Pullup ticket #6799 - requested by bouyer
sysutils/xenkernel415: security fix

Revisions pulled up:
- sysutils/xenkernel415/Makefile                                1.11
- sysutils/xenkernel415/distinfo                                1.10
- sysutils/xenkernel415/patches/patch-XSA438                    1.1

---
   Module Name:	pkgsrc
   Committed By:	bouyer
   Date:		Thu Sep 21 10:39:45 UTC 2023

   Modified Files:
   	pkgsrc/sysutils/xenkernel415: Makefile distinfo
   Added Files:
   	pkgsrc/sysutils/xenkernel415/patches: patch-XSA438

   Log Message:
   Apply upstream patch for security issue XSA438
   Bump PKGREVISION


(bsiegert)

$NetBSD: patch-XSA438,v 1.1.2.2 2023/09/23 18:04:05 bsiegert Exp $

From: Jan Beulich <jbeulich@suse.com>
Subject: x86/shadow: defer releasing of PV's top-level shadow reference

sh_set_toplevel_shadow() re-pinning the top-level shadow we may be
running on is not enough (and at the same time unnecessary when the
shadow isn't what we're running on): That shadow becomes eligible for
blowing away (from e.g. shadow_prealloc()) immediately after the
paging lock was dropped. Yet it needs to remain valid until the actual
page table switch occurred.

Propagate up the call chain the shadow entry that needs releasing
eventually, and carry out the release immediately after switching page
tables. Handle update_cr3() failures by switching to idle pagetables.
Note that various further uses of update_cr3() are HVM-only or only act
on paused vCPU-s, in which case sh_set_toplevel_shadow() will not defer
releasing of the reference.

While changing the update_cr3() hook, also convert the "do_locking"
parameter to boolean.

This is CVE-2023-34322 / XSA-438.

Reported-by: Tim Deegan <tim@xen.org>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: George Dunlap <george.dunlap@cloud.com>

--- xen/arch/x86/mm/hap/hap.c.orig
+++ xen/arch/x86/mm/hap/hap.c
@@ -728,10 +728,12 @@ static bool_t hap_invlpg(struct vcpu *v,
     return 1;
 }
 
-static void hap_update_cr3(struct vcpu *v, int do_locking, bool noflush)
+static pagetable_t hap_update_cr3(struct vcpu *v, bool do_locking, bool noflush)
 {
     v->arch.hvm.hw_cr[3] = v->arch.hvm.guest_cr[3];
     hvm_update_guest_cr3(v, noflush);
+
+    return pagetable_null();
 }
 
 /*
--- xen/arch/x86/mm/shadow/common.c.orig
+++ xen/arch/x86/mm/shadow/common.c
@@ -2641,13 +2641,13 @@ void shadow_update_paging_modes(struct v
 }
 
 /* Set up the top-level shadow and install it in slot 'slot' of shadow_table */
-void sh_set_toplevel_shadow(struct vcpu *v,
-                            unsigned int slot,
-                            mfn_t gmfn,
-                            unsigned int root_type,
-                            mfn_t (*make_shadow)(struct vcpu *v,
-                                                 mfn_t gmfn,
-                                                 uint32_t shadow_type))
+pagetable_t sh_set_toplevel_shadow(struct vcpu *v,
+                                   unsigned int slot,
+                                   mfn_t gmfn,
+                                   unsigned int root_type,
+                                   mfn_t (*make_shadow)(struct vcpu *v,
+                                                        mfn_t gmfn,
+                                                        uint32_t shadow_type))
 {
     mfn_t smfn;
     pagetable_t old_entry, new_entry;
@@ -2704,20 +2704,37 @@ void sh_set_toplevel_shadow(struct vcpu
                   mfn_x(gmfn), mfn_x(pagetable_get_mfn(new_entry)));
     v->arch.paging.shadow.shadow_table[slot] = new_entry;
 
