ArmPkg/ArmMmuLib AARCH64: get rid of needless TLB invalidation

Currently, we always invalidate the TLBs entirely after making
any modification to the page tables. Now that we have introduced
strict memory permissions in quite a number of places, such
modifications occur much more often, and it is better for performance
to flush only those TLB entries that are actually affected by
the changes.

At the same time, relax some system wide data synchronization barriers
to non-shared. When running in UEFI, we don't share virtual address
translations with other masters, unless we are running under virt, but
in that case, the host will upgrade them as appropriate (by setting
an override at EL2)

Contributed-under: TianoCore Contribution Agreement 1.1
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org>

ArmPkg/Include/Library/ArmMmuLib.h

@@ -59,7 +59,8 @@ VOID
 EFIAPI
 ArmReplaceLiveTranslationEntry (
   IN  UINT64  *Entry,
-  IN  UINT64  Value
+  IN  UINT64  Value,
+  IN  UINT64  RegionStart
   );
 
 EFI_STATUS

ArmPkg/Library/ArmLib/AArch64/ArmLibSupport.S

@@ -124,15 +124,15 @@ ASM_FUNC(ArmSetMAIR)
 //  IN VOID  *MVA                    // X1
 //  );
 ASM_FUNC(ArmUpdateTranslationTableEntry)
-   dc      civac, x0             // Clean and invalidate data line
-   dsb     sy
+   dsb     nshst
+   lsr     x1, x1, #12
    EL1_OR_EL2_OR_EL3(x0)
 1: tlbi    vaae1, x1             // TLB Invalidate VA , EL1
    b       4f
 2: tlbi    vae2, x1              // TLB Invalidate VA , EL2
    b       4f
 3: tlbi    vae3, x1              // TLB Invalidate VA , EL3
-4: dsb     sy
+4: dsb     nsh
    isb
    ret
 

ArmPkg/Library/ArmMmuLib/AArch64/ArmMmuLibCore.c

@@ -129,13 +129,14 @@ STATIC
 VOID
 ReplaceLiveEntry (
   IN  UINT64  *Entry,
-  IN  UINT64  Value
+  IN  UINT64  Value,
+  IN  UINT64  RegionStart
   )
 {
   if (!ArmMmuEnabled ()) {
     *Entry = Value;
   } else {
-    ArmReplaceLiveTranslationEntry (Entry, Value);
+    ArmReplaceLiveTranslationEntry (Entry, Value, RegionStart);
   }
 }
 
@@ -296,7 +297,8 @@ GetBlockEntryListFromAddress (
 
         // Fill the BlockEntry with the new TranslationTable
         ReplaceLiveEntry (BlockEntry,
-          ((UINTN)TranslationTable & TT_ADDRESS_MASK_DESCRIPTION_TABLE) | TableAttributes | TT_TYPE_TABLE_ENTRY);
+          (UINTN)TranslationTable | TableAttributes | TT_TYPE_TABLE_ENTRY,
+          RegionStart);
       }
     } else {
       if (IndexLevel != PageLevel) {
@@ -375,6 +377,8 @@ UpdateRegionMapping (
       *BlockEntry &= BlockEntryMask;
       *BlockEntry |= (RegionStart & TT_ADDRESS_MASK_BLOCK_ENTRY) | Attributes | Type;
 
+      ArmUpdateTranslationTableEntry (BlockEntry, (VOID *)RegionStart);
+
       // Go to the next BlockEntry
       RegionStart += BlockEntrySize;
       RegionLength -= BlockEntrySize;
@@ -487,9 +491,6 @@ ArmSetMemoryAttributes (
     return Status;
   }
 
-  // Invalidate all TLB entries so changes are synced
-  ArmInvalidateTlb ();
-
   return EFI_SUCCESS;
 }
 
@@ -512,9 +513,6 @@ SetMemoryRegionAttribute (
     return Status;
   }
 
-  // Invalidate all TLB entries so changes are synced
-  ArmInvalidateTlb ();
-
   return EFI_SUCCESS;
 }
 

ArmPkg/Library/ArmMmuLib/AArch64/ArmMmuLibReplaceEntry.S

@@ -32,13 +32,14 @@
   dmb   sy
   dc    ivac, x0
 
-  // flush the TLBs
+  // flush translations for the target address from the TLBs
+  lsr   x2, x2, #12
   .if   \el == 1
-  tlbi  vmalle1
+  tlbi  vaae1, x2
   .else
-  tlbi  alle\el
+  tlbi  vae\el, x2
   .endif
-  dsb   sy
+  dsb   nsh
 
   // re-enable the MMU
   msr   sctlr_el\el, x8
@@ -48,19 +49,20 @@
 //VOID
 //ArmReplaceLiveTranslationEntry (
 //  IN  UINT64  *Entry,
-//  IN  UINT64  Value
+//  IN  UINT64  Value,
+//  IN  UINT64  Address
 //  )
 ASM_FUNC(ArmReplaceLiveTranslationEntry)
 
   // disable interrupts
-  mrs   x2, daif
+  mrs   x4, daif
   msr   daifset, #0xf
   isb
 
   // clean and invalidate first so that we don't clobber
   // adjacent entries that are dirty in the caches
   dc    civac, x0
-  dsb   ish
+  dsb   nsh
 
   EL1_OR_EL2_OR_EL3(x3)
 1:__replace_entry 1
@@ -69,7 +71,7 @@ ASM_FUNC(ArmReplaceLiveTranslationEntry)
   b     4f
 3:__replace_entry 3
 
-4:msr   daif, x2
+4:msr   daif, x4
   ret
 
 ASM_GLOBAL ASM_PFX(ArmReplaceLiveTranslationEntrySize)