aboutsummaryrefslogtreecommitdiffstats
path: root/mm/pagewalk.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--mm/pagewalk.c101
1 files changed, 80 insertions, 21 deletions
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 928df1638c30..2ff3a5bebceb 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -58,6 +58,45 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
return err;
}
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk, int pdshift)
+{
+ int err = 0;
+ const struct mm_walk_ops *ops = walk->ops;
+ int shift = hugepd_shift(*phpd);
+ int page_size = 1 << shift;
+
+ if (!ops->pte_entry)
+ return 0;
+
+ if (addr & (page_size - 1))
+ return 0;
+
+ for (;;) {
+ pte_t *pte;
+
+ spin_lock(&walk->mm->page_table_lock);
+ pte = hugepte_offset(*phpd, addr, pdshift);
+ err = ops->pte_entry(pte, addr, addr + page_size, walk);
+ spin_unlock(&walk->mm->page_table_lock);
+
+ if (err)
+ break;
+ if (addr >= end - page_size)
+ break;
+ addr += page_size;
+ }
+ return err;
+}
+#else
+static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk, int pdshift)
+{
+ return 0;
+}
+#endif
+
static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -71,7 +110,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
do {
again:
next = pmd_addr_end(addr, end);
- if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
+ if (pmd_none(*pmd)) {
if (ops->pte_hole)
err = ops->pte_hole(addr, next, depth, walk);
if (err)
@@ -108,7 +147,10 @@ again:
goto again;
}
- err = walk_pte_range(pmd, addr, next, walk);
+ if (is_hugepd(__hugepd(pmd_val(*pmd))))
+ err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT);
+ else
+ err = walk_pte_range(pmd, addr, next, walk);
if (err)
break;
} while (pmd++, addr = next, addr != end);
@@ -129,7 +171,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
do {
again:
next = pud_addr_end(addr, end);
- if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
+ if (pud_none(*pud)) {
if (ops->pte_hole)
err = ops->pte_hole(addr, next, depth, walk);
if (err)
@@ -157,7 +199,10 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
if (pud_none(*pud))
goto again;
- err = walk_pmd_range(pud, addr, next, walk);
+ if (is_hugepd(__hugepd(pud_val(*pud))))
+ err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT);
+ else
+ err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
@@ -189,7 +234,9 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
if (err)
break;
}
- if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
+ if (is_hugepd(__hugepd(p4d_val(*p4d))))
+ err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT);
+ else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
err = walk_pud_range(p4d, addr, next, walk);
if (err)
break;
@@ -224,8 +271,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
if (err)
break;
}
- if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
- ops->pte_entry)
+ if (is_hugepd(__hugepd(pgd_val(*pgd))))
+ err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT);
+ else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry)
err = walk_p4d_range(pgd, addr, next, walk);
if (err)
break;
@@ -318,19 +366,19 @@ static int __walk_page_range(unsigned long start, unsigned long end,
struct vm_area_struct *vma = walk->vma;
const struct mm_walk_ops *ops = walk->ops;
- if (vma && ops->pre_vma) {
+ if (ops->pre_vma) {
err = ops->pre_vma(start, end, walk);
if (err)
return err;
}
- if (vma && is_vm_hugetlb_page(vma)) {
+ if (is_vm_hugetlb_page(vma)) {
if (ops->hugetlb_entry)
err = walk_hugetlb_range(start, end, walk);
} else
err = walk_pgd_range(start, end, walk);
- if (vma && ops->post_vma)
+ if (ops->post_vma)
ops->post_vma(walk);
return err;
@@ -373,7 +421,7 @@ static int __walk_page_range(unsigned long start, unsigned long end,
* caller-specific data to callbacks, @private should be helpful.
*
* Locking:
- * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_sem,
+ * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock,
* because these function traverse vma list and/or access to vma's data.
*/
int walk_page_range(struct mm_struct *mm, unsigned long start,
@@ -395,20 +443,24 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
if (!walk.mm)
return -EINVAL;
- lockdep_assert_held(&walk.mm->mmap_sem);
+ mmap_assert_locked(walk.mm);
vma = find_vma(walk.mm, start);
do {
if (!vma) { /* after the last vma */
walk.vma = NULL;
next = end;
+ if (ops->pte_hole)
+ err = ops->pte_hole(start, next, -1, &walk);
} else if (start < vma->vm_start) { /* outside vma */
walk.vma = NULL;
next = min(end, vma->vm_start);
+ if (ops->pte_hole)
+ err = ops->pte_hole(start, next, -1, &walk);
} else { /* inside vma */
walk.vma = vma;
next = min(end, vma->vm_end);
- vma = vma->vm_next;
+ vma = find_vma(mm, vma->vm_end);
err = walk_page_test(start, next, &walk);
if (err > 0) {
@@ -422,16 +474,23 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
}
if (err < 0)
break;
- }
- if (walk.vma || walk.ops->pte_hole)
err = __walk_page_range(start, next, &walk);
+ }
if (err)
break;
} while (start = next, start < end);
return err;
}
-/*
+/**
+ * walk_page_range_novma - walk a range of pagetables not backed by a vma
+ * @mm: mm_struct representing the target process of page table walk
+ * @start: start address of the virtual address range
+ * @end: end address of the virtual address range
+ * @ops: operation to call during the walk
+ * @pgd: pgd to walk if different from mm->pgd
+ * @private: private data for callbacks' usage
+ *
* Similar to walk_page_range() but can walk any page tables even if they are
* not backed by VMAs. Because 'unusual' entries may be walked this function
* will also not lock the PTEs for the pte_entry() callback. This is useful for
@@ -453,9 +512,9 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
if (start >= end || !walk.mm)
return -EINVAL;
- lockdep_assert_held(&walk.mm->mmap_sem);
+ mmap_assert_write_locked(walk.mm);
- return __walk_page_range(start, end, &walk);
+ return walk_pgd_range(start, end, &walk);
}
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
@@ -472,7 +531,7 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
if (!walk.mm)
return -EINVAL;
- lockdep_assert_held(&walk.mm->mmap_sem);
+ mmap_assert_locked(walk.mm);
err = walk_page_test(vma->vm_start, vma->vm_end, &walk);
if (err > 0)
@@ -498,11 +557,11 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
* Also see walk_page_range() for additional information.
*
* Locking:
- * This function can't require that the struct mm_struct::mmap_sem is held,
+ * This function can't require that the struct mm_struct::mmap_lock is held,
* since @mapping may be mapped by multiple processes. Instead
* @mapping->i_mmap_rwsem must be held. This might have implications in the
* callbacks, and it's up tho the caller to ensure that the
- * struct mm_struct::mmap_sem is not needed.
+ * struct mm_struct::mmap_lock is not needed.
*
* Also this means that a caller can't rely on the struct
* vm_area_struct::vm_flags to be constant across a call,
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.