xen/pvh: Secondary VCPU bringup (non-bootup CPUs)

The VCPU bringup protocol follows the PV with certain twists.
From xen/include/public/arch-x86/xen.h:

Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise
for HVM and PVH guests, not all information in this structure is updated:

 - For HVM guests, the structures read include: fpu_ctxt (if
 VGCT_I387_VALID is set), flags, user_regs, debugreg[*]

 - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to
 set cr3. All other fields not used should be set to 0.

This is what we do. We piggyback on the 'xen_setup_gdt' - but modify
a bit - we need to call 'load_percpu_segment' so that 'switch_to_new_gdt'
can load per-cpu data-structures. It has no effect on the VCPU0.

We also piggyback on the %rdi register to pass in the CPU number - so
that when we bootup a new CPU, the cpu_bringup_and_idle will have
passed as the first parameter the CPU number (via %rdi for 64-bit).

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

3 files changed, 42 insertions, 19 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1170d00879d5..2eca6187fc92 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1409,14 +1409,19 @@ static void __init xen_boot_params_init_edd(void)
  * Set up the GDT and segment registers for -fstack-protector.  Until
  * we do this, we have to be careful not to call any stack-protected
  * function, which is most of the kernel.
+ *
+ * Note, that it is __ref because the only caller of this after init
+ * is PVH which is not going to use xen_load_gdt_boot or other
+ * __init functions.
  */
-static void __init xen_setup_gdt(void)
+void __ref xen_setup_gdt(int cpu)
 {
         if (xen_feature(XENFEAT_auto_translated_physmap)) {
 #ifdef CONFIG_X86_64
                 unsigned long dummy;
 
-                switch_to_new_gdt(0); /* GDT and GS set */
+                load_percpu_segment(cpu); /* We need to access per-cpu area */
+                switch_to_new_gdt(cpu); /* GDT and GS set */
 
                 /* We are switching of the Xen provided GDT to our HVM mode
                  * GDT. The new GDT has  __KERNEL_CS with CS.L = 1
@@ -1529,7 +1534,7 @@ asmlinkage void __init xen_start_kernel(void)
          * Set up kernel GDT and segment registers, mainly so that
          * -fstack-protector code can be executed.
          */
-        xen_setup_gdt();
+        xen_setup_gdt(0);
 
         xen_init_irq_ops();
         xen_init_cpuid_mask();
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index c36b325abd83..5e46190133b2 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -73,9 +73,11 @@ static void 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;
@@ -97,8 +99,14 @@ static void cpu_bringup(void)
         wmb();                  /* make sure everything is out */
 }
 
-static void cpu_bringup_and_idle(void)
+/* Note: cpu parameter is only relevant for PVH */
+static void cpu_bringup_and_idle(int cpu)
 {
+#ifdef CONFIG_X86_64
+        if (xen_feature(XENFEAT_auto_translated_physmap) &&
+            xen_feature(XENFEAT_supervisor_mode_kernel))
+                xen_setup_gdt(cpu);
+#endif
         cpu_bringup();
         cpu_startup_entry(CPUHP_ONLINE);
 }
@@ -274,9 +282,10 @@ static void __init xen_smp_prepare_boot_cpu(void)
         native_smp_prepare_boot_cpu();
 
         if (xen_pv_domain()) {
-                /* 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);
 
 #ifdef CONFIG_X86_32
                 /*
@@ -360,22 +369,21 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 
         gdt = get_cpu_gdt_table(cpu);
 
-        ctxt->flags = VGCF_IN_KERNEL;
-        ctxt->user_regs.ss = __KERNEL_DS;
 #ifdef CONFIG_X86_32
+        /* Note: PVH is not yet supported on x86_32. */
         ctxt->user_regs.fs = __KERNEL_PERCPU;
         ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
-#else
-        ctxt->gs_base_kernel = per_cpu_offset(cpu);
 #endif
         ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
 
         memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
 
-        {
+        if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+                ctxt->flags = VGCF_IN_KERNEL;
                 ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
                 ctxt->user_regs.ds = __USER_DS;
                 ctxt->user_regs.es = __USER_DS;
+                ctxt->user_regs.ss = __KERNEL_DS;
 
                 xen_copy_trap_info(ctxt->trap_ctxt);
 
@@ -396,18 +404,27 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 #ifdef CONFIG_X86_32
                 ctxt->event_callback_cs     = __KERNEL_CS;
                 ctxt->failsafe_callback_cs  = __KERNEL_CS;
+#else
+                ctxt->gs_base_kernel = per_cpu_offset(cpu);
 #endif
                 ctxt->event_callback_eip    =
                                         (unsigned long)xen_hypervisor_callback;
                 ctxt->failsafe_callback_eip =
                                         (unsigned long)xen_failsafe_callback;
+                ctxt->user_regs.cs = __KERNEL_CS;
+                per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
+#ifdef CONFIG_X86_32
         }
-        ctxt->user_regs.cs = __KERNEL_CS;
+#else
+        } else
+                /* N.B. The user_regs.eip (cpu_bringup_and_idle) is called with
+                 * %rdi having the cpu number - which means are passing in
+                 * as the first parameter the cpu. Subtle!
+                 */
+                ctxt->user_regs.rdi = cpu;
+#endif
         ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
-
-        per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
         ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
-
         if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt))
                 BUG();
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 95f8c6142328..9059c24ed564 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -123,4 +123,5 @@ __visible void xen_adjust_exception_frame(void);
 
 extern int xen_panic_handler_init(void);
 
+void xen_setup_gdt(int cpu);
 #endif /* XEN_OPS_H */