mm: ptep_get() conversion

Convert all instances of direct pte_t* dereferencing to instead use
ptep_get() helper.  This means that by default, the accesses change from a
C dereference to a READ_ONCE().  This is technically the correct thing to
do since where pgtables are modified by HW (for access/dirty) they are
volatile and therefore we should always ensure READ_ONCE() semantics.

But more importantly, by always using the helper, it can be overridden by
the architecture to fully encapsulate the contents of the pte.  Arch code
is deliberately not converted, as the arch code knows best.  It is
intended that arch code (arm64) will override the default with its own
implementation that can (e.g.) hide certain bits from the core code, or
determine young/dirty status by mixing in state from another source.

Conversion was done using Coccinelle:

----

// $ make coccicheck \
//          COCCI=ptepget.cocci \
//          SPFLAGS="--include-headers" \
//          MODE=patch

virtual patch

@ depends on patch @
pte_t *v;
@@

- *v
+ ptep_get(v)

----

Then reviewed and hand-edited to avoid multiple unnecessary calls to
ptep_get(), instead opting to store the result of a single call in a
variable, where it is correct to do so.  This aims to negate any cost of
READ_ONCE() and will benefit arch-overrides that may be more complex.

Included is a fix for an issue in an earlier version of this patch that
was pointed out by kernel test robot.  The issue arose because config
MMU=n elides definition of the ptep helper functions, including
ptep_get().  HUGETLB_PAGE=n configs still define a simple
huge_ptep_clear_flush() for linking purposes, which dereferences the ptep.
So when both configs are disabled, this caused a build error because
ptep_get() is not defined.  Fix by continuing to do a direct dereference
when MMU=n.  This is safe because for this config the arch code cannot be
trying to virtualize the ptes because none of the ptep helpers are
defined.

Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 20 insertions, 14 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index cd918cb9a431..0c0d8857dfce 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -826,7 +826,8 @@ static bool folio_referenced_one(struct folio *folio,
 		}
 
 		if (pvmw.pte) {
-			if (lru_gen_enabled() && pte_young(*pvmw.pte)) {
+			if (lru_gen_enabled() &&
+			    pte_young(ptep_get(pvmw.pte))) {
 				lru_gen_look_around(&pvmw);
 				referenced++;
 			}
@@ -956,13 +957,13 @@ static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
 
 		address = pvmw->address;
 		if (pvmw->pte) {
-			pte_t entry;
 			pte_t *pte = pvmw->pte;
+			pte_t entry = ptep_get(pte);
 
-			if (!pte_dirty(*pte) && !pte_write(*pte))
+			if (!pte_dirty(entry) && !pte_write(entry))
 				continue;
 
-			flush_cache_page(vma, address, pte_pfn(*pte));
+			flush_cache_page(vma, address, pte_pfn(entry));
 			entry = ptep_clear_flush(vma, address, pte);
 			entry = pte_wrprotect(entry);
 			entry = pte_mkclean(entry);
@@ -1137,7 +1138,7 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
  * @folio:	Folio which contains page.
  * @page:	Page to add to rmap.
  * @vma:	VM area to add page to.
- * @address:	User virtual address of the mapping	
+ * @address:	User virtual address of the mapping
  * @exclusive:	the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct folio *folio, struct page *page,
@@ -1458,6 +1459,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 	bool anon_exclusive, ret = true;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
+	unsigned long pfn;
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
@@ -1508,8 +1510,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			break;
 		}
 
-		subpage = folio_page(folio,
-					pte_pfn(*pvmw.pte) - folio_pfn(folio));
+		pfn = pte_pfn(ptep_get(pvmw.pte));
+		subpage = folio_page(folio, pfn - folio_pfn(folio));
 		address = pvmw.address;
 		anon_exclusive = folio_test_anon(folio) &&
 				 PageAnonExclusive(subpage);
@@ -1571,7 +1573,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			}
 			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
 		} else {
-			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+			flush_cache_page(vma, address, pfn);
 			/* Nuke the page table entry. */
 			if (should_defer_flush(mm, flags)) {
 				/*
@@ -1818,6 +1820,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 	bool anon_exclusive, ret = true;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
+	unsigned long pfn;
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
@@ -1877,6 +1880,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		/* Unexpected PMD-mapped THP? */
 		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
 
+		pfn = pte_pfn(ptep_get(pvmw.pte));
+
 		if (folio_is_zone_device(folio)) {
 			/*
 			 * Our PTE is a non-present device exclusive entry and
@@ -1891,8 +1896,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio);
 			subpage = &folio->page;
 		} else {
-			subpage = folio_page(folio,
-					pte_pfn(*pvmw.pte) - folio_pfn(folio));
+			subpage = folio_page(folio, pfn - folio_pfn(folio));
 		}
 		address = pvmw.address;
 		anon_exclusive = folio_test_anon(folio) &&
@@ -1952,7 +1956,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			/* Nuke the hugetlb page table entry */
 			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
 		} else {
-			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+			flush_cache_page(vma, address, pfn);
 			/* Nuke the page table entry. */
 			if (should_defer_flush(mm, flags)) {
 				/*
@@ -2187,6 +2191,7 @@ static bool page_make_device_exclusive_one(struct folio *folio,
 	struct mmu_notifier_range range;
 	swp_entry_t entry;
 	pte_t swp_pte;
+	pte_t ptent;
 
 	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
 				      vma->vm_mm, address, min(vma->vm_end,
@@ -2198,18 +2203,19 @@ static bool page_make_device_exclusive_one(struct folio *folio,
 		/* Unexpected PMD-mapped THP? */
 		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
 
-		if (!pte_present(*pvmw.pte)) {
+		ptent = ptep_get(pvmw.pte);
+		if (!pte_present(ptent)) {
 			ret = false;
 			page_vma_mapped_walk_done(&pvmw);
 			break;
 		}
 
 		subpage = folio_page(folio,
-				pte_pfn(*pvmw.pte) - folio_pfn(folio));
+				pte_pfn(ptent) - folio_pfn(folio));
 		address = pvmw.address;
 
 		/* Nuke the page table entry. */
-		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+		flush_cache_page(vma, address, pte_pfn(ptent));
 		pteval = ptep_clear_flush(vma, address, pvmw.pte);
 
 		/* Set the dirty flag on the folio now the pte is gone. */