summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r--arch/x86/include/asm/acpi.h11
-rw-r--r--arch/x86/include/asm/alternative.h8
-rw-r--r--arch/x86/include/asm/amd_nb.h60
-rw-r--r--arch/x86/include/asm/apic.h13
-rw-r--r--arch/x86/include/asm/apicdef.h1
-rw-r--r--arch/x86/include/asm/boot.h6
-rw-r--r--arch/x86/include/asm/cacheflush.h42
-rw-r--r--arch/x86/include/asm/cpu.h1
-rw-r--r--arch/x86/include/asm/debugreg.h2
-rw-r--r--arch/x86/include/asm/e820.h3
-rw-r--r--arch/x86/include/asm/fixmap.h8
-rw-r--r--arch/x86/include/asm/gpio.h5
-rw-r--r--arch/x86/include/asm/hypervisor.h12
-rw-r--r--arch/x86/include/asm/i387.h24
-rw-r--r--arch/x86/include/asm/io_apic.h9
-rw-r--r--arch/x86/include/asm/irq.h7
-rw-r--r--arch/x86/include/asm/jump_label.h2
-rw-r--r--arch/x86/include/asm/kdebug.h3
-rw-r--r--arch/x86/include/asm/kvm_emulate.h35
-rw-r--r--arch/x86/include/asm/kvm_host.h102
-rw-r--r--arch/x86/include/asm/kvm_para.h24
-rw-r--r--arch/x86/include/asm/mach_traps.h12
-rw-r--r--arch/x86/include/asm/mce.h3
-rw-r--r--arch/x86/include/asm/microcode.h6
-rw-r--r--arch/x86/include/asm/mpspec.h31
-rw-r--r--arch/x86/include/asm/mpspec_def.h7
-rw-r--r--arch/x86/include/asm/msr-index.h18
-rw-r--r--arch/x86/include/asm/nmi.h71
-rw-r--r--arch/x86/include/asm/numa_32.h2
-rw-r--r--arch/x86/include/asm/numa_64.h3
-rw-r--r--arch/x86/include/asm/olpc.h10
-rw-r--r--arch/x86/include/asm/olpc_ofw.h9
-rw-r--r--arch/x86/include/asm/paravirt.h36
-rw-r--r--arch/x86/include/asm/paravirt_types.h6
-rw-r--r--arch/x86/include/asm/pci.h1
-rw-r--r--arch/x86/include/asm/percpu.h158
-rw-r--r--arch/x86/include/asm/perf_event.h2
-rw-r--r--arch/x86/include/asm/perf_event_p4.h66
-rw-r--r--arch/x86/include/asm/pgalloc.h2
-rw-r--r--arch/x86/include/asm/pgtable-2level.h9
-rw-r--r--arch/x86/include/asm/pgtable-3level.h23
-rw-r--r--arch/x86/include/asm/pgtable.h143
-rw-r--r--arch/x86/include/asm/pgtable_64.h28
-rw-r--r--arch/x86/include/asm/pgtable_types.h3
-rw-r--r--arch/x86/include/asm/processor.h10
-rw-r--r--arch/x86/include/asm/prom.h1
-rw-r--r--arch/x86/include/asm/pvclock.h1
-rw-r--r--arch/x86/include/asm/smpboot_hooks.h1
-rw-r--r--arch/x86/include/asm/stacktrace.h33
-rw-r--r--arch/x86/include/asm/svm.h57
-rw-r--r--arch/x86/include/asm/system_64.h22
-rw-r--r--arch/x86/include/asm/timer.h6
-rw-r--r--arch/x86/include/asm/traps.h1
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h9
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h4
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h208
-rw-r--r--arch/x86/include/asm/vmx.h15
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h35
-rw-r--r--arch/x86/include/asm/xen/interface.h6
-rw-r--r--arch/x86/include/asm/xen/interface_32.h5
-rw-r--r--arch/x86/include/asm/xen/interface_64.h13
-rw-r--r--arch/x86/include/asm/xen/page.h21
62 files changed, 1059 insertions, 416 deletions
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 55d106b5e31b..211ca3f7fd16 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -185,17 +185,16 @@ struct bootnode;
#ifdef CONFIG_ACPI_NUMA
extern int acpi_numa;
-extern int acpi_get_nodes(struct bootnode *physnodes);
+extern void acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
+ unsigned long end);
extern int acpi_scan_nodes(unsigned long start, unsigned long end);
#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+
+#ifdef CONFIG_NUMA_EMU
extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
int num_nodes);
-#else
-static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
- int num_nodes)
-{
-}
#endif
+#endif /* CONFIG_ACPI_NUMA */
#define acpi_unlazy_tlb(x) leave_mm(x)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 76561d20ea2f..13009d1af99a 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -66,6 +66,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
extern void alternatives_smp_module_del(struct module *mod);
extern void alternatives_smp_switch(int smp);
extern int alternatives_text_reserved(void *start, void *end);
+extern bool skip_smp_alternatives;
#else
static inline void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
@@ -180,8 +181,15 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
* On the local CPU you need to be protected again NMI or MCE handlers seeing an
* inconsistent instruction while you patch.
*/
+struct text_poke_param {
+ void *addr;
+ const void *opcode;
+ size_t len;
+};
+
extern void *text_poke(void *addr, const void *opcode, size_t len);
extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
+extern void text_poke_smp_batch(struct text_poke_param *params, int n);
#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
#define IDEAL_NOP_SIZE_5 5
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index c8517f81b21e..64dc82ee19f0 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -3,36 +3,64 @@
#include <linux/pci.h>
-extern struct pci_device_id k8_nb_ids[];
+struct amd_nb_bus_dev_range {
+ u8 bus;
+ u8 dev_base;
+ u8 dev_limit;
+};
+
+extern struct pci_device_id amd_nb_misc_ids[];
+extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
struct bootnode;
-extern int early_is_k8_nb(u32 value);
-extern int cache_k8_northbridges(void);
-extern void k8_flush_garts(void);
-extern int k8_get_nodes(struct bootnode *nodes);
-extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
-extern int k8_scan_nodes(void);
+extern int early_is_amd_nb(u32 value);
+extern int amd_cache_northbridges(void);
+extern void amd_flush_garts(void);
+extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn);
+extern int amd_scan_nodes(void);
+
+#ifdef CONFIG_NUMA_EMU
+extern void amd_fake_nodes(const struct bootnode *nodes, int nr_nodes);
+extern void amd_get_nodes(struct bootnode *nodes);
+#endif
-struct k8_northbridge_info {
+struct amd_northbridge {
+ struct pci_dev *misc;
+};
+
+struct amd_northbridge_info {
u16 num;
- u8 gart_supported;
- struct pci_dev **nb_misc;
+ u64 flags;
+ struct amd_northbridge *nb;
};
-extern struct k8_northbridge_info k8_northbridges;
+extern struct amd_northbridge_info amd_northbridges;
+
+#define AMD_NB_GART 0x1
+#define AMD_NB_L3_INDEX_DISABLE 0x2
#ifdef CONFIG_AMD_NB
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
+static inline int amd_nb_num(void)
{
- return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL;
+ return amd_northbridges.num;
}
-#else
+static inline int amd_nb_has_feature(int feature)
+{
+ return ((amd_northbridges.flags & feature) == feature);
+}
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
+static inline struct amd_northbridge *node_to_amd_nb(int node)
{
- return NULL;
+ return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
}
+
+#else
+
+#define amd_nb_num(x) 0
+#define amd_nb_has_feature(x) false
+#define node_to_amd_nb(x) NULL
+
#endif
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 286de34b0ed6..5e3969c36d7f 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -141,13 +141,13 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
static inline u32 native_apic_msr_read(u32 reg)
{
- u32 low, high;
+ u64 msr;
if (reg == APIC_DFR)
return -1;
- rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
- return low;
+ rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+ return (u32)msr;
}
static inline void native_x2apic_wait_icr_idle(void)
@@ -181,12 +181,12 @@ extern void enable_x2apic(void);
extern void x2apic_icr_write(u32 low, u32 id);
static inline int x2apic_enabled(void)
{
- int msr, msr2;
+ u64 msr;
if (!cpu_has_x2apic)
return 0;
- rdmsr(MSR_IA32_APICBASE, msr, msr2);
+ rdmsrl(MSR_IA32_APICBASE, msr);
if (msr & X2APIC_ENABLE)
return 1;
return 0;
@@ -234,16 +234,17 @@ extern void init_bsp_APIC(void);
extern void setup_local_APIC(void);
extern void end_local_APIC_setup(void);
extern void init_apic_mappings(void);
+void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
extern void setup_secondary_APIC_clock(void);
extern int APIC_init_uniprocessor(void);
extern void enable_NMI_through_LVT0(void);
+extern int apic_force_enable(void);
/*
* On 32bit this is mach-xxx local
*/
#ifdef CONFIG_X86_64
-extern void early_init_lapic_mapping(void);
extern int apic_is_clustered_box(void);
#else
static inline int apic_is_clustered_box(void)
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index a859ca461fb0..47a30ff8e517 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -145,6 +145,7 @@
#ifdef CONFIG_X86_32
# define MAX_IO_APICS 64
+# define MAX_LOCAL_APIC 256
#else
# define MAX_IO_APICS 128
# define MAX_LOCAL_APIC 32768
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 3b62ab56c7a0..5e1a2eef3e7c 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -32,11 +32,7 @@
#define BOOT_HEAP_SIZE 0x400000
#else /* !CONFIG_KERNEL_BZIP2 */
-#ifdef CONFIG_X86_64
-#define BOOT_HEAP_SIZE 0x7000
-#else
-#define BOOT_HEAP_SIZE 0x4000
-#endif
+#define BOOT_HEAP_SIZE 0x8000
#endif /* !CONFIG_KERNEL_BZIP2 */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 63e35ec9075c..62f084478f7e 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -1,48 +1,8 @@
#ifndef _ASM_X86_CACHEFLUSH_H
#define _ASM_X86_CACHEFLUSH_H
-/* Keep includes the same across arches. */
-#include <linux/mm.h>
-
/* Caches aren't brain-dead on the intel. */
-static inline void flush_cache_all(void) { }
-static inline void flush_cache_mm(struct mm_struct *mm) { }
-static inline void flush_cache_dup_mm(struct mm_struct *mm) { }
-static inline void flush_cache_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end) { }
-static inline void flush_cache_page(struct vm_area_struct *vma,
- unsigned long vmaddr, unsigned long pfn) { }
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-static inline void flush_dcache_page(struct page *page) { }
-static inline void flush_dcache_mmap_lock(struct address_space *mapping) { }
-static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { }
-static inline void flush_icache_range(unsigned long start,
- unsigned long end) { }
-static inline void flush_icache_page(struct vm_area_struct *vma,
- struct page *page) { }
-static inline void flush_icache_user_range(struct vm_area_struct *vma,
- struct page *page,
- unsigned long addr,
- unsigned long len) { }
-static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
-static inline void flush_cache_vunmap(unsigned long start,
- unsigned long end) { }
-
-static inline void copy_to_user_page(struct vm_area_struct *vma,
- struct page *page, unsigned long vaddr,
- void *dst, const void *src,
- unsigned long len)
-{
- memcpy(dst, src, len);
-}
-
-static inline void copy_from_user_page(struct vm_area_struct *vma,
- struct page *page, unsigned long vaddr,
- void *dst, const void *src,
- unsigned long len)
-{
- memcpy(dst, src, len);
-}
+#include <asm-generic/cacheflush.h>
#ifdef CONFIG_X86_PAT
/*
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 4fab24de26b1..6e6e7558e702 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,5 +32,6 @@ extern void arch_unregister_cpu(int);
DECLARE_PER_CPU(int, cpu_state);
+int __cpuinit mwait_usable(const struct cpuinfo_x86 *);
#endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index b81002f23614..078ad0caefc6 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -94,7 +94,7 @@ static inline void hw_breakpoint_disable(void)
static inline int hw_breakpoint_active(void)
{
- return __get_cpu_var(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
+ return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
}
extern void aout_dump_debugregs(struct user *dump);
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 5be1542fbfaf..e99d55d74df5 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -72,6 +72,9 @@ struct e820map {
#define BIOS_BEGIN 0x000a0000
#define BIOS_END 0x00100000
+#define BIOS_ROM_BASE 0xffe00000
+#define BIOS_ROM_END 0xffffffff
+
#ifdef __KERNEL__
/* see comment in arch/x86/kernel/e820.c */
extern struct e820map e820;
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 139591a933f6..4729b2b63117 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -116,11 +116,11 @@ enum fixed_addresses {
#endif
FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */
FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
- __end_of_permanent_fixed_addresses,
-
#ifdef CONFIG_X86_MRST
FIX_LNW_VRTC,
#endif
+ __end_of_permanent_fixed_addresses,
+
/*
* 256 temporary boot-time mappings, used by early_ioremap(),
* before ioremap() is functional.
