From: Roger Pau Monne <roger.pau@citrix.com>
Date: Fri, 21 Jun 2024 13:28:49 +0000 (+0200)
Subject: (no commit message)
X-Git-Url: http://xenbits.xensource.com/gitweb?a=commitdiff_plain;h=0d26d222dbc9c44cf9e5c9f02b6e4d4f8e02c46e;p=people%2Froyger%2Fxen.git

---

diff --git a/xen/arch/x86/boot/x86_64.S b/xen/arch/x86/boot/x86_64.S
index 04bb62ae86..af78548201 100644
--- a/xen/arch/x86/boot/x86_64.S
+++ b/xen/arch/x86/boot/x86_64.S
@@ -15,6 +15,17 @@ ENTRY(__high_start)
         mov     $XEN_MINIMAL_CR4,%rcx
         mov     %rcx,%cr4
 
+        /*
+         * Possibly switch to the per-CPU idle page-tables. Note we cannot
+         * switch earlier as the per-CPU page-tables might be above 4G, and
+         * hence need to load them from 64bit code.
+         */
+        mov     ap_cr3(%rip), %rax
+        test    %rax, %rax
+        jz      .L_skip_cr3
+        mov     %rax, %cr3
+.L_skip_cr3:
+
         mov     stack_start(%rip),%rsp
 
         /* Reset EFLAGS (subsumes CLI and CLD). */
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 7ea2439b5c..410d295c3c 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -555,6 +555,7 @@ void arch_vcpu_regs_init(struct vcpu *v)
 int arch_vcpu_create(struct vcpu *v)
 {
     struct domain *d = v->domain;
+    root_pgentry_t *pgt = NULL;
     int rc;
 
     v->arch.flags = TF_kernel_mode;
@@ -589,7 +590,23 @@ int arch_vcpu_create(struct vcpu *v)
     else
     {
         /* Idle domain */
-        v->arch.cr3 = __pa(idle_pg_table);
+        if ( (opt_asi_pv || opt_asi_hvm) && v->vcpu_id )
+        {
+            pgt = alloc_xenheap_page();
+
+            /*
+             * For the idle vCPU 0 (the BSP idle vCPU) use idle_pg_table
+             * directly, there's no need to create yet another copy.
+             */
+            rc = -ENOMEM;
+            if ( !pgt )
+                goto fail;
+
+            copy_page(pgt, idle_pg_table);
+            v->arch.cr3 = __pa(pgt);
+        }
+        else
+            v->arch.cr3 = __pa(idle_pg_table);
         rc = 0;
         v->arch.msrs = ZERO_BLOCK_PTR; /* Catch stray misuses */
     }
@@ -611,6 +628,7 @@ int arch_vcpu_create(struct vcpu *v)
     vcpu_destroy_fpu(v);
     xfree(v->arch.msrs);
     v->arch.msrs = NULL;
+    free_xenheap_page(pgt);
 
     return rc;
 }
diff --git a/xen/arch/x86/domain_page.c b/xen/arch/x86/domain_page.c
index eac5e3304f..99b78af90f 100644
--- a/xen/arch/x86/domain_page.c
+++ b/xen/arch/x86/domain_page.c
@@ -51,7 +51,7 @@ static inline struct vcpu *mapcache_current_vcpu(void)
         if ( (v = idle_vcpu[smp_processor_id()]) == current )
             sync_local_execstate();
         /* We must now be running on the idle page table. */
-        ASSERT(cr3_pa(read_cr3()) == __pa(idle_pg_table));
+        ASSERT(cr3_pa(read_cr3()) == cr3_pa(v->arch.cr3));
     }
 
     return v;
diff --git a/xen/arch/x86/include/asm/setup.h b/xen/arch/x86/include/asm/setup.h
index d75589178b..a8452fce8f 100644
--- a/xen/arch/x86/include/asm/setup.h
+++ b/xen/arch/x86/include/asm/setup.h
@@ -14,6 +14,7 @@ extern unsigned long xenheap_initial_phys_start;
 extern uint64_t boot_tsc_stamp;
 
 extern void *stack_start;
+extern unsigned long ap_cr3;
 
 void early_cpu_init(bool verbose);
 void early_time_init(void);
diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index eee20bb175..c4f6dbcb61 100644
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -158,6 +158,9 @@ char asmlinkage __section(".init.bss.stack_aligned") __aligned(STACK_SIZE)
 /* Used by the BSP/AP paths to find the higher half stack mapping to use. */
 void *stack_start = cpu0_stack + STACK_SIZE - sizeof(struct cpu_info);
 
+/* cr3 value for the AP to load on boot. */
+unsigned long ap_cr3;
+
 /* Used by the boot asm to stash the relocated multiboot info pointer. */
 unsigned int asmlinkage __initdata multiboot_ptr;
 
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 8fc8710ec8..302b1a0c75 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -581,6 +581,13 @@ static int do_boot_cpu(int apicid, int cpu)
 
     stack_start = stack_base[cpu] + STACK_SIZE - sizeof(struct cpu_info);
 
+    /*
+     * If per-CPU idle root page table has been allocated, switch to it as
+     * part of the AP bringup trampoline.
+     */
+    ap_cr3 = idle_vcpu[cpu]->arch.cr3 != __pa(idle_pg_table) ?
+             idle_vcpu[cpu]->arch.cr3 : 0;
+
     /* This grunge runs the startup process for the targeted processor. */
 
     set_cpu_state(CPU_STATE_INIT);