diff options
Diffstat (limited to 'arch/x86/xen')
-rw-r--r-- | arch/x86/xen/Kconfig | 19 | ||||
-rw-r--r-- | arch/x86/xen/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 168 | ||||
-rw-r--r-- | arch/x86/xen/enlighten_hvm.c | 6 | ||||
-rw-r--r-- | arch/x86/xen/enlighten_pv.c | 162 | ||||
-rw-r--r-- | arch/x86/xen/enlighten_pvh.c | 10 | ||||
-rw-r--r-- | arch/x86/xen/irq.c | 73 | ||||
-rw-r--r-- | arch/x86/xen/mmu_hvm.c | 37 | ||||
-rw-r--r-- | arch/x86/xen/mmu_pv.c | 160 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 2 | ||||
-rw-r--r-- | arch/x86/xen/pci-swiotlb-xen.c | 4 | ||||
-rw-r--r-- | arch/x86/xen/setup.c | 16 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 28 | ||||
-rw-r--r-- | arch/x86/xen/smp_pv.c | 6 | ||||
-rw-r--r-- | arch/x86/xen/xen-asm.S | 79 | ||||
-rw-r--r-- | arch/x86/xen/xen-head.S | 46 | ||||
-rw-r--r-- | arch/x86/xen/xen-ops.h | 9 |
17 files changed, 350 insertions, 477 deletions
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index afc1da68b06d..6bcd3d8ca6ac 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -43,13 +43,9 @@ config XEN_PV_SMP def_bool y depends on XEN_PV && SMP -config XEN_DOM0 - bool "Xen PV Dom0 support" - default y - depends on XEN_PV && PCI_XEN && SWIOTLB_XEN - depends on X86_IO_APIC && ACPI && PCI - help - Support running as a Xen PV Dom0 guest. +config XEN_PV_DOM0 + def_bool y + depends on XEN_PV && XEN_DOM0 config XEN_PVHVM def_bool y @@ -86,3 +82,12 @@ config XEN_PVH def_bool n help Support for running as a Xen PVH guest. + +config XEN_DOM0 + bool "Xen Dom0 support" + default XEN_PV + depends on (XEN_PV && SWIOTLB_XEN) || (XEN_PVH && X86_64) + depends on X86_IO_APIC && ACPI && PCI + select X86_X2APIC if XEN_PVH && X86_64 + help + Support running as a Xen Dom0 guest. diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 40b5779fce21..4953260e281c 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -45,7 +45,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += vga.o +obj-$(CONFIG_XEN_PV_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c79bd0af2e8c..30c6e986a6cd 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -3,6 +3,7 @@ #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG #include <linux/memblock.h> #endif +#include <linux/console.h> #include <linux/cpu.h> #include <linux/kexec.h> #include <linux/slab.h> @@ -10,12 +11,15 @@ #include <xen/xen.h> #include <xen/features.h> +#include <xen/interface/sched.h> +#include <xen/interface/version.h> #include <xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> #include <asm/cpu.h> #include <asm/e820/api.h> +#include <asm/setup.h> #include "xen-ops.h" #include "smp.h" @@ -27,34 +31,16 @@ EXPORT_SYMBOL_GPL(hypercall_page); * Pointer to the xen_vcpu_info structure or * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info - * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point - * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to - * acknowledge pending events. - * Also more subtly it is used by the patched version of irq enable/disable - * e.g. xen_irq_enable_direct and xen_iret in PV mode. - * - * The desire to be able to do those mask/unmask operations as a single - * instruction by using the per-cpu offset held in %gs is the real reason - * vcpu info is in a per-cpu pointer and the original reason for this - * hypercall. - * + * but during boot it is switched to point to xen_vcpu_info. + * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events. */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); - -/* - * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info - * hypercall. This can be used both in PV and PVHVM mode. The structure - * overrides the default per_cpu(xen_vcpu, cpu) value. - */ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); -enum xen_domain_type xen_domain_type = XEN_NATIVE; -EXPORT_SYMBOL_GPL(xen_domain_type); - unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; EXPORT_SYMBOL(machine_to_phys_mapping); unsigned long machine_to_phys_nr; @@ -69,10 +55,12 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* - * NB: needs to live in .data because it's used by xen_prepare_pvh which runs - * before clearing the bss. + * NB: These need to live in .data or alike because they're used by + * xen_prepare_pvh() which runs before clearing the bss. */ -uint32_t xen_start_flags __section(".data") = 0; +enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE; +EXPORT_SYMBOL_GPL(xen_domain_type); +uint32_t __ro_after_init xen_start_flags; EXPORT_SYMBOL(xen_start_flags); /* @@ -81,21 +69,6 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; -/* - * Flag to determine whether vcpu info placement is available on all - * VCPUs. We assume it is to start with, and then set it to zero on - * the first failure. This is because it can succeed on some VCPUs - * and not others, since it can involve hypervisor memory allocation, - * or because the guest failed to guarantee all the appropriate - * constraints on all VCPUs (ie buffer can't cross a page boundary). - * - * Note that any particular CPU may be using a placed vcpu structure, - * but we can only optimise if the all are. - * - * 0: not available, 1: available - */ -int xen_have_vcpu_info_placement = 1; - static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); @@ -121,10 +94,8 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), return rc >= 0 ? 