x86/shadow: account for log-dirty mode when pre-allocating

Pre-allocation is intended to ensure that in the course of constructing
or updating shadows there won't be any risk of just made shadows or
shadows being acted upon can disappear under our feet. The amount of
pages pre-allocated then, however, needs to account for all possible
subsequent allocations. While the use in sh_page_fault() accounts for
all shadows which may need making, so far it didn't account for
allocations coming from log-dirty tracking (which piggybacks onto the
P2M allocation functions).

Since shadow_prealloc() takes a count of shadows (or other data
structures) rather than a count of pages, putting the adjustment at the
call site of this function won't work very well: We simply can't express
the correct count that way in all cases. Instead take care of this in
the function itself, by "snooping" for L1 type requests. (While not
applicable right now, future new request sites of L1 tables would then
also be covered right away.)

It is relevant to note here that pre-allocations like the one done from
shadow_alloc_p2m_page() are benign when they fall in the "scope" of an
earlier pre-alloc which already included that count: The inner call will
simply find enough pages available then; it'll bail right away.

This is CVE-2022-42332 / XSA-427.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
(cherry picked from commit 91767a71061035ae42be93de495cd976f863a41a)

diff --git a/xen/arch/x86/mm/paging.c b/xen/arch/x86/mm/paging.c
index 7662db1ad4ebc4e2d31fa44d544adc78aa1b8c8f..75573df9abad9db25faa929d1fb0b387d9f8b4d0 100644 (file)
--- a/xen/arch/x86/mm/paging.c
+++ b/xen/arch/x86/mm/paging.c
@@ -278,6 +278,7 @@ void paging_mark_pfn_dirty(struct domain *d, pfn_t pfn)
     if ( unlikely(!VALID_M2P(pfn_x(pfn))) )
         return;
 
+    BUILD_BUG_ON(paging_logdirty_levels() != 4);
     i1 = L1_LOGDIRTY_IDX(pfn);
     i2 = L2_LOGDIRTY_IDX(pfn);
     i3 = L3_LOGDIRTY_IDX(pfn);

diff --git a/xen/arch/x86/mm/shadow/common.c b/xen/arch/x86/mm/shadow/common.c
index e803ac786622ca192dbf2a781c6c38752af71b5c..96d77fec87a8198f913a67e7505dc070d746e7fe 100644 (file)
--- a/xen/arch/x86/mm/shadow/common.c
+++ b/xen/arch/x86/mm/shadow/common.c
@@ -1012,7 +1012,17 @@ bool shadow_prealloc(struct domain *d, unsigned int type, unsigned int count)
     if ( unlikely(d->is_dying) )
        return false;
 
-    ret = _shadow_prealloc(d, shadow_size(type) * count);
+    count *= shadow_size(type);
+    /*
+     * Log-dirty handling may result in allocations when populating its
+     * tracking structures.  Tie this to the caller requesting space for L1
+     * shadows.
+     */
+    if ( paging_mode_log_dirty(d) &&
+         ((SHF_L1_ANY | SHF_FL1_ANY) & (1u << type)) )
+        count += paging_logdirty_levels();
+
+    ret = _shadow_prealloc(d, count);
     if ( !ret && (!d->is_shutting_down || d->shutdown_code != SHUTDOWN_crash) )
         /*
          * Failing to allocate memory required for shadow usage can only result in

diff --git a/xen/arch/x86/mm/shadow/private.h b/xen/arch/x86/mm/shadow/private.h
index e2100f0f34405f6bca2aafe881fe821ee738563a..25803b7e0742d36c94bb16696f0a8667464c70b4 100644 (file)
--- a/xen/arch/x86/mm/shadow/private.h
+++ b/xen/arch/x86/mm/shadow/private.h
@@ -269,6 +269,7 @@ static inline void sh_terminate_list(struct page_list_head *tmp_list)
 #define SHF_64  (SHF_L1_64|SHF_FL1_64|SHF_L2_64|SHF_L2H_64|SHF_L3_64|SHF_L4_64)
 
 #define SHF_L1_ANY  (SHF_L1_32|SHF_L1_PAE|SHF_L1_64)
+#define SHF_FL1_ANY (SHF_FL1_32|SHF_FL1_PAE|SHF_FL1_64)
 
 #if (SHADOW_OPTIMIZATIONS & SHOPT_OUT_OF_SYNC)
 /* Marks a guest L1 page table which is shadowed but not write-protected.

diff --git a/xen/include/asm-x86/paging.h b/xen/include/asm-x86/paging.h
index 2ca6325c5f773b585689e39630d1cb3f13eff658..2c2709b9d38e10407d722c4fd73225e10ac5344e 100644 (file)
--- a/xen/include/asm-x86/paging.h
+++ b/xen/include/asm-x86/paging.h
@@ -190,6 +190,10 @@ int paging_mfn_is_dirty(struct domain *d, mfn_t gmfn);
 #define L4_LOGDIRTY_IDX(pfn) ((pfn_x(pfn) >> (PAGE_SHIFT + 3 + PAGETABLE_ORDER * 2)) & \
                               (LOGDIRTY_NODE_ENTRIES-1))
 
+#define paging_logdirty_levels() \
+    (DIV_ROUND_UP(PADDR_BITS - PAGE_SHIFT - (PAGE_SHIFT + 3), \
+                  PAGE_SHIFT - ilog2(sizeof(mfn_t))) + 1)
+
 /* VRAM dirty tracking support */
 struct sh_dirty_vram {
     unsigned long begin_pfn;