@@ -220,8 +220,8 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
}
/* Return an pointer with offset calculated */
-static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx,
- phys_addr_t phys, pgprot_t flags)
+static __always_inline unsigned long
+__set_fixmap_offset(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
{
__set_fixmap(idx, phys, flags);
return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1));
diff --git a/arch/x86/include/asm/gpio.h b/arch/x86/include/asm/gpio.h
index 49dbfdfa50f9..91d915a65259 100644
--- a/arch/x86/include/asm/gpio.h
+++ b/arch/x86/include/asm/gpio.h
@@ -38,12 +38,9 @@ static inline int gpio_cansleep(unsigned int gpio)
return __gpio_cansleep(gpio);
}
-/*
- * Not implemented, yet.
- */
static inline int gpio_to_irq(unsigned int gpio)
{
- return -ENOSYS;
+ return __gpio_to_irq(gpio);
}
static inline int irq_to_gpio(unsigned int irq)
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index ff2546ce7178..7a15153c675d 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,6 +20,9 @@
#ifndef _ASM_X86_HYPERVISOR_H
#define _ASM_X86_HYPERVISOR_H
+#include <asm/kvm_para.h>
+#include <asm/xen/hypervisor.h>
+
extern void init_hypervisor(struct cpuinfo_x86 *c);
extern void init_hypervisor_platform(void);
@@ -47,4 +50,13 @@ extern const struct hypervisor_x86 x86_hyper_vmware;
extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+static inline bool hypervisor_x2apic_available(void)
+{
+ if (kvm_para_available())
+ return true;
+ if (xen_x2apic_para_available())
+ return true;
+ return false;
+}
+
#endif
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 4aa2bb3b242a..ef328901c802 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -93,6 +93,17 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
int err;
/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+ asm volatile("1: fxrstorq %[fx]\n\t"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3: movl $-1,%[err]\n"
+ " jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ : [err] "=r" (err)
+ : [fx] "m" (*fx), "0" (0));
+#else
asm volatile("1: rex64/fxrstor (%[fx])\n\t"
"2:\n"
".section .fixup,\"ax\"\n"
@@ -102,6 +113,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err)
: [fx] "R" (fx), "m" (*fx), "0" (0));
+#endif
return err;
}
@@ -119,6 +131,17 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
return -EFAULT;
/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+ asm volatile("1: fxsaveq %[fx]\n\t"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3: movl $-1,%[err]\n"
+ " jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ : [err] "=r" (err), [fx] "=m" (*fx)
+ : "0" (0));
+#else
asm volatile("1: rex64/fxsave (%[fx])\n\t"
"2:\n"
".section .fixup,\"ax\"\n"
@@ -128,6 +151,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err), "=m" (*fx)
: [fx] "R" (fx), "0" (0));
+#endif
if (unlikely(err) &&
__clear_user(fx, sizeof(struct i387_fxsave_struct)))
err = -EFAULT;
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index a6b28d017c2f..f327d386d6cc 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -159,7 +159,7 @@ struct io_apic_irq_attr;
extern int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr);
void setup_IO_APIC_irq_extra(u32 gsi);
-extern void ioapic_init_mappings(void);
+extern void ioapic_and_gsi_init(void);
extern void ioapic_insert_resources(void);
extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
@@ -168,10 +168,10 @@ extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
-extern void probe_nr_irqs_gsi(void);
extern int get_nr_irqs_gsi(void);
extern void setup_ioapic_ids_from_mpc(void);
+extern void setup_ioapic_ids_from_mpc_nocheck(void);
struct mp_ioapic_gsi{
u32 gsi_base;
@@ -184,14 +184,15 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi);
void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
extern void __init pre_init_apic_IRQ0(void);
+extern void mp_save_irq(struct mpc_intsrc *m);
+
#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
#define setup_ioapic_ids_from_mpc x86_init_noop
static const int timer_through_8259 = 0;
-static inline void ioapic_init_mappings(void) { }
+static inline void ioapic_and_gsi_init(void) { }
static inline void ioapic_insert_resources(void) { }
-static inline void probe_nr_irqs_gsi(void) { }
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 13b0ebaa512f..c704b38c57a2 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -10,15 +10,14 @@
#include <asm/apicdef.h>
#include <asm/irq_vectors.h>
+/* Even though we don't support this, supply it to appease OF */
+static inline void irq_dispose_mapping(unsigned int virq) { }
+
static inline int irq_canonicalize(int irq)
{
return ((irq == 2) ? 9 : irq);
}
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG
-#endif
-
#ifdef CONFIG_X86_32
extern void irq_ctx_init(int cpu);
#else
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index f52d42e80585..574dbc22893a 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -14,7 +14,7 @@
do { \
asm goto("1:" \
JUMP_LABEL_INITIAL_NOP \
- ".pushsection __jump_table, \"a\" \n\t"\
+ ".pushsection __jump_table, \"aw\" \n\t"\
_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
".popsection \n\t" \
: : "i" (key) : : label); \
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 5bdfca86581b..ca242d35e873 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -18,7 +18,6 @@ enum die_val {
DIE_TRAP,
DIE_GPF,
DIE_CALL,
- DIE_NMI_IPI,
DIE_PAGE_FAULT,
DIE_NMIUNKNOWN,
};
@@ -28,7 +27,7 @@ extern void die(const char *, struct pt_regs *,long);
extern int __must_check __die(const char *, struct pt_regs *, long);
extern void show_registers(struct pt_regs *regs);
extern void show_trace(struct task_struct *t, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp);
+ unsigned long *sp);
extern void __show_regs(struct pt_regs *regs, int all);
extern void show_regs(struct pt_regs *regs);
extern unsigned long oops_begin(void);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index b36c6b3fe144..8e37deb1eb38 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -15,6 +15,14 @@
struct x86_emulate_ctxt;
+struct x86_exception {
+ u8 vector;
+ bool error_code_valid;
+ u16 error_code;
+ bool nested_page_fault;
+ u64 address; /* cr2 or nested page fault gpa */
+};
+
/*
* x86_emulate_ops:
*
@@ -64,7 +72,8 @@ struct x86_emulate_ops {
* @bytes: [IN ] Number of bytes to read from memory.
*/
int (*read_std)(unsigned long addr, void *val,
- unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+ unsigned int bytes, struct kvm_vcpu *vcpu,
+ struct x86_exception *fault);
/*
* write_std: Write bytes of standard (non-emulated/special) memory.
@@ -74,7 +83,8 @@ struct x86_emulate_ops {
* @bytes: [IN ] Number of bytes to write to memory.
*/
int (*write_std)(unsigned long addr, void *val,
- unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+ unsigned int bytes, struct kvm_vcpu *vcpu,
+ struct x86_exception *fault);
/*
* fetch: Read bytes of standard (non-emulated/special) memory.
* Used for instruction fetch.
@@ -83,7 +93,8 @@ struct x86_emulate_ops {
* @bytes: [IN ] Number of bytes to read from memory.
*/
int (*fetch)(unsigned long addr, void *val,
- unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+ unsigned int bytes, struct kvm_vcpu *vcpu,
+ struct x86_exception *fault);
/*
* read_emulated: Read bytes from emulated/special memory area.
