Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 4eb09e0..e81640d 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -4,14 +4,28 @@
#include <linux/sched.h>
#include <linux/hugetlb.h>
-static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
- struct mm_walk *walk)
+/*
+ * We want to know the real level where a entry is located ignoring any
+ * folding of levels which may be happening. For example if p4d is folded then
+ * a missing entry found at level 1 (p4d) is actually at level 0 (pgd).
+ */
+static int real_depth(int depth)
{
- pte_t *pte;
- int err = 0;
- const struct mm_walk_ops *ops = walk->ops;
+ if (depth == 3 && PTRS_PER_PMD == 1)
+ depth = 2;
+ if (depth == 2 && PTRS_PER_PUD == 1)
+ depth = 1;
+ if (depth == 1 && PTRS_PER_P4D == 1)
+ depth = 0;
+ return depth;
+}
- pte = pte_offset_map(pmd, addr);
+static int walk_pte_range_inner(pte_t *pte, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ const struct mm_walk_ops *ops = walk->ops;
+ int err = 0;
+
for (;;) {
err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
if (err)
@@ -21,8 +35,26 @@
addr += PAGE_SIZE;
pte++;
}
+ return err;
+}
- pte_unmap(pte);
+static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ pte_t *pte;
+ int err = 0;
+ spinlock_t *ptl;
+
+ if (walk->no_vma) {
+ pte = pte_offset_map(pmd, addr);
+ err = walk_pte_range_inner(pte, addr, end, walk);
+ pte_unmap(pte);
+ } else {
+ pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ err = walk_pte_range_inner(pte, addr, end, walk);
+ pte_unmap_unlock(pte, ptl);
+ }
+
return err;
}
@@ -33,18 +65,22 @@
unsigned long next;
const struct mm_walk_ops *ops = walk->ops;
int err = 0;
+ int depth = real_depth(3);
pmd = pmd_offset(pud, addr);
do {
again:
next = pmd_addr_end(addr, end);
- if (pmd_none(*pmd) || !walk->vma) {
+ if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
if (ops->pte_hole)
- err = ops->pte_hole(addr, next, walk);
+ err = ops->pte_hole(addr, next, depth, walk);
if (err)
break;
continue;
}
+
+ walk->action = ACTION_SUBTREE;
+
/*
* This implies that each ->pmd_entry() handler
* needs to know about pmd_trans_huge() pmds
@@ -54,16 +90,24 @@
if (err)
break;
+ if (walk->action == ACTION_AGAIN)
+ goto again;
+
/*
* Check this here so we only break down trans_huge
* pages when we _need_ to
*/
- if (!ops->pte_entry)
+ if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) ||
+ walk->action == ACTION_CONTINUE ||
+ !(ops->pte_entry))
continue;
- split_huge_pmd(walk->vma, pmd, addr);
- if (pmd_trans_unstable(pmd))
- goto again;
+ if (walk->vma) {
+ split_huge_pmd(walk->vma, pmd, addr);
+ if (pmd_trans_unstable(pmd))
+ goto again;
+ }
+
err = walk_pte_range(pmd, addr, next, walk);
if (err)
break;
@@ -79,37 +123,41 @@
unsigned long next;
const struct mm_walk_ops *ops = walk->ops;
int err = 0;
+ int depth = real_depth(2);
pud = pud_offset(p4d, addr);
do {
again:
next = pud_addr_end(addr, end);
- if (pud_none(*pud) || !walk->vma) {
+ if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
if (ops->pte_hole)
- err = ops->pte_hole(addr, next, walk);
+ err = ops->pte_hole(addr, next, depth, walk);
if (err)
break;
continue;
}
- if (ops->pud_entry) {
- spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
+ walk->action = ACTION_SUBTREE;
- if (ptl) {
- err = ops->pud_entry(pud, addr, next, walk);
- spin_unlock(ptl);
- if (err)
- break;
- continue;
- }
- }
+ if (ops->pud_entry)
+ err = ops->pud_entry(pud, addr, next, walk);
+ if (err)
+ break;
- split_huge_pud(walk->vma, pud, addr);
+ if (walk->action == ACTION_AGAIN)
+ goto again;
+
+ if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) ||
+ walk->action == ACTION_CONTINUE ||
+ !(ops->pmd_entry || ops->pte_entry))
+ continue;
+
+ if (walk->vma)
+ split_huge_pud(walk->vma, pud, addr);
if (pud_none(*pud))
goto again;
- if (ops->pmd_entry || ops->pte_entry)
- err = walk_pmd_range(pud, addr, next, walk);
+ err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
@@ -124,18 +172,24 @@
unsigned long next;
const struct mm_walk_ops *ops = walk->ops;
int err = 0;
+ int depth = real_depth(1);
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(p4d)) {
if (ops->pte_hole)
- err = ops->pte_hole(addr, next, walk);
+ err = ops->pte_hole(addr, next, depth, walk);
if (err)
break;
continue;
}
- if (ops->pmd_entry || ops->pte_entry)
+ if (ops->p4d_entry) {
+ err = ops->p4d_entry(p4d, addr, next, walk);
+ if (err)
+ break;
+ }
+ if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
err = walk_pud_range(p4d, addr, next, walk);
if (err)
break;
@@ -152,17 +206,26 @@
const struct mm_walk_ops *ops = walk->ops;
int err = 0;
- pgd = pgd_offset(walk->mm, addr);
+ if (walk->pgd)
+ pgd = walk->pgd + pgd_index(addr);
+ else
+ pgd = pgd_offset(walk->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd)) {
if (ops->pte_hole)
