diff options
| author | Jiri Kosina <jkosina@suse.cz> | 2011-02-15 10:24:31 +0100 |
|---|---|---|
| committer | Jiri Kosina <jkosina@suse.cz> | 2011-02-15 10:24:31 +0100 |
| commit | 0a9d59a2461477bd9ed143c01af9df3f8f00fa81 (patch) | |
| tree | df997d1cfb0786427a0df1fbd6f0640fa4248cf4 /arch/x86 | |
| parent | a23ce6da9677d245aa0aadc99f4197030350ab54 (diff) | |
| parent | 795abaf1e4e188c4171e3cd3dbb11a9fcacaf505 (diff) | |
Merge branch 'master' into for-next
Diffstat (limited to 'arch/x86')
64 files changed, 1262 insertions, 666 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 36ed2e2c896b..d5ed94d30aad 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -627,11 +627,11 @@ config APB_TIMER as it is off-chip. APB timers are always running regardless of CPU C states, they are used as per CPU clockevent device when possible. -# Mark as embedded because too many people got it wrong. +# Mark as expert because too many people got it wrong. # The code disables itself when not needed. config DMI default y - bool "Enable DMI scanning" if EMBEDDED + bool "Enable DMI scanning" if EXPERT ---help--- Enabled scanning of DMI to identify machine quirks. Say Y here unless you have verified that your setup is not @@ -639,7 +639,7 @@ config DMI BIOS code. config GART_IOMMU - bool "GART IOMMU support" if EMBEDDED + bool "GART IOMMU support" if EXPERT default y select SWIOTLB depends on X86_64 && PCI && AMD_NB @@ -889,7 +889,7 @@ config X86_THERMAL_VECTOR depends on X86_MCE_INTEL config VM86 - bool "Enable VM86 support" if EMBEDDED + bool "Enable VM86 support" if EXPERT default y depends on X86_32 ---help--- @@ -1073,7 +1073,7 @@ endchoice choice depends on EXPERIMENTAL - prompt "Memory split" if EMBEDDED + prompt "Memory split" if EXPERT default VMSPLIT_3G depends on X86_32 ---help--- @@ -1135,7 +1135,7 @@ config ARCH_DMA_ADDR_T_64BIT def_bool X86_64 || HIGHMEM64G config DIRECT_GBPAGES - bool "Enable 1GB pages for kernel pagetables" if EMBEDDED + bool "Enable 1GB pages for kernel pagetables" if EXPERT default y depends on X86_64 ---help--- @@ -1369,7 +1369,7 @@ config MATH_EMULATION config MTRR def_bool y - prompt "MTRR (Memory Type Range Register) support" if EMBEDDED + prompt "MTRR (Memory Type Range Register) support" if EXPERT ---help--- On Intel P6 family processors (Pentium Pro, Pentium II and later) the Memory Type Range Registers (MTRRs) may be used to control @@ -1435,7 +1435,7 @@ config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT config X86_PAT def_bool y - prompt "x86 PAT support" if EMBEDDED + prompt "x86 PAT support" if EXPERT depends on MTRR ---help--- Use PAT attributes to setup page level cache control. @@ -1539,7 +1539,7 @@ config KEXEC_JUMP code in physical address mode via KEXEC config PHYSICAL_START - hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) + hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP) default "0x1000000" ---help--- This gives the physical address where the kernel is loaded. @@ -1934,13 +1934,19 @@ config PCI_MMCONFIG depends on X86_64 && PCI && ACPI config PCI_CNB20LE_QUIRK - bool "Read CNB20LE Host Bridge Windows" - depends on PCI + bool "Read CNB20LE Host Bridge Windows" if EXPERT + default n + depends on PCI && EXPERIMENTAL help Read the PCI windows out of the CNB20LE host bridge. This allows PCI hotplug to work on systems with the CNB20LE chipset which do not have ACPI. + There's no public spec for this chipset, and this functionality + is known to be incomplete. + + You should say N unless you know you need this. + config DMAR bool "Support for DMA Remapping Devices (EXPERIMENTAL)" depends on PCI_MSI && ACPI && EXPERIMENTAL @@ -2062,13 +2068,14 @@ config OLPC bool "One Laptop Per Child support" select GPIOLIB select OLPC_OPENFIRMWARE + depends on !X86_64 && !X86_PAE ---help--- Add support for detecting the unique features of the OLPC XO hardware. config OLPC_XO1 tristate "OLPC XO-1 support" - depends on OLPC && PCI + depends on OLPC && MFD_CS5535 ---help--- Add support for non-essential features of the OLPC XO-1 laptop. diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 15588a0ef466..283c5a6a03a6 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -424,7 +424,7 @@ config X86_DEBUGCTLMSR depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386) && !UML menuconfig PROCESSOR_SELECT - bool "Supported processor vendors" if EMBEDDED + bool "Supported processor vendors" if EXPERT ---help--- This lets you choose what x86 vendor support code your kernel will include. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 45143bbcfe5e..615e18810f48 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -31,7 +31,7 @@ config X86_VERBOSE_BOOTUP see errors. Disable this if you want silent bootup. config EARLY_PRINTK - bool "Early printk" if EMBEDDED + bool "Early printk" if EXPERT default y ---help--- Write kernel log output directly into the VGA buffer or to a serial @@ -138,7 +138,7 @@ config DEBUG_NX_TEST config DOUBLEFAULT default y - bool "Enable doublefault exception handler" if EMBEDDED + bool "Enable doublefault exception handler" if EXPERT depends on X86_32 ---help--- This option allows trapping of rare doublefault exceptions that 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/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/kvm_host.h b/arch/x86/include/asm/kvm_host.h index aa75f21a9fba..ffd7f8d29187 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -822,6 +822,7 @@ extern bool kvm_rebooting; #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); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 4a2d4e0c18d9..8b5393ec1080 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -36,8 +36,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, unsigned cpu = smp_processor_id(); if (likely(prev != next)) { - /* stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); #ifdef CONFIG_SMP percpu_write(cpu_tlbstate.state, TLBSTATE_OK); percpu_write(cpu_tlbstate.active_mm, next); @@ -47,6 +45,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); + /* stop flush ipis for the previous mm */ + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + /* * load the LDT, if the LDT is different: */ 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 5ae87285a502..0493be39607c 100644 --- a/arch/x86/include/asm/numa_64.h +++ b/arch/x86/include/asm/numa_64.h @@ -40,6 +40,7 @@ extern void __cpuinit numa_remove_cpu(int cpu); #ifdef CONFIG_NUMA_EMU #define FAKE_NODE_MIN_SIZE ((u64)32 << 20) #define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) +void numa_emu_cmdline(char *); #endif /* CONFIG_NUMA_EMU */ #else static inline void init_cpu_to_node(void) { } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7709c12431b8..ebbc4d8ab170 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -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); 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/percpu.h b/arch/x86/include/asm/percpu.h index 8ee45167e817..7e172955ee57 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -273,34 +273,34 @@ do { \ typeof(var) pxo_new__ = (nval); \ switch (sizeof(var)) { \ case 1: \ - asm("\n1:mov "__percpu_arg(1)",%%al" \ - "\n\tcmpxchgb %2, "__percpu_arg(1) \ + asm("\n\tmov "__percpu_arg(1)",%%al" \ + "\n1:\tcmpxchgb %2, "__percpu_arg(1) \ "\n\tjnz 1b" \ - : "=a" (pxo_ret__), "+m" (var) \ + : "=&a" (pxo_ret__), "+m" (var) \ : "q" (pxo_new__) \ : "memory"); \ break; \ case 2: \ - asm("\n1:mov "__percpu_arg(1)",%%ax" \ - "\n\tcmpxchgw %2, "__percpu_arg(1) \ + asm("\n\tmov "__percpu_arg(1)",%%ax" \ + "\n1:\tcmpxchgw %2, "__percpu_arg(1) \ "\n\tjnz 1b" \ - : "=a" (pxo_ret__), "+m" (var) \ + : "=&a" (pxo_ret__), "+m" (var) \ : "r" (pxo_new__) \ : "memory"); \ break; \ case 4: \ - asm("\n1:mov "__percpu_arg(1)",%%eax" \ - "\n\tcmpxchgl %2, "__percpu_arg(1) \ + asm("\n\tmov "__percpu_arg(1)",%%eax" \ + "\n1:\tcmpxchgl %2, "__percpu_arg(1) \ "\n\tjnz 1b" \ - : "=a" (pxo_ret__), "+m" (var) \ + : "=&a" (pxo_ret__), "+m" (var) \ : "r" (pxo_new__) \ : "memory"); \ break; \ case 8: \ - asm("\n1:mov "__percpu_arg(1)",%%rax" \ - "\n\tcmpxchgq %2, "__percpu_arg(1) \ + asm("\n\tmov "__percpu_arg(1)",%%rax" \ + "\n1:\tcmpxchgq %2, "__percpu_arg(1) \ "\n\tjnz 1b" \ - : "=a" (pxo_ret__), "+m" (var) \ + : "=&a" (pxo_ret__), "+m" (var) \ : "r" (pxo_new__) \ : "memory"); \ break; \ @@ -414,8 +414,6 @@ do { \ #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 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_1(pcp, val) percpu_add_op((pcp), val) #define irqsafe_cpu_add_2(pcp, val) percpu_add_op((pcp), val) @@ -432,8 +430,6 @@ do { \ #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) -#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) #ifndef CONFIG_M386 #define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val) @@ -475,11 +471,15 @@ do { \ #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/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 53fd1d5a1fe0..45636cefa186 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -761,10 +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); diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4c2f63c7fc1b..1f4695136776 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -40,10 +40,7 @@ DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); /* Static state in head.S used to set up a CPU */ -extern struct { - void *sp; - unsigned short ss; -} stack_start; +extern unsigned long stack_start; /* Initial stack pointer address */ struct smp_ops { void (*smp_prepare_boot_cpu)(void); 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/xen/page.h b/arch/x86/include/asm/xen/page.h index 8760cc60a21c..f25bdf238a33 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -42,6 +42,11 @@ 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; @@ -72,9 +77,6 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely((mfn >> machine_to_phys_order) != 0)) - return ~0; - pfn = 0; /* * The array access can fail (e.g., device space beyond end of RAM). @@ -83,6 +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; } diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index ec881c6bfee0..b3a71137983a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -509,6 +509,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) return 0; } +EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 69fd72aa5594..68d1537b8c81 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -12,10 +12,8 @@ #include <linux/cpumask.h> #include <asm/segment.h> #include <asm/desc.h> - -#ifdef CONFIG_X86_32 #include <asm/pgtable.h> -#endif +#include <asm/cacheflush.h> #include "realmode/wakeup.h" #include "sleep.h" @@ -100,7 +98,7 @@ int acpi_save_state_mem(void) #else /* CONFIG_64BIT */ header->trampoline_segment = setup_trampoline() >> 4; #ifdef CONFIG_SMP - stack_start.sp = temp_stack + sizeof(temp_stack); + stack_start = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); @@ -149,6 +147,15 @@ void __init acpi_reserve_wakeup_memory(void) memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); } +int __init acpi_configure_wakeup_memory(void) +{ + if (acpi_realmode) + set_memory_x(acpi_realmode, WAKEUP_SIZE >> PAGE_SHIFT); + + return 0; +} +arch_initcall(acpi_configure_wakeup_memory); + static int __init acpi_sleep_setup(char *str) { diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 7c9ab59653e8..51ef31a89be9 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -313,14 +313,16 @@ static void apbt_setup_irq(struct apbt_dev *adev) if (adev->irq == 0) return; + irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); + irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); + /* APB timer irqs are set up as mp_irqs, timer is edge type */ + __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge"); + if (system_state == SYSTEM_BOOTING) { - irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); - irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); - /* APB timer irqs are set up as mp_irqs, timer is edge type */ - __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge"); if (request_irq(adev->irq, apbt_interrupt_handler, - IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING, - adev->name, adev)) { + IRQF_TIMER | IRQF_DISABLED | + IRQF_NOBALANCING, + adev->name, adev)) { printk(KERN_ERR "Failed request IRQ for APBT%d\n", adev->num); } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 7283e98deaae..ec2c19a7b8ef 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -45,6 +45,7 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0x0a, LVL_1_DATA, 8 }, /* 2 way set assoc, 32 byte line size */ { 0x0c, LVL_1_DATA, 16 }, /* 4-way set assoc, 32 byte line size */ { 0x0d, LVL_1_DATA, 16 }, /* 4-way set assoc, 64 byte line size */ + { 0x0e, LVL_1_DATA, 24 }, /* 6-way set assoc, 64 byte line size */ { 0x21, LVL_2, 256 }, /* 8-way set assoc, 64 byte line size */ { 0x22, LVL_3, 512 }, /* 4-way set assoc, sectored cache, 64 byte line size */ { 0x23, LVL_3, MB(1) }, /* 8-way set assoc, sectored cache, 64 byte line size */ @@ -66,6 +67,7 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0x45, LVL_2, MB(2) }, /* 4-way set assoc, 32 byte line size */ { 0x46, LVL_3, MB(4) }, /* 4-way set assoc, 64 byte line size */ { 0x47, LVL_3, MB(8) }, /* 8-way set assoc, 64 byte line size */ + { 0x48, LVL_2, MB(3) }, /* 12-way set assoc, 64 byte line size */ { 0x49, LVL_3, MB(4) }, /* 16-way set assoc, 64 byte line size */ { 0x4a, LVL_3, MB(6) }, /* 12-way set assoc, 64 byte line size */ { 0x4b, LVL_3, MB(8) }, /* 16-way set assoc, 64 byte line size */ @@ -87,6 +89,7 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0x7c, LVL_2, MB(1) }, /* 8-way set assoc, sectored cache, 64 byte line size */ { 0x7d, LVL_2, MB(2) }, /* 8-way set assoc, 64 byte line size */ { 0x7f, LVL_2, 512 }, /* 2-way set assoc, 64 byte line size */ + { 0x80, LVL_2, 512 }, /* 8-way set assoc, 64 byte line size */ { 0x82, LVL_2, 256 }, /* 8-way set assoc, 32 byte line size */ { 0x83, LVL_2, 512 }, /* 8-way set assoc, 32 byte line size */ { 0x84, LVL_2, MB(1) }, /* 8-way set assoc, 32 byte line size */ diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index e12246ff5aa6..6f8c5e9da97f 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -59,6 +59,7 @@ struct thermal_state { /* Callback to handle core threshold interrupts */ int (*platform_thermal_notify)(__u64 msr_val); +EXPORT_SYMBOL(platform_thermal_notify); static DEFINE_PER_CPU(struct thermal_state, thermal_state); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 01c0f3ee6cc3..bebabec5b448 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -793,13 +793,21 @@ void set_mtrr_aps_delayed_init(void) } /* - * MTRR initialization for all AP's + * Delayed MTRR initialization for all AP's */ void mtrr_aps_init(void) { if (!use_intel()) return; + /* + * Check if someone has requested the delay of AP MTRR initialization, + * by doing set_mtrr_aps_delayed_init(), prior to this point. If not, + * then we are done. + */ + if (!mtrr_aps_delayed_init) + return; + set_mtrr(~0U, 0, 0, 0); mtrr_aps_delayed_init = false; } diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index e56b9bfbabd1..f7a0993c1e7c 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -682,7 +682,7 @@ static int p4_validate_raw_event(struct perf_event *event) * if an event is shared accross the logical threads * the user needs special permissions to be able to use it */ - if (p4_event_bind_map[v].shared) { + if (p4_ht_active() && p4_event_bind_map[v].shared) { if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return -EACCES; } @@ -727,7 +727,8 @@ static int p4_hw_config(struct perf_event *event) event->hw.config = p4_set_ht_bit(event->hw.config); if (event->attr.type == PERF_TYPE_RAW) { - + struct p4_event_bind *bind; + unsigned int esel; /* * Clear bits we reserve to be managed by kernel itself * and never allowed from a user space @@ -743,6 +744,13 @@ static int p4_hw_config(struct perf_event *event) * bits since we keep additional info here (for cache events and etc) */ event->hw.config |= event->attr.config; + bind = p4_config_get_bind(event->attr.config); + if (!bind) { + rc = -EINVAL; + goto out; + } + esel = P4_OPCODE_ESEL(bind->opcode); + event->hw.config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel)); } rc = x86_setup_perfctr(event); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index d6fb146c0d8b..df20723a6a1b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -234,6 +234,7 @@ unsigned __kprobes long oops_begin(void) bust_spinlocks(1); return flags; } +EXPORT_SYMBOL_GPL(oops_begin); void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) { diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 64101335de19..a6b6fcf7f0ae 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -149,13 +149,13 @@ void dump_trace(struct task_struct *task, unsigned used = 0; struct thread_info *tinfo; int graph = 0; + unsigned long dummy; unsigned long bp; if (!task) task = current; if (!stack) { - unsigned long dummy; stack = &dummy; if (task && task != current) stack = (unsigned long *)task->thread.sp; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 0c2b7ef7a34d..294f26da0c0c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -14,6 +14,7 @@ #include <linux/bootmem.h> #include <linux/pfn.h> #include <linux/suspend.h> +#include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/memblock.h> diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index fc293dc8dc35..767d6c43de37 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -85,6 +85,8 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) */ __HEAD ENTRY(startup_32) + movl pa(stack_start),%ecx + /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ testb $(1<<6), BP_loadflags(%esi) @@ -99,7 +101,9 @@ ENTRY(startup_32) movl %eax,%es movl %eax,%fs movl %eax,%gs + movl %eax,%ss 2: + leal -__PAGE_OFFSET(%ecx),%esp /* * Clear BSS first so that there are no surprises... @@ -145,8 +149,6 @@ ENTRY(startup_32) * _brk_end is set up to point to the first "safe" location. * Mappings are created both at virtual address 0 (identity mapping) * and PAGE_OFFSET for up to _end. - * - * Note that the stack is not yet set up! */ #ifdef CONFIG_X86_PAE @@ -282,6 +284,9 @@ ENTRY(startup_32_smp) movl %eax,%es movl %eax,%fs movl %eax,%gs + movl pa(stack_start),%ecx + movl %eax,%ss + leal -__PAGE_OFFSET(%ecx),%esp #endif /* CONFIG_SMP */ default_entry: @@ -347,8 +352,8 @@ default_entry: movl %eax,%cr0 /* ..and set paging (PG) bit */ ljmp $__BOOT_CS,$1f /* Clear prefetch and normalize %eip */ 1: - /* Set up the stack pointer */ - lss stack_start,%esp + /* Shift the stack pointer to a virtual address */ + addl $__PAGE_OFFSET, %esp /* * Initialize eflags. Some BIOS's leave bits like NT set. This would @@ -360,9 +365,7 @@ default_entry: #ifdef CONFIG_SMP cmpb $0, ready - jz 1f /* Initial CPU cleans BSS */ - jmp checkCPUtype -1: + jnz checkCPUtype #endif /* CONFIG_SMP */ /* @@ -470,14 +473,7 @@ is386: movl $2,%ecx # set MP cld # gcc2 wants the direction flag cleared at all times pushl $0 # fake return address for unwinder -#ifdef CONFIG_SMP - movb ready, %cl movb $1, ready - cmpb $0,%cl # the first CPU calls start_kernel - je 1f - movl (stack_start), %esp -1: -#endif /* CONFIG_SMP */ jmp *(initial_code) /* @@ -670,15 +666,15 @@ ENTRY(initial_page_table) #endif .data +.balign 4 ENTRY(stack_start) .long init_thread_union+THREAD_SIZE - .long __BOOT_DS - -ready: .byte 0 early_recursion_flag: .long 0 +ready: .byte 0 + int_msg: .asciz "Unknown interrupt or fault at: %p %p %p\n" diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 48ff6dcffa02..9974d21048fd 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -129,8 +129,7 @@ void __cpuinit irq_ctx_init(int cpu) irqctx = page_address(alloc_pages_node(cpu_to_node(cpu), THREAD_FLAGS, THREAD_ORDER)); - irqctx->tinfo.task = NULL; - irqctx->tinfo.exec_domain = NULL; + memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); irqctx->tinfo.cpu = cpu; irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); @@ -140,10 +139,8 @@ void __cpuinit irq_ctx_init(int cpu) irqctx = page_address(alloc_pages_node(cpu_to_node(cpu), THREAD_FLAGS, THREAD_ORDER)); - irqctx->tinfo.task = NULL; - irqctx->tinfo.exec_domain = NULL; + memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = 0; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); per_cpu(softirq_ctx, cpu) = irqctx; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 8f2956091735..ab23f1ad4bf1 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -37,20 +37,11 @@ void *module_alloc(unsigned long size) { - struct vm_struct *area; - - if (!size) - return NULL; - size = PAGE_ALIGN(size); - if (size > MODULES_LEN) + if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - - area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END); - if (!area) - return NULL; - - return __vmalloc_area(area, GFP_KERNEL | __GFP_HIGHMEM, - PAGE_KERNEL_EXEC); + return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, + GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, + -1, __builtin_return_address(0)); } /* Free memory returned from module_alloc */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c5b250011fd4..869e1aeeb71b 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -421,8 +421,11 @@ struct pv_mmu_ops pv_mmu_ops = { .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, .set_pmd = native_set_pmd, + .set_pmd_at = native_set_pmd_at, .pte_update = paravirt_nop, .pte_update_defer = paravirt_nop, + .pmd_update = paravirt_nop, + .pmd_update_defer = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 09c08a1c706f..e764fc05d700 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -14,6 +14,7 @@ #include <linux/utsname.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> +#include <asm/cpu.h> #include <asm/system.h> #include <asm/apic.h> #include <asm/syscalls.h> @@ -22,11 +23,6 @@ #include <asm/i387.h> #include <asm/debugreg.h> -unsigned long idle_halt; -EXPORT_SYMBOL(idle_halt); -unsigned long idle_nomwait; -EXPORT_SYMBOL(idle_nomwait); - struct kmem_cache *task_xstate_cachep; EXPORT_SYMBOL_GPL(task_xstate_cachep); @@ -327,7 +323,7 @@ long sys_execve(const char __user *name, /* * Idle related variables and functions */ -unsigned long boot_option_idle_override = 0; +unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); /* @@ -386,6 +382,8 @@ void default_idle(void) else local_irq_enable(); current_thread_info()->status |= TS_POLLING; + trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); /* loop is done by the caller */ @@ -443,8 +441,6 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); */ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { - trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); - trace_cpu_idle((ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -471,6 +467,8 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); + trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } else local_irq_enable(); } @@ -503,17 +501,16 @@ static void poll_idle(void) * * idle=mwait overrides this decision and forces the usage of mwait. */ -static int __cpuinitdata force_mwait; #define MWAIT_INFO 0x05 #define MWAIT_ECX_EXTENDED_INFO 0x01 #define MWAIT_EDX_C1 0xf0 -static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) +int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; - if (force_mwait) + if (boot_option_idle_override == IDLE_FORCE_MWAIT) return 1; if (c->cpuid_level < MWAIT_INFO) @@ -633,9 +630,10 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { printk("using polling idle threads.\n"); pm_idle = poll_idle; - } else if (!strcmp(str, "mwait")) - force_mwait = 1; - else if (!strcmp(str, "halt")) { + boot_option_idle_override = IDLE_POLL; + } else if (!strcmp(str, "mwait")) { + boot_option_idle_override = IDLE_FORCE_MWAIT; + } else if (!strcmp(str, "halt")) { /* * When the boot option of idle=halt is added, halt is * forced to be used for CPU idle. In such case CPU C2/C3 @@ -644,8 +642,7 @@ static int __init idle_setup(char *str) * the boot_option_idle_override. */ pm_idle = default_idle; - idle_halt = 1; - return 0; + boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { /* * If the boot option of "idle=nomwait" is added, @@ -653,12 +650,10 @@ static int __init idle_setup(char *str) * states. In such case it won't touch the variable * of boot_option_idle_override. */ - idle_nomwait = 1; - return 0; + boot_option_idle_override = IDLE_NOMWAIT; } else return -1; - boot_option_idle_override = 1; return 0; } early_param("idle", idle_setup); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4b9befa0e347..8d128783af47 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -57,8 +57,6 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> -#include <trace/events/power.h> - asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); /* @@ -113,8 +111,6 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4c818a738396..bd387e8f73b4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,8 +51,6 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> -#include <trace/events/power.h> - asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); @@ -141,10 +139,6 @@ void cpu_idle(void) pm_idle(); start_critical_timings(); - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, - smp_processor_id()); - /* In many cases the interrupt that ended idle has already called exit_idle. But some idle loops can be woken up without interrupt. */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 763df77343dd..03273b6c272c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -638,7 +638,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) * target processor state. */ startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - (unsigned long)stack_start.sp); + stack_start); /* * Run STARTUP IPI loop. @@ -785,7 +785,7 @@ do_rest: #endif early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; - stack_start.sp = (void *) c_idle.idle->thread.sp; + stack_start = c_idle.idle->thread.sp; /* start_ip had better be page-aligned! */ start_ip = setup_trampoline(); @@ -1402,8 +1402,9 @@ static inline void mwait_play_dead(void) unsigned int highest_subcstate = 0; int i; void *mwait_ptr; + struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info); - if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_MWAIT)) + if (!(cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c))) return; if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLSH)) return; diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index c2f1b26141e2..998e972f3b1a 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -133,7 +133,7 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, pmd = pmd_alloc(&tboot_mm, pud, vaddr); if (!pmd) return -1; - pte = pte_alloc_map(&tboot_mm, pmd, vaddr); + pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr); if (!pte) return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 823f79a17ad1..ffe5755caa8b 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -464,7 +464,7 @@ unsigned long native_calibrate_tsc(void) tsc_pit_min = min(tsc_pit_min, tsc_pit_khz); /* hpet or pmtimer available ? */ - if (!hpet && !ref1 && !ref2) + if (ref1 == ref2) continue; /* Check, whether the sampling was disturbed by an SMI */ @@ -935,7 +935,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) tsc_stop = tsc_read_refs(&ref_stop, hpet); /* hpet or pmtimer available ? */ - if (!hpet && !ref_start && !ref_stop) + if (ref_start == ref_stop) goto out; /* Check, whether the sampling was disturbed by an SMI */ diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 61fb98519622..863f8753ab0a 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -179,6 +179,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); + split_huge_page_pmd(mm, pmd); if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9cafbb499813..f02b8edc3d44 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -554,14 +554,18 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) return ret; } -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) +static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) { struct kvm_memory_slot *slot; - int host_level, level, max_level; - slot = gfn_to_memslot(vcpu->kvm, large_gfn); if (slot && slot->dirty_bitmap) - return PT_PAGE_TABLE_LEVEL; + return true; + return false; +} + +static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) +{ + int host_level, level, max_level; host_level = host_mapping_level(vcpu->kvm, large_gfn); @@ -941,6 +945,35 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, return young; } +static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, + unsigned long data) +{ + u64 *spte; + int young = 0; + + /* + * If there's no access bit in the secondary pte set by the + * hardware it's up to gup-fast/gup to set the access bit in + * the primary pte or in the page structure. + */ + if (!shadow_accessed_mask) + goto out; + + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + u64 _spte = *spte; + BUG_ON(!(_spte & PT_PRESENT_MASK)); + young = _spte & PT_ACCESSED_MASK; + if (young) { + young = 1; + break; + } + spte = rmap_next(kvm, rmapp, spte); + } +out: + return young; +} + #define RMAP_RECYCLE_THRESHOLD 1000 static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) @@ -961,6 +994,11 @@ int kvm_age_hva(struct kvm *kvm, unsigned long hva) return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp); } +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp); +} + #ifdef MMU_DEBUG static int is_empty_shadow_page(u64 *spt) { @@ -2281,6 +2319,48 @@ static int kvm_handle_bad_page(struct kvm *kvm, gfn_t gfn, pfn_t pfn) return 1; } +static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, + gfn_t *gfnp, pfn_t *pfnp, int *levelp) +{ + pfn_t pfn = *pfnp; + gfn_t gfn = *gfnp; + int level = *levelp; + + /* + * Check if it's a transparent hugepage. If this would be an + * hugetlbfs page, level wouldn't be set to + * PT_PAGE_TABLE_LEVEL and there would be no adjustment done + * here. + */ + if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn) && + level == PT_PAGE_TABLE_LEVEL && + PageTransCompound(pfn_to_page(pfn)) && + !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) { + unsigned long mask; + /* + * mmu_notifier_retry was successful and we hold the + * mmu_lock here, so the pmd can't become splitting + * from under us, and in turn + * __split_huge_page_refcount() can't run from under + * us and we can safely transfer the refcount from + * PG_tail to PG_head as we switch the pfn to tail to + * head. + */ + *levelp = level = PT_DIRECTORY_LEVEL; + mask = KVM_PAGES_PER_HPAGE(level) - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + if (pfn & mask) { + gfn &= ~mask; + *gfnp = gfn; + kvm_release_pfn_clean(pfn); + pfn &= ~mask; + if (!get_page_unless_zero(pfn_to_page(pfn))) + BUG(); + *pfnp = pfn; + } + } +} + static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable); @@ -2289,20 +2369,25 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn, { int r; int level; + int force_pt_level; pfn_t pfn; unsigned long mmu_seq; bool map_writable; - level = mapping_level(vcpu, gfn); - - /* - * This path builds a PAE pagetable - so we can map 2mb pages at - * maximum. Therefore check if the level is larger than that. - */ - if (level > PT_DIRECTORY_LEVEL) - level = PT_DIRECTORY_LEVEL; + force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + if (likely(!force_pt_level)) { + level = mapping_level(vcpu, gfn); + /* + * This path builds a PAE pagetable - so we can map + * 2mb pages at maximum. Therefore check if the level + * is larger than that. + */ + if (level > PT_DIRECTORY_LEVEL) + level = PT_DIRECTORY_LEVEL; - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + } else + level = PT_PAGE_TABLE_LEVEL; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -2318,6 +2403,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn, if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; kvm_mmu_free_some_pages(vcpu); + if (likely(!force_pt_level)) + transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); @@ -2655,6 +2742,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, pfn_t pfn; int r; int level; + int force_pt_level; gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; @@ -2667,9 +2755,12 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - level = mapping_level(vcpu, gfn); - - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + if (likely(!force_pt_level)) { + level = mapping_level(vcpu, gfn); + gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + } else + level = PT_PAGE_TABLE_LEVEL; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -2684,6 +2775,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; kvm_mmu_free_some_pages(vcpu); + if (likely(!force_pt_level)) + transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); r = __direct_map(vcpu, gpa, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 53210f1e94c2..6bccc24c4181 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -550,6 +550,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; + int force_pt_level; unsigned long mmu_seq; bool map_writable; @@ -577,7 +578,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, return 0; } - if (walker.level >= PT_DIRECTORY_LEVEL) { + if (walker.level >= PT_DIRECTORY_LEVEL) + force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn); + else + force_pt_level = 1; + if (!force_pt_level) { level = min(walker.level, mapping_level(vcpu, walker.gfn)); walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); } @@ -599,6 +604,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); kvm_mmu_free_some_pages(vcpu); + if (!force_pt_level) + transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, level, &write_pt, pfn, map_writable, prefault); (void)sptep; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 25bd1bc5aad2..54ce246a383e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1150,8 +1150,8 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) kvm_load_ldt(svm->host.ldt); #ifdef CONFIG_X86_64 loadsegment(fs, svm->host.fs); - load_gs_index(svm->host.gs); wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); + load_gs_index(svm->host.gs); #else loadsegment(gs, svm->host.gs); #endif diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig index 38718041efc3..6e121a2a49e1 100644 --- a/arch/x86/lguest/Kconfig +++ b/arch/x86/lguest/Kconfig @@ -2,6 +2,7 @@ config LGUEST_GUEST bool "Lguest guest support" select PARAVIRT depends on X86_32 + select VIRTUALIZATION select VIRTIO select VIRTIO_RING select VIRTIO_CONSOLE diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 4996cf5f73a0..eba687f0cc0c 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -824,7 +824,7 @@ static void __init lguest_init_IRQ(void) for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) { /* Some systems map "vectors" to interrupts weirdly. Not us! */ - __get_cpu_var(vector_irq)[i] = i - FIRST_EXTERNAL_VECTOR; + __this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR); if (i != SYSCALL_VECTOR) set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 738e6593799d..dbe34b931374 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -8,6 +8,7 @@ #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/highmem.h> +#include <linux/swap.h> #include <asm/pgtable.h> @@ -89,6 +90,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); get_page(page); + SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -103,6 +105,17 @@ static inline void get_head_page_multiple(struct page *page, int nr) VM_BUG_ON(page != compound_head(page)); VM_BUG_ON(page_count(page) == 0); atomic_add(nr, &page->_count); + SetPageReferenced(page); +} + +static inline void get_huge_page_tail(struct page *page) +{ + /* + * __split_huge_page_refcount() cannot run + * from under us. + */ + VM_BUG_ON(atomic_read(&page->_count) < 0); + atomic_inc(&page->_count); } static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, @@ -128,6 +141,8 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; + if (PageTail(page)) + get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -148,7 +163,18 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) + /* + * The pmd_trans_splitting() check below explains why + * pmdp_splitting_flush has to flush the tlb, to stop + * this gup-fast code from running while we set the + * splitting bit in the pmd. Returning zero will take + * the slow path that will call wait_split_huge_page() + * if the pmd is still in splitting state. gup-fast + * can't because it has irq disabled and + * wait_split_huge_page() would never return as the + * tlb flush IPI wouldn't run. + */ + if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; if (unlikely(pmd_large(pmd))) { if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 787c52ca49c3..ebf6d7887a38 