[PATCH 5/5] mm: Introduce ZAP_FLAG_SKIP_SWAP

From: Peter Xu
Date: Wed Sep 01 2021 - 16:57:41 EST


Firstly, the comment in zap_pte_range() is misleading because it checks against
details rather than check_mappings, so it's against what the code did.

Meanwhile, it's confusing too on not explaining why passing in the details
pointer would mean to skip all swap entries. New user of zap_details could
very possibly miss this fact if they don't read deep until zap_pte_range()
because there's no comment at zap_details talking about it at all, so swap
entries could be errornously skipped without being noticed.

This partly reverts 3e8715fdc03e ("mm: drop zap_details::check_swap_entries"),
but introduce ZAP_FLAG_SKIP_SWAP flag, which means the opposite of previous
"details" parameter: the caller should explicitly set this to skip swap
entries, otherwise swap entries will always be considered (which is still the
major case here).

Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
Reviewed-by: Alistair Popple <apopple@xxxxxxxxxx>
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
---
include/linux/mm.h | 12 ++++++++++++
mm/memory.c | 8 +++++---
2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fcbc1c4f8e8e..f798f5e4baa5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1718,6 +1718,8 @@ extern void user_shm_unlock(size_t, struct ucounts *);

/* Whether to check page->mapping when zapping */
#define ZAP_FLAG_CHECK_MAPPING BIT(0)
+/* Whether to skip zapping swap entries */
+#define ZAP_FLAG_SKIP_SWAP BIT(1)

/*
* Parameter block passed down to zap_pte_range in exceptional cases.
@@ -1741,6 +1743,16 @@ zap_skip_check_mapping(struct zap_details *details, struct page *page)
return details->zap_mapping != page_rmapping(page);
}

+/* Return true if skip swap entries, false otherwise */
+static inline bool
+zap_skip_swap(struct zap_details *details)
+{
+ if (!details)
+ return false;
+
+ return details->zap_flags & ZAP_FLAG_SKIP_SWAP;
+}
+
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte);
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
diff --git a/mm/memory.c b/mm/memory.c
index 05ccacda4fe9..79957265afb4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1379,8 +1379,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
continue;
}

- /* If details->check_mapping, we leave swap entries. */
- if (unlikely(details))
+ if (unlikely(zap_skip_swap(details)))
continue;

if (!non_swap_entry(entry))
@@ -3379,7 +3378,10 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start,
pgoff_t nr, bool even_cows)
{
pgoff_t first_index = start, last_index = start + nr - 1;
- struct zap_details details = { .zap_mapping = mapping };
+ struct zap_details details = {
+ .zap_mapping = mapping,
+ .zap_flags = ZAP_FLAG_SKIP_SWAP,
+ };

if (!even_cows)
details.zap_flags |= ZAP_FLAG_CHECK_MAPPING;
--
2.31.1