Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933372Ab2JWSZp (ORCPT ); Tue, 23 Oct 2012 14:25:45 -0400 Received: from userp1040.oracle.com ([156.151.31.81]:39138 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933276Ab2JWSYd (ORCPT ); Tue, 23 Oct 2012 14:24:33 -0400 From: Konrad Rzeszutek Wilk To: xen-devel@lists.xensource.com, linux-kernel@vger.kernel.org, stefano.stabellini@eu.citrix.com, Ian.Campbell@citrix.com, mukesh.rathor@oracle.com Cc: Konrad Rzeszutek Wilk Subject: [PATCH 05/10] xen/pvh: Extend vcpu_guest_context, p2m, event, and XenBus. Date: Tue, 23 Oct 2012 14:12:06 -0400 Message-Id: <1351015931-16991-6-git-send-email-konrad.wilk@oracle.com> X-Mailer: git-send-email 1.7.7.6 In-Reply-To: <1351015931-16991-1-git-send-email-konrad.wilk@oracle.com> References: <1351015931-16991-1-git-send-email-konrad.wilk@oracle.com> X-Source-IP: ucsinet22.oracle.com [156.151.31.94] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8213 Lines: 236 From: Mukesh Rathor Make gdt_frames[]/gdt_ents into a union with {gdtaddr, gdtsz}, as PVH only needs to send down gdtaddr and gdtsz in the vcpu_guest_context structure.. For interrupts, PVH uses native_irq_ops so we can skip most of the PV ones. In the future we can support the pirq_eoi_map.. Also VCPU hotplug is currently not available for PVH. For events (and IRQs) we follow what PVHVM does - so use callback vector. Lastly, for XenBus we use the same logic that is used in the PVHVM case. Acked-by: Stefano Stabellini Signed-off-by: Mukesh Rathor [v2: Rebased it] [v3: Move 64-bit ifdef and based on Stefan add extra comments.] [v4: Rebased it once more] Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/include/asm/xen/interface.h | 11 ++++++++- arch/x86/xen/irq.c | 5 +++- arch/x86/xen/p2m.c | 2 +- arch/x86/xen/smp.c | 39 +++++++++++++++++++++++++-------- drivers/xen/cpu_hotplug.c | 4 ++- drivers/xen/events.c | 9 +++++++- drivers/xen/xenbus/xenbus_client.c | 3 +- 7 files changed, 57 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index 6d2f75a..4c08f23 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -144,7 +144,16 @@ struct vcpu_guest_context { struct cpu_user_regs user_regs; /* User-level CPU registers */ struct trap_info trap_ctxt[256]; /* Virtual IDT */ unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */ - unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ + union { + struct { + /* PV: GDT (machine frames, # ents).*/ + unsigned long gdt_frames[16], gdt_ents; + } pv; + struct { + /* PVH: GDTR addr and size */ + unsigned long gdtaddr, gdtsz; + } pvh; + } u; unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */ unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */ diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 01a4dc0..fcbe56a 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -129,6 +130,8 @@ static const struct pv_irq_ops xen_irq_ops __initconst = { void __init xen_init_irq_ops(void) { - pv_irq_ops = xen_irq_ops; + /* For PVH we use default pv_irq_ops settings */ + if (!xen_feature(XENFEAT_hvm_callback_vector)) + pv_irq_ops = xen_irq_ops; x86_init.irqs.intr_init = xen_init_IRQ; } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 95fb2aa..ea553c8 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -798,7 +798,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) { unsigned topidx, mididx, idx; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + if (xen_feature(XENFEAT_auto_translated_physmap)) { BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); return true; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 6947c4e..448f737 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -68,9 +68,11 @@ static void __cpuinit cpu_bringup(void) touch_softlockup_watchdog(); preempt_disable(); - xen_enable_sysenter(); - xen_enable_syscall(); - + /* PVH