x86/xen: use xen_vcpu_id mapping when pointing vcpu_info to shared_info

[cascardo/linux.git] / arch / x86 / xen / enlighten.c

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 880862c..5ca92e6 100644 (file)
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -59,6 +59,7 @@
 #include <asm/xen/pci.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <asm/xen/cpuid.h>
 #include <asm/fixmap.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -75,7 +76,6 @@
 #include <asm/mach_traps.h>
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
-#include <asm/pat.h>
 #include <asm/cpu.h>
 
 #ifdef CONFIG_ACPI
@@ -119,6 +119,10 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
  */
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 
+/* Linux <-> Xen vCPU id mapping */
+DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
+
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
 EXPORT_SYMBOL_GPL(xen_domain_type);
 
@@ -203,8 +207,9 @@ static void xen_vcpu_setup(int cpu)
                if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
                        return;
        }
-       if (cpu < MAX_VIRT_CPUS)
-               per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+       if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS)
+               per_cpu(xen_vcpu, cpu) =
+                       &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
 
        if (!have_vcpu_info_placement) {
                if (cpu >= MAX_VIRT_CPUS)
@@ -224,7 +229,8 @@ static void xen_vcpu_setup(int cpu)
           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, cpu, &info);
+       err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+                                &info);
 
        if (err) {
                printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
@@ -248,10 +254,11 @@ void xen_vcpu_restore(void)
 
        for_each_possible_cpu(cpu) {
                bool other_cpu = (cpu != smp_processor_id());
-               bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL);
+               bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu),
+                                               NULL);
 
                if (other_cpu && is_up &&
-                   HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+                   HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL))
                        BUG();
 
                xen_setup_runstate_info(cpu);
@@ -260,7 +267,7 @@ void xen_vcpu_restore(void)
                        xen_vcpu_setup(cpu);
 
                if (other_cpu && is_up &&
-                   HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+                   HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
                        BUG();
        }
 }
@@ -591,7 +598,7 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
 {
        unsigned long va = dtr->address;
        unsigned int size = dtr->size + 1;
-       unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+       unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
        unsigned long frames[pages];
        int f;
 
@@ -640,7 +647,7 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
 {
        unsigned long va = dtr->address;
        unsigned int size = dtr->size + 1;
-       unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+       unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
        unsigned long frames[pages];
        int f;
 
@@ -1093,6 +1100,26 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
        return ret;
 }
 
+static u64 xen_read_msr(unsigned int msr)
+{
+       /*
+        * This will silently swallow a #GP from RDMSR.  It may be worth
+        * changing that.
+        */
+       int err;
+
+       return xen_read_msr_safe(msr, &err);
+}
+
+static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+{
+       /*
+        * This will silently swallow a #GP from WRMSR.  It may be worth
+        * changing that.
+        */
+       xen_write_msr_safe(msr, low, high);
+}
+
 void xen_setup_shared_info(void)
 {
        if (!xen_feature(XENFEAT_auto_translated_physmap)) {
@@ -1118,8 +1145,11 @@ void xen_setup_vcpu_info_placement(void)
 {
        int cpu;
 
-       for_each_possible_cpu(cpu)
+       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);
+       }
 
        /* xen_vcpu_setup managed to place the vcpu_info within the
         * percpu area for all cpus, so make use of it. Note that for
@@ -1187,13 +1217,11 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 }
 
 static const struct pv_info xen_info __initconst = {
-       .paravirt_enabled = 1,
        .shared_kernel_pmd = 0,
 
 #ifdef CONFIG_X86_64
        .extra_user_64bit_cs = FLAT_USER_CS64,
 #endif
-       .features = 0,
        .name = "Xen",
 };
 
@@ -1223,8 +1251,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
        .wbinvd = native_wbinvd,
 
-       .read_msr = xen_read_msr_safe,
-       .write_msr = xen_write_msr_safe,
+       .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_pmc = xen_read_pmc,
 
