[xen staging-4.14] x86/shadow: account for log-dirty mode when pre-allocating

[patchbot@xxxxxxx]

commit 254663bec2bcae8b0a658f3db7a4dfb5ab6a0c83
Author:     Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Tue Mar 21 12:00:14 2023 +0000
Commit:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CommitDate: Tue Mar 21 12:07:44 2023 +0000

    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@xxxxxxxx>
    Reviewed-by: Tim Deegan <tim@xxxxxxx>
    (cherry picked from commit 91767a71061035ae42be93de495cd976f863a41a)
---
 xen/arch/x86/mm/paging.c         |  1 +
 xen/arch/x86/mm/shadow/common.c  | 12 +++++++++++-
 xen/arch/x86/mm/shadow/private.h |  1 +
 xen/include/asm-x86/paging.h     |  4 ++++
 4 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/xen/arch/x86/mm/paging.c b/xen/arch/x86/mm/paging.c
index 7662db1ad4..75573df9ab 100644
--- 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 e803ac7866..96d77fec87 100644
--- 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 e2100f0f34..25803b7e07 100644
--- 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 2ca6325c5f..2c2709b9d3 100644
--- 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;
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.14