diff options
Diffstat (limited to 'arch/x86')
97 files changed, 921 insertions, 625 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bc25b9f5e4c..a6efe0a2e9a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -277,6 +277,7 @@ config SPARSE_IRQ config NUMA_MIGRATE_IRQ_DESC bool "Move irq desc when changing irq smp_affinity" depends on SPARSE_IRQ && NUMA + depends on BROKEN default n ---help--- This enables moving irq_desc to cpu/node that irq will use handled. @@ -353,6 +354,7 @@ config X86_UV bool "SGI Ultraviolet" depends on X86_64 depends on X86_EXTENDED_PLATFORM + depends on NUMA select X86_X2APIC ---help--- This option is needed in order to support SGI Ultraviolet systems. @@ -496,6 +498,19 @@ config PARAVIRT over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_SPINLOCKS + bool "Paravirtualization layer for spinlocks" + depends on PARAVIRT && SMP && EXPERIMENTAL + ---help--- + Paravirtualized spinlocks allow a pvops backend to replace the + spinlock implementation with something virtualization-friendly + (for example, block the virtual CPU rather than spinning). + + Unfortunately the downside is an up to 5% performance hit on + native kernels, with various workloads. + + If you are unsure how to answer this question, answer N. + config PARAVIRT_CLOCK bool default n @@ -663,6 +678,7 @@ config MAXSMP config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP + range 2 8 if SMP && X86_32 && !X86_BIGSMP range 2 512 if SMP && !MAXSMP default "1" if !SMP default "4096" if MAXSMP diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 924e156a85a..8130334329c 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -506,6 +506,7 @@ config X86_PTRACE_BTS bool "Branch Trace Store" default y depends on X86_DEBUGCTLMSR + depends on BROKEN ---help--- This adds a ptrace interface to the hardware's branch trace store. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index f05d8c91d9e..8c86b72afdc 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -153,7 +153,7 @@ endif boot := arch/x86/boot -BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage install +BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage PHONY += bzImage $(BOOT_TARGETS) @@ -171,6 +171,10 @@ bzImage: vmlinux $(BOOT_TARGETS): vmlinux $(Q)$(MAKE) $(build)=$(boot) $@ +PHONY += install +install: + $(Q)$(MAKE) $(build)=$(boot) $@ + PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/x86/vdso $@ diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index 857e492c571..bbeb0c3fbd9 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -504,8 +504,11 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) if (sym->st_shndx == SHN_ABS) { continue; } - if (r_type == R_386_PC32) { - /* PC relative relocations don't need to be adjusted */ + if (r_type == R_386_NONE || r_type == R_386_PC32) { + /* + * NONE can be ignored and and PC relative + * relocations don't need to be adjusted. + */ } else if (r_type == R_386_32) { /* Visit relocations that need to be adjusted */ diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 5054c2ddd1a..74b3d2ba84e 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -17,11 +17,6 @@ #define SMAP 0x534d4150 /* ASCII "SMAP" */ -struct e820_ext_entry { - struct e820entry std; - u32 ext_flags; -} __attribute__((packed)); - static int detect_memory_e820(void) { int count = 0; @@ -29,13 +24,21 @@ static int detect_memory_e820(void) u32 size, id, edi; u8 err; struct e820entry *desc = boot_params.e820_map; - static struct e820_ext_entry buf; /* static so it is zeroed */ + static struct e820entry buf; /* static so it is zeroed */ /* - * Set this here so that if the BIOS doesn't change this field - * but still doesn't change %ecx, we're still okay... + * Note: at least one BIOS is known which assumes that the + * buffer pointed to by one e820 call is the same one as + * the previous call, and only changes modified fields. Therefore, + * we use a temporary buffer and copy the results entry by entry. + * + * This routine deliberately does not try to account for + * ACPI 3+ extended attributes. This is because there are + * BIOSes in the field which report zero for the valid bit for + * all ranges, and we don't currently make any use of the + * other attribute bits. Revisit this if we see the extended + * attribute bits deployed in a meaningful way in the future. */ - buf.ext_flags = 1; do { size = sizeof buf; @@ -66,13 +69,7 @@ static int detect_memory_e820(void) break; } - /* ACPI 3.0 added the extended flags support. If bit 0 - in the extended flags is zero, we're supposed to simply - ignore the entry -- a backwards incompatible change! */ - if (size > 20 && !(buf.ext_flags & 1)) - continue; - - *desc++ = buf.std; + *desc++ = buf; count++; } while (next && count < ARRAY_SIZE(boot_params.e820_map)); diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index efac92fd1ef..085a8c35f14 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -129,21 +129,12 @@ asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename, struct stat64 __user *statbuf, int flag) { struct kstat stat; - int error = -EINVAL; + int error; - if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0) - goto out; - - if (flag & AT_SYMLINK_NOFOLLOW) - error = vfs_lstat_fd(dfd, filename, &stat); - else - error = vfs_stat_fd(dfd, filename, &stat); - - if (!error) - error = cp_stat64(statbuf, &stat); - -out: - return error; + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_stat64(statbuf, &stat); } /* diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0beba0d1468..bb83b1c397a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -154,6 +154,7 @@ * CPUID levels like 0x6, 0xA etc */ #define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ /* Virtualization flags: Linux defined */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 5623c50d67b..c45f415ce31 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -37,7 +37,7 @@ extern gate_desc idt_table[]; struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); -DECLARE_PER_CPU(struct gdt_page, gdt_page); +DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) { diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 81937a5dc77..2d81af3974a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -151,11 +151,11 @@ extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); void native_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags); + phys_addr_t phys, pgprot_t flags); #ifndef CONFIG_PARAVIRT static inline void __set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { native_set_fixmap(idx, phys, flags); } diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 039db6aa8e0..37555e52f98 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -26,7 +26,7 @@ typedef struct { #endif } ____cacheline_aligned irq_cpustat_t; -DECLARE_PER_CPU(irq_cpustat_t, irq_stat); +DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); /* We can have at most NR_VECTORS irqs routed to a cpu at a time */ #define MAX_HARDIRQS_PER_CPU NR_VECTORS diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e5383e3d2f8..73739322b6d 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -193,8 +193,10 @@ extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); */ extern void early_ioremap_init(void); extern void early_ioremap_reset(void); -extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); -extern void __iomem *early_memremap(unsigned long offset, unsigned long size); +extern void __iomem *early_ioremap(resource_size_t phys_addr, + unsigned long size); +extern void __iomem *early_memremap(resource_size_t phys_addr, + unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 0f4ee7148af..faae1996487 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -5,7 +5,6 @@ #define LHCALL_FLUSH_ASYNC 0 #define LHCALL_LGUEST_INIT 1 #define LHCALL_SHUTDOWN 2 -#define LHCALL_LOAD_GDT 3 #define LHCALL_NEW_PGTABLE 4 #define LHCALL_FLUSH_TLB 5 #define LHCALL_LOAD_IDT_ENTRY 6 @@ -17,6 +16,7 @@ #define LHCALL_SET_PMD 15 #define LHCALL_LOAD_TLS 16 #define LHCALL_NOTIFY 17 +#define LHCALL_LOAD_GDT_ENTRY 18 #define LGUEST_TRAP_ENTRY 0x1F diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 563933e06a3..4f8c199584e 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -137,6 +137,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); enum mcp_flags { MCP_TIMESTAMP = (1 << 0), /* log time stamp */ MCP_UC = (1 << 1), /* log uncorrected errors */ + MCP_DONTLOG = (1 << 2), /* only clear, don't log */ }; extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7727aa8b7dd..a53da004e08 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -347,7 +347,7 @@ struct pv_mmu_ops { /* Sometimes the physical address is a pfn, and sometimes its an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, - unsigned long phys, pgprot_t flags); + phys_addr_t phys, pgprot_t flags); }; struct raw_spinlock; @@ -1432,7 +1432,7 @@ static inline void arch_leave_lazy_mmu_mode(void) void arch_flush_lazy_mmu_mode(void); static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { pv_mmu_ops.set_fixmap(idx, phys, flags); } @@ -1443,7 +1443,7 @@ u64 _paravirt_ident_64(u64); #define paravirt_nop ((void *)_paravirt_nop) -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) static inline int __raw_spin_is_locked(struct raw_spinlock *lock) { diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 2cd07b9422f..7af14e512f9 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -18,9 +18,5 @@ extern int free_memtype(u64 start, u64 end); extern int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flag); -extern void map_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); -extern void unmap_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index aee103b26d0..02ecb30982a 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -82,22 +82,22 @@ do { \ case 1: \ asm(op "b %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)val)); \ + : "qi" ((T__)(val))); \ break; \ case 2: \ asm(op "w %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)val)); \ + : "ri" ((T__)(val))); \ break; \ case 4: \ asm(op "l %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)val)); \ + : "ri" ((T__)(val))); \ break; \ case 8: \ asm(op "q %1,"__percpu_arg(0) \ : "+m" (var) \ - : "re" ((T__)val)); \ + : "re" ((T__)(val))); \ break; \ default: __bad_percpu_size(); \ } \ @@ -109,7 +109,7 @@ do { \ switch (sizeof(var)) { \ case 1: \ asm(op "b "__percpu_arg(1)",%0" \ - : "=r" (ret__) \ + : "=q" (ret__) \ : "m" (var)); \ break; \ case 2: \ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 34c52370f2f..c2cceae709c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -138,7 +138,7 @@ extern struct tss_struct doublefault_tss; extern __u32 cleared_cpu_caps[NCAPINTS]; #ifdef CONFIG_SMP -DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info); +DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) #define current_cpu_data __get_cpu_var(cpu_info) #else @@ -270,7 +270,7 @@ struct tss_struct { } ____cacheline_aligned; -DECLARE_PER_CPU(struct tss_struct, init_tss); +DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss); /* * Save the original ist values for checking stack pointers during debugging @@ -352,6 +352,11 @@ struct i387_soft_struct { u32 entry_eip; }; +struct ymmh_struct { + /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ + u32 ymmh_space[64]; +}; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -361,6 +366,7 @@ struct xsave_hdr_struct { struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; + struct ymmh_struct ymmh; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); @@ -387,7 +393,7 @@ union irq_stack_union { }; }; -DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); +DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union); DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index e304b66abee..624f133943e 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -187,14 +187,15 @@ static inline int v8086_mode(struct pt_regs *regs) /* * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode - * when it traps. So regs will be the current sp. + * when it traps. The previous stack will be directly underneath the saved + * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. * * This is valid only for kernel mode traps. */ -static inline unsigned long kernel_trap_sp(struct pt_regs *regs) +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { #ifdef CONFIG_X86_32 - return (unsigned long)regs; + return (unsigned long)(®s->sp); #else return regs->sp; #endif diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d5cd6c58688..a4737dddfd5 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -50,7 +50,7 @@ #ifdef CONFIG_X86_64 #define NEED_PSE 0 #define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) -#define NEED_PGE (1<<(X86_FEATURE_PGE & 31)) +#define NEED_PGE 0 #define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) #define NEED_XMM (1<<(X86_FEATURE_XMM & 31)) #define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31)) diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index ec666491aaa..72e5a449166 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -269,6 +269,11 @@ struct _xsave_hdr { __u64 reserved2[5]; }; +struct _ymmh_state { + /* 16 * 16 bytes for each YMMH-reg */ + __u32 ymmh_space[64]; +}; + /* * Extended state pointed by the fpstate pointer in the sigcontext. * In addition to the fpstate, information encoded in the xstate_hdr @@ -278,6 +283,7 @@ struct _xsave_hdr { struct _xstate { struct _fpstate fpstate; struct _xsave_hdr xstate_hdr; + struct _ymmh_state ymmh; /* new processor state extensions go here */ }; diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index e5e6caffec8..b7e5db87639 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -172,7 +172,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock) return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1; } -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_SPINLOCKS static inline int __raw_spin_is_locked(raw_spinlock_t *lock) { @@ -206,7 +206,7 @@ static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock, __raw_spin_lock(lock); } -#endif +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock) { diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d3539f998f8..16a5c84b032 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -152,7 +152,7 @@ struct tlb_state { struct mm_struct *active_mm; int state; }; -DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate); +DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); static inline void reset_lazy_tlbstate(void) { diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 892b119dba6..f44b49abca4 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -200,7 +200,7 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) } struct pci_bus; -void set_pci_bus_resources_arch_default(struct pci_bus *b); +void x86_pci_root_bus_res_quirks(struct pci_bus *b); #ifdef CONFIG_SMP #define mc_capable() (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids) diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index db68ac8a5ac..2cae46c7c8a 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -17,6 +17,11 @@ /* ========================================================================= */ /* UVH_BAU_DATA_CONFIG */ /* ========================================================================= */ +#define UVH_LB_BAU_MISC_CONTROL 0x320170UL +#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL +/* 1011 timebase 7 (168millisec) * 3 ticks -> 500ms */ #define UVH_BAU_DATA_CONFIG 0x61680UL #define UVH_BAU_DATA_CONFIG_32 0x0438 diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a918dde46b..018a0a40079 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -124,7 +124,8 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) static inline unsigned long pte_mfn(pte_t pte) diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 08e9a1ac07a..727acc15234 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -7,6 +7,7 @@ #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -15,7 +16,7 @@ /* * These are the features that the OS can handle currently. */ -#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE) +#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 145cce75cda..88d1bfc847d 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -89,7 +89,8 @@ obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o -obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o paravirt-spinlocks.o +obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o +obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 42c33cebf00..8c0be0902da 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -49,10 +49,10 @@ #define IVHD_DEV_EXT_SELECT 0x46 #define IVHD_DEV_EXT_SELECT_RANGE 0x47 -#define IVHD_FLAG_HT_TUN_EN 0x00 -#define IVHD_FLAG_PASSPW_EN 0x01 -#define IVHD_FLAG_RESPASSPW_EN 0x02 -#define IVHD_FLAG_ISOC_EN 0x03 +#define IVHD_FLAG_HT_TUN_EN_MASK 0x01 +#define IVHD_FLAG_PASSPW_EN_MASK 0x02 +#define IVHD_FLAG_RESPASSPW_EN_MASK 0x04 +#define IVHD_FLAG_ISOC_EN_MASK 0x08 #define IVMD_FLAG_EXCL_RANGE 0x08 #define IVMD_FLAG_UNITY_MAP 0x01 @@ -569,19 +569,19 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, * First set the recommended feature enable bits from ACPI * into the IOMMU control registers */ - h->flags & IVHD_FLAG_HT_TUN_EN ? + h->flags & IVHD_FLAG_HT_TUN_EN_MASK ? iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - h->flags & IVHD_FLAG_PASSPW_EN ? + h->flags & IVHD_FLAG_PASSPW_EN_MASK ? iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - h->flags & IVHD_FLAG_RESPASSPW_EN ? + h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ? iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - h->flags & IVHD_FLAG_ISOC_EN ? + h->flags & IVHD_FLAG_ISOC_EN_MASK ? iommu_feature_enable(iommu, CONTROL_ISOC_EN) : iommu_feature_disable(iommu, CONTROL_ISOC_EN); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 098ec84b8c0..f2870920f24 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -431,6 +431,12 @@ static void __cpuinit setup_APIC_timer(void) { struct clock_event_device *levt = &__get_cpu_var(lapic_events); + if (cpu_has(¤t_cpu_data, X86_FEATURE_ARAT)) { + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP; + /* Make LAPIC timer preferrable over percpu HPET */ + lapic_clockevent.rating = 150; + } + memcpy(levt, &lapic_clockevent, sizeof(*levt)); levt->cpumask = cpumask_of(smp_processor_id()); diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 1c11b819f24..30294777557 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -254,7 +254,7 @@ static int parse_unisys_oem(char *oemptr) } #ifdef CONFIG_ACPI -static int find_unisys_acpi_oem_table(unsigned long *oem_addr) +static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) { struct acpi_table_header *header = NULL; struct es7000_oem_table *table; @@ -285,7 +285,7 @@ static int find_unisys_acpi_oem_table(unsigned long *oem_addr) return 0; } -static void unmap_unisys_acpi_oem_table(unsigned long oem_addr) +static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr) { if (!oem_addr) return; @@ -306,7 +306,7 @@ static int es7000_check_dsdt(void) static int es7000_acpi_ret; /* Hook from generic ACPI tables.c */ -static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { unsigned long oem_addr = 0; int check_dsdt; @@ -717,7 +717,7 @@ struct apic apic_es7000_cluster = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, }; -struct apic apic_es7000 = { +struct apic __refdata apic_es7000 = { .name = "es7000", .probe = probe_es7000, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index a2789e42e16..30da617d18e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3670,12 +3670,14 @@ int arch_setup_hpet_msi(unsigned int irq) { int ret; struct msi_msg msg; + struct irq_desc *desc = irq_to_desc(irq); ret = msi_compose_msg(NULL, irq, &msg); if (ret < 0) return ret; hpet_msi_write(irq, &msg); + desc->status |= IRQ_MOVE_PCNTXT; set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq, "edge"); diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index d6bd6240715..ce4fbfa315a 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -138,7 +138,7 @@ int __init check_nmi_watchdog(void) if (!prev_nmi_count) goto error; - alloc_cpumask_var(&backtrace_mask, GFP_KERNEL); + alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO); printk(KERN_INFO "Testing NMI watchdog ... "); #ifdef CONFIG_SMP @@ -414,7 +414,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) touched = 1; } - if (cpumask_test_cpu(cpu, backtrace_mask)) { + /* We can be called before check_nmi_watchdog, hence NULL check. */ + if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) { static DEFINE_SPINLOCK(lock); /* Serialise the printks */ spin_lock(&lock); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1248318436e..2bda6935297 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -19,6 +19,7 @@ #include <linux/timer.h> #include <linux/cpu.h> #include <linux/init.h> +#include <linux/io.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -34,6 +35,17 @@ DEFINE_PER_CPU(int, x2apic_extra_bits); static enum uv_system_type uv_system_type; +static int early_get_nodeid(void) +{ + union uvh_node_id_u node_id; + unsigned long *mmr; + + mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr)); + node_id.v = *mmr; + early_iounmap(mmr, sizeof(*mmr)); + return node_id.s.node_id; +} + static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { if (!strcmp(oem_id, "SGI")) { @@ -42,6 +54,8 @@ static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) else if (!strcmp(oem_table_id, "UVX")) uv_system_type = UV_X2APIC; else if (!strcmp(oem_table_id, "UVH")) { + __get_cpu_var(x2apic_extra_bits) = + early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1); uv_system_type = UV_NON_UNIQUE_APIC; return 1; } @@ -549,7 +563,8 @@ void __init uv_system_init(void) unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; int max_pnode = 0; - unsigned long mmr_base, present; + unsigned long mmr_base, present, paddr; + unsigned short pnode_mask; map_low_mmrs(); @@ -592,6 +607,7 @@ void __init uv_system_init(void) } } + pnode_mask = (1 << n_val) - 1; node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_upper = (((unsigned long)node_id.s.node_id) & ~((1 << n_val) - 1)) << m_val; @@ -615,7 +631,7 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->numa_blade_id = blade; uv_cpu_hub_info(cpu)->blade_processor_id = lcpu; uv_cpu_hub_info(cpu)->pnode = pnode; - uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1; + uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1; uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper; uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base; @@ -631,6 +647,17 @@ void __init uv_system_init(void) lcpu, blade); } + /* Add blade/pnode info for nodes without cpus */ + for_each_online_node(nid) { + if (uv_node_to_blade[nid] >= 0) + continue; + paddr = node_start_pfn(nid) << PAGE_SHIFT; + paddr = uv_soc_phys_ram_to_gpa(paddr); + pnode = (paddr >> m_val) & pnode_mask; + blade = boot_pnode_to_blade(pnode); + uv_node_to_blade[nid] = blade; + } + map_gru_high(max_pnode); map_mmr_high(max_pnode); map_config_high(max_pnode); diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c index f63882728d9..63a88e1f987 100644 --- a/arch/x86/kernel/bios_uv.c +++ b/arch/x86/kernel/bios_uv.c @@ -182,7 +182,8 @@ void uv_bios_init(void) memcpy(&uv_systab, tab, sizeof(struct uv_systab)); iounmap(tab); - printk(KERN_INFO "EFI UV System Table Revision %d\n", tab->revision); + printk(KERN_INFO "EFI UV System Table Revision %d\n", + uv_systab.revision); } #else /* !CONFIG_EFI */ diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 8220ae69849..c965e521271 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, + { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 }, { 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c4f667896c2..77848d9fca6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -114,6 +114,13 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); +static int __init x86_xsave_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + return 1; +} +__setup("noxsave", x86_xsave_setup); + #ifdef CONFIG_X86_32 static int cachesize_override __cpuinitdata = -1; static int disable_x86_serial_nr __cpuinitdata = 1; @@ -1203,6 +1210,8 @@ void __cpuinit cpu_init(void) load_TR_desc(); load_LDT(&init_mm.context); + t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 19f6b9d27e8..54b6de2cd94 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -65,13 +65,18 @@ enum { struct acpi_cpufreq_data { struct acpi_processor_performance *acpi_data; struct cpufreq_frequency_table *freq_table; - unsigned int max_freq; unsigned int resume; unsigned int cpu_feature; }; static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data); +struct acpi_msr_data { + u64 saved_aperf, saved_mperf; +}; + +static DEFINE_PER_CPU(struct acpi_msr_data, msr_data); + DEFINE_TRACE(power_mark); /* acpi_perf_data is a pointer to percpu data. */ @@ -152,7 +157,8 @@ struct drv_cmd { u32 val; }; -static long do_drv_read(void *_cmd) +/* Called via smp_call_function_single(), on the target CPU */ +static void do_drv_read(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 h; @@ -169,10 +175,10 @@ static long do_drv_read(void *_cmd) default: break; } - return 0; } -static long do_drv_write(void *_cmd) +/* Called via smp_call_function_many(), on the target CPUs */ +static void do_drv_write(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 lo, hi; @@ -191,23 +197,24 @@ static long do_drv_write(void *_cmd) default: break; } - return 0; } static void drv_read(struct drv_cmd *cmd) { cmd->val = 0; - work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd); + smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1); } static void drv_write(struct drv_cmd *cmd) { - unsigned int i; + int this_cpu; - for_each_cpu(i, cmd->mask) { - work_on_cpu(i, do_drv_write, cmd); - } + this_cpu = get_cpu(); + if (cpumask_test_cpu(this_cpu, cmd->mask)) + do_drv_write(cmd); + smp_call_function_many(cmd->mask, do_drv_write, cmd, 1); + put_cpu(); } static u32 get_cur_val(const struct cpumask *mask) @@ -241,28 +248,23 @@ static u32 get_cur_val(const struct cpumask *mask) return cmd.val; } -struct perf_cur { +struct perf_pair { union { struct { u32 lo; u32 hi; } split; u64 whole; - } aperf_cur, mperf_cur; + } aperf, mperf; }; - -static long read_measured_perf_ctrs(void *_cur) +/* Called via