@@ -732,13 +732,13 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
result = SCAN_SUCCEED;
trace_mm_collapse_huge_page_isolate(page, none_or_zero,
referenced, writable, result);
- return 1;
+ return SCAN_SUCCEED;
}
out:
release_pte_pages(pte, _pte, compound_pagelist);
trace_mm_collapse_huge_page_isolate(page, none_or_zero,
referenced, writable, result);
- return 0;
+ return result;
}
static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
@@ -1096,9 +1096,9 @@ static int alloc_charge_hpage(struct mm_struct *mm, struct collapse_control *cc)
return SCAN_SUCCEED;
}
-static void collapse_huge_page(struct mm_struct *mm, unsigned long address,
- int referenced, int unmapped,
- struct collapse_control *cc)
+static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
+ int referenced, int unmapped,
+ struct collapse_control *cc)
{
LIST_HEAD(compound_pagelist);
pmd_t *pmd, _pmd;
@@ -1106,7 +1106,7 @@ static void collapse_huge_page(struct mm_struct *mm, unsigned long address,
pgtable_t pgtable;
struct page *new_page;
spinlock_t *pmd_ptl, *pte_ptl;
- int isolated = 0, result = 0;
+ int result = SCAN_FAIL;
struct vm_area_struct *vma;
struct mmu_notifier_range range;
@@ -1186,11 +1186,11 @@ static void collapse_huge_page(struct mm_struct *mm, unsigned long address,
mmu_notifier_invalidate_range_end(&range);
spin_lock(pte_ptl);
- isolated = __collapse_huge_page_isolate(vma, address, pte,
- &compound_pagelist);
+ result = __collapse_huge_page_isolate(vma, address, pte,
+ &compound_pagelist);
spin_unlock(pte_ptl);
- if (unlikely(!isolated)) {
+ if (unlikely(result != SCAN_SUCCEED)) {
pte_unmap(pte);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
@@ -1238,25 +1238,23 @@ static void collapse_huge_page(struct mm_struct *mm, unsigned long address,
cc->hpage = NULL;
- khugepaged_pages_collapsed++;
result = SCAN_SUCCEED;
out_up_write:
mmap_write_unlock(mm);
out_nolock:
if (!IS_ERR_OR_NULL(cc->hpage))
mem_cgroup_uncharge(page_folio(cc->hpage));
- trace_mm_collapse_huge_page(mm, isolated, result);
- return;
+ trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result);
+ return result;
}
-static int khugepaged_scan_pmd(struct mm_struct *mm,
- struct vm_area_struct *vma,
- unsigned long address,
+static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, bool *mmap_locked,
struct collapse_control *cc)
{
pmd_t *pmd;
pte_t *pte, *_pte;
- int ret = 0, result = 0, referenced = 0;
+ int result = SCAN_FAIL, referenced = 0;
int none_or_zero = 0, shared = 0;
struct page *page = NULL;
unsigned long _address;
@@ -1266,6 +1264,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+ *mmap_locked = true;
+
result = find_pmd_or_thp_or_none(mm, address, &pmd);
if (result != SCAN_SUCCEED)
goto out;
@@ -1391,18 +1391,22 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
- ret = 1;
}
out_unmap:
pte_unmap_unlock(pte, ptl);
- if (ret) {
- /* collapse_huge_page will return with the mmap_lock released */
- collapse_huge_page(mm, address, referenced, unmapped, cc);
+ if (result == SCAN_SUCCEED) {
+ /*
+ * collapse_huge_page() will return with the mmap_lock released
+ * - so let the caller know mmap_lock was dropped
+ */
+ *mmap_locked = false;
+ result = collapse_huge_page(mm, address, referenced,
+ unmapped, cc);
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
none_or_zero, result, unmapped);
- return ret;
+ return result;
}
static void collect_mm_slot(struct mm_slot *mm_slot)