0 : rc; } -static int xen_vcpu_setup_restore(int cpu) +static void xen_vcpu_setup_restore(int cpu) { - int rc = 0; - /* Any per_cpu(xen_vcpu) is stale, so reset it */ xen_vcpu_info_reset(cpu); @@ -133,11 +104,8 @@ static int xen_vcpu_setup_restore(int cpu) * be handled by hotplug. */ if (xen_pv_domain() || - (xen_hvm_domain() && cpu_online(cpu))) { - rc = xen_vcpu_setup(cpu); - } - - return rc; + (xen_hvm_domain() && cpu_online(cpu))) + xen_vcpu_setup(cpu); } /* @@ -147,7 +115,7 @@ static int xen_vcpu_setup_restore(int cpu) */ void xen_vcpu_restore(void) { - int cpu, rc; + int cpu; for_each_possible_cpu(cpu) { bool other_cpu = (cpu != smp_processor_id()); @@ -167,20 +135,9 @@ void xen_vcpu_restore(void) if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_runstate_info(cpu); - rc = xen_vcpu_setup_restore(cpu); - if (rc) - pr_emerg_once("vcpu restore failed for cpu=%d err=%d. " - "System will hang.\n", cpu, rc); - /* - * In case xen_vcpu_setup_restore() fails, do not bring up the - * VCPU. This helps us avoid the resulting OOPS when the VCPU - * accesses pvclock_vcpu_time via xen_vcpu (which is NULL.) - * Note that this does not improve the situation much -- now the - * VM hangs instead of OOPSing -- with the VCPUs that did not - * fail, spinning in stop_machine(), waiting for the failed - * VCPUs to come up. - */ - if (other_cpu && is_up && (rc == 0) && + xen_vcpu_setup_restore(cpu); + + if (other_cpu && is_up && HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL)) BUG(); } @@ -197,7 +154,7 @@ void xen_vcpu_info_reset(int cpu) } } -int xen_vcpu_setup(int cpu) +void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; int err; @@ -218,44 +175,65 @@ int xen_vcpu_setup(int cpu) */ if (xen_hvm_domain()) { if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu)) - return 0; + return; } - if (xen_have_vcpu_info_placement) { - vcpup = &per_cpu(xen_vcpu_info, cpu); - info.mfn = arbitrary_virt_to_mfn(vcpup); - info.offset = offset_in_page(vcpup); + vcpup = &per_cpu(xen_vcpu_info, cpu); + info.mfn = arbitrary_virt_to_mfn(vcpup); + info.offset = offset_in_page(vcpup); - /* - * Check to see if the hypervisor will put the vcpu_info - * structure where we want it, which allows direct access via - * a percpu-variable. - * N.B. This hypercall can _only_ be called once per CPU. - * Subsequent calls will error out with -EINVAL. This is due to - * the fact that hypervisor has no unregister variant and this - * hypercall does not allow to over-write info.mfn and - * info.offset. - */ - err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, - xen_vcpu_nr(cpu), &info); - - if (err) { - pr_warn_once("register_vcpu_info failed: cpu=%d err=%d\n", - cpu, err); - xen_have_vcpu_info_placement = 0; - } else { - /* - * This cpu is using the registered vcpu info, even if - * later ones fail to. - */ - per_cpu(xen_vcpu, cpu) = vcpup; - } - } + /* + * N.B. This hypercall can _only_ be called once per CPU. + * Subsequent calls will error out with -EINVAL. This is due to + * the fact that hypervisor has no unregister variant and this + * hypercall does not allow to over-write info.mfn and + * info.offset. + */ + err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu), + &info); + if (err) + panic("register_vcpu_info failed: cpu=%d err=%d\n", cpu, err); + + per_cpu(xen_vcpu, cpu) = vcpup; +} + +void __init xen_banner(void) +{ + unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); + struct xen_extraversion extra; - if (!xen_have_vcpu_info_placement) - xen_vcpu_info_reset(cpu); + HYPERVISOR_xen_version(XENVER_extraversion, &extra); - return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0); + pr_info("Booting kernel on %s\n", pv_info.name); + pr_info("Xen version: %u.%u%s%s\n", + version >> 16, version & 0xffff, extra.extraversion, + xen_feature(XENFEAT_mmu_pt_update_preserve_ad) + ? " (preserve-AD)" : ""); +} + +/* Check if running on Xen version (major, minor) or later */ +bool xen_running_on_version_or_later(unsigned int major, unsigned int minor) +{ + unsigned int version; + + if (!xen_domain()) + return false; + + version = HYPERVISOR_xen_version(XENVER_version, NULL); + if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || + ((version >> 16) > major)) + return true; + return false; +} + +void __init xen_add_preferred_consoles(void) +{ + add_preferred_console("xenboot", 0, NULL); + if (!boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + if (boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); } void xen_reboot(int reason) diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index e68ea5f4ad1c..42300941ec29 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -163,9 +163,9 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); else per_cpu(xen_vcpu_id, cpu) = cpu; - rc = xen_vcpu_setup(cpu); - if (rc || !xen_have_vector_callback) - return rc; + xen_vcpu_setup(cpu); + if (!xen_have_vector_callback) + return 0; if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 753f63734c13..5004feb16783 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -27,8 +27,6 @@ #include <linux/export.h> #include <linux/mm.h> #include <linux/page-flags.h> -#include <linux/highmem.h> -#include <linux/console.h> #include <linux/pci.h> #include <linux/gfp.h> #include <linux/edd.h> @@ -109,17 +107,6 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); -static void __init xen_banner(void) -{ - unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); - struct xen_extraversion extra; - HYPERVISOR_xen_version(XENVER_extraversion, &extra); - - pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); - pr_info("Xen version: %d.