@@ -94,7 +105,7 @@ struct x86_emulate_ops {
int (*read_emulated)(unsigned long addr,
void *val,
unsigned int bytes,
- unsigned int *error,
+ struct x86_exception *fault,
struct kvm_vcpu *vcpu);
/*
@@ -107,7 +118,7 @@ struct x86_emulate_ops {
int (*write_emulated)(unsigned long addr,
const void *val,
unsigned int bytes,
- unsigned int *error,
+ struct x86_exception *fault,
struct kvm_vcpu *vcpu);
/*
@@ -122,7 +133,7 @@ struct x86_emulate_ops {
const void *old,
const void *new,
unsigned int bytes,
- unsigned int *error,
+ struct x86_exception *fault,
struct kvm_vcpu *vcpu);
int (*pio_in_emulated)(int size, unsigned short port, void *val,
@@ -159,7 +170,10 @@ struct operand {
};
union {
unsigned long *reg;
- unsigned long mem;
+ struct segmented_address {
+ ulong ea;
+ unsigned seg;
+ } mem;
} addr;
union {
unsigned long val;
@@ -226,9 +240,8 @@ struct x86_emulate_ctxt {
bool perm_ok; /* do not check permissions if true */
- int exception; /* exception that happens during emulation or -1 */
- u32 error_code; /* error code for exception */
- bool error_code_valid;
+ bool have_exception;
+ struct x86_exception exception;
/* decode cache */
struct decode_cache decode;
@@ -252,7 +265,7 @@ struct x86_emulate_ctxt {
#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
#endif
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
#define EMULATION_FAILED -1
#define EMULATION_OK 0
#define EMULATION_RESTART 1
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9e6fe391094e..ffd7f8d29187 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,15 +79,18 @@
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
-#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_MAX_CPUID_ENTRIES 80
#define KVM_NR_FIXED_MTRR_REGION 88
#define KVM_NR_VAR_MTRR 8
+#define ASYNC_PF_PER_VCPU 64
+
extern spinlock_t kvm_lock;
extern struct list_head vm_list;
struct kvm_vcpu;
struct kvm;
+struct kvm_async_pf;
enum kvm_reg {
VCPU_REGS_RAX = 0,
@@ -114,6 +117,7 @@ enum kvm_reg {
enum kvm_reg_ex {
VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+ VCPU_EXREG_CR3,
};
enum {
@@ -238,16 +242,18 @@ struct kvm_mmu {
void (*new_cr3)(struct kvm_vcpu *vcpu);
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
- int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
- void (*inject_page_fault)(struct kvm_vcpu *vcpu);
+ int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+ bool prefault);
+ void (*inject_page_fault)(struct kvm_vcpu *vcpu,
+ struct x86_exception *fault);
void (*free)(struct kvm_vcpu *vcpu);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
- u32 *error);
+ struct x86_exception *exception);
gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
void (*prefetch_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *page);
int (*sync_page)(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp, bool clear_unsync);
+ struct kvm_mmu_page *sp);
void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
hpa_t root_hpa;
int root_level;
@@ -315,16 +321,6 @@ struct kvm_vcpu_arch {
*/
struct kvm_mmu *walk_mmu;
- /*
- * This struct is filled with the necessary information to propagate a
- * page fault into the guest
- */
- struct {
- u64 address;
- unsigned error_code;
- bool nested;
- } fault;
-
/* only needed in kvm_pv_mmu_op() path, but it's hot so
* put it here to avoid allocation */
struct kvm_pv_mmu_op_buffer mmu_op_buffer;
@@ -412,6 +408,15 @@ struct kvm_vcpu_arch {
u64 hv_vapic;
cpumask_var_t wbinvd_dirty_mask;
+
+ struct {
+ bool halted;
+ gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
+ struct gfn_to_hva_cache data;
+ u64 msr_val;
+ u32 id;
+ bool send_user_only;
+ } apf;
};
struct kvm_arch {
@@ -456,6 +461,10 @@ struct kvm_arch {
/* fields used by HYPER-V emulation */
u64 hv_guest_os_id;
u64 hv_hypercall;
+
+ #ifdef CONFIG_KVM_MMU_AUDIT
+ int audit_point;
+ #endif
};
struct kvm_vm_stat {
@@ -529,6 +538,7 @@ struct kvm_x86_ops {
struct kvm_segment *var, int seg);
void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
+ void (*decache_cr3)(struct kvm_vcpu *vcpu);
void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -582,9 +592,17 @@ struct kvm_x86_ops {
void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
+ void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
const struct trace_print_flags *exit_reasons_str;
};
+struct kvm_arch_async_pf {
+ u32 token;
+ gfn_t gfn;
+ unsigned long cr3;
+ bool direct_map;
+};
+
extern struct kvm_x86_ops *kvm_x86_ops;
int kvm_mmu_module_init(void);
@@ -594,7 +612,6 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
int kvm_mmu_setup(struct kvm_vcpu *vcpu);
void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
-void kvm_mmu_set_base_ptes(u64 base_pte);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
u64 dirty_mask, u64 nx_mask, u64 x_mask);
@@ -623,8 +640,15 @@ enum emulation_result {
#define EMULTYPE_NO_DECODE (1 << 0)
#define EMULTYPE_TRAP_UD (1 << 1)
#define EMULTYPE_SKIP (1 << 2)
-int emulate_instruction(struct kvm_vcpu *vcpu,
- unsigned long cr2, u16 error_code, int emulation_type);
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+ int emulation_type, void *insn, int insn_len);
+
+static inline int emulate_instruction(struct kvm_vcpu *vcpu,
+ int emulation_type)
+{
+ return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+}
+
void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
@@ -650,7 +674,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
-void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
+int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
@@ -668,11 +692,11 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t gfn, void *data, int offset, int len,
u32 access);
-void kvm_propagate_fault(struct kvm_vcpu *vcpu);
+void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
int kvm_pic_set_irq(void *opaque, int irq, int level);
@@ -690,16 +714,21 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception);
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+ void *insn, int insn_len);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_enable_tdp(void);
@@ -766,20 +795,25 @@ enum {
#define HF_VINTR_MASK (1 << 2)
#define HF_NMI_MASK (1 << 3)
#define HF_IRET_MASK (1 << 4)
+#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
/*
* Hardware virtualization extension instructions may fault if a
* reboot turns off virtualization while processes are running.
* Trap the fault and ignore the instruction if that happens.
*/
-asmlinkage void kvm_handle_fault_on_reboot(void);
+asmlinkage void kvm_spurious_fault(void);
+extern bool kvm_rebooting;
#define __kvm_handle_fault_on_reboot(insn) \
"666: " insn "\n\t" \
+ "668: \n\t" \
".pushsection .fixup, \"ax\" \n" \
"667: \n\t" \
+ "cmpb $0, kvm_rebooting \n\t" \
+ "jne 668b \n\t" \
__ASM_SIZE(push) " $666b \n\t" \
- "jmp kvm_handle_fault_on_reboot \n\t" \
+ "call kvm_spurious_fault \n\t" \
".popsection \n\t" \
".pushsection __ex_table, \"a\" \n\t" \
_ASM_PTR " 666b, 667b \n\t" \
@@ -788,6 +822,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
@@ -799,4 +834,15 @@ void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+
+void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 7b562b6184bc..a427bf77a93d 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -20,6 +20,7 @@
* are available. The use of 0x11 and 0x12 is deprecated
*/
#define KVM_FEATURE_CLOCKSOURCE2 3
+#define KVM_FEATURE_ASYNC_PF 4
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
@@ -32,9 +33,13 @@
/* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
#define MSR_KVM_WALL_CLOCK_NEW 0x4b564d00
#define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
+#define MSR_KVM_ASYNC_PF_EN 0x4b564d02
#define KVM_MAX_MMU_OP_BATCH 32
+#define KVM_ASYNC_PF_ENABLED (1 << 0)
+#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
+
/* Operations for KVM_HC_MMU_OP */
#define KVM_MMU_OP_WRITE_PTE 1
#define KVM_MMU_OP_FLUSH_TLB 2
@@ -61,10 +66,20 @@ struct kvm_mmu_op_release_pt {
__u64 pt_phys;
};
+#define KVM_PV_REASON_PAGE_NOT_PRESENT 1
+#define KVM_PV_REASON_PAGE_READY 2
+
+struct kvm_vcpu_pv_apf_data {
+ __u32 reason;
+ __u8 pad[60];
+ __u32 enabled;
+};
+
#ifdef __KERNEL__
#include <asm/processor.h>
extern void kvmclock_init(void);
+extern int kvm_register_clock(char *txt);
/* This instruction is vmcall. On non-VT architectures, it will generate a
@@ -160,8 +175,17 @@ static inline unsigned int kvm_arch_para_features(void)
#ifdef CONFIG_KVM_GUEST
void __init kvm_guest_init(void);
+void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wake(u32 token);
+u32 kvm_read_and_reset_pf_reason(void);
#else
#define kvm_guest_init() do { } while (0)
+#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wake(T) do {} while(0)
+static inline u32 kvm_read_and_reset_pf_reason(void)
+{
+ return 0;
+}
#endif
#endif /* __KERNEL__ */
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index f7920601e472..72a8b52e7dfd 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -7,9 +7,19 @@
#include <asm/mc146818rtc.h>
+#define NMI_REASON_PORT 0x61
+
+#define NMI_REASON_SERR 0x80
+#define NMI_REASON_IOCHK 0x40
+#define NMI_REASON_MASK (NMI_REASON_SERR | NMI_REASON_IOCHK)
+
+#define NMI_REASON_CLEAR_SERR 0x04
+#define NMI_REASON_CLEAR_IOCHK 0x08
+#define NMI_REASON_CLEAR_MASK 0x0f
+
static inline unsigned char get_nmi_reason(void)
{
- return inb(0x61);
+ return inb(NMI_REASON_PORT);
}
static inline void reassert_nmi(void)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c62c13cb9788..eb16e94ae04f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -223,6 +223,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c);
void mce_log_therm_throt_event(__u64 status);
+/* Interrupt Handler for core thermal thresholds */
+extern int (*platform_thermal_notify)(__u64 msr_val);
+
#ifdef CONFIG_X86_THERMAL_VECTOR
extern void mcheck_intel_therm_init(void);
#else
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index ef51b501e22a..24215072d0e1 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -48,6 +48,12 @@ static inline struct microcode_ops * __init init_intel_microcode(void)
#ifdef CONFIG_MICROCODE_AMD
extern struct microcode_ops * __init init_amd_microcode(void);
+
+static inline void get_ucode_data(void *to, const u8 *from, size_t n)
+{
+ memcpy(to, from, n);
+}
+
#else
static inline struct microcode_ops * __init init_amd_microcode(void)
{
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index c82868e9f905..0c90dd9f0505 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -5,8 +5,9 @@
#include <asm/mpspec_def.h>
#include <asm/x86_init.h>
+#include <asm/apicdef.h>
-extern int apic_version[MAX_APICS];