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -2,6 +2,28 @@ #include <linux/topology.h> #include <linux/module.h> #include <linux/bootmem.h> +#include <asm/numa.h> +#include <asm/acpi.h> + +int __initdata numa_off; + +static __init int numa_setup(char *opt) +{ + if (!opt) + return -EINVAL; + if (!strncmp(opt, "off", 3)) + numa_off = 1; +#ifdef CONFIG_NUMA_EMU + if (!strncmp(opt, "fake=", 5)) + numa_emu_cmdline(opt + 5); +#endif +#ifdef CONFIG_ACPI_NUMA + if (!strncmp(opt, "noacpi", 6)) + acpi_numa = -1; +#endif + return 0; +} +early_param("numa", numa_setup); /* * Which logical CPUs are on which nodes diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 1e72102e80c9..95ea1551eebc 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -30,7 +30,6 @@ s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; -int numa_off __initdata; static unsigned long __initdata nodemap_addr; static unsigned long __initdata nodemap_size; @@ -263,6 +262,11 @@ static struct bootnode nodes[MAX_NUMNODES] __initdata; static struct bootnode physnodes[MAX_NUMNODES] __cpuinitdata; static char *cmdline __initdata; +void __init numa_emu_cmdline(char *str) +{ + cmdline = str; +} + static int __init setup_physnodes(unsigned long start, unsigned long end, int acpi, int amd) { @@ -670,24 +674,6 @@ unsigned long __init numa_free_all_bootmem(void) return pages; } -static __init int numa_setup(char *opt) -{ - if (!opt) - return -EINVAL; - if (!strncmp(opt, "off", 3)) - numa_off = 1; -#ifdef CONFIG_NUMA_EMU - if (!strncmp(opt, "fake=", 5)) - cmdline = opt + 5; -#endif -#ifdef CONFIG_ACPI_NUMA - if (!strncmp(opt, "noacpi", 6)) - acpi_numa = -1; -#endif - return 0; -} -early_param("numa", numa_setup); - #ifdef CONFIG_NUMA static __init int find_near_online_node(int node) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 8b830ca14ac4..d343b3c81f3c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -256,7 +256,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, unsigned long pfn) { pgprot_t forbidden = __pgprot(0); - pgprot_t required = __pgprot(0); /* * The BIOS area between 640k and 1Mb needs to be executable for @@ -282,12 +281,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT, __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; - /* - * .data and .bss should always be writable. - */ - if (within(address, (unsigned long)_sdata, (unsigned long)_edata) || - within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop)) - pgprot_val(required) |= _PAGE_RW; #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) /* @@ -327,7 +320,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, #endif prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); - prot = __pgprot(pgprot_val(prot) | pgprot_val(required)); return prot; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 8be8c7d7bc89..500242d3c96d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -320,6 +320,25 @@ int ptep_set_access_flags(struct vm_area_struct *vma, return changed; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + int changed = !pmd_same(*pmdp, entry); + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + if (changed && dirty) { + *pmdp = entry; + pmd_update_defer(vma->vm_mm, address, pmdp); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + } + + return changed; +} +#endif + int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { @@ -335,6 +354,23 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma, return ret; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + int ret = 0; + + if (pmd_young(*pmdp)) + ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, + (unsigned long *)pmdp); + + if (ret) + pmd_update(vma->vm_mm, addr, pmdp); + + return ret; +} +#endif + int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { @@ -347,6 +383,36 @@ int ptep_clear_flush_young(struct vm_area_struct *vma, return young; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + int young; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + young = pmdp_test_and_clear_young(vma, address, pmdp); + if (young) + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + return young; +} + +void pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + int set; + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + set = !test_and_set_bit(_PAGE_BIT_SPLITTING, + (unsigned long *)pmdp); + if (set) { + pmd_update(vma->vm_mm, address, pmdp); + /* need tlb flush only to serialize against gup-fast */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + } +} +#endif + /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index f16434568a51..ae96e7b8051d 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -59,7 +59,6 @@ static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS]; static int __initdata num_memory_chunks; /* total number of memory chunks */ static u8 __initdata apicid_to_pxm[MAX_APICID]; -int numa_off __initdata; int acpi_numa __initdata; static __init void bad_srat(void) diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c index 0846a5bbbfbd..ab8269b0da29 100644 --- a/arch/x86/pci/broadcom_bus.c +++ b/arch/x86/pci/broadcom_bus.c @@ -9,6 +9,7 @@ * option) any later version. */ +#include <linux/acpi.h> #include <linux/delay.h> #include <linux/dmi.h> #include <linux/pci.h> @@ -25,12 +26,14 @@ static void __devinit cnb20le_res(struct pci_dev *dev) u8 fbus, lbus; int i; +#ifdef CONFIG_ACPI /* - * The x86_pci_root_bus_res_quirks() function already refuses to use - * this information if ACPI _CRS was used. Therefore, we don't bother - * checking if ACPI is enabled, and just generate the information - * for both the ACPI _CRS and no ACPI cases. + * We should get host bridge information from ACPI unless the BIOS + * doesn't support it. */ + if (acpi_os_get_root_pointer()) + return; +#endif info = &pci_root_info[pci_root_num]; pci_root_num++; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index f7c8a399978c..5fe75026ecc2 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -22,6 +22,7 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | unsigned int pci_early_dump_regs; static int pci_bf_sort; +static int smbios_type_b1_flag; int pci_routeirq; int noioapicquirk; #ifdef CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS @@ -185,6 +186,39 @@ static int __devinit set_bf_sort(const struct dmi_system_id *d) return 0; } +static void __devinit read_dmi_type_b1(const struct dmi_header *dm, + void *private_data) +{ + u8 *d = (u8 *)dm + 4; + + if (dm->type != 0xB1) + return; + switch (((*(u32 *)d) >> 9) & 0x03) { + case 0x00: + printk(KERN_INFO "dmi type 0xB1 record - unknown flag\n"); + break; + case 0x01: /* set pci=bfsort */ + smbios_type_b1_flag = 1; + break; + case 0x02: /* do not set pci=bfsort */ + smbios_type_b1_flag = 2; + break; + default: + break; + } +} + +static int __devinit find_sort_method(const struct dmi_system_id *d) +{ + dmi_walk(read_dmi_type_b1, NULL); + + if (smbios_type_b1_flag == 1) { + set_bf_sort(d); + return 0; + } + return -1; +} + /* * Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus) */ @@ -213,6 +247,13 @@ static const struct dmi_system_id __devinitconst pciprobe_dmi_table[] = { }, #endif /* __i386__ */ { + .callback = find_sort_method, + .ident = "Dell System", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + }, + }, + { .callback = set_bf_sort, .ident = "Dell PowerEdge 1950", .matches = { diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 9f9bfb705cf9..87e6c8323117 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -589,7 +589,8 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH10_1: case PCI_DEVICE_ID_INTEL_ICH10_2: case PCI_DEVICE_ID_INTEL_ICH10_3: - case PCI_DEVICE_ID_INTEL_PATSBURG_LPC: + case PCI_DEVICE_ID_INTEL_PATSBURG_LPC_0: + case PCI_DEVICE_ID_INTEL_PATSBURG_LPC_1: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/x86/platform/olpc/olpc-xo1.c b/arch/x86/platform/olpc/olpc-xo1.c index f5442c03abc3..127775696d6c 100644 --- a/arch/x86/platform/olpc/olpc-xo1.c +++ b/arch/x86/platform/olpc/olpc-xo1.c @@ -1,6 +1,7 @@ /* * Support for features of the OLPC XO-1 laptop * + * Copyright (C) 2010 Andres Salomon <dilinger@queued.net> * Copyright (C) 2010 One Laptop per Child * Copyright (C) 2006 Red Hat, Inc. * Copyright (C) 2006 Advanced Micro Devices, Inc. @@ -12,8 +13,6 @@ */ #include <linux/module.h> -#include <linux/pci.h> -#include <linux/pci_ids.h> #include <linux/platform_device.h> #include <linux/pm.h> @@ -22,9 +21,6 @@ #define DRV_NAME "olpc-xo1" -#define PMS_BAR 4 -#define ACPI_BAR 5 - /* PMC registers (PMS block) */ #define PM_SCLK 0x10 #define PM_IN_SLPCTL 0x20 @@ -57,65 +53,67 @@ static void xo1_power_off(void) outl(0x00002000, acpi_base + PM1_CNT); } -/* Read the base addresses from the PCI BAR info */ -static int __devinit setup_bases(struct pci_dev *pdev) +static int __devinit olpc_xo1_probe(struct platform_device *pdev) { - int r; + struct resource *res; - r = pci_enable_device_io(pdev); - if (r) { - dev_err(&pdev->dev, "can't enable device IO\n"); - return r; - } + /* don't run on non-XOs */ + if (!machine_is_olpc()) + return -ENODEV; - r = pci_request_region(pdev, ACPI_BAR, DRV_NAME); - if (r) { - dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", ACPI_BAR); - return r; + res = platform_get_resource(pdev, IORESOURCE_IO, 0); + if (!res) { + dev_err(&pdev->dev, "can't fetch device resource info\n"); + return -EIO; } - r = pci_request_region(pdev, PMS_BAR, DRV_NAME); - if (r) { - dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", PMS_BAR); - pci_release_region(pdev, ACPI_BAR); - return r; + if (!request_region(res->start, resource_size(res), DRV_NAME)) { + dev_err(&pdev->dev, "can't request region\n"); + return -EIO; } - acpi_base = pci_resource_start(pdev, ACPI_BAR); - pms_base = pci_resource_start(pdev, PMS_BAR); + if (strcmp(pdev->name, "cs5535-pms") == 0) + pms_base = res->start; + else if (strcmp(pdev->name, "cs5535-acpi") == 0) + acpi_base = res->start; + + /* If we have both addresses, we can override the poweroff hook */ + if (pms_base && acpi_base) { + pm_power_off = xo1_power_off; + printk(KERN_INFO "OLPC XO-1 support registered\n"); + } return 0; } -static int __devinit olpc_xo1_probe(struct platform_device *pdev) +static int __devexit olpc_xo1_remove(struct platform_device *pdev) { - struct pci_dev *pcidev; - int r; - - pcidev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, - NULL); - if (!pdev) - return -ENODEV; - - r = setup_bases(pcidev); - if (r) - return r; + struct resource *r; - pm_power_off = xo1_power_off; + r = platform_get_resource(pdev, IORESOURCE_IO, 0); + release_region(r->start, resource_size(r)); - printk(KERN_INFO "OLPC XO-1 support registered\n"); - return 0; -} + if (strcmp(pdev->name, "cs5535-pms") == 0) + pms_base = 0; + else if (strcmp(pdev->name, "cs5535-acpi") == 0) + acpi_base = 0; -static int __devexit olpc_xo1_remove(struct platform_device *pdev) -{ pm_power_off = NULL; return 0; } -static struct platform_driver olpc_xo1_driver = { +static struct platform_driver cs5535_pms_drv = { + .driver = { + .name = "cs5535-pms", + .owner = THIS_MODULE, + }, + .probe = olpc_xo1_probe, + .remove = __devexit_p(olpc_xo1_remove), +}; + +static struct platform_driver cs5535_acpi_drv = { .driver = { - .name = DRV_NAME, + .name = "cs5535-acpi", .owner = THIS_MODULE, }, .probe = olpc_xo1_probe, @@ -124,12 +122,23 @@ static struct platform_driver olpc_xo1_driver = { static int __init olpc_xo1_init(void) { - return platform_driver_register(&olpc_xo1_driver); + int r; + + r = platform_driver_register(&cs5535_pms_drv); + if (r) + return r; + + r = platform_driver_register(&cs5535_acpi_drv); + if (r) + platform_driver_unregister(&cs5535_pms_drv); + + return r; } static void __exit olpc_xo1_exit(void) { - platform_driver_unregister(&olpc_xo1_driver); + platform_driver_unregister(&cs5535_acpi_drv); + platform_driver_unregister(&cs5535_pms_drv); } MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>"); diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 779385158915..17c565de3d64 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -12,7 +12,8 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ - grant-table.o suspend.o platform-pci-unplug.o + grant-table.o suspend.o platform-pci-unplug.o \ + p2m.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 7e8d3bc80af6..50542efe45fb 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1194,7 +1194,7 @@ asmlinkage void __init xen_start_kernel(void) per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; local_irq_disable(); - early_boot_irqs_off(); + early_boot_irqs_disabled = true; memblock_init(); diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 9d30105a0c4a..6a6fe8939645 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -126,7 +126,7 @@ static const struct pv_irq_ops xen_irq_ops __initdata = { #endif }; -void __init xen_init_irq_ops() +void __init xen_init_irq_ops(void) { pv_irq_ops = xen_irq_ops; x86_init.irqs.intr_init = xen_init_IRQ; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 44924e551fde..5e92b61ad574 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -173,371 +173,6 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ */ #define USER_LIMIT ((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK) -/* - * Xen leaves the responsibility for maintaining p2m mappings to the - * guests themselves, but it must also access and update the p2m array - * during suspend/resume when all the pages are reallocated. - * - * The p2m table is logically a flat array, but we implement it as a - * three-level tree to allow the address space to be sparse. - * - * Xen - * | - * p2m_top p2m_top_mfn - * / \ / \ - * p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn - * / \ / \ / / - * p2m p2m p2m p2m p2m p2m p2m ... - * - * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p. - * - * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the - * maximum representable pseudo-physical address space is: - * P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages - * - * P2M_PER_PAGE depends on the architecture, as a mfn is always - * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to - * 512 and 1024 entries respectively. - */ - -unsigned long xen_max_p2m_pfn __read_mostly; - -#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) -#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) -#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) - -#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) - -/* Placeholders for holes in the address space */ -static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE); -static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE); -static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE); - -static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE); -static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE); -static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE); - -RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); -RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); - -static inline unsigned p2m_top_index(unsigned long pfn) -{ - BUG_ON(pfn >= MAX_P2M_PFN); - return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE); -} - -static inline unsigned p2m_mid_index(unsigned long pfn) -{ - return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; -} - -static inline unsigned p2m_index(unsigned long pfn) -{ - return pfn % P2M_PER_PAGE; -} - -static void p2m_top_init(unsigned long ***top) -{ - unsigned i; - - for (i = 0; i < P2M_TOP_PER_PAGE; i++) - top[i] = p2m_mid_missing; -} - -static void p2m_top_mfn_init(unsigned long *top) -{ - unsigned i; - - for (i = 0; i < P2M_TOP_PER_PAGE; i++) - top[i] = virt_to_mfn(p2m_mid_missing_mfn); -} - -static void p2m_top_mfn_p_init(unsigned long **top) -{ - unsigned i; - - for (i = 0; i < P2M_TOP_PER_PAGE; i++) - top[i] = p2m_mid_missing_mfn; -} - -static void p2m_mid_init(unsigned long **mid) -{ - unsigned i; - - for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = p2m_missing; -} - -static void p2m_mid_mfn_init(unsigned long *mid) -{ - unsigned i; - - for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = virt_to_mfn(p2m_missing); -} - -static void p2m_init(unsigned long *p2m) -{ - unsigned i; - - for (i = 0; i < P2M_MID_PER_PAGE; i++) - p2m[i] = INVALID_P2M_ENTRY; -} - -/* - * Build the parallel p2m_top_mfn and p2m_mid_mfn structures - * - * This is called both at boot time, and after resuming from suspend: - * - At boot time we're called very early, and must use extend_brk() - * to allocate memory. - * - * - After resume we're called from within stop_machine, but the mfn - * tree should alreay be completely allocated. - */ -void xen_build_mfn_list_list(void) -{ - unsigned long pfn; - - /* Pre-initialize p2m_top_mfn to be completely missing */ - if (p2m_top_mfn == NULL) { - p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(p2m_mid_missing_mfn); - - p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_top_mfn_p_init(p2m_top_mfn_p); - - p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_top_mfn_init(p2m_top_mfn); - } else { - /* Reinitialise, mfn's all change after migration */ - p2m_mid_mfn_init(p2m_mid_missing_mfn); - } - - for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) { - unsigned topidx = p2m_top_index(pfn); - unsigned mididx = p2m_mid_index(pfn); - unsigned long **mid; - unsigned long *mid_mfn_p; - - mid = p2m_top[topidx]; - mid_mfn_p = p2m_top_mfn_p[topidx]; - - /* Don't bother allocating any mfn mid levels if - * they're just missing, just update the stored mfn, - * since all could have changed over a migrate. - */ - if (mid == p2m_mid_missing) { - BUG_ON(mididx); - BUG_ON(mid_mfn_p != p2m_mid_missing_mfn); - p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn); - pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE; - continue; - } - - if (mid_mfn_p == p2m_mid_missing_mfn) { - /* - * XXX boot-time only! We should never find - * missing parts of the mfn tree after - * runtime. extend_brk() will BUG if we call - * it too late. - */ - mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(mid_mfn_p); - - p2m_top_mfn_p[topidx] = mid_mfn_p; - } - - p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p); - mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]); - } -} - -void xen_setup_mfn_list_list(void) -{ - BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - - HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = - virt_to_mfn(p2m_top_mfn); - HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn; -} - -/* Set