smp_call_function_single(), on the target CPU */ +static void read_measured_perf_ctrs(void *_cur) { - struct perf_cur *cur = _cur; - - rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi); - rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi); + struct perf_pair *cur = _cur; - wrmsr(MSR_IA32_APERF, 0, 0); - wrmsr(MSR_IA32_MPERF, 0, 0); - - return 0; + rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi); + rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi); } /* @@ -281,58 +283,63 @@ static long read_measured_perf_ctrs(void *_cur) static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int cpu) { - struct perf_cur cur; + struct perf_pair readin, cur; unsigned int perf_percent; unsigned int retval; - if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur)) + if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1)) return 0; + cur.aperf.whole = readin.aperf.whole - + per_cpu(msr_data, cpu).saved_aperf; + cur.mperf.whole = readin.mperf.whole - + per_cpu(msr_data, cpu).saved_mperf; + per_cpu(msr_data, cpu).saved_aperf = readin.aperf.whole; + per_cpu(msr_data, cpu).saved_mperf = readin.mperf.whole; + #ifdef __i386__ /* * We dont want to do 64 bit divide with 32 bit kernel * Get an approximate value. Return failure in case we cannot get * an approximate value. */ - if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) { + if (unlikely(cur.aperf.split.hi || cur.mperf.split.hi)) { int shift_count; u32 h; - h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi); + h = max_t(u32, cur.aperf.split.hi, cur.mperf.split.hi); shift_count = fls(h); - cur.aperf_cur.whole >>= shift_count; - cur.mperf_cur.whole >>= shift_count; + cur.aperf.whole >>= shift_count; + cur.mperf.whole >>= shift_count; } - if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) { + if (((unsigned long)(-1) / 100) < cur.aperf.split.lo) { int shift_count = 7; - cur.aperf_cur.split.lo >>= shift_count; - cur.mperf_cur.split.lo >>= shift_count; + cur.aperf.split.lo >>= shift_count; + cur.mperf.split.lo >>= shift_count; } - if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo) - perf_percent = (cur.aperf_cur.split.lo * 100) / - cur.mperf_cur.split.lo; + if (cur.aperf.split.lo && cur.mperf.split.lo) + perf_percent = (cur.aperf.split.lo * 100) / cur.mperf.split.lo; else perf_percent = 0; #else - if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) { + if (unlikely(((unsigned long)(-1) / 100) < cur.aperf.whole)) { int shift_count = 7; - cur.aperf_cur.whole >>= shift_count; - cur.mperf_cur.whole >>= shift_count; + cur.aperf.whole >>= shift_count; + cur.mperf.whole >>= shift_count; } - if (cur.aperf_cur.whole && cur.mperf_cur.whole) - perf_percent = (cur.aperf_cur.whole * 100) / - cur.mperf_cur.whole; + if (cur.aperf.whole && cur.mperf.whole) + perf_percent = (cur.aperf.whole * 100) / cur.mperf.whole; else perf_percent = 0; #endif - retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100; + retval = (policy->cpuinfo.max_freq * perf_percent) / 100; return retval; } @@ -685,16 +692,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */ if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE && policy->cpuinfo.transition_latency > 20 * 1000) { - static int print_once; policy->cpuinfo.transition_latency = 20 * 1000; - if (!print_once) { - print_once = 1; - printk(KERN_INFO "Capping off P-state tranision latency" - " at 20 uS\n"); - } + printk_once(KERN_INFO + "P-state transition latency capped at 20 uS\n"); } - data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ for (i = 0; i < perf->state_count; i++) { if (i > 0 && perf->states[i].core_frequency >= @@ -713,6 +715,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (result) goto err_freqfree; + if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq) + printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n"); + switch (perf->control_register.space_id) { case ACPI_ADR_SPACE_SYSTEM_IO: /* Current speed is unknown and not detectable by IO port */ diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index 0bd48e65a0c..ce2ed3e4aad 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -33,7 +33,6 @@ #include <linux/timex.h> #include <linux/io.h> #include <linux/acpi.h> -#include <linux/kernel.h> #include <asm/msr.h> #include <acpi/processor.h> diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 6ac55bd341a..86961519372 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -168,6 +168,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) case 0x0E: /* Core */ case 0x0F: /* Core Duo */ case 0x16: /* Celeron Core */ + case 0x1C: /* Atom */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE); case 0x0D: /* Pentium M (Dothan) */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 3c28ccd4974..a8363e5be4e 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -168,10 +168,12 @@ static int check_powernow(void) return 1; } +#ifdef CONFIG_X86_POWERNOW_K7_ACPI static void invalidate_entry(unsigned int entry) { powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; } +#endif static int get_ranges(unsigned char *pst) { diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 4709ead2db5..f6b32d11235 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -649,6 +649,20 @@ static void print_basics(struct powernow_k8_data *data) data->batps); } +static u32 freq_from_fid_did(u32 fid, u32 did) +{ + u32 mhz = 0; + + if (boot_cpu_data.x86 == 0x10) + mhz = (100 * (fid + 0x10)) >> did; + else if (boot_cpu_data.x86 == 0x11) + mhz = (100 * (fid + 8)) >> did; + else + BUG(); + + return mhz * 1000; +} + static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) { @@ -923,8 +937,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, powernow_table[i].index = index; - powernow_table[i].frequency = - data->acpi_data.states[i].core_frequency * 1000; + /* Frequency may be rounded for these */ + if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) { + powernow_table[i].frequency = + freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7); + } else + powernow_table[i].frequency = + data->acpi_data.states[i].core_frequency * 1000; } return 0; } @@ -1215,13 +1234,16 @@ static int powernowk8_verify(struct cpufreq_policy *pol) return cpufreq_frequency_table_verify(pol, data->powernow_table); } +static const char ACPI_PSS_BIOS_BUG_MSG[] = + KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n" + KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n"; + /* per CPU init entry point to the driver */ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; cpumask_t oldmask; int rc; - static int print_once; if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1244,19 +1266,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { - /* - * Replace this one with print_once as soon as such a - * thing gets introduced - */ - if (!print_once) { - WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS " - "does not provide ACPI _PSS objects " - "in a way that Linux understands. " - "Please report this to the Linux ACPI" - " maintainers and complain to your " - "BIOS vendor.\n"); - print_once++; - } + printk_once(ACPI_PSS_BIOS_BUG_MSG); goto err_out; } if (pol->cpu != 0) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 863f89568b1..6fb0b359d2a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - - mce_log(&m); - add_taint(TAINT_MACHINE_CHECK); + if (!(flags & MCP_DONTLOG)) { + mce_log(&m); + add_taint(TAINT_MACHINE_CHECK); + } /* * Clear state for this bank. @@ -452,13 +453,14 @@ void mce_log_therm_throt_event(__u64 status) */ static int check_interval = 5 * 60; /* 5 minutes */ -static int next_interval; /* in jiffies */ +static DEFINE_PER_CPU(int, next_interval); /* in jiffies */ static void mcheck_timer(unsigned long); static DEFINE_PER_CPU(struct timer_list, mce_timer); static void mcheck_timer(unsigned long data) { struct timer_list *t = &per_cpu(mce_timer, data); + int *n; WARN_ON(smp_processor_id() != data); @@ -470,14 +472,14 @@ static void mcheck_timer(unsigned long data) * Alert userspace if needed. If we logged an MCE, reduce the * polling interval, otherwise increase the polling interval. */ + n = &__get_cpu_var(next_interval); if (mce_notify_user()) { - next_interval = max(next_interval/2, HZ/100); + *n = max(*n/2, HZ/100); } else { - next_interval = min(next_interval * 2, - (int)round_jiffies_relative(check_interval*HZ)); + *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ)); } - t->expires = jiffies + next_interval; + t->expires = jiffies + *n; add_timer(t); } @@ -584,7 +586,7 @@ static void mce_init(void *dummy) * Log the machine checks left over from the previous reset. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC, &all_banks); + machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks); set_in_cr4(X86_CR4_MCE); @@ -632,14 +634,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c) static void mce_init_timer(void) { struct timer_list *t = &__get_cpu_var(mce_timer); + int *n = &__get_cpu_var(next_interval); - /* data race harmless because everyone sets to the same value */ - if (!next_interval) - next_interval = check_interval * HZ; - if (!next_interval) + *n = check_interval * HZ; + if (!*n) return; setup_timer(t, mcheck_timer, smp_processor_id()); - t->expires = round_jiffies(jiffies + next_interval); + t->expires = round_jiffies(jiffies + *n); add_timer(t); } @@ -907,7 +908,6 @@ static void mce_cpu_restart(void *data) /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { - next_interval = check_interval * HZ; on_each_cpu(mce_cpu_restart, NULL, 1); } @@ -1110,7 +1110,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - t->expires = round_jiffies(jiffies + next_interval); + t->expires = round_jiffies(jiffies + + __get_cpu_var(next_interval)); add_timer_on(t, cpu); smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); break; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index d6b72df89d6..cef3ee30744 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num) static void cmci_discover(int banks, int boot) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + unsigned long flags; int hdr = 0; int i; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; @@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot) WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); if (hdr) printk(KERN_CONT "\n"); } @@ -211,13 +212,14 @@ void cmci_recheck(void) */ void cmci_clear(void) { + unsigned long flags; int i; int banks; u64 val; if (!cmci_supported(&banks)) return; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { if (!test_bit(i, __get_cpu_var(mce_banks_owned))) continue; @@ -227,7 +229,7 @@ void cmci_clear(void) wrmsrl(MSR_IA32_MC0_CTL2 + i, val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); } /* diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 0b776c09aff..d21d4fb161f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -275,7 +275,11 @@ static void __init print_mtrr_state(void) } printk(KERN_DEBUG "MTRR variable ranges %sabled:\n", mtrr_state.enabled & 2 ? "en" : "dis"); - high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4; + if (size_or_mask & 0xffffffffUL) + high_width = ffs(size_or_mask & 0xffffffffUL) - 1; + else + high_width = ffs(size_or_mask>>32) + 32 - 1; + high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) printk(KERN_DEBUG " %u base %0*X%05X000 mask %0*X%05X000 %s\n", diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index f93047fed79..d5e30397246 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); seq_printf(m, "siblings\t: %d\n", - cpumask_weight(cpu_sibling_mask(cpu))); + cpumask_weight(cpu_core_mask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ef2c3563357..00628130292 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1074,12 +1074,13 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) u64 addr; u64 start; - start = startt; - while (size < sizet && (start + 1)) + for (start = startt; ; start += size) { start = find_e820_area_size(start, &size, align); - - if (size < sizet) - return 0; + if (!