+extern int apic_version[];
extern int pic_mode;
#ifdef CONFIG_X86_32
@@ -107,7 +108,7 @@ extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
int active_high_low);
#endif /* CONFIG_ACPI */
-#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_APICS)
+#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC)
struct physid_mask {
unsigned long mask[PHYSID_ARRAY_SIZE];
@@ -122,31 +123,31 @@ typedef struct physid_mask physid_mask_t;
test_and_set_bit(physid, (map).mask)
#define physids_and(dst, src1, src2) \
- bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+ bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
#define physids_or(dst, src1, src2) \
- bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+ bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
#define physids_clear(map) \
- bitmap_zero((map).mask, MAX_APICS)
+ bitmap_zero((map).mask, MAX_LOCAL_APIC)
#define physids_complement(dst, src) \
- bitmap_complement((dst).mask, (src).mask, MAX_APICS)
+ bitmap_complement((dst).mask, (src).mask, MAX_LOCAL_APIC)
#define physids_empty(map) \
- bitmap_empty((map).mask, MAX_APICS)
+ bitmap_empty((map).mask, MAX_LOCAL_APIC)
#define physids_equal(map1, map2) \
- bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
+ bitmap_equal((map1).mask, (map2).mask, MAX_LOCAL_APIC)
#define physids_weight(map) \
- bitmap_weight((map).mask, MAX_APICS)
+ bitmap_weight((map).mask, MAX_LOCAL_APIC)
#define physids_shift_right(d, s, n) \
- bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
+ bitmap_shift_right((d).mask, (s).mask, n, MAX_LOCAL_APIC)
#define physids_shift_left(d, s, n) \
- bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
+ bitmap_shift_left((d).mask, (s).mask, n, MAX_LOCAL_APIC)
static inline unsigned long physids_coerce(physid_mask_t *map)
{
@@ -159,14 +160,6 @@ static inline void physids_promote(unsigned long physids, physid_mask_t *map)
map->mask[0] = physids;
}
-/* Note: will create very large stack frames if physid_mask_t is big */
-#define physid_mask_of_physid(physid) \
- ({ \
- physid_mask_t __physid_mask = PHYSID_MASK_NONE; \
- physid_set(physid, __physid_mask); \
- __physid_mask; \
- })
-
static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
{
physids_clear(*map);
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 4a7f96d7c188..c0a955a9a087 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -15,13 +15,6 @@
#ifdef CONFIG_X86_32
# define MAX_MPC_ENTRY 1024
-# define MAX_APICS 256
-#else
-# if NR_CPUS <= 255
-# define MAX_APICS 255
-# else
-# define MAX_APICS 32768
-# endif
#endif
/* Intel MP Floating Pointer Structure */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 3ea3dc487047..4d0dfa0d998e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -123,12 +123,16 @@
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL 0xc0010200
+#define MSR_F15H_PERF_CTR 0xc0010201
+
/* Fam 10h MSRs */
#define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058
#define FAM10H_MMIO_CONF_ENABLE (1<<0)
#define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf
#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
-#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffff
+#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL
#define FAM10H_MMIO_CONF_BASE_SHIFT 20
#define MSR_FAM10H_NODE_ID 0xc001100c
@@ -253,6 +257,18 @@
#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1)
#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24)
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE (1 << 15)
+#define THERM_SHIFT_THRESHOLD0 8
+#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE (1 << 23)
+#define THERM_SHIFT_THRESHOLD1 16
+#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0 (1 << 6)
+#define THERM_LOG_THRESHOLD0 (1 << 7)
+#define THERM_STATUS_THRESHOLD1 (1 << 8)
+#define THERM_LOG_THRESHOLD1 (1 << 9)
+
/* MISC_ENABLE bits: architectural */
#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0)
#define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 932f0f86b4b7..c76f5b92b840 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -5,41 +5,15 @@
#include <asm/irq.h>
#include <asm/io.h>
-#ifdef ARCH_HAS_NMI_WATCHDOG
-
-/**
- * do_nmi_callback
- *
- * Check to see if a callback exists and execute it. Return 1
- * if the handler exists and was handled successfully.
- */
-int do_nmi_callback(struct pt_regs *regs, int cpu);
+#ifdef CONFIG_X86_LOCAL_APIC
extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
-extern int check_nmi_watchdog(void);
-#if !defined(CONFIG_LOCKUP_DETECTOR)
-extern int nmi_watchdog_enabled;
-#endif
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
extern int reserve_perfctr_nmi(unsigned int);
extern void release_perfctr_nmi(unsigned int);
extern int reserve_evntsel_nmi(unsigned int);
extern void release_evntsel_nmi(unsigned int);
-extern void setup_apic_nmi_watchdog(void *);
-extern void stop_apic_nmi_watchdog(void *);
-extern void disable_timer_nmi_watchdog(void);
-extern void enable_timer_nmi_watchdog(void);
-extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
-extern void cpu_nmi_set_wd_enabled(void);
-
-extern atomic_t nmi_active;
-extern unsigned int nmi_watchdog;
-#define NMI_NONE 0
-#define NMI_IO_APIC 1
-#define NMI_LOCAL_APIC 2
-#define NMI_INVALID 3
-
struct ctl_table;
extern int proc_nmi_enabled(struct ctl_table *, int ,
void __user *, size_t *, loff_t *);
@@ -47,33 +21,28 @@ extern int unknown_nmi_panic;
void arch_trigger_all_cpu_backtrace(void);
#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+#endif
-static inline void localise_nmi_watchdog(void)
-{
- if (nmi_watchdog == NMI_IO_APIC)
- nmi_watchdog = NMI_LOCAL_APIC;
-}
+/*
+ * Define some priorities for the nmi notifier call chain.
+ *
+ * Create a local nmi bit that has a higher priority than
+ * external nmis, because the local ones are more frequent.
+ *
+ * Also setup some default high/normal/low settings for
+ * subsystems to registers with. Using 4 bits to seperate
+ * the priorities. This can go alot higher if needed be.
+ */
-/* check if nmi_watchdog is active (ie was specified at boot) */
-static inline int nmi_watchdog_active(void)
-{
- /*
- * actually it should be:
- * return (nmi_watchdog == NMI_LOCAL_APIC ||
- * nmi_watchdog == NMI_IO_APIC)
- * but since they are power of two we could use a
- * cheaper way --cvg
- */
- return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC);
-}
-#endif
+#define NMI_LOCAL_SHIFT 16 /* randomly picked */
+#define NMI_LOCAL_BIT (1ULL << NMI_LOCAL_SHIFT)
+#define NMI_HIGH_PRIOR (1ULL << 8)
+#define NMI_NORMAL_PRIOR (1ULL << 4)
+#define NMI_LOW_PRIOR (1ULL << 0)
+#define NMI_LOCAL_HIGH_PRIOR (NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
+#define NMI_LOCAL_NORMAL_PRIOR (NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
+#define NMI_LOCAL_LOW_PRIOR (NMI_LOCAL_BIT | NMI_LOW_PRIOR)
-void lapic_watchdog_stop(void);
-int lapic_watchdog_init(unsigned nmi_hz);
-int lapic_wd_event(unsigned nmi_hz);
-unsigned lapic_adjust_nmi_hz(unsigned hz);
-void disable_lapic_nmi_watchdog(void);
-void enable_lapic_nmi_watchdog(void);
void stop_nmi(void);
void restart_nmi(void);
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index a37229011b56..b0ef2b449a9d 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_NUMA_32_H
#define _ASM_X86_NUMA_32_H
+extern int numa_off;
+
extern int pxm_to_nid(int pxm);
extern void numa_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 823e070e7c26..0493be39607c 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -38,8 +38,9 @@ extern void __cpuinit numa_add_cpu(int cpu);
extern void __cpuinit numa_remove_cpu(int cpu);
#ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE ((u64)64 << 20)
+#define FAKE_NODE_MIN_SIZE ((u64)32 << 20)
#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
+void numa_emu_cmdline(char *);
#endif /* CONFIG_NUMA_EMU */
#else
static inline void init_cpu_to_node(void) { }
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index 42a978c0c1b3..f482010350fb 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -107,10 +107,14 @@ extern int olpc_ec_mask_unset(uint8_t bits);
/* GPIO assignments */
#define OLPC_GPIO_MIC_AC 1
-#define OLPC_GPIO_DCON_IRQ geode_gpio(7)
+#define OLPC_GPIO_DCON_STAT0 5
+#define OLPC_GPIO_DCON_STAT1 6
+#define OLPC_GPIO_DCON_IRQ 7
#define OLPC_GPIO_THRM_ALRM geode_gpio(10)
-#define OLPC_GPIO_SMB_CLK geode_gpio(14)
-#define OLPC_GPIO_SMB_DATA geode_gpio(15)
+#define OLPC_GPIO_DCON_LOAD 11
+#define OLPC_GPIO_DCON_BLANK 12
+#define OLPC_GPIO_SMB_CLK 14
+#define OLPC_GPIO_SMB_DATA 15
#define OLPC_GPIO_WORKAUX geode_gpio(24)
#define OLPC_GPIO_LID geode_gpio(26)
#define OLPC_GPIO_ECSCI geode_gpio(27)
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index 2a8478140bb3..641988efe063 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -8,6 +8,8 @@
#ifdef CONFIG_OLPC_OPENFIRMWARE
+extern bool olpc_ofw_is_installed(void);
+
/* run an OFW command by calling into the firmware */
#define olpc_ofw(name, args, res) \
__olpc_ofw((name), ARRAY_SIZE(args), args, ARRAY_SIZE(res), res)
@@ -26,10 +28,17 @@ extern bool olpc_ofw_present(void);
#else /* !CONFIG_OLPC_OPENFIRMWARE */
+static inline bool olpc_ofw_is_installed(void) { return false; }
static inline void olpc_ofw_detect(void) { }
static inline void setup_olpc_ofw_pgd(void) { }
static inline bool olpc_ofw_present(void) { return false; }
#endif /* !CONFIG_OLPC_OPENFIRMWARE */
+#ifdef CONFIG_OLPC_OPENFIRMWARE_DT
+extern void olpc_dt_build_devicetree(void);
+#else
+static inline void olpc_dt_build_devicetree(void) { }
+#endif /* CONFIG_OLPC_OPENFIRMWARE_DT */
+
#endif /* _ASM_X86_OLPC_OFW_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 18e3b8a8709f..ebbc4d8ab170 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -112,7 +112,7 @@ static inline void arch_safe_halt(void)
static inline void halt(void)
{
- PVOP_VCALL0(pv_irq_ops.safe_halt);
+ PVOP_VCALL0(pv_irq_ops.halt);
}
static inline void wbinvd(void)
@@ -435,6 +435,11 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr,
{
PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
}
+static inline void pmd_update(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp);
+}
static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
@@ -442,6 +447,12 @@ static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
}
+static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp);
+}
+
static inline pte_t __pte(pteval_t val)
{
pteval_t ret;
@@ -543,6 +554,19 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp, pmd_t pmd)
+{
+ if (sizeof(pmdval_t) > sizeof(long))
