|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen master] x86/shadow: defer releasing of PV's top-level shadow reference
commit fb0ff49fe9f784bfee0370c2a3c5f20e39d7a1cb
Author: Jan Beulich <JBeulich@xxxxxxxx>
AuthorDate: Wed Sep 20 10:31:42 2023 +0100
Commit: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CommitDate: Wed Sep 20 10:31:42 2023 +0100
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@xxxxxxx>
Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
Reviewed-by: George Dunlap <george.dunlap@xxxxxxxxx>
---
xen/arch/x86/include/asm/mm.h | 2 +-
xen/arch/x86/include/asm/paging.h | 6 ++---
xen/arch/x86/include/asm/shadow.h | 8 ++++++
xen/arch/x86/mm.c | 27 ++++++++++++++-----
xen/arch/x86/mm/hap/hap.c | 6 +++--
xen/arch/x86/mm/shadow/common.c | 55 +++++++++++++++++++++++++--------------
xen/arch/x86/mm/shadow/multi.c | 33 +++++++++++++++--------
xen/arch/x86/mm/shadow/none.c | 4 ++-
xen/arch/x86/mm/shadow/private.h | 14 +++++-----
xen/arch/x86/pv/domain.c | 25 ++++++++++++++++--
10 files changed, 127 insertions(+), 53 deletions(-)
diff --git a/xen/arch/x86/include/asm/mm.h b/xen/arch/x86/include/asm/mm.h
index 8f6681429d..05dfe35502 100644
--- a/xen/arch/x86/include/asm/mm.h
+++ b/xen/arch/x86/include/asm/mm.h
@@ -556,7 +556,7 @@ 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);
diff --git a/xen/arch/x86/include/asm/paging.h
b/xen/arch/x86/include/asm/paging.h
index 403243bfbd..8fad4cfc18 100644
--- a/xen/arch/x86/include/asm/paging.h
+++ b/xen/arch/x86/include/asm/paging.h
@@ -118,7 +118,7 @@ struct paging_mode {
paddr_t ga, uint32_t *pfec,
unsigned int *page_order);
#endif
- void (*update_cr3 )(struct vcpu *v, int do_locking,
+ pagetable_t (*update_cr3 )(struct vcpu *v, bool do_locking,
bool noflush);
unsigned int guest_levels;
@@ -294,9 +294,9 @@ static inline bool paging_flush_tlb(const unsigned long
*vcpu_bitmap)
/* 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.
diff --git a/xen/arch/x86/include/asm/shadow.h
b/xen/arch/x86/include/asm/shadow.h
index 20df34d0a8..9a8d1b8353 100644
--- a/xen/arch/x86/include/asm/shadow.h
+++ b/xen/arch/x86/include/asm/shadow.h
@@ -94,6 +94,9 @@ void shadow_blow_tables_per_domain(struct domain *d);
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))
@@ -114,6 +117,11 @@ static inline void shadow_prepare_page_type_change(struct
domain *d,
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)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 28fdf820ef..39544bd9f9 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -549,15 +549,12 @@ 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);
@@ -565,6 +562,8 @@ 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)
@@ -3269,6 +3268,7 @@ 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) )
{
@@ -3336,9 +3336,22 @@ 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) )
{
diff --git a/xen/arch/x86/mm/hap/hap.c b/xen/arch/x86/mm/hap/hap.c
index d05f1b7a95..e30f543d2c 100644
--- a/xen/arch/x86/mm/hap/hap.c
+++ b/xen/arch/x86/mm/hap/hap.c
@@ -707,11 +707,13 @@ static bool cf_check hap_invlpg(struct vcpu *v, unsigned
long linear)
return 1;
}
-static void cf_check hap_update_cr3(
- struct vcpu *v, int do_locking, bool noflush)
+static pagetable_t cf_check 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();
}
static bool flush_vcpu(const struct vcpu *v, const unsigned long *vcpu_bitmap)
diff --git a/xen/arch/x86/mm/shadow/common.c b/xen/arch/x86/mm/shadow/common.c
index a0ae6adb4f..8211e77cc7 100644
--- a/xen/arch/x86/mm/shadow/common.c
+++ b/xen/arch/x86/mm/shadow/common.c
@@ -2526,13 +2526,13 @@ static void cf_check shadow_update_paging_modes(struct
vcpu *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;
@@ -2589,20 +2589,37 @@ void sh_set_toplevel_shadow(struct vcpu *v,
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);
}
/**************************************************************************/
diff --git a/xen/arch/x86/mm/shadow/multi.c b/xen/arch/x86/mm/shadow/multi.c
index cf74fdf5dd..447512870d 100644
--- a/xen/arch/x86/mm/shadow/multi.c
+++ b/xen/arch/x86/mm/shadow/multi.c
@@ -3156,7 +3156,8 @@ sh_update_linear_entries(struct vcpu *v)
sh_flush_local(d);
}
-static void cf_check sh_update_cr3(struct vcpu *v, int do_locking, bool
noflush)
+static pagetable_t cf_check 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).