@@ -1679,8 +1683,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
* + restore gaps in the page cache;
* + unlock and free huge page;
*/
-static void collapse_file(struct mm_struct *mm, struct file *file,
- pgoff_t start, struct collapse_control *cc)
+static int collapse_file(struct mm_struct *mm, struct file *file,
+ pgoff_t start, struct collapse_control *cc)
{
struct address_space *mapping = file->f_mapping;
struct page *new_page;
@@ -1982,8 +1986,6 @@ static void collapse_file(struct mm_struct *mm, struct file *file,
*/
retract_page_tables(mapping, start);
cc->hpage = NULL;
-
- khugepaged_pages_collapsed++;
} else {
struct page *page;
@@ -2031,11 +2033,12 @@ static void collapse_file(struct mm_struct *mm, struct file *file,
if (!IS_ERR_OR_NULL(cc->hpage))
mem_cgroup_uncharge(page_folio(cc->hpage));
/* TODO: tracepoints */
+ return result;
}
-static void khugepaged_scan_file(struct mm_struct *mm,
- struct file *file, pgoff_t start,
- struct collapse_control *cc)
+static int khugepaged_scan_file(struct mm_struct *mm,
+ struct file *file, pgoff_t start,
+ struct collapse_control *cc)
{
struct page *page = NULL;
struct address_space *mapping = file->f_mapping;
@@ -2108,16 +2111,16 @@ static void khugepaged_scan_file(struct mm_struct *mm,
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
} else {
- collapse_file(mm, file, start, cc);
+ result = collapse_file(mm, file, start, cc);
}
}
/* TODO: tracepoints */
+ return result;
}
#else
-static void khugepaged_scan_file(struct mm_struct *mm,
- struct file *file, pgoff_t start,
- struct collapse_control *cc)
+static int khugepaged_scan_file(struct mm_struct *mm, struct file *file, pgoff_t start,
+ struct collapse_control *cc)
{
BUILD_BUG();
}
@@ -2189,7 +2192,9 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
goto skip;
while (khugepaged_scan.address < hend) {
- int ret;
+ int result;
+ bool mmap_locked;
+
cond_resched();
if (unlikely(khugepaged_test_exit(mm)))
goto breakouterloop;
@@ -2203,17 +2208,21 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
khugepaged_scan.address);
mmap_read_unlock(mm);
- ret = 1;
- khugepaged_scan_file(mm, file, pgoff, cc);
+ mmap_locked = false;
+ result = khugepaged_scan_file(mm, file, pgoff,
+ cc);
fput(file);
} else {
- ret = khugepaged_scan_pmd(mm, vma,
- khugepaged_scan.address, cc);
+ result = khugepaged_scan_pmd(mm, vma,
+ khugepaged_scan.address,
+ &mmap_locked, cc);
}
+ if (result == SCAN_SUCCEED)
+ ++khugepaged_pages_collapsed;
/* move to next address */
khugepaged_scan.address += HPAGE_PMD_SIZE;
progress += HPAGE_PMD_NR;
- if (ret)
+ if (!mmap_locked)
/* we released mmap_lock so break loop */
goto breakouterloop_mmap_lock;
if (progress >= pages)
Pipe enum scan_result codes back through return values of functions downstream of khugepaged_scan_file() and khugepaged_scan_pmd() to inform callers if the operation was successful, and if not, why. Since khugepaged_scan_pmd()'s return value already has a specific meaning (whether mmap_lock was unlocked or not), add a bool* argument to khugepaged_scan_pmd() to retrieve this information. Change khugepaged to take action based on the return values of khugepaged_scan_file() and khugepaged_scan_pmd() instead of acting deep within the collapsing functions themselves. Signed-off-by: Zach O'Keefe <zokeefe@google.com> --- mm/khugepaged.c | 85 +++++++++++++++++++++++++++---------------------- 1 file changed, 47 insertions(+), 38 deletions(-)