(start + 1)) + return 0; + if (size >= sizet) + break; + } #ifdef CONFIG_X86_32 if (start >= MAXMEM) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a331ec38af9..38946c6e843 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1410,7 +1410,10 @@ ENTRY(paranoid_exit) paranoid_swapgs: TRACE_IRQS_IRETQ 0 SWAPGS_UNSAFE_STACK + RESTORE_ALL 8 + jmp irq_return paranoid_restore: + TRACE_IRQS_IRETQ 0 RESTORE_ALL 8 jmp irq_return paranoid_userspace: diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 70a10ca100f..b79c5533c42 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -18,6 +18,8 @@ #include <linux/init.h> #include <linux/list.h> +#include <trace/syscall.h> + #include <asm/cacheflush.h> #include <asm/ftrace.h> #include <asm/nops.h> @@ -440,7 +442,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) _ASM_EXTABLE(1b, 4b) _ASM_EXTABLE(2b, 4b) - : [old] "=r" (old), [faulted] "=r" (faulted) + : [old] "=&r" (old), [faulted] "=r" (faulted) : [parent] "r" (parent), [return_hooker] "r" (return_hooker) : "memory" ); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 648b3a2a3a4..81408b93f88 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -236,6 +236,10 @@ static void hpet_stop_counter(void) unsigned long cfg = hpet_readl(HPET_CFG); cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); +} + +static void hpet_reset_counter(void) +{ hpet_writel(0, HPET_COUNTER); hpet_writel(0, HPET_COUNTER + 4); } @@ -250,6 +254,7 @@ static void hpet_start_counter(void) static void hpet_restart_counter(void) { hpet_stop_counter(); + hpet_reset_counter(); hpet_start_counter(); } @@ -309,7 +314,7 @@ static int hpet_setup_msi_irq(unsigned int irq); static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { - unsigned long cfg; + unsigned long cfg, cmp, now; uint64_t delta; switch (mode) { @@ -317,12 +322,23 @@ static void hpet_set_mode(enum clock_event_mode mode, hpet_stop_counter(); delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; + now = hpet_readl(HPET_COUNTER); + cmp = now + (unsigned long) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | HPET_TN_32BIT; hpet_writel(cfg, HPET_Tn_CFG(timer)); + hpet_writel(cmp, HPET_Tn_CMP(timer)); + udelay(1); + /* + * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL + * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL + * bit is automatically cleared after the first write. + * (See AMD-8111 HyperTransport I/O Hub Data Sheet, + * Publication # 24674) + */ hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); hpet_start_counter(); hpet_print_config(); @@ -722,7 +738,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, /* * Clock source related code */ -static cycle_t read_hpet(void) +static cycle_t read_hpet(struct clocksource *cs) { return (cycle_t)hpet_readl(HPET_COUNTER); } @@ -756,7 +772,7 @@ static int hpet_clocksource_register(void) hpet_restart_counter(); /* Verify whether hpet counter works */ - t1 = read_hpet(); + t1 = hpet_readl(HPET_COUNTER); rdtscll(start); /* @@ -770,7 +786,7 @@ static int hpet_clocksource_register(void) rdtscll(now); } while ((now - start) < 200000UL); - if (t1 == read_hpet()) { + if (t1 == hpet_readl(HPET_COUNTER)) { printk(KERN_WARNING "HPET counter not counting. HPET disabled\n"); return -ENODEV; diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 3475440baa5..c2e0bb0890d 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -129,7 +129,7 @@ void __init setup_pit_timer(void) * to just read by itself. So use jiffies to emulate a free * running counter: */ -static cycle_t pit_read(void) +static cycle_t pit_read(struct clocksource *cs) { static int old_count; static u32 old_jifs; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index eedfaebe106..b1f4dffb919 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -88,6 +88,7 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs[GDB_SS] = __KERNEL_DS; gdb_regs[GDB_FS] = 0xFFFF; gdb_regs[GDB_GS] = 0xFFFF; + gdb_regs[GDB_SP] = (int)®s->sp; #else gdb_regs[GDB_R8] = regs->r8; gdb_regs[GDB_R9] = regs->r9; @@ -100,8 +101,8 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs32[GDB_PS] = regs->flags; gdb_regs32[GDB_CS] = regs->cs; gdb_regs32[GDB_SS] = regs->ss; -#endif gdb_regs[GDB_SP] = regs->sp; +#endif } /** diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 137f2e8132d..223af43f152 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -77,6 +77,11 @@ static cycle_t kvm_clock_read(void) return ret; } +static cycle_t kvm_clock_get_cycles(struct clocksource *cs) +{ + return kvm_clock_read(); +} + /* * If we don't do that, there is the possibility that the guest * will calibrate under heavy load - thus, getting a lower lpj - @@ -107,7 +112,7 @@ static void kvm_get_preset_lpj(void) static struct clocksource kvm_clock = { .name = "kvm-clock", - .read = kvm_clock_read, + .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .mult = 1 << KVM_SCALE, diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index e7368c1da01..c1c429d0013 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -194,7 +194,7 @@ void machine_kexec(struct kimage *image) unsigned int preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) save_processor_state(); #endif @@ -253,7 +253,7 @@ void machine_kexec(struct kimage *image) image->preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) restore_processor_state(); #endif diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 89cea4d4467..84c3bf209e9 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -274,7 +274,7 @@ void machine_kexec(struct kimage *image) int save_ftrace_enabled; #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) save_processor_state(); #endif @@ -333,7 +333,7 @@ void machine_kexec(struct kimage *image) image->preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) restore_processor_state(); #endif diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index a0f3851ef31..98c470c069d 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -108,40 +108,29 @@ struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(ucode_cpu_info); #ifdef CONFIG_MICROCODE_OLD_INTERFACE -struct update_for_cpu { - const void __user *buf; - size_t size; -}; - -static long update_for_cpu(void *_ufc) -{ - struct update_for_cpu *ufc = _ufc; - int error; - - error = microcode_ops->request_microcode_user(smp_processor_id(), - ufc->buf, ufc->size); - if (error < 0) - return error; - if (!error) - microcode_ops->apply_microcode(smp_processor_id()); - return error; -} - static int do_microcode_update(const void __user *buf, size_t size) { + cpumask_t old; int error = 0; int cpu; - struct update_for_cpu ufc = { .buf = buf, .size = size }; + + old = current->cpus_allowed; for_each_online_cpu(cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!uci->valid) continue; - error = work_on_cpu(cpu, update_for_cpu, &ufc); + + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); + error = microcode_ops->request_microcode_user(cpu, buf, size); if (error < 0) - break; + goto out; + if (!error) + microcode_ops->apply_microcode(cpu); } +out: + set_cpus_allowed_ptr(current, &old); return error; } @@ -391,8 +380,6 @@ static int mc_sysdev_add(struct sys_device *sys_dev) return err; err = microcode_init_cpu(cpu); - if (err) - sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); return err; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index dce99dca6cf..70fd7e414c1 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -679,7 +679,7 @@ void __init get_smp_config(void) __get_smp_config(0); } -static void smp_reserve_bootmem(struct mpf_intel *mpf) +static void __init smp_reserve_bootmem(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); #ifdef CONFIG_X86_32 @@ -838,7 +838,7 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m) static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM]; -static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) +static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) { int i; @@ -866,7 +866,8 @@ static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) } } #else /* CONFIG_X86_IO_APIC */ -static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} +static +inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} #endif /* CONFIG_X86_IO_APIC */ static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 8e45f446488..9faf43bea33 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -134,7 +134,9 @@ static void *get_call_destination(u8 type) .pv_irq_ops = pv_irq_ops, .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, +#ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, +#endif }; return *((void **)&tmpl + type); } diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 34f12e9996e..221a3853e26 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -50,7 +50,7 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -struct dma_map_ops swiotlb_dma_ops = { +static struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index fe9345c967d..23b7c8f017e 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,7 +21,6 @@ #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/signal.h> -#include <linux/ftrace.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -35,6 +34,8 @@ #include <asm/proto.h> #include <asm/ds.h> +#include <trace/syscall.h> + #include "tls.h" enum x86_regset { diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 94ad0c029f0..af71d06624b 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -261,8 +261,6 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev) { if (hpet_force_user) old_ich_force_enable_hpet(dev); - else - hpet_print_force_info(); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 1340dad417f..667188e0b5a 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -232,6 +232,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"), }, }, + { /* Handle problems with rebooting on Sony VGN-Z540N */ + .callback = set_bios_reboot, + .ident = "Sony VGN-Z540N", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 3a97a4cf187..8f0e13be36b 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -160,8 +160,10 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) /* * If large page isn't supported, there's no benefit in doing * this. Also, on non-NUMA, embedding is better. + * + * NOTE: disabled for now. */ - if (!cpu_has_pse || !pcpu_need_numa()) + if (true || !cpu_has_pse || !pcpu_need_numa()) return -EINVAL; /* diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index deb5ebb32c3..ed0c33761e6 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -25,6 +25,8 @@ static int uv_bau_retry_limit __read_mostly; /* position of pnode (which is nasid>>1): */ static int uv_nshift __read_mostly; +/* base pnode in this partition */ +static int uv_partition_base_pnode __read_mostly; static unsigned long uv_mmask __read_mostly; @@ -32,6 +34,34 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); /* + * Determine the first node on a blade. + */ +static int __init blade_to_first_node(int blade) +{ + int node, b; + + for_each_online_node(node) { + b = uv_node_to_blade_id(node); + if (blade == b) + return node; + } + return -1; /* shouldn't happen */ +} + +/* + * Determine the apicid of the first cpu on a blade. + */ +static int __init blade_to_first_apicid(int blade) +{ + int cpu; + + for_each_present_cpu(cpu) + if (blade == uv_cpu_to_blade_id(cpu)) + return per_cpu(x86_cpu_to_apicid, cpu); + return -1; +} + +/* * Free a software acknowledge hardware resource by clearing its Pending * bit. This will return a reply to the sender. * If the message has timed out, a reply has already been sent by the @@ -67,7 +97,7 @@ static void uv_bau_process_message(struct bau_payload_queue_entry *msg, msp = __get_cpu_var(bau_control).msg_statuses + msg_slot; cpu = uv_blade_processor_id(); msg->number_of_cpus = - uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); + uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); this_cpu_mask = 1UL << cpu; if (msp->seen_by.bits & this_cpu_mask) return; @@ -215,14 +245,14 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * Returns @flush_mask if some remote flushing remains to be done. The * mask will have some bits still set. */ -const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, +const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode, struct bau_desc *bau_desc, struct cpumask *flush_mask) { int completion_status = 0; int right_shift; int tries = 0; - int blade; + int pnode; int bit; unsigned long mmr_offset; unsigned long index; @@ -265,8 +295,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, * use the IPI method of shootdown on them. */ for_each_cpu(bit, flush_mask) { - blade = uv_cpu_to_blade_id(bit); - if (blade == this_blade) + pnode = uv_cpu_to_pnode(bit); + if (pnode == this_pnode) continue; cpumask_clear_cpu(bit, flush_mask); } @@ -309,16 +339,16 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask); int i; int bit; - int blade; + int pnode; int uv_cpu; - int this_blade; + int this_pnode; int locals = 0; struct bau_desc *bau_desc; cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); uv_cpu = uv_blade_processor_id(); - this_blade = uv_numa_blade_id(); + this_pnode = uv_hub_info->pnode; bau_desc = __get_cpu_var(bau_control).descriptor_base; bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu; @@ -326,13 +356,14 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, i = 0; for_each_cpu(bit, flush_mask) { - blade = uv_cpu_to_blade_id(bit); - BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1)); - if (blade == this_blade) { + pnode = uv_cpu_to_pnode(bit); + BUG_ON(pnode > (UV_DISTRIBUTION_SIZE - 1)); + if (pnode == this_pnode) { locals++; continue; } - bau_node_set(blade, &bau_desc->distribution); + bau_node_set(pnode - uv_partition_base_pnode, + &bau_desc->distribution); i++; } if (i == 0) { @@ -350,7 +381,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, bau_desc->payload.address = va; bau_desc->payload.sending_cpu = cpu; - return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask); + return uv_flush_send_and_wait(uv_cpu, this_pnode, bau_desc, flush_mask); } /* @@ -418,24 +449,58 @@ void uv_bau_message_interrupt(struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * uv_enable_timeouts + * + * Each target blade (i.e. blades that have cpu's) needs to have + * shootdown message timeouts enabled. The timeout does not cause + * an interrupt, but causes an error message to be returned to + * the sender. + */ static void