-    /* Decrement the refcount of the old contents of this slot */
-    if ( !pagetable_is_null(old_entry) )
+    /*
+     * Decrement the refcount of the old contents of this slot, unless
+     * we're still running on that shadow - in that case it'll need holding
+     * on to until the actual page table switch did occur.
+     */
+    if ( !pagetable_is_null(old_entry) && (v != current || !is_pv_domain(d)) )
     {
-        mfn_t old_smfn = pagetable_get_mfn(old_entry);
-        /* Need to repin the old toplevel shadow if it's been unpinned
-         * by shadow_prealloc(): in PV mode we're still running on this
-         * shadow and it's not safe to free it yet. */
-        if ( !mfn_to_page(old_smfn)->u.sh.pinned && !sh_pin(d, old_smfn) )
-        {
-            printk(XENLOG_G_ERR "can't re-pin %"PRI_mfn"\n", mfn_x(old_smfn));
-            domain_crash(d);
-        }
-        sh_put_ref(d, old_smfn, 0);
+        sh_put_ref(d, pagetable_get_mfn(old_entry), 0);
+        old_entry = pagetable_null();
     }
+
+    /*
+     * 2- and 3-level shadow mode is used for HVM only. Therefore we never run
+     * on such a shadow, so only call sites requesting an L4 shadow need to pay
+     * attention to the returned value.
+     */
+    ASSERT(pagetable_is_null(old_entry) || root_type == SH_type_l4_64_shadow);
+
+    return old_entry;
+}
+
+/*
+ * Helper invoked when releasing of a top-level shadow's reference was
+ * deferred in sh_set_toplevel_shadow() above.
+ */
+void shadow_put_top_level(struct domain *d, pagetable_t old_entry)
+{
+    ASSERT(!pagetable_is_null(old_entry));
+    paging_lock(d);
+    sh_put_ref(d, pagetable_get_mfn(old_entry), 0);
+    paging_unlock(d);
 }
 
 /**************************************************************************/
--- xen/arch/x86/mm/shadow/multi.c.orig
+++ xen/arch/x86/mm/shadow/multi.c
@@ -3604,8 +3604,8 @@ sh_detach_old_tables(struct vcpu *v)
     }
 }
 
-static void
-sh_update_cr3(struct vcpu *v, int do_locking, bool noflush)
+static pagetable_t
+sh_update_cr3(struct vcpu *v, bool do_locking, bool noflush)
 /* Updates vcpu->arch.cr3 after the guest has changed CR3.
  * Paravirtual guests should set v->arch.guest_table (and guest_table_user,
  * if appropriate).
@@ -3619,6 +3619,7 @@ sh_update_cr3(struct vcpu *v, int do_loc
 {
     struct domain *d = v->domain;
     mfn_t gmfn;
+    pagetable_t old_entry = pagetable_null();
 #if GUEST_PAGING_LEVELS == 3 && defined(CONFIG_HVM)
     const guest_l3e_t *gl3e;
     unsigned int i, guest_idx;
@@ -3628,7 +3629,7 @@ sh_update_cr3(struct vcpu *v, int do_loc
     if ( is_pv_domain(d) && !v->is_initialised )
     {
         ASSERT(v->arch.cr3 == 0);
-        return;
+        return old_entry;
     }
 
