mm: Move pte/pmd_mkwrite() callers with no VMA to _novma()

The x86 Shadow stack feature includes a new type of memory called shadow
stack. This shadow stack memory has some unusual properties, which requires
some core mm changes to function properly.

One of these unusual properties is that shadow stack memory is writable,
but only in limited ways. These limits are applied via a specific PTE
bit combination. Nevertheless, the memory is writable, and core mm code
will need to apply the writable permissions in the typical paths that
call pte_mkwrite(). Future patches will make pte_mkwrite() take a VMA, so
that the x86 implementation of it can know whether to create regular
writable or shadow stack mappings.

But there are a couple of challenges to this. Modifying the signatures of
each arch pte_mkwrite() implementation would be error prone because some
are generated with macros and would need to be re-implemented. Also, some
pte_mkwrite() callers operate on kernel memory without a VMA.

So this can be done in a three step process. First pte_mkwrite() can be
renamed to pte_mkwrite_novma() in each arch, with a generic pte_mkwrite()
added that just calls pte_mkwrite_novma(). Next callers without a VMA can
be moved to pte_mkwrite_novma(). And lastly, pte_mkwrite() and all callers
can be changed to take/pass a VMA.

Earlier work did the first step, so next move the callers that don't have
a VMA to pte_mkwrite_novma(). Also do the same for pmd_mkwrite().  This
will be ok for the shadow stack feature, as these callers are on kernel
memory which will not need to be made shadow stack, and the other
architectures only currently support one type of memory in pte_mkwrite()

Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/all/20230613001108.3040476-3-rick.p.edgecombe%40intel.com

diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index 4ea2eefbc053f673ca1575cbf50cf6b61139319b..a01493f3a06f0ab34a5639ef91943255403afe7f 100644 (file)
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -40,7 +40,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
                 * read only (code, rodata). Clear the RDONLY bit from
                 * the temporary mappings we use during restore.
                 */
-               set_pte(dst_ptep, pte_mkwrite(pte));
+               set_pte(dst_ptep, pte_mkwrite_novma(pte));
        } else if (debug_pagealloc_enabled() && !pte_none(pte)) {
                /*
                 * debug_pagealloc will removed the PTE_VALID bit if
@@ -53,7 +53,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
                 */
                BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-               set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
+               set_pte(dst_ptep, pte_mkpresent(pte_mkwrite_novma(pte)));
        }
 }
 

diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index ca5a418c58a8c87e9671c1869b0abec7b5b26c19..e5ec76271b160e4b398df9fc4918a6b7ea02b31b 100644 (file)
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -98,7 +98,7 @@ static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end,
                if (flags & SET_MEMORY_RO)
                        new = pte_wrprotect(new);
                else if (flags & SET_MEMORY_RW)
-                       new = pte_mkwrite(pte_mkdirty(new));
+                       new = pte_mkwrite_novma(pte_mkdirty(new));
                if (flags & SET_MEMORY_NX)
                        new = set_pte_bit(new, __pgprot(_PAGE_NOEXEC));
                else if (flags & SET_MEMORY_X)
@@ -156,7 +156,7 @@ static void modify_pmd_page(pmd_t *pmdp, unsigned long addr,
        if (flags & SET_MEMORY_RO)
                new = pmd_wrprotect(new);
        else if (flags & SET_MEMORY_RW)
-               new = pmd_mkwrite(pmd_mkdirty(new));
+               new = pmd_mkwrite_novma(pmd_mkdirty(new));
        if (flags & SET_MEMORY_NX)
                new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC));
        else if (flags & SET_MEMORY_X)

diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index e0a975165de7869c7ee00aca011c6104f1465334..ccf3d308c874e26bb00347883bbdebe115f97bd2 100644 (file)
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -166,7 +166,7 @@ void make_lowmem_page_readwrite(void *vaddr)
        if (pte == NULL)
                return;         /* vaddr missing */
 
-       ptev = pte_mkwrite(*pte);
+       ptev = pte_mkwrite_novma(*pte);
 
        if (HYPERVISOR_update_va_mapping(address, ptev, 0))
                BUG();