x86: correct LDT checks

- MMUEXT_SET_LDT should behave as similarly to the LLDT instruction as
  possible: fail only if the base address is non-canonical
- instead LDT descriptor accesses should fault if the descriptor
  address ends up being non-canonical (by ensuring this we at once
  avoid reading an entry from the mach-to-phys table and consider it a
  page table entry)
- fault propagation on using LDT selectors must distinguish #PF and #GP
  (the latter must be raised for a non-canonical descriptor address,
  which also applies to several other uses of propagate_page_fault(),
  and hence the problem is being fixed there)
- map_ldt_shadow_page() should properly wrap addresses for 32-bit VMs

At once remove the odd invokation of map_ldt_shadow_page() from the
MMUEXT_SET_LDT handler: There's nothing really telling us that the
first LDT page is going to be preferred over others.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Keir Fraser <keir@xen.org>
master commit: 40d66baa46ca8a9ffa6df3e063a967d08ec92bcf
master date: 2013-10-11 09:28:26 +0200

6 files changed, 38 insertions, 26 deletions

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 89dd3cb4ba..68c435e401 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -779,12 +779,7 @@ int arch_set_info_guest(
                 fixup_guest_code_selector(d, c.nat->trap_ctxt[i].cs);
             }
 
-            /* LDT safety checks. */
-            if ( ((c.nat->ldt_base & (PAGE_SIZE-1)) != 0) ||
-                 (c.nat->ldt_ents > 8192) ||
-                 !array_access_ok(c.nat->ldt_base,
-                                  c.nat->ldt_ents,
-                                  LDT_ENTRY_SIZE) )
+            if ( !__addr_ok(c.nat->ldt_base) )
                 return -EINVAL;
         }
 #ifdef CONFIG_COMPAT
@@ -798,16 +793,13 @@ int arch_set_info_guest(
 
             for ( i = 0; i < 256; i++ )
                 fixup_guest_code_selector(d, c.cmp->trap_ctxt[i].cs);
-
-            /* LDT safety checks. */
-            if ( ((c.cmp->ldt_base & (PAGE_SIZE-1)) != 0) ||
-                 (c.cmp->ldt_ents > 8192) ||
-                 !compat_array_access_ok(c.cmp->ldt_base,
-                                         c.cmp->ldt_ents,
-                                         LDT_ENTRY_SIZE) )
-                return -EINVAL;
         }
 #endif
+
+        /* LDT safety checks. */
+        if ( ((c(ldt_base) & (PAGE_SIZE - 1)) != 0) ||
+             (c(ldt_ents) > 8192) )
+            return -EINVAL;
     }
 
     v->fpu_initialised = !!(flags & VGCF_I387_VALID);
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index fcd793973c..df687afa6f 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -660,6 +660,8 @@ int map_ldt_shadow_page(unsigned int off)
 
     BUG_ON(unlikely(in_irq()));
 
+    if ( is_pv_32bit_domain(d) )
+        gva = (u32)gva;
     guest_get_eff_kern_l1e(v, gva, &l1e);
     if ( unlikely(!(l1e_get_flags(l1e) & _PAGE_PRESENT)) )
         return 0;
@@ -3495,9 +3497,8 @@ long do_mmuext_op(
                 MEM_LOG("ignoring SET_LDT hypercall from external domain");
                 okay = 0;
             }
-            else if ( ((ptr & (PAGE_SIZE-1)) != 0) || 
-                      (ents > 8192) ||
-                      !array_access_ok(ptr, ents, LDT_ENTRY_SIZE) )
+            else if ( ((ptr & (PAGE_SIZE - 1)) != 0) || !__addr_ok(ptr) ||
+                      (ents > 8192) )
             {
                 okay = 0;
                 MEM_LOG("Bad args to SET_LDT: ptr=%lx, ents=%lx", ptr, ents);
@@ -3510,8 +3511,6 @@ long do_mmuext_op(
                 curr->arch.pv_vcpu.ldt_base = ptr;
                 curr->arch.pv_vcpu.ldt_ents = ents;
                 load_LDT(curr);
-                if ( ents != 0 )
-                    (void)map_ldt_shadow_page(0);
             }
             break;
         }
diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index 2fc992766f..fd8bd8ca99 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -1107,12 +1107,26 @@ static void reserved_bit_page_fault(
     show_execution_state(regs);
 }
 
