diff options
Diffstat (limited to 'arch/x86')
43 files changed, 562 insertions, 434 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bc25b9f5e4cd..c9086e6307a5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -353,6 +353,7 @@ config X86_UV bool "SGI Ultraviolet" depends on X86_64 depends on X86_EXTENDED_PLATFORM + depends on NUMA select X86_X2APIC ---help--- This option is needed in order to support SGI Ultraviolet systems. diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 924e156a85ab..8130334329c0 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -506,6 +506,7 @@ config X86_PTRACE_BTS bool "Branch Trace Store" default y depends on X86_DEBUGCTLMSR + depends on BROKEN ---help--- This adds a ptrace interface to the hardware's branch trace store. diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index efac92fd1efb..085a8c35f149 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -129,21 +129,12 @@ asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename, struct stat64 __user *statbuf, int flag) { struct kstat stat; - int error = -EINVAL; + int error; - if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0) - goto out; - - if (flag & AT_SYMLINK_NOFOLLOW) - error = vfs_lstat_fd(dfd, filename, &stat); - else - error = vfs_stat_fd(dfd, filename, &stat); - - if (!error) - error = cp_stat64(statbuf, &stat); - -out: - return error; + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_stat64(statbuf, &stat); } /* diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 5623c50d67b2..c45f415ce315 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -37,7 +37,7 @@ extern gate_desc idt_table[]; struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); -DECLARE_PER_CPU(struct gdt_page, gdt_page); +DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) { diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 039db6aa8e02..37555e52f980 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -26,7 +26,7 @@ typedef struct { #endif } ____cacheline_aligned irq_cpustat_t; -DECLARE_PER_CPU(irq_cpustat_t, irq_stat); +DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); /* We can have at most NR_VECTORS irqs routed to a cpu at a time */ #define MAX_HARDIRQS_PER_CPU NR_VECTORS diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e5383e3d2f8c..73739322b6d0 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -193,8 +193,10 @@ extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); */ extern void early_ioremap_init(void); extern void early_ioremap_reset(void); -extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); -extern void __iomem *early_memremap(unsigned long offset, unsigned long size); +extern void __iomem *early_ioremap(resource_size_t phys_addr, + unsigned long size); +extern void __iomem *early_memremap(resource_size_t phys_addr, + unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 0f4ee7148afe..faae1996487b 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -5,7 +5,6 @@ #define LHCALL_FLUSH_ASYNC 0 #define LHCALL_LGUEST_INIT 1 #define LHCALL_SHUTDOWN 2 -#define LHCALL_LOAD_GDT 3 #define LHCALL_NEW_PGTABLE 4 #define LHCALL_FLUSH_TLB 5 #define LHCALL_LOAD_IDT_ENTRY 6 @@ -17,6 +16,7 @@ #define LHCALL_SET_PMD 15 #define LHCALL_LOAD_TLS 16 #define LHCALL_NOTIFY 17 +#define LHCALL_LOAD_GDT_ENTRY 18 #define LGUEST_TRAP_ENTRY 0x1F diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 2cd07b9422f4..7af14e512f97 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -18,9 +18,5 @@ extern int free_memtype(u64 start, u64 end); extern int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flag); -extern void map_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); -extern void unmap_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 34c52370f2fe..c2cceae709c8 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -138,7 +138,7 @@ extern struct tss_struct doublefault_tss; extern __u32 cleared_cpu_caps[NCAPINTS]; #ifdef CONFIG_SMP -DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info); +DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) #define current_cpu_data __get_cpu_var(cpu_info) #else @@ -270,7 +270,7 @@ struct tss_struct { } ____cacheline_aligned; -DECLARE_PER_CPU(struct tss_struct, init_tss); +DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss); /* * Save the original ist values for checking stack pointers during debugging @@ -352,6 +352,11 @@ struct i387_soft_struct { u32 entry_eip; }; +struct ymmh_struct { + /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ + u32 ymmh_space[64]; +}; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -361,6 +366,7 @@ struct xsave_hdr_struct { struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; + struct ymmh_struct ymmh; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); @@ -387,7 +393,7 @@ union irq_stack_union { }; }; -DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); +DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union); DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d5cd6c586881..a4737dddfd58 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -50,7 +50,7 @@ #ifdef CONFIG_X86_64 #define NEED_PSE 0 #define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) -#define NEED_PGE (1<<(X86_FEATURE_PGE & 31)) +#define NEED_PGE 0 #define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) #define NEED_XMM (1<<(X86_FEATURE_XMM & 31)) #define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31)) diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index ec666491aaa4..72e5a4491661 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -269,6 +269,11 @@ struct _xsave_hdr { __u64 reserved2[5]; }; +struct _ymmh_state { + /* 16 * 16 bytes for each YMMH-reg */ + __u32 ymmh_space[64]; +}; + /* * Extended state pointed by the fpstate pointer in the sigcontext. * In addition to the fpstate, information encoded in the xstate_hdr @@ -278,6 +283,7 @@ struct _xsave_hdr { struct _xstate { struct _fpstate fpstate; struct _xsave_hdr xstate_hdr; + struct _ymmh_state ymmh; /* new processor state extensions go here */ }; diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d3539f998f88..16a5c84b0329 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -152,7 +152,7 @@ struct tlb_state { struct mm_struct *active_mm; int state; }; -DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate); +DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); static inline void reset_lazy_tlbstate(void) { diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index db68ac8a5ac2..2cae46c7c8a2 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -17,6 +17,11 @@ /* ========================================================================= */ /* UVH_BAU_DATA_CONFIG */ /* ========================================================================= */ +#define UVH_LB_BAU_MISC_CONTROL 0x320170UL +#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL +/* 1011 timebase 7 (168millisec) * 3 ticks -> 500ms */ #define UVH_BAU_DATA_CONFIG 0x61680UL #define UVH_BAU_DATA_CONFIG_32 0x0438 diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a918dde46b5..018a0a400799 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -124,7 +124,8 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) static inline unsigned long pte_mfn(pte_t pte) diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 08e9a1ac07a9..727acc152344 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -7,6 +7,7 @@ #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -15,7 +16,7 @@ /* * These are the features that the OS can handle currently. */ -#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE) +#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 767fe7e46d68..a2789e42e162 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2524,7 +2524,6 @@ static void irq_complete_move(struct irq_desc **descp) static inline void irq_complete_move(struct irq_desc **descp) {} #endif -#ifdef CONFIG_X86_X2APIC static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) { int apic, pin; @@ -2558,6 +2557,7 @@ eoi_ioapic_irq(struct irq_desc *desc) spin_unlock_irqrestore(&ioapic_lock, flags); } +#ifdef CONFIG_X86_X2APIC static void ack_x2apic_level(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -2634,6 +2634,9 @@ static void ack_apic_level(unsigned int irq) */ ack_APIC_irq(); + if (irq_remapped(irq)) + eoi_ioapic_irq(desc); + /* Now we can move and renable the irq */ if (unlikely(do_unmask_irq)) { /* Only migrate the irq if the ack has been received. diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1248318436e8..de1a50af807b 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -549,7 +549,8 @@ void __init uv_system_init(void) unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; int max_pnode = 0; - unsigned long mmr_base, present; + unsigned long mmr_base, present, paddr; + unsigned short pnode_mask; map_low_mmrs(); @@ -592,6 +593,7 @@ void __init uv_system_init(void) } } + pnode_mask = (1 << n_val) - 1; node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_upper = (((unsigned long)node_id.s.node_id) & ~((1 << n_val) - 1)) << m_val; @@ -615,7 +617,7 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->numa_blade_id = blade; uv_cpu_hub_info(cpu)->blade_processor_id = lcpu; uv_cpu_hub_info(cpu)->pnode = pnode; - uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1; + uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1; uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper; uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base; @@ -631,6 +633,16 @@ void __init uv_system_init(void) lcpu, blade); } + /* Add blade/pnode info for nodes without cpus */ + for_each_online_node(nid) { + if (uv_node_to_blade[nid] >= 0) + continue; + paddr = node_start_pfn(nid) << PAGE_SHIFT; + pnode = (paddr >> m_val) & pnode_mask; + blade = boot_pnode_to_blade(pnode); + uv_node_to_blade[nid] = blade; + } + map_gru_high(max_pnode); map_mmr_high(max_pnode); map_config_high(max_pnode); diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c index f63882728d91..63a88e1f987d 100644 --- a/arch/x86/kernel/bios_uv.c +++ b/arch/x86/kernel/bios_uv.c @@ -182,7 +182,8 @@ void uv_bios_init(void) memcpy(&uv_systab, tab, sizeof(struct uv_systab)); iounmap(tab); - printk(KERN_INFO "EFI UV System Table Revision %d\n", tab->revision); + printk(KERN_INFO "EFI UV System Table Revision %d\n", + uv_systab.revision); } #else /* !CONFIG_EFI */ diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 9d3af380c6bd..ecdb682ab516 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -153,7 +153,8 @@ struct drv_cmd { u32 val; }; -static long do_drv_read(void *_cmd) +/* Called via smp_call_function_single(), on the target CPU */ +static void do_drv_read(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 h; @@ -170,10 +171,10 @@ static long do_drv_read(void *_cmd) default: break; } - return 0; } -static long do_drv_write(void *_cmd) +/* Called via smp_call_function_many(), on the target CPUs */ +static void do_drv_write(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 lo, hi; @@ -192,23 +193,24 @@ static long do_drv_write(void *_cmd) default: break; } - return 0; } static void drv_read(struct drv_cmd *cmd) { cmd->val = 0; - work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd); + smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1); } static void drv_write(struct drv_cmd *cmd) { - unsigned int i; + int this_cpu; - for_each_cpu(i, cmd->mask) { - work_on_cpu(i, do_drv_write, cmd); - } + this_cpu = get_cpu(); + if (cpumask_test_cpu(this_cpu, cmd->mask)) + do_drv_write(cmd); + smp_call_function_many(cmd->mask, do_drv_write, cmd, 1); + put_cpu(); } static u32 get_cur_val(const struct cpumask *mask) @@ -252,15 +254,13 @@ struct perf_pair { } aperf, mperf; }; - -static long read_measured_perf_ctrs(void *_cur) +/* Called via smp_call_function_single(), on the target CPU */ +static void read_measured_perf_ctrs(void *_cur) { struct perf_pair *cur = _cur; rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi); rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi); - - return 0; } /* @@ -283,7 +283,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int perf_percent; unsigned int retval; - if (!work_on_cpu(cpu, read_measured_perf_ctrs, &readin)) + if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1)) return 0; cur.aperf.whole = readin.aperf.whole - diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 648b3a2a3a44..3f0019e0a229 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -722,7 +722,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, /* * Clock source related code */ -static cycle_t read_hpet(void) +static cycle_t read_hpet(struct clocksource *cs) { return (cycle_t)hpet_readl(HPET_COUNTER); } @@ -756,7 +756,7 @@ static int hpet_clocksource_register(void) hpet_restart_counter(); /* Verify whether hpet counter works */ - t1 = read_hpet(); + t1 = hpet_readl(HPET_COUNTER); rdtscll(start); /* @@ -770,7 +770,7 @@ static int hpet_clocksource_register(void) rdtscll(now); } while ((now - start) < 200000UL); - if (t1 == read_hpet()) { + if (t1 == hpet_readl(HPET_COUNTER)) { printk(KERN_WARNING "HPET counter not counting. HPET disabled\n"); return -ENODEV; diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 3475440baa54..c2e0bb0890d4 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -129,7 +129,7 @@ void __init setup_pit_timer(void) * to just read by itself. So use jiffies to emulate a free * running counter: */ -static cycle_t pit_read(void) +static cycle_t pit_read(struct clocksource *cs) { static int old_count; static u32 old_jifs; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 137f2e8132df..223af43f1526 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -77,6 +77,11 @@ static cycle_t kvm_clock_read(void) return ret; } +static cycle_t kvm_clock_get_cycles(struct clocksource *cs) +{ + return kvm_clock_read(); +} + /* * If we don't do that, there is the possibility that the guest * will calibrate under heavy load - thus, getting a lower lpj - @@ -107,7 +112,7 @@ static void kvm_get_preset_lpj(void) static struct clocksource kvm_clock = { .name = "kvm-clock", - .read = kvm_clock_read, + .