- err = ops->pte_hole(addr, next, walk);
+ err = ops->pte_hole(addr, next, 0, walk);
if (err)
break;
continue;
}
- if (ops->pmd_entry || ops->pte_entry)
+ if (ops->pgd_entry) {
+ err = ops->pgd_entry(pgd, addr, next, walk);
+ if (err)
+ break;
+ }
+ if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
+ ops->pte_entry)
err = walk_p4d_range(pgd, addr, next, walk);
if (err)
break;
@@ -198,7 +261,7 @@
if (pte)
err = ops->hugetlb_entry(pte, hmask, addr, next, walk);
else if (ops->pte_hole)
- err = ops->pte_hole(addr, next, walk);
+ err = ops->pte_hole(addr, next, -1, walk);
if (err)
break;
@@ -242,7 +305,7 @@
if (vma->vm_flags & VM_PFNMAP) {
int err = 1;
if (ops->pte_hole)
- err = ops->pte_hole(start, end, walk);
+ err = ops->pte_hole(start, end, -1, walk);
return err ? err : 1;
}
return 0;
@@ -253,13 +316,23 @@
{
int err = 0;
struct vm_area_struct *vma = walk->vma;
+ const struct mm_walk_ops *ops = walk->ops;
+
+ if (vma && ops->pre_vma) {
+ err = ops->pre_vma(start, end, walk);
+ if (err)
+ return err;
+ }
if (vma && is_vm_hugetlb_page(vma)) {
- if (walk->ops->hugetlb_entry)
+ if (ops->hugetlb_entry)
err = walk_hugetlb_range(start, end, walk);
} else
err = walk_pgd_range(start, end, walk);
+ if (vma && ops->post_vma)
+ ops->post_vma(walk);
+
return err;
}
@@ -290,12 +363,17 @@
* its vm_flags. walk_page_test() and @ops->test_walk() are used for this
* purpose.
*
+ * If operations need to be staged before and committed after a vma is walked,
+ * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(),
+ * since it is intended to handle commit-type operations, can't return any
+ * errors.
+ *
* struct mm_walk keeps current values of some common data like vma and pmd,
* which are useful for the access from callbacks. If you want to pass some
* 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,
@@ -317,7 +395,7 @@
if (!walk.mm)
return -EINVAL;
- lockdep_assert_held(&walk.mm->mmap_sem);
+ mmap_assert_locked(walk.mm);
vma = find_vma(walk.mm, start);
do {
@@ -353,6 +431,33 @@
return err;
}
+/*
+ * 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
+ * walking the kernel pages tables or page tables for firmware.
+ */
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+ unsigned long end, const struct mm_walk_ops *ops,
+ pgd_t *pgd,
+ void *private)
+{
+ struct mm_walk walk = {
+ .ops = ops,
+ .mm = mm,
+ .pgd = pgd,
+ .private = private,
+ .no_vma = true
+ };
+
+ if (start >= end || !walk.mm)
+ return -EINVAL;
+
+ mmap_assert_locked(walk.mm);
+
+ return __walk_page_range(start, end, &walk);
+}
+
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
void *private)
{
@@ -367,7 +472,7 @@
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)
@@ -376,3 +481,80 @@
return err;
return __walk_page_range(vma->vm_start, vma->vm_end, &walk);
}
+
+/**
+ * walk_page_mapping - walk all memory areas mapped into a struct address_space.
+ * @mapping: Pointer to the struct address_space
+ * @first_index: First page offset in the address_space
+ * @nr: Number of incremental page offsets to cover
+ * @ops: operation to call during the walk
+ * @private: private data for callbacks' usage
+ *
+ * This function walks all memory areas mapped into a struct address_space.
+ * The walk is limited to only the given page-size index range, but if
+ * the index boundaries cross a huge page-table entry, that entry will be
+ * included.
+ *
+ * Also see walk_page_range() for additional information.
+ *
+ * Locking:
+ * 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_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,
+ * except for immutable flags. Callers requiring this shouldn't use
+ * this function.
+ *
+ * Return: 0 on success, negative error code on failure, positive number on
+ * caller defined premature termination.
+ */
+int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
+ pgoff_t nr, const struct mm_walk_ops *ops,
+ void *private)
+{
+ struct mm_walk walk = {
+ .ops = ops,
+ .private = private,
+ };
+ struct vm_area_struct *vma;
+ pgoff_t vba, vea, cba, cea;
+ unsigned long start_addr, end_addr;
+ int err = 0;
+
+ lockdep_assert_held(&mapping->i_mmap_rwsem);
+ vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index,
+ first_index + nr - 1) {
+ /* Clip to the vma */
+ vba = vma->vm_pgoff;
+ vea = vba + vma_pages(vma);
+ cba = first_index;
+ cba = max(cba, vba);
+ cea = first_index + nr;
+ cea = min(cea, vea);
+
+ start_addr = ((cba - vba) << PAGE_SHIFT) + vma->vm_start;
+ end_addr = ((cea - vba) << PAGE_SHIFT) + vma->vm_start;
+ if (start_addr >= end_addr)
+ continue;
+
+ walk.vma = vma;
+ walk.mm = vma->vm_mm;
+
+ err = walk_page_test(vma->vm_start, vma->vm_end, &walk);
+ if (err > 0) {
+ err = 0;
+ break;
+ } else if (err < 0)
+ break;
+
+ err = __walk_page_range(start_addr, end_addr, &walk);
+ if (err)
+ break;
+ }
+
+ return err;
+}