. CPU0 is offline and user mode hibernation
+ * software initializes during boot time.
+ *
+ * If CPU0 is online and user application accesses snapshot
+ * device after boot time, this will offline CPU0 and user may
+ * see different CPU0 state before and after accessing
+ * the snapshot device. But hopefully this is not a case when
+ * user debugging CPU0 hotplug. Even if users hit this case,
+ * they can easily online CPU0 back.
+ *
+ * To simplify this debug code, we only consider normal boot
+ * case. Otherwise we need to remember CPU0's state and restore
+ * to that state and resolve racy conditions etc.
+ */
+ _debug_hotplug_cpu(0, 0);
+ break;
+#endif
+ default:
+ break;
+ }
+ return notifier_from_errno(ret);
+}
+
+static int __init bsp_pm_check_init(void)
+{
+ /*
+ * Set this bsp_pm_callback as lower priority than
+ * cpu_hotplug_pm_callback. So cpu_hotplug_pm_callback will be called
+ * earlier to disable cpu hotplug before bsp online check.
+ */
+ pm_notifier(bsp_pm_callback, -INT_MAX);
+ return 0;
+}
+
+core_initcall(bsp_pm_check_init);
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index a47103f..ee3c220 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -8,7 +8,7 @@
#
0 i386 restart_syscall sys_restart_syscall
1 i386 exit sys_exit
-2 i386 fork ptregs_fork stub32_fork
+2 i386 fork sys_fork stub32_fork
3 i386 read sys_read
4 i386 write sys_write
5 i386 open sys_open compat_sys_open
@@ -126,7 +126,7 @@
117 i386 ipc sys_ipc sys32_ipc
118 i386 fsync sys_fsync
119 i386 sigreturn ptregs_sigreturn stub32_sigreturn
-120 i386 clone ptregs_clone stub32_clone
+120 i386 clone sys_clone stub32_clone
121 i386 setdomainname sys_setdomainname
122 i386 uname sys_newuname
123 i386 modify_ldt sys_modify_ldt
@@ -196,7 +196,7 @@
187 i386 sendfile sys_sendfile sys32_sendfile
188 i386 getpmsg
189 i386 putpmsg
-190 i386 vfork ptregs_vfork stub32_vfork
+190 i386 vfork sys_vfork stub32_vfork
191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit
192 i386 mmap2 sys_mmap_pgoff
193 i386 truncate64 sys_truncate64 sys32_truncate64
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index ddcf39b..e6773dc 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -356,7 +356,7 @@ END {
exit 1
# print escape opcode map's array
print "/* Escape opcode map array */"
- print "const insn_attr_t const *inat_escape_tables[INAT_ESC_MAX + 1]" \
+ print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
"[INAT_LSTPFX_MAX + 1] = {"
for (i = 0; i < geid; i++)
for (j = 0; j < max_lprefix; j++)
@@ -365,7 +365,7 @@ END {
print "};\n"
# print group opcode map's array
print "/* Group opcode map array */"
- print "const insn_attr_t const *inat_group_tables[INAT_GRP_MAX + 1]"\
+ print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
"[INAT_LSTPFX_MAX + 1] = {"
for (i = 0; i < ggid; i++)
for (j = 0; j < max_lprefix; j++)
@@ -374,7 +374,7 @@ END {
print "};\n"
# print AVX opcode map's array
print "/* AVX opcode map array */"
- print "const insn_attr_t const *inat_avx_tables[X86_VEX_M_MAX + 1]"\
+ print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
"[INAT_LSTPFX_MAX + 1] = {"
for (i = 0; i < gaid; i++)
for (j = 0; j < max_lprefix; j++)
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 0761175..9839970 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -25,13 +25,14 @@ config X86_32
select HAVE_AOUT
select ARCH_WANT_IPC_PARSE_VERSION
select MODULES_USE_ELF_REL
+ select CLONE_BACKWARDS
config X86_64
def_bool 64BIT
select MODULES_USE_ELF_RELA
config RWSEM_XCHGADD_ALGORITHM
- def_bool X86_XADD && 64BIT
+ def_bool 64BIT
config RWSEM_GENERIC_SPINLOCK
def_bool !RWSEM_XCHGADD_ALGORITHM
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
index ca255a8..bd9a89b 100644
--- a/arch/x86/um/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -1,5 +1,3 @@
-extern long sys_clone(unsigned long clone_flags, unsigned long newsp,
- void __user *parent_tid, void __user *child_tid);
#ifdef __i386__
#include "syscalls_32.h"
#else
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 232e605..812e98c 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -24,13 +24,10 @@
#define old_mmap sys_old_mmap
-#define ptregs_fork sys_fork
#define ptregs_iopl sys_iopl
#define ptregs_vm86old sys_vm86old
-#define ptregs_clone i386_clone
#define ptregs_vm86 sys_vm86
#define ptregs_sigaltstack sys_sigaltstack
-#define ptregs_vfork sys_vfork
#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ;
#include <asm/syscalls_32.h>
diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c
index db444c7..e8bcea9 100644
--- a/arch/x86/um/syscalls_32.c
+++ b/arch/x86/um/syscalls_32.c
@@ -6,21 +6,6 @@
#include <linux/syscalls.h>
#include <sysdep/syscalls.h>
-/*
- * The prototype on i386 is:
- *
- * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls
- *
- * and the "newtls" arg. on i386 is read by copy_thread directly from the
- * register saved on the stack.
- */
-long i386_clone(unsigned long clone_flags, unsigned long newsp,
- int __user *parent_tid, void *newtls, int __user *child_tid)
-{
- return sys_clone(clone_flags, newsp, parent_tid, child_tid);
-}
-
-
long sys_sigaction(int sig, const struct old_sigaction __user *act,
struct old_sigaction __user *oact)
{
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 00aaf04..431e875 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -141,7 +141,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
* unaligned here as a result of stack start randomization.
*/
addr = PAGE_ALIGN(addr);
- addr = align_addr(addr, NULL, ALIGN_VDSO);
+ addr = align_vdso_addr(addr);
return addr;
}
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index c31ee77..131dacd 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -8,7 +8,7 @@ config XEN
select PARAVIRT_CLOCK
select XEN_HAVE_PVMMU
depends on X86_64 || (X86_32 && X86_PAE && !X86_VISWS)
- depends on X86_CMPXCHG && X86_TSC
+ depends on X86_TSC
help
This is the Linux Xen port. Enabling this will allow the
kernel to boot in a paravirtualized environment under the
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fd8393f..01de35c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1288,6 +1288,25 @@ unsigned long xen_read_cr2_direct(void)
return this_cpu_read(xen_vcpu_info.arch.cr2);
}
+void xen_flush_tlb_all(void)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+
+ trace_xen_mmu_flush_tlb_all(0);
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
+
+ op = mcs.args;
+ op->cmd = MMUEXT_TLB_FLUSH_ALL;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
+}
static void xen_flush_tlb(void)
{
struct mmuext_op *op;
@@ -2520,7 +2539,7 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
err = 0;
out:
- flush_tlb_all();
+ xen_flush_tlb_all();
return err;
}