-void propagate_page_fault(unsigned long addr, u16 error_code)
+struct trap_bounce *propagate_page_fault(unsigned long addr, u16 error_code)
 {
     struct trap_info *ti;
     struct vcpu *v = current;
     struct trap_bounce *tb = &v->arch.pv_vcpu.trap_bounce;
 
+#ifdef __x86_64__
+    if ( unlikely(!is_canonical_address(addr)) )
+    {
+        ti = &v->arch.pv_vcpu.trap_ctxt[TRAP_gp_fault];
+        tb->flags      = TBF_EXCEPTION | TBF_EXCEPTION_ERRCODE;
+        tb->error_code = 0;
+        tb->cs         = ti->cs;
+        tb->eip        = ti->address;
+        if ( TI_GET_IF(ti) )
+            tb->flags |= TBF_INTERRUPT;
+        return tb;
+    }
+#endif
+
     v->arch.pv_vcpu.ctrlreg[2] = addr;
     arch_set_cr2(v, addr);
 
@@ -1139,6 +1153,8 @@ void propagate_page_fault(unsigned long addr, u16 error_code)
 
     if ( unlikely(error_code & PFEC_reserved_bit) )
         reserved_bit_page_fault(addr, guest_cpu_user_regs());
+
+    return NULL;
 }
 
 static int handle_gdt_ldt_mapping_fault(
@@ -1172,13 +1188,16 @@ static int handle_gdt_ldt_mapping_fault(
         }
         else
         {
+            struct trap_bounce *tb;
+
             /* In hypervisor mode? Leave it to the #PF handler to fix up. */
             if ( !guest_mode(regs) )
                 return 0;
-            /* In guest mode? Propagate #PF to guest, with adjusted %cr2. */
-            propagate_page_fault(
-                curr->arch.pv_vcpu.ldt_base + offset,
-                regs->error_code);
+            /* In guest mode? Propagate fault to guest, with adjusted %cr2. */
+            tb = propagate_page_fault(curr->arch.pv_vcpu.ldt_base + offset,
+                                      regs->error_code);
+            if ( tb )
+                tb->error_code = ((u16)offset & ~3) | 4;
         }
     }
     else
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index e783d8a9ab..10a543e868 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -602,7 +602,7 @@ int new_guest_cr3(unsigned long pfn);
 void make_cr3(struct vcpu *v, unsigned long mfn);
 void update_cr3(struct vcpu *v);
 int vcpu_destroy_pagetables(struct vcpu *);
-void propagate_page_fault(unsigned long addr, u16 error_code);
+struct trap_bounce *propagate_page_fault(unsigned long addr, u16 error_code);
 void *do_page_walk(struct vcpu *v, unsigned long addr);
 
 int __sync_local_execstate(void);
diff --git a/xen/include/asm-x86/paging.h b/xen/include/asm-x86/paging.h
index c432a973ed..ee35dff865 100644
--- a/xen/include/asm-x86/paging.h
+++ b/xen/include/asm-x86/paging.h
@@ -408,7 +408,8 @@ guest_get_eff_l1e(struct vcpu *v, unsigned long addr, void *eff_l1e)
     if ( likely(!paging_mode_translate(v->domain)) )
     {
         ASSERT(!paging_mode_external(v->domain));
-        if ( __copy_from_user(eff_l1e, 
+        if ( !__addr_ok(addr) ||
+             __copy_from_user(eff_l1e,
                               &__linear_l1_table[l1_linear_offset(addr)],
                               sizeof(l1_pgentry_t)) != 0 )
             *(l1_pgentry_t *)eff_l1e = l1e_empty();
diff --git a/xen/include/asm-x86/x86_32/uaccess.h b/xen/include/asm-x86/x86_32/uaccess.h
index d6a52301af..9ac21c4e12 100644
--- a/xen/include/asm-x86/x86_32/uaccess.h
+++ b/xen/include/asm-x86/x86_32/uaccess.h
@@ -15,6 +15,7 @@
 		:"1" (addr),"g" ((int)(size)),"r" (HYPERVISOR_VIRT_START)); \
 	flag; })
 
+#define __addr_ok(addr) (likely((unsigned long)(addr) < HYPERVISOR_VIRT_START))
 #define access_ok(addr,size) (likely(__range_not_ok(addr,size) == 0))
 
 #define array_access_ok(addr,count,size) \