x86/mm/encrypt: Simplify sme_populate_pgd() and sme_populate_pgd_large()

sme_populate_pgd() and sme_populate_pgd_large() operate on the identity
mapping, which means they want virtual addresses to be equal to physical
one, without PAGE_OFFSET shift.

We also need to avoid paravirtualization call there.

Getting this done is tricky. We cannot use usual page table helpers.
It forces us to open-code a lot of things. It makes code ugly and hard
to modify.

We can get it work with the page table helpers, but it requires few
preprocessor tricks.

  - Define __pa() and __va() to be compatible with identity mapping.

  - Undef CONFIG_PARAVIRT and CONFIG_PARAVIRT_SPINLOCKS before including
    any file. This way we can avoid paravirtualization calls.

Now we can user normal page table helpers just fine.

Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20180131135404.40692-3-kirill.shutemov@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index a28978a37bfa54ed4e20008055ca9b02f2e7cdda..4b6a2e3098c5a5382384b13e924028f9c9df792e 100644 (file)
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -12,6 +12,24 @@
 
 #define DISABLE_BRANCH_PROFILING
 
+/*
+ * Since we're dealing with identity mappings, physical and virtual
+ * addresses are the same, so override these defines which are ultimately
+ * used by the headers in misc.h.
+ */
+#define __pa(x)  ((unsigned long)(x))
+#define __va(x)  ((void *)((unsigned long)(x)))
+
+/*
+ * Special hack: we have to be careful, because no indirections are
+ * allowed here, and paravirt_ops is a kind of one. As it will only run in
+ * baremetal anyway, we just keep it from happening. (This list needs to
+ * be extended when new paravirt and debugging variants are added.)
+ */
+#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_SPINLOCKS
+
+#include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/mem_encrypt.h>
 
@@ -73,116 +91,83 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
        memset(pgd_p, 0, pgd_size);
 }
 
-static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
+static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
 {
-       pgd_t *pgd_p;
-       p4d_t *p4d_p;
-       pud_t *pud_p;
-       pmd_t *pmd_p;
-
-       pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
-       if (native_pgd_val(*pgd_p)) {
-               if (IS_ENABLED(CONFIG_X86_5LEVEL))
-                       p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
-               else
-                       pud_p = (pud_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
-       } else {
-               pgd_t pgd;
-
-               if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-                       p4d_p = ppd->pgtable_area;
-                       memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
-                       ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
-
-                       pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
-               } else {
-                       pud_p = ppd->pgtable_area;
-                       memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
-                       ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
-
-                       pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
-               }
-               native_set_pgd(pgd_p, pgd);
+       pgd_t *pgd;
+       p4d_t *p4d;
+       pud_t *pud;
+       pmd_t *pmd;
+
+       pgd = ppd->pgd + pgd_index(ppd->vaddr);
+       if (pgd_none(*pgd)) {
+               p4d = ppd->pgtable_area;
+               memset(p4d, 0, sizeof(*p4d) * PTRS_PER_P4D);
+               ppd->pgtable_area += sizeof(*p4d) * PTRS_PER_P4D;
+               set_pgd(pgd, __pgd(PGD_FLAGS | __pa(p4d)));
        }
 
-       if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-               p4d_p += p4d_index(ppd->vaddr);
-               if (native_p4d_val(*p4d_p)) {
-                       pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
-               } else {
-                       p4d_t p4d;
-
-                       pud_p = ppd->pgtable_area;
-                       memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
-                       ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
-
-                       p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
-                       native_set_p4d(p4d_p, p4d);
-               }
+       p4d = p4d_offset(pgd, ppd->vaddr);
+       if (p4d_none(*p4d)) {
+               pud = ppd->pgtable_area;
+               memset(pud, 0, sizeof(*pud) * PTRS_PER_PUD);
+               ppd->pgtable_area += sizeof(*pud) * PTRS_PER_PUD;
+               set_p4d(p4d, __p4d(P4D_FLAGS | __pa(pud)));
        }
 
-       pud_p += pud_index(ppd->vaddr);
-       if (native_pud_val(*pud_p)) {
-               if (native_pud_val(*pud_p) & _PAGE_PSE)
-                       return NULL;
-
-               pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
-       } else {
-               pud_t pud;
-
-               pmd_p = ppd->pgtable_area;
-               memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
-               ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
-
-               pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
-               native_set_pud(pud_p, pud);
+       pud = pud_offset(p4d, ppd->vaddr);
+       if (pud_none(*pud)) {
+               pmd = ppd->pgtable_area;
+               memset(pmd, 0, sizeof(*pmd) * PTRS_PER_PMD);
+               ppd->pgtable_area += sizeof(*pmd) * PTRS_PER_PMD;
+               set_pud(pud, __pud(PUD_FLAGS | __pa(pmd)));
        }
 
-       return pmd_p;
+       if (pud_large(*pud))
+               return NULL;
+
+       return pud;
 }
 
 static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
 {
-       pmd_t *pmd_p;
+       pud_t *pud;
+       pmd_t *pmd;
 
-       pmd_p = sme_prepare_pgd(ppd);
-       if (!pmd_p)
+       pud = sme_prepare_pgd(ppd);
+       if (!pud)
                return;
 
-       pmd_p += pmd_index(ppd->vaddr);
-       if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
-               native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
+       pmd = pmd_offset(pud, ppd->vaddr);
+       if (pmd_large(*pmd))
+               return;
+
+       set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags));
 }
 
 static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 {
-       pmd_t *pmd_p;
-       pte_t *pte_p;
+       pud_t *pud;
+       pmd_t *pmd;
+       pte_t *pte;
 
-       pmd_p = sme_prepare_pgd(ppd);
-       if (!pmd_p)
+       pud = sme_prepare_pgd(ppd);
+       if (!pud)
                return;
 
-       pmd_p += pmd_index(ppd->vaddr);
-       if (native_pmd_val(*pmd_p)) {
-               if (native_pmd_val(*pmd_p) & _PAGE_PSE)
-                       return;
-
-               pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
-       } else {
-               pmd_t pmd;
-
-               pte_p = ppd->pgtable_area;
-               memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
-               ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;
-
-               pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
-               native_set_pmd(pmd_p, pmd);
+       pmd = pmd_offset(pud, ppd->vaddr);
+       if (pmd_none(*pmd)) {
+               pte = ppd->pgtable_area;
+               memset(pte, 0, sizeof(pte) * PTRS_PER_PTE);
+               ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE;
+               set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
        }
 
-       pte_p += pte_index(ppd->vaddr);
-       if (!native_pte_val(*pte_p))
-               native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
+       if (pmd_large(*pmd))
+               return;
+
+       pte = pte_offset_map(pmd, ppd->vaddr);
+       if (pte_none(*pte))
+               set_pte(pte, __pte(ppd->paddr | ppd->pte_flags));
 }
 
 static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)