[PATCH RFC v13 08/20] pvh: PVH access to hypercalls

[George Dunlap <george.dunlap@eu.citrix.com>]

Hypercalls where we now have unrestricted access:
* memory_op
* console_io
* vcpu_op
* mmuext_op

We also restrict PVH domain access to HVMOP_*_param to reading and
writing HVM_PARAM_CALLBACK_IRQ.

Most hvm_op functions require "is_hvm_domain()" and will default to
-EINVAL; exceptions are HVMOP_get_time and HVMOP_xentrace.

Finally, we restrict setting IOPL permissions for a PVH domain.

Signed-off-by: George Dunlap <george.dunlap@eu.citrix.com>
Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
---
v13:
 - Minor code tweaks, as suggested during review
 - return -ENOSYS for set_iopl and set_iobitmap calls
 - Allow HVMOP_set_param for HVM_PARAM_CALLBACK_IRQ.  We still don't
   allow other values to be written.

CC: Jan Beulich <jbeulich@suse.com>
CC: Tim Deegan <tim@xen.org>
CC: Keir Fraser <keir@xen.org>
---
 xen/arch/x86/hvm/hvm.c  |   48 ++++++++++++++++++++++++++++++++++++++---------
 xen/arch/x86/hvm/mtrr.c |    1 +
 xen/arch/x86/physdev.c  |   10 ++++++++++
 xen/common/kernel.c     |   13 +++++++++++--
 4 files changed, 61 insertions(+), 11 deletions(-)

diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 7f7b9f5..fd2e117 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -3375,6 +3375,24 @@ static hvm_hypercall_t *const hvm_hypercall32_table[NR_hypercalls] = {
     HYPERCALL(tmem_op)
 };
 
+/* PVH 32bitfixme. */
+static hvm_hypercall_t *const pvh_hypercall64_table[NR_hypercalls] = {
+    HYPERCALL(platform_op),
+    HYPERCALL(memory_op),
+    HYPERCALL(xen_version),
+    HYPERCALL(console_io),
+    [ __HYPERVISOR_grant_table_op ]  = (hvm_hypercall_t *)hvm_grant_table_op,
+    HYPERCALL(vcpu_op),
+    HYPERCALL(mmuext_op),
+    HYPERCALL(xsm_op),
+    HYPERCALL(sched_op),
+    HYPERCALL(event_channel_op),
+    [ __HYPERVISOR_physdev_op ]      = (hvm_hypercall_t *)hvm_physdev_op,
+    HYPERCALL(hvm_op),
+    HYPERCALL(sysctl),
+    HYPERCALL(domctl)
+};
+
 int hvm_do_hypercall(struct cpu_user_regs *regs)
 {
     struct vcpu *curr = current;
@@ -3401,7 +3419,9 @@ int hvm_do_hypercall(struct cpu_user_regs *regs)
     if ( (eax & 0x80000000) && is_viridian_domain(curr->domain) )
         return viridian_hypercall(regs);
 
-    if ( (eax >= NR_hypercalls) || !hvm_hypercall32_table[eax] )
+    if ( (eax >= NR_hypercalls) ||
+         (is_pvh_vcpu(curr) ? !pvh_hypercall64_table[eax]
+                            : !hvm_hypercall32_table[eax]) )
     {
         regs->eax = -ENOSYS;
         return HVM_HCALL_completed;
@@ -3416,16 +3436,20 @@ int hvm_do_hypercall(struct cpu_user_regs *regs)
                     regs->r10, regs->r8, regs->r9);
 
         curr->arch.hvm_vcpu.hcall_64bit = 1;
-        regs->rax = hvm_hypercall64_table[eax](regs->rdi,
-                                               regs->rsi,
-                                               regs->rdx,
-                                               regs->r10,
-                                               regs->r8,
-                                               regs->r9); 
+        if ( is_pvh_vcpu(curr) )
+            regs->rax = pvh_hypercall64_table[eax](regs->rdi, regs->rsi,
+                                                   regs->rdx, regs->r10,
+                                                   regs->r8, regs->r9);
+        else
+            regs->rax = hvm_hypercall64_table[eax](regs->rdi, regs->rsi,
+                                                   regs->rdx, regs->r10,
+                                                   regs->r8, regs->r9);
         curr->arch.hvm_vcpu.hcall_64bit = 0;
     }
     else
     {
+        ASSERT(!is_pvh_vcpu(curr));   /* PVH 32bitfixme. */
+
         HVM_DBG_LOG(DBG_LEVEL_HCALL, "hcall%u(%x, %x, %x, %x, %x, %x)", eax,
                     (uint32_t)regs->ebx, (uint32_t)regs->ecx,
                     (uint32_t)regs->edx, (uint32_t)regs->esi,
@@ -3850,7 +3874,11 @@ long do_hvm_op(unsigned long op, XEN_GUEST_HANDLE_PARAM(void) arg)
             return -ESRCH;
 
