x86/xen: Set EFER.NX and EFER.SCE in PVH guests

This fixes two bugs in PVH guests:

  - Not setting EFER.NX means the NX bit in page table entries is
    ignored on Intel processors and causes reserved bit page faults on
    AMD processors.

  - After the Xen commit 7645640d6ff1 ("x86/PVH: don't set EFER_SCE for
    pvh guest") PVH guests are required to set EFER.SCE to enable the
    SYSCALL instruction.

Secondary VCPUs are started with pagetables with the NX bit set so
EFER.NX must be set before using any stack or data segment.
xen_pvh_cpu_early_init() is the new secondary VCPU entry point that
sets EFER before jumping to cpu_bringup_and_idle().

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f7e01fa1545f9dd30ad3f8ca9fd91cc13f293d37..acb0effd80773f347ef8a7e6591d6a447c894423 100644 (file)
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1463,6 +1463,7 @@ static void __ref xen_setup_gdt(int cpu)
        pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
+#ifdef CONFIG_XEN_PVH
 /*
  * A PV guest starts with default flags that are not set for PVH, set them
  * here asap.
@@ -1508,12 +1509,15 @@ static void __init xen_pvh_early_guest_init(void)
                return;
 
        xen_have_vector_callback = 1;
+
+       xen_pvh_early_cpu_init(0, false);
        xen_pvh_set_cr_flags(0);
 
 #ifdef CONFIG_X86_32
        BUG(); /* PVH: Implement proper support. */
 #endif
 }
+#endif    /* CONFIG_XEN_PVH */
 
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
@@ -1528,7 +1532,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
        xen_domain_type = XEN_PV_DOMAIN;
 
        xen_setup_features();
+#ifdef CONFIG_XEN_PVH
        xen_pvh_early_guest_init();
+#endif
        xen_setup_machphys_mapping();
 
        /* Install Xen paravirt ops */

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7005974c3ff308a2504def1cb035d393ed82693f..c670d7518cf4a21e4b8e3238d2825a34b67b5a03 100644 (file)
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -37,6 +37,7 @@
 #include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "mmu.h"
+#include "smp.h"
 
 cpumask_var_t xen_cpu_initialized_map;
 
@@ -99,10 +100,14 @@ static void cpu_bringup(void)
        wmb();                  /* make sure everything is out */
 }
 
-/* Note: cpu parameter is only relevant for PVH */
-static void cpu_bringup_and_idle(int cpu)
+/*
+ * Note: cpu parameter is only relevant for PVH. The reason for passing it
+ * is we can't do smp_processor_id until the percpu segments are loaded, for
+ * which we need the cpu number! So we pass it in rdi as first parameter.
+ */
+asmlinkage __visible void cpu_bringup_and_idle(int cpu)
 {
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_XEN_PVH
        if (xen_feature(XENFEAT_auto_translated_physmap) &&
            xen_feature(XENFEAT_supervisor_mode_kernel))
                xen_pvh_secondary_vcpu_init(cpu);
@@ -374,11 +379,10 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
        ctxt->user_regs.fs = __KERNEL_PERCPU;
        ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
 #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->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
                ctxt->flags = VGCF_IN_KERNEL;
                ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
                ctxt->user_regs.ds = __USER_DS;
@@ -413,15 +417,18 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
                                        (unsigned long)xen_failsafe_callback;
                ctxt->user_regs.cs = __KERNEL_CS;
                per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
-#ifdef CONFIG_X86_32
        }
-#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!
+#ifdef CONFIG_XEN_PVH
+       else {
+               /*
+                * The vcpu comes on kernel page tables which have the NX pte
+                * bit set. This means before DS/SS is touched, NX in
+                * EFER must be set. Hence the following assembly glue code.
                 */
+               ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init;
                ctxt->user_regs.rdi = cpu;
+               ctxt->user_regs.rsi = true;  /* entry == true */
+       }
 #endif
        ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
        ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));

diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c7c2d89efd76ac3c7627168b0a3d2f3964627f66..963d62a35c824f69400675b51c2f4dc95e947826 100644 (file)
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -8,4 +8,12 @@ extern void xen_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);
 
+#ifdef CONFIG_XEN_PVH
+extern void xen_pvh_early_cpu_init(int cpu, bool entry);
+#else
+static inline void xen_pvh_early_cpu_init(int cpu, bool entry)
+{
+}
+#endif
+
 #endif

diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 46408e51c1dcec12601d9941a07da8b6bc673cc3..674b222544b78dde6c3b737a767500e5f19627b3 100644 (file)
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -47,6 +47,41 @@ ENTRY(startup_xen)
 
        __FINIT
 
+#ifdef CONFIG_XEN_PVH
+/*
+ * xen_pvh_early_cpu_init() - early PVH VCPU initialization
+ * @cpu:   this cpu number (%rdi)
+ * @entry: true if this is a secondary vcpu coming up on this entry
+ *         point, false if this is the boot CPU being initialized for
+ *         the first time (%rsi)
+ *
+ * Note: This is called as a function on the boot CPU, and is the entry point
+ *       on the secondary CPU.
+ */
+ENTRY(xen_pvh_early_cpu_init)
+       mov     %rsi, %r11
+
+       /* Gather features to see if NX implemented. */
+       mov     $0x80000001, %eax
+       cpuid
+       mov     %edx, %esi
+
+       mov     $MSR_EFER, %ecx
+       rdmsr
+       bts     $_EFER_SCE, %eax
+
+       bt      $20, %esi
+       jnc     1f              /* No NX, skip setting it */
+       bts     $_EFER_NX, %eax
+1:     wrmsr
+#ifdef CONFIG_SMP
+       cmp     $0, %r11b
+       jne     cpu_bringup_and_idle
+#endif
+       ret
+
+#endif /* CONFIG_XEN_PVH */
+
 .pushsection .text
        .balign PAGE_SIZE
 ENTRY(hypercall_page)