uv_enable_timeouts(void) { - int i; int blade; - int last_blade; + int nblades; int pnode; - int cur_cpu = 0; - unsigned long apicid; + unsigned long mmr_image; - last_blade = -1; - for_each_online_node(i) { - blade = uv_node_to_blade_id(i); - if (blade == last_blade) + nblades = uv_num_possible_blades(); + + for (blade = 0; blade < nblades; blade++) { + if (!uv_blade_nr_possible_cpus(blade)) continue; - last_blade = blade; - apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + pnode = uv_blade_to_pnode(blade); - cur_cpu += uv_blade_nr_possible_cpus(i); + mmr_image = + uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL); + /* + * Set the timeout period and then lock it in, in three + * steps; captures and locks in the period. + * + * To program the period, the SOFT_ACK_MODE must be off. + */ + mmr_image &= ~((unsigned long)1 << + UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + /* + * Set the 4-bit period. + */ + mmr_image &= ~((unsigned long)0xf << + UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD << + UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + /* + * Subsequent reversals of the timebase bit (3) cause an + * immediate timeout of one or all INTD resources as + * indicated in bits 2:0 (7 causes all of them to timeout). + */ + mmr_image |= ((unsigned long)1 << + UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); } } @@ -482,8 +547,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) stat->requestee, stat->onetlb, stat->alltlb, stat->s_retry, stat->d_retry, stat->ptc_i); seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n", - uv_read_global_mmr64(uv_blade_to_pnode - (uv_cpu_to_blade_id(cpu)), + uv_read_global_mmr64(uv_cpu_to_pnode(cpu), UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), stat->sflush, stat->dflush, stat->retriesok, stat->nomsg, @@ -617,16 +681,18 @@ static struct bau_control * __init uv_table_bases_init(int blade, int node) * finish the initialization of the per-blade control structures */ static void __init -uv_table_bases_finish(int blade, int node, int cur_cpu, +uv_table_bases_finish(int blade, struct bau_control *bau_tablesp, struct bau_desc *adp) { struct bau_control *bcp; - int i; + int cpu; - for (i = cur_cpu; i < cur_cpu + uv_blade_nr_possible_cpus(blade); i++) { - bcp = (struct bau_control *)&per_cpu(bau_control, i); + for_each_present_cpu(cpu) { + if (blade != uv_cpu_to_blade_id(cpu)) + continue; + bcp = (struct bau_control *)&per_cpu(bau_control, cpu); bcp->bau_msg_head = bau_tablesp->va_queue_first; bcp->va_queue_first = bau_tablesp->va_queue_first; bcp->va_queue_last = bau_tablesp->va_queue_last; @@ -649,11 +715,10 @@ uv_activation_descriptor_init(int node, int pnode) struct bau_desc *adp; struct bau_desc *ad2; - adp = (struct bau_desc *) - kmalloc_node(16384, GFP_KERNEL, node); + adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node); BUG_ON(!adp); - pa = __pa((unsigned long)adp); + pa = uv_gpa(adp); /* need the real nasid*/ n = pa >> uv_nshift; m = pa & uv_mmask; @@ -667,8 +732,12 @@ uv_activation_descriptor_init(int node, int pnode) for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) { memset(ad2, 0, sizeof(struct bau_desc)); ad2->header.sw_ack_flag = 1; - ad2->header.base_dest_nodeid = - uv_blade_to_pnode(uv_cpu_to_blade_id(0)); + /* + * base_dest_nodeid is the first node in the partition, so + * the bit map will indicate partition-relative node numbers. + * note that base_dest_nodeid is actually a nasid. + */ + ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1; ad2->header.command = UV_NET_ENDPOINT_INTD; ad2->header.int_both = 1; /* @@ -686,6 +755,8 @@ static struct bau_payload_queue_entry * __init uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) { struct bau_payload_queue_entry *pqp; + unsigned long pa; + int pn; char *cp; pqp = (struct bau_payload_queue_entry *) kmalloc_node( @@ -696,10 +767,14 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) cp = (char *)pqp + 31; pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5); bau_tablesp->va_queue_first = pqp; + /* + * need the pnode of where the memory was really allocated + */ + pa = uv_gpa(pqp); + pn = pa >> uv_nshift; uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, - ((unsigned long)pnode << - UV_PAYLOADQ_PNODE_SHIFT) | + ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | uv_physnodeaddr(pqp)); uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, uv_physnodeaddr(pqp)); @@ -715,8 +790,9 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) /* * Initialization of each UV blade's structures */ -static int __init uv_init_blade(int blade, int node, int cur_cpu) +static int __init uv_init_blade(int blade) { + int node; int pnode; unsigned long pa; unsigned long apicid; @@ -724,16 +800,17 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu) struct bau_payload_queue_entry *pqp; struct bau_control *bau_tablesp; + node = blade_to_first_node(blade); bau_tablesp = uv_table_bases_init(blade, node); pnode = uv_blade_to_pnode(blade); adp = uv_activation_descriptor_init(node, pnode); pqp = uv_payload_queue_init(node, pnode, bau_tablesp); - uv_table_bases_finish(blade, node, cur_cpu, bau_tablesp, adp); + uv_table_bases_finish(blade, bau_tablesp, adp); /* * the below initialization can't be in firmware because the * messaging IRQ will be determined by the OS */ - apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + apicid = blade_to_first_apicid(blade); pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); if ((pa & 0xff) != UV_BAU_MESSAGE) { uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, @@ -748,9 +825,7 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu) static int __init uv_bau_init(void) { int blade; - int node; int nblades; - int last_blade; int cur_cpu; if (!is_uv_system()) @@ -763,29 +838,21 @@ static int __init uv_bau_init(void) uv_bau_retry_limit = 1; uv_nshift = uv_hub_info->n_val; uv_mmask = (1UL << uv_hub_info->n_val) - 1; - nblades = 0; - last_blade = -1; - cur_cpu = 0; - for_each_online_node(node) { - blade = uv_node_to_blade_id(node); - if (blade == last_blade) - continue; - last_blade = blade; - nblades++; - } + nblades = uv_num_possible_blades(); + uv_bau_table_bases = (struct bau_control **) kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL); BUG_ON(!uv_bau_table_bases); - last_blade = -1; - for_each_online_node(node) { - blade = uv_node_to_blade_id(node); - if (blade == last_blade) - continue; - last_blade = blade; - uv_init_blade(blade, node, cur_cpu); - cur_cpu += uv_blade_nr_possible_cpus(blade); - } + uv_partition_base_pnode = 0x7fffffff; + for (blade = 0; blade < nblades; blade++) + if (uv_blade_nr_possible_cpus(blade) && + (uv_blade_to_pnode(blade) < uv_partition_base_pnode)) + uv_partition_base_pnode = uv_blade_to_pnode(blade); + for (blade = 0; blade < nblades; blade++) + if (uv_blade_nr_possible_cpus(blade)) + uv_init_blade(blade); + alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); uv_enable_timeouts(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7a567ebe636..d57de05dc43 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -699,7 +699,7 @@ static struct clocksource clocksource_tsc; * code, which is necessary to support wrapping clocksources like pm * timer. */ -static cycle_t read_tsc(void) +static cycle_t read_tsc(struct clocksource *cs) { cycle_t ret = (cycle_t)get_cycles(); diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c index 67f9b9dbf80..36afb98675a 100644 --- a/arch/x86/kernel/uv_sysfs.c +++ b/arch/x86/kernel/uv_sysfs.c @@ -21,6 +21,7 @@ #include <linux/sysdev.h> #include <asm/uv/bios.h> +#include <asm/uv/uv.h> struct kobject *sgi_uv_kobj; @@ -47,6 +48,9 @@ static int __init sgi_uv_sysfs_init(void) { unsigned long ret; + if (!is_uv_system()) + return -ENODEV; + if (!sgi_uv_kobj) sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj); if (!sgi_uv_kobj) { diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c index 2ffb6c53326..583f11d5c48 100644 --- a/arch/x86/kernel/uv_time.c +++ b/arch/x86/kernel/uv_time.c @@ -29,7 +29,7 @@ #define RTC_NAME "sgi_rtc" -static cycle_t uv_read_rtc(void); +static cycle_t uv_read_rtc(struct clocksource *cs); static int uv_rtc_next_event(unsigned long, struct clock_event_device *); static void uv_rtc_timer_setup(enum clock_event_mode, struct clock_event_device *); @@ -123,7 +123,7 @@ static int uv_setup_intr(int cpu, u64 expires) /* Initialize comparator value */ uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires); - return (expires < uv_read_rtc() && !uv_intr_pending(pnode)); + return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode)); } /* @@ -256,7 +256,7 @@ static int uv_rtc_unset_timer(int cpu) spin_lock_irqsave(&head->lock, flags); - if (head->next_cpu == bcpu && uv_read_rtc() >= *t) + if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) rc = 1; *t = ULLONG_MAX; @@ -278,7 +278,7 @@ static int uv_rtc_unset_timer(int cpu) /* * Read the RTC. */ -static cycle_t uv_read_rtc(void) +static cycle_t uv_read_rtc(struct clocksource *cs) { return (cycle_t)uv_read_local_mmr(UVH_RTC); } @@ -291,7 +291,7 @@ static int uv_rtc_next_event(unsigned long delta, { int ced_cpu = cpumask_first(ced->cpumask); - return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc()); + return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc(NULL)); } /* diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index d303369a7ba..2b3eb82efee 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -283,7 +283,7 @@ void __devinit vmi_time_ap_init(void) /** vmi clocksource */ static struct clocksource clocksource_vmi; -static cycle_t read_real_cycles(void) +static cycle_t read_real_cycles(struct clocksource *cs) { cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); return max(ret, clocksource_vmi.cycle_last); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 2b54fe002e9..c5ee17e8c6d 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -89,7 +89,7 @@ int save_i387_xstate(void __user *buf) if (!used_math()) return 0; - clear_used_math(); /* trigger finit */ + if (task_thread_info(tsk)->status & TS_USEDFPU) { /* * Start with clearing the user buffer. This will present a @@ -114,6 +114,8 @@ int save_i387_xstate(void __user *buf) return -1; } + clear_used_math(); /* trigger finit */ + if (task_thread_info(tsk)->status & TS_XSAVE) { struct _fpstate __user *fx = buf; struct _xstate __user *x = buf; @@ -324,7 +326,7 @@ void __ref xsave_cntxt_init(void) } /* - * for now OS knows only about FP/SSE + * Support only the state known to OS. */ pcntxt_mask = pcntxt_mask & XCNTXT_MASK; xsave_init(); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2a36f7f7c4c..32cf11e5728 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1248,7 +1248,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; - sp->global = role.cr4_pge; + sp->global = 0; hlist_add_head(&sp->hash_link, bucket); if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) @@ -2897,8 +2897,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) { - kvm_x86_ops->tlb_flush(vcpu); - set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); + kvm_set_cr3(vcpu, vcpu->arch.cr3); return 1; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1821c207819..1f8510c51d6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -411,7 +411,6 @@ static __init int svm_hardware_setup(void) iopm_va = page_address(iopm_pages); memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); - clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */ iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; if (boot_cpu_has(X86_FEATURE_NX)) @@ -796,6 +795,11 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; + /* AMD's VMCB does not have an explicit unusable field, so emulate it + * for cross vendor migration purposes by "not present" + */ + var->unusable = !var->present || (var->type == 0); + switch (seg) { case VCPU_SREG_CS: /* @@ -827,8 +831,6 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->type |= 0x1; break; } - - var->unusable = !var->present; } static int svm_get_cpl(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8ca100a9eca..3944e917e79 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -338,6 +338,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { + unsigned long old_cr4 = vcpu->arch.cr4; + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; + if (cr4 & CR4_RESERVED_BITS) { printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); @@ -351,7 +354,8 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_inject_gp(vcpu, 0); return; } - } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) + } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) + && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); kvm_inject_gp(vcpu, 0); @@ -1121,9 +1125,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int is_efer_nx(void) { - u64 efer; + unsigned long long efer = 0; - rdmsrl(MSR_EFER, efer); + rdmsrl_safe(MSR_EFER, &efer); return efer & EFER_NX; } @@ -1259,7 +1263,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) | bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) | bit(X86_FEATURE_SYSCALL) | - (bit(X86_FEATURE_NX) && is_efer_nx()) | + (is_efer_nx() ? bit(X86_FEATURE_NX) : 0) | #ifdef CONFIG_X86_64 