diff options
Diffstat (limited to 'arch/x86')
60 files changed, 1188 insertions, 1154 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0896008f7509..f15f37bfbd62 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -31,6 +31,7 @@ config X86 select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS select HAVE_KRETPROBES + select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER @@ -184,6 +185,9 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y +config HAVE_EARLY_RES + def_bool y + config HAVE_INTEL_TXT def_bool y depends on EXPERIMENTAL && DMAR && ACPI @@ -569,6 +573,18 @@ config PARAVIRT_DEBUG Enable to debug paravirt_ops internals. Specifically, BUG if a paravirt_op is missing when it is called. +config NO_BOOTMEM + default y + bool "Disable Bootmem code" + ---help--- + Use early_res directly instead of bootmem before slab is ready. + - allocator (buddy) [generic] + - early allocator (bootmem) [generic] + - very early allocator (reserve_early*()) [x86] + - very very early allocator (early brk model) [x86] + So reduce one layer between early allocator to final allocator + + config MEMTEST bool "Memtest" ---help--- diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 9046e4af66ce..280c019cfad8 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -327,7 +327,6 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) current->mm->free_area_cache = TASK_UNMAPPED_BASE; current->mm->cached_hole_size = 0; - current->mm->mmap = NULL; install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index f1e253ceba4b..b09ec55650b3 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -165,10 +165,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, * invalid instruction possible) or if the instructions are changed from a * consistent state to another consistent state atomically. * More care must be taken when modifying code in the SMP case because of - * Intel's errata. + * Intel's errata. text_poke_smp() takes care that errata, but still + * doesn't support NMI/MCE handler code modifying. * On the local CPU you need to be protected again NMI or MCE handlers seeing an * inconsistent instruction while you patch. */ extern void *text_poke(void *addr, const void *opcode, size_t len); +extern void *text_poke_smp(void *addr, const void *opcode, size_t len); #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 761249e396fe..0e22296790d3 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -111,11 +111,8 @@ extern unsigned long end_user_pfn; extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align); extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align); -extern void reserve_early(u64 start, u64 end, char *name); -extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); -extern void free_early(u64 start, u64 end); -extern void early_res_to_bootmem(u64 start, u64 end); extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); +#include <linux/early_res.h> extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 014c2b85ae45..a726650fc80f 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -66,10 +66,6 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); -#ifndef CONFIG_PARAVIRT -#define kmap_atomic_pte(page, type) kmap_atomic(page, type) -#endif - #define flush_cache_kmaps() do { } while (0) extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn, diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index 58d7091eeb1f..7ec65b18085d 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -24,7 +24,7 @@ extern unsigned int cached_irq_mask; #define SLAVE_ICW4_DEFAULT 0x01 #define PIC_ICW4_AEOI 2 -extern spinlock_t i8259A_lock; +extern raw_spinlock_t i8259A_lock; extern void init_8259A(int auto_eoi); extern void enable_8259A_irq(unsigned int irq); diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 7c7c16cde1f8..5f61f6e0ffdd 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -160,6 +160,7 @@ extern int io_apic_get_redir_entries(int ioapic); struct io_apic_irq_attr; extern int io_apic_set_pci_routing(struct device *dev, int irq, struct io_apic_irq_attr *irq_attr); +void setup_IO_APIC_irq_extra(u32 gsi); extern int (*ioapic_renumber_irq)(int ioapic, int irq); extern void ioapic_init_mappings(void); extern void ioapic_insert_resources(void); diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 5458380b6ef8..262292729fc4 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -48,5 +48,6 @@ extern DECLARE_BITMAP(used_vectors, NR_VECTORS); extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); +extern int nr_legacy_irqs; #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 4611f085cd43..8767d99c4f64 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -28,28 +28,33 @@ #define MCE_VECTOR 0x12 /* - * IDT vectors usable for external interrupt sources start - * at 0x20: + * IDT vectors usable for external interrupt sources start at 0x20. + * (0x80 is the syscall vector, 0x30-0x3f are for ISA) */ #define FIRST_EXTERNAL_VECTOR 0x20 - -#ifdef CONFIG_X86_32 -# define SYSCALL_VECTOR 0x80 -# define IA32_SYSCALL_VECTOR 0x80 -#else -# define IA32_SYSCALL_VECTOR 0x80 -#endif +/* + * We start allocating at 0x21 to spread out vectors evenly between + * priority levels. (0x80 is the syscall vector) + */ +#define VECTOR_OFFSET_START 1 /* - * Reserve the lowest usable priority level 0x20 - 0x2f for triggering - * cleanup after irq migration. + * Reserve the lowest usable vector (and hence lowest priority) 0x20 for + * triggering cleanup after irq migration. 0x21-0x2f will still be used + * for device interrupts. */ #define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR +#define IA32_SYSCALL_VECTOR 0x80 +#ifdef CONFIG_X86_32 +# define SYSCALL_VECTOR 0x80 +#endif + /* * Vectors 0x30-0x3f are used for ISA interrupts. + * round up to the next 16-vector boundary */ -#define IRQ0_VECTOR (FIRST_EXTERNAL_VECTOR + 0x10) +#define IRQ0_VECTOR ((FIRST_EXTERNAL_VECTOR + 16) & ~15) #define IRQ1_VECTOR (IRQ0_VECTOR + 1) #define IRQ2_VECTOR (IRQ0_VECTOR + 2) @@ -120,13 +125,6 @@ */ #define MCE_SELF_VECTOR 0xeb -/* - * First APIC vector available to drivers: (vectors 0x30-0xee) we - * start at 0x31(0x41) to spread out vectors evenly between priority - * levels. (0x80 is the syscall vector) - */ -#define FIRST_DEVICE_VECTOR (IRQ15_VECTOR + 2) - #define NR_VECTORS 256 #define FPU_IRQ 13 @@ -154,21 +152,21 @@ static inline int invalid_vm86_irq(int irq) #define NR_IRQS_LEGACY 16 -#define CPU_VECTOR_LIMIT ( 8 * NR_CPUS ) #define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS ) #ifdef CONFIG_X86_IO_APIC # ifdef CONFIG_SPARSE_IRQ +# define CPU_VECTOR_LIMIT (64 * NR_CPUS) # define NR_IRQS \ (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \ (NR_VECTORS + CPU_VECTOR_LIMIT) : \ (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) # else -# if NR_CPUS < MAX_IO_APICS -# define NR_IRQS (NR_VECTORS + 4*CPU_VECTOR_LIMIT) -# else -# define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT) -# endif +# define CPU_VECTOR_LIMIT (32 * NR_CPUS) +# define NR_IRQS \ + (CPU_VECTOR_LIMIT < IO_APIC_VECTOR_LIMIT ? \ + (NR_VECTORS + CPU_VECTOR_LIMIT) : \ + (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) # endif #else /* !CONFIG_X86_IO_APIC: */ # define NR_IRQS NR_IRQS_LEGACY diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4fe681de1e76..4ffa345a8ccb 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -32,7 +32,10 @@ struct kprobe; typedef u8 kprobe_opcode_t; #define BREAKPOINT_INSTRUCTION 0xcc -#define RELATIVEJUMP_INSTRUCTION 0xe9 +#define RELATIVEJUMP_OPCODE 0xe9 +#define RELATIVEJUMP_SIZE 5 +#define RELATIVECALL_OPCODE 0xe8 +#define RELATIVE_ADDR_SIZE 4 #define MAX_INSN_SIZE 16 #define MAX_STACK_SIZE 64 #define MIN_STACK_SIZE(ADDR) \ @@ -44,6 +47,17 @@ typedef u8 kprobe_opcode_t; #define flush_insn_slot(p) do { } while (0) +/* optinsn template addresses */ +extern kprobe_opcode_t optprobe_template_entry; +extern kprobe_opcode_t optprobe_template_val; +extern kprobe_opcode_t optprobe_template_call; +extern kprobe_opcode_t optprobe_template_end; +#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) +#define MAX_OPTINSN_SIZE \ + (((unsigned long)&optprobe_template_end - \ + (unsigned long)&optprobe_template_entry) + \ + MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE) + extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); @@ -64,6 +78,21 @@ struct arch_specific_insn { int boostable; }; +struct arch_optimized_insn { + /* copy of the original instructions */ + kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE]; + /* detour code buffer */ + kprobe_opcode_t *insn; + /* the size of instructions copied to detour code buffer */ + size_t size; +}; + +/* Return true (!0) if optinsn is prepared for optimization. */ +static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn) +{ + return optinsn->size; +} + struct prev_kprobe { struct kprobe *kp; unsigned long status; diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 47b9b6f19057..2e9972468a5d 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -195,41 +195,4 @@ static inline long local_sub_return(long i, local_t *l) #define __local_add(i, l) local_add((i), (l)) #define __local_sub(i, l) local_sub((i), (l)) -/* Use these for per-cpu local_t variables: on some archs they are - * much more efficient than these naive implementations. Note they take - * a variable, not an address. - * - * X86_64: This could be done better if we moved the per cpu data directly - * after GS. - */ - -/* Need to disable preemption for the cpu local counters otherwise we could - still access a variable of a previous CPU in a non atomic way. */ -#define cpu_local_wrap_v(l) \ -({ \ - local_t res__; \ - preempt_disable(); \ - res__ = (l); \ - preempt_enable(); \ - res__; \ -}) -#define cpu_local_wrap(l) \ -({ \ - preempt_disable(); \ - (l); \ - preempt_enable(); \ -}) \ - -#define cpu_local_read(l) cpu_local_wrap_v(local_read(&__get_cpu_var((l)))) -#define cpu_local_set(l, i) cpu_local_wrap(local_set(&__get_cpu_var((l)), (i))) -#define cpu_local_inc(l) cpu_local_wrap(local_inc(&__get_cpu_var((l)))) -#define cpu_local_dec(l) cpu_local_wrap(local_dec(&__get_cpu_var((l)))) -#define cpu_local_add(i, l) cpu_local_wrap(local_add((i), &__get_cpu_var((l)))) -#define cpu_local_sub(i, l) cpu_local_wrap(local_sub((i), &__get_cpu_var((l)))) - -#define __cpu_local_inc(l) cpu_local_inc((l)) -#define __cpu_local_dec(l) cpu_local_dec((l)) -#define __cpu_local_add(i, l) cpu_local_add((i), (l)) -#define __cpu_local_sub(i, l) cpu_local_sub((i), (l)) - #endif /* _ASM_X86_LOCAL_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index dd59a85a918f..5653f43d90e5 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -435,15 +435,6 @@ static inline void paravirt_release_pud(unsigned long pfn) PVOP_VCALL1(pv_mmu_ops.release_pud, pfn); } -#ifdef CONFIG_HIGHPTE -static inline void *kmap_atomic_pte(struct page *page, enum km_type type) -{ - unsigned long ret; - ret = PVOP_CALL2(unsigned long, pv_mmu_ops.kmap_atomic_pte, page, type); - return (void *)ret; -} -#endif - static inline void pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b1e70d51e40c..db9ef5532341 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -304,10 +304,6 @@ struct pv_mmu_ops { #endif /* PAGETABLE_LEVELS == 4 */ #endif /* PAGETABLE_LEVELS >= 3 */ -#ifdef CONFIG_HIGHPTE - void *(*kmap_atomic_pte)(struct page *page, enum km_type type); -#endif - struct pv_lazy_ops lazy_mode; /* dom0 ops */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index ada8c201d513..b4a00dd4eed5 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -124,6 +124,8 @@ extern void pci_iommu_alloc(void); #include "pci_64.h" #endif +void dma32_reserve_bootmem(void); + /* implement the pci_ DMA API in terms of the generic device dma_ one */ #include <asm-generic/pci-dma-compat.h> diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index ae5e40f67daf..fe15cfb21b9b 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -22,8 +22,6 @@ extern int (*pci_config_read)(int seg, int bus, int dev, int fn, extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int len, u32 value); -extern void dma32_reserve_bootmem(void); - #endif /* __KERNEL__ */ #endif /* _ASM_X86_PCI_64_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 0c44196b78ac..66a272dfd8b8 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -25,19 +25,18 @@ */ #ifdef CONFIG_SMP #define PER_CPU(var, reg) \ - __percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg; \ - lea per_cpu__##var(reg), reg -#define PER_CPU_VAR(var) %__percpu_seg:per_cpu__##var + __percpu_mov_op %__percpu_seg:this_cpu_off, reg; \ + lea var(reg), reg +#define PER_CPU_VAR(var) %__percpu_seg:var #else /* ! SMP */ -#define PER_CPU(var, reg) \ - __percpu_mov_op $per_cpu__##var, reg -#define PER_CPU_VAR(var) per_cpu__##var +#define PER_CPU(var, reg) __percpu_mov_op $var, reg +#define PER_CPU_VAR(var) var #endif /* SMP */ #ifdef CONFIG_X86_64_SMP #define INIT_PER_CPU_VAR(var) init_per_cpu__##var #else -#define INIT_PER_CPU_VAR(var) per_cpu__##var +#define INIT_PER_CPU_VAR(var) var #endif #else /* ...!ASSEMBLY */ @@ -60,12 +59,12 @@ * There also must be an entry in vmlinux_64.lds.S */ #define DECLARE_INIT_PER_CPU(var) \ - extern typeof(per_cpu_var(var)) init_per_cpu_var(var) + extern typeof(var) init_per_cpu_var(var) #ifdef CONFIG_X86_64_SMP #define init_per_cpu_var(var) init_per_cpu__##var #else -#define init_per_cpu_var(var) per_cpu_var(var) +#define init_per_cpu_var(var) var #endif /* For arch-specific code, we can use direct single-insn ops (they @@ -104,6 +103,64 @@ do { \ } \ } while (0) +/* + * Generate a percpu add to memory instruction and optimize code + * if a one is added or subtracted. + */ +#define percpu_add_op(var, val) \ +do { \ + typedef typeof(var) pao_T__; \ + const int pao_ID__ = (__builtin_constant_p(val) && \ + ((val) == 1 || (val) == -1)) ? (val) : 0; \ + if (0) { \ + pao_T__ pao_tmp__; \ + pao_tmp__ = (val); \ + } \ + switch (sizeof(var)) { \ + case 1: \ + if (pao_ID__ == 1) \ + asm("incb "__percpu_arg(0) : "+m" (var)); \ + else if (pao_ID__ == -1) \ + asm("decb "__percpu_arg(0) : "+m" (var)); \ + else \ + asm("addb %1, "__percpu_arg(0) \ + : "+m" (var) \ + : "qi" ((pao_T__)(val))); \ + break; \ + case 2: \ + if (pao_ID__ == 1) \ + asm("incw "__percpu_arg(0) : "+m" (var)); \ + else if (pao_ID__ == -1) \ + asm("decw "__percpu_arg(0) : "+m" (var)); \ + else \ + asm("addw %1, "__percpu_arg(0) \ + : "+m" (var) \ + : "ri" ((pao_T__)(val))); \ + break; \ + case 4: \ + if (pao_ID__ == 1) \ + asm("incl "__percpu_arg(0) : "+m" (var)); \ + else if (pao_ID__ == -1) \ + asm("decl "__percpu_arg(0) : "+m" (var)); \ + else \ + asm("addl %1, "__percpu_arg(0) \ + : "+m" (var) \ + : "ri" ((pao_T__)(val))); \ + break; \ + case 8: \ + if (pao_ID__ == 1) \ + asm("incq "__percpu_arg(0) : "+m" (var)); \ + else if (pao_ID__ == -1) \ + asm("decq "__percpu_arg(0) : "+m" (var)); \ + else \ + asm("addq %1, "__percpu_arg(0) \ + : "+m" (var) \ + : "re" ((pao_T__)(val))); \ + break; \ + default: __bad_percpu_size(); \ + } \ +} while (0) + #define percpu_from_op(op, var, constraint) \ ({ \ typeof(var) pfo_ret__; \ @@ -142,16 +199,14 @@ do { \ * per-thread variables implemented as per-cpu variables and thus * stable for the duration of the respective task. */ -#define percpu_read(var) percpu_from_op("mov", per_cpu__##var, \ - "m" (per_cpu__##var)) -#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var, \ - "p" (&per_cpu__##var)) -#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val) -#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val) -#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val) -#define percpu_and(var, val) percpu_to_op("and", per_cpu__##var, val) -#define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val) -#define percpu_xor(var, val) percpu_to_op("xor", per_cpu__##var, val) +#define percpu_read(var) percpu_from_op("mov", var, "m" (var)) +#define percpu_read_stable(var) percpu_from_op("mov", var, "p" (&(var))) +#define percpu_write(var, val) percpu_to_op("mov", var, val) +#define percpu_add(var, val) percpu_add_op(var, val) +#define percpu_sub(var, val) percpu_add_op(var, -(val)) +#define percpu_and(var, val) percpu_to_op("and", var, val) +#define percpu_or(var, val) percpu_to_op("or", var, val) +#define percpu_xor(var, val) percpu_to_op("xor", var, val) #define __this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define __this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) @@ -160,9 +215,9 @@ do { \ #define __this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) #define __this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) #define __this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) -#define __this_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val) -#define __this_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val) -#define __this_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val) +#define __this_cpu_add_1(pcp, val) percpu_add_op((pcp), val) +#define __this_cpu_add_2(pcp, val) percpu_add_op((pcp), val) +#define __this_cpu_add_4(pcp, val) percpu_add_op((pcp), val) #define __this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) #define __this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) #define __this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) @@ -179,9 +234,9 @@ do { \ #define this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) #define this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) #define this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) -#define this_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val) -#define this_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val) -#define this_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val) +#define this_cpu_add_1(pcp, val) percpu_add_op((pcp), val) +#define this_cpu_add_2(pcp, val) percpu_add_op((pcp), val) +#define this_cpu_add_4(pcp, val) percpu_add_op((pcp), val) #define this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) #define this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) #define this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) @@ -192,9 +247,9 @@ do { \ #define this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) #define this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) -#define irqsafe_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val) -#define irqsafe_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val) -#define irqsafe_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val) +#define irqsafe_cpu_add_1(pcp, val) percpu_add_op((pcp), val) +#define irqsafe_cpu_add_2(pcp, val) percpu_add_op((pcp), val) +#define irqsafe_cpu_add_4(pcp, val) percpu_add_op((pcp), val) #define irqsafe_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) #define irqsafe_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) #define irqsafe_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) @@ -212,19 +267,19 @@ do { \ #ifdef CONFIG_X86_64 #define __this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define __this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) -#define __this_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val) +#define __this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) #define __this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) -#define this_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val) +#define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) #define this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) -#define irqsafe_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val) +#define irqsafe_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define irqsafe_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define irqsafe_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) #define irqsafe_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) @@ -236,7 +291,7 @@ do { \ ({ \ int old__; \ asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0" \ - : "=r" (old__), "+m" (per_cpu__##var) \ + : "=r" (old__), "+m" (var) \ : "dIr" (bit)); \ old__; \ }) diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 01fd9461d323..47339a1ac7b6 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -54,10 +54,10 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t); in_irq() ? KM_IRQ_PTE : \ KM_PTE0) #define pte_offset_map(dir, address) \ - ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), __KM_PTE) + \ + ((pte_t *)kmap_atomic(pmd_page(*(dir)), __KM_PTE) + \ pte_index((address))) #define pte_offset_map_nested(dir, address) \ - ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) + \ + ((pte_t *)kmap_atomic(pmd_page(*(dir)), KM_PTE1) + \ pte_index((address))) #define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE) #define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1) @@ -80,7 +80,7 @@ do { \ * The i386 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ -#define update_mmu_cache(vma, address, pte) do { } while (0) +#define update_mmu_cache(vma, address, ptep) do { } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index c57a30117149..181be528c612 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -129,7 +129,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define pte_unmap(pte) /* NOP */ #define pte_unmap_nested(pte) /* NOP */ -#define update_mmu_cache(vma, address, pte) do { } while (0) +#define update_mmu_cache(vma, address, ptep) do { } while (0) /* Encode and de-code a swap entry */ #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 4009f6534f52..6f414ed88620 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -23,14 +23,4 @@ extern int reboot_force; long do_arch_prctl(struct task_struct *task, int code, unsigned long addr); -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x,y) ((__typeof__(x))((y)-1)) -#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1) -#define round_down(x,y) ((x) & ~__round_mask(x,y)) - #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index e04740f7a0bb..b8fe48ee2ed9 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -32,7 +32,7 @@ extern void show_regs_common(void); "movl %P[task_canary](%[next]), %%ebx\n\t" \ "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" #define __switch_canary_oparam \ - , [stack_canary] "=m" (per_cpu_var(stack_canary.canary)) + , [stack_canary] "=m" (stack_canary.canary) #define __switch_canary_iparam \ , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) #else /* CC_STACKPROTECTOR */ @@ -114,7 +114,7 @@ do { \ "movq %P[task_canary](%%rsi),%%r8\n\t" \ "movq %%r8,"__percpu_arg([gs_canary])"\n\t" #define __switch_canary_oparam \ - , [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary)) + , [gs_canary] "=m" (irq_stack_union.stack_canary) #define __switch_canary_iparam \ , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) #else /* CC_STACKPROTECTOR */ @@ -133,7 +133,7 @@ do { \ __switch_canary \ "movq %P[thread_info](%%rsi),%%r8\n\t" \ "movq %%rax,%%rdi\n\t" \ - "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ + "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ "jnz ret_from_fork\n\t" \ RESTORE_CONTEXT \ : "=a" (last) \ @@ -143,7 +143,7 @@ do { \ [ti_flags] "i" (offsetof(struct thread_info, flags)), \ [_tif_fork] "i" (_TIF_FORK), \ [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [current_task] "m" (per_cpu_var(current_task)) \ + [current_task] "m" (current_task) \ __switch_canary_iparam \ : "memory", "cc" __EXTRA_CLOBBER) #endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index f95703098f8d..738fcb60e708 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -447,6 +447,12 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) { *irq = gsi; + +#ifdef CONFIG_X86_IO_APIC + if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) + setup_IO_APIC_irq_extra(gsi); +#endif + return 0; } @@ -474,7 +480,8 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity); } #endif - acpi_gsi_to_irq(plat_gsi, &irq); + irq = plat_gsi; + return irq; } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e6ea0342c8f8..3a4bf35c179b 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/memory.h> +#include <linux/stop_machine.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -572,3 +573,62 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) local_irq_restore(flags); return addr; } + +/* + * Cross-modifying kernel text with stop_machine(). + * This code originally comes from immediate value. + */ +static atomic_t stop_machine_first; +static int wrote_text; + +struct text_poke_params { + void *addr; + const void *opcode; + size_t len; +}; + +static int __kprobes stop_machine_text_poke(void *data) +{ + struct text_poke_params *tpp = data; + + if (atomic_dec_and_test(&stop_machine_first)) { + text_poke(tpp->addr, tpp->opcode, tpp->len); + smp_wmb(); /* Make sure other cpus see that this has run */ + wrote_text = 1; + } else { + while (!wrote_text) + cpu_relax(); + smp_mb(); /* Load wrote_text before following execution */ + } + + flush_icache_range((unsigned long)tpp->addr, + (unsigned long)tpp->addr + tpp->len); + return 0; +} + +/** + * text_poke_smp - Update instructions on a live kernel on SMP + * @addr: address to modify + * @opcode: source of the copy + * @len: length to copy + * + * Modify multi-byte instruction by using stop_machine() on SMP. This allows + * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying + * should be allowed, since stop_machine() does _not_ protect code against + * NMI and MCE. + * + * Note: Must be called under get_online_cpus() and text_mutex. + */ +void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) +{ + struct text_poke_params tpp; + + tpp.addr = addr; + tpp.opcode = opcode; + tpp.len = len; + atomic_set(&stop_machine_first, 1); + wrote_text = 0; + stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); + return addr; +} + diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 6bdd2c7ead75..14862f11cc4a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -73,8 +73,8 @@ */ int sis_apic_bug = -1; -static DEFINE_SPINLOCK(ioapic_lock); -static DEFINE_SPINLOCK(vector_lock); +static DEFINE_RAW_SPINLOCK(ioapic_lock); +static DEFINE_RAW_SPINLOCK(vector_lock); /* * # of IRQ routing registers @@ -94,8 +94,6 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; /* # of MP IRQ source entries */ int mp_irq_entries; -/* Number of legacy interrupts */ -static int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY; /* GSI interrupts */ static int nr_irqs_gsi = NR_IRQS_LEGACY; @@ -140,27 +138,10 @@ static struct irq_pin_list *get_one_free_irq_2_pin(int node) /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */ #ifdef CONFIG_SPARSE_IRQ -static struct irq_cfg irq_cfgx[] = { +static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY]; #else -static struct irq_cfg irq_cfgx[NR_IRQS] = { +static struct irq_cfg irq_cfgx[NR_IRQS]; #endif - [0] = { .vector = IRQ0_VECTOR, }, - [1] = { .vector = IRQ1_VECTOR, }, - [2] = { .vector = IRQ2_VECTOR, }, - [3] = { .vector = IRQ3_VECTOR, }, - [4] = { .vector = IRQ4_VECTOR, }, - [5] = { .vector = IRQ5_VECTOR, }, - [6] = { .vector = IRQ6_VECTOR, }, - [7] = { .vector = IRQ7_VECTOR, }, - [8] = { .vector = IRQ8_VECTOR, }, - [9] = { .vector = IRQ9_VECTOR, }, - [10] = { .vector = IRQ10_VECTOR, }, - [11] = { .vector = IRQ11_VECTOR, }, - [12] = { .vector = IRQ12_VECTOR, }, - [13] = { .vector = IRQ13_VECTOR, }, - [14] = { .vector = IRQ14_VECTOR, }, - [15] = { .vector = IRQ15_VECTOR, }, -}; void __init io_apic_disable_legacy(void) { @@ -185,8 +166,14 @@ int __init arch_early_irq_init(void) desc->chip_data = &cfg[i]; zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node); zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node); - if (i < nr_legacy_irqs) - cpumask_setall(cfg[i].domain); + /* + * For legacy IRQ's, start with assigning irq0 to irq15 to + * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0. + */ + if (i < nr_legacy_irqs) { + cfg[i].vector = IRQ0_VECTOR + i; + cpumask_set_cpu(0, cfg[i].domain); + } } return 0; @@ -406,7 +393,7 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) struct irq_pin_list *entry; unsigned long flags; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); for_each_irq_pin(entry, cfg->irq_2_pin) { unsigned int reg; int pin; @@ -415,11 +402,11 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) reg = io_apic_read(entry->apic, 0x10 + pin*2); /* Is the remote IRR bit set? */ if (reg & IO_APIC_REDIR_REMOTE_IRR) { - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return true; } } - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return false; } @@ -433,10 +420,10 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) { union entry_union eu; unsigned long flags; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return eu.entry; } @@ -459,9 +446,9 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { unsigned long flags; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); __ioapic_write_entry(apic, pin, e); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); } /* @@ -474,10 +461,10 @@ static void ioapic_mask_entry(int apic, int pin) unsigned long flags; union entry_union eu = { .entry.mask = 1 }; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0x10 + 2*pin, eu.w1); io_apic_write(apic, 0x11 + 2*pin, eu.w2); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); } /* @@ -604,9 +591,9 @@ static void mask_IO_APIC_irq_desc(struct irq_desc *desc) BUG_ON(!cfg); - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); __mask_IO_APIC_irq(cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void