+ /* 5 arg words */
+ pv_mmu_ops.set_pmd_at(mm, addr, pmdp, pmd);
+ else
+ PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp,
+ native_pmd_val(pmd));
+}
+#endif
+
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
pmdval_t val = native_pmd_val(pmd);
@@ -824,27 +848,27 @@ static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
#define __PV_IS_CALLEE_SAVE(func) \
((struct paravirt_callee_save) { func })
-static inline unsigned long arch_local_save_flags(void)
+static inline notrace unsigned long arch_local_save_flags(void)
{
return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
}
-static inline void arch_local_irq_restore(unsigned long f)
+static inline notrace void arch_local_irq_restore(unsigned long f)
{
PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
}
-static inline void arch_local_irq_disable(void)
+static inline notrace void arch_local_irq_disable(void)
{
PVOP_VCALLEE0(pv_irq_ops.irq_disable);
}
-static inline void arch_local_irq_enable(void)
+static inline notrace void arch_local_irq_enable(void)
{
PVOP_VCALLEE0(pv_irq_ops.irq_enable);
}
-static inline unsigned long arch_local_irq_save(void)
+static inline notrace unsigned long arch_local_irq_save(void)
{
unsigned long f;
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index b82bac975250..82885099c869 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -265,10 +265,16 @@ struct pv_mmu_ops {
void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval);
void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+ void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp, pmd_t pmdval);
void (*pte_update)(struct mm_struct *mm, unsigned long addr,
pte_t *ptep);
void (*pte_update_defer)(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
+ void (*pmd_update)(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp);
+ void (*pmd_update_defer)(struct mm_struct *mm,
+ unsigned long addr, pmd_t *pmdp);
pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
pte_t *ptep);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index ca0437c714b2..676129229630 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -65,6 +65,7 @@ extern unsigned long pci_mem_start;
#define PCIBIOS_MIN_CARDBUS_IO 0x4000
+extern int pcibios_enabled;
void pcibios_config_init(void);
struct pci_bus *pcibios_scan_root(int bus);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index f899e01a8ac9..7e172955ee57 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -230,6 +230,125 @@ do { \
})
/*
+ * Add return operation
+ */
+#define percpu_add_return_op(var, val) \
+({ \
+ typeof(var) paro_ret__ = val; \
+ switch (sizeof(var)) { \
+ case 1: \
+ asm("xaddb %0, "__percpu_arg(1) \
+ : "+q" (paro_ret__), "+m" (var) \
+ : : "memory"); \
+ break; \
+ case 2: \
+ asm("xaddw %0, "__percpu_arg(1) \
+ : "+r" (paro_ret__), "+m" (var) \
+ : : "memory"); \
+ break; \
+ case 4: \
+ asm("xaddl %0, "__percpu_arg(1) \
+ : "+r" (paro_ret__), "+m" (var) \
+ : : "memory"); \
+ break; \
+ case 8: \
+ asm("xaddq %0, "__percpu_arg(1) \
+ : "+re" (paro_ret__), "+m" (var) \
+ : : "memory"); \
+ break; \
+ default: __bad_percpu_size(); \
+ } \
+ paro_ret__ += val; \
+ paro_ret__; \
+})
+
+/*
+ * xchg is implemented using cmpxchg without a lock prefix. xchg is
+ * expensive due to the implied lock prefix. The processor cannot prefetch
+ * cachelines if xchg is used.
+ */
+#define percpu_xchg_op(var, nval) \
+({ \
+ typeof(var) pxo_ret__; \
+ typeof(var) pxo_new__ = (nval); \
+ switch (sizeof(var)) { \
+ case 1: \
+ asm("\n\tmov "__percpu_arg(1)",%%al" \
+ "\n1:\tcmpxchgb %2, "__percpu_arg(1) \
+ "\n\tjnz 1b" \
+ : "=&a" (pxo_ret__), "+m" (var) \
+ : "q" (pxo_new__) \
+ : "memory"); \
+ break; \
+ case 2: \
+ asm("\n\tmov "__percpu_arg(1)",%%ax" \
+ "\n1:\tcmpxchgw %2, "__percpu_arg(1) \
+ "\n\tjnz 1b" \
+ : "=&a" (pxo_ret__), "+m" (var) \
+ : "r" (pxo_new__) \
+ : "memory"); \
+ break; \
+ case 4: \
+ asm("\n\tmov "__percpu_arg(1)",%%eax" \
+ "\n1:\tcmpxchgl %2, "__percpu_arg(1) \
+ "\n\tjnz 1b" \
+ : "=&a" (pxo_ret__), "+m" (var) \
+ : "r" (pxo_new__) \
+ : "memory"); \
+ break; \
+ case 8: \
+ asm("\n\tmov "__percpu_arg(1)",%%rax" \
+ "\n1:\tcmpxchgq %2, "__percpu_arg(1) \
+ "\n\tjnz 1b" \
+ : "=&a" (pxo_ret__), "+m" (var) \
+ : "r" (pxo_new__) \
+ : "memory"); \
+ break; \
+ default: __bad_percpu_size(); \
+ } \
+ pxo_ret__; \
+})
+
+/*
+ * cmpxchg has no such implied lock semantics as a result it is much
+ * more efficient for cpu local operations.
+ */
+#define percpu_cmpxchg_op(var, oval, nval) \
+({ \
+ typeof(var) pco_ret__; \
+ typeof(var) pco_old__ = (oval); \
+ typeof(var) pco_new__ = (nval); \
+ switch (sizeof(var)) { \
+ case 1: \
+ asm("cmpxchgb %2, "__percpu_arg(1) \
+ : "=a" (pco_ret__), "+m" (var) \
+ : "q" (pco_new__), "0" (pco_old__) \
+ : "memory"); \
+ break; \
+ case 2: \
+ asm("cmpxchgw %2, "__percpu_arg(1) \
+ : "=a" (pco_ret__), "+m" (var) \
+ : "r" (pco_new__), "0" (pco_old__) \
+ : "memory"); \
+ break; \
+ case 4: \
+ asm("cmpxchgl %2, "__percpu_arg(1) \
+ : "=a" (pco_ret__), "+m" (var) \
+ : "r" (pco_new__), "0" (pco_old__) \
+ : "memory"); \
+ break; \
+ case 8: \
+ asm("cmpxchgq %2, "__percpu_arg(1) \
+ : "=a" (pco_ret__), "+m" (var) \
+ : "r" (pco_new__), "0" (pco_old__) \
+ : "memory"); \
+ break; \
+ default: __bad_percpu_size(); \
+ } \
+ pco_ret__; \
+})
+
+/*
* percpu_read() makes gcc load the percpu variable every time it is
* accessed while percpu_read_stable() allows the value to be cached.
* percpu_read_stable() is more efficient and can be used if its value
@@ -267,6 +386,12 @@ do { \
#define __this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val)
#define __this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val)
#define __this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val)
+/*
+ * Generic fallback operations for __this_cpu_xchg_[1-4] are okay and much
+ * faster than an xchg with forced lock semantics.
+ */
+#define __this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval)
+#define __this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
#define this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
@@ -286,6 +411,9 @@ do { \
#define this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val)
#define this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val)
#define this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val)
+#define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(pcp, nval)
#define irqsafe_cpu_add_1(pcp, val) percpu_add_op((pcp), val)
#define irqsafe_cpu_add_2(pcp, val) percpu_add_op((pcp), val)
@@ -299,6 +427,29 @@ do { \
#define irqsafe_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val)
#define irqsafe_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val)
#define irqsafe_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xchg_1(pcp, nval) percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_2(pcp, nval) percpu_xchg_op(pcp, nval)
+#define irqsafe_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)
+#define __this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
+#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)
+
+#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)
+#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
+#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)
+
+#define irqsafe_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
+#endif /* !CONFIG_M386 */
/*
* Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -311,6 +462,7 @@ do { \
#define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
#define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val)
#define __this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)
+#define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val)
#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
@@ -318,12 +470,16 @@ do { \
#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
#define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val)
#define this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)
+#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val)
+#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval)
+#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
#define irqsafe_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define irqsafe_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
#define irqsafe_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val)
#define irqsafe_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)
-
+#define irqsafe_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
#endif
/* This is not atomic against other CPUs -- CPU preemption needs to be off */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 550e26b1dbb3..d9d4dae305f6 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -125,7 +125,6 @@ union cpuid10_edx {
#define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */
#ifdef CONFIG_PERF_EVENTS
-extern void init_hw_perf_events(void);
extern void perf_events_lapic_init(void);
#define PERF_EVENT_INDEX_OFFSET 0
@@ -156,7 +155,6 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
}
#else
-static inline void init_hw_perf_events(void) { }
static inline void perf_events_lapic_init(void) { }
#endif
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index a70cd216be5d..e2f6a99f14ab 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -20,6 +20,9 @@
#define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
#define ARCH_P4_MAX_CCCR (18)
+#define ARCH_P4_CNTRVAL_BITS (40)
+#define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
+
#define P4_ESCR_EVENT_MASK 0x7e000000U
#define P4_ESCR_EVENT_SHIFT 25
#define P4_ESCR_EVENTMASK_MASK 0x01fffe00U
@@ -744,14 +747,6 @@ enum P4_ESCR_EMASKS {
};
/*
- * P4 PEBS specifics (Replay Event only)
- *
- * Format (bits):
- * 0-6: metric from P4_PEBS_METRIC enum
- * 7 : reserved
- * 8 : reserved
- * 9-11 : reserved
- *
* Note we have UOP and PEBS bits reserved for now
* just in case if we will need them once
*/
@@ -788,5 +783,60 @@ enum P4_PEBS_METRIC {
P4_PEBS_METRIC__max
};
+/*
+ * Notes on internal configuration of ESCR+CCCR tuples
+ *
+ * Since P4 has quite the different architecture of
+ * performance registers in compare with "architectural"
+ * once and we have on 64 bits to keep configuration
+ * of performance event, the following trick is used.
+ *
+ * 1) Since both ESCR and CCCR registers have only low
+ * 32 bits valuable, we pack them into a single 64 bit
+ * configuration. Low 32 bits of such config correspond
+ * to low 32 bits of CCCR register and high 32 bits
+ * correspond to low 32 bits of ESCR register.