bit(X86_FEATURE_LM) | #endif @@ -2775,6 +2779,9 @@ out: void kvm_arch_exit(void) { + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); kvm_x86_ops = NULL; kvm_mmu_module_exit(); } @@ -4159,6 +4166,11 @@ EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + if (vcpu->arch.time_page) { + kvm_release_page_dirty(vcpu->arch.time_page); + vcpu->arch.time_page = NULL; + } + kvm_x86_ops->vcpu_free(vcpu); } diff --git a/arch/x86/lguest/Makefile b/arch/x86/lguest/Makefile index 27f0c9ed7f6..94e0e54056a 100644 --- a/arch/x86/lguest/Makefile +++ b/arch/x86/lguest/Makefile @@ -1 +1,2 @@ obj-y := i386_head.o boot.o +CFLAGS_boot.o := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index e94a11e42f9..33a93b41739 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -67,6 +67,7 @@ #include <asm/mce.h> #include <asm/io.h> #include <asm/i387.h> +#include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ /*G:010 Welcome to the Guest! @@ -273,15 +274,15 @@ static void lguest_load_idt(const struct desc_ptr *desc) * controls the entire thing and the Guest asks it to make changes using the * LOAD_GDT hypercall. * - * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY - * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? Wouldn't - * it be even better if you were the one to send the patch to fix it? + * This is the exactly like the IDT code. */ static void lguest_load_gdt(const struct desc_ptr *desc) { - BUG_ON((desc->size + 1) / 8 != GDT_ENTRIES); - kvm_hypercall2(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES); + unsigned int i; + struct desc_struct *gdt = (void *)desc->address; + + for (i = 0; i < (desc->size+1)/8; i++) + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b); } /* For a single GDT entry which changes, we do the lazy thing: alter our GDT, @@ -291,7 +292,9 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) { native_write_gdt_entry(dt, entrynum, desc, type); - kvm_hypercall2(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES); + /* Tell Host about this new entry. */ + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum, + dt[entrynum].a, dt[entrynum].b); } /* OK, I lied. There are three "thread local storage" GDT entries which change @@ -661,7 +664,7 @@ static unsigned long lguest_tsc_khz(void) /* If we can't use the TSC, the kernel falls back to our lower-priority * "lguest_clock", where we read the time value given to us by the Host. */ -static cycle_t lguest_clock_read(void) +static cycle_t lguest_clock_read(struct clocksource *cs) { unsigned long sec, nsec; @@ -1086,13 +1089,21 @@ __init void lguest_init(void) * lguest_init() where the rest of the fairly chaotic boot setup * occurs. */ + /* The stack protector is a weird thing where gcc places a canary + * value on the stack and then checks it on return. This file is + * compiled with -fno-stack-protector it, so we got this far without + * problems. The value of the canary is kept at offset 20 from the + * %gs register, so we need to set that up before calling C functions + * in other files. */ + setup_stack_canary_segment(0); + /* We could just call load_stack_canary_segment(), but we might as + * call switch_to_new_gdt() which loads the whole table and sets up + * the per-cpu segment descriptor register %fs as well. */ + switch_to_new_gdt(0); + /* As described in head_32.S, we map the first 128M of memory. */ max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; - /* Load the %fs segment register (the per-cpu segment register) with - * the normal data segment to get through booting. */ - asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory"); - /* The Host<->Guest Switcher lives at the top of our address space, and * the Host told us how big it is when we made LGUEST_INIT hypercall: * it put the answer in lguest_data.reserve_mem */ diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8f307d914c2..f46c340727b 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -26,12 +26,16 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma, unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + /* * match the virtual addresses, permission and the alignment of the * page table page. */ if (pmd_index(addr) != pmd_index(saddr) || - vma->vm_flags != svma->vm_flags || + vm_flags != svm_flags || sbase < svma->vm_start || svma->vm_end < s_end) return 0; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fd3da1dda1c..ae4f7b5d710 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -7,6 +7,7 @@ #include <asm/page.h> #include <asm/page_types.h> #include <asm/sections.h> +#include <asm/setup.h> #include <asm/system.h> #include <asm/tlbflush.h> @@ -304,8 +305,23 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, #endif #ifdef CONFIG_X86_64 - if (!after_bootmem) + if (!after_bootmem && !start) { + pud_t *pud; + pmd_t *pmd; + mmu_cr4_features = read_cr4(); + + /* + * _brk_end cannot change anymore, but it and _end may be + * located on different 2M pages. cleanup_highmap(), however, + * can only consider _end when it runs, so destroy any + * mappings beyond _brk_end here. + */ + pud = pud_offset(pgd_offset_k(_brk_end), _brk_end); + pmd = pmd_offset(pud, _brk_end - 1); + while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1)) + pmd_clear(pmd); + } #endif __flush_tlb_all(); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0dfa09d69e8..8a450930834 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -280,15 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return NULL; area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; - if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { + + if (kernel_map_sync_memtype(phys_addr, size, prot_val)) { free_memtype(phys_addr, phys_addr + size); free_vm_area(area); return NULL; } - if (ioremap_change_attr(vaddr, size, prot_val) < 0) { + if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { free_memtype(phys_addr, phys_addr + size); - vunmap(area->addr); + free_vm_area(area); return NULL; } @@ -374,7 +375,8 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, * - UC_MINUS for non-WB-able memory with no other conflicting mappings * - Inherit from confliting mappings otherwise */ - err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags); + err = reserve_memtype(phys_addr, phys_addr + size, + _PAGE_CACHE_WB, &flags); if (err < 0) return NULL; @@ -547,7 +549,7 @@ void __init early_ioremap_reset(void) } static void __init __early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *pte; @@ -566,7 +568,7 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, } static inline void __init early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t prot) + phys_addr_t phys, pgprot_t prot) { if (after_paging_init) __set_fixmap(idx, phys, prot); @@ -607,9 +609,10 @@ static int __init check_early_ioremap_leak(void) late_initcall(check_early_ioremap_leak); static void __init __iomem * -__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) { - unsigned long offset, last_addr; + unsigned long offset; + resource_size_t last_addr; unsigned int nrpages; enum fixed_addresses idx0, idx; int i, slot; @@ -625,15 +628,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } if (slot < 0) { - printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n", - phys_addr, size); + printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n", + (u64)phys_addr, size); WARN_ON(1); return NULL; } if (early_ioremap_debug) { - printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ", - phys_addr, size, slot); + printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ", + (u64)phys_addr, size, slot); dump_stack(); } @@ -680,13 +683,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } /* Remap an IO device */ -void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); } /* Remap memory */ -void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_memremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL); } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 4f115e00486..50dc802a1c4 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -87,7 +87,7 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr) { struct kmmio_probe *p; list_for_each_entry_rcu(p, &kmmio_probes, list) { - if (addr >= p->addr && addr <= (p->addr + p->len)) + if (addr >= p->addr && addr < (p->addr + p->len)) return p; } return NULL; diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 3daefa04ace..d2530062fe0 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -257,7 +257,7 @@ void resume_map_numa_kva(pgd_t *pgd_base) } #endif -static unsigned long calculate_numa_remap_pages(void) +static __init unsigned long calculate_numa_remap_pages(void) { int nid; unsigned long size, reserve_pages = 0; diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index d73aaa89237..2d05a12029d 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -188,6 +188,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE); int nid; + if (!end) + return; + start = roundup(start, ZONE_ALIGN); printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid, diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index d71e1b636ce..e17efed088c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -153,7 +153,7 @@ static void __cpa_flush_all(void *arg) */ __flush_tlb_all(); - if (cache && boot_cpu_data.x86_model >= 4) + if (cache && boot_cpu_data.x86 >= 4) wbinvd(); } @@ -208,20 +208,15 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, int in_flags, struct page **pages) { unsigned int i, level; + unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ BUG_ON(irqs_disabled()); - on_each_cpu(__cpa_flush_range, NULL, 1); + on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1); - if (!cache) + if (!cache || do_wbinvd) return; - /* 4M threshold */ - if (numpages >= 1024) { - if (boot_cpu_data.x86_model >= 4) - wbinvd(); - return; - } /* * We only need to flush on one CPU, * clflush is a MESI-coherent instruction that @@ -945,71 +940,94 @@ int _set_memory_uc(unsigned long addr, int numpages) int set_memory_uc(unsigned long addr, int numpages) { + int ret; + /* * for now UC MINUS. see comments in ioremap_nocache() */ - if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_UC_MINUS, NULL)) - return -EINVAL; + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_err; + + ret = _set_memory_uc(addr, numpages); + if (ret) + goto out_free; - return _set_memory_uc(addr, numpages); + return 0; + +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_uc); int set_memory_array_uc(unsigned long *addr, int addrinarray) { - unsigned long start; - unsigned long end; - int i; + int i, j; + int ret; + /* * for now UC MINUS. see comments in ioremap_nocache() */ for (i = 0; i < addrinarray; i++) { - start = __pa(addr[i]); - for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) - goto out; + ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_free; } - return change_page_attr_set(addr, addrinarray, + ret = change_page_attr_set(addr, addrinarray, __pgprot(_PAGE_CACHE_UC_MINUS), 1); -out: - for (i = 0; i < addrinarray; i++) { - unsigned long tmp = __pa(addr[i]); - - if (tmp == start) - break; - for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - free_memtype(tmp, end); - } - return -EINVAL; + if (ret) + goto out_free; + + return 0; + +out_free: + for (j = 0; j < i; j++) + free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE); + + return ret; } EXPORT_SYMBOL(set_memory_array_uc); int _set_memory_wc(unsigned long addr, int numpages) { - return change_page_attr_set(&addr, numpages, + int ret; + ret = change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_CACHE_UC_MINUS), 0); + + if (!ret) { + ret = change_page_attr_set(&addr, numpages, __pgprot(_PAGE_CACHE_WC), 0); + } + return ret; } int set_memory_wc(unsigned long addr, int numpages) { + int ret; + if (!pat_enabled) return set_memory_uc(addr, numpages); - if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_WC, NULL)) - return -EINVAL; + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_WC, NULL); + if (ret) + goto out_err; - return _set_memory_wc(addr, numpages); + ret = _set_memory_wc(addr, numpages); + if (ret) + goto out_free; + + return 0; + +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_wc); @@ -1021,29 +1039,31 @@ int _set_memory_wb(unsigned long addr, int numpages) int set_memory_wb(unsigned long addr, int numpages) { - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + int ret; + + ret = _set_memory_wb(addr, numpages); + if (ret) + return ret; - return _set_memory_wb(addr, numpages); + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + return 0; } EXPORT_SYMBOL(set_memory_wb); int set_memory_array_wb(unsigned long *addr, int addrinarray) { int i; + int ret; - for (i = 0; i < addrinarray; i++) { - unsigned long start = __pa(addr[i]); - unsigned long end; - - for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - free_memtype(start, end); - } - return change_page_attr_clear(addr, addrinarray, + ret = change_page_attr_clear(addr, addrinarray, __pgprot(_PAGE_CACHE_MASK), 1); + if (ret) + return ret; + + for (i = 0; i < addrinarray; i++) + free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE); + + return 0; } EXPORT_SYMBOL(set_memory_array_wb); @@ -1136,6 +1156,8 @@ int set_pages_array_wb(struct page **pages, int addrinarray) retval = cpa_clear_pages_array(pages, addrinarray, __pgprot(_PAGE_CACHE_MASK)); + if (retval) + return retval; for (i = 0; i < addrinarray; i++) { start = (unsigned long)page_address(pages[i]); @@ -1143,7 +1165,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray) free_memtype(start, end); } - return retval; + return 0; } EXPORT_SYMBOL(set_pages_array_wb); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 640339ee4fb..e6718bb2806 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -31,7 +31,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(const char *reason) +static inline void pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); @@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) u8 mtrr_type; mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == MTRR_TYPE_UNCACHABLE) - return _PAGE_CACHE_UC; - if (mtrr_type == MTRR_TYPE_WRCOMB) - return _PAGE_CACHE_WC; + if (mtrr_type != MTRR_TYPE_WRBACK) + return _PAGE_CACHE_UC_MINUS; + + return _PAGE_CACHE_WB; } return req_type; @@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return 0; } - if (req_type == -1) { - /* - * Call mtrr_lookup to get the type hint. This is an - * optimization for /dev/mem mmap'ers into WB memory (BIOS - * tools and ACPI tools). Use WB request for WB memory and use - * UC_MINUS otherwise. - */ - u8 mtrr_type = mtrr_type_lookup(start, end); - - if (mtrr_type == MTRR_TYPE_WRBACK) - actual_type = _PAGE_CACHE_WB; - else - actual_type = _PAGE_CACHE_UC_MINUS; - } else { - actual_type = pat_x_mtrr_type(start, end, - req_type & _PAGE_CACHE_MASK); - } + /* + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. + */ + actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK); if (new_type) *new_type = actual_type; @@ -546,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { - u64 offset = ((u64) pfn) << PAGE_SHIFT; - unsigned long flags = -1; - int retval; + unsigned long flags = _PAGE_CACHE_WB; if (!range_is_allowed(pfn, size)) return 0; @@ -576,64 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, } #endif - /* - * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot. - * - * Without O_SYNC, we want to get - * - WB for WB-able memory and no other conflicting mappings - * - UC_MINUS for non-WB-able memory with no other conflicting mappings - * - Inherit from confliting mappings otherwise - */ - if (flags != -1) { - retval = reserve_memtype(offset, offset + size, flags, NULL); - } else { - retval = reserve_memtype(offset, offset + size, -1, &flags); - } - - if (retval < 0) - return 0; - - if (((pfn < max_low_pfn_mapped) || - (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { - free_memtype(offset, offset + size); - printk(KERN_INFO - "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", - current->comm, current->pid, - cattr_name(flags), - offset, (unsigned long long)(offset + size)); - return 0; - } - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | flags); return 1; } -void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK); - u64 addr = (u64)pfn << PAGE_SHIFT; - unsigned long flags; - - reserve_memtype(addr, addr + size, want_flags, &flags); - if (flags != want_flags) { - printk(KERN_INFO - "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", - current->comm, current->pid, - cattr_name(want_flags), - addr, (unsigned long long)(addr + size), - cattr_name(flags)); - } -} - -void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - u64 addr = (u64)pfn << PAGE_SHIFT; - - free_memtype(addr, addr + size); -} - /* * Change the memory type for the physial address range in kernel identity * mapping space if that range is a part of identity map. @@ -671,8 +606,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, { int is_ram = 0; int ret; - unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); + unsigned long flags = want_flags; is_ram = pat_pagerange_is_ram(paddr, paddr + size); @@ -734,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size) * * If the vma has a linear pfn mapping for the entire range, we get the prot * from pte and reserve the entire vma range with single reserve_pfn_range call. - * Otherwise, we reserve the entire vma range, my ging through the PTEs page - * by page to get physical address and protection. */ int track_pfn_vma_copy(struct vm_area_struct *vma) { - int retval = 0; - unsigned long i, j; resource_size_t paddr; unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* * reserve the whole chunk covered by vma. We need the * starting address and protection from pte. */ - if (follow_phys(vma, vma_start, 0, &prot, &paddr)) { + if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { WARN_ON_ONCE(1); return -EINVAL; } @@ -764,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma) return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } - /* reserve entire vma page by page, using pfn and prot from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - pgprot = __pgprot(prot); - retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - if (follow_phys(vma, vma_start + j, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -795,50 +708,28 @@ cleanup_ret: * prot is passed in as a parameter for the new mapping. If the vma has a * linear pfn mapping for the entire range reserve the entire vma range with * single reserve_pfn_range call. - * Otherwise, we look t the pfn and size and reserve only the specified range - * page by page. - * - * Note that this function can be called with caller trying to map only a - * subrange/page inside the vma. */ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long size) { - int retval = 0; - unsigned long i, j; - resource_size_t base_paddr; resource_size_t paddr; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* reserve the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; return reserve_pfn_range(paddr, vma_size, prot, 0); } - /* reserve page by page using pfn and size */ - base_paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = base_paddr + i; - retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - paddr = base_paddr + j; - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -849,39 +740,23 @@ cleanup_ret: void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { - unsigned long i; resource_size_t paddr; - unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* free the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; free_pfn_range(paddr, vma_size); return; } - - if (size != 0 && size != vma_size) { - /* free page by page, using pfn and size */ - paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = paddr + i; - free_pfn_range(paddr, PAGE_SIZE); - } - } else { - /* free entire vma, page by page, using the pfn from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - } } pgprot_t pgprot_writecombine(pgprot_t prot) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 5b7c7c8464f..7aa03a5389f 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -345,7 +345,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) fixmaps_set++; } -void native_set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t flags) +void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, + pgprot_t flags) { __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index 16ae70fc57e..29a0e37114f 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -216,7 +216,7 @@ int __init get_memcfg_from_srat(void) if (num_memory_chunks == 0) { printk(KERN_WARNING - "could not finy any ACPI SRAT memory areas.\n"); + "could not find any ACPI SRAT memory areas.\n"); goto out_fail; } diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index c7d272b8574..01765955baa 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -28,6 +28,7 @@ int acpi_numa __initdata; static struct acpi_table_slit *acpi_slit; static nodemask_t nodes_parsed __initdata; +static nodemask_t cpu_nodes_parsed __initdata; static struct bootnode nodes[MAX_NUMNODES] __initdata; static struct bootnode nodes_add[MAX_NUMNODES]; static int found_add_area __initdata; @@ -141,6 +142,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) apic_id = pa->apic_id; apicid_to_node[apic_id] = node; + node_set(node, cpu_nodes_parsed); acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", pxm, apic_id, node); @@ -174,6 +176,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) else apic_id = pa->apic_id; apicid_to_node[apic_id] = node; + node_set(node, cpu_nodes_parsed); acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", pxm, apic_id, node); @@ -358,6 +361,7 @@ static void __init unparse_node(int node) { int i; node_clear(node, nodes_parsed); + node_clear(node, cpu_nodes_parsed); for (i = 0; i < MAX_LOCAL_APIC; i++) { if (apicid_to_node[i] == node) apicid_to_node[i] = NUMA_NO_NODE; @@ -402,7 +406,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) return -1; } - node_possible_map = nodes_parsed; + /* Account for nodes with cpus and no memory */ + nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed); /* Finally register nodes */ for_each_node_mask(i, node_possible_map) diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 04df67f8a7b..044897be021 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -76,9 +76,9 @@ void x86_backtrace(struct pt_regs * const regs, unsigned int depth) { struct frame_head *head = (struct frame_head *)frame_pointer(regs); - unsigned long stack = kernel_trap_sp(regs); if (!user_mode_vm(regs)) { + unsigned long stack = kernel_stack_pointer(regs); if (depth) dump_trace(NULL, regs, (unsigned long *)stack, 0, &backtrace_ops, &depth); diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 9bb09823b36..f893d6a6e80 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -94,12 +94,16 @@ struct pci_root_info { static int pci_root_num; static struct pci_root_info pci_root_info[PCI_ROOT_NR]; -void set_pci_bus_resources_arch_default(struct pci_bus *b) +void x86_pci_root_bus_res_quirks(struct pci_bus *b) { int i; int j; struct pci_root_info *info; + /* don't go for it if _CRS is used */ + if (pci_probe & PCI_USE__CRS) + return; + /* if only one root bus, don't need to anything */ if (pci_root_num < 2) return; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 8c362b96b64..2202b6257b8 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -147,10 +147,13 @@ static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) * are examined. */ -void __devinit pcibios_fixup_bus(struct pci_bus *b) +void __devinit pcibios_fixup_bus(struct pci_bus *b) { struct pci_dev *dev; + /* root bus? */ + if (!b->parent) + x86_pci_root_bus_res_quirks(b); pci_read_bridge_bases(b); list_for_each_entry(dev, &b->devices, bus_list) pcibios_fixup_device_resources(dev); diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index f1817f71e00..a85bef20a3b 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -238,6 +238,10 @@ void __init pcibios_resource_survey(void) */ fs_initcall(pcibios_assign_resources); +void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b) +{ +} + /* * If we set up a device for bus mastering, we need to check the latency * timer as certain crappy BIOSes forget to set it properly. diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 905bb526b13..5fa10bb9604 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -375,7 +375,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res, if (!fixmem32) return AE_OK; if ((mcfg_res->start >= fixmem32->address) && - (mcfg_res->end < (fixmem32->address + + (mcfg_res->end <= (fixmem32->address + fixmem32->address_length))) { mcfg_res->flags = 1; return AE_CTRL_TERMINATE; @@ -392,7 +392,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res, return AE_OK; if ((mcfg_res->start >= address.minimum) && - (mcfg_res->end < (address.minimum + address.address_length))) { + (mcfg_res->end <= (address.minimum + address.address_length))) { mcfg_res->flags = 1; return AE_CTRL_TERMINATE; } @@ -439,7 +439,7 @@ static int __init is_mmconf_reserved(check_reserved_t is_reserved, u64 old_size = size; int valid = 0; - while (!is_reserved(addr, addr + size - 1, E820_RESERVED)) { + while (!is_reserved(addr, addr + size, E820_RESERVED)) { size >>= 1; if (size < (16UL<<20)) break; diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index d9d35824c56..6a40b78b46a 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -104,11 +104,13 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { long ret; if (likely(gtod->sysctl_enabled && gtod->clock.vread)) { - BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != - offsetof(struct timespec, tv_nsec) || - sizeof(*tv) != sizeof(struct timespec)); - do_realtime((struct timespec *)tv); - tv->tv_usec /= 1000; + if (likely(tv != NULL)) { + BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != + offsetof(struct timespec, tv_nsec) || + sizeof(*tv) != sizeof(struct timespec)); + do_realtime((struct timespec *)tv); + tv->tv_usec /= 1000; + } if (unlikely(tz != NULL)) { /* Avoid memcpy. Some old compilers fail to inline it */ tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3b767d03fd6..172438f86a0 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -9,5 +9,6 @@ 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 -obj-$(CONFIG_SMP) += smp.o spinlock.o -obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