%d%s (preserve-AD)\n", - version >> 16, version & 0xffff, extra.extraversion); -} - static void __init xen_pv_init_platform(void) { populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); @@ -142,22 +129,6 @@ static void __init xen_pv_guest_late_init(void) #endif } -/* Check if running on Xen version (major, minor) or later */ -bool -xen_running_on_version_or_later(unsigned int major, unsigned int minor) -{ - unsigned int version; - - if (!xen_domain()) - return false; - - version = HYPERVISOR_xen_version(XENVER_version, NULL); - if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || - ((version >> 16) > major)) - return true; - return false; -} - static __read_mostly unsigned int cpuid_leaf5_ecx_val; static __read_mostly unsigned int cpuid_leaf5_edx_val; @@ -311,12 +282,12 @@ static void __init xen_init_capabilities(void) } } -static void xen_set_debugreg(int reg, unsigned long val) +static noinstr void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); } -static unsigned long xen_get_debugreg(int reg) +static noinstr unsigned long xen_get_debugreg(int reg) { return HYPERVISOR_get_debugreg(reg); } @@ -755,8 +726,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) preempt_enable(); } -static void xen_convert_trap_info(const struct desc_ptr *desc, - struct trap_info *traps) +static unsigned xen_convert_trap_info(const struct desc_ptr *desc, + struct trap_info *traps, bool full) { unsigned in, out, count; @@ -766,17 +737,18 @@ static void xen_convert_trap_info(const struct desc_ptr *desc, for (in = out = 0; in < count; in++) { gate_desc *entry = (gate_desc *)(desc->address) + in; - if (cvt_gate_to_trap(in, entry, &traps[out])) + if (cvt_gate_to_trap(in, entry, &traps[out]) || full) out++; } - traps[out].address = 0; + + return out; } void xen_copy_trap_info(struct trap_info *traps) { const struct desc_ptr *desc = this_cpu_ptr(&idt_desc); - xen_convert_trap_info(desc, traps); + xen_convert_trap_info(desc, traps, true); } /* Load a new IDT into Xen. In principle this can be per-CPU, so we @@ -786,6 +758,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + unsigned out; trace_xen_cpu_load_idt(desc); @@ -793,7 +766,8 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); - xen_convert_trap_info(desc, traps); + out = xen_convert_trap_info(desc, traps, false); + memset(&traps[out], 0, sizeof(traps[0])); xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) @@ -1018,31 +992,13 @@ void __init xen_setup_vcpu_info_placement(void) for_each_possible_cpu(cpu) { /* Set up direct vCPU id mapping for PV guests. */ per_cpu(xen_vcpu_id, cpu) = cpu; - - /* - * xen_vcpu_setup(cpu) can fail -- in which case it - * falls back to the shared_info version for cpus - * where xen_vcpu_nr(cpu) < MAX_VIRT_CPUS. - * - * xen_cpu_up_prepare_pv() handles the rest by failing - * them in hotplug. - */ - (void) xen_vcpu_setup(cpu); + xen_vcpu_setup(cpu); } - /* - * xen_vcpu_setup managed to place the vcpu_info within the - * percpu area for all cpus, so make use of it. - */ - if (xen_have_vcpu_info_placement) { - pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); - pv_ops.irq.irq_disable = - __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); - pv_ops.irq.irq_enable = - __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); - pv_ops.mmu.read_cr2 = - __PV_IS_CALLEE_SAVE(xen_read_cr2_direct); - } + pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); + pv_ops.irq.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); + pv_ops.irq.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); + pv_ops.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2_direct); } static const struct pv_info xen_info __initconst = { @@ -1050,52 +1006,54 @@ static const struct pv_info xen_info __initconst = { .name = "Xen", }; -static const struct pv_cpu_ops xen_cpu_ops __initconst = { - .cpuid = xen_cpuid, +static const typeof(pv_ops) xen_cpu_ops __initconst = { + .cpu = { + .cpuid = xen_cpuid, - .set_debugreg = xen_set_debugreg, - .get_debugreg = xen_get_debugreg, + .set_debugreg = xen_set_debugreg, + .get_debugreg = xen_get_debugreg, - .read_cr0 = xen_read_cr0, - .write_cr0 = xen_write_cr0, + .read_cr0 = xen_read_cr0, + .write_cr0 = xen_write_cr0, - .write_cr4 = xen_write_cr4, + .write_cr4 = xen_write_cr4, - .wbinvd = native_wbinvd, + .wbinvd = native_wbinvd, - .read_msr = xen_read_msr, - .write_msr = xen_write_msr, + .read_msr = xen_read_msr, + .write_msr = xen_write_msr, - .read_msr_safe = xen_read_msr_safe, - .write_msr_safe = xen_write_msr_safe, + .read_msr_safe = xen_read_msr_safe, + .write_msr_safe = xen_write_msr_safe, - .read_pmc = xen_read_pmc, + .read_pmc = xen_read_pmc, - .load_tr_desc = paravirt_nop, - .set_ldt = xen_set_ldt, - .load_gdt = xen_load_gdt, - .load_idt = xen_load_idt, - .load_tls = xen_load_tls, - .load_gs_index = xen_load_gs_index, + .load_tr_desc = paravirt_nop, + .set_ldt = xen_set_ldt, + .load_gdt = xen_load_gdt, + .load_idt = xen_load_idt, + .load_tls = xen_load_tls, + .load_gs_index = xen_load_gs_index, - .alloc_ldt = xen_alloc_ldt, - .free_ldt = xen_free_ldt, + .alloc_ldt = xen_alloc_ldt, + .free_ldt = xen_free_ldt, - .store_tr = xen_store_tr, + .store_tr = xen_store_tr, - .write_ldt_entry = xen_write_ldt_entry, - .write_gdt_entry = xen_write_gdt_entry, - .write_idt_entry = xen_write_idt_entry, - .load_sp0 = xen_load_sp0, + .write_ldt_entry = xen_write_ldt_entry, + .write_gdt_entry = xen_write_gdt_entry, + .write_idt_entry = xen_write_idt_entry, + .load_sp0 = xen_load_sp0, #ifdef CONFIG_X86_IOPL_IOPERM - .invalidate_io_bitmap = xen_invalidate_io_bitmap, - .update_io_bitmap = xen_update_io_bitmap, + .invalidate_io_bitmap = xen_invalidate_io_bitmap, + .update_io_bitmap = xen_update_io_bitmap, #endif - .io_delay = xen_io_delay, + .io_delay = xen_io_delay, - .start_context_switch = paravirt_start_context_switch, - .end_context_switch = xen_end_context_switch, + .start_context_switch = paravirt_start_context_switch, + .end_context_switch = xen_end_context_switch, + }, }; static void xen_restart(char *msg) @@ -1214,6 +1172,11 @@ static void __init xen_dom0_set_legacy_features(void) x86_platform.legacy.rtc = 1; } +static void __init xen_domu_set_legacy_features(void) +{ + x86_platform.legacy.rtc = 0; +} + /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { @@ -1231,7 +1194,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; - pv_ops.cpu = xen_cpu_ops; + pv_ops.cpu = xen_cpu_ops.cpu; paravirt_iret = xen_iret; xen_init_irq_ops(); @@ -1265,12 +1228,6 @@ asmlinkage __visible void __init xen_start_kernel(void) __supported_pte_mask &= ~_PAGE_GLOBAL; __default_kernel_pte_mask &= ~_PAGE_GLOBAL; - /* - * Prevent page tables from being allocated in highmem, even - * if CONFIG_HIGHPTE is enabled. - */ - __userpte_alloc_gfp &= ~__GFP_HIGHMEM; - /* Get mfn list */ xen_build_dynamic_phys_to_machine(); @@ -1356,9 +1313,10 @@ asmlinkage __visible void __init xen_start_kernel(void) boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN; if (!xen_initial_domain()) { - add_preferred_console("xenboot", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; + x86_platform.set_legacy_features = + xen_domu_set_legacy_features; } else { const struct dom0_vga_console_info *info = (void *)((char *)xen_start_info + @@ -1399,11 +1357,7 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif } - if (!boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); - if (boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); + xen_add_preferred_consoles(); #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 0d5e34b9e6f9..bcae606bbc5c 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> +#include <linux/export.h> #include <xen/hvc-console.h> @@ -18,10 +19,11 @@ /* * PVH variables. * - * The variable xen_pvh needs to live in the data segment since it is used + * The variable xen_pvh needs to live in a data segment since it is used * after startup_{32|64} is invoked, which will clear the .bss segment. */ -bool xen_pvh __section(".data") = 0; +bool __ro_after_init xen_pvh; +EXPORT_SYMBOL_GPL(xen_pvh); void __init xen_pvh_init(struct boot_params *boot_params) { @@ -36,6 +38,10 @@ void __init xen_pvh_init(struct boot_params *boot_params) pfn = __pa(hypercall_page); wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + if (xen_initial_domain()) + x86_init.oem.arch_setup = xen_add_preferred_consoles; + x86_init.oem.banner = xen_banner; + xen_efi_init(boot_params); } diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index dfa091d79c2e..06c3c2fb4b06 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -19,65 +19,11 @@ * callback mask. We do this in a very simple manner, by making a call * down into Xen. The pending flag will be checked by Xen on return. */ -void xen_force_evtchn_callback(void) +noinstr void xen_force_evtchn_callback(void) { (void)HYPERVISOR_xen_version(0, NULL); } -asmlinkage __visible unsigned long xen_save_fl(void) -{ - struct vcpu_info *vcpu; - unsigned long flags; - - vcpu = this_cpu_read(xen_vcpu); - - /* flag has opposite sense of mask */ - flags = !vcpu->evtchn_upcall_mask; - - /* convert to IF type flag - -0 -> 0x00000000 - -1 -> 0xffffffff - */ - return (-flags) & X86_EFLAGS_IF; -} -PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl); - -asmlinkage __visible void xen_irq_disable(void) -{ - /* There's a one instruction preempt window here. We need to - make sure we're don't switch CPUs between getting the vcpu - pointer and updating the mask. */ - preempt_disable(); - this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1; - preempt_enable_no_resched(); -} -PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable); - -asmlinkage __visible void xen_irq_enable(void) -{ - struct vcpu_info *vcpu; - - /* - * We may be preempted as soon as vcpu->evtchn_upcall_mask is - * cleared, so disable preemption to ensure we check for - * events on the VCPU we are still running on. - */ - preempt_disable(); - - vcpu = this_cpu_read(xen_vcpu); - vcpu->evtchn_upcall_mask = 0; - - /* Doesn't matter if we get preempted here, because any - pending event will get dealt with anyway. */ - - barrier(); /* unmask then check (avoid races) */ - if (unlikely(vcpu->evtchn_upcall_pending)) - xen_force_evtchn_callback(); - - preempt_enable(); -} -PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable); - static void xen_safe_halt(void) { /* Blocking includes an implicit local_irq_enable(). */ @@ -94,17 +40,20 @@ static void xen_halt(void) xen_safe_halt(); } -static const struct pv_irq_ops xen_irq_ops __initconst = { - .save_fl = PV_CALLEE_SAVE(xen_save_fl), - .