+ *
+ * 2) The meaning of every bit of such config field can
+ * be found in Intel SDM but it should be noted that
+ * we "borrow" some reserved bits for own usage and
+ * clean them or set to a proper value when we do
+ * a real write to hardware registers.
+ *
+ * 3) The format of bits of config is the following
+ * and should be either 0 or set to some predefined
+ * values:
+ *
+ * Low 32 bits
+ * -----------
+ * 0-6: P4_PEBS_METRIC enum
+ * 7-11: reserved
+ * 12: reserved (Enable)
+ * 13-15: reserved (ESCR select)
+ * 16-17: Active Thread
+ * 18: Compare
+ * 19: Complement
+ * 20-23: Threshold
+ * 24: Edge
+ * 25: reserved (FORCE_OVF)
+ * 26: reserved (OVF_PMI_T0)
+ * 27: reserved (OVF_PMI_T1)
+ * 28-29: reserved
+ * 30: reserved (Cascade)
+ * 31: reserved (OVF)
+ *
+ * High 32 bits
+ * ------------
+ * 0: reserved (T1_USR)
+ * 1: reserved (T1_OS)
+ * 2: reserved (T0_USR)
+ * 3: reserved (T0_OS)
+ * 4: Tag Enable
+ * 5-8: Tag Value
+ * 9-24: Event Mask (may use P4_ESCR_EMASK_BIT helper)
+ * 25-30: enum P4_EVENTS
+ * 31: reserved (HT thread)
+ */
+
#endif /* PERF_EVENT_P4_H */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 271de94c3810..b4389a468fb6 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -92,7 +92,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
- unsigned long adddress)
+ unsigned long address)
{
___pmd_free_tlb(tlb, pmd);
}
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 2334982b339e..98391db840c6 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -46,6 +46,15 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
#endif
+#ifdef CONFIG_SMP
+static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
+{
+ return __pmd(xchg((pmdval_t *)xp, 0));
+}
+#else
+#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
+#endif
+
/*
* Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
* split up the 29 bits of offset into this range:
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 177b0165ea01..94b979d1b58d 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -104,6 +104,29 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
#endif
+#ifdef CONFIG_SMP
+union split_pmd {
+ struct {
+ u32 pmd_low;
+ u32 pmd_high;
+ };
+ pmd_t pmd;
+};
+static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
+{
+ union split_pmd res, *orig = (union split_pmd *)pmdp;
+
+ /* xchg acts as a barrier before setting of the high bits */
+ res.pmd_low = xchg(&orig->pmd_low, 0);
+ res.pmd_high = orig->pmd_high;
+ orig->pmd_high = 0;
+
+ return res.pmd;
+}
+#else
+#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
+#endif
+
/*
* Bits 0, 6 and 7 are taken in the low part of the pte,
* put the 32 bits of offset into the high part.
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index ada823a13c7c..18601c86fab1 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -35,6 +35,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
#else /* !CONFIG_PARAVIRT */
#define set_pte(ptep, pte) native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
+#define set_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd)
#define set_pte_atomic(ptep, pte) \
native_set_pte_atomic(ptep, pte)
@@ -59,6 +60,8 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
#define pte_update(mm, addr, ptep) do { } while (0)
#define pte_update_defer(mm, addr, ptep) do { } while (0)
+#define pmd_update(mm, addr, ptep) do { } while (0)
+#define pmd_update_defer(mm, addr, ptep) do { } while (0)
#define pgd_val(x) native_pgd_val(x)
#define __pgd(x) native_make_pgd(x)
@@ -94,6 +97,11 @@ static inline int pte_young(pte_t pte)
return pte_flags(pte) & _PAGE_ACCESSED;
}
+static inline int pmd_young(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_ACCESSED;
+}
+
static inline int pte_write(pte_t pte)
{
return pte_flags(pte) & _PAGE_RW;
@@ -142,6 +150,23 @@ static inline int pmd_large(pmd_t pte)
(_PAGE_PSE | _PAGE_PRESENT);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+ return pmd_val(pmd) & _PAGE_SPLITTING;
+}
+
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+ return pmd_val(pmd) & _PAGE_PSE;
+}
+
+static inline int has_transparent_hugepage(void)
+{
+ return cpu_has_pse;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
{
pteval_t v = native_pte_val(pte);
@@ -216,6 +241,55 @@ static inline pte_t pte_mkspecial(pte_t pte)
return pte_set_flags(pte, _PAGE_SPECIAL);
}
+static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
+{
+ pmdval_t v = native_pmd_val(pmd);
+
+ return __pmd(v | set);
+}
+
+static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
+{
+ pmdval_t v = native_pmd_val(pmd);
+
+ return __pmd(v & ~clear);
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+ return pmd_clear_flags(pmd, _PAGE_ACCESSED);
+}
+
+static inline pmd_t pmd_wrprotect(pmd_t pmd)
+{
+ return pmd_clear_flags(pmd, _PAGE_RW);
+}
+
+static inline pmd_t pmd_mkdirty(pmd_t pmd)
+{
+ return pmd_set_flags(pmd, _PAGE_DIRTY);
+}
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+ return pmd_set_flags(pmd, _PAGE_PSE);
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+ return pmd_set_flags(pmd, _PAGE_ACCESSED);
+}
+
+static inline pmd_t pmd_mkwrite(pmd_t pmd)
+{
+ return pmd_set_flags(pmd, _PAGE_RW);
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+ return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+
/*
* Mask out unsupported bits in a present pgprot. Non-present pgprots
* can use those bits for other purposes, so leave them be.
@@ -256,6 +330,16 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
return __pte(val);
}
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+ pmdval_t val = pmd_val(pmd);
+
+ val &= _HPAGE_CHG_MASK;
+ val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
+
+ return __pmd(val);
+}
+
/* mprotect needs to preserve PAT bits when updating vm_page_prot */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
@@ -350,7 +434,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
* Currently stuck as a macro due to indirect forward reference to
* linux/mmzone.h's __section_mem_map_addr() definition:
*/
-#define pmd_page(pmd) pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+#define pmd_page(pmd) pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT)
/*
* the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
@@ -524,12 +608,26 @@ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
return res;
}
+static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp)
+{
+ pmd_t res = *pmdp;
+
+ native_pmd_clear(pmdp);
+ return res;
+}
+
static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep , pte_t pte)
{
native_set_pte(ptep, pte);
}
+static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp , pmd_t pmd)
+{
+ native_set_pmd(pmdp, pmd);
+}
+
#ifndef CONFIG_PARAVIRT
/*
* Rules for using pte_update - it must be called after any PTE update which
@@ -607,6 +705,49 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
#define flush_tlb_fix_spurious_fault(vma, address)
+#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot))
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp,
+ pmd_t entry, int dirty);
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp);
+
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+ unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMD_WRITE
+static inline int pmd_write(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_RW;
+}
+
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ pmd_t pmd = native_pmdp_get_and_clear(pmdp);
+ pmd_update(mm, addr, pmdp);
+ return pmd;
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr, pmd_t *pmdp)
+{
+ clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
+ pmd_update(mm, addr, pmdp);
+}
+
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index f86da20347f2..975f709e09ae 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -59,6 +59,16 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
native_set_pte(ptep, pte);
}
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ *pmdp = pmd;
+}
+
+static inline void native_pmd_clear(pmd_t *pmd)
+{
+ native_set_pmd(pmd, native_make_pmd(0));
+}
+
static inline pte_t native_ptep_get_and_clear(pte_t *xp)
{
#ifdef CONFIG_SMP
@@ -72,14 +82,17 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
#endif
}
-static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
{
- *pmdp = pmd;
-}
-
-static inline void native_pmd_clear(pmd_t *pmd)
-{
- native_set_pmd(pmd, native_make_pmd(0));
+#ifdef CONFIG_SMP
+ return native_make_pmd(xchg(&xp->pmd, 0));
+#else
+ /* native_local_pmdp_get_and_clear,
+ but duplicated because of cyclic dependency */
+ pmd_t ret = *xp;
+ native_pmd_clear(xp);
+ return ret;
+#endif
}
static inline void native_set_pud(pud_t *pudp, pud_t pud)
@@ -168,6 +181,7 @@ extern void cleanup_highmap(void);
#define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
#define __HAVE_ARCH_PTE_SAME
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index d1f4a760be23..7db7723d1f32 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -22,6 +22,7 @@
#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1
+#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */
#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
/* If _PAGE_BIT_PRESENT is clear, we use these: */
@@ -45,6 +46,7 @@
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
#define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING)
#define __HAVE_ARCH_PTE_SPECIAL
#ifdef CONFIG_KMEMCHECK
@@ -70,6 +72,7 @@
/* Set of bits not changed in pte_modify */
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
#define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT)
#define _PAGE_CACHE_WB (0)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cae9c3cb95cf..45636cefa186 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -141,10 +141,9 @@ extern __u32 cpu_caps_set[NCAPINTS];
#ifdef CONFIG_SMP
DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
#define cpu_data(cpu) per_cpu(cpu_info, cpu)
-#define current_cpu_data __get_cpu_var(cpu_info)
#else
+#define cpu_info boot_cpu_data
#define cpu_data(cpu) boot_cpu_data
-#define current_cpu_data boot_cpu_data
#endif
extern const struct seq_operations cpuinfo_op;
@@ -762,10 +761,11 @@ extern void select_idle_routine(const struct cpuinfo_x86 *c);
extern void init_c1e_mask(void);
extern unsigned long boot_option_idle_override;
-extern unsigned long idle_halt;
-extern unsigned long idle_nomwait;
extern bool c1e_detected;
+enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
+ IDLE_POLL, IDLE_FORCE_MWAIT};
+
extern void enable_sep_cpu(void);
extern int sysenter_setup(void);
@@ -902,7 +902,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
/*
* The below -8 is to reserve 8 bytes on top of the ring0 stack.
* This is necessary to guarantee that the entire "struct pt_regs"
- * is accessable even if the CPU haven't stored the SS/ESP registers
+ * is accessible even if the CPU haven't stored the SS/ESP registers
* on the stack (interrupt gate does not save these registers
* when switching to the same priv ring).
