[RFC PATCH 1/1] pagemap: report swap location for shared pages

From: Tiberiu Georgescu
Date: Wed Jul 14 2021 - 11:25:20 EST


When a page allocated using the MAP_SHARED flag is swapped out, its pagemap
entry is cleared. In many cases, there is no difference between swapped-out
shared pages and newly allocated, non-dirty pages in the pagemap interface.

This patch addresses the behaviour and modifies pte_to_pagemap_entry() to
make use of the XArray associated with the virtual memory area struct
passed as an argument. The XArray contains the location of virtual pages
in the page cache, swap cache or on disk. If they are on either of the
caches, then the original implementation still works. If not, then the
missing information will be retrieved from the XArray.

Co-developed-by: Florian Schmidt <florian.schmidt@xxxxxxxxxxx>
Signed-off-by: Florian Schmidt <florian.schmidt@xxxxxxxxxxx>
Co-developed-by: Carl Waldspurger <carl.waldspurger@xxxxxxxxxxx>
Signed-off-by: Carl Waldspurger <carl.waldspurger@xxxxxxxxxxx>
Co-developed-by: Ivan Teterevkov <ivan.teterevkov@xxxxxxxxxxx>
Signed-off-by: Ivan Teterevkov <ivan.teterevkov@xxxxxxxxxxx>
Signed-off-by: Tiberiu Georgescu <tiberiu.georgescu@xxxxxxxxxxx>
---
fs/proc/task_mmu.c | 37 +++++++++++++++++++++++++++++--------
1 file changed, 29 insertions(+), 8 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index eb97468dfe4c..b17c8aedd32e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1359,12 +1359,25 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
return err;
}

+static void *get_xa_entry_at_vma_addr(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ struct address_space *mapping = inode->i_mapping;
+ pgoff_t offset = linear_page_index(vma, addr);
+
+ return xa_load(&mapping->i_pages, offset);
+}
+
static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
u64 frame = 0, flags = 0;
struct page *page = NULL;

+ if (vma->vm_flags & VM_SOFTDIRTY)
+ flags |= PM_SOFT_DIRTY;
+
if (pte_present(pte)) {
if (pm->show_pfn)
frame = pte_pfn(pte);
@@ -1374,13 +1387,22 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
flags |= PM_SOFT_DIRTY;
if (pte_uffd_wp(pte))
flags |= PM_UFFD_WP;
- } else if (is_swap_pte(pte)) {
+ } else if (is_swap_pte(pte) || shmem_file(vma->vm_file)) {
swp_entry_t entry;
- if (pte_swp_soft_dirty(pte))
- flags |= PM_SOFT_DIRTY;
- if (pte_swp_uffd_wp(pte))
- flags |= PM_UFFD_WP;
- entry = pte_to_swp_entry(pte);
+ if (is_swap_pte(pte)) {
+ entry = pte_to_swp_entry(pte);
+ if (pte_swp_soft_dirty(pte))
+ flags |= PM_SOFT_DIRTY;
+ if (pte_swp_uffd_wp(pte))
+ flags |= PM_UFFD_WP;
+ } else {
+ void *xa_entry = get_xa_entry_at_vma_addr(vma, addr);
+
+ if (xa_is_value(xa_entry))
+ entry = radix_to_swp_entry(xa_entry);
+ else
+ goto out;
+ }
if (pm->show_pfn)
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
@@ -1393,9 +1415,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
flags |= PM_FILE;
if (page && page_mapcount(page) == 1)
flags |= PM_MMAP_EXCLUSIVE;
- if (vma->vm_flags & VM_SOFTDIRTY)
- flags |= PM_SOFT_DIRTY;

+out:
return make_pme(frame, flags);
}

--
2.32.0