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), - .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), +static const typeof(pv_ops) xen_irq_ops __initconst = { + .irq = { + /* Initial interrupt flag handling only called while interrupts off. */ + .save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0), + .irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop), + .irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG), - .safe_halt = xen_safe_halt, - .halt = xen_halt, + .safe_halt = xen_safe_halt, + .halt = xen_halt, + }, }; void __init xen_init_irq_ops(void) { - pv_ops.irq = xen_irq_ops; + pv_ops.irq = xen_irq_ops.irq; x86_init.irqs.intr_init = xen_init_IRQ; } diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c index 57409373750f..509bdee3ab90 100644 --- a/arch/x86/xen/mmu_hvm.c +++ b/arch/x86/xen/mmu_hvm.c @@ -9,39 +9,28 @@ #ifdef CONFIG_PROC_VMCORE /* - * This function is used in two contexts: - * - the kdump kernel has to check whether a pfn of the crashed kernel - * was a ballooned page. vmcore is using this function to decide - * whether to access a pfn of the crashed kernel. - * - the kexec kernel has to check whether a pfn was ballooned by the - * previous kernel. If the pfn is ballooned, handle it properly. - * Returns 0 if the pfn is not backed by a RAM page, the caller may + * The kdump kernel has to check whether a pfn of the crashed kernel + * was a ballooned page. vmcore is using this function to decide + * whether to access a pfn of the crashed kernel. + * Returns "false" if the pfn is not backed by a RAM page, the caller may * handle the pfn special in this case. */ -static int xen_oldmem_pfn_is_ram(unsigned long pfn) +static bool xen_vmcore_pfn_is_ram(struct vmcore_cb *cb, unsigned long pfn) { struct xen_hvm_get_mem_type a = { .domid = DOMID_SELF, .pfn = pfn, }; - int ram; - if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a)) - return -ENXIO; - - switch (a.mem_type) { - case HVMMEM_mmio_dm: - ram = 0; - break; - case HVMMEM_ram_rw: - case HVMMEM_ram_ro: - default: - ram = 1; - break; + if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a)) { + pr_warn_once("Unexpected HVMOP_get_mem_type failure\n"); + return true; } - - return ram; + return a.mem_type != HVMMEM_mmio_dm; } +static struct vmcore_cb xen_vmcore_cb = { + .pfn_is_ram = xen_vmcore_pfn_is_ram, +}; #endif static void xen_hvm_exit_mmap(struct mm_struct *mm) @@ -75,6 +64,6 @@ void __init xen_hvm_init_mmu_ops(void) if (is_pagetable_dying_supported()) pv_ops.mmu.exit_mmap = xen_hvm_exit_mmap; #ifdef CONFIG_PROC_VMCORE - WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram)); + register_vmcore_cb(&xen_vmcore_cb); #endif } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1df5f01529e5..00354866921b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -41,7 +41,6 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ #include <linux/sched/mm.h> -#include <linux/highmem.h> #include <linux/debugfs.h> #include <linux/bug.h> #include <linux/vmalloc.h> @@ -86,8 +85,10 @@ #include "mmu.h" #include "debugfs.h" +#ifdef CONFIG_X86_VSYSCALL_EMULATION /* l3 pud for userspace vsyscall mapping */ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; +#endif /* * Protects atomic reservation decrease/increase against concurrent increases. @@ -241,9 +242,11 @@ static void xen_set_pmd(pmd_t *ptr, pmd_t val) * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. */ -void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) +void __init set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) { - set_pte_vaddr(vaddr, mfn_pte(mfn, flags)); + if (HYPERVISOR_update_va_mapping(vaddr, mfn_pte(mfn, flags), + UVMF_INVLPG)) + BUG(); } static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) @@ -789,7 +792,9 @@ static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, static void __init xen_after_bootmem(void) { static_branch_enable(&xen_struct_pages_ready); +#ifdef CONFIG_X86_VSYSCALL_EMULATION SetPagePinned(virt_to_page(level3_user_vsyscall)); +#endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1025,7 +1030,7 @@ static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size) for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) make_lowmem_page_readwrite(vaddr); - memblock_free(paddr, size); + memblock_phys_free(paddr, size); } static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) @@ -1151,7 +1156,7 @@ static void __init xen_pagetable_p2m_free(void) xen_cleanhighmap(addr, addr + size); size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_free(__pa(addr), size); + memblock_free((void *)addr, size); } else { xen_cleanmfnmap(addr); } @@ -1192,6 +1197,13 @@ static void __init xen_pagetable_p2m_setup(void) static void __init xen_pagetable_init(void) { + /* + * The majority of further PTE writes is to pagetables already + * announced as such to Xen. Hence it is more efficient to use + * hypercalls for these updates. + */ + pv_ops.mmu.set_pte = __xen_set_pte; + paging_init(); xen_post_allocator_init(); @@ -1204,7 +1216,8 @@ static void __init xen_pagetable_init(void) xen_remap_memory(); xen_setup_mfn_list_list(); } -static void xen_write_cr2(unsigned long cr2) + +static noinstr void xen_write_cr2(unsigned long cr2) { this_cpu_read(xen_vcpu)->arch.cr2 = cr2; } @@ -1420,10 +1433,18 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) * * Many of these PTE