* Therefore beware: accessing the ss/esp fields of the
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
new file mode 100644
index 000000000000..b4ec95f07518
--- /dev/null
+++ b/arch/x86/include/asm/prom.h
@@ -0,0 +1 @@
+/* dummy prom.h; here to make linux/of.h's #includes happy */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7f7e577a0e39..31d84acc1512 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -11,6 +11,7 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
struct pvclock_vcpu_time_info *vcpu,
struct timespec *ts);
+void pvclock_resume(void);
/*
* Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h
index 1def60114906..6c22bf353f26 100644
--- a/arch/x86/include/asm/smpboot_hooks.h
+++ b/arch/x86/include/asm/smpboot_hooks.h
@@ -48,7 +48,6 @@ static inline void __init smpboot_setup_io_apic(void)
setup_IO_APIC();
else {
nr_ioapics = 0;
- localise_nmi_watchdog();
}
#endif
}
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 2b16a2ad23dc..52b5c7ed3608 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -7,6 +7,7 @@
#define _ASM_X86_STACKTRACE_H
#include <linux/uaccess.h>
+#include <linux/ptrace.h>
extern int kstack_depth_to_print;
@@ -46,7 +47,7 @@ struct stacktrace_ops {
};
void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp,
+ unsigned long *stack,
const struct stacktrace_ops *ops, void *data);
#ifdef CONFIG_X86_32
@@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
#endif
+#ifdef CONFIG_FRAME_POINTER
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+ unsigned long bp;
+
+ if (regs)
+ return regs->bp;
+
+ if (task == current) {
+ /* Grab bp right from our regs */
+ get_bp(bp);
+ return bp;
+ }
+
+ /* bp is the last reg pushed by switch_to */
+ return *(unsigned long *)task->thread.sp;
+}
+#else
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+ return 0;
+}
+#endif
+
extern void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp, char *log_lvl);
+ unsigned long *stack, char *log_lvl);
extern void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl);
+ unsigned long *sp, char *log_lvl);
extern unsigned int code_bytes;
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 0e831059ac5a..f2b83bc7d784 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -47,14 +47,13 @@ enum {
INTERCEPT_MONITOR,
INTERCEPT_MWAIT,
INTERCEPT_MWAIT_COND,
+ INTERCEPT_XSETBV,
};
struct __attribute__ ((__packed__)) vmcb_control_area {
- u16 intercept_cr_read;
- u16 intercept_cr_write;
- u16 intercept_dr_read;
- u16 intercept_dr_write;
+ u32 intercept_cr;
+ u32 intercept_dr;
u32 intercept_exceptions;
u64 intercept;
u8 reserved_1[42];
@@ -81,14 +80,19 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
u32 event_inj_err;
u64 nested_cr3;
u64 lbr_ctl;
- u64 reserved_5;
+ u32 clean;
+ u32 reserved_5;
u64 next_rip;
- u8 reserved_6[816];
+ u8 insn_len;
+ u8 insn_bytes[15];
+ u8 reserved_6[800];
};
#define TLB_CONTROL_DO_NOTHING 0
#define TLB_CONTROL_FLUSH_ALL_ASID 1
+#define TLB_CONTROL_FLUSH_ASID 3
+#define TLB_CONTROL_FLUSH_ASID_LOCAL 7
#define V_TPR_MASK 0x0f
@@ -204,19 +208,31 @@ struct __attribute__ ((__packed__)) vmcb {
#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
#define SVM_SELECTOR_CODE_MASK (1 << 3)
-#define INTERCEPT_CR0_MASK 1
-#define INTERCEPT_CR3_MASK (1 << 3)
-#define INTERCEPT_CR4_MASK (1 << 4)
-#define INTERCEPT_CR8_MASK (1 << 8)
-
-#define INTERCEPT_DR0_MASK 1
-#define INTERCEPT_DR1_MASK (1 << 1)
-#define INTERCEPT_DR2_MASK (1 << 2)
-#define INTERCEPT_DR3_MASK (1 << 3)
-#define INTERCEPT_DR4_MASK (1 << 4)
-#define INTERCEPT_DR5_MASK (1 << 5)
-#define INTERCEPT_DR6_MASK (1 << 6)
-#define INTERCEPT_DR7_MASK (1 << 7)
+#define INTERCEPT_CR0_READ 0
+#define INTERCEPT_CR3_READ 3
+#define INTERCEPT_CR4_READ 4
+#define INTERCEPT_CR8_READ 8
+#define INTERCEPT_CR0_WRITE (16 + 0)
+#define INTERCEPT_CR3_WRITE (16 + 3)
+#define INTERCEPT_CR4_WRITE (16 + 4)
+#define INTERCEPT_CR8_WRITE (16 + 8)
+
+#define INTERCEPT_DR0_READ 0
+#define INTERCEPT_DR1_READ 1
+#define INTERCEPT_DR2_READ 2
+#define INTERCEPT_DR3_READ 3
+#define INTERCEPT_DR4_READ 4
+#define INTERCEPT_DR5_READ 5
+#define INTERCEPT_DR6_READ 6
+#define INTERCEPT_DR7_READ 7
+#define INTERCEPT_DR0_WRITE (16 + 0)
+#define INTERCEPT_DR1_WRITE (16 + 1)
+#define INTERCEPT_DR2_WRITE (16 + 2)
+#define INTERCEPT_DR3_WRITE (16 + 3)
+#define INTERCEPT_DR4_WRITE (16 + 4)
+#define INTERCEPT_DR5_WRITE (16 + 5)
+#define INTERCEPT_DR6_WRITE (16 + 6)
+#define INTERCEPT_DR7_WRITE (16 + 7)
#define SVM_EVTINJ_VEC_MASK 0xff
@@ -246,6 +262,8 @@ struct __attribute__ ((__packed__)) vmcb {
#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
+#define SVM_EXITINFO_REG_MASK 0x0F
+
#define SVM_EXIT_READ_CR0 0x000
#define SVM_EXIT_READ_CR3 0x003
#define SVM_EXIT_READ_CR4 0x004
@@ -316,6 +334,7 @@ struct __attribute__ ((__packed__)) vmcb {
#define SVM_EXIT_MONITOR 0x08a
#define SVM_EXIT_MWAIT 0x08b
#define SVM_EXIT_MWAIT_COND 0x08c
+#define SVM_EXIT_XSETBV 0x08d
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_ERR -1
diff --git a/arch/x86/include/asm/system_64.h b/arch/x86/include/asm/system_64.h
deleted file mode 100644
index 1159e091ad09..000000000000
--- a/arch/x86/include/asm/system_64.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_64_H
-#define _ASM_X86_SYSTEM_64_H
-
-#include <asm/segment.h>
-#include <asm/cmpxchg.h>
-
-
-static inline unsigned long read_cr8(void)
-{
- unsigned long cr8;
- asm volatile("movq %%cr8,%0" : "=r" (cr8));
- return cr8;
-}
-
-static inline void write_cr8(unsigned long val)
-{
- asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-
-#include <linux/irqflags.h>
-
-#endif /* _ASM_X86_SYSTEM_64_H */
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 5469630b27f5..fa7b9176b76c 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -10,12 +10,6 @@
unsigned long long native_sched_clock(void);
extern int recalibrate_cpu_khz(void);
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
-extern int timer_ack;
-#else
-# define timer_ack (0)
-#endif
-
extern int no_timer_check;
/* Accelerators for sched_clock()
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index f66cda56781d..0310da67307f 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -30,6 +30,7 @@ asmlinkage void segment_not_present(void);
asmlinkage void stack_segment(void);
asmlinkage void general_protection(void);
asmlinkage void page_fault(void);
+asmlinkage void async_page_fault(void);
asmlinkage void spurious_interrupt_bug(void);
asmlinkage void coprocessor_error(void);
asmlinkage void alignment_check(void);
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 42d412fd8b02..ce1d54c8a433 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -26,20 +26,22 @@
* BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
* set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
*
- * We will use 31 sets, one for sending BAU messages from each of the 32
+ * We will use one set for sending BAU messages from each of the
* cpu's on the uvhub.
*
* TLB shootdown will use the first of the 8 descriptors of each set.
* Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
*/
+#define MAX_CPUS_PER_UVHUB 64
+#define MAX_CPUS_PER_SOCKET 32
+#define UV_ADP_SIZE 64 /* hardware-provided max. */
+#define UV_CPUS_PER_ACT_STATUS 32 /* hardware-provided max. */
#define UV_ITEMS_PER_DESCRIPTOR 8
/* the 'throttle' to prevent the hardware stay-busy bug */
#define MAX_BAU_CONCURRENT 3
-#define UV_CPUS_PER_ACT_STATUS 32
#define UV_ACT_STATUS_MASK 0x3
#define UV_ACT_STATUS_SIZE 2
-#define UV_ADP_SIZE 32
#define UV_DISTRIBUTION_SIZE 256
#define UV_SW_ACK_NPENDING 8
#define UV_NET_ENDPOINT_INTD 0x38
@@ -100,7 +102,6 @@
* number of destination side software ack resources
*/
#define DEST_NUM_RESOURCES 8
-#define MAX_CPUS_PER_NODE 32
/*
* completion statuses for sending a TLB flush message
*/
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index e969f691cbfd..a501741c2335 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -199,6 +199,8 @@ union uvh_apicid {
#define UVH_APICID 0x002D0E00L
#define UV_APIC_PNODE_SHIFT 6
+#define UV_APICID_HIBIT_MASK 0xffff0000
+
/* Local Bus from cpu's perspective */
#define LOCAL_BUS_BASE 0x1c00000
#define LOCAL_BUS_SIZE (4 * 1024 * 1024)
@@ -491,8 +493,10 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
}
}
+extern unsigned int uv_apicid_hibits;
static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode)
{
+ apicid |= uv_apicid_hibits;
return (1UL << UVH_IPI_INT_SEND_SHFT) |
((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
(mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index b2f2d2e05cec..20cafeac7455 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -5,7 +5,7 @@
*
* SGI UV MMR definitions
*
- * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved.
