[PATCH 36/46] hugetlb: remove huge_pte_lock and huge_pte_lockptr

From: James Houghton
Date: Thu Jan 05 2023 - 05:23:08 EST


They are replaced with hugetlb_pte_lock{,ptr}. All callers that haven't
already been replaced don't get called when using HGM, so we handle them
by populating hugetlb_ptes with the standard, hstate-sized huge PTEs.

Signed-off-by: James Houghton <jthoughton@xxxxxxxxxx>
---
arch/powerpc/mm/pgtable.c | 7 +++++--
include/linux/hugetlb.h | 42 +++++++++++++++------------------------
mm/hugetlb.c | 22 +++++++++++++-------
3 files changed, 36 insertions(+), 35 deletions(-)

diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 035a0df47af0..e20d6aa9a2a6 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -258,11 +258,14 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,

#ifdef CONFIG_PPC_BOOK3S_64
struct hstate *h = hstate_vma(vma);
+ struct hugetlb_pte hpte;

psize = hstate_get_psize(h);
#ifdef CONFIG_DEBUG_VM
- assert_spin_locked(huge_pte_lockptr(huge_page_shift(h),
- vma->vm_mm, ptep));
+ /* HGM is not supported for powerpc yet. */
+ hugetlb_pte_populate(&hpte, ptep, huge_page_shift(h),
+ hpage_size_to_level(psize));
+ assert_spin_locked(hpte.ptl);
#endif

#else
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index e1baf939afb6..4d318bf2ced9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1032,14 +1032,6 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
return modified_mask;
}

-static inline spinlock_t *huge_pte_lockptr(unsigned int shift,
- struct mm_struct *mm, pte_t *pte)
-{
- if (shift == PMD_SHIFT)
- return pmd_lockptr(mm, (pmd_t *) pte);
- return &mm->page_table_lock;
-}
-
#ifndef hugepages_supported
/*
* Some platform decide whether they support huge pages at boot
@@ -1248,12 +1240,6 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
return 0;
}

-static inline spinlock_t *huge_pte_lockptr(unsigned int shift,
- struct mm_struct *mm, pte_t *pte)
-{
- return &mm->page_table_lock;
-}
-
static inline void hugetlb_count_init(struct mm_struct *mm)
{
}
@@ -1328,16 +1314,6 @@ int hugetlb_collapse(struct mm_struct *mm, struct vm_area_struct *vma,
}
#endif

-static inline spinlock_t *huge_pte_lock(struct hstate *h,
- struct mm_struct *mm, pte_t *pte)
-{
- spinlock_t *ptl;
-
- ptl = huge_pte_lockptr(huge_page_shift(h), mm, pte);
- spin_lock(ptl);
- return ptl;
-}
-
static inline
spinlock_t *hugetlb_pte_lockptr(struct hugetlb_pte *hpte)
{
@@ -1358,8 +1334,22 @@ void hugetlb_pte_populate(struct mm_struct *mm, struct hugetlb_pte *hpte,
pte_t *ptep, unsigned int shift,
enum hugetlb_level level)
{
- __hugetlb_pte_populate(hpte, ptep, shift, level,
- huge_pte_lockptr(shift, mm, ptep));
+ spinlock_t *ptl;
+
+ /*
+ * For contiguous HugeTLB PTEs that can contain other HugeTLB PTEs
+ * on the same level, the same PTL for both must be used.
+ *
+ * For some architectures that implement hugetlb_walk_step, this
+ * version of hugetlb_pte_populate() may not be correct to use for
+ * high-granularity PTEs. Instead, call __hugetlb_pte_populate()
+ * directly.
+ */
+ if (level == HUGETLB_LEVEL_PMD)
+ ptl = pmd_lockptr(mm, (pmd_t *) ptep);
+ else
+ ptl = &mm->page_table_lock;
+ __hugetlb_pte_populate(hpte, ptep, shift, level, ptl);
}

#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 388c46c7e77a..d71adc03138d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5303,9 +5303,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
put_page(hpage);

/* Install the new huge page if src pte stable */
- dst_ptl = huge_pte_lock(h, dst, dst_pte);
- src_ptl = huge_pte_lockptr(huge_page_shift(h),
- src, src_pte);
+ dst_ptl = hugetlb_pte_lock(&dst_hpte);
+ src_ptl = hugetlb_pte_lockptr(&src_hpte);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
if (!pte_same(src_pte_old, entry)) {
@@ -7383,7 +7382,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long saddr;
pte_t *spte = NULL;
pte_t *pte;
- spinlock_t *ptl;
+ struct hugetlb_pte hpte;
+ struct hstate *shstate;

i_mmap_lock_read(mapping);
vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
@@ -7404,7 +7404,11 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
if (!spte)
goto out;

- ptl = huge_pte_lock(hstate_vma(vma), mm, spte);
+ shstate = hstate_vma(svma);
+
+ hugetlb_pte_populate(mm, &hpte, spte, huge_page_shift(shstate),
+ hpage_size_to_level(huge_page_size(shstate)));
+ spin_lock(hpte.ptl);
if (pud_none(*pud)) {
pud_populate(mm, pud,
(pmd_t *)((unsigned long)spte & PAGE_MASK));
@@ -7412,7 +7416,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
} else {
put_page(virt_to_page(spte));
}
- spin_unlock(ptl);
+ spin_unlock(hpte.ptl);
out:
pte = (pte_t *)pmd_alloc(mm, pud, addr);
i_mmap_unlock_read(mapping);
@@ -8132,6 +8136,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
unsigned long address, start, end;
spinlock_t *ptl;
pte_t *ptep;
+ struct hugetlb_pte hpte;

if (!(vma->vm_flags & VM_MAYSHARE))
return;
@@ -8156,7 +8161,10 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
ptep = hugetlb_walk(vma, address, sz);
if (!ptep)
continue;
- ptl = huge_pte_lock(h, mm, ptep);
+
+ hugetlb_pte_populate(mm, &hpte, ptep, huge_page_shift(h),
+ hpage_size_to_level(sz));
+ ptl = hugetlb_pte_lock(&hpte);
huge_pmd_unshare(mm, vma, address, ptep);
spin_unlock(ptl);
}
--
2.39.0.314.g84b9a713c41-goog