updates are done on unpinned and writable pages * and doing a hypercall for these is unnecessary and expensive. At - * this point it is not possible to tell if a page is pinned or not, - * so always write the PTE directly and rely on Xen trapping and + * this point it is rarely possible to tell if a page is pinned, so + * mostly write the PTE directly and rely on Xen trapping and * emulating any updates as necessary. */ +static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +{ + if (unlikely(is_early_ioremap_ptep(ptep))) + __xen_set_pte(ptep, pte); + else + native_set_pte(ptep, pte); +} + __visible pte_t xen_make_pte_init(pteval_t pte) { unsigned long pfn; @@ -1445,11 +1466,6 @@ __visible pte_t xen_make_pte_init(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); -static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) -{ - __xen_set_pte(ptep, pte); -} - /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1518,14 +1534,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, if (pinned) { struct page *page = pfn_to_page(pfn); - if (static_branch_likely(&xen_struct_pages_ready)) + pinned = false; + if (static_branch_likely(&xen_struct_pages_ready)) { + pinned = PagePinned(page); SetPagePinned(page); + } xen_mc_batch(); __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(PARAVIRT_LAZY_MMU); @@ -1746,7 +1765,6 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(init_top_pgt, PAGE_KERNEL_RO); set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); @@ -1763,6 +1781,13 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Unpin Xen-provided one */ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); +#ifdef CONFIG_X86_VSYSCALL_EMULATION + /* Pin user vsyscall L3 */ + set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, + PFN_DOWN(__pa_symbol(level3_user_vsyscall))); +#endif + /* * At this stage there can be no user pgd, and no page structure to * attach it to, so make sure we just set kernel pgd. @@ -1952,7 +1977,7 @@ void __init xen_relocate_p2m(void) pfn_end = p2m_pfn_end; } - memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); + memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); while (pfn < pfn_end) { if (pfn == p2m_pfn) { pfn = p2m_pfn_end; @@ -1995,6 +2020,7 @@ static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) { pte_t pte; + unsigned long vaddr; phys >>= PAGE_SHIFT; @@ -2035,15 +2061,15 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) break; } - __native_set_fixmap(idx, pte); + vaddr = __fix_to_virt(idx); + if (HYPERVISOR_update_va_mapping(vaddr, pte, UVMF_INVLPG)) + BUG(); #ifdef CONFIG_X86_VSYSCALL_EMULATION /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ - if (idx == VSYSCALL_PAGE) { - unsigned long vaddr = __fix_to_virt(idx); + if (idx == VSYSCALL_PAGE) set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); - } #endif } @@ -2075,67 +2101,69 @@ static void xen_leave_lazy_mmu(void) preempt_enable(); } -static const struct pv_mmu_ops xen_mmu_ops __initconst = { - .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2), - .write_cr2 = xen_write_cr2, +static const typeof(pv_ops) xen_mmu_ops __initconst = { + .mmu = { + .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2), + .write_cr2 = xen_write_cr2, - .read_cr3 = xen_read_cr3, - .write_cr3 = xen_write_cr3_init, + .read_cr3 = xen_read_cr3, + .write_cr3 = xen_write_cr3_init, - .flush_tlb_user = xen_flush_tlb, - .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_one_user = xen_flush_tlb_one_user, - .flush_tlb_multi = xen_flush_tlb_multi, - .tlb_remove_table = tlb_remove_table, + .flush_tlb_user = xen_flush_tlb, + .flush_tlb_kernel = xen_flush_tlb, + .flush_tlb_one_user = xen_flush_tlb_one_user, + .flush_tlb_multi = xen_flush_tlb_multi, + .tlb_remove_table = tlb_remove_table, - .pgd_alloc = xen_pgd_alloc, - .pgd_free = xen_pgd_free, + .pgd_alloc = xen_pgd_alloc, + .pgd_free = xen_pgd_free, - .alloc_pte = xen_alloc_pte_init, - .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pmd_init, - .release_pmd = xen_release_pmd_init, + .alloc_pte = xen_alloc_pte_init, + .release_pte = xen_release_pte_init, + .alloc_pmd = xen_alloc_pmd_init, + .release_pmd = xen_release_pmd_init, - .set_pte = xen_set_pte_init, - .set_pmd = xen_set_pmd_hyper, + .set_pte = xen_set_pte_init, + .set_pmd = xen_set_pmd_hyper, - .ptep_modify_prot_start = xen_ptep_modify_prot_start, - .ptep_modify_prot_commit = xen_ptep_modify_prot_commit, + .ptep_modify_prot_start = xen_ptep_modify_prot_start, + .ptep_modify_prot_commit = xen_ptep_modify_prot_commit, - .pte_val = PV_CALLEE_SAVE(xen_pte_val), - .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), + .pte_val = PV_CALLEE_SAVE(xen_pte_val), + .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), - .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), - .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), + .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), + .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), - .set_pud = xen_set_pud_hyper, + .set_pud = xen_set_pud_hyper, - .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), - .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), + .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), + .