     if ( do_locking ) paging_lock(v->domain);
@@ -3701,11 +3702,12 @@ sh_update_cr3(struct vcpu *v, int do_loc
 #if GUEST_PAGING_LEVELS == 4
     if ( sh_remove_write_access(d, gmfn, 4, 0) != 0 )
         guest_flush_tlb_mask(d, d->dirty_cpumask);
-    sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l4_shadow, sh_make_shadow);
+    old_entry = sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l4_shadow,
+                                       sh_make_shadow);
     if ( unlikely(pagetable_is_null(v->arch.paging.shadow.shadow_table[0])) )
     {
         ASSERT(d->is_dying || d->is_shutting_down);
-        return;
+        return old_entry;
     }
     if ( !shadow_mode_external(d) && !is_pv_32bit_domain(d) )
     {
@@ -3751,26 +3753,32 @@ sh_update_cr3(struct vcpu *v, int do_loc
                 gl2gfn = guest_l3e_get_gfn(gl3e[i]);
                 gl2mfn = get_gfn_query_unlocked(d, gfn_x(gl2gfn), &p2mt);
                 if ( p2m_is_ram(p2mt) )
-                    sh_set_toplevel_shadow(v, i, gl2mfn, (i == 3)
-                                           ? SH_type_l2h_shadow
-                                           : SH_type_l2_shadow,
-                                           sh_make_shadow);
+                    old_entry = sh_set_toplevel_shadow(v, i, gl2mfn,
+                                                       (i == 3
+                                                        ? SH_type_l2h_shadow
+                                                        : SH_type_l2_shadow),
+                                                       sh_make_shadow);
                 else
-                    sh_set_toplevel_shadow(v, i, INVALID_MFN, 0,
-                                           sh_make_shadow);
+                    old_entry = sh_set_toplevel_shadow(v, i, INVALID_MFN, 0,
+                                                       sh_make_shadow);
             }
             else
-                sh_set_toplevel_shadow(v, i, INVALID_MFN, 0, sh_make_shadow);
+                old_entry = sh_set_toplevel_shadow(v, i, INVALID_MFN, 0,
+                                                   sh_make_shadow);
+
+            ASSERT(pagetable_is_null(old_entry));
         }
     }
 #elif GUEST_PAGING_LEVELS == 2
     if ( sh_remove_write_access(d, gmfn, 2, 0) != 0 )
         guest_flush_tlb_mask(d, d->dirty_cpumask);
-    sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l2_shadow, sh_make_shadow);
+    old_entry = sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l2_shadow,
+                                       sh_make_shadow);
+    ASSERT(pagetable_is_null(old_entry));
     if ( unlikely(pagetable_is_null(v->arch.paging.shadow.shadow_table[0])) )
     {
         ASSERT(d->is_dying || d->is_shutting_down);
-        return;
+        return old_entry;
     }
 #else
 #error This should never happen
@@ -3864,6 +3872,8 @@ sh_update_cr3(struct vcpu *v, int do_loc
 
     /* Release the lock, if we took it (otherwise it's the caller's problem) */
     if ( do_locking ) paging_unlock(v->domain);
+
+    return old_entry;
 }
 
 
--- xen/arch/x86/mm/shadow/none.c.orig
+++ xen/arch/x86/mm/shadow/none.c
@@ -50,9 +50,10 @@ static unsigned long _gva_to_gfn(struct
     return gfn_x(INVALID_GFN);
 }
 
-static void _update_cr3(struct vcpu *v, int do_locking, bool noflush)
+static pagetable_t _update_cr3(struct vcpu *v, bool do_locking, bool noflush)
 {
     ASSERT_UNREACHABLE();
+    return pagetable_null();
 }
 
 static void _update_paging_modes(struct vcpu *v)
--- xen/arch/x86/mm/shadow/private.h.orig
+++ xen/arch/x86/mm/shadow/private.h
@@ -360,13 +360,13 @@ mfn_t shadow_alloc(struct domain *d,
 void  shadow_free(struct domain *d, mfn_t smfn);
 
 /* Set up the top-level shadow and install it in slot 'slot' of shadow_table */
-void sh_set_toplevel_shadow(struct vcpu *v,
-                            unsigned int slot,
-                            mfn_t gmfn,
-                            unsigned int root_type,
-                            mfn_t (*make_shadow)(struct vcpu *v,
-                                                 mfn_t gmfn,
-                                                 uint32_t shadow_type));
+pagetable_t sh_set_toplevel_shadow(struct vcpu *v,
+                                   unsigned int slot,
+                                   mfn_t gmfn,
+                                   unsigned int root_type,
+                                   mfn_t (*make_shadow)(struct vcpu *v,
+                                                        mfn_t gmfn,
+                                                        uint32_t shadow_type));
 