up p2m_top to point to the domain-builder provided p2m pages */ -void __init xen_build_dynamic_phys_to_machine(void) -{ - unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list; - unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages); - unsigned long pfn; - - xen_max_p2m_pfn = max_pfn; - - p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_init(p2m_missing); - - p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(p2m_mid_missing); - - p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_top_init(p2m_top); - - /* - * The domain builder gives us a pre-constructed p2m array in - * mfn_list for all the pages initially given to us, so we just - * need to graft that into our tree structure. - */ - for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) { - unsigned topidx = p2m_top_index(pfn); - unsigned mididx = p2m_mid_index(pfn); - - if (p2m_top[topidx] == p2m_mid_missing) { - unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(mid); - - p2m_top[topidx] = mid; - } - - p2m_top[topidx][mididx] = &mfn_list[pfn]; - } -} - -unsigned long get_phys_to_machine(unsigned long pfn) -{ - unsigned topidx, mididx, idx; - - if (unlikely(pfn >= MAX_P2M_PFN)) - return INVALID_P2M_ENTRY; - - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); - idx = p2m_index(pfn); - - return p2m_top[topidx][mididx][idx]; -} -EXPORT_SYMBOL_GPL(get_phys_to_machine); - -static void *alloc_p2m_page(void) -{ - return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); -} - -static void free_p2m_page(void *p) -{ - free_page((unsigned long)p); -} - -/* - * Fully allocate the p2m structure for a given pfn. We need to check - * that both the top and mid levels are allocated, and make sure the - * parallel mfn tree is kept in sync. We may race with other cpus, so - * the new pages are installed with cmpxchg; if we lose the race then - * simply free the page we allocated and use the one that's there. - */ -static bool alloc_p2m(unsigned long pfn) -{ - unsigned topidx, mididx; - unsigned long ***top_p, **mid; - unsigned long *top_mfn_p, *mid_mfn; - - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); - - top_p = &p2m_top[topidx]; - mid = *top_p; - - if (mid == p2m_mid_missing) { - /* Mid level is missing, allocate a new one */ - mid = alloc_p2m_page(); - if (!mid) - return false; - - p2m_mid_init(mid); - - if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing) - free_p2m_page(mid); - } - - top_mfn_p = &p2m_top_mfn[topidx]; - mid_mfn = p2m_top_mfn_p[topidx]; - - BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); - - if (mid_mfn == p2m_mid_missing_mfn) { - /* Separately check the mid mfn level */ - unsigned long missing_mfn; - unsigned long mid_mfn_mfn; - - mid_mfn = alloc_p2m_page(); - if (!mid_mfn) - return false; - - p2m_mid_mfn_init(mid_mfn); - - missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); - mid_mfn_mfn = virt_to_mfn(mid_mfn); - if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn) - free_p2m_page(mid_mfn); - else - p2m_top_mfn_p[topidx] = mid_mfn; - } - - if (p2m_top[topidx][mididx] == p2m_missing) { - /* p2m leaf page is missing */ - unsigned long *p2m; - - p2m = alloc_p2m_page(); - if (!p2m) - return false; - - p2m_init(p2m); - - if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing) - free_p2m_page(p2m); - else - mid_mfn[mididx] = virt_to_mfn(p2m); - } - - return true; -} - -/* Try to install p2m mapping; fail if intermediate bits missing */ -bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - unsigned topidx, mididx, idx; - - if (unlikely(pfn >= MAX_P2M_PFN)) { - BUG_ON(mfn != INVALID_P2M_ENTRY); - return true; - } - - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); - idx = p2m_index(pfn); - - if (p2m_top[topidx][mididx] == p2m_missing) - return mfn == INVALID_P2M_ENTRY; - - p2m_top[topidx][mididx][idx] = mfn; - - return true; -} - -bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return true; - } - - if (unlikely(!__set_phys_to_machine(pfn, mfn))) { - if (!alloc_p2m(pfn)) - return false; - - if (!__set_phys_to_machine(pfn, mfn)) - return false; - } - - return true; -} - unsigned long arbitrary_virt_to_mfn(void *vaddr) { xmaddr_t maddr = arbitrary_virt_to_machine(vaddr); @@ -566,6 +201,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) offset = address & ~PAGE_MASK; return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset); } +EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); void make_lowmem_page_readonly(void *vaddr) { diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c new file mode 100644 index 000000000000..fd12d7ce7ff9 --- /dev/null +++ b/arch/x86/xen/p2m.c @@ -0,0 +1,522 @@ +/* + * Xen leaves the responsibility for maintaining p2m mappings to the + * guests themselves, but it must also access and update the p2m array + * during suspend/resume when all the pages are reallocated. + * + * The p2m table is logically a flat array, but we implement it as a + * three-level tree to allow the address space to be sparse. + * + * Xen + * | + * p2m_top p2m_top_mfn + * / \ / \ + * p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn + * / \ / \ / / + * p2m p2m p2m p2m p2m p2m p2m ... + * + * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p. + * + * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the + * maximum representable pseudo-physical address space is: + * P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages + * + * P2M_PER_PAGE depends on the architecture, as a mfn is always + * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to + * 512 and 1024 entries respectively. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/sched.h> + +#include <asm/cache.h> +#include <asm/setup.h> + +#include <asm/xen/page.h> +#include <asm/xen/hypercall.h> +#include <asm/xen/hypervisor.h> + +#include "xen-ops.h" + +static void __init m2p_override_init(void); + +unsigned long xen_max_p2m_pfn __read_mostly; + +#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) +#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) +#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) + +#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) + +/* Placeholders for holes in the address space */ +static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE); + +static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE); + +RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); +RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); + +static inline unsigned p2m_top_index(unsigned long pfn) +{ + BUG_ON(pfn >= MAX_P2M_PFN); + return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE); +} + +static inline unsigned p2m_mid_index(unsigned long pfn) +{ + return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; +} + +static inline unsigned p2m_index(unsigned long pfn) +{ + return pfn % P2M_PER_PAGE; +} + +static void p2m_top_init(unsigned long ***top) +{ + unsigned i; + + for (i = 0; i < P2M_TOP_PER_PAGE; i++) + top[i] = p2m_mid_missing; +} + +static void p2m_top_mfn_init(unsigned long *top) +{ + unsigned i; + + for (i = 0; i < P2M_TOP_PER_PAGE; i++) + top[i] = virt_to_mfn(p2m_mid_missing_mfn); +} + +static void p2m_top_mfn_p_init(unsigned long **top) +{ + unsigned i; + + for (i = 0; i < P2M_TOP_PER_PAGE; i++) + top[i] = p2m_mid_missing_mfn; +} + +static void p2m_mid_init(unsigned long **mid) +{ + unsigned i; + + for (i = 0; i < P2M_MID_PER_PAGE; i++) + mid[i] = p2m_missing; +} + +static void p2m_mid_mfn_init(unsigned long *mid) +{ + unsigned i; + + for (i = 0; i < P2M_MID_PER_PAGE; i++) + mid[i] = virt_to_mfn(p2m_missing); +} + +static void p2m_init(unsigned long *p2m) +{ + unsigned i; + + for (i = 0; i < P2M_MID_PER_PAGE; i++) + p2m[i] = INVALID_P2M_ENTRY; +} + +/* + * Build the parallel p2m_top_mfn and p2m_mid_mfn structures + * + * This is called both at boot time, and after resuming from suspend: + * - At boot time we're called very early, and must use extend_brk() + * to allocate memory. + * + * - After resume we're called from within stop_machine, but the mfn + * tree should alreay be completely allocated. + */ +void xen_build_mfn_list_list(void) +{ + unsigned long pfn; + + /* Pre-initialize p2m_top_mfn to be completely missing */ + if (p2m_top_mfn == NULL) { + p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_mfn_init(p2m_mid_missing_mfn); + + p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_top_mfn_p_init(p2m_top_mfn_p); + + p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_top_mfn_init(p2m_top_mfn); + } else { + /* Reinitialise, mfn's all change after migration */ + p2m_mid_mfn_init(p2m_mid_missing_mfn); + } + + for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx = p2m_mid_index(pfn); + unsigned long **mid; + unsigned long *mid_mfn_p; + + mid = p2m_top[topidx]; + mid_mfn_p = p2m_top_mfn_p[topidx]; + + /* Don't bother allocating any mfn mid levels if + * they're just missing, just update the stored mfn, + * since all could have changed over a migrate. + */ + if (mid == p2m_mid_missing) { + BUG_ON(mididx); + BUG_ON(mid_mfn_p != p2m_mid_missing_mfn); + p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn); + pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE; + continue; + } + + if (mid_mfn_p == p2m_mid_missing_mfn) { + /* + * XXX boot-time only! We should never find + * missing parts of the mfn tree after + * runtime. extend_brk() will BUG if we call + * it too late. + */ + mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_mfn_init(mid_mfn_p); + + p2m_top_mfn_p[topidx] = mid_mfn_p; + } + + p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p); + mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]); + } +} + +void xen_setup_mfn_list_list(void) +{ + BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); + + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(p2m_top_mfn); + HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn; +} + +/* Set up p2m_top to point to the domain-builder provided p2m pages */ +void __init xen_build_dynamic_phys_to_machine(void) +{ + unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list; + unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages); + unsigned long pfn; + + xen_max_p2m_pfn = max_pfn; + + p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_init(p2m_missing); + + p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_init(p2m_mid_missing); + + p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_top_init(p2m_top); + + /* + * The domain builder gives us a pre-constructed p2m array in + * mfn_list for all the pages initially given to us, so we just + * need to graft that into our tree structure. + */ + for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx = p2m_mid_index(pfn); + + if (p2m_top[topidx] == p2m_mid_missing) { + unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_init(mid); + + p2m_top[topidx] = mid; + } + + /* + * As long as the mfn_list has enough entries to completely + * fill a p2m page, pointing into the array is ok. But if + * not the entries beyond the last pfn will be undefined. + */ + if (unlikely(pfn + P2M_PER_PAGE > max_pfn)) { + unsigned long p2midx; + + p2midx = max_pfn % P2M_PER_PAGE; + for ( ; p2midx < P2M_PER_PAGE; p2midx++) + mfn_list[pfn + p2midx] = INVALID_P2M_ENTRY; + } + p2m_top[topidx][mididx] = &mfn_list[pfn]; + } + + m2p_override_init(); +} + +unsigned long get_phys_to_machine(unsigned long pfn) +{ + unsigned topidx, mididx, idx; + + if (unlikely(pfn >= MAX_P2M_PFN)) + return INVALID_P2M_ENTRY; + + topidx = p2m_top_index(pfn); + mididx = p2m_mid_index(pfn); + idx = p2m_index(pfn); + + return p2m_top[topidx][mididx][idx]; +} +EXPORT_SYMBOL_GPL(get_phys_to_machine); + +static void *alloc_p2m_page(void) +{ + return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); +} + +static void free_p2m_page(void *p) +{ + free_page((unsigned long)p); +} + +/* + * Fully allocate the p2m structure for a given pfn. We need to check + * that both the top and mid levels are allocated, and make sure the + * parallel mfn tree is kept in sync. We may race with other cpus, so + * the new pages are installed with cmpxchg; if we lose the race then + * simply free the page we allocated and use the one that's there. + */ +static bool alloc_p2m(unsigned long pfn) +{ + unsigned topidx, mididx; + unsigned long ***top_p, **mid; + unsigned long *top_mfn_p, *mid_mfn; + + topidx = p2m_top_index(pfn); + mididx = p2m_mid_index(pfn); + + top_p = &p2m_top[topidx]; + mid = *top_p; + + if (mid == p2m_mid_missing) { + /* Mid level is missing, allocate a new one */ + mid = alloc_p2m_page(); + if (!mid) + return false; + + p2m_mid_init(mid); + + if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing) + free_p2m_page(mid); + } + + top_mfn_p = &p2m_top_mfn[topidx]; + mid_mfn = p2m_top_mfn_p[topidx]; + + BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); + + if (mid_mfn == p2m_mid_missing_mfn) { + /* Separately check the mid mfn level */ + unsigned long missing_mfn; + unsigned long mid_mfn_mfn; + + mid_mfn = alloc_p2m_page(); + if (!mid_mfn) + return false; + + p2m_mid_mfn_init(mid_mfn); + + missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); + mid_mfn_mfn = virt_to_mfn(mid_mfn); + if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn) + free_p2m_page(mid_mfn); + else + p2m_top_mfn_p[topidx] = mid_mfn; + } + + if (p2m_top[topidx][mididx] == p2m_missing) { + /* p2m leaf page is missing */ + unsigned long *p2m; + + p2m = alloc_p2m_page(); + if (!p2m) + return false; + + p2m_init(p2m); + + if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing) + free_p2m_page(p2m); + else + mid_mfn[mididx] = virt_to_mfn(p2m); + } + + return true; +} + +/* Try to install p2m mapping; fail if intermediate bits missing */ +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, mididx, idx; + + if (unlikely(pfn >= MAX_P2M_PFN)) { + BUG_ON(mfn != INVALID_P2M_ENTRY); + return true; + } + + topidx = p2m_top_index(pfn); + mididx = p2m_mid_index(pfn); + idx = p2m_index(pfn); + + if (p2m_top[topidx][mididx] == p2m_missing) + return mfn == INVALID_P2M_ENTRY; + + p2m_top[topidx][mididx][idx] = mfn; + + return true; +} + +bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return true; + } + + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + if (!alloc_p2m(pfn)) + return false; + + if (!__set_phys_to_machine(pfn, mfn)) + return false; + } + + return true; +} + +#define M2P_OVERRIDE_HASH_SHIFT 10 +#define M2P_OVERRIDE_HASH (1 << M2P_OVERRIDE_HASH_SHIFT) + +static RESERVE_BRK_ARRAY(struct list_head, m2p_overrides, M2P_OVERRIDE_HASH); +static DEFINE_SPINLOCK(m2p_override_lock); + +static void __init m2p_override_init(void) +{ + unsigned i; + + m2p_overrides = extend_brk(sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH, + sizeof(unsigned long)); + + for (i = 0; i < M2P_OVERRIDE_HASH; i++) + INIT_LIST_HEAD(&m2p_overrides[i]); +} + +static unsigned long mfn_hash(unsigned long mfn) +{ + return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT); +} + +/* Add an MFN override for a particular page */ +int m2p_add_override(unsigned long mfn, struct page *page) +{ + unsigned long flags; + unsigned long pfn; + unsigned long address; + unsigned level; + pte_t *ptep = NULL; + + pfn = page_to_pfn(page); + if (!PageHighMem(page)) { + address = (unsigned long)__va(pfn << PAGE_SHIFT); + ptep = lookup_address(address, &level); + + if (WARN(ptep == NULL || level != PG_LEVEL_4K, + "m2p_add_override: pfn %lx not mapped", pfn)) + return -EINVAL; + } + + page->private = mfn; + page->index = pfn_to_mfn(pfn); + + __set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); + if (!PageHighMem(page)) + /* Just zap old mapping for now */ + pte_clear(&init_mm, address, ptep); + + spin_lock_irqsave(&m2p_override_lock, flags); + list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); + spin_unlock_irqrestore(&m2p_override_lock, flags); + + return 0; +} + +int m2p_remove_override(struct page *page) +{ + unsigned long flags; + unsigned long mfn; + unsigned long pfn; + unsigned long address; + unsigned level; + pte_t *ptep = NULL; + + pfn = page_to_pfn(page); + mfn = get_phys_to_machine(pfn); + if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) + return -EINVAL; + + if (!PageHighMem(page)) { + address = (unsigned long)__va(pfn << PAGE_SHIFT); + ptep = lookup_address(address, &level); + + if (WARN(ptep == NULL || level != PG_LEVEL_4K, + "m2p_remove_override: pfn %lx not mapped", pfn)) + return -EINVAL; + } + + spin_lock_irqsave(&m2p_override_lock, flags); + list_del(&page->lru); + spin_unlock_irqrestore(&m2p_override_lock, flags); + __set_phys_to_machine(pfn, page->index); + + if (!PageHighMem(page)) + set_pte_at(&init_mm, address, ptep, + pfn_pte(pfn, PAGE_KERNEL)); + /* No tlb flush necessary because the caller already + * left the pte unmapped. */ + + return 0; +} + +struct page *m2p_find_override(unsigned long mfn) +{ + unsigned long flags; + struct list_head *bucket = &m2p_overrides[mfn_hash(mfn)]; + struct page *p, *ret; + + ret = NULL; + + spin_lock_irqsave(&m2p_override_lock, flags); + + list_for_each_entry(p, bucket, lru) { + if (p->private == mfn) { + ret = p; + break; + } + } + + spin_unlock_irqrestore(&m2p_override_lock, flags); + + return ret; +} + +unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) +{ + struct page *p = m2p_find_override(mfn); + unsigned long ret = pfn; + + if (p) + ret = page_to_pfn(p); + + return ret; +} +EXPORT_SYMBOL_GPL(m2p_find_override_pfn); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index b5a7f928234b..a8a66a50d446 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -179,8 +179,13 @@ char * __init xen_memory_setup(void) e820.nr_map = 0; xen_extra_mem_start = mem_end; for (i = 0; i < memmap.nr_entries; i++) { - unsigned long long end = map[i].addr + map[i].size; + unsigned long long end; + /* Guard against non-page aligned E820 entries. */ + if (map[i].type == E820_RAM) + map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE; + + end = map[i].addr + map[i].size; if (map[i].type == E820_RAM && end > mem_end) { /* RAM off the end - may be partially included */ u64 delta = min(map[i].size, end - mem_end); @@ -350,6 +355,7 @@ void __init xen_arch_setup(void) boot_cpu_data.hlt_works_ok = 1; #endif pm_idle = default_idle; + boot_option_idle_override = IDLE_HALT; fiddle_vdso(); } |