diff mbox series

[v1,3/6] fs/proc/task_mmu: properly detect PM_MMAP_EXCLUSIVE per page of PMD-mapped THPs

Message ID 20240607122357.115423-4-david@redhat.com (mailing list archive)
State New
Headers show
Series fs/proc: move page_mapcount() to fs/proc/internal.h | expand

Commit Message

David Hildenbrand June 7, 2024, 12:23 p.m. UTC 
We added PM_MMAP_EXCLUSIVE in 2015 via commit 77bb499bb60f ("pagemap: add
mmap-exclusive bit for marking pages mapped only here"), when THPs could
not be partially mapped and page_mapcount() returned something
that was true for all pages of the THP.

In 2016, we added support for partially mapping THPs via
commit 53f9263baba6 ("mm: rework mapcount accounting to enable 4k mapping
of THPs") but missed to determine PM_MMAP_EXCLUSIVE as well per page.

Checking page_mapcount() on the head page does not tell the whole story.

We should check each individual page. In a future without per-page
mapcounts it will be different, but we'll change that to be consistent
with PTE-mapped THPs once we deal with that.

Fixes: 53f9263baba6 ("mm: rework mapcount accounting to enable 4k mapping of THPs")
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 fs/proc/task_mmu.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

Comments

Oscar Salvador June 10, 2024, 4:51 a.m. UTC | #1 
On Fri, Jun 07, 2024 at 02:23:54PM +0200, David Hildenbrand wrote:
> We added PM_MMAP_EXCLUSIVE in 2015 via commit 77bb499bb60f ("pagemap: add
> mmap-exclusive bit for marking pages mapped only here"), when THPs could
> not be partially mapped and page_mapcount() returned something
> that was true for all pages of the THP.
> 
> In 2016, we added support for partially mapping THPs via
> commit 53f9263baba6 ("mm: rework mapcount accounting to enable 4k mapping
> of THPs") but missed to determine PM_MMAP_EXCLUSIVE as well per page.
> 
> Checking page_mapcount() on the head page does not tell the whole story.
> 
> We should check each individual page. In a future without per-page
> mapcounts it will be different, but we'll change that to be consistent
> with PTE-mapped THPs once we deal with that.
> 
> Fixes: 53f9263baba6 ("mm: rework mapcount accounting to enable 4k mapping of THPs")
> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Signed-off-by: David Hildenbrand <david@redhat.com>

Reviewed-by: Oscar Salvador <osalvador@suse.de>
diff mbox series

Patch

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 40e38bc33a9d2..f427176ce2c34 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1474,6 +1474,7 @@  static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 	ptl = pmd_trans_huge_lock(pmdp, vma);
 	if (ptl) {
+		unsigned int idx = (addr & ~PMD_MASK) >> PAGE_SHIFT;
 		u64 flags = 0, frame = 0;
 		pmd_t pmd = *pmdp;
 		struct page *page = NULL;
@@ -1490,8 +1491,7 @@  static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			if (pmd_uffd_wp(pmd))
 				flags |= PM_UFFD_WP;
 			if (pm->show_pfn)
-				frame = pmd_pfn(pmd) +
-					((addr & ~PMD_MASK) >> PAGE_SHIFT);
+				frame = pmd_pfn(pmd) + idx;
 		}
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 		else if (is_swap_pmd(pmd)) {
@@ -1500,11 +1500,9 @@  static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 			if (pm->show_pfn) {
 				if (is_pfn_swap_entry(entry))
-					offset = swp_offset_pfn(entry);
+					offset = swp_offset_pfn(entry) + idx;
 				else
-					offset = swp_offset(entry);
-				offset = offset +
-					((addr & ~PMD_MASK) >> PAGE_SHIFT);
+					offset = swp_offset(entry) + idx;
 				frame = swp_type(entry) |
 					(offset << MAX_SWAPFILES_SHIFT);
 			}
@@ -1520,12 +1518,16 @@  static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 		if (page && !PageAnon(page))
 			flags |= PM_FILE;
-		if (page && (flags & PM_PRESENT) && page_mapcount(page) == 1)
-			flags |= PM_MMAP_EXCLUSIVE;
 
-		for (; addr != end; addr += PAGE_SIZE) {
-			pagemap_entry_t pme = make_pme(frame, flags);
+		for (; addr != end; addr += PAGE_SIZE, idx++) {
+			unsigned long cur_flags = flags;
+			pagemap_entry_t pme;
+
+			if (page && (flags & PM_PRESENT) &&
+			    page_mapcount(page + idx) == 1)
+				cur_flags |= PM_MMAP_EXCLUSIVE;
 
+			pme = make_pme(frame, cur_flags);
 			err = add_to_pagemap(&pme, pm);
 			if (err)
 				break;