@@ -1469,10 +1500,10 @@ static void xen_pvh_set_cr_flags(int cpu)
         * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
         * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
        */
-       if (cpu_has_pse)
+       if (boot_cpu_has(X86_FEATURE_PSE))
                cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
-       if (cpu_has_pge)
+       if (boot_cpu_has(X86_FEATURE_PGE))
                cr4_set_bits_and_update_boot(X86_CR4_PGE);
 }
 
@@ -1506,12 +1537,16 @@ static void __init xen_pvh_early_guest_init(void)
 }
 #endif    /* CONFIG_XEN_PVH */
 
+static void __init xen_dom0_set_legacy_features(void)
+{
+       x86_platform.legacy.rtc = 1;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
        struct physdev_set_iopl set_iopl;
        unsigned long initrd_start = 0;
-       u64 pat;
        int rc;
 
        if (!xen_start_info)
@@ -1527,8 +1562,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
        /* Install Xen paravirt ops */
        pv_info = xen_info;
-       if (xen_initial_domain())
-               pv_info.features |= PV_SUPPORTED_RTC;
        pv_init_ops = xen_init_ops;
        if (!xen_pvh_domain()) {
                pv_cpu_ops = xen_cpu_ops;
@@ -1618,13 +1651,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
                                   xen_start_info->nr_pages);
        xen_reserve_special_pages();
 
-       /*
-        * Modify the cache mode translation tables to match Xen's PAT
-        * configuration.
-        */
-       rdmsrl(MSR_IA32_CR_PAT, pat);
-       pat_init_cache_modes(pat);
-
        /* keep using Xen gdt for now; no urgent need to change it */
 
 #ifdef CONFIG_X86_32
@@ -1670,6 +1696,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
        boot_params.hdr.ramdisk_image = initrd_start;
        boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
        boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
+       boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
 
        if (!xen_initial_domain()) {
                add_preferred_console("xenboot", 0, NULL);
@@ -1687,6 +1714,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
                        .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
                };
 
+               x86_platform.set_legacy_features =
+                               xen_dom0_set_legacy_features;
                xen_init_vga(info, xen_start_info->console.dom0.info_size);
                xen_start_info->console.domU.mfn = 0;
                xen_start_info->console.domU.evtchn = 0;
@@ -1711,6 +1740,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
        xen_raw_console_write("about to get started...\n");
 
+       /* Let's presume PV guests always boot on vCPU with id 0. */
+       per_cpu(xen_vcpu_id, 0) = 0;
+
        xen_setup_runstate_info(0);
 
        xen_efi_init();
@@ -1752,9 +1784,10 @@ void __ref xen_hvm_init_shared_info(void)
         * in that case multiple vcpus might be online. */
        for_each_online_cpu(cpu) {
                /* Leave it to be NULL. */
-               if (cpu >= MAX_VIRT_CPUS)
+               if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS)
                        continue;
-               per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+               per_cpu(xen_vcpu, cpu) =
+                       &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
        }
 }
 
@@ -1779,6 +1812,12 @@ static void __init init_hvm_pv_info(void)
 
        xen_setup_features();
 
+       cpuid(base + 4, &eax, &ebx, &ecx, &edx);
+       if (eax & XEN_HVM_CPUID_VCPU_ID_PRESENT)
+               this_cpu_write(xen_vcpu_id, ebx);
+       else
+               this_cpu_write(xen_vcpu_id, smp_processor_id());
+
        pv_info.name = "Xen HVM";
 
        xen_domain_type = XEN_HVM_DOMAIN;
@@ -1790,6 +1829,10 @@ static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action,
        int cpu = (long)hcpu;
        switch (action) {
        case CPU_UP_PREPARE:
+               if (cpu_acpi_id(cpu) != U32_MAX)
+                       per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
+               else
+                       per_cpu(xen_vcpu_id, cpu) = cpu;
                xen_vcpu_setup(cpu);
                if (xen_have_vector_callback) {
                        if (xen_feature(XENFEAT_hvm_safe_pvclock))