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .mult = 1 << KVM_SCALE, diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index a0f3851ef310..98c470c069d1 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -108,40 +108,29 @@ struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(ucode_cpu_info); #ifdef CONFIG_MICROCODE_OLD_INTERFACE -struct update_for_cpu { - const void __user *buf; - size_t size; -}; - -static long update_for_cpu(void *_ufc) -{ - struct update_for_cpu *ufc = _ufc; - int error; - - error = microcode_ops->request_microcode_user(smp_processor_id(), - ufc->buf, ufc->size); - if (error < 0) - return error; - if (!error) - microcode_ops->apply_microcode(smp_processor_id()); - return error; -} - static int do_microcode_update(const void __user *buf, size_t size) { + cpumask_t old; int error = 0; int cpu; - struct update_for_cpu ufc = { .buf = buf, .size = size }; + + old = current->cpus_allowed; for_each_online_cpu(cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!uci->valid) continue; - error = work_on_cpu(cpu, update_for_cpu, &ufc); + + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); + error = microcode_ops->request_microcode_user(cpu, buf, size); if (error < 0) - break; + goto out; + if (!error) + microcode_ops->apply_microcode(cpu); } +out: + set_cpus_allowed_ptr(current, &old); return error; } @@ -391,8 +380,6 @@ static int mc_sysdev_add(struct sys_device *sys_dev) return err; err = microcode_init_cpu(cpu); - if (err) - sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); return err; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index dce99dca6cf8..70fd7e414c15 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -679,7 +679,7 @@ void __init get_smp_config(void) __get_smp_config(0); } -static void smp_reserve_bootmem(struct mpf_intel *mpf) +static void __init smp_reserve_bootmem(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); #ifdef CONFIG_X86_32 @@ -838,7 +838,7 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m) static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM]; -static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) +static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) { int i; @@ -866,7 +866,8 @@ static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) } } #else /* CONFIG_X86_IO_APIC */ -static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} +static +inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} #endif /* CONFIG_X86_IO_APIC */ static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 34f12e9996ed..221a3853e268 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -50,7 +50,7 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -struct dma_map_ops swiotlb_dma_ops = { +static struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index deb5ebb32c3b..ed0c33761e6d 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -25,6 +25,8 @@ static int uv_bau_retry_limit __read_mostly; /* position of pnode (which is nasid>>1): */ static int uv_nshift __read_mostly; +/* base pnode in this partition */ +static int uv_partition_base_pnode __read_mostly; static unsigned long uv_mmask __read_mostly; @@ -32,6 +34,34 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); /* + * Determine the first node on a blade. + */ +static int __init blade_to_first_node(int blade) +{ + int node, b; + + for_each_online_node(node) { + b = uv_node_to_blade_id(node); + if (blade == b) + return node; + } + return -1; /* shouldn't happen */ +} + +/* + * Determine the apicid of the first cpu on a blade. + */ +static int __init blade_to_first_apicid(int blade) +{ + int cpu; + + for_each_present_cpu(cpu) + if (blade == uv_cpu_to_blade_id(cpu)) + return per_cpu(x86_cpu_to_apicid, cpu); + return -1; +} + +/* * Free a software acknowledge hardware resource by clearing its Pending * bit. This will return a reply to the sender. * If the message has timed out, a reply has already been sent by the @@ -67,7 +97,7 @@ static void uv_bau_process_message(struct bau_payload_queue_entry *msg, msp = __get_cpu_var(bau_control).msg_statuses + msg_slot; cpu = uv_blade_processor_id(); msg->number_of_cpus = - uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); + uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); this_cpu_mask = 1UL << cpu; if (msp->seen_by.bits & this_cpu_mask) return; @@ -215,14 +245,14 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * Returns @flush_mask if some remote flushing remains to be done. The * mask will have some bits still set. */ -const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, +const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode, struct bau_desc *bau_desc, struct cpumask *flush_mask) { int completion_status = 0; int right_shift; int tries = 0; - int blade; + int pnode; int bit; unsigned long mmr_offset; unsigned long index; @@ -265,8 +295,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, * use the IPI method of shootdown on them. */ for_each_cpu(bit, flush_mask) { - blade = uv_cpu_to_blade_id(bit); - if (blade == this_blade) + pnode = uv_cpu_to_pnode(bit); + if (pnode == this_pnode) continue; cpumask_clear_cpu(bit, flush_mask); } @@ -309,16 +339,16 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask); int i; int bit; - int blade; + int pnode; int uv_cpu; - int this_blade; + int this_pnode; int locals = 0; struct bau_desc *bau_desc; cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); uv_cpu = uv_blade_processor_id(); - this_blade = uv_numa_blade_id(); + this_pnode = uv_hub_info->pnode; bau_desc = __get_cpu_var(bau_control).descriptor_base; bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu; @@ -326,13 +356,14 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, i = 0; for_each_cpu(bit, flush_mask) { - blade = uv_cpu_to_blade_id(bit); - BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1)); - if (blade == this_blade) { + pnode = uv_cpu_to_pnode(bit); + BUG_ON(pnode > (UV_DISTRIBUTION_SIZE - 1)); + if (pnode == this_pnode) { locals++; continue; } - bau_node_set(blade, &bau_desc->distribution); + bau_node_set(pnode - uv_partition_base_pnode, + &bau_desc->distribution); i++; } if (i == 0) { @@ -350,7 +381,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, bau_desc->payload.address = va; bau_desc->payload.sending_cpu = cpu; - return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask); + return uv_flush_send_and_wait(uv_cpu, this_pnode, bau_desc, flush_mask); } /* @@ -418,24 +449,58 @@ void uv_bau_message_interrupt(struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * uv_enable_timeouts + * + * Each target blade (i.e. blades that have cpu's) needs to have + * shootdown message timeouts enabled. The timeout does not cause + * an interrupt, but causes an error message to be returned to + * the sender. + */ static void uv_enable_timeouts(void) { - int i; int blade; - int last_blade; + int nblades; int pnode; - int cur_cpu = 0; - unsigned long apicid; + unsigned long mmr_image; - last_blade = -1; - for_each_online_node(i) { - blade = uv_node_to_blade_id(i); - if (blade == last_blade) + nblades = uv_num_possible_blades(); + + for (blade = 0; blade < nblades; blade++) { + if (!uv_blade_nr_possible_cpus(blade)) continue; - last_blade = blade; - apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + pnode = uv_blade_to_pnode(blade); - cur_cpu += uv_blade_nr_possible_cpus(i); + mmr_image = + uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL); + /* + * Set the timeout period and then lock it in, in three + * steps; captures and locks in the period. + * + * To program the period, the SOFT_ACK_MODE must be off. + */ + mmr_image &= ~((unsigned long)1 << + UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + /* + * Set the 4-bit period. + */ + mmr_image &= ~((unsigned long)0xf << + UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD << + UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + /* + * Subsequent reversals of the timebase bit (3) cause an + * immediate timeout of one or all INTD resources as + * indicated in bits 2:0 (7 causes all of them to timeout). + */ + mmr_image |= ((unsigned long)1 << + UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); } } @@ -482,8 +547,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) stat->requestee, stat->onetlb, stat->alltlb, stat->s_retry, stat->d_retry, stat->ptc_i); seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n", - uv_read_global_mmr64(uv_blade_to_pnode - (uv_cpu_to_blade_id(cpu)), + uv_read_global_mmr64(uv_cpu_to_pnode(cpu), UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), stat->sflush, stat->dflush, stat->retriesok, stat->nomsg, @@ -617,16 +681,18 @@ static struct bau_control * __init uv_table_bases_init(int blade, int node) * finish the initialization of the per-blade control structures */ static void __init -uv_table_bases_finish(int blade, int node, int cur_cpu, +uv_table_bases_finish(int blade, struct bau_control *bau_tablesp, struct bau_desc *adp) { struct bau_control *bcp; - int i; + int cpu; - for (i = cur_cpu; i < cur_cpu + uv_blade_nr_possible_cpus(blade); i++) { - bcp = (struct bau_control *)&per_cpu(bau_control, i); + for_each_present_cpu(cpu) { + if (blade != uv_cpu_to_blade_id(cpu)) + continue; + bcp = (struct bau_control *)&per_cpu(bau_control, cpu); bcp->bau_msg_head = bau_tablesp->va_queue_first; bcp->va_queue_first = bau_tablesp->va_queue_first; bcp->va_queue_last = bau_tablesp->va_queue_last; @@ -649,11 +715,10 @@ uv_activation_descriptor_init(int node, int pnode) struct bau_desc *adp; struct bau_desc *ad2; - adp = (struct bau_desc *) - kmalloc_node(16384, GFP_KERNEL, node); + adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node); BUG_ON(!adp); - pa = __pa((unsigned long)adp); + pa = uv_gpa(adp); /* need the real nasid*/ n = pa >> uv_nshift; m = pa & uv_mmask; @@ -667,8 +732,12 @@ uv_activation_descriptor_init(int node, int pnode) for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) { memset(ad2, 0, sizeof(struct bau_desc)); ad2->header.sw_ack_flag = 1; - ad2->header.base_dest_nodeid = - uv_blade_to_pnode(uv_cpu_to_blade_id(0)); + /* + * base_dest_nodeid is the first node in the partition, so + * the bit map will indicate partition-relative node numbers. + * note that base_dest_nodeid is actually a nasid. + */ + ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1; ad2->header.command = UV_NET_ENDPOINT_INTD; ad2->header.int_both = 1; /* @@ -686,6 +755,8 @@ static struct bau_payload_queue_entry * __init uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) { struct bau_payload_queue_entry *pqp; + unsigned long pa; + int pn; char *cp; pqp = (struct bau_payload_queue_entry *) kmalloc_node( @@ -696,10 +767,14 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) cp = (char *)pqp + 31; pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5); bau_tablesp->va_queue_first = pqp; + /* + * need the pnode of where the memory was really allocated + */ + pa = uv_gpa(pqp); + pn = pa >> uv_nshift; uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, - ((unsigned long)pnode << - UV_PAYLOADQ_PNODE_SHIFT) | + ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | uv_physnodeaddr(pqp)); uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, uv_physnodeaddr(pqp)); @@ -715,8 +790,9 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) /* * Initialization of each UV blade's structures */ -static int __init uv_init_blade(int blade, int node, int cur_cpu) +static int __init uv_init_blade(int blade) { + int node; int pnode; unsigned long pa; unsigned long apicid; @@ -724,16 +800,17 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu) struct bau_payload_queue_entry *pqp; struct bau_control *bau_tablesp; + node = blade_to_first_node(blade); bau_tablesp = uv_table_bases_init(blade, node); pnode = uv_blade_to_pnode(blade); adp = uv_activation_descriptor_init(node, pnode); pqp = uv_payload_queue_init(node, pnode, bau_tablesp); - uv_table_bases_finish(blade, node, cur_cpu, bau_tablesp, adp); + uv_table_bases_finish(blade, bau_tablesp, adp); /* * the below initialization can't be in firmware because the * messaging IRQ will be determined by the OS */ - apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + apicid = blade_to_first_apicid(blade); pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); if ((pa & 0xff) != UV_BAU_MESSAGE) { uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, @@ -748,9 +825,7 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu) static int __init uv_bau_init(void) { int blade; - int node; int nblades; - int last_blade; int cur_cpu; if (!is_uv_system()) @@ -763,29 +838,21 @@ static int __init uv_bau_init(void) uv_bau_retry_limit = 1; uv_nshift = uv_hub_info->n_val; uv_mmask = (1UL << uv_hub_info->n_val) - 1; - nblades = 0; - last_blade = -1; - cur_cpu = 0; - for_each_online_node(node) { - blade = uv_node_to_blade_id(node); - if (blade == last_blade) - continue; - last_blade = blade; - nblades++; - } + nblades = uv_num_possible_blades(); + uv_bau_table_bases = (struct bau_control **) kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL); BUG_ON(!uv_bau_table_bases); - last_blade = -1; - for_each_online_node(node) { - blade = uv_node_to_blade_id(node); - if (blade == last_blade) - continue; - last_blade = blade; - uv_init_blade(blade, node, cur_cpu); - cur_cpu += uv_blade_nr_possible_cpus(blade); - } + uv_partition_base_pnode = 0x7fffffff; + for (blade = 0; blade < nblades; blade++) + if (uv_blade_nr_possible_cpus(blade) && + (uv_blade_to_pnode(blade) < uv_partition_base_pnode)) + uv_partition_base_pnode = uv_blade_to_pnode(blade); + for (blade = 0; blade < nblades; blade++) + if (uv_blade_nr_possible_cpus(blade)) + uv_init_blade(blade); + alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); uv_enable_timeouts(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7a567ebe6361..d57de05dc430 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -699,7 +699,7 @@ static struct clocksource clocksource_tsc; * code, which is necessary to support wrapping clocksources like pm * timer. */ -static cycle_t read_tsc(void) +static cycle_t read_tsc(struct clocksource *cs) { cycle_t ret = (cycle_t)get_cycles(); diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c index 67f9b9dbf800..36afb98675a4 100644 --- a/arch/x86/kernel/uv_sysfs.c +++ b/arch/x86/kernel/uv_sysfs.c @@ -21,6 +21,7 @@ #include <linux/sysdev.h> #include <asm/uv/bios.h> +#include <asm/uv/uv.h> struct kobject *sgi_uv_kobj; @@ -47,6 +48,9 @@ static int __init sgi_uv_sysfs_init(void) { unsigned long ret; + if (!is_uv_system()) + return -ENODEV; + if (!sgi_uv_kobj) sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj); if (!sgi_uv_kobj) { diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index d303369a7bad..2b3eb82efeeb 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -283,7 +283,7 @@ void __devinit vmi_time_ap_init(void) /** vmi clocksource */ static struct clocksource clocksource_vmi; -static cycle_t read_real_cycles(void) +static cycle_t read_real_cycles(struct clocksource *cs) { cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); return max(ret, clocksource_vmi.cycle_last); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 2b54fe002e94..0a5b04aa98f1 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -324,7 +324,7 @@ void __ref xsave_cntxt_init(void) } /* - * for now OS knows only about FP/SSE + * Support only the state known to OS. */ pcntxt_mask = pcntxt_mask & XCNTXT_MASK; xsave_init(); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2a36f7f7c4c7..b6caf1329b1b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1248,7 +1248,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; - sp->global = role.cr4_pge; + sp->global = 0; hlist_add_head(&sp->hash_link, bucket); if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8ca100a9ecac..7c1ce5ac6131 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2775,6 +2775,9 @@ out: void kvm_arch_exit(void) { + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); kvm_x86_ops = NULL; kvm_mmu_module_exit(); } @@ -4159,6 +4162,11 @@ EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + if (vcpu->arch.time_page) { + kvm_release_page_dirty(vcpu->arch.time_page); + vcpu->arch.time_page = NULL; + } + kvm_x86_ops->vcpu_free(vcpu); } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index e94a11e42f98..ca7ec44bafc3 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -273,15 +273,15 @@ static void lguest_load_idt(const struct desc_ptr *desc) * controls the entire thing and the Guest asks it to make changes using the * LOAD_GDT hypercall. * - * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY - * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? Wouldn't - * it be even better if you were the one to send the patch to fix it? + * This is the exactly like the IDT code. */ static void lguest_load_gdt(const struct desc_ptr *desc) { - BUG_ON((desc->size + 1) / 8 != GDT_ENTRIES); - kvm_hypercall2(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES); + unsigned int i; + struct desc_struct *gdt = (void *)desc->address; + + for (i = 0; i < (desc->size+1)/8; i++) + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b); } /* For a single GDT entry which changes, we do the lazy thing: alter our GDT, @@ -291,7 +291,9 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) { native_write_gdt_entry(dt, entrynum, desc, type); - kvm_hypercall2(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES); + /* Tell Host about this new entry. */ + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum, + dt[entrynum].a, dt[entrynum].b); } /* OK, I lied. There are three "thread local storage" GDT entries which change @@ -661,7 +663,7 @@ static unsigned long lguest_tsc_khz(void) /* If we can't use the TSC, the kernel falls back to our lower-priority * "lguest_clock", where we read the time value given to us by the Host. */ -static cycle_t lguest_clock_read(void) +static cycle_t lguest_clock_read(struct clocksource *cs) { unsigned long sec, nsec; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index be54176e9eb2..6340cef6798a 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -219,6 +219,22 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_sem. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. + */ int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0dfa09d69e80..8a450930834f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -280,15 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return NULL; area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; - if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { + + if (kernel_map_sync_memtype(phys_addr, size, prot_val)) { free_memtype(phys_addr, phys_addr + size); free_vm_area(area); return NULL; } - if (ioremap_change_attr(vaddr, size, prot_val) < 0) { + if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { free_memtype(phys_addr, phys_addr + size); - vunmap(area->addr); + free_vm_area(area); return NULL; } @@ -374,7 +375,8 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, * - UC_MINUS for non-WB-able memory with no other conflicting mappings * - Inherit from confliting mappings otherwise */ - err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags); + err = reserve_memtype(phys_addr, phys_addr + size, + _PAGE_CACHE_WB, &flags); if (err < 0) return NULL; @@ -547,7 +549,7 @@ void __init early_ioremap_reset(void) } static void __init __early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *pte; @@ -566,7 +568,7 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, } static inline void __init early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t prot) + phys_addr_t phys, pgprot_t prot) { if (after_paging_init) __set_fixmap(idx, phys, prot); @@ -607,9 +609,10 @@ static int __init check_early_ioremap_leak(void) late_initcall(check_early_ioremap_leak); static void __init __iomem * -__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) { - unsigned long offset, last_addr; + unsigned long offset; + resource_size_t last_addr; unsigned int nrpages; enum fixed_addresses idx0, idx; int i, slot; @@ -625,15 +628,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } if (slot < 0) { - printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n", - phys_addr, size); + printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n", + (u64)phys_addr, size); WARN_ON(1); return NULL; } if (early_ioremap_debug) { - printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ", - phys_addr, size, slot); + printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ", + (u64)phys_addr, size, slot); dump_stack(); } @@ -680,13 +683,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } /* Remap an IO device */ -void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); } /* Remap memory */ -void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_memremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL); } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index d71e1b636ce6..797f9f107cb6 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -945,71 +945,94 @@ int _set_memory_uc(unsigned long addr, int numpages) int set_memory_uc(unsigned long addr, int numpages) { + int ret; + /* * for now UC MINUS. see comments in ioremap_nocache() */ - if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_UC_MINUS, NULL)) - return -EINVAL; + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_err; + + ret = _set_memory_uc(addr, numpages); + if (ret) + goto out_free; - return _set_memory_uc(addr, numpages); + return 