*/
#ifndef _ASM_X86_UV_UV_MMRS_H
@@ -754,6 +754,23 @@ union uvh_lb_bau_sb_descriptor_base_u {
};
/* ========================================================================= */
+/* UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK */
+/* ========================================================================= */
+#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL
+#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x009f0
+
+#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0
+#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL
+
+union uvh_lb_target_physical_apic_id_mask_u {
+ unsigned long v;
+ struct uvh_lb_target_physical_apic_id_mask_s {
+ unsigned long bit_enables : 32; /* RW */
+ unsigned long rsvd_32_63 : 32; /* */
+ } s;
+};
+
+/* ========================================================================= */
/* UVH_NODE_ID */
/* ========================================================================= */
#define UVH_NODE_ID 0x0UL
@@ -806,6 +823,78 @@ union uvh_node_present_table_u {
};
/* ========================================================================= */
+/* UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
+ unsigned long v;
+ struct uvh_rh_gam_alias210_overlay_config_0_mmr_s {
+ unsigned long rsvd_0_23: 24; /* */
+ unsigned long base : 8; /* RW */
+ unsigned long rsvd_32_47: 16; /* */
+ unsigned long m_alias : 5; /* RW */
+ unsigned long rsvd_53_62: 10; /* */
+ unsigned long enable : 1; /* RW */
+ } s;
+};
+
+/* ========================================================================= */
+/* UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
+ unsigned long v;
+ struct uvh_rh_gam_alias210_overlay_config_1_mmr_s {
+ unsigned long rsvd_0_23: 24; /* */
+ unsigned long base : 8; /* RW */
+ unsigned long rsvd_32_47: 16; /* */
+ unsigned long m_alias : 5; /* RW */
+ unsigned long rsvd_53_62: 10; /* */
+ unsigned long enable : 1; /* RW */
+ } s;
+};
+
+/* ========================================================================= */
+/* UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
+ unsigned long v;
+ struct uvh_rh_gam_alias210_overlay_config_2_mmr_s {
+ unsigned long rsvd_0_23: 24; /* */
+ unsigned long base : 8; /* RW */
+ unsigned long rsvd_32_47: 16; /* */
+ unsigned long m_alias : 5; /* RW */
+ unsigned long rsvd_53_62: 10; /* */
+ unsigned long enable : 1; /* RW */
+ } s;
+};
+
+/* ========================================================================= */
/* UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR */
/* ========================================================================= */
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
@@ -857,6 +946,29 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
};
/* ========================================================================= */
+/* UVH_RH_GAM_CONFIG_MMR */
+/* ========================================================================= */
+#define UVH_RH_GAM_CONFIG_MMR 0x1600000UL
+
+#define UVH_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
+#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+union uvh_rh_gam_config_mmr_u {
+ unsigned long v;
+ struct uvh_rh_gam_config_mmr_s {
+ unsigned long m_skt : 6; /* RW */
+ unsigned long n_skt : 4; /* RW */
+ unsigned long rsvd_10_11: 2; /* */
+ unsigned long mmiol_cfg : 1; /* RW */
+ unsigned long rsvd_13_63: 51; /* */
+ } s;
+};
+
+/* ========================================================================= */
/* UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR */
/* ========================================================================= */
#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
@@ -987,97 +1099,5 @@ union uvh_rtc1_int_config_u {
} s;
};
-/* ========================================================================= */
-/* UVH_SI_ADDR_MAP_CONFIG */
-/* ========================================================================= */
-#define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
-
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_SHFT 0
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_SHFT 8
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_MASK 0x0000000000000f00UL
-
-union uvh_si_addr_map_config_u {
- unsigned long v;
- struct uvh_si_addr_map_config_s {
- unsigned long m_skt : 6; /* RW */
- unsigned long rsvd_6_7: 2; /* */
- unsigned long n_skt : 4; /* RW */
- unsigned long rsvd_12_63: 52; /* */
- } s;
-};
-
-/* ========================================================================= */
-/* UVH_SI_ALIAS0_OVERLAY_CONFIG */
-/* ========================================================================= */
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
-
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias0_overlay_config_u {
- unsigned long v;
- struct uvh_si_alias0_overlay_config_s {
- unsigned long rsvd_0_23: 24; /* */
- unsigned long base : 8; /* RW */
- unsigned long rsvd_32_47: 16; /* */
- unsigned long m_alias : 5; /* RW */
- unsigned long rsvd_53_62: 10; /* */
- unsigned long enable : 1; /* RW */
- } s;
-};
-
-/* ========================================================================= */
-/* UVH_SI_ALIAS1_OVERLAY_CONFIG */
-/* ========================================================================= */
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
-
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias1_overlay_config_u {
- unsigned long v;
- struct uvh_si_alias1_overlay_config_s {
- unsigned long rsvd_0_23: 24; /* */
- unsigned long base : 8; /* RW */
- unsigned long rsvd_32_47: 16; /* */
- unsigned long m_alias : 5; /* RW */
- unsigned long rsvd_53_62: 10; /* */
- unsigned long enable : 1; /* RW */
- } s;
-};
-
-/* ========================================================================= */
-/* UVH_SI_ALIAS2_OVERLAY_CONFIG */
-/* ========================================================================= */
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
-
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias2_overlay_config_u {
- unsigned long v;
- struct uvh_si_alias2_overlay_config_s {
- unsigned long rsvd_0_23: 24; /* */
- unsigned long base : 8; /* RW */
- unsigned long rsvd_32_47: 16; /* */
- unsigned long m_alias : 5; /* RW */
- unsigned long rsvd_53_62: 10; /* */
- unsigned long enable : 1; /* RW */
- } s;
-};
-
-#endif /* _ASM_X86_UV_UV_MMRS_H */
+#endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9f0cbd987d50..84471b810460 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -66,15 +66,23 @@
#define PIN_BASED_NMI_EXITING 0x00000008
#define PIN_BASED_VIRTUAL_NMIS 0x00000020
+#define VM_EXIT_SAVE_DEBUG_CONTROLS 0x00000002
#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL 0x00001000
#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000
#define VM_EXIT_SAVE_IA32_PAT 0x00040000
#define VM_EXIT_LOAD_IA32_PAT 0x00080000
+#define VM_EXIT_SAVE_IA32_EFER 0x00100000
+#define VM_EXIT_LOAD_IA32_EFER 0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS 0x00000002
#define VM_ENTRY_IA32E_MODE 0x00000200
#define VM_ENTRY_SMM 0x00000400
#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL 0x00002000
#define VM_ENTRY_LOAD_IA32_PAT 0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER 0x00008000
/* VMCS Encodings */
enum vmcs_field {
@@ -239,6 +247,7 @@ enum vmcs_field {
#define EXIT_REASON_TASK_SWITCH 9
#define EXIT_REASON_CPUID 10
#define EXIT_REASON_HLT 12
+#define EXIT_REASON_INVD 13
#define EXIT_REASON_INVLPG 14
#define EXIT_REASON_RDPMC 15
#define EXIT_REASON_RDTSC 16
@@ -296,6 +305,12 @@ enum vmcs_field {
#define GUEST_INTR_STATE_SMI 0x00000004
#define GUEST_INTR_STATE_NMI 0x00000008
+/* GUEST_ACTIVITY_STATE flags */
+#define GUEST_ACTIVITY_ACTIVE 0
+#define GUEST_ACTIVITY_HLT 1
+#define GUEST_ACTIVITY_SHUTDOWN 2
+#define GUEST_ACTIVITY_WAIT_SIPI 3
+
/*
* Exit Qualifications for MOV for Control Register Access
*/
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 396ff4cc8ed4..66d0fff1ee84 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -37,4 +37,39 @@
extern struct shared_info *HYPERVISOR_shared_info;
extern struct start_info *xen_start_info;
+#include <asm/processor.h>
+
+static inline uint32_t xen_cpuid_base(void)
+{
+ uint32_t base, eax, ebx, ecx, edx;
+ char signature[13];
+
+ for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+ cpuid(base, &eax, &ebx, &ecx, &edx);
+ *(uint32_t *)(signature + 0) = ebx;
+ *(uint32_t *)(signature + 4) = ecx;
+ *(uint32_t *)(signature + 8) = edx;
+ signature[12] = 0;
+
+ if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
+ return base;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_XEN
+extern bool xen_hvm_need_lapic(void);
+
+static inline bool xen_x2apic_para_available(void)
+{
+ return xen_hvm_need_lapic();
+}
+#else
+static inline bool xen_x2apic_para_available(void)
+{
+ return (xen_cpuid_base() != 0);
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index e8506c1f0c55..1c10c88ee4e1 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -61,9 +61,9 @@ DEFINE_GUEST_HANDLE(void);
#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
#endif
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT)
/* Maximum number of virtual CPUs in multi-processor guests. */
#define MAX_VIRT_CPUS 32
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index 42a7e004ae5c..8413688b2571 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -32,6 +32,11 @@
/* And the trap vector is... */
#define TRAP_INSTR "int $0x82"
+#define __MACH2PHYS_VIRT_START 0xF5800000
+#define __MACH2PHYS_VIRT_END 0xF6800000
+
+#define __MACH2PHYS_SHIFT 2
+
/*
* Virtual addresses beyond this are not modifiable by guest OSes. The
* machine->physical mapping table starts at this address, read-only.
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index 100d2662b97c..839a4811cf98 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -39,18 +39,7 @@
#define __HYPERVISOR_VIRT_END 0xFFFF880000000000
#define __MACH2PHYS_VIRT_START 0xFFFF800000000000
#define __MACH2PHYS_VIRT_END 0xFFFF804000000000
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#define HYPERVISOR_VIRT_END mk_unsigned_long(__HYPERVISOR_VIRT_END)
-#endif
-
-#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START)
-#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END)
-#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define __MACH2PHYS_SHIFT 3
/*
* int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index dd8c1414b3d5..f25bdf238a33 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -5,6 +5,7 @@
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/pfn.h>
+#include <linux/mm.h>
#include <asm/uaccess.h>
#include <asm/page.h>
@@ -35,10 +36,17 @@ typedef struct xpaddr {
#define MAX_DOMAIN_PAGES \
((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
+extern unsigned long *machine_to_phys_mapping;
+extern unsigned int machine_to_phys_order;
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern int m2p_add_override(unsigned long mfn, struct page *page);
+extern int m2p_remove_override(struct page *page);
+extern struct page *m2p_find_override(unsigned long mfn);
+extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
+
static inline unsigned long pfn_to_mfn(unsigned long pfn)
{
unsigned long mfn;
@@ -69,11 +77,6 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
-#if 0
- if (unlikely((mfn >> machine_to_phys_order) != 0))
- return max_mapnr;
-#endif
-
pfn = 0;
/*
* The array access can fail (e.g., device space beyond end of RAM).
@@ -82,6 +85,14 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
*/
__get_user(pfn, &machine_to_phys_mapping[mfn]);
+ /*
+ * If this appears to be a foreign mfn (because the pfn
+ * doesn't map back to the mfn), then check the local override
+ * table to see if there's a better pfn to use.
+ */
+ if (get_phys_to_machine(pfn) != mfn)
+ pfn = m2p_find_override_pfn(mfn, pfn);
+
return pfn;
}