         rc = -EINVAL;
-        if ( !is_hvm_domain(d) )
+        if ( !has_hvm_container_domain(d) )
+            goto param_fail;
+
+        if ( is_pvh_domain(d)
+             && (a.index != HVM_PARAM_CALLBACK_IRQ) )
             goto param_fail;
 
         rc = xsm_hvm_param(XSM_TARGET, d, op);
@@ -4024,7 +4052,9 @@ long do_hvm_op(unsigned long op, XEN_GUEST_HANDLE_PARAM(void) arg)
 
             if ( rc == 0 ) 
             {
-                d->arch.hvm_domain.params[a.index] = a.value;
+                /* PVH domains don't have a params struct */
+                if ( d->arch.hvm_domain.params )
+                    d->arch.hvm_domain.params[a.index] = a.value;
 
                 switch( a.index )
                 {
diff --git a/xen/arch/x86/hvm/mtrr.c b/xen/arch/x86/hvm/mtrr.c
index ef51a8d..9785cef 100644
--- a/xen/arch/x86/hvm/mtrr.c
+++ b/xen/arch/x86/hvm/mtrr.c
@@ -578,6 +578,7 @@ int32_t hvm_set_mem_pinned_cacheattr(
 {
     struct hvm_mem_pinned_cacheattr_range *range;
 
+    /* Side note: A PVH guest writes to MSR_IA32_CR_PAT natively. */
     if ( !((type == PAT_TYPE_UNCACHABLE) ||
            (type == PAT_TYPE_WRCOMB) ||
            (type == PAT_TYPE_WRTHROUGH) ||
diff --git a/xen/arch/x86/physdev.c b/xen/arch/x86/physdev.c
index dab6213..7d787dc 100644
--- a/xen/arch/x86/physdev.c
+++ b/xen/arch/x86/physdev.c
@@ -519,6 +519,11 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 
     case PHYSDEVOP_set_iopl: {
         struct physdev_set_iopl set_iopl;
+        
+        ret = -ENOSYS;
+        if ( is_pvh_vcpu(current) )
+            break;
+
         ret = -EFAULT;
         if ( copy_from_guest(&set_iopl, arg, 1) != 0 )
             break;
@@ -532,6 +537,11 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 
     case PHYSDEVOP_set_iobitmap: {
         struct physdev_set_iobitmap set_iobitmap;
+
+        ret = -ENOSYS;
+        if ( is_pvh_vcpu(current) )
+            break;
+
         ret = -EFAULT;
         if ( copy_from_guest(&set_iobitmap, arg, 1) != 0 )
             break;
diff --git a/xen/common/kernel.c b/xen/common/kernel.c
index 2d68a7c..6a708f3 100644
--- a/xen/common/kernel.c
+++ b/xen/common/kernel.c
@@ -305,14 +305,23 @@ DO(xen_version)(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
             if ( current->domain == dom0 )
                 fi.submap |= 1U << XENFEAT_dom0;
 #ifdef CONFIG_X86
-            if ( is_pv_vcpu(current) )
+            switch(d->guest_type) {
+            case guest_type_pv:
                 fi.submap |= (1U << XENFEAT_mmu_pt_update_preserve_ad) |
                              (1U << XENFEAT_highmem_assist) |
                              (1U << XENFEAT_gnttab_map_avail_bits);
-            else
+                break;
+            case guest_type_pvh:
+                fi.submap |= (1U << XENFEAT_hvm_safe_pvclock) |
+                             (1U << XENFEAT_supervisor_mode_kernel) |
+                             (1U << XENFEAT_hvm_callback_vector);
+                break;
+            case guest_type_hvm:
                 fi.submap |= (1U << XENFEAT_hvm_safe_pvclock) |
                              (1U << XENFEAT_hvm_callback_vector) |
                              (1U << XENFEAT_hvm_pirqs);
+                break;
+            }
 #endif
             break;
         default:
-- 
1.7.9.5