xen/arm: mm: Allow other mapping size in xen_pt_update_entry()

At the moment, xen_pt_update_entry() only supports mapping at level 3
(i.e 4KB mapping). While this is fine for most of the runtime helper,
the boot code will require to use superpage mapping.

We don't want to allow superpage mapping by default as some of the
callers may expect small mappings (i.e populate_pt_range()) or even
expect to unmap only a part of a superpage.

To keep the code simple, a new flag _PAGE_BLOCK is introduced to
allow the caller to enable superpage mapping.

As the code doesn't support all the combinations, xen_pt_check_entry()
is extended to take into account the cases we don't support when
using block mapping:
    - Replacing a table with a mapping. This may happen if region was
    first mapped with 4KB mapping and then later on replaced with a 2MB
    (or 1GB mapping).
    - Removing/modifying a table. This may happen if a caller try to
    remove a region with _PAGE_BLOCK set when it was created without it.

Note that the current restriction means that the caller must ensure that
_PAGE_BLOCK is consistently set/cleared across all the updates on a
given virtual region. This ought to be fine with the expected use-cases.

More rework will be necessary if we wanted to remove the restrictions.

Note that nr_mfns is now marked const as it is used for flushing the
TLBs and we don't want it to be modified.

Signed-off-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Hongda Deng <Hongda.Heng@arm.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>

diff --git a/xen/arch/arm/include/asm/page.h b/xen/arch/arm/include/asm/page.h
index c6f9fb0d4e0c4268ebc98b47dd784eb0f4df5a6d..07998df47bac962831d081d6e93e9c9f00ff539a 100644 (file)
--- a/xen/arch/arm/include/asm/page.h
+++ b/xen/arch/arm/include/asm/page.h
@@ -69,6 +69,7 @@
  * [3:4] Permission flags
  * [5]   Page present
  * [6]   Only populate page tables
+ * [7]   Superpage mappings is allowed
  */
 #define PAGE_AI_MASK(x) ((x) & 0x7U)
 
@@ -82,6 +83,9 @@
 #define _PAGE_PRESENT    (1U << 5)
 #define _PAGE_POPULATE   (1U << 6)
 
+#define _PAGE_BLOCK_BIT     7
+#define _PAGE_BLOCK         (1U << _PAGE_BLOCK_BIT)
+
 /*
  * _PAGE_DEVICE and _PAGE_NORMAL are convenience defines. They are not
  * meant to be used outside of this header.

diff --git a/xen/arch/arm/mm.c b/xen/arch/arm/mm.c
index 7b1f2f49060daf5c3eaf80f39e9809990d4a0449..be2ac302d731e162ca1ee05e7eed0ac2b653704b 100644 (file)
--- a/xen/arch/arm/mm.c
+++ b/xen/arch/arm/mm.c
@@ -1078,9 +1078,10 @@ static int xen_pt_next_level(bool read_only, unsigned int level,
 }
 
 /* Sanity check of the entry */
-static bool xen_pt_check_entry(lpae_t entry, mfn_t mfn, unsigned int flags)
+static bool xen_pt_check_entry(lpae_t entry, mfn_t mfn, unsigned int level,
+                               unsigned int flags)
 {
-    /* Sanity check when modifying a page. */
+    /* Sanity check when modifying an entry. */
     if ( (flags & _PAGE_PRESENT) && mfn_eq(mfn, INVALID_MFN) )
     {
         /* We don't allow modifying an invalid entry. */
@@ -1090,6 +1091,13 @@ static bool xen_pt_check_entry(lpae_t entry, mfn_t mfn, unsigned int flags)
             return false;
         }
 
+        /* We don't allow modifying a table entry */
+        if ( !lpae_is_mapping(entry, level) )
+        {
+            mm_printk("Modifying a table entry is not allowed.\n");
+            return false;
+        }
+
         /* We don't allow changing memory attributes. */
         if ( entry.pt.ai != PAGE_AI_MASK(flags) )
         {
@@ -1105,7 +1113,7 @@ static bool xen_pt_check_entry(lpae_t entry, mfn_t mfn, unsigned int flags)
             return false;
         }
     }
-    /* Sanity check when inserting a page */
+    /* Sanity check when inserting a mapping */
     else if ( flags & _PAGE_PRESENT )
     {
         /* We should be here with a valid MFN. */
@@ -1114,18 +1122,28 @@ static bool xen_pt_check_entry(lpae_t entry, mfn_t mfn, unsigned int flags)
         /* We don't allow replacing any valid entry. */
         if ( lpae_is_valid(entry) )
         {
-            mm_printk("Changing MFN for a valid entry is not allowed (%#"PRI_mfn" -> %#"PRI_mfn").\n",
-                      mfn_x(lpae_get_mfn(entry)), mfn_x(mfn));
+            if ( lpae_is_mapping(entry, level) )
+                mm_printk("Changing MFN for a valid entry is not allowed (%#"PRI_mfn" -> %#"PRI_mfn").\n",
+                          mfn_x(lpae_get_mfn(entry)), mfn_x(mfn));
+            else
+                mm_printk("Trying to replace a table with a mapping.\n");
             return false;
         }
     }
-    /* Sanity check when removing a page. */
+    /* Sanity check when removing a mapping. */
     else if ( (flags & (_PAGE_PRESENT|_PAGE_POPULATE)) == 0 )
     {
         /* We should be here with an invalid MFN. */
         ASSERT(mfn_eq(mfn, INVALID_MFN));
 