unmask_IO_APIC_irq_desc(struct irq_desc *desc) @@ -614,9 +601,9 @@ static void unmask_IO_APIC_irq_desc(struct irq_desc *desc) struct irq_cfg *cfg = desc->chip_data; unsigned long flags; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); __unmask_IO_APIC_irq(cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void mask_IO_APIC_irq(unsigned int irq) @@ -1140,12 +1127,12 @@ void lock_vector_lock(void) /* Used to the online set of cpus does not change * during assign_irq_vector. */ - spin_lock(&vector_lock); + raw_spin_lock(&vector_lock); } void unlock_vector_lock(void) { - spin_unlock(&vector_lock); + raw_spin_unlock(&vector_lock); } static int @@ -1162,7 +1149,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * Also, we've got to be careful not to trash gate * 0x80, because int 0x80 is hm, kind of importantish. ;) */ - static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0; + static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; + static int current_offset = VECTOR_OFFSET_START % 8; unsigned int old_vector; int cpu, err; cpumask_var_t tmp_mask; @@ -1198,7 +1186,7 @@ next: if (vector >= first_system_vector) { /* If out of vectors on large boxen, must share them. */ offset = (offset + 1) % 8; - vector = FIRST_DEVICE_VECTOR + offset; + vector = FIRST_EXTERNAL_VECTOR + offset; } if (unlikely(current_vector == vector)) continue; @@ -1232,9 +1220,9 @@ int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) int err; unsigned long flags; - spin_lock_irqsave(&vector_lock, flags); + raw_spin_lock_irqsave(&vector_lock, flags); err = __assign_irq_vector(irq, cfg, mask); - spin_unlock_irqrestore(&vector_lock, flags); + raw_spin_unlock_irqrestore(&vector_lock, flags); return err; } @@ -1268,11 +1256,16 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) void __setup_vector_irq(int cpu) { /* Initialize vector_irq on a new cpu */ - /* This function must be called with vector_lock held */ int irq, vector; struct irq_cfg *cfg; struct irq_desc *desc; + /* + * vector_lock will make sure that we don't run into irq vector + * assignments that might be happening on another cpu in parallel, + * while we setup our initial vector to irq mappings. + */ + raw_spin_lock(&vector_lock); /* Mark the inuse vectors */ for_each_irq_desc(irq, desc) { cfg = desc->chip_data; @@ -1291,6 +1284,7 @@ void __setup_vector_irq(int cpu) if (!cpumask_test_cpu(cpu, cfg->domain)) per_cpu(vector_irq, cpu)[vector] = -1; } + raw_spin_unlock(&vector_lock); } static struct irq_chip ioapic_chip; @@ -1440,6 +1434,14 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq cfg = desc->chip_data; + /* + * For legacy irqs, cfg->domain starts with cpu 0 for legacy + * controllers like 8259. Now that IO-APIC can handle this irq, update + * the cfg->domain. + */ + if (irq < nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain)) + apic->vector_allocation_domain(0, cfg->domain); + if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; @@ -1473,7 +1475,7 @@ static struct { static void __init setup_IO_APIC_irqs(void) { - int apic_id = 0, pin, idx, irq; + int apic_id, pin, idx, irq; int notcon = 0; struct irq_desc *desc; struct irq_cfg *cfg; @@ -1481,14 +1483,7 @@ static void __init setup_IO_APIC_irqs(void) apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); -#ifdef CONFIG_ACPI - if (!acpi_disabled && acpi_ioapic) { - apic_id = mp_find_ioapic(0); - if (apic_id < 0) - apic_id = 0; - } -#endif - + for (apic_id = 0; apic_id < nr_ioapics; apic_id++) for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) { idx = find_irq_entry(apic_id, pin, mp_INT); if (idx == -1) { @@ -1510,6 +1505,9 @@ static void __init setup_IO_APIC_irqs(void) irq = pin_2_irq(idx, apic_id, pin); + if ((apic_id > 0) && (irq > 16)) + continue; + /* * Skip the timer IRQ if there's a quirk handler * installed and if it returns 1: @@ -1539,6 +1537,56 @@ static void __init setup_IO_APIC_irqs(void) } /* + * for the gsit that is not in first ioapic + * but could not use acpi_register_gsi() + * like some special sci in IBM x3330 + */ +void setup_IO_APIC_irq_extra(u32 gsi) +{ + int apic_id = 0, pin, idx, irq; + int node = cpu_to_node(boot_cpu_id); + struct irq_desc *desc; + struct irq_cfg *cfg; + + /* + * Convert 'gsi' to 'ioapic.pin'. + */ + apic_id = mp_find_ioapic(gsi); + if (apic_id < 0) + return; + + pin = mp_find_ioapic_pin(apic_id, gsi); + idx = find_irq_entry(apic_id, pin, mp_INT); + if (idx == -1) + return; + + irq = pin_2_irq(idx, apic_id, pin); +#ifdef CONFIG_SPARSE_IRQ + desc = irq_to_desc(irq); + if (desc) + return; +#endif + desc = irq_to_desc_alloc_node(irq, node); + if (!desc) { + printk(KERN_INFO "can not get irq_desc for %d\n", irq); + return; + } + + cfg = desc->chip_data; + add_pin_to_irq_node(cfg, node, apic_id, pin); + + if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) { + pr_debug("Pin %d-%d already programmed\n", + mp_ioapics[apic_id].apicid, pin); + return; + } + set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed); + + setup_IO_APIC_irq(apic_id, pin, irq, desc, + irq_trigger(idx), irq_polarity(idx)); +} + +/* * Set up the timer pin, possibly with the 8259A-master behind. */ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, @@ -1601,14 +1649,14 @@ __apicdebuginit(void) print_IO_APIC(void) for (apic = 0; apic < nr_ioapics; apic++) { - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(apic, 0); reg_01.raw = io_apic_read(apic, 1); if (reg_01.bits.version >= 0x10) reg_02.raw = io_apic_read(apic, 2); if (reg_01.bits.version >= 0x20) reg_03.raw = io_apic_read(apic, 3); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); printk("\n"); printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid); @@ -1830,7 +1878,7 @@ __apicdebuginit(void) print_PIC(void) printk(KERN_DEBUG "\nprinting PIC contents\n"); - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); v = inb(0xa1) << 8 | inb(0x21); printk(KERN_DEBUG "... PIC IMR: %04x\n", v); @@ -1844,7 +1892,7 @@ __apicdebuginit(void) print_PIC(void) outb(0x0a,0xa0); outb(0x0a,0x20); - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); printk(KERN_DEBUG "... PIC ISR: %04x\n", v); @@ -1903,9 +1951,9 @@ void __init enable_IO_APIC(void) * The number of IO-APIC IRQ registers (== #pins): */ for (apic = 0; apic < nr_ioapics; apic++) { - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_01.raw = io_apic_read(apic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); nr_ioapic_registers[apic] = reg_01.bits.entries+1; } @@ -2045,9 +2093,9 @@ void __init setup_ioapic_ids_from_mpc(void) for (apic_id = 0; apic_id < nr_ioapics; apic_id++) { /* Read the register 0 value */ - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(apic_id, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); old_id = mp_ioapics[apic_id].apicid; @@ -2106,16 +2154,16 @@ void __init setup_ioapic_ids_from_mpc(void) mp_ioapics[apic_id].apicid); reg_00.bits.ID = mp_ioapics[apic_id].apicid; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic_id, 0, reg_00.raw); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); /* * Sanity check */ - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(apic_id, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); if (reg_00.bits.ID != mp_ioapics[apic_id].apicid) printk("could not set ID!\n"); else @@ -2198,7 +2246,7 @@ static unsigned int startup_ioapic_irq(unsigned int irq) unsigned long flags; struct irq_cfg *cfg; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); if (irq < nr_legacy_irqs) { disable_8259A_irq(irq); if (i8259A_irq_pending(irq)) @@ -2206,7 +2254,7 @@ static unsigned int startup_ioapic_irq(unsigned int irq) } cfg = irq_cfg(irq); __unmask_IO_APIC_irq(cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return was_pending; } @@ -2217,9 +2265,9 @@ static int ioapic_retrigger_irq(unsigned int irq) struct irq_cfg *cfg = irq_cfg(irq); unsigned long flags; - spin_lock_irqsave(&vector_lock, flags); + raw_spin_lock_irqsave(&vector_lock, flags); apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); - spin_unlock_irqrestore(&vector_lock, flags); + raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; } @@ -2312,14 +2360,14 @@ set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask) irq = desc->irq; cfg = desc->chip_data; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); ret = set_desc_affinity(desc, mask, &dest); if (!ret) { /* Only the high 8 bits are valid. */ dest = SET_APIC_LOGICAL_ID(dest); __target_IO_APIC_irq(irq, dest, cfg); } - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return ret; } @@ -2554,9 +2602,9 @@ static void eoi_ioapic_irq(struct irq_desc *desc) irq = desc->irq; cfg = desc->chip_data; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); __eoi_ioapic_irq(irq, cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void ack_apic_level(unsigned int irq) @@ -3138,13 +3186,13 @@ static int ioapic_resume(struct sys_device *dev) data = container_of(dev, struct sysfs_ioapic_data, dev); entry = data->entry; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(dev->id, 0); if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) { reg_00.bits.ID = mp_ioapics[dev->id].apicid; io_apic_write(dev->id, 0, reg_00.raw); } - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); for (i = 0; i < nr_ioapic_registers[dev->id]; i++) ioapic_write_entry(dev->id, i, entry[i]); @@ -3207,7 +3255,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) if (irq_want < nr_irqs_gsi) irq_want = nr_irqs_gsi; - spin_lock_irqsave(&vector_lock, flags); + raw_spin_lock_irqsave(&vector_lock, flags); for (new = irq_want; new < nr_irqs; new++) { desc_new = irq_to_desc_alloc_node(new, node); if (!desc_new) { @@ -3226,14 +3274,11 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) irq = new; break; } - spin_unlock_irqrestore(&vector_lock, flags); + raw_spin_unlock_irqrestore(&vector_lock, flags); + + if (irq > 0) + dynamic_irq_init_keep_chip_data(irq); - if (irq > 0) { - dynamic_irq_init(irq); - /* restore it, in case dynamic_irq_init clear it */ - if (desc_new) - desc_new->chip_data = cfg_new; - } return irq; } @@ -3255,20 +3300,13 @@ int create_irq(void) void destroy_irq(unsigned int irq) { unsigned long flags; - struct irq_cfg *cfg; - struct irq_desc *desc; - /* store it, in case dynamic_irq_cleanup clear it */ - desc = irq_to_desc(irq); - cfg = desc->chip_data; - dynamic_irq_cleanup(irq); - /* connect back irq_cfg */ - desc->chip_data = cfg; + dynamic_irq_cleanup_keep_chip_data(irq); free_irte(irq); - spin_lock_irqsave(&vector_lock, flags); - __clear_irq_vector(irq, cfg); - spin_unlock_irqrestore(&vector_lock, flags); + raw_spin_lock_irqsave(&vector_lock, flags); + __clear_irq_vector(irq, get_irq_chip_data(irq)); + raw_spin_unlock_irqrestore(&vector_lock, flags); } /* @@ -3805,9 +3843,9 @@ int __init io_apic_get_redir_entries (int ioapic) union IO_APIC_reg_01 reg_01; unsigned long flags; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return reg_01.bits.entries; } @@ -3969,9 +4007,9 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) if (physids_empty(apic_id_map)) apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map); - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(ioapic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); if (apic_id >= get_physical_broadcast()) { printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying " @@ -4005,10 +4043,10 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) if (reg_00.bits.ID != apic_id) { reg_00.bits.ID = apic_id; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(ioapic, 0, reg_00.raw); reg_00.raw = io_apic_read(ioapic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); /* Sanity check */ if (reg_00.bits.ID != apic_id) { @@ -4029,9 +4067,9 @@ int __init io_apic_get_version(int ioapic) union IO_APIC_reg_01 reg_01; unsigned long flags; - spin_lock_irqsave(&ioapic_lock, flags); + raw_spin_lock_irqsave(&ioapic_lock, flags); reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); return reg_01.bits.version; } @@ -4063,27 +4101,23 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) #ifdef CONFIG_SMP void __init setup_ioapic_dest(void) { - int pin, ioapic = 0, irq, irq_entry; + int pin, ioapic, irq, irq_entry; struct irq_desc *desc; const struct cpumask *mask; if (skip_ioapic_setup == 1) return; -#ifdef CONFIG_ACPI - if (!acpi_disabled && acpi_ioapic) { - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - ioapic = 0; - } -#endif - + for (ioapic = 0; ioapic < nr_ioapics; ioapic++) for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) { irq_entry = find_irq_entry(ioapic, pin, mp_INT); if (irq_entry == -1) continue; irq = pin_2_irq(irq_entry, ioapic, pin); + if ((ioapic > 0) && (irq > 16)) + continue; + desc = irq_to_desc(irq); /* diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 0159a69396cb..bd7c96b5e8d8 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -416,13 +416,13 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) /* We can be called before check_nmi_watchdog, hence NULL check. */ if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - static DEFINE_SPINLOCK(lock); /* Serialise the printks */ + static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */ - spin_lock(&lock); + raw_spin_lock(&lock); printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); show_regs(regs); dump_stack(); - spin_unlock(&lock); + raw_spin_unlock(&lock); cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); rc = 1; @@ -438,8 +438,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) * Ayiee, looks like this CPU is stuck ... * wait a few IRQs (5 seconds) before doing the oops ... */ - __this_cpu_inc(per_cpu_var(alert_counter)); - if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz) + __this_cpu_inc(alert_counter); + if (__this_cpu_read(alert_counter) == 5 * nmi_hz) /* * die_nmi will return ONLY if NOTIFY_STOP happens.. */ @@ -447,7 +447,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) regs, panic_on_timeout); } else { __get_cpu_var(last_irq_sum) = sum; - __this_cpu_write(per_cpu_var(alert_counter), 0); + __this_cpu_write(alert_counter, 0); } /* see if the nmi watchdog went off */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 6e44519960c8..d360b56e9825 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -806,7 +806,7 @@ static int find_psb_table(struct powernow_k8_data *data) static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { - acpi_integer control; + u64 control; if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE)) return; @@ -824,7 +824,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { struct cpufreq_frequency_table *powernow_table; int ret_val = -ENODEV; - acpi_integer control, status; + u64 control, status; if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) { dprintk("register performance failed: bad ACPI data\n"); @@ -948,7 +948,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, u32 fid; u32 vid; u32 freq, index; - acpi_integer status, control; + u64 status, control; if (data->exttype) { status = data->acpi_data.states[i].status; diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 09b1698e0466..06130b52f012 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -22,10 +22,10 @@ #include <linux/pci.h> #include <linux/smp.h> #include <linux/cpu.h> -#include <linux/sort.h> #include <linux/mutex.h> #include <linux/uaccess.h> #include <linux/kvm_para.h> +#include <linux/range.h> #include <asm/processor.h> #include <asm/e820.h> @@ -34,11 +34,6 @@ #include "mtrr.h" -struct res_range { - unsigned long start; - unsigned long end; -}; - struct var_mtrr_range_state { unsigned long base_pfn; unsigned long size_pfn; @@ -56,7 +51,7 @@ struct var_mtrr_state { /* Should be related to MTRR_VAR_RANGES nums */ #define RANGE_NUM 256 -static struct res_range __initdata range[RANGE_NUM]; +static struct range __initdata range[RANGE_NUM]; static int __initdata nr_range; static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; @@ -64,152 +59,11 @@ static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; static int __initdata debug_print; #define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0) - -static int __init -add_range(struct res_range *range, int nr_range, - unsigned long start, unsigned long end) -{ - /* Out of slots: */ - if (nr_range >= RANGE_NUM) - return nr_range; - - range[nr_range].start = start; - range[nr_range].end = end; - - nr_range++; - - return nr_range; -} - -static int __init -add_range_with_merge(struct res_range *range, int nr_range, - unsigned long start, unsigned long end) -{ - int i; - - /* Try to merge it with old one: */ - for (i = 0; i < nr_range; i++) { - unsigned long final_start, final_end; - unsigned long common_start, common_end; - - if (!range[i].end) - continue; - - common_start = max(range[i].start, start); - common_end = min(range[i].end, end); - if (common_start > common_end + 1) - continue; - - final_start = min(range[i].start, start); - final_end = max(range[i].end, end); - - range[i].start = final_start; - range[i].end = final_end; - return nr_range; - } - - /* Need to add it: */ - return add_range(range, nr_range, start, end); -} - -static void __init -subtract_range(struct res_range *range, unsigned long start, unsigned long end) -{ - int i, j; - - for (j = 0; j < RANGE_NUM; j++) { - if (!range[j].end) - continue; - - if (start <= range[j].start && end >= range[j].end) { - range[j].start = 0; - range[j].end = 0; - continue; - } - - if (start <= range[j].start && end < range[j].end && - range[j].start < end + 1) { - range[j].start = end + 1; - continue; - } - - - if (start > range[j].start && end >= range[j].end && - range[j].end > start - 1) { - range[j].end = start - 1; - continue; - } - - if (start > range[j].start && end < range[j].end) { - /* Find the new spare: */ - for (i = 0; i < RANGE_NUM; i++) { - if (range[i].end == 0) - break; - } - if (i < RANGE_NUM) { - range[i].end = range[j].end; - range[i].start = end + 1; - } else { - printk(KERN_ERR "run of slot in ranges\n"); - } - range[j].end = start - 1; - continue; - } - } -} - -static int __init cmp_range(const void *x1, const void *x2) -{ - const struct res_range *r1 = x1; - const struct res_range *r2 = x2; - long start1, start2; - - start1 = r1->start; - start2 = r2->start; - - return start1 - start2; -} - -static int __init clean_sort_range(struct res_range *range, int az) -{ - int i, j, k = az - 1, nr_range = 0; - - for (i = 0; i < k; i++) { - if (range[i].end) - continue; - for (j = k; j > i; j--) { - if (range[j].end) { - k = j; - break; - } - } - if (j == i) - break; - range[i].start = range[k].start; - range[i].end = range[k].end; - range[k].start = 0; - range[k].end = 0; - k--; - } - /* count it */ - for (i = 0; i < az; i++) { - if (!range[i].end) { - nr_range = i; - break; - } - } - - /* sort them */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); - - return nr_range; -} - #define BIOS_BUG_MSG KERN_WARNING \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" static int __init -x86_get_mtrr_mem_range(struct res_range *range, int nr_range, +x86_get_mtrr_mem_range(struct range *range, int nr_range, unsigned long extra_remove_base, unsigned long extra_remove_size) { @@ -223,14 +77,14 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, continue; base = range_state[i].base_pfn; size = range_state[i].size_pfn; - nr_range = add_range_with_merge(range, nr_range, base, - base + size - 1); + nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, + base, base + size); } if (debug_print) { printk(KERN_DEBUG "After WB checking\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", - range[i].start, range[i].end + 1); + printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); } /* Take out UC ranges: */ @@ -252,19 +106,19 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, size -= (1<<(20-PAGE_SHIFT)) - base; base = 1<<(20-PAGE_SHIFT); } - subtract_range(range, base, base + size - 1); + subtract_range(range, RANGE_NUM, base, base + size); } if (extra_remove_size) - subtract_range(range, extra_remove_base, - extra_remove_base + extra_remove_size - 1); + subtract_range(range, RANGE_NUM, extra_remove_base, + extra_remove_base + extra_remove_size); if (debug_print) { printk(KERN_DEBUG "After UC checking\n"); for (i = 0; i < RANGE_NUM; i++) { if (!range[i].end) continue; - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", - range[i].start, range[i].end + 1); + printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); } } @@ -273,26 +127,22 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, if (debug_print) { printk(KERN_DEBUG "After sorting\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", - range[i].start, range[i].end + 1); + printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); } - /* clear those is not used */ - for (i = nr_range; i < RANGE_NUM; i++) - memset(&range[i], 0, sizeof(range[i])); - return nr_range; } #ifdef CONFIG_MTRR_SANITIZER -static unsigned long __init sum_ranges(struct res_range *range, int nr_range) +static unsigned long __init sum_ranges(struct range *range, int nr_range) { unsigned long sum = 0; int i; for (i = 0; i < nr_range; i++) - sum += range[i].end + 1 - range[i].start; + sum += range[i].end - range[i].start; return sum; } @@ -621,7 +471,7 @@ static int __init parse_mtrr_spare_reg(char *arg) early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg); static int __init -x86_setup_var_mtrrs(struct res_range *range, int nr_range, +x86_setup_var_mtrrs(struct range *range, int nr_range, u64 chunk_size, u64 gran_size) { struct var_mtrr_state var_state; @@ -639,7 +489,7 @@ x86_setup_var_mtrrs(struct res_range *range, int nr_range, /* Write the range: */ for (i = 0; i < nr_range; i++) { set_var_mtrr_range(&var_state, range[i].start, - range[i].end - range[i].start + 1); + range[i].end - range[i].start); } /* Write the last range: */ @@ -742,7 +592,7 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size, unsigned long x_remove_base, unsigned long x_remove_size, int i) { - static struct res_range range_new[RANGE_NUM]; + static struct range range_new[RANGE_NUM]; unsigned long range_sums_new; static int nr_range_new; int num_reg; @@ -869,10 +719,10 @@ int __init mtrr_cleanup(unsigned address_bits) * [0, 1M) should always be covered by var mtrr with WB * and fixed mtrrs should take effect before var mtrr for it: */ - nr_range = add_range_with_merge(range, nr_range, 0, - (1ULL<<(20 - PAGE_SHIFT)) - 1); + nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0, + 1ULL<<(20 - PAGE_SHIFT)); /* Sort the ranges: */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + sort_range(range, nr_range); range_sums = sum_ranges(range, nr_range); printk(KERN_INFO "total RAM covered: %ldM\n", @@ -1089,9 +939,9 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) nr_range = 0; if (mtrr_tom2) { range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT)); - range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1; - if (highest_pfn < range[nr_range].end + 1) - highest_pfn = range[nr_range].end + 1; + range[nr_range].end = mtrr_tom2 >> PAGE_SHIFT; + if (highest_pfn < range[nr_range].end) + highest_pfn = range[nr_range].end; nr_range++; } nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0); @@ -1103,15 +953,15 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* Check the holes: */ for (i = 0; i < nr_range - 1; i++) { - if (range[i].end + 1 < range[i+1].start) - total_trim_size += real_trim_memory(range[i].end + 1, + if (range[i].end < range[i+1].start) + total_trim_size += real_trim_memory(range[i].end, range[i+1].start); } /* Check the top: */ i = nr_range - 1; - if (range[i].end + 1 < end_pfn) - total_trim_size += real_trim_memory(range[i].end + 1, + if (range[i].end < end_pfn) + total_trim_size += real_trim_memory(range[i].end, end_pfn); if (total_trim_size) { diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index fe4622e8c837..79556bd9b602 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -145,6 +145,7 @@ struct set_mtrr_data { /** * ipi_handler - Synchronisation handler. Executed by "other" CPUs. + * @info: pointer to mtrr configuration data * * Returns nothing. */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a966b753e496..740b440fbd73 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -12,21 +12,13 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/bootmem.h> -#include <linux/ioport.h> -#include <linux/string.h> -#include <linux/kexec.h> -#include <linux/module.h> -#include <linux/mm.h> #include <linux/pfn.h> #include <linux/suspend.h> #include <linux/firmware-map.h> -#include <asm/pgtable.h> -#include <asm/page.h> #include <asm/e820.h> #include <asm/proto.h> #include <asm/setup.h> -#include <asm/trampoline.h> /* * The e820 map is the map that gets modified e.g. with command line parameters @@ -730,319 +722,44 @@ core_initcall(e820_mark_nvs_memory); #endif /* - * Early reserved memory areas. - */ -#define MAX_EARLY_RES 32 - -struct early_res { - u64 start, end; - char name[16]; - char overlap_ok; -}; -static struct early_res early_res[MAX_EARLY_RES] __initdata = { - { 0, PAGE_SIZE, "BIOS data page", 1 }, /* BIOS data page */ -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE) - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 }, -#endif - - {} -}; - -static int __init find_overlapped_early(u64 start, u64 end) -{ - int i; - struct early_res *r; - - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - r = &early_res[i]; - if (end > r->start && start < r->end) - break; - } - - return i; -} - -/* - * Drop the i-th range from the early reservation map, - * by copying any higher ranges down one over it, and - * clearing what had been the last slot. - */ -static void __init drop_range(int i) -{ - int j; - - for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++) - ; - - memmove(&early_res[i], &early_res[i + 1], - (j - 1 - i) * sizeof(struct early_res)); - - early_res[j - 1].end = 0; -} - -/* - * Split any existing ranges that: - * 1) are marked 'overlap_ok', and - * 2) overlap with the stated range [start, end) - * into whatever portion (if any) of the existing range is entirely - * below or entirely above the stated range. Drop the portion - * of the existing range that overlaps with the stated range, - * which will allow the caller of this routine to then add that - * stated range without conflicting with any existing range. + * Find a free area with specified alignment in a specific range. */ -static void __init drop_overlaps_that_are_ok(u64 start, u64 end) +u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align) { int i; - struct early_res *r; - u64 lower_start, lower_end; - u64 upper_start, upper_end; - char name[16]; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - r = &early_res[i]; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 addr; + u64 ei_start, ei_last; - /* Continue past non-overlapping ranges */ - if (end <= r->start || start >= r->end) + if (ei->type != E820_RAM) continue; - /* - * Leave non-ok overlaps as is; let caller - * panic "Overlapping early reservations" - * when it hits this overlap. - */ - if (!r->overlap_ok) - return; - - /* - * We have an ok overlap. We will drop it from the early - * reservation map, and add back in any non-overlapping - * portions (lower or upper) as separate, overlap_ok, - * non-overlapping ranges. - */ - - /* 1. Note any non-overlapping (lower or upper) ranges. */ - strncpy(name, r->name, sizeof(name) - 1); - - lower_start = lower_end = 0; - upper_start = upper_end = 0; - if (r->start < start) { - lower_start = r->start; - lower_end = start; - } - if (r->end > end) { - upper_start = end; - upper_end = r->end; - } - - /* 2. Drop the original ok overlapping range */ - drop_range(i); - - i--; /* resume for-loop on copied down entry */ - - /* 3. Add back in any non-overlapping ranges. */ - if (lower_end) - reserve_early_overlap_ok(lower_start, lower_end, name); - if (upper_end) - reserve_early_overlap_ok(upper_start, upper_end, name); - } -} - -static void __init __reserve_early(u64 start, u64 end, char *name, - int overlap_ok) -{ - int i; - struct early_res *r; - - i = find_overlapped_early(start, end); - if (i >= MAX_EARLY_RES) - panic("Too many early reservations"); - r = &early_res[i]; - if (r->end) - panic("Overlapping early reservations " - "%llx-%llx %s to %llx-%llx %s\n", - start, end - 1, name?name:"", r->start, - r->end - 1, r->name); - r->start = start; - r->end = end; - r->overlap_ok = overlap_ok; - if (name) - strncpy(r->name, name, sizeof(r->name) - 1); -} - -/* - * A few early reservtations come here. - * - * The 'overlap_ok' in the name of this routine does -not- mean it - * is ok for these reservations to overlap an earlier reservation. - * Rather it means that it is ok for subsequent reservations to - * overlap this one. - * - * Use this entry point to reserve early ranges when you are doing - * so out of "Paranoia", reserving perhaps more memory than you need, - * just in case, and don't mind a subsequent overlapping reservation - * that is known to be needed. - * - * The drop_overlaps_that_are_ok() call here isn't really needed. - * It would be needed if we had two colliding 'overlap_ok' - * reservations, so that the second such would not panic on the - * overlap with the first. We don't have any such as of this - * writing, but might as well tolerate such if it happens in - * the future. - */ -void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) -{ - drop_overlaps_that_are_ok(start, end); - __reserve_early(start, end, name, 1); -} - -/* - * Most early reservations come here. - * - * We first have drop_overlaps_that_are_ok() drop any pre-existing - * 'overlap_ok' ranges, so that we can then reserve this memory - * range without risk of panic'ing on an overlapping overlap_ok - * early reservation. - */ -void __init reserve_early(u64 start, u64 end, char *name) -{ - if (start >= end) - return; - - drop_overlaps_that_are_ok(start, end); - __reserve_early(start, end, name, 0); -} - -void __init free_early(u64 start, u64 end) -{ - struct early_res *r; - int i; - - i = find_overlapped_early(start, end); - r = &early_res[i]; - if (i >= MAX_EARLY_RES || r->end != end || r->start != start) - panic("free_early on not reserved area: %llx-%llx!", - start, end - 1); - - drop_range(i); -} - -void __init early_res_to_bootmem(u64 start, u64 end) -{ - int i, count; - u64 final_start, final_end; - - count = 0; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) - count++; - - printk(KERN_INFO "(%d early reservations) ==> bootmem [%010llx - %010llx]\n", - count, start, end); - for (i = 0; i < count; i++) { - struct early_res *r = &early_res[i]; - printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, - r->start, r->end, r->name); - final_start = max(start, r->start); - final_end = min(end, r->end); - if (final_start >= final_end) { - printk(KERN_CONT "\n"); - continue; - } - printk(KERN_CONT " ==> [%010llx - %010llx]\n", - final_start, final_end); - reserve_bootmem_generic(final_start, final_end - final_start, - BOOTMEM_DEFAULT); - } -} + ei_last = ei->addr + ei->size; + ei_start = ei->addr; + addr = find_early_area(ei_start, ei_last, start, end, + size, align); -/* Check for already reserved areas */ -static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) -{ - int i; - u64 addr = *addrp; - int changed = 0; - struct early_res *r; -again: - i = find_overlapped_early(addr, addr + size); - r = &early_res[i]; - if (i < MAX_EARLY_RES && r->end) { - *addrp = addr = round_up(r->end, align); - changed = 1; - goto again; + if (addr != -1ULL) + return addr; } - return changed; + return -1ULL; } -/* Check for already reserved areas */ -static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) +u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align) { - int i; - u64 addr = *addrp, last; - u64 size = *sizep; - int changed = 0; -again: - last = addr + size; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - struct early_res *r = &early_res[i]; - if (last > r->start && addr < r->start) { - size = r->start - addr; - changed = 1; - goto again; - } - if (last > r->end && addr < r->end) { - addr = round_up(r->end, align); - size = last - addr; - changed = 1; - goto again; - } - if (last <= r->end && addr >= r->start) { - (*sizep)++; - return 0; - } - } - if (changed) { - *addrp = addr; - *sizep = size; - } - return changed; + return find_e820_area(start, end, size, align); } -/* - * Find a free area with specified alignment in a specific range. - */ -u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align) +u64 __init get_max_mapped(void) { - int i; + u64 end = max_pfn_mapped; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 addr, last; - u64 ei_last; + end <<= PAGE_SHIFT; - if (ei->type != E820_RAM) - continue; - addr = round_up(ei->addr, align); - ei_last = ei->addr + ei->size; - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - continue; - while (bad_addr(&addr, size, align) && addr+size <= ei_last) - ; - last = addr + size; - if (last > ei_last) - continue; - if (last > end) - continue; - return addr; - } - return -1ULL; + return end; } - /* * Find next free range after *start */ @@ -1052,25 +769,19 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align) for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; - u64 addr, last; - u64 ei_last; + u64 addr; + u64 ei_start, ei_last; if (ei->type != E820_RAM) continue; - addr = round_up(ei->addr, align); + ei_last = ei->addr + ei->size; - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - continue; - *sizep = ei_last - addr; - while (bad_addr_size(&addr, sizep, align) && - addr + *sizep <= ei_last) - ; - last = addr + *sizep; - if (last > ei_last) - continue; - return addr; + ei_start = ei->addr; + addr = find_early_area_size(ei_start, ei_last, start, + sizep, align); + + if (addr != -1ULL) + return addr; } return -1ULL; @@ -1429,6 +1140,8 @@ void __init e820_reserve_resources_late(void) end = MAX_RESOURCE_SIZE; if (start >= end) continue; + printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ", + start, end); reserve_region_with_split(&iomem_resource, start, end, "RAM buffer"); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 5051b94c9069..adedeef1dedc 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,6 +29,16 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { +#ifdef CONFIG_X86_TRAMPOLINE + /* + * But first pinch a few for the stack/trampoline stuff + * FIXME: Don't need the extra page at 4K, but need to fix + * trampoline before removing it. (see the GDT stuff) + */ + reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, + "EX TRAMPOLINE"); +#endif + reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 7fd318bac59c..37c3d4b17d85 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -442,8 +442,8 @@ is386: movl $2,%ecx # set MP */ cmpb $0,ready jne 1f - movl $per_cpu__gdt_page,%eax - movl $per_cpu__stack_canary,%ecx + movl $gdt_page,%eax + movl $stack_canary,%ecx movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax) shrl $16, %ecx movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax) @@ -706,7 +706,7 @@ idt_descr: .word 0 # 32 bit align gdt_desc.address ENTRY(early_gdt_descr) .word GDT_ENTRIES*8-1 - .long per_cpu__gdt_page /* Overwritten for secondary CPUs */ + .long gdt_page /* Overwritten for secondary CPUs */ /* * The boot_gdt must mirror the equivalent in setup.S and is diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ad80a1c718c6..ee4fa1bfcb33 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -266,7 +266,7 @@ static void hpet_resume_device(void) force_hpet_resume(); } -static void hpet_resume_counter(void) +static void hpet_resume_counter(struct clocksource *cs) { hpet_resume_device(); hpet_restart_counter(); diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index df89102bef80..8c93a84bb627 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -32,7 +32,7 @@ */ static int i8259A_auto_eoi; -DEFINE_SPINLOCK(i8259A_lock); +DEFINE_RAW_SPINLOCK(i8259A_lock); static void mask_and_ack_8259A(unsigned int); struct irq_chip i8259A_chip = { @@ -68,13 +68,13 @@ void disable_8259A_irq(unsigned int irq) unsigned int mask = 1 << irq; unsigned long flags; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask |= mask; if (irq & 8) outb(cached_slave_mask, PIC_SLAVE_IMR); else outb(cached_master_mask, PIC_MASTER_IMR); - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); } void enable_8259A_irq(unsigned int irq) @@ -82,13 +82,13 @@ void enable_8259A_irq(unsigned int irq) unsigned int mask = ~(1 << irq); unsigned long flags; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask &= mask; if (irq & 8) outb(cached_slave_mask, PIC_SLAVE_IMR); else outb(cached_master_mask, PIC_MASTER_IMR); - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); } int i8259A_irq_pending(unsigned int irq) @@ -97,12 +97,12 @@ int i8259A_irq_pending(unsigned int irq) unsigned long flags; int ret; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); if (irq < 8) ret = inb(PIC_MASTER_CMD) & mask; else ret = inb(PIC_SLAVE_CMD) & (mask >> 8); - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); return ret; } @@ -150,7 +150,7 @@ static void mask_and_ack_8259A(unsigned int irq) unsigned int irqmask = 1 << irq; unsigned long flags; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); /* * Lightweight spurious IRQ detection. We do not want * to overdo spurious IRQ handling - it's usually a sign @@ -183,7 +183,7 @@ handle_real_irq: outb(cached_master_mask, PIC_MASTER_IMR); outb(0x60+irq, PIC_MASTER_CMD); /* 'Specific EOI to master */ } - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); return; spurious_8259A_irq: @@ -285,24 +285,24 @@ void mask_8259A(void) { unsigned long flags; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); } void unmask_8259A(void) { unsigned long flags; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */ outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */ - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); } void init_8259A(int auto_eoi) @@ -311,7 +311,7 @@ void init_8259A(int auto_eoi) i8259A_auto_eoi = auto_eoi; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ @@ -356,5 +356,5 @@ void init_8259A(int auto_eoi) outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */ outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */ - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index d5932226614f..fce55d532631 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -84,24 +84,7 @@ static struct irqaction irq2 = { }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { - [0 ... IRQ0_VECTOR - 1] = -1, - [IRQ0_VECTOR] = 0, - [IRQ1_VECTOR] = 1, - [IRQ2_VECTOR] = 2, - [IRQ3_VECTOR] = 3, - [IRQ4_VECTOR] = 4, - [IRQ5_VECTOR] = 5, - [IRQ6_VECTOR] = 6, - [IRQ7_VECTOR] = 7, - [IRQ8_VECTOR] = 8, - [IRQ9_VECTOR] = 9, - [IRQ10_VECTOR] = 10, - [IRQ11_VECTOR] = 11, - [IRQ12_VECTOR] = 12, - [IRQ13_VECTOR] = 13, - [IRQ14_VECTOR] = 14, - [IRQ15_VECTOR] = 15, - [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1 + [0 ... NR_VECTORS - 1] = -1, }; int vector_used_by_percpu_irq(unsigned int vector) @@ -116,6 +99,9 @@ int vector_used_by_percpu_irq(unsigned int vector) return 0; } +/* Number of legacy interrupts */ +int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY; + void __init init_ISA_irqs(void) { int i; @@ -142,6 +128,19 @@ void __init init_ISA_irqs(void) void __init init_IRQ(void) { + int i; + + /* + * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15. + * If these IRQ's are handled by legacy interrupt-controllers like PIC, + * then this configuration will likely be static after the boot. If + * these IRQ's are handled by more mordern controllers like IO-APIC, + * then this vector space can be freed and re-used dynamically as the + * irq's migrate etc. + */ + for (i = 0; i < nr_legacy_irqs; i++) + per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i; + x86_init.irqs.intr_init(); } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 5de9f4a9c3fd..b43bbaebe2c0 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -49,6 +49,7 @@ #include <linux/module.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/ftrace.h> #include <asm/cacheflush.h> #include <asm/desc.h> @@ -106,16 +107,22 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { }; const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); -/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -static void __kprobes set_jmp_op(void *from, void *to) +static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) { - struct __arch_jmp_op { - char op; + struct __arch_relative_insn { + u8 op; s32 raddr; - } __attribute__((packed)) * jop; - jop = (struct __arch_jmp_op *)from; - jop->raddr = (s32)((long)(to) - ((long)(from) + 5)); - jop->op = RELATIVEJUMP_INSTRUCTION; + } __attribute__((packed)) *insn; + + insn = (struct __arch_relative_insn *)from; + insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); + insn->op = op; +} + +/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ +static void __kprobes synthesize_reljump(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); } /* @@ -202,7 +209,7 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) /* * Basically, kp->ainsn.insn has an original instruction. * However, RIP-relative instruction can not do single-stepping - * at different place, fix_riprel() tweaks the displacement of + * at different place, __copy_instruction() tweaks the displacement of * that instruction. In that case, we can't recover the instruction * from the kp->ainsn.insn. * @@ -284,21 +291,37 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) } /* - * Adjust the displacement if the instruction uses the %rip-relative - * addressing mode. + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. * If it does, Return the address of the 32-bit displacement word. * If not, return null. * Only applicable to 64-bit x86. */ -static void __kprobes fix_riprel(struct kprobe *p) +static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) { -#ifdef CONFIG_X86_64 struct insn insn; - kernel_insn_init(&insn, p->ainsn.insn); + int ret; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + kernel_insn_init(&insn, src); + if (recover) { + insn_get_opcode(&insn); + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { + ret = recover_probed_instruction(buf, + (unsigned long)src); + if (ret) + return 0; + kernel_insn_init(&insn, buf); + } + } + insn_get_length(&insn); + memcpy(dest, insn.kaddr, insn.length); + +#ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { s64 newdisp; u8 *disp; + kernel_insn_init(&insn, dest); insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing @@ -312,20 +335,23 @@ static void __kprobes fix_riprel(struct kprobe *p) * extension of the original signed 32-bit displacement would * have given. */ - newdisp = (u8 *) p->addr + (s64) insn.displacement.value - - (u8 *) p->ainsn.insn; + newdisp = (u8 *) src + (s64) insn.displacement.value - + (u8 *) dest; BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ - disp = (u8 *) p->ainsn.insn + insn_offset_displacement(&insn); + disp = (u8 *) dest + insn_offset_displacement(&insn); *(s32 *) disp = (s32) newdisp; } #endif + return insn.length; } static void __kprobes arch_copy_kprobe(struct kprobe *p) { - memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - - fix_riprel(p); + /* + * Copy an instruction without recovering int3, because it will be + * put by another subsystem. + */ + __copy_instruction(p->ainsn.insn, p->addr, 0); if (can_boost(p->addr)) p->ainsn.boostable = 0; @@ -406,18 +432,6 @@ static void __kprobes restore_btf(void) update_debugctlmsr(current->thread.debugctlmsr); } -static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) -{ - clear_btf(); - regs->flags |= X86_EFLAGS_TF; - regs->flags &= ~X86_EFLAGS_IF; - /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) - regs->ip = (unsigned long)p->addr; - else - regs->ip = (unsigned long)p->ainsn.insn; -} - void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -429,20 +443,50 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, *sara = (unsigned long) &kretprobe_trampoline; } +#ifdef CONFIG_OPTPROBES +static int __kprobes setup_detour_execution(struct kprobe *p, + struct pt_regs *regs, + int reenter); +#else +#define setup_detour_execution(p, regs, reenter) (0) +#endif + static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) + struct kprobe_ctlblk *kcb, int reenter) { + if (setup_detour_execution(p, regs, reenter)) + return; + #if !defined(CONFIG_PREEMPT) if (p->ainsn.boostable == 1 && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ - reset_current_kprobe(); + if (!reenter) + reset_current_kprobe(); + /* + * Reentering boosted probe doesn't reset current_kprobe, + * nor set current_kprobe, because it doesn't use single + * stepping. + */ regs->ip = (unsigned long)p->ainsn.insn; preempt_enable_no_resched(); return; } #endif - prepare_singlestep(p, regs); - kcb->kprobe_status = KPROBE_HIT_SS; + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_REENTER; + } else + kcb->kprobe_status = KPROBE_HIT_SS; + /* Prepare real single stepping */ + clear_btf(); + regs->flags |= X86_EFLAGS_TF; + regs->flags &= ~X86_EFLAGS_IF; + /* single step inline if the instruction is an int3 */ + if (p->opcode == BREAKPOINT_INSTRUCTION) + regs->ip = (unsigned long)p->addr; + else + regs->ip = (unsigned long)p->ainsn.insn; } /* @@ -456,11 +500,8 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: case KPROBE_HIT_ACTIVE: - save_previous_kprobe(kcb); - set_current_kprobe(p, regs, kcb); kprobes_inc_nmissed_count(p); - prepare_singlestep(p, regs); - kcb->kprobe_status = KPROBE_REENTER; + setup_singlestep(p, regs, kcb, 1); break; case KPROBE_HIT_SS: /* A probe has been hit in the codepath leading up to, or just @@ -535,13 +576,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) * more here. */ if (!p->pre_handler || !p->pre_handler(p, regs)) - setup_singlestep(p, regs, kcb); + setup_singlestep(p, regs, kcb, 0); return 1; } } else if (kprobe_running()) { p = __get_cpu_var(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { - setup_singlestep(p, regs, kcb); + setup_singlestep(p, regs, kcb, 0); return 1; } } /* else: not a kprobe fault; let the kernel handle it */ @@ -550,6 +591,69 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) return 0; } +#ifdef CONFIG_X86_64 +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax. */ \ + " subq $24, %rsp\n" \ + " pushq %rdi\n" \ + " pushq %rsi\n" \ + " pushq %rdx\n" \ + " pushq %rcx\n" \ + " pushq %rax\n" \ + " pushq %r8\n" \ + " pushq %r9\n" \ + " pushq %r10\n" \ + " pushq %r11\n" \ + " pushq %rbx\n" \ + " pushq %rbp\n" \ + " pushq %r12\n" \ + " pushq %r13\n" \ + " pushq %r14\n" \ + " pushq %r15\n" +#define RESTORE_REGS_STRING \ + " popq %r15\n" \ + " popq %r14\n" \ + " popq %r13\n" \ + " popq %r12\n" \ + " popq %rbp\n" \ + " popq %rbx\n" \ + " popq %r11\n" \ + " popq %r10\n" \ + " popq %r9\n" \ + " popq %r8\n" \ + " popq %rax\n" \ + " popq %rcx\n" \ + " popq %rdx\n" \ + " popq %rsi\n" \ + " popq %rdi\n" \ + /* Skip orig_ax, ip, cs */ \ + " addq $24, %rsp\n" +#else +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax and gs. */ \ + " subl $16, %esp\n" \ + " pushl %fs\n" \ + " pushl %ds\n" \ + " pushl %es\n" \ + " pushl %eax\n" \ + " pushl %ebp\n" \ + " pushl %edi\n" \ + " pushl %esi\n" \ + " pushl %edx\n" \ + " pushl %ecx\n" \ + " pushl %ebx\n" +#define RESTORE_REGS_STRING \ + " popl %ebx\n" \ + " popl %ecx\n" \ + " popl %edx\n" \ + " popl %esi\n" \ + " popl %edi\n" \ + " popl %ebp\n" \ + " popl %eax\n" \ + /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ + " addl $24, %esp\n" +#endif + /* * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. @@ -563,65 +667,16 @@ static void __used __kprobes kretprobe_trampoline_holder(void) /* We don't bother saving the ss register */ " pushq %rsp\n" " pushfq\n" - /* - * Skip cs, ip, orig_ax. - * trampoline_handler() will plug in these values - */ - " subq $24, %rsp\n" - " pushq %rdi\n" - " pushq %rsi\n" - " pushq %rdx\n" - " pushq %rcx\n" - " pushq %rax\n" - " pushq %r8\n" - " pushq %r9\n" - " pushq %r10\n" - " pushq %r11\n" - " pushq %rbx\n" - " pushq %rbp\n" - " pushq %r12\n" - " pushq %r13\n" - " pushq %r14\n" - " pushq %r15\n" + SAVE_REGS_STRING " movq %rsp, %rdi\n" " call trampoline_handler\n" /* Replace saved sp with true return address. */ " movq %rax, 152(%rsp)\n" - " popq %r15\n" - " popq %r14\n" - " popq %r13\n" - " popq %r12\n" - " popq %rbp\n" - " popq %rbx\n" - " popq %r11\n" - " popq %r10\n" - " popq %r9\n" - " popq %r8\n" - " popq %rax\n" - " popq %rcx\n" - " popq %rdx\n" - " popq %rsi\n" - " popq %rdi\n" - /* Skip orig_ax, ip, cs */ - " addq $24, %rsp\n" + RESTORE_REGS_STRING " popfq\n" #else " pushf\n" - /* - * Skip cs, ip, orig_ax and gs. - * trampoline_handler() will plug in these values - */ - " subl $16, %esp\n" - " pushl %fs\n" - " pushl %es\n" - " pushl %ds\n" - " pushl %eax\n" - " pushl %ebp\n" - " pushl %edi\n" - " pushl %esi\n" - " pushl %edx\n" - " pushl %ecx\n" - " pushl %ebx\n" + SAVE_REGS_STRING " movl %esp, %eax\n" " call trampoline_handler\n" /* Move flags to cs */ @@ -629,15 +684,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " movl %edx, 52(%esp)\n" /* Replace saved flags with true return address. */ " movl %eax, 56(%esp)\n" - " popl %ebx\n" - " popl %ecx\n" - " popl %edx\n" - " popl %esi\n" - " popl %edi\n" - " popl %ebp\n" - " popl %eax\n" - /* Skip ds, es, fs, gs, orig_ax and ip */ - " addl $24, %esp\n" + RESTORE_REGS_STRING " popf\n" #endif " ret\n"); @@ -805,8 +852,8 @@ static void __kprobes resume_execution(struct kprobe *p, * These instructions can be executed directly if it * jumps back to correct address. */ - set_jmp_op((void *)regs->ip, - (void *)orig_ip + (regs->ip - copy_ip)); + synthesize_reljump((void *)regs->ip, + (void *)orig_ip + (regs->ip - copy_ip)); p->ainsn.boostable = 1; } else { p->ainsn.boostable = -1; @@ -1033,6 +1080,358 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } + +#ifdef CONFIG_OPTPROBES + +/* Insert a call instruction at address 'from', which calls address 'to'.*/ +static void __kprobes synthesize_relcall(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); +} + +/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ +static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, + unsigned long val) +{ +#ifdef CONFIG_X86_64 + *addr++ = 0x48; + *addr++ = 0xbf; +#else + *addr++ = 0xb8; +#endif + *(unsigned long *)addr = val; +} + +void __kprobes kprobes_optinsn_template_holder(void) +{ + asm volatile ( + ".global optprobe_template_entry\n" + "optprobe_template_entry: \n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rsi\n" + ".global optprobe_template_val\n" + "optprobe_template_val: \n" + ASM_NOP5 + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call: \n" + ASM_NOP5 + /* Move flags to rsp */ + " movq 144(%rsp), %rdx\n" + " movq %rdx, 152(%rsp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addq $8, %rsp\n" + " popfq\n" +#else /* CONFIG_X86_32 */ + " pushf\n" + SAVE_REGS_STRING + " movl %esp, %edx\n" + ".global optprobe_template_val\n" + "optprobe_template_val: \n" + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call: \n" + ASM_NOP5 + RESTORE_REGS_STRING + " addl $4, %esp\n" /* skip cs */ + " popf\n" +#endif + ".global optprobe_template_end\n" + "optprobe_template_end: \n"); +} + +#define TMPL_MOVE_IDX \ + ((long)&optprobe_template_val - (long)&optprobe_template_entry) +#define TMPL_CALL_IDX \ + ((long)&optprobe_template_call - (long)&optprobe_template_entry) +#define TMPL_END_IDX \ + ((long)&optprobe_template_end - (long)&optprobe_template_entry) + +#define INT3_SIZE sizeof(kprobe_opcode_t) + +/* Optimized kprobe call back function: called from optinsn */ +static void __kprobes optimized_callback(struct optimized_kprobe *op, + struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + preempt_disable(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + /* Save skipped registers */ +#ifdef CONFIG_X86_64 + regs->cs = __KERNEL_CS; +#else + regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; +#endif + regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->orig_ax = ~0UL; + + __get_cpu_var(current_kprobe) = &op->kp; + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __get_cpu_var(current_kprobe) = NULL; + } + preempt_enable_no_resched(); +} + +static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +{ + int len = 0, ret; + + while (len < RELATIVEJUMP_SIZE) { + ret = __copy_instruction(dest + len, src + len, 1); + if (!ret || !can_boost(dest + len)) + return -EINVAL; + len += ret; + } + /* Check whether the address range is reserved */ + if (ftrace_text_reserved(src, src + len - 1) || + alternatives_text_reserved(src, src + len - 1)) + return -EBUSY; + + return len; +} + +/* Check whether insn is indirect jump */ +static int __kprobes insn_is_indirect_jump(struct insn *insn) +{ + return ((insn->opcode.bytes[0] == 0xff && + (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ + insn->opcode.bytes[0] == 0xea); /* Segment based jump */ +} + +/* Check whether insn jumps into specified address range */ +static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) +{ + unsigned long target = 0; + + switch (insn->opcode.bytes[0]) { + case 0xe0: /* loopne */ + case 0xe1: /* loope */ + case 0xe2: /* loop */ + case 0xe3: /* jcxz */ + case 0xe9: /* near relative jump */ + case 0xeb: /* short relative jump */ + break; + case 0x0f: + if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ + break; + return 0; + default: + if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ + break; + return 0; + } + target = (unsigned long)insn->next_byte + insn->immediate.value; + + return (start <= target && target <= start + len); +} + +/* Decode whole function to ensure any instructions don't jump into target */ +static int __kprobes can_optimize(unsigned long paddr) +{ + int ret; + unsigned long addr, size = 0, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + /* Dummy buffers for lookup_symbol_attrs */ + static char __dummy_buf[KSYM_NAME_LEN]; + + /* Lookup symbol including addr */ + if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf)) + return 0; + + /* Check there is enough space for a relative jump. */ + if (size - offset < RELATIVEJUMP_SIZE) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr - offset + size) { /* Decode until function end */ + if (search_exception_tables(addr)) + /* + * Since some fixup code will jumps into this function, + * we can't optimize kprobe in this function. + */ + return 0; + kernel_insn_init(&insn, (void *)addr); + insn_get_opcode(&insn); + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { + ret = recover_probed_instruction(buf, addr); + if (ret) + return 0; + kernel_insn_init(&insn, buf); + } + insn_get_length(&insn); + /* Recover address */ + insn.kaddr = (void *)addr; + insn.next_byte = (void *)(addr + insn.length); + /* Check any instructions don't jump into target */ + if (insn_is_indirect_jump(&insn) || + insn_jump_into_range(&insn, paddr + INT3_SIZE, + RELATIVE_ADDR_SIZE)) + return 0; + addr += insn.length; + } + + return 1; +} + +/* Check optimized_kprobe can actually be optimized. */ +int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + int i; + struct kprobe *p; + + for (i = 1; i < op->optinsn.size; i++) { + p = get_kprobe(op->kp.addr + i); + if (p && !kprobe_disabled(p)) + return -EEXIST; + } + + return 0; +} + +/* Check the addr is within the optimized instructions. */ +int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + op->optinsn.size > addr); +} + +/* Free optimized instruction slot */ +static __kprobes +void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) +{ + if (op->optinsn.insn) { + free_optinsn_slot(op->optinsn.insn, dirty); + op->optinsn.insn = NULL; + op->optinsn.size = 0; + } +} + +void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + __arch_remove_optimized_kprobe(op, 1); +} + +/* + * Copy replacing target instructions + * Target instructions MUST be relocatable (checked inside) + */ +int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +{ + u8 *buf; + int ret; + long rel; + + if (!can_optimize((unsigned long)op->kp.addr)) + return -EILSEQ; + + op->optinsn.insn = get_optinsn_slot(); + if (!op->optinsn.insn) + return -ENOMEM; + + /* + * Verify if the address gap is in 2GB range, because this uses + * a relative jump. + */ + rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + if (abs(rel) > 0x7fffffff) + return -ERANGE; + + buf = (u8 *)op->optinsn.insn; + + /* Copy instructions into the out-of-line buffer */ + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); + if (ret < 0) { + __arch_remove_optimized_kprobe(op, 0); + return ret; + } + op->optinsn.size = ret; + + /* Copy arch-dep-instance from template */ + memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + + /* Set probe information */ + synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); + + /* Set probe function call */ + synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + + /* Set returning jmp instruction at the tail of out-of-line buffer */ + synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + (u8 *)op->kp.addr + op->optinsn.size); + + flush_icache_range((unsigned long) buf, + (unsigned long) buf + TMPL_END_IDX + + op->optinsn.size + RELATIVEJUMP_SIZE); + return 0; +} + +/* Replace a breakpoint (int3) with a relative jump. */ +int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) +{ + unsigned char jmp_code[RELATIVEJUMP_SIZE]; + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + jmp_code[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&jmp_code[1]) = rel; + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE); + return 0; +} + +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) +{ + u8 buf[RELATIVEJUMP_SIZE]; + + /* Set int3 to first byte for kprobes */ + buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); +} + +static int __kprobes setup_detour_execution(struct kprobe *p, + struct pt_regs *regs, + int reenter) +{ + struct optimized_kprobe *op; + + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + /* This kprobe is really able to run optimized path. */ + op = container_of(p, struct optimized_kprobe, kp); + /* Detour through copied instructions */ + regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; + if (!reenter) + reset_current_kprobe(); + preempt_enable_no_resched(); + return 1; + } + return 0; +} +#endif + int __init arch_init_kprobes(void) { return 0; diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index 712d15fdc416..71825806cd44 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -7,6 +7,8 @@ #include <linux/string.h> #include <linux/pci.h> #include <linux/dmi.h> +#include <linux/range.h> + #include <asm/pci-direct.h> #include <linux/sort.h> #include <asm/io.h> @@ -30,11 +32,6 @@ static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = { { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, }; -struct range { - u64 start; - u64 end; -}; - static int __cpuinit cmp_range(const void *x1, const void *x2) { const struct range *r1 = x1; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 1b1739d16310..1db183ed7c01 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -428,10 +428,6 @@ struct pv_mmu_ops pv_mmu_ops = { .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, -#ifdef CONFIG_HIGHPTE - .kmap_atomic_pte = kmap_atomic, -#endif - #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE .set_pte_atomic = native_set_pte_atomic, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 75e14e21f61a..1aa966c565f9 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -65,7 +65,7 @@ int dma_set_mask(struct device *dev, u64 mask) } EXPORT_SYMBOL(dma_set_mask); -#ifdef CONFIG_X86_64 +#if defined(CONFIG_X86_64) && !defined(CONFIG_NUMA) static __initdata void *dma32_bootmem_ptr; static unsigned long dma32_bootmem_size __initdata = (128ULL<<20); @@ -116,14 +116,21 @@ static void __init dma32_free_bootmem(void) dma32_bootmem_ptr = NULL; dma32_bootmem_size = 0; } +#else +void __init dma32_reserve_bootmem(void) +{ +} +static void __init dma32_free_bootmem(void) +{ +} + #endif void __init pci_iommu_alloc(void) { -#ifdef CONFIG_X86_64 /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); -#endif + if (pci_swiotlb_detect()) goto out; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 704bddcdf64d..8e1aac86b50c 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -461,6 +461,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"), }, }, + { /* Handle problems with rebooting on the iMac9,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac9,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cb42109a55b4..5d7ba1a449bd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -969,15 +969,11 @@ void __init setup_arch(char **cmdline_p) #endif initmem_init(0, max_pfn, acpi, k8); +#ifndef CONFIG_NO_BOOTMEM + early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT); +#endif -#ifdef CONFIG_X86_64 - /* - * dma32_reserve_bootmem() allocates bootmem which may conflict - * with the crashkernel command line, so do that after - * reserve_crashkernel() - */ dma32_reserve_bootmem(); -#endif reserve_ibft_region(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 35abcb8b00e9..ef6370b00e70 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -137,7 +137,13 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { +#ifdef CONFIG_NO_BOOTMEM + u64 start = __pa(ptr); + u64 end = start + size; + free_early_partial(start, end); +#else free_bootmem(__pa(ptr), size); +#endif } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9b4401115ea1..a435c76d714e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -241,6 +241,11 @@ static void __cpuinit smp_callin(void) map_cpu_to_logical_apicid(); notify_cpu_starting(cpuid); + + /* + * Need to setup vector mappings before we enable interrupts. + */ + __setup_vector_irq(smp_processor_id()); /* * Get our bogomips. * @@ -315,7 +320,6 @@ notrace static void __cpuinit start_secondary(void *unused) */ ipi_call_lock(); lock_vector_lock(); - __setup_vector_irq(smp_processor_id()); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); ipi_call_unlock(); @@ -1212,11 +1216,12 @@ __init void prefill_possible_map(void) total_cpus = max_t(int, possible, num_processors + disabled_cpus); - if (possible > CONFIG_NR_CPUS) { + /* nr_cpu_ids could be reduced via nr_cpus= */ + if (possible > nr_cpu_ids) { printk(KERN_WARNING "%d Processors exceeds NR_CPUS limit of %d\n", - possible, CONFIG_NR_CPUS); - possible = CONFIG_NR_CPUS; + possible, nr_cpu_ids); + possible = nr_cpu_ids; } printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index be2573448ed9..fb5cc5e14cfa 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -70,11 +70,11 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) * manually to deassert NMI lines for the watchdog if run * on an 82489DX-based system. */ - spin_lock(&i8259A_lock); + raw_spin_lock(&i8259A_lock); outb(0x0c, PIC_MASTER_OCW3); /* Ack the IRQ; AEOI will end it automatically. */ inb(PIC_MASTER_POLL); - spin_unlock(&i8259A_lock); + raw_spin_unlock(&i8259A_lock); } global_clock_event->event_handler(global_clock_event); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 23066ecf12fa..208a857c679f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -740,7 +740,7 @@ static cycle_t __vsyscall_fn vread_tsc(void) } #endif -static void resume_tsc(void) +static void resume_tsc(struct clocksource *cs) { clocksource_tsc.cycle_last = 0; } diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 34a279a7471d..ab38ce0984fa 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -559,7 +559,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id) struct irq_desc *desc; unsigned long flags; - spin_lock_irqsave(&i8259A_lock, flags); + raw_spin_lock_irqsave(&i8259A_lock, flags); /* Find out what's interrupting in the PIIX4 master 8259 */ outb(0x0c, 0x20); /* OCW3 Poll command */ @@ -596,7 +596,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id) outb(0x60 + realirq, 0x20); } - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); desc = irq_to_desc(realirq); @@ -614,7 +614,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id) return IRQ_HANDLED; out_unlock: - spin_unlock_irqrestore(&i8259A_lock, flags); + raw_spin_unlock_irqrestore(&i8259A_lock, flags); return IRQ_NONE; } diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index d430e4c30193..7dd599deca4a 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -33,6 +33,7 @@ #include <asm/fixmap.h> #include <asm/apicdef.h> #include <asm/apic.h> +#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/timer.h> #include <asm/vmi_time.h> @@ -266,30 +267,6 @@ static void vmi_nop(void) { } -#ifdef CONFIG_HIGHPTE -static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type) -{ - void *va = kmap_atomic(page, type); - - /* - * Internally, the VMI ROM must map virtual addresses to physical - * addresses for processing MMU updates. By the time MMU updates - * are issued, this information is typically already lost. - * Fortunately, the VMI provides a cache of mapping slots for active - * page tables. - * - * We use slot zero for the linear mapping of physical memory, and - * in HIGHPTE kernels, slot 1 and 2 for KM_PTE0 and KM_PTE1. - * - * args: SLOT VA COUNT PFN - */ - BUG_ON(type != KM_PTE0 && type != KM_PTE1); - vmi_ops.set_linear_mapping((type - KM_PTE0)+1, va, 1, page_to_pfn(page)); - - return va; -} -#endif - static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn) { vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0); @@ -640,6 +617,12 @@ static inline int __init activate_vmi(void) u64 reloc; const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc; + /* + * Prevent page tables from being allocated in highmem, even if + * CONFIG_HIGHPTE is enabled. + */ + __userpte_alloc_gfp &= ~__GFP_HIGHMEM; + if (call_vrom_func(vmi_rom, vmi_init) != 0) { printk(KERN_ERR "VMI ROM failed to initialize!"); return 0; @@ -778,10 +761,6 @@ static inline int __init activate_vmi(void) /* Set linear is needed in all cases */ vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping); -#ifdef CONFIG_HIGHPTE - if (vmi_ops.set_linear_mapping) - pv_mmu_ops.kmap_atomic_pte = vmi_kmap_atomic_pte; -#endif /* * These MUST always be patched. Don't support indirect jumps diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 74c92bb194df..2f1ca5614292 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -79,11 +79,7 @@ unsigned long vmi_tsc_khz(void) static inline unsigned int vmi_get_timer_vector(void) { -#ifdef CONFIG_X86_IO_APIC - return FIRST_DEVICE_VECTOR; -#else - return FIRST_EXTERNAL_VECTOR; -#endif + return IRQ0_VECTOR; } /** vmi clockchip */ diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f92a0da608cb..44879df55696 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -341,7 +341,7 @@ SECTIONS * Per-cpu symbols which need to be offset from __per_cpu_load * for the boot processor. */ -#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load +#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load INIT_PER_CPU(gdt_page); INIT_PER_CPU(irq_stack_union); @@ -352,7 +352,7 @@ INIT_PER_CPU(irq_stack_union); "kernel image bigger than KERNEL_IMAGE_SIZE"); #ifdef CONFIG_SMP -. = ASSERT((per_cpu__irq_stack_union == 0), +. = ASSERT((irq_stack_union == 0), "irq_stack_union is not at start of per-cpu area"); #endif diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 06871111bf54..970bbd479516 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -66,6 +66,7 @@ config KVM_AMD # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. +source drivers/vhost/Kconfig source drivers/lguest/Kconfig source drivers/virtio/Kconfig diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2226f2c70ea3..5cb3f0f54f47 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -750,6 +750,7 @@ static void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } +#ifndef CONFIG_NO_BOOTMEM static unsigned long __init setup_node_bootmem(int nodeid, unsigned long start_pfn, unsigned long end_pfn, @@ -766,13 +767,14 @@ static unsigned long __init setup_node_bootmem(int nodeid, printk(KERN_INFO " node %d bootmap %08lx - %08lx\n", nodeid, bootmap, bootmap + bootmap_size); free_bootmem_with_active_regions(nodeid, end_pfn); - early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); return bootmap + bootmap_size; } +#endif void __init setup_bootmem_allocator(void) { +#ifndef CONFIG_NO_BOOTMEM int nodeid; unsigned long bootmap_size, bootmap; /* @@ -784,11 +786,13 @@ void __init setup_bootmem_allocator(void) if (bootmap == -1L) panic("Cannot find bootmem map of size %ld\n", bootmap_size); reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); +#endif printk(KERN_INFO " mapped low ram: 0 - %08lx\n", max_pfn_mapped<<PAGE_SHIFT); printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT); +#ifndef CONFIG_NO_BOOTMEM for_each_online_node(nodeid) { unsigned long start_pfn, end_pfn; @@ -806,6 +810,7 @@ void __init setup_bootmem_allocator(void) bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn, bootmap); } +#endif after_bootmem = 1; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 69ddfbd91135..e9b040e1cde5 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -572,6 +572,7 @@ kernel_physical_mapping_init(unsigned long start, void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, int acpi, int k8) { +#ifndef CONFIG_NO_BOOTMEM unsigned long bootmap_size, bootmap; bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; @@ -579,13 +580,15 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, PAGE_SIZE); if (bootmap == -1L) panic("Cannot find bootmem map of size %ld\n", bootmap_size); + reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); /* don't touch min_low_pfn */ bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT, 0, end_pfn); e820_register_active_regions(0, start_pfn, end_pfn); free_bootmem_with_active_regions(0, end_pfn); - early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT); - reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT); +#else + e820_register_active_regions(0, start_pfn, end_pfn); +#endif } #endif @@ -974,7 +977,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) if (pmd_none(*pmd)) { pte_t entry; - p = vmemmap_alloc_block(PMD_SIZE, node); + p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (!p) return -ENOMEM; diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index b20760ca7244..809baaaf48b1 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -418,7 +418,10 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, for_each_online_node(nid) { memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); + NODE_DATA(nid)->node_id = nid; +#ifndef CONFIG_NO_BOOTMEM NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; +#endif } setup_bootmem_allocator(); diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 3307ea8bd43a..8948f47fde05 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -163,30 +163,48 @@ static void * __init early_node_mem(int nodeid, unsigned long start, unsigned long end, unsigned long size, unsigned long align) { - unsigned long mem = find_e820_area(start, end, size, align); - void *ptr; + unsigned long mem; + /* + * put it on high as possible + * something will go with NODE_DATA + */ + if (start < (MAX_DMA_PFN<<PAGE_SHIFT)) + start = MAX_DMA_PFN<<PAGE_SHIFT; + if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) && + end > (MAX_DMA32_PFN<<PAGE_SHIFT)) + start = MAX_DMA32_PFN<<PAGE_SHIFT; + mem = find_e820_area(start, end, size, align); + if (mem != -1L) + return __va(mem); + + /* extend the search scope */ + end = max_pfn_mapped << PAGE_SHIFT; + if (end > (MAX_DMA32_PFN<<PAGE_SHIFT)) + start = MAX_DMA32_PFN<<PAGE_SHIFT; + else + start = MAX_DMA_PFN<<PAGE_SHIFT; + mem = find_e820_area(start, end, size, align); if (mem != -1L) return __va(mem); - ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS)); - if (ptr == NULL) { - printk(KERN_ERR "Cannot find %lu bytes in node %d\n", + printk(KERN_ERR "Cannot find %lu bytes in node %d\n", size, nodeid); - return NULL; - } - return ptr; + + return NULL; } /* Initialize bootmem allocator for a node */ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) { - unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size; + unsigned long start_pfn, last_pfn, nodedata_phys; const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - unsigned long bootmap_start, nodedata_phys; - void *bootmap; int nid; +#ifndef CONFIG_NO_BOOTMEM + unsigned long bootmap_start, bootmap_pages, bootmap_size; + void *bootmap; +#endif if (!end) return; @@ -200,7 +218,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) start = roundup(start, ZONE_ALIGN); - printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid, + printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid, start, end); start_pfn = start >> PAGE_SHIFT; @@ -211,14 +229,21 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) if (node_data[nodeid] == NULL) return; nodedata_phys = __pa(node_data[nodeid]); + reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA"); printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys, nodedata_phys + pgdat_size - 1); + nid = phys_to_nid(nodedata_phys); + if (nid != nodeid) + printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid); memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); - NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid]; + NODE_DATA(nodeid)->node_id = nodeid; NODE_DATA(nodeid)->node_start_pfn = start_pfn; NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; +#ifndef CONFIG_NO_BOOTMEM + NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid]; + /* * Find a place for the bootmem map * nodedata_phys could be on other nodes by alloc_bootmem, @@ -227,11 +252,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) * of alloc_bootmem, that could clash with reserved range */ bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn); - nid = phys_to_nid(nodedata_phys); - if (nid == nodeid) - bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE); - else - bootmap_start = roundup(start, PAGE_SIZE); + bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE); /* * SMP_CACHE_BYTES could be enough, but init_bootmem_node like * to use that to align to PAGE_SIZE @@ -239,18 +260,13 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) bootmap = early_node_mem(nodeid, bootmap_start, end, bootmap_pages<<PAGE_SHIFT, PAGE_SIZE); if (bootmap == NULL) { - if (nodedata_phys < start || nodedata_phys >= end) { - /* - * only need to free it if it is from other node - * bootmem - */ - if (nid != nodeid) - free_bootmem(nodedata_phys, pgdat_size); - } + free_early(nodedata_phys, nodedata_phys + pgdat_size); node_data[nodeid] = NULL; return; } bootmap_start = __pa(bootmap); + reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT), + "BOOTMAP"); bootmap_size = init_bootmem_node(NODE_DATA(nodeid), bootmap_start >> PAGE_SHIFT, @@ -259,31 +275,12 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) printk(KERN_INFO " bootmap [%016lx - %016lx] pages %lx\n", bootmap_start, bootmap_start + bootmap_size - 1, bootmap_pages); - - free_bootmem_with_active_regions(nodeid, end); - - /* - * convert early reserve to bootmem reserve earlier - * otherwise early_node_mem could use early reserved mem - * on previous node - */ - early_res_to_bootmem(start, end); - - /* - * in some case early_node_mem could use alloc_bootmem - * to get range on other node, don't reserve that again - */ - if (nid != nodeid) - printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid); - else - reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, - pgdat_size, BOOTMEM_DEFAULT); nid = phys_to_nid(bootmap_start); if (nid != nodeid) printk(KERN_INFO " bootmap(%d) on node %d\n", nodeid, nid); - else - reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, - bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT); + + free_bootmem_with_active_regions(nodeid, end); +#endif node_set_online(nodeid); } @@ -709,6 +706,10 @@ unsigned long __init numa_free_all_bootmem(void) for_each_online_node(i) pages += free_all_bootmem_node(NODE_DATA(i)); +#ifdef CONFIG_NO_BOOTMEM + pages += free_all_memory_core_early(MAX_NUMNODES); +#endif + return pages; } diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 39fba37f702f..0b7d3e9593e1 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -14,8 +14,7 @@ obj-$(CONFIG_X86_VISWS) += visws.o obj-$(CONFIG_X86_NUMAQ) += numaq_32.o obj-y += common.o early.o -obj-y += amd_bus.o -obj-$(CONFIG_X86_64) += bus_numa.o +obj-y += amd_bus.o bus_numa.o ifeq ($(CONFIG_PCI_DEBUG),y) EXTRA_CFLAGS += -DDEBUG diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 95ecbd495955..fc1e8fe07e5c 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -2,11 +2,11 @@ #include <linux/pci.h> #include <linux/topology.h> #include <linux/cpu.h> +#include <linux/range.h> + #include <asm/pci_x86.h> -#ifdef CONFIG_X86_64 #include <asm/pci-direct.h> -#endif #include "bus_numa.h" @@ -15,60 +15,6 @@ * also get peer root bus resource for io,mmio */ -#ifdef CONFIG_X86_64 - -#define RANGE_NUM 16 - -struct res_range { - size_t start; - size_t end; -}; - -static void __init update_range(struct res_range *range, size_t start, - size_t end) -{ - int i; - int j; - - for (j = 0; j < RANGE_NUM; j++) { - if (!range[j].end) - continue; - - if (start <= range[j].start && end >= range[j].end) { - range[j].start = 0; - range[j].end = 0; - continue; - } - - if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) { - range[j].start = end + 1; - continue; - } - - - if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) { - range[j].end = start - 1; - continue; - } - - if (start > range[j].start && end < range[j].end) { - /* find the new spare */ - for (i = 0; i < RANGE_NUM; i++) { - if (range[i].end == 0) - break; - } - if (i < RANGE_NUM) { - range[i].end = range[j].end; - range[i].start = end + 1; - } else { - printk(KERN_ERR "run of slot in ranges\n"); - } - range[j].end = start - 1; - continue; - } - } -} - struct pci_hostbridge_probe { u32 bus; u32 slot; @@ -111,6 +57,8 @@ static void __init get_pci_mmcfg_amd_fam10h_range(void) fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1; } +#define RANGE_NUM 16 + /** * early_fill_mp_bus_to_node() * called before pcibios_scan_root and pci_scan_bus @@ -130,16 +78,17 @@ static int __init early_fill_mp_bus_info(void) struct pci_root_info *info; u32 reg; struct resource *res; - size_t start; - size_t end; - struct res_range range[RANGE_NUM]; + u64 start; + u64 end; + struct range range[RANGE_NUM]; u64 val; u32 address; + bool found; if (!early_pci_allowed()) return -1; - found_all_numa_early = 0; + found = false; for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { u32 id; u16 device; @@ -153,12 +102,12 @@ static int __init early_fill_mp_bus_info(void) device = (id>>16) & 0xffff; if (pci_probes[i].vendor == vendor && pci_probes[i].device == device) { - found_all_numa_early = 1; + found = true; break; } } - if (!found_all_numa_early) + if (!found) return 0; pci_root_num = 0; @@ -196,7 +145,7 @@ static int __init early_fill_mp_bus_info(void) def_link = (reg >> 8) & 0x03; memset(range, 0, sizeof(range)); - range[0].end = 0xffff; + add_range(range, RANGE_NUM, 0, 0, 0xffff + 1); /* io port resource */ for (i = 0; i < 4; i++) { reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3)); @@ -220,13 +169,13 @@ static int __init early_fill_mp_bus_info(void) info = &pci_root_info[j]; printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n", - node, link, (u64)start, (u64)end); + node, link, start, end); /* kernel only handle 16 bit only */ if (end > 0xffff) end = 0xffff; update_res(info, start, end, IORESOURCE_IO, 1); - update_range(range, start, end); + subtract_range(range, RANGE_NUM, start, end + 1); } /* add left over io port range to def node/link, [0, 0xffff] */ /* find the position */ @@ -241,29 +190,32 @@ static int __init early_fill_mp_bus_info(void) if (!range[i].end) continue; - update_res(info, range[i].start, range[i].end, + update_res(info, range[i].start, range[i].end - 1, IORESOURCE_IO, 1); } } memset(range, 0, sizeof(range)); /* 0xfd00000000-0xffffffffff for HT */ - range[0].end = (0xfdULL<<32) - 1; + end = cap_resource((0xfdULL<<32) - 1); + end++; + add_range(range, RANGE_NUM, 0, 0, end); /* need to take out [0, TOM) for RAM*/ address = MSR_K8_TOP_MEM1; rdmsrl(address, val); end = (val & 0xffffff800000ULL); - printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20); + printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20); if (end < (1ULL<<32)) - update_range(range, 0, end - 1); + subtract_range(range, RANGE_NUM, 0, end); /* get mmconfig */ get_pci_mmcfg_amd_fam10h_range(); /* need to take out mmconf range */ if (fam10h_mmconf_end) { printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end); - update_range(range, fam10h_mmconf_start, fam10h_mmconf_end); + subtract_range(range, RANGE_NUM, fam10h_mmconf_start, + fam10h_mmconf_end + 1); } /* mmio resource */ @@ -293,7 +245,7 @@ static int __init early_fill_mp_bus_info(void) info = &pci_root_info[j]; printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]", - node, link, (u64)start, (u64)end); + node, link, start, end); /* * some sick allocation would have range overlap with fam10h * mmconf range, so need to update start and end. @@ -318,14 +270,15 @@ static int __init early_fill_mp_bus_info(void) /* we got a hole */ endx = fam10h_mmconf_start - 1; update_res(info, start, endx, IORESOURCE_MEM, 0); - update_range(range, start, endx); - printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx); + subtract_range(range, RANGE_NUM, start, + endx + 1); + printk(KERN_CONT " ==> [%llx, %llx]", start, endx); start = fam10h_mmconf_end + 1; changed = 1; } if (changed) { if (start <= end) { - printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end); + printk(KERN_CONT " %s [%llx, %llx]", endx ? "and" : "==>", start, end); } else { printk(KERN_CONT "%s\n", endx?"":" ==> none"); continue; @@ -333,8 +286,9 @@ static int __init early_fill_mp_bus_info(void) } } - update_res(info, start, end, IORESOURCE_MEM, 1); - update_range(range, start, end); + update_res(info, cap_resource(start), cap_resource(end), + IORESOURCE_MEM, 1); + subtract_range(range, RANGE_NUM, start, end + 1); printk(KERN_CONT "\n"); } @@ -348,8 +302,8 @@ static int __init early_fill_mp_bus_info(void) address = MSR_K8_TOP_MEM2; rdmsrl(address, val); end = (val & 0xffffff800000ULL); - printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20); - update_range(range, 1ULL<<32, end - 1); + printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20); + subtract_range(range, RANGE_NUM, 1ULL<<32, end); } /* @@ -368,7 +322,8 @@ static int __init early_fill_mp_bus_info(void) if (!range[i].end) continue; - update_res(info, range[i].start, range[i].end, + update_res(info, cap_resource(range[i].start), + cap_resource(range[i].end - 1), IORESOURCE_MEM, 1); } } @@ -384,24 +339,14 @@ static int __init early_fill_mp_bus_info(void) info->bus_min, info->bus_max, info->node, info->link); for (j = 0; j < res_num; j++) { res = &info->res[j]; - printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n", - busnum, j, - (res->flags & IORESOURCE_IO)?"io port":"mmio", - res->start, res->end); + printk(KERN_DEBUG "bus: %02x index %x %pR\n", + busnum, j, res); } } return 0; } -#else /* !CONFIG_X86_64 */ - -static int __init early_fill_mp_bus_info(void) { return 0; } - -#endif /* !CONFIG_X86_64 */ - -/* common 32/64 bit code */ - #define ENABLE_CF8_EXT_CFG (1ULL << 46) static void enable_pci_io_ecs(void *unused) diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 12d54ff3654d..64a122883896 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -1,11 +1,11 @@ #include <linux/init.h> #include <linux/pci.h> +#include <linux/range.h> #include "bus_numa.h" int pci_root_num; struct pci_root_info pci_root_info[PCI_ROOT_NR]; -int found_all_numa_early; void x86_pci_root_bus_res_quirks(struct pci_bus *b) { @@ -21,10 +21,6 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) if (!pci_root_num) return; - /* for amd, if only one root bus, don't need to do anything */ - if (pci_root_num < 2 && found_all_numa_early) - return; - for (i = 0; i < pci_root_num; i++) { if (pci_root_info[i].bus_min == b->number) break; @@ -52,8 +48,8 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) } } -void __devinit update_res(struct pci_root_info *info, size_t start, - size_t end, unsigned long flags, int merge) +void __devinit update_res(struct pci_root_info *info, resource_size_t start, + resource_size_t end, unsigned long flags, int merge) { int i; struct resource *res; @@ -61,25 +57,28 @@ void __devinit update_res(struct pci_root_info *info, size_t start, if (start > end) return; + if (start == MAX_RESOURCE) + return; + if (!merge) goto addit; /* try to merge it with old one */ for (i = 0; i < info->res_num; i++) { - size_t final_start, final_end; - size_t common_start, common_end; + resource_size_t final_start, final_end; + resource_size_t common_start, common_end; res = &info->res[i]; if (res->flags != flags) continue; - common_start = max((size_t)res->start, start); - common_end = min((size_t)res->end, end); + common_start = max(res->start, start); + common_end = min(res->end, end); if (common_start > common_end + 1) continue; - final_start = min((size_t)res->start, start); - final_end = max((size_t)res->end, end); + final_start = min(res->start, start); + final_end = max(res->end, end); res->start = final_start; res->end = final_end; diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h index 731b64ee8d84..804a4b40c31a 100644 --- a/arch/x86/pci/bus_numa.h +++ b/arch/x86/pci/bus_numa.h @@ -1,5 +1,5 @@ -#ifdef CONFIG_X86_64 - +#ifndef __BUS_NUMA_H +#define __BUS_NUMA_H /* * sub bus (transparent) will use entres from 3 to store extra from * root, so need to make sure we have enough slot there. @@ -19,8 +19,7 @@ struct pci_root_info { #define PCI_ROOT_NR 4 extern int pci_root_num; extern struct pci_root_info pci_root_info[PCI_ROOT_NR]; -extern int found_all_numa_early; -extern void update_res(struct pci_root_info *info, size_t start, - size_t end, unsigned long flags, int merge); +extern void update_res(struct pci_root_info *info, resource_size_t start, + resource_size_t end, unsigned long flags, int merge); #endif diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 5a8fbf8d4cac..dece3eb9c906 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -255,10 +255,6 @@ 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/xen/enlighten.c b/arch/x86/xen/enlighten.c index 36daccb68642..b607239c1ba8 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -50,6 +50,7 @@ #include <asm/traps.h> #include <asm/setup.h> #include <asm/desc.h> +#include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/reboot.h> @@ -1094,6 +1095,12 @@ asmlinkage void __init xen_start_kernel(void) __supported_pte_mask |= _PAGE_IOMAP; + /* + * Prevent page tables from being allocated in highmem, even + * if CONFIG_HIGHPTE is enabled. + */ + __userpte_alloc_gfp &= ~__GFP_HIGHMEM; + /* Work out if we support NX */ x86_configure_nx(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index bf4cd6bfe959..f9eb7de74f42 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1427,23 +1427,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) #endif } -#ifdef CONFIG_HIGHPTE -static void *xen_kmap_atomic_pte(struct page *page, enum km_type type) -{ - pgprot_t prot = PAGE_KERNEL; - - if (PagePinned(page)) - prot = PAGE_KERNEL_RO; - - if (0 && PageHighMem(page)) - printk("mapping highpte %lx type %d prot %s\n", - page_to_pfn(page), type, - (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ"); - - return kmap_atomic_prot(page, type, prot); -} -#endif - #ifdef CONFIG_X86_32 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) { @@ -1902,10 +1885,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .alloc_pmd_clone = paravirt_nop, .release_pmd = xen_release_pmd_init, -#ifdef CONFIG_HIGHPTE - .kmap_atomic_pte = xen_kmap_atomic_pte, -#endif - #ifdef CONFIG_X86_64 .set_pte = xen_set_pte, #else diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index 88e15deb8b82..22a2093b5862 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -90,9 +90,9 @@ ENTRY(xen_iret) GET_THREAD_INFO(%eax) movl TI_cpu(%eax), %eax movl __per_cpu_offset(,%eax,4), %eax - mov per_cpu__xen_vcpu(%eax), %eax + mov xen_vcpu(%eax), %eax #else - movl per_cpu__xen_vcpu, %eax + movl xen_vcpu, %eax #endif /* check IF state we're restoring */ |