[PATCH v4 3/4] xen/riscv: fix A/D bits in Xen's page-table mappings

[Baptiste Le Duc <baptiste.le-duc@xxxxxxxxxx>]

Xen does not handle page faults caused by clear A/D bits, so it presets
them when creating PTEs. pt_update_entry() does so, but three places build
leaf PTEs directly without going through it: setup_initial_mapping() (the
boot page tables), check_pgtbl_mode_support() (the temporary root entry
used to probe SATP mode support) and arch_pmap_map() (the fixmap).

Without Svadu, all three fault on first access. For
check_pgtbl_mode_support(), the fault is raised by the instruction fetch
right after the SATP write, before any trap handler is set.

Add PTE_ACCESSED and PTE_DIRTY to PAGE_HYPERVISOR_RO, and build
PAGE_HYPERVISOR_RW and PAGE_HYPERVISOR_RX on top of it. PTE_DIRTY is set in
all cases for consistency with pt_update_entry() which sets it at runtime.

This fixes arch_pmap_map() for free, since it already builds its PTE from
PAGE_HYPERVISOR_RW. Switch setup_initial_mapping() to use these macros for
its default, text and rodata permissions, and check_pgtbl_mode_support() to
use PAGE_HYPERVISOR_RX for its temporary root entry. The latter drops
PTE_WRITABLE, going from RWX to RX, but this is harmless, as that entry
only has to make the current instruction stream fetchable between the two
CSR_SATP writes, and nothing writes through it.

Drop the now-redundant PTE_LEAF_DEFAULT, since converting the last
open-coded site above leaves it with no user outside page.h itself.

pte_is_table() and pte_is_mapping() both assert that a PTE doesn't use one
of the two reserved encodings, (V=1, W=1, R=0) and (V=1, X=1, W=1, R=0), by
masking it with PAGE_HYPERVISOR_RW. Now that PAGE_HYPERVISOR_RW also
carries A and D, a reserved PTE with A or D set would no longer be caught.
Mask with the V, R and W bits explicitly instead, and factor the check out
into pte_has_reserved_rwx().

Fixes: e66003e7be19 ("xen/riscv: introduce setup_initial_pages")
Assisted-by: Claude:claude-opus-5
Signed-off-by: Baptiste Le Duc <baptiste.le-duc@xxxxxxxxxx>
---
Changes since v3:
- rebase patch 2/6 which modified wrong indentation.
- change commit message to address review comments.
---
Changes since v2:
- add fixes commit ref.
- add A/D bits to PAGE_HYPERVISOR_RO and derive PAGE_HYPERVISOR_RW/RX
  from it for consistency with runtime.
- introduce pte_is_reserved() to factor out the reserved-encoding assert
  shared by pte_is_table() and pte_is_mapping().
- reword commit title
---
Changes since v1:
- change commit title
- mention in patch message that arch_pmap_map() is fixed too, via the
  PAGE_HYPERVISOR_RW change, not just setup_initial_mapping().
- convert check_pgtbl_mode_support()'s temporary root entry to
  PAGE_HYPERVISOR_RX, as it's harmless.
- drop PTE_LEAF_DEFAULT entirely instead of keeping it, now that no site
  open-codes it anymore.
- drop the pte_is_table() comment line that referenced PAGE_HYPERVISOR_RW,
  now stale.
---
 xen/arch/riscv/include/asm/page.h | 33 +++++++++++++++++----------------
 xen/arch/riscv/mm.c               |  8 ++++----
 2 files changed, 21 insertions(+), 20 deletions(-)

diff --git a/xen/arch/riscv/include/asm/page.h 
b/xen/arch/riscv/include/asm/page.h
index b465a90325..8a3e3e1e66 100644
--- a/xen/arch/riscv/include/asm/page.h
+++ b/xen/arch/riscv/include/asm/page.h
@@ -46,12 +46,12 @@
 #define PTE_PBMT_NOCACHE            BIT(61, UL)
 #define PTE_PBMT_IO                 BIT(62, UL)
 
-#define PTE_LEAF_DEFAULT            (PTE_VALID | PTE_READABLE | PTE_WRITABLE)
 #define PTE_TABLE                   (PTE_VALID)
 
-#define PAGE_HYPERVISOR_RO          (PTE_VALID | PTE_READABLE)
-#define PAGE_HYPERVISOR_RW          (PTE_VALID | PTE_READABLE | PTE_WRITABLE)
-#define PAGE_HYPERVISOR_RX          (PTE_VALID | PTE_READABLE | PTE_EXECUTABLE)
+#define PAGE_HYPERVISOR_RO          (PTE_VALID | PTE_READABLE | \
+                                     PTE_ACCESSED | PTE_DIRTY)
+#define PAGE_HYPERVISOR_RW          (PAGE_HYPERVISOR_RO | PTE_WRITABLE)
+#define PAGE_HYPERVISOR_RX          (PAGE_HYPERVISOR_RO | PTE_EXECUTABLE)
 