\ No newline at end of file +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o +obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 82cd39a6cbd..f09e8c36ee8 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -42,6 +42,7 @@ #include <asm/xen/hypervisor.h> #include <asm/fixmap.h> #include <asm/processor.h> +#include <asm/proto.h> #include <asm/msr-index.h> #include <asm/setup.h> #include <asm/desc.h> @@ -168,21 +169,23 @@ static void __init xen_banner(void) xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; +static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; + static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { + unsigned maskecx = ~0; unsigned maskedx = ~0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. */ - if (*ax == 1) - maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ - (1 << X86_FEATURE_ACPI) | /* disable ACPI */ - (1 << X86_FEATURE_MCE) | /* disable MCE */ - (1 << X86_FEATURE_MCA) | /* disable MCA */ - (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + if (*ax == 1) { + maskecx = cpuid_leaf1_ecx_mask; + maskedx = cpuid_leaf1_edx_mask; + } asm(XEN_EMULATE_PREFIX "cpuid" : "=a" (*ax), @@ -190,9 +193,43 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, "=c" (*cx), "=d" (*dx) : "0" (*ax), "2" (*cx)); + + *cx &= maskecx; *dx &= maskedx; } +static __init void xen_init_cpuid_mask(void) +{ + unsigned int ax, bx, cx, dx; + + cpuid_leaf1_edx_mask = + ~((1 << X86_FEATURE_MCE) | /* disable MCE */ + (1 << X86_FEATURE_MCA) | /* disable MCA */ + (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + + if (!xen_initial_domain()) + cpuid_leaf1_edx_mask &= + ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ + (1 << X86_FEATURE_ACPI)); /* disable ACPI */ + + ax = 1; + xen_cpuid(&ax, &bx, &cx, &dx); + + /* cpuid claims we support xsave; try enabling it to see what happens */ + if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { + unsigned long cr4; + + set_in_cr4(X86_CR4_OSXSAVE); + + cr4 = read_cr4(); + + if ((cr4 & X86_CR4_OSXSAVE) == 0) + cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); + + clear_in_cr4(X86_CR4_OSXSAVE); + } +} + static void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); @@ -284,12 +321,11 @@ static void xen_set_ldt(const void *addr, unsigned entries) static void xen_load_gdt(const struct desc_ptr *dtr) { - unsigned long *frames; unsigned long va = dtr->address; unsigned int size = dtr->size + 1; unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE; + unsigned long frames[pages]; int f; - struct multicall_space mcs; /* A GDT can be up to 64k in size, which corresponds to 8192 8-byte entries, or 16 4k pages.. */ @@ -297,19 +333,26 @@ static void xen_load_gdt(const struct desc_ptr *dtr) BUG_ON(size > 65536); BUG_ON(va & ~PAGE_MASK); - mcs = xen_mc_entry(sizeof(*frames) * pages); - frames = mcs.args; - for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - frames[f] = arbitrary_virt_to_mfn((void *)va); + int level; + pte_t *ptep = lookup_address(va, &level); + unsigned long pfn, mfn; + void *virt; + + BUG_ON(ptep == NULL); + + pfn = pte_pfn(*ptep); + mfn = pfn_to_mfn(pfn); + virt = __va(PFN_PHYS(pfn)); + + frames[f] = mfn; make_lowmem_page_readonly((void *)va); - make_lowmem_page_readonly(mfn_to_virt(frames[f])); + make_lowmem_page_readonly(virt); } - MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct)); - - xen_mc_issue(PARAVIRT_LAZY_CPU); + if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + BUG(); } static void load_TLS_descriptor(struct thread_struct *t, @@ -385,7 +428,7 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { - if (val->type != 0xf && val->type != 0xe) + if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT) return 0; info->vector = vector; @@ -393,8 +436,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, info->cs = gate_segment(*val); info->flags = val->dpl; /* interrupt gates clear IF */ - if (val->type == 0xe) - info->flags |= 4; + if (val->type == GATE_INTERRUPT) + info->flags |= 1 << 2; return 1; } @@ -872,7 +915,6 @@ static const struct machine_ops __initdata xen_machine_ops = { .emergency_restart = xen_emergency_restart, }; - /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { @@ -897,6 +939,8 @@ asmlinkage void __init xen_start_kernel(void) xen_init_irq_ops(); + xen_init_cpuid_mask(); + #ifdef CONFIG_X86_LOCAL_APIC /* * set up the basic apic ops. @@ -938,6 +982,11 @@ asmlinkage void __init xen_start_kernel(void) if (!xen_initial_domain()) __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); +#ifdef CONFIG_X86_64 + /* Work out if we support NX */ + check_efer(); +#endif + /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index db3802fb7b8..fba55b1a402 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,6 +42,7 @@ #include <linux/highmem.h> #include <linux/debugfs.h> #include <linux/bug.h> +#include <linux/module.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -184,7 +185,7 @@ static inline unsigned p2m_index(unsigned long pfn) } /* Build the parallel p2m_top_mfn structures */ -void xen_setup_mfn_list_list(void) +static void __init xen_build_mfn_list_list(void) { unsigned pfn, idx; @@ -198,7 +199,10 @@ void xen_setup_mfn_list_list(void) unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); } +} +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 = @@ -218,6 +222,8 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_top[topidx] = &mfn_list[pfn]; } + + xen_build_mfn_list_list(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -233,47 +239,74 @@ unsigned long get_phys_to_machine(unsigned long pfn) } EXPORT_SYMBOL_GPL(get_phys_to_machine); -static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +/* install a new p2m_top page */ +bool install_p2mtop_page(unsigned long pfn, unsigned long *p) { - unsigned long *p; + unsigned topidx = p2m_top_index(pfn); + unsigned long **pfnp, *mfnp; unsigned i; - p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); - BUG_ON(p == NULL); + pfnp = &p2m_top[topidx]; + mfnp = &p2m_top_mfn[topidx]; for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++) p[i] = INVALID_P2M_ENTRY; - if (cmpxchg(pp, p2m_missing, p) != p2m_missing) - free_page((unsigned long)p); - else + if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) { *mfnp = virt_to_mfn(p); + return true; + } + + return false; } -void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +static void alloc_p2m(unsigned long pfn) { - unsigned topidx, idx; + unsigned long *p; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return; - } + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + if (!install_p2mtop_page(pfn, p)) + free_page((unsigned long)p); +} + +/* Try to install p2m mapping; fail if intermediate bits missing */ +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { BUG_ON(mfn != INVALID_P2M_ENTRY); - return; + return true; } topidx = p2m_top_index(pfn); if (p2m_top[topidx] == p2m_missing) { - /* no need to allocate a page to store an invalid entry */ if (mfn == INVALID_P2M_ENTRY) - return; - alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + return true; + return false; } idx = p2m_index(pfn); p2m_top[topidx][idx] = mfn; + + return true; +} + +void 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; + } + + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + alloc_p2m(pfn); + + if (!__set_phys_to_machine(pfn, mfn)) + BUG(); + } } unsigned long arbitrary_virt_to_mfn(void *vaddr) @@ -987,7 +1020,7 @@ static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page, return 0; } -void __init xen_mark_init_mm_pinned(void) +static void __init xen_mark_init_mm_pinned(void) { xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1270,8 +1303,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - BUG_ON(cpumask_empty(cpus)); - BUG_ON(!mm); + if (cpumask_empty(cpus)) + return; /* nothing to do */ mcs = xen_mc_entry(sizeof(*args)); args = mcs.args; @@ -1438,6 +1471,15 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) } #endif +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1446,22 +1488,29 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) BUG_ON(mem_map); /* should only be used early */ #endif make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); +} + +/* Used for pmd and pud */ +static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn) +{ +#ifdef CONFIG_FLATMEM + BUG_ON(mem_map); /* should only be used early */ +#endif + make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); } /* Early release_pte assumes that all pts are pinned, since there's only init_mm and anything attached to that is pinned. */ -static void xen_release_pte_init(unsigned long pfn) +static __init void xen_release_pte_init(unsigned long pfn) { + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +static __init void xen_release_pmd_init(unsigned long pfn) { - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } /* This needs to make sure the new pte page is pinned iff its being @@ -1746,11 +1795,16 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + reserve_early(__pa(xen_start_info->pt_base), + __pa(xen_start_info->pt_base + + xen_start_info->nr_pt_frames * PAGE_SIZE), + "XEN PAGETABLES"); + return swapper_pg_dir; } #endif /* CONFIG_X86_64 */ -static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) +static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) { pte_t pte; @@ -1773,6 +1827,9 @@ static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) #ifdef CONFIG_X86_LOCAL_APIC case FIX_APIC_BASE: /* maps dummy local APIC */ #endif + case FIX_TEXT_POKE0: + case FIX_TEXT_POKE1: + /* All local page mappings */ pte = pfn_pte(phys, prot); break; @@ -1819,7 +1876,6 @@ __init void xen_post_allocator_init(void) xen_mark_init_mm_pinned(); } - const struct pv_mmu_ops xen_mmu_ops __initdata = { .pagetable_setup_start = xen_pagetable_setup_start, .pagetable_setup_done = xen_pagetable_setup_done, @@ -1843,9 +1899,9 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .alloc_pte = xen_alloc_pte_init, .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pte_init, + .alloc_pmd = xen_alloc_pmd_init, .alloc_pmd_clone = paravirt_nop, - .release_pmd = xen_release_pte_init, + .release_pmd = xen_release_pmd_init, #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = xen_kmap_atomic_pte, @@ -1883,8 +1939,8 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_pgd = xen_set_pgd_hyper, - .alloc_pud = xen_alloc_pte_init, - .release_pud = xen_release_pte_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #endif /* PAGETABLE_LEVELS == 4 */ .activate_mm = xen_activate_mm, diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 24d1b44a337..da730262489 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -11,6 +11,9 @@ enum pt_level { }; +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool install_p2mtop_page(unsigned long pfn, unsigned long *p); + void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 585a6e33083..429834ec168 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -317,7 +317,7 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) BUG_ON(rc); while(per_cpu(cpu_state, cpu) != CPU_ONLINE) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); barrier(); } @@ -422,7 +422,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask) /* Make sure other vcpus get a chance to run if they need to. */ for_each_cpu(cpu, mask) { if (xen_vcpu_stolen(cpu)) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); break; } } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 14f24062349..0a5aa44299a 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -213,6 +213,11 @@ cycle_t xen_clocksource_read(void) return ret; } +static cycle_t xen_clocksource_get_cycles(struct clocksource *cs) +{ + return xen_clocksource_read(); +} + static void xen_read_wallclock(struct timespec *ts) { struct shared_info *s = HYPERVISOR_shared_info; @@ -241,7 +246,7 @@ int xen_set_wallclock(unsigned long now) static struct clocksource xen_clocksource __read_mostly = { .name = "xen", .rating = 400, - .read = xen_clocksource_read, + .read = xen_clocksource_get_cycles, .mask = ~0, .mult = 1<<XEN_SHIFT, /* time directly in nanoseconds */ .shift = XEN_SHIFT, diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 2f5ef2632ea..ca6596b05d5 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -57,22 +57,31 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id); bool xen_vcpu_stolen(int vcpu); -void xen_mark_init_mm_pinned(void); - void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP void xen_smp_init(void); -void __init xen_init_spinlocks(void); -__cpuinit void xen_init_lock_cpu(int cpu); -void xen_uninit_lock_cpu(int cpu); - extern cpumask_var_t xen_cpu_initialized_map; #else static inline void xen_smp_init(void) {} #endif +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init xen_init_spinlocks(void); +__cpuinit void xen_init_lock_cpu(int cpu); +void xen_uninit_lock_cpu(int cpu); +#else +static inline void xen_init_spinlocks(void) +{ +} +static inline void xen_init_lock_cpu(int cpu) +{ +} +static inline void xen_uninit_lock_cpu(int cpu) +{ +} +#endif /* Declare an asm function, along with symbols needed to make it inlineable */ |