 /* Update the shadows in response to a pagetable write from Xen */
 int sh_validate_guest_entry(struct vcpu *v, mfn_t gmfn, void *entry, u32 size);
--- xen/arch/x86/mm.c.orig
+++ xen/arch/x86/mm.c
@@ -564,15 +564,12 @@ void write_ptbase(struct vcpu *v)
  *
  * Update ref counts to shadow tables appropriately.
  */
-void update_cr3(struct vcpu *v)
+pagetable_t update_cr3(struct vcpu *v)
 {
     mfn_t cr3_mfn;
 
     if ( paging_mode_enabled(v->domain) )
-    {
-        paging_update_cr3(v, false);
-        return;
-    }
+        return paging_update_cr3(v, false);
 
     if ( !(v->arch.flags & TF_kernel_mode) )
         cr3_mfn = pagetable_get_mfn(v->arch.guest_table_user);
@@ -580,6 +577,8 @@ void update_cr3(struct vcpu *v)
         cr3_mfn = pagetable_get_mfn(v->arch.guest_table);
 
     make_cr3(v, cr3_mfn);
+
+    return pagetable_null();
 }
 
 static inline void set_tlbflush_timestamp(struct page_info *page)
@@ -3241,6 +3240,7 @@ int new_guest_cr3(mfn_t mfn)
     struct domain *d = curr->domain;
     int rc;
     mfn_t old_base_mfn;
+    pagetable_t old_shadow;
 
     if ( is_pv_32bit_domain(d) )
     {
@@ -3308,9 +3308,22 @@ int new_guest_cr3(mfn_t mfn)
     if ( !VM_ASSIST(d, m2p_strict) )
         fill_ro_mpt(mfn);
     curr->arch.guest_table = pagetable_from_mfn(mfn);
-    update_cr3(curr);
+    old_shadow = update_cr3(curr);
+
+    /*
+     * In shadow mode update_cr3() can fail, in which case here we're still
+     * running on the prior top-level shadow (which we're about to release).
+     * Switch to the idle page tables in such an event; the guest will have
+     * been crashed already.
+     */
+    if ( likely(!mfn_eq(pagetable_get_mfn(old_shadow),
+                        maddr_to_mfn(curr->arch.cr3 & ~X86_CR3_NOFLUSH))) )
+        write_ptbase(curr);
+    else
+        write_ptbase(idle_vcpu[curr->processor]);
 
-    write_ptbase(curr);
+    if ( !pagetable_is_null(old_shadow) )
+        shadow_put_top_level(d, old_shadow);
 
     if ( likely(mfn_x(old_base_mfn) != 0) )
     {
--- xen/arch/x86/pv/domain.c.orig
+++ xen/arch/x86/pv/domain.c
@@ -408,10 +408,13 @@ bool __init xpti_pcid_enabled(void)
 
 static void _toggle_guest_pt(struct vcpu *v)
 {
+    bool guest_update;
+    pagetable_t old_shadow;
     unsigned long cr3;
 
     v->arch.flags ^= TF_kernel_mode;
-    update_cr3(v);
+    guest_update = v->arch.flags & TF_kernel_mode;
+    old_shadow = update_cr3(v);
 