@@ -3170,6 +3171,7 @@ static void cf_check sh_update_cr3(struct vcpu *v, int
do_locking, bool noflush)
{
struct domain *d = v->domain;
mfn_t gmfn;
+ pagetable_t old_entry = pagetable_null();
#if GUEST_PAGING_LEVELS == 3
const guest_l3e_t *gl3e;
unsigned int i, guest_idx;
@@ -3179,7 +3181,7 @@ static void cf_check sh_update_cr3(struct vcpu *v, int
do_locking, bool noflush)
if ( !is_hvm_domain(d) && !v->is_initialised )
{
ASSERT(v->arch.cr3 == 0);
- return;
+ return old_entry;
}
if ( do_locking ) paging_lock(v->domain);
@@ -3252,11 +3254,12 @@ static void cf_check sh_update_cr3(struct vcpu *v, int
do_locking, bool noflush)
#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) )
{
@@ -3300,24 +3303,30 @@ static void cf_check sh_update_cr3(struct vcpu *v, int
do_locking, bool noflush)
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, SH_type_l2_shadow,
- sh_make_shadow);
+ old_entry = sh_set_toplevel_shadow(v, i, gl2mfn,
+ 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
@@ -3405,6 +3414,8 @@ static void cf_check sh_update_cr3(struct vcpu *v, int
do_locking, bool noflush)
/* Release the lock, if we took it (otherwise it's the caller's problem) */
if ( do_locking ) paging_unlock(v->domain);
+
+ return old_entry;
}
diff --git a/xen/arch/x86/mm/shadow/none.c b/xen/arch/x86/mm/shadow/none.c
index c462639eab..9c4be4562f 100644
--- a/xen/arch/x86/mm/shadow/none.c
+++ b/xen/arch/x86/mm/shadow/none.c
@@ -55,9 +55,11 @@ static unsigned long cf_check _gva_to_gfn(
}
#endif
-static void cf_check _update_cr3(struct vcpu *v, int do_locking, bool noflush)
+static pagetable_t cf_check _update_cr3(struct vcpu *v, bool do_locking,
+ bool noflush)
{
ASSERT_UNREACHABLE();
+ return pagetable_null();
}
static const struct paging_mode sh_paging_none = {
diff --git a/xen/arch/x86/mm/shadow/private.h b/xen/arch/x86/mm/shadow/private.h
index a0f275251f..a5fc3a7676 100644
--- a/xen/arch/x86/mm/shadow/private.h
+++ b/xen/arch/x86/mm/shadow/private.h
@@ -383,13 +383,13 @@ 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);
diff --git a/xen/arch/x86/pv/domain.c b/xen/arch/x86/pv/domain.c
index 5c92812dc6..2a445bb17b 100644
--- a/xen/arch/x86/pv/domain.c
+++ b/xen/arch/x86/pv/domain.c
@@ -424,10 +424,13 @@ 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.
@@ -436,13 +439,31 @@ static void _toggle_guest_pt(struct vcpu *v)
* 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) )
--
generated by git-patchbot for /home/xen/git/xen.git#master
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |