Re: [PATCH v10 03/10] mm/vmalloc: use pte_set_huge()/pte_clear_huge() for PTE-level block mappings

vmap installs PTE-level block mappings by reusing set_huge_pte_at() and
huge_ptep_get_and_clear() under #ifdef CONFIG_HUGETLB_PAGE. This makes
the feature silently unavailable on CONFIG_HUGETLB_PAGE=n kernels and
couples mm/vmalloc.c to HugeTLB internals it does not otherwise need.

Now that arm64 and powerpc/8xx provide pte_set_huge() and
pte_clear_huge(), add the generic fallbacks next to the existing
pmd/pud_set_huge() family and convert vmap_pte_range() and
vunmap_pte_range() to the new helpers. The CONFIG_HUGETLB_PAGE guards
around the block-mapping paths are dropped, so PTE-level block mappings
now also work on CONFIG_HUGETLB_PAGE=n kernels, and mm/vmalloc.c no
longer includes <linux/hugetlb.h>.

The fallbacks exist only to keep the build working on architectures
without PTE-level block mapping support. They are unreachable there:
the callers only run when arch_vmap_pte_range_map_size() or
arch_vmap_pte_range_unmap_size() return a size other than PAGE_SIZE,
which requires an arch implementation. BUILD_BUG() makes that
explicit rather than silently doing nothing.

Signed-off-by: Wen Jiang <redacted>
Reviewed-by: Barry Song <baohua@kernel.org>
---
 include/linux/pgtable.h | 29 +++++++++++++++++++++++++++++
 mm/vmalloc.c            | 19 ++++++-------------
 2 files changed, 35 insertions(+), 13 deletions(-)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 8c093c119e5a8..a7fd51fec8a17 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h

@@ -2204,6 +2204,35 @@ static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 }
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
 
+/*
+ * PTE-level block mappings for vmap.
+ *
+ * pte_set_huge() only has to be implemented by architectures whose
+ * arch_vmap_pte_range_map_size() can return a size other than PAGE_SIZE.
+ */
+#ifndef __HAVE_ARCH_PTE_SET_HUGE
+static inline void pte_set_huge(pte_t *ptep, unsigned long addr,
+				phys_addr_t phys, pgprot_t prot,
+				unsigned long size)
+{
+	BUILD_BUG();
+}
+#endif
+
+/*
+ * Likewise, pte_clear_huge() only has to be implemented by architectures
+ * whose arch_vmap_pte_range_unmap_size() can return a size other than
+ * PAGE_SIZE.
+ */
+#ifndef __HAVE_ARCH_PTE_CLEAR_HUGE
+static inline pte_t pte_clear_huge(pte_t *ptep, unsigned long addr,
+				   unsigned long size)
+{
+	BUILD_BUG();
+	return __pte(0);
+}
+#endif
+
 #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index bea9f76ed7e74..fb757d95bde25 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c

@@ -38,7 +38,6 @@
 #include <linux/rbtree_augmented.h>
 #include <linux/overflow.h>
 #include <linux/pgtable.h>
-#include <linux/hugetlb.h>
 #include <linux/sched/mm.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>

@@ -100,7 +99,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	u64 pfn;
 	struct page *page;
-	unsigned long size = PAGE_SIZE;
+	unsigned long size;
 
 	if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr)))
 		return -EINVAL;

@@ -121,17 +120,12 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			BUG();
 		}
 
-#ifdef CONFIG_HUGETLB_PAGE
 		size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift);
 		if (size != PAGE_SIZE) {
-			pte_t entry = pfn_pte(pfn, prot);
-
-			entry = arch_make_huge_pte(entry, ilog2(size), 0);
-			set_huge_pte_at(&init_mm, addr, pte, entry, size);
+			pte_set_huge(pte, addr, PFN_PHYS(pfn), prot, size);