     /*
      * Don't flush user global mappings from the TLB. Don't tick TLB clock.
@@ -420,13 +423,31 @@ static void _toggle_guest_pt(struct vcpu
      * TLB flush (for just the incoming PCID), as the top level page table may
      * have changed behind our backs. To be on the safe side, suppress the
      * no-flush unconditionally in this case.
+     *
+     * Furthermore in shadow mode update_cr3() can fail, in which case here
+     * we're still running on the prior top-level shadow (which we're about
+     * to release). Switch to the idle page tables in such an event; the
+     * guest will have been crashed already.
      */
     cr3 = v->arch.cr3;
     if ( shadow_mode_enabled(v->domain) )
+    {
         cr3 &= ~X86_CR3_NOFLUSH;
+
+        if ( unlikely(mfn_eq(pagetable_get_mfn(old_shadow),
+                             maddr_to_mfn(cr3))) )
+        {
+            cr3 = idle_vcpu[v->processor]->arch.cr3;
+            /* Also suppress runstate/time area updates below. */
+            guest_update = false;
+        }
+    }
     write_cr3(cr3);
 
-    if ( !(v->arch.flags & TF_kernel_mode) )
+    if ( !pagetable_is_null(old_shadow) )
+        shadow_put_top_level(v->domain, old_shadow);
+
+    if ( !guest_update )
         return;
 
     if ( v->arch.pv.need_update_runstate_area && update_runstate_area(v) )
--- xen/include/asm-x86/mm.h.orig
+++ xen/include/asm-x86/mm.h
@@ -569,7 +569,7 @@ void audit_domains(void);
 #endif
 
 void make_cr3(struct vcpu *v, mfn_t mfn);
-void update_cr3(struct vcpu *v);
+pagetable_t update_cr3(struct vcpu *v);
 int vcpu_destroy_pagetables(struct vcpu *);
 void *do_page_walk(struct vcpu *v, unsigned long addr);
 
--- xen/include/asm-x86/paging.h.orig
+++ xen/include/asm-x86/paging.h
@@ -136,7 +136,7 @@ struct paging_mode {
                                             unsigned long cr3,
                                             paddr_t ga, uint32_t *pfec,
                                             unsigned int *page_order);
-    void          (*update_cr3            )(struct vcpu *v, int do_locking,
+    pagetable_t   (*update_cr3            )(struct vcpu *v, bool do_locking,
                                             bool noflush);
     void          (*update_paging_modes   )(struct vcpu *v);
     bool          (*flush_tlb             )(bool (*flush_vcpu)(void *ctxt,
@@ -309,9 +309,9 @@ static inline unsigned long paging_ga_to
 /* Update all the things that are derived from the guest's CR3.
  * Called when the guest changes CR3; the caller can then use v->arch.cr3
  * as the value to load into the host CR3 to schedule this vcpu */
-static inline void paging_update_cr3(struct vcpu *v, bool noflush)
+static inline pagetable_t paging_update_cr3(struct vcpu *v, bool noflush)
 {
-    paging_get_hostmode(v)->update_cr3(v, 1, noflush);
+    return paging_get_hostmode(v)->update_cr3(v, 1, noflush);
 }
 
 /* Update all the things that are derived from the guest's CR0/CR3/CR4.
--- xen/include/asm-x86/shadow.h.orig
+++ xen/include/asm-x86/shadow.h
@@ -97,6 +97,9 @@ void shadow_blow_tables_per_domain(struc
 int shadow_set_allocation(struct domain *d, unsigned int pages,
                           bool *preempted);
 
+/* Helper to invoke for deferred releasing of a top-level shadow's reference. */
+void shadow_put_top_level(struct domain *d, pagetable_t old);
+
 #else /* !CONFIG_SHADOW_PAGING */
 
 #define shadow_vcpu_teardown(v) ASSERT(is_pv_vcpu(v))
@@ -118,6 +121,11 @@ static inline void shadow_prepare_page_t
 
 static inline void shadow_blow_tables_per_domain(struct domain *d) {}
 
+static inline void shadow_put_top_level(struct domain *d, pagetable_t old)
+{
+    ASSERT_UNREACHABLE();
+}
+
 static inline int shadow_domctl(struct domain *d,
                                 struct xen_domctl_shadow_op *sc,
                                 XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)