arm64: hugetlb: refactor find_num_contig()

Patch series "Support for contiguous pte hugepages", v4.

This patchset updates the hugetlb code to fix issues arising from
contiguous pte hugepages (such as on arm64).  Compared to v3, This
version addresses a build failure on arm64 by including two cleanup
patches.  Other than the arm64 cleanups, the rest are generic code
changes.  The remaining arm64 support based on these patches will be
posted separately.  The patches are based on v4.12-rc2.  Previous
related postings can be found at [0], [1], [2], and [3].

The patches fall into three categories -

* Patch 1-2 - arm64 cleanups required to greatly simplify changing
  huge_pte_offset() prototype in Patch 5.

  Catalin, Will - are you happy for these patches to go via mm?

* Patches 3-4 address issues with gup

* Patches 5-8 relate to passing a size argument to hugepage helpers to
  disambiguate the size of the referred page. These changes are
  required to enable arch code to properly handle swap entries for
  contiguous pte hugepages.

  The changes to huge_pte_offset() (patch 5) touch multiple
  architectures but I've managed to minimise these changes for the
  other affected functions - huge_pte_clear() and set_huge_pte_at().

These patches gate the enabling of contiguous hugepages support on arm64
which has been requested for systems using !4k page granule.

The ARM64 architecture supports two flavours of hugepages -

* Block mappings at the pud/pmd level

  These are regular hugepages where a pmd or a pud page table entry
  points to a block of memory. Depending on the PAGE_SIZE in use the
  following size of block mappings are supported -

          PMD	PUD
          ---	---
  4K:      2M	 1G
  16K:    32M
  64K:   512M

  For certain applications/usecases such as HPC and large enterprise
  workloads, folks are using 64k page size but the minimum hugepage size
  of 512MB isn't very practical.

To overcome this ...

* Using the Contiguous bit

  The architecture provides a contiguous bit in the translation table
  entry which acts as a hint to the mmu to indicate that it is one of a
  contiguous set of entries that can be cached in a single TLB entry.

  We use the contiguous bit in Linux to increase the mapping size at the
  pmd and pte (last) level.

  The number of supported contiguous entries varies by page size and
  level of the page table.

  Using the contiguous bit allows additional hugepage sizes -

           CONT PTE    PMD    CONT PMD    PUD
           --------    ---    --------    ---
    4K:         64K     2M         32M     1G
    16K:         2M    32M          1G
    64K:         2M   512M         16G

  Of these, 64K with 4K and 2M with 64K pages have been explicitly
  requested by a few different users.

Entries with the contiguous bit set are required to be modified all
together - which makes things like memory poisoning and migration
impossible to do correctly without knowing the size of hugepage being
dealt with - the reason for adding size parameter to a few of the
hugepage helpers in this series.

This patch (of 8):

As we regularly check for contiguous pte's in the huge accessors, remove
this extra check from find_num_contig.

[punit.agrawal@arm.com: resolve rebase conflicts due to patch re-ordering]
Link: http://lkml.kernel.org/r/20170524115409.31309-2-punit.agrawal@arm.com
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Cc: David Woods <dwoods@mellanox.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 8 insertions, 9 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 69b8200b1cfd..710bf935a473 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -42,15 +42,13 @@ int pud_huge(pud_t pud)
 }
 
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pte, size_t *pgsize)
+			   pte_t *ptep, size_t *pgsize)
 {
 	pgd_t *pgd = pgd_offset(mm, addr);
 	pud_t *pud;
 	pmd_t *pmd;
 
 	*pgsize = PAGE_SIZE;
-	if (!pte_cont(pte))
-		return 1;
 	pud = pud_offset(pgd, addr);
 	pmd = pmd_offset(pud, addr);
 	if ((pte_t *)pmd == ptep) {
@@ -65,15 +63,16 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 {
 	size_t pgsize;
 	int i;
-	int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize);
+	int ncontig;
 	unsigned long pfn;
 	pgprot_t hugeprot;
 
-	if (ncontig == 1) {
+	if (!pte_cont(pte)) {
 		set_pte_at(mm, addr, ptep, pte);
 		return;
 	}
 
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
 	hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
 	for (i = 0; i < ncontig; i++) {
@@ -188,7 +187,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 		bool is_dirty = false;
 
 		cpte = huge_pte_offset(mm, addr);
-		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
+		ncontig = find_num_contig(mm, addr, cpte, &pgsize);
 		/* save the 1st pte to return */
 		pte = ptep_get_and_clear(mm, addr, cpte);
 		for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
@@ -228,7 +227,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 		cpte = huge_pte_offset(vma->vm_mm, addr);
 		pfn = pte_pfn(*cpte);
 		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
-					  *cpte, &pgsize);
+					  &pgsize);
 		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) {
 			changed |= ptep_set_access_flags(vma, addr, cpte,
 							pfn_pte(pfn,
@@ -251,7 +250,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 		size_t pgsize = 0;
 
 		cpte = huge_pte_offset(mm, addr);
-		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
+		ncontig = find_num_contig(mm, addr, cpte, &pgsize);
 		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize)
 			ptep_set_wrprotect(mm, addr, cpte);
 	} else {
@@ -269,7 +268,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
 
 		cpte = huge_pte_offset(vma->vm_mm, addr);
 		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
-					  *cpte, &pgsize);
+					  &pgsize);
 		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize)
 			ptep_clear_flush(vma, addr, cpte);
 	} else {