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), - .pud_val = PV_CALLEE_SAVE(xen_pud_val), - .make_pud = PV_CALLEE_SAVE(xen_make_pud), - .set_p4d = xen_set_p4d_hyper, + .pud_val = PV_CALLEE_SAVE(xen_pud_val), + .make_pud = PV_CALLEE_SAVE(xen_make_pud), + .set_p4d = xen_set_p4d_hyper, - .alloc_pud = xen_alloc_pmd_init, - .release_pud = xen_release_pmd_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #if CONFIG_PGTABLE_LEVELS >= 5 - .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), - .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), + .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), + .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), #endif - .activate_mm = xen_activate_mm, - .dup_mmap = xen_dup_mmap, - .exit_mmap = xen_exit_mmap, + .activate_mm = xen_activate_mm, + .dup_mmap = xen_dup_mmap, + .exit_mmap = xen_exit_mmap, - .lazy_mode = { - .enter = paravirt_enter_lazy_mmu, - .leave = xen_leave_lazy_mmu, - .flush = paravirt_flush_lazy_mmu, - }, + .lazy_mode = { + .enter = paravirt_enter_lazy_mmu, + .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, + }, - .set_fixmap = xen_set_fixmap, + .set_fixmap = xen_set_fixmap, + }, }; void __init xen_init_mmu_ops(void) @@ -2143,7 +2171,7 @@ void __init xen_init_mmu_ops(void) x86_init.paging.pagetable_init = xen_pagetable_init; x86_init.hyper.init_after_bootmem = xen_after_bootmem; - pv_ops.mmu = xen_mmu_ops; + pv_ops.mmu = xen_mmu_ops.mmu; memset(dummy_mapping, 0xff, PAGE_SIZE); } @@ -2395,7 +2423,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages) + unsigned int domid, bool no_translate) { int err = 0; struct remap_data rmd; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 5e6e236977c7..58db86f7b384 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -197,7 +197,7 @@ static void * __ref alloc_p2m_page(void) static void __ref free_p2m_page(void *p) { if (unlikely(!slab_is_available())) { - memblock_free((unsigned long)p, PAGE_SIZE); + memblock_free(p, PAGE_SIZE); return; } diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 54f9aa7e8457..46df59aeaa06 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -18,7 +18,7 @@ #endif #include <linux/export.h> -int xen_swiotlb __read_mostly; +static int xen_swiotlb __read_mostly; /* * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary @@ -56,7 +56,7 @@ int __init pci_xen_swiotlb_detect(void) return xen_swiotlb; } -void __init pci_xen_swiotlb_init(void) +static void __init pci_xen_swiotlb_init(void) { if (xen_swiotlb) { xen_swiotlb_init_early(); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8bfc10330107..af216feb63d9 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -153,7 +153,7 @@ static void __init xen_del_extra_mem(unsigned long start_pfn, break; } } - memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); + memblock_phys_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } /* @@ -306,10 +306,6 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn) BUG(); } - /* Update kernel mapping, but not for highmem. */ - if (pfn >= PFN_UP(__pa(high_memory - 1))) - return; - if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT), mfn_pte(mfn, PAGE_KERNEL), 0)) { WARN(1, "Failed to update kernel mapping for mfn=%ld pfn=%ld\n", @@ -429,13 +425,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk( } /* - * If the PFNs are currently mapped, the VA mapping also needs - * to be updated to be 1:1. + * If the PFNs are currently mapped, their VA mappings need to be + * zapped. */ for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) (void)HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), - mfn_pte(pfn, PAGE_KERNEL_IO), 0); + native_make_pte(0), 0); return remap_pfn; } @@ -719,7 +715,7 @@ static void __init xen_reserve_xen_mfnlist(void) return; xen_relocate_p2m(); - memblock_free(start, size); + memblock_phys_free(start, size); } /** @@ -885,7 +881,7 @@ char * __init xen_memory_setup(void) xen_phys_memcpy(new_area, start, size); pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n", start, start + size, new_area, new_area + size); - memblock_free(start, size); + memblock_phys_free(start, size); boot_params.hdr.ramdisk_image = new_area; boot_params.ext_ramdisk_image = new_area >> 32; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index c1b2f764b29a..c3e1f9a7d43a 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -121,34 +121,10 @@ int xen_smp_intr_init(unsigned int cpu) void __init xen_smp_cpus_done(unsigned int max_cpus) { - int cpu, rc, count = 0; - if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); else calculate_max_logical_packages(); - - if (xen_have_vcpu_info_placement) - return; - - for_each_online_cpu(cpu) { - if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) - continue; - - rc = remove_cpu(cpu); - - if (rc == 0) { - /* - * Reset vcpu_info so this cpu cannot be onlined again. - */ - xen_vcpu_info_reset(cpu); - count++; - } else { - pr_warn("%s: failed to bring CPU %d down, error %d\n", - __func__, cpu, rc); - } - } - WARN(count, "%s: brought %d CPUs offline\n", __func__, count); } void xen_smp_send_reschedule(int cpu) @@ -268,20 +244,16 @@ void xen_send_IPI_allbutself(int vector) static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) { - irq_enter(); generic_smp_call_function_interrupt(); inc_irq_stat(irq_call_count); - irq_exit(); return IRQ_HANDLED; } static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id) { - irq_enter(); generic_smp_call_function_single_interrupt(); inc_irq_stat(irq_call_count); - irq_exit(); return IRQ_HANDLED; } diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 96afadf9878e..9e55bcbfcd33 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -290,8 +290,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) gdt = get_cpu_gdt_rw(cpu); - memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); - /* * Bring up the CPU in cpu_bringup_and_idle() with the stack * pointing just below where pt_regs would be if it were a normal @@ -308,8 +306,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) xen_copy_trap_info(ctxt->trap_ctxt); - ctxt->ldt_ents = 0; - BUG_ON((unsigned long)gdt & ~PAGE_MASK); gdt_mfn = arbitrary_virt_to_mfn(gdt); @@ -462,10 +458,8 @@ static void xen_pv_stop_other_cpus(int wait) static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id) { - irq_enter(); irq_work_run(); inc_irq_stat(apic_irq_work_irqs); - irq_exit(); return IRQ_HANDLED; } diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1e626444712b..220dd9678494 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -21,6 +21,45 @@ #include <linux/init.h> #include <linux/linkage.h> +.pushsection .noinstr.text, "ax" +/* + * Disabling events is simply a matter of making the event mask + * non-zero. + */ +SYM_FUNC_START(xen_irq_disable_direct) + movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + ret +SYM_FUNC_END(xen_irq_disable_direct) + +/* + * Force an event check by making a hypercall, but preserve regs + * before making the call. + */ +SYM_FUNC_START(check_events) + FRAME_BEGIN + push %rax + push %rcx + push %rdx + push %rsi + push %rdi + push %r8 + push %r9 + push %r10 + push %r11 + call xen_force_evtchn_callback + pop %r11 + pop %r10 + pop %r9 + pop %r8 + pop %rdi + pop %rsi + pop %rdx + pop %rcx + pop %rax + FRAME_END + ret +SYM_FUNC_END(check_events) + /* * Enable events. This clears the event mask and tests the pending * event status with one and operation. If there are pending events, @@ -47,16 +86,6 @@ SYM_FUNC_START(xen_irq_enable_direct) ret SYM_FUNC_END(xen_irq_enable_direct) - -/* - * Disabling events is simply a matter of making the event mask - * non-zero. - */ -SYM_FUNC_START(xen_irq_disable_direct) - movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask - ret -SYM_FUNC_END(xen_irq_disable_direct) - /* * (xen_)save_fl is used to get the current interrupt enable status. * Callers expect the status to be in X86_EFLAGS_IF, and other bits @@ -73,35 +102,6 @@ SYM_FUNC_START(xen_save_fl_direct) ret SYM_FUNC_END(xen_save_fl_direct) -/* - * Force an event check by making a hypercall, but preserve regs - * before making the call. - */ -SYM_FUNC_START(check_events) - FRAME_BEGIN - push %rax - push %rcx - push %rdx - push %rsi - push %rdi - push %r8 - push %r9 - push %r10 - push %r11 - call xen_force_evtchn_callback - pop %r11 - pop %r10 - pop %r9 - pop %r8 - pop %rdi - pop %rsi - pop %rdx - pop %rcx - pop %rax - FRAME_END - ret -SYM_FUNC_END(check_events) - SYM_FUNC_START(xen_read_cr2) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX @@ -116,6 +116,7 @@ SYM_FUNC_START(xen_read_cr2_direct) FRAME_END ret SYM_FUNC_END(xen_read_cr2_direct); +.popsection .macro xen_pv_trap name SYM_CODE_START(xen_\name) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index cb6538ae2fe0..6a64496edefb 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -20,6 +20,23 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> +.pushsection .noinstr.text, "ax" + .balign PAGE_SIZE +SYM_CODE_START(hypercall_page) + .rept (PAGE_SIZE / 32) + UNWIND_HINT_FUNC + .skip 31, 0x90 + ret + .endr + +#define HYPERCALL(n) \ + .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ + .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 +#include <asm/xen-hypercalls.h> +#undef HYPERCALL +SYM_CODE_END(hypercall_page) +.popsection + #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -28,13 +45,13 @@ SYM_CODE_START(startup_xen) /* Clear .bss */ xor %eax,%eax - mov $__bss_start, %_ASM_DI - mov $__bss_stop, %_ASM_CX - sub %_ASM_DI, %_ASM_CX - shr $__ASM_SEL(2, 3), %_ASM_CX - rep __ASM_SIZE(stos) + mov $__bss_start, %rdi + mov $__bss_stop, %rcx + sub %rdi, %rcx + shr $3, %rcx + rep stosq - mov %_ASM_SI, xen_start_info + mov %rsi, xen_start_info mov initial_stack(%rip), %rsp /* Set up %gs. @@ -64,23 +81,6 @@ SYM_CODE_END(asm_cpu_bringup_and_idle) #endif #endif -.pushsection .text - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - .skip 31, 0x90 - ret - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 8d7ec49a35fb..fd0fec6e92f4 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -51,6 +51,7 @@ void __init xen_remap_memory(void); phys_addr_t __init xen_find_free_area(phys_addr_t size); char * __init xen_memory_setup(void); void __init xen_arch_setup(void); +void xen_banner(void); void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); @@ -75,9 +76,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id); bool xen_vcpu_stolen(int vcpu); -extern int xen_have_vcpu_info_placement; - -int xen_vcpu_setup(int cpu); +void xen_vcpu_setup(int cpu); void xen_vcpu_info_reset(int cpu); void xen_setup_vcpu_info_placement(void); @@ -109,7 +108,7 @@ static inline void xen_uninit_lock_cpu(int cpu) struct dom0_vga_console_info; -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, @@ -118,6 +117,8 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, } #endif +void xen_add_preferred_consoles(void); + void __init xen_init_apic(void); #ifdef CONFIG_XEN_EFI |