0; + +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_uc); int set_memory_array_uc(unsigned long *addr, int addrinarray) { - unsigned long start; - unsigned long end; - int i; + int i, j; + int ret; + /* * for now UC MINUS. see comments in ioremap_nocache() */ for (i = 0; i < addrinarray; i++) { - start = __pa(addr[i]); - for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) - goto out; + ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_free; } - return change_page_attr_set(addr, addrinarray, + ret = change_page_attr_set(addr, addrinarray, __pgprot(_PAGE_CACHE_UC_MINUS), 1); -out: - for (i = 0; i < addrinarray; i++) { - unsigned long tmp = __pa(addr[i]); - - if (tmp == start) - break; - for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - free_memtype(tmp, end); - } - return -EINVAL; + if (ret) + goto out_free; + + return 0; + +out_free: + for (j = 0; j < i; j++) + free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE); + + return ret; } EXPORT_SYMBOL(set_memory_array_uc); int _set_memory_wc(unsigned long addr, int numpages) { - return change_page_attr_set(&addr, numpages, + int ret; + ret = change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_CACHE_UC_MINUS), 0); + + if (!ret) { + ret = change_page_attr_set(&addr, numpages, __pgprot(_PAGE_CACHE_WC), 0); + } + return ret; } int set_memory_wc(unsigned long addr, int numpages) { + int ret; + if (!pat_enabled) return set_memory_uc(addr, numpages); - if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_WC, NULL)) - return -EINVAL; + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_WC, NULL); + if (ret) + goto out_err; + + ret = _set_memory_wc(addr, numpages); + if (ret) + goto out_free; + + return 0; - return _set_memory_wc(addr, numpages); +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_wc); @@ -1021,29 +1044,31 @@ int _set_memory_wb(unsigned long addr, int numpages) int set_memory_wb(unsigned long addr, int numpages) { - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + int ret; + + ret = _set_memory_wb(addr, numpages); + if (ret) + return ret; - return _set_memory_wb(addr, numpages); + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + return 0; } EXPORT_SYMBOL(set_memory_wb); int set_memory_array_wb(unsigned long *addr, int addrinarray) { int i; + int ret; - for (i = 0; i < addrinarray; i++) { - unsigned long start = __pa(addr[i]); - unsigned long end; - - for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - free_memtype(start, end); - } - return change_page_attr_clear(addr, addrinarray, + ret = change_page_attr_clear(addr, addrinarray, __pgprot(_PAGE_CACHE_MASK), 1); + if (ret) + return ret; + + for (i = 0; i < addrinarray; i++) + free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE); + + return 0; } EXPORT_SYMBOL(set_memory_array_wb); @@ -1136,6 +1161,8 @@ int set_pages_array_wb(struct page **pages, int addrinarray) retval = cpa_clear_pages_array(pages, addrinarray, __pgprot(_PAGE_CACHE_MASK)); + if (retval) + return retval; for (i = 0; i < addrinarray; i++) { start = (unsigned long)page_address(pages[i]); @@ -1143,7 +1170,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray) free_memtype(start, end); } - return retval; + return 0; } EXPORT_SYMBOL(set_pages_array_wb); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 640339ee4fb2..e6718bb28065 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -31,7 +31,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(const char *reason) +static inline void pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); @@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) u8 mtrr_type; mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == MTRR_TYPE_UNCACHABLE) - return _PAGE_CACHE_UC; - if (mtrr_type == MTRR_TYPE_WRCOMB) - return _PAGE_CACHE_WC; + if (mtrr_type != MTRR_TYPE_WRBACK) + return _PAGE_CACHE_UC_MINUS; + + return _PAGE_CACHE_WB; } return req_type; @@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return 0; } - if (req_type == -1) { - /* - * Call mtrr_lookup to get the type hint. This is an - * optimization for /dev/mem mmap'ers into WB memory (BIOS - * tools and ACPI tools). Use WB request for WB memory and use - * UC_MINUS otherwise. - */ - u8 mtrr_type = mtrr_type_lookup(start, end); - - if (mtrr_type == MTRR_TYPE_WRBACK) - actual_type = _PAGE_CACHE_WB; - else - actual_type = _PAGE_CACHE_UC_MINUS; - } else { - actual_type = pat_x_mtrr_type(start, end, - req_type & _PAGE_CACHE_MASK); - } + /* + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. + */ + actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK); if (new_type) *new_type = actual_type; @@ -546,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { - u64 offset = ((u64) pfn) << PAGE_SHIFT; - unsigned long flags = -1; - int retval; + unsigned long flags = _PAGE_CACHE_WB; if (!range_is_allowed(pfn, size)) return 0; @@ -576,64 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, } #endif - /* - * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot. - * - * Without O_SYNC, we want to get - * - WB for WB-able memory and no other conflicting mappings - * - UC_MINUS for non-WB-able memory with no other conflicting mappings - * - Inherit from confliting mappings otherwise - */ - if (flags != -1) { - retval = reserve_memtype(offset, offset + size, flags, NULL); - } else { - retval = reserve_memtype(offset, offset + size, -1, &flags); - } - - if (retval < 0) - return 0; - - if (((pfn < max_low_pfn_mapped) || - (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { - free_memtype(offset, offset + size); - printk(KERN_INFO - "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", - current->comm, current->pid, - cattr_name(flags), - offset, (unsigned long long)(offset + size)); - return 0; - } - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | flags); return 1; } -void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK); - u64 addr = (u64)pfn << PAGE_SHIFT; - unsigned long flags; - - reserve_memtype(addr, addr + size, want_flags, &flags); - if (flags != want_flags) { - printk(KERN_INFO - "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", - current->comm, current->pid, - cattr_name(want_flags), - addr, (unsigned long long)(addr + size), - cattr_name(flags)); - } -} - -void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - u64 addr = (u64)pfn << PAGE_SHIFT; - - free_memtype(addr, addr + size); -} - /* * Change the memory type for the physial address range in kernel identity * mapping space if that range is a part of identity map. @@ -671,8 +606,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, { int is_ram = 0; int ret; - unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); + unsigned long flags = want_flags; is_ram = pat_pagerange_is_ram(paddr, paddr + size); @@ -734,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size) * * If the vma has a linear pfn mapping for the entire range, we get the prot * from pte and reserve the entire vma range with single reserve_pfn_range call. - * Otherwise, we reserve the entire vma range, my ging through the PTEs page - * by page to get physical address and protection. */ int track_pfn_vma_copy(struct vm_area_struct *vma) { - int retval = 0; - unsigned long i, j; resource_size_t paddr; unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* * reserve the whole chunk covered by vma. We need the * starting address and protection from pte. */ - if (follow_phys(vma, vma_start, 0, &prot, &paddr)) { + if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { WARN_ON_ONCE(1); return -EINVAL; } @@ -764,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma) return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } - /* reserve entire vma page by page, using pfn and prot from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - pgprot = __pgprot(prot); - retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - if (follow_phys(vma, vma_start + j, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -795,50 +708,28 @@ cleanup_ret: * prot is passed in as a parameter for the new mapping. If the vma has a * linear pfn mapping for the entire range reserve the entire vma range with * single reserve_pfn_range call. - * Otherwise, we look t the pfn and size and reserve only the specified range - * page by page. - * - * Note that this function can be called with caller trying to map only a - * subrange/page inside the vma. */ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long size) { - int retval = 0; - unsigned long i, j; - resource_size_t base_paddr; resource_size_t paddr; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* reserve the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; return reserve_pfn_range(paddr, vma_size, prot, 0); } - /* reserve page by page using pfn and size */ - base_paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = base_paddr + i; - retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - paddr = base_paddr + j; - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -849,39 +740,23 @@ cleanup_ret: void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { - unsigned long i; resource_size_t paddr; - unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* free the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; free_pfn_range(paddr, vma_size); return; } - - if (size != 0 && size != vma_size) { - /* free page by page, using pfn and size */ - paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = paddr + i; - free_pfn_range(paddr, PAGE_SIZE); - } - } else { - /* free entire vma, page by page, using the pfn from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - } } pgprot_t pgprot_writecombine(pgprot_t prot) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 82cd39a6cbd3..f09e8c36ee80 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -42,6 +42,7 @@ #include <asm/xen/hypervisor.h> #include <asm/fixmap.h> #include <asm/processor.h> +#include <asm/proto.h> #include <asm/msr-index.h> #include <asm/setup.h> #include <asm/desc.h> @@ -168,21 +169,23 @@ static void __init xen_banner(void) xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; +static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; + static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { + unsigned maskecx = ~0; unsigned maskedx = ~0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. */ - if (*ax == 1) - maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ - (1 << X86_FEATURE_ACPI) | /* disable ACPI */ - (1 << X86_FEATURE_MCE) | /* disable MCE */ - (1 << X86_FEATURE_MCA) | /* disable MCA */ - (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + if (*ax == 1) { + maskecx = cpuid_leaf1_ecx_mask; + maskedx = cpuid_leaf1_edx_mask; + } asm(XEN_EMULATE_PREFIX "cpuid" : "=a" (*ax), @@ -190,9 +193,43 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, "=c" (*cx), "=d" (*dx) : "0" (*ax), "2" (*cx)); + + *cx &= maskecx; *dx &= maskedx; } +static __init void xen_init_cpuid_mask(void) +{ + unsigned int ax, bx, cx, dx; + + cpuid_leaf1_edx_mask = + ~((1 << X86_FEATURE_MCE) | /* disable MCE */ + (1 << X86_FEATURE_MCA) | /* disable MCA */ + (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + + if (!xen_initial_domain()) + cpuid_leaf1_edx_mask &= + ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ + (1 << X86_FEATURE_ACPI)); /* disable ACPI */ + + ax = 1; + xen_cpuid(&ax, &bx, &cx, &dx); + + /* cpuid claims we support xsave; try enabling it to see what happens */ + if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { + unsigned long cr4; + + set_in_cr4(X86_CR4_OSXSAVE); + + cr4 = read_cr4(); + + if ((cr4 & X86_CR4_OSXSAVE) == 0) + cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); + + clear_in_cr4(X86_CR4_OSXSAVE); + } +} + static void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); @@ -284,12 +321,11 @@ static void xen_set_ldt(const void *addr, unsigned entries) static void xen_load_gdt(const struct desc_ptr *dtr) { - unsigned long *frames; unsigned long va = dtr->address; unsigned int size = dtr->size + 1; unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE; + unsigned long frames[pages]; int f; - struct multicall_space mcs; /* A GDT can be up to 64k in size, which corresponds to 8192 8-byte entries, or 16 4k pages.. */ @@ -297,19 +333,26 @@ static void xen_load_gdt(const struct desc_ptr *dtr) BUG_ON(size > 65536); BUG_ON(va & ~PAGE_MASK); - mcs = xen_mc_entry(sizeof(*frames) * pages); - frames = mcs.args; - for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - frames[f] = arbitrary_virt_to_mfn((void *)va); + int level; + pte_t *ptep = lookup_address(va, &level); + unsigned long pfn, mfn; + void *virt; + + BUG_ON(ptep == NULL); + + pfn = pte_pfn(*ptep); + mfn = pfn_to_mfn(pfn); + virt = __va(PFN_PHYS(pfn)); + + frames[f] = mfn; make_lowmem_page_readonly((void *)va); - make_lowmem_page_readonly(mfn_to_virt(frames[f])); + make_lowmem_page_readonly(virt); } - MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct)); - - xen_mc_issue(PARAVIRT_LAZY_CPU); + if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + BUG(); } static void load_TLS_descriptor(struct thread_struct *t, @@ -385,7 +428,7 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { - if (val->type != 0xf && val->type != 0xe) + if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT) return 0; info->vector = vector; @@ -393,8 +436,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, info->cs = gate_segment(*val); info->flags = val->dpl; /* interrupt gates clear IF */ - if (val->type == 0xe) - info->flags |= 4; + if (val->type == GATE_INTERRUPT) + info->flags |= 1 << 2; return 1; } @@ -872,7 +915,6 @@ static const struct machine_ops __initdata xen_machine_ops = { .emergency_restart = xen_emergency_restart, }; - /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { @@ -897,6 +939,8 @@ asmlinkage void __init xen_start_kernel(void) xen_init_irq_ops(); + xen_init_cpuid_mask(); + #ifdef CONFIG_X86_LOCAL_APIC /* * set up the basic apic ops. @@ -938,6 +982,11 @@ asmlinkage void __init xen_start_kernel(void) if (!xen_initial_domain()) __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); +#ifdef CONFIG_X86_64 + /* Work out if we support NX */ + check_efer(); +#endif + /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2a81838a9ab7..9842b1212407 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -184,7 +184,7 @@ static inline unsigned p2m_index(unsigned long pfn) } /* Build the parallel p2m_top_mfn structures */ -void xen_setup_mfn_list_list(void) +static void __init xen_build_mfn_list_list(void) { unsigned pfn, idx; @@ -198,7 +198,10 @@ void xen_setup_mfn_list_list(void) unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); } +} +void xen_setup_mfn_list_list(void) +{ BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = @@ -218,6 +221,8 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_top[topidx] = &mfn_list[pfn]; } + + xen_build_mfn_list_list(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -233,47 +238,74 @@ unsigned long get_phys_to_machine(unsigned long pfn) } EXPORT_SYMBOL_GPL(get_phys_to_machine); -static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +/* install a new p2m_top page */ +bool install_p2mtop_page(unsigned long pfn, unsigned long *p) { - unsigned long *p; + unsigned topidx = p2m_top_index(pfn); + unsigned long **pfnp, *mfnp; unsigned i; - p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); - BUG_ON(p == NULL); + pfnp = &p2m_top[topidx]; + mfnp = &p2m_top_mfn[topidx]; for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++) p[i] = INVALID_P2M_ENTRY; - if (cmpxchg(pp, p2m_missing, p) != p2m_missing) - free_page((unsigned long)p); - else + if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) { *mfnp = virt_to_mfn(p); + return true; + } + + return false; } -void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +static void alloc_p2m(unsigned long pfn) { - unsigned topidx, idx; + unsigned long *p; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return; - } + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + if (!install_p2mtop_page(pfn, p)) + free_page((unsigned long)p); +} + +/* Try to install p2m mapping; fail if intermediate bits missing */ +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { BUG_ON(mfn != INVALID_P2M_ENTRY); - return; + return true; } topidx = p2m_top_index(pfn); if (p2m_top[topidx] == p2m_missing) { - /* no need to allocate a page to store an invalid entry */ if (mfn == INVALID_P2M_ENTRY) - return; - alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + return true; + return false; } idx = p2m_index(pfn); p2m_top[topidx][idx] = mfn; + + return true; +} + +void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + alloc_p2m(pfn); + + if (!__set_phys_to_machine(pfn, mfn)) + BUG(); + } } unsigned long arbitrary_virt_to_mfn(void *vaddr) @@ -987,7 +1019,7 @@ static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page, return 0; } -void __init xen_mark_init_mm_pinned(void) +static void __init xen_mark_init_mm_pinned(void) { xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1270,8 +1302,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - BUG_ON(cpumask_empty(cpus)); - BUG_ON(!mm); + if (cpumask_empty(cpus)) + return; /* nothing to do */ mcs = xen_mc_entry(sizeof(*args)); args = mcs.args; @@ -1438,6 +1470,15 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) } #endif +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1446,22 +1487,29 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) BUG_ON(mem_map); /* should only be used early */ #endif make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); +} + +/* Used for pmd and pud */ +static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn) +{ +#ifdef CONFIG_FLATMEM + BUG_ON(mem_map); /* should only be used early */ +#endif + make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); } /* Early release_pte assumes that all pts are pinned, since there's only init_mm and anything attached to that is pinned. */ -static void xen_release_pte_init(unsigned long pfn) +static __init void xen_release_pte_init(unsigned long pfn) { + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +static __init void xen_release_pmd_init(unsigned long pfn) { - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } /* This needs to make sure the new pte page is pinned iff its being @@ -1773,6 +1821,9 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #ifdef CONFIG_X86_LOCAL_APIC case FIX_APIC_BASE: /* maps dummy local APIC */ #endif + case FIX_TEXT_POKE0: + case FIX_TEXT_POKE1: + /* All local page mappings */ pte = pfn_pte(phys, prot); break; @@ -1819,7 +1870,6 @@ __init void xen_post_allocator_init(void) xen_mark_init_mm_pinned(); } - const struct pv_mmu_ops xen_mmu_ops __initdata = { .pagetable_setup_start = xen_pagetable_setup_start, .pagetable_setup_done = xen_pagetable_setup_done, @@ -1843,9 +1893,9 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .alloc_pte = xen_alloc_pte_init, .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pte_init, + .alloc_pmd = xen_alloc_pmd_init, .alloc_pmd_clone = paravirt_nop, - .release_pmd = xen_release_pte_init, + .release_pmd = xen_release_pmd_init, #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = xen_kmap_atomic_pte, @@ -1883,8 +1933,8 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_pgd = xen_set_pgd_hyper, - .alloc_pud = xen_alloc_pte_init, - .release_pud = xen_release_pte_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #endif /* PAGETABLE_LEVELS == 4 */ .activate_mm = xen_activate_mm, diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 24d1b44a337d..da7302624897 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -11,6 +11,9 @@ enum pt_level { }; +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool install_p2mtop_page(unsigned long pfn, unsigned long *p); + void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 585a6e330837..429834ec1687 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -317,7 +317,7 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) BUG_ON(rc); while(per_cpu(cpu_state, cpu) != CPU_ONLINE) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); barrier(); } @@ -422,7 +422,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask) /* Make sure other vcpus get a chance to run if they need to. */ for_each_cpu(cpu, mask) { if (xen_vcpu_stolen(cpu)) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); break; } } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 14f240623497..0a5aa44299a5 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -213,6 +213,11 @@ cycle_t xen_clocksource_read(void) return ret; } +static cycle_t xen_clocksource_get_cycles(struct clocksource *cs) +{ + return xen_clocksource_read(); +} + static void xen_read_wallclock(struct timespec *ts) { struct shared_info *s = HYPERVISOR_shared_info; @@ -241,7 +246,7 @@ int xen_set_wallclock(unsigned long now) static struct clocksource xen_clocksource __read_mostly = { .name = "xen", .rating = 400, - .read = xen_clocksource_read, + .read = xen_clocksource_get_cycles, .mask = ~0, .mult = 1<<XEN_SHIFT, /* time directly in nanoseconds */ .shift = XEN_SHIFT, diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 2f5ef2632ea2..20139464943c 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -57,8 +57,6 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id); bool xen_vcpu_stolen(int vcpu); -void xen_mark_init_mm_pinned(void); - void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP |