This is included in this RFC to demonstrate how an architecture that
doesn't use ARCH_WANT_GENERAL_HUGETLB can be updated to support HugeTLB
high-granularity mappings: an architecture just needs to implement
hugetlb_walk_to.
Signed-off-by: James Houghton <jthoughton@xxxxxxxxxx>
---
arch/arm64/Kconfig | 1 +
arch/arm64/mm/hugetlbpage.c | 63 +++++++++++++++++++++++++++++++++++++
2 files changed, 64 insertions(+)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1652a9800ebe..74108713a99a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -99,6 +99,7 @@ config ARM64
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+ select ARCH_HAS_SPECIAL_HUGETLB_HGM
select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANTS_NO_INSTR
select ARCH_HAS_UBSAN_SANITIZE_ALL
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index e2a5ec9fdc0d..1901818bed9d 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -281,6 +281,69 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
set_pte(ptep, pte);
}
+int hugetlb_walk_to(struct mm_struct *mm, struct hugetlb_pte *hpte,
+ unsigned long addr, unsigned long sz, bool stop_at_none)
+{
+ pgd_t *pgdp;
+ p4d_t *p4dp;
+ pte_t *ptep;
+
+ if (!hpte->ptep) {
+ pgdp = pgd_offset(mm, addr);
+ p4dp = p4d_offset(pgdp, addr);
+ if (!p4dp)
+ return -ENOMEM;
+ hugetlb_pte_populate(hpte, (pte_t *)p4dp, P4D_SHIFT);
+ }
+
+ while (hugetlb_pte_size(hpte) > sz &&
+ !hugetlb_pte_present_leaf(hpte) &&
+ !(stop_at_none && hugetlb_pte_none(hpte))) {
+ if (hpte->shift == PMD_SHIFT) {
+ unsigned long rounded_addr = sz == CONT_PTE_SIZE
+ ? addr & CONT_PTE_MASK
+ : addr;
+
+ ptep = pte_offset_kernel((pmd_t *)hpte->ptep,
+ rounded_addr);
+ if (!ptep)
+ return -ENOMEM;
+ if (sz == CONT_PTE_SIZE)
+ hpte->shift = CONT_PTE_SHIFT;
+ else
+ hpte->shift = pte_cont(*ptep) ? CONT_PTE_SHIFT
+ : PAGE_SHIFT;
+ hpte->ptep = ptep;
+ } else if (hpte->shift == PUD_SHIFT) {
+ pud_t *pudp = (pud_t *)hpte->ptep;
+
+ ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
+
+ if (!ptep)
+ return -ENOMEM;
+ if (sz == CONT_PMD_SIZE)
+ hpte->shift = CONT_PMD_SHIFT;
+ else
+ hpte->shift = pte_cont(*ptep) ? CONT_PMD_SHIFT
+ : PMD_SHIFT;
+ hpte->ptep = ptep;
+ } else if (hpte->shift == P4D_SHIFT) {
+ ptep = (pte_t *)pud_alloc(mm, (p4d_t *)hpte->ptep, addr);
+ if (!ptep)
+ return -ENOMEM;
+ hpte->shift = PUD_SHIFT;
+ hpte->ptep = ptep;
+ } else
+ /*
+ * This also catches the cases of CONT_PMD_SHIFT and
+ * CONT_PTE_SHIFT. Those PTEs should always be leaves.
+ */
+ BUG();
+ }
+
+ return 0;
+}
+
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long sz)
{
--
2.37.0.rc0.161.g10f37bed90-goog