 #define PAGE_HYPERVISOR             PAGE_HYPERVISOR_RW
 /*
@@ -161,31 +161,32 @@ static inline bool pte_is_valid(pte_t p)
  *      X W R Meaning
  *      0 0 0 Pointer to next level of page table.
  *      0 0 1 Read-only page.
- *      0 1 0 Reserved for future use.
+ *      0 1 0 Reserved for future use. [1]
  *      0 1 1 Read-write page.
  *      1 0 0 Execute-only page.
  *      1 0 1 Read-execute page.
- *      1 1 0 Reserved for future use.
+ *      1 1 0 Reserved for future use. [2]
  *      1 1 1 Read-write-execute page.
+ *
+ *   So if V=1 and W=1 then R also needs to be 1 as R = 0 is reserved for
+ *   future use ([1], [2]).
  */
+static inline bool pte_has_reserved_rwx(pte_t p)
+{
+    return (p.pte & (PTE_VALID | PTE_READABLE | PTE_WRITABLE)) ==
+           (PTE_VALID | PTE_WRITABLE);
+}
+
 static inline bool pte_is_table(pte_t p)
 {
-    /*
-     * According to the spec if V=1 and W=1 then R also needs to be 1 as
-     * R = 0 is reserved for future use ( look at the Table 4.5 ) so check
-     * in ASSERT that if (V==1 && W==1) then R isn't 0.
-     *
-     * PAGE_HYPERVISOR_RW contains PTE_VALID too.
-     */
-    ASSERT(((p.pte & PAGE_HYPERVISOR_RW) != (PTE_VALID | PTE_WRITABLE)));
+    ASSERT(!pte_has_reserved_rwx(p));
 
     return ((p.pte & (PTE_VALID | PTE_ACCESS_MASK)) == PTE_VALID);
 }
 
 static inline bool pte_is_mapping(pte_t p)
 {
-    /* See pte_is_table() */
-    ASSERT(((p.pte & PAGE_HYPERVISOR_RW) != (PTE_VALID | PTE_WRITABLE)));
+    ASSERT(!pte_has_reserved_rwx(p));
 
     return (p.pte & PTE_VALID) && (p.pte & PTE_ACCESS_MASK);
 }
diff --git a/xen/arch/riscv/mm.c b/xen/arch/riscv/mm.c
index a9bce48f4a..6f7dcd10b2 100644
--- a/xen/arch/riscv/mm.c
+++ b/xen/arch/riscv/mm.c
@@ -140,7 +140,7 @@ static void __init setup_initial_mapping(struct mmu_desc 
*mmu_desc,
         case 1: /* Level 0 */
             {
                 unsigned long paddr = (page_addr - map_start) + pa_start;
-                unsigned int pte_flags = PTE_LEAF_DEFAULT;
+                unsigned int pte_flags = PAGE_HYPERVISOR_RW;
                 unsigned long addr = is_identity_mapping
                                      ? page_addr : virt_to_maddr(page_addr);
                 pte_t pte_to_be_written;
@@ -148,10 +148,10 @@ static void __init setup_initial_mapping(struct mmu_desc 
*mmu_desc,
                 index = pt_index(0, page_addr);
 
                 if ( is_kernel_text(addr) || is_kernel_inittext(addr) )
-                    pte_flags = PTE_EXECUTABLE | PTE_READABLE | PTE_VALID;
+                    pte_flags = PAGE_HYPERVISOR_RX;
 
                 if ( is_kernel_rodata(addr) )
-                    pte_flags = PTE_READABLE | PTE_VALID;
+                    pte_flags = PAGE_HYPERVISOR_RO;
 
                 pte_to_be_written = paddr_to_pte(paddr, pte_flags);
 
@@ -196,7 +196,7 @@ static bool __init check_pgtbl_mode_support(struct mmu_desc 
*mmu_desc,
 
     index = pt_index(page_table_level, aligned_load_start);
     stage1_pgtbl_root[index] = paddr_to_pte(aligned_load_start,
-                                            PTE_LEAF_DEFAULT | PTE_EXECUTABLE);
+                                            PAGE_HYPERVISOR_RX);
 
     sfence_vma();
     csr_write(CSR_SATP,

-- 
2.55.0