runs in ring 0 and allows us to do native syscalls. Yay! */ + if (!xen_feature(XENFEAT_supervisor_mode_kernel)) { + xen_enable_sysenter(); + xen_enable_syscall(); + } cpu = smp_processor_id(); smp_store_cpu_info(cpu); cpu_data(cpu).x86_max_cores = 1; @@ -230,10 +232,11 @@ static void __init xen_smp_prepare_boot_cpu(void) BUG_ON(smp_processor_id() != 0); native_smp_prepare_boot_cpu(); - /* We've switched to the "real" per-cpu gdt, so make sure the - old memory can be recycled */ - make_lowmem_page_readwrite(xen_initial_gdt); - + if (!xen_feature(XENFEAT_writable_page_tables)) { + /* We've switched to the "real" per-cpu gdt, so make sure the + * old memory can be recycled */ + make_lowmem_page_readwrite(xen_initial_gdt); + } xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); } @@ -311,7 +314,23 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); - { + if (xen_feature(XENFEAT_auto_translated_physmap) && + xen_feature(XENFEAT_supervisor_mode_kernel)) { + /* Note: PVH is not supported on x86_32. */ +#ifdef CONFIG_X86_64 + ctxt->user_regs.ds = __KERNEL_DS; + ctxt->user_regs.es = 0; + ctxt->user_regs.gs = 0; + + /* GUEST_GDTR_BASE and */ + ctxt->u.pvh.gdtaddr = (unsigned long)gdt; + /* GUEST_GDTR_LIMIT in the VMCS. */ + ctxt->u.pvh.gdtsz = (unsigned long)(GDT_SIZE - 1); + + ctxt->gs_base_user = (unsigned long) + per_cpu(irq_stack_union.gs_base, cpu); +#endif + } else { ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ ctxt->user_regs.ds = __USER_DS; ctxt->user_regs.es = __USER_DS; @@ -326,8 +345,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) make_lowmem_page_readonly(gdt); make_lowmem_page_readonly(mfn_to_virt(gdt_mfn)); - ctxt->gdt_frames[0] = gdt_mfn; - ctxt->gdt_ents = GDT_ENTRIES; + ctxt->u.pv.gdt_frames[0] = gdt_mfn; + ctxt->u.pv.gdt_ents = GDT_ENTRIES; ctxt->kernel_ss = __KERNEL_DS; ctxt->kernel_sp = idle->thread.sp0; diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index 4dcfced..de6bcf9 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -2,6 +2,7 @@ #include #include +#include #include #include @@ -100,7 +101,8 @@ static int __init setup_vcpu_hotplug_event(void) static struct notifier_block xsn_cpu = { .notifier_call = setup_cpu_watcher }; - if (!xen_pv_domain()) + /* PVH TBD/FIXME: future work */ + if (!xen_pv_domain() || xen_feature(XENFEAT_auto_translated_physmap)) return -ENODEV; register_xenstore_notifier(&xsn_cpu); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 59e10a1..7131fdd 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -1774,7 +1774,7 @@ int xen_set_callback_via(uint64_t via) } EXPORT_SYMBOL_GPL(xen_set_callback_via); -#ifdef CONFIG_XEN_PVHVM +#ifdef CONFIG_X86 /* Vector callbacks are better than PCI interrupts to receive event * channel notifications because we can receive vector callbacks on any * vcpu and we don't need PCI support or APIC interactions. */ @@ -1835,6 +1835,13 @@ void __init xen_init_IRQ(void) if (xen_initial_domain()) pci_xen_initial_domain(); + if (xen_feature(XENFEAT_hvm_callback_vector)) { + xen_callback_vector(); + return; + } + + /* PVH: TBD/FIXME: debug and fix eio map to work with pvh */ + pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO); eoi_gmfn.gmfn = virt_to_mfn(pirq_eoi_map); rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn); diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index bcf3ba4..356461e 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "xenbus_probe.h" @@ -741,7 +742,7 @@ static const struct xenbus_ring_ops ring_ops_hvm = { void __init xenbus_ring_ops_init(void) { - if (xen_pv_domain()) + if (xen_pv_domain() && !xen_feature(XENFEAT_auto_translated_physmap)) ring_ops = &ring_ops_pv; else ring_ops = &ring_ops_hvm; -- 1.7.7.6 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/