-        /* We don't allow removing page with contiguous bit set. */
+        /* We don't allow removing a table */
+        if ( lpae_is_table(entry, level) )
+        {
+            mm_printk("Removing a table is not allowed.\n");
+            return false;
+        }
+
+        /* We don't allow removing a mapping with contiguous bit set. */
         if ( entry.pt.contig )
         {
             mm_printk("Removing entry with contiguous bit set is not allowed.\n");
@@ -1143,13 +1161,13 @@ static bool xen_pt_check_entry(lpae_t entry, mfn_t mfn, unsigned int flags)
     return true;
 }
 
+/* Update an entry at the level @target. */
 static int xen_pt_update_entry(mfn_t root, unsigned long virt,
-                               mfn_t mfn, unsigned int flags)
+                               mfn_t mfn, unsigned int target,
+                               unsigned int flags)
 {
     int rc;
     unsigned int level;
-    /* We only support 4KB mapping (i.e level 3) for now */
-    unsigned int target = 3;
     lpae_t *table;
     /*
      * The intermediate page tables are read-only when the MFN is not valid
@@ -1204,7 +1222,7 @@ static int xen_pt_update_entry(mfn_t root, unsigned long virt,
     entry = table + offsets[level];
 
     rc = -EINVAL;
-    if ( !xen_pt_check_entry(*entry, mfn, flags) )
+    if ( !xen_pt_check_entry(*entry, mfn, level, flags) )
         goto out;
 
     /* If we are only populating page-table, then we are done. */
@@ -1222,8 +1240,11 @@ static int xen_pt_update_entry(mfn_t root, unsigned long virt,
         {
             pte = mfn_to_xen_entry(mfn, PAGE_AI_MASK(flags));
 
-            /* Third level entries set pte.pt.table = 1 */
-            pte.pt.table = 1;
+            /*
+             * First and second level pages set pte.pt.table = 0, but
+             * third level entries set pte.pt.table = 1.
+             */
+            pte.pt.table = (level == 3);
         }
         else /* We are updating the permission => Copy the current pte. */
             pte = *entry;
@@ -1243,15 +1264,57 @@ out:
     return rc;
 }
 
+/* Return the level where mapping should be done */
+static int xen_pt_mapping_level(unsigned long vfn, mfn_t mfn, unsigned long nr,
+                                unsigned int flags)
+{
+    unsigned int level;
+    unsigned long mask;
+
+    /*
+      * Don't take into account the MFN when removing mapping (i.e
+      * MFN_INVALID) to calculate the correct target order.
+      *
+      * Per the Arm Arm, `vfn` and `mfn` must be both superpage aligned.
+      * They are or-ed together and then checked against the size of
+      * each level.
+      *
+      * `left` is not included and checked separately to allow
+      * superpage mapping even if it is not properly aligned (the
+      * user may have asked to map 2MB + 4k).
+      */
+     mask = !mfn_eq(mfn, INVALID_MFN) ? mfn_x(mfn) : 0;
+     mask |= vfn;
+
+     /*
+      * Always use level 3 mapping unless the caller request block
+      * mapping.
+      */
+     if ( likely(!(flags & _PAGE_BLOCK)) )
+         level = 3;
+     else if ( !(mask & (BIT(FIRST_ORDER, UL) - 1)) &&
+               (nr >= BIT(FIRST_ORDER, UL)) )
+         level = 1;
+     else if ( !(mask & (BIT(SECOND_ORDER, UL) - 1)) &&
+               (nr >= BIT(SECOND_ORDER, UL)) )
+         level = 2;
+     else
+         level = 3;
+
+     return level;
+}
+
 static DEFINE_SPINLOCK(xen_pt_lock);
 
 static int xen_pt_update(unsigned long virt,
                          mfn_t mfn,
-                         unsigned long nr_mfns,
+                         /* const on purpose as it is used for TLB flush */
+                         const unsigned long nr_mfns,
                          unsigned int flags)
 {
     int rc = 0;
-    unsigned long addr = virt, addr_end = addr + nr_mfns * PAGE_SIZE;
+    unsigned long vfn = virt >> PAGE_SHIFT;
+    unsigned long left = nr_mfns;
 
     /*
      * For arm32, page-tables are different on each CPUs. Yet, they share
@@ -1283,14 +1346,24 @@ static int xen_pt_update(unsigned long virt,
 
     spin_lock(&xen_pt_lock);
 
-    for ( ; addr < addr_end; addr += PAGE_SIZE )
+    while ( left )
     {
-        rc = xen_pt_update_entry(root, addr, mfn, flags);
+        unsigned int order, level;
+
+        level = xen_pt_mapping_level(vfn, mfn, left, flags);
+        order = XEN_PT_LEVEL_ORDER(level);
+
+        ASSERT(left >= BIT(order, UL));
+
+        rc = xen_pt_update_entry(root, vfn << PAGE_SHIFT, mfn, level, flags);
         if ( rc )
             break;
 
+        vfn += 1U << order;
         if ( !mfn_eq(mfn, INVALID_MFN) )
-            mfn = mfn_add(mfn, 1);
+            mfn = mfn_add(mfn, 1U << order);
+
+        left -= (1U << order);
     }
 
     /*