[PATCH v3 0/6] Fix some bugs related to ramp and dax

[PATCH v3 0/6] Fix some bugs related to ramp and dax

[Muchun Song]

This series is based on next-20220225.

Patch 1-2 fix a cache flush bug, because subsequent patches depend on
those on those changes, there are placed in this series.  Patch 3-4
are preparation for fixing a dax bug in patch 5.  Patch 6 is code cleanup
since the previous patch remove the usage of follow_invalidate_pte().

v3:
- Based on next-20220225.

v2:
- Avoid the overly long line in lots of places suggested by Christoph.
- Fix a compiler warning reported by kernel test robot since pmd_pfn()
  is not defined when !CONFIG_TRANSPARENT_HUGEPAGE on powerpc architecture.
- Split a new patch 4 for preparation of fixing the dax bug.

Muchun Song (6):
  mm: rmap: fix cache flush on THP pages
  dax: fix cache flush on PMD-mapped pages
  mm: rmap: introduce pfn_mkclean_range() to cleans PTEs
  mm: pvmw: add support for walking devmap pages
  dax: fix missing writeprotect the pte entry
  mm: remove range parameter from follow_invalidate_pte()

 fs/dax.c             | 82 +++++-----------------------------------------------
 include/linux/mm.h   |  3 --
 include/linux/rmap.h |  3 ++
 mm/internal.h        | 26 +++++++++++------
 mm/memory.c          | 23 ++-------------
 mm/page_vma_mapped.c |  4 +--
 mm/rmap.c            | 68 +++++++++++++++++++++++++++++++++++--------
 7 files changed, 88 insertions(+), 121 deletions(-)

-- 
2.11.0

[PATCH v3 1/6] mm: rmap: fix cache flush on THP pages

[Muchun Song]

The flush_cache_page() only remove a PAGE_SIZE sized range from the cache.
However, it does not cover the full pages in a THP except a head page.
Replace it with flush_cache_range() to fix this issue. At least, no
problems were found due to this. Maybe because the architectures that
have virtual indexed caches is less.

Fixes: f27176cfc363 ("mm: convert page_mkclean_one() to use page_vma_mapped_walk()")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
---
 mm/rmap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index fc46a3d7b704..723682ddb9e8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -970,7 +970,8 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
 				continue;
 
-			flush_cache_page(vma, address, folio_pfn(folio));
+			flush_cache_range(vma, address,
+					  address + HPAGE_PMD_SIZE);
 			entry = pmdp_invalidate(vma, address, pmd);
 			entry = pmd_wrprotect(entry);
 			entry = pmd_mkclean(entry);
-- 
2.11.0

[PATCH v3 2/6] dax: fix cache flush on PMD-mapped pages

[Muchun Song]

The flush_cache_page() only remove a PAGE_SIZE sized range from the cache.
However, it does not cover the full pages in a THP except a head page.
Replace it with flush_cache_range() to fix this issue.

Fixes: f729c8c9b24f ("dax: wrprotect pmd_t in dax_mapping_entry_mkclean")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 fs/dax.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/dax.c b/fs/dax.c
index 67a08a32fccb..a372304c9695 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -845,7 +845,8 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
 			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
 				goto unlock_pmd;
 
-			flush_cache_page(vma, address, pfn);
+			flush_cache_range(vma, address,
+					  address + HPAGE_PMD_SIZE);
 			pmd = pmdp_invalidate(vma, address, pmdp);
 			pmd = pmd_wrprotect(pmd);
 			pmd = pmd_mkclean(pmd);
-- 
2.11.0

[PATCH v3 3/6] mm: rmap: introduce pfn_mkclean_range() to cleans PTEs

[Muchun Song]

The page_mkclean_one() is supposed to be used with the pfn that has a
associated struct page, but not all the pfns (e.g. DAX) have a struct
page. Introduce a new function pfn_mkclean_range() to cleans the PTEs
(including PMDs) mapped with range of pfns which has no struct page
associated with them. This helper will be used by DAX device in the
next patch to make pfns clean.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/rmap.h |  3 +++
 mm/internal.h        | 26 +++++++++++++--------
 mm/rmap.c            | 65 +++++++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 74 insertions(+), 20 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index b58ddb8b2220..a6ec0d3e40c1 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -263,6 +263,9 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
  */
 int folio_mkclean(struct folio *);
 
+int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
+		      struct vm_area_struct *vma);
+
 void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);
 
 /*
diff --git a/mm/internal.h b/mm/internal.h
index f45292dc4ef5..ff873944749f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -516,26 +516,22 @@ void mlock_page_drain(int cpu);
 extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 
 /*
- * At what user virtual address is page expected in vma?
- * Returns -EFAULT if all of the page is outside the range of vma.
- * If page is a compound head, the entire compound page is considered.
+ * * Return the start of user virtual address at the specific offset within
+ * a vma.
  */
 static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
+vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
+		  struct vm_area_struct *vma)
 {
-	pgoff_t pgoff;
 	unsigned long address;
 
-	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
-	pgoff = page_to_pgoff(page);
 	if (pgoff >= vma->vm_pgoff) {
 		address = vma->vm_start +
 			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 		/* Check for address beyond vma (or wrapped through 0?) */
 		if (address < vma->vm_start || address >= vma->vm_end)
 			address = -EFAULT;
-	} else if (PageHead(page) &&
-		   pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+	} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
 		/* Test above avoids possibility of wrap to 0 on 32-bit */
 		address = vma->vm_start;
 	} else {
@@ -545,6 +541,18 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 }
 
 /*
+ * Return the start of user virtual address of a page within a vma.
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
+ */
+static inline unsigned long
+vma_address(struct page *page, struct vm_area_struct *vma)
+{
+	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
+	return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma);
+}
+
+/*
  * Then at what user virtual address will none of the range be found in vma?
  * Assumes that vma_address() already returned a good starting address.
  */
diff --git a/mm/rmap.c b/mm/rmap.c
index 723682ddb9e8..ad5cf0e45a73 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -929,12 +929,12 @@ int folio_referenced(struct folio *folio, int is_locked,
 	return pra.referenced;
 }
 
-static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
-			    unsigned long address, void *arg)
+static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
 {
-	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+	int cleaned = 0;
+	struct vm_area_struct *vma = pvmw->vma;
 	struct mmu_notifier_range range;
-	int *cleaned = arg;
+	unsigned long address = pvmw->address;
 
 	/*
 	 * We have to assume the worse case ie pmd for invalidation. Note that
@@ -942,16 +942,16 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 	 */
 	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
 				0, vma, vma->vm_mm, address,
-				vma_address_end(&pvmw));
+				vma_address_end(pvmw));
 	mmu_notifier_invalidate_range_start(&range);
 
-	while (page_vma_mapped_walk(&pvmw)) {
+	while (page_vma_mapped_walk(pvmw)) {
 		int ret = 0;
 
-		address = pvmw.address;
-		if (pvmw.pte) {
+		address = pvmw->address;
+		if (pvmw->pte) {
 			pte_t entry;
-			pte_t *pte = pvmw.pte;
+			pte_t *pte = pvmw->pte;
 
 			if (!pte_dirty(*pte) && !pte_write(*pte))
 				continue;
@@ -964,7 +964,7 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 			ret = 1;
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			pmd_t *pmd = pvmw.pmd;
+			pmd_t *pmd = pvmw->pmd;
 			pmd_t entry;
 
 			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
@@ -991,11 +991,22 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		if (ret)
-			(*cleaned)++;
+			cleaned++;
 	}
 
 	mmu_notifier_invalidate_range_end(&range);
 
+	return cleaned;
+}
+
+static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
+			     unsigned long address, void *arg)
+{
+	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+	int *cleaned = arg;
+
+	*cleaned += page_vma_mkclean_one(&pvmw);
+
 	return true;
 }
 
@@ -1033,6 +1044,38 @@ int folio_mkclean(struct folio *folio)
 EXPORT_SYMBOL_GPL(folio_mkclean);
 
 /**
+ * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
+ *                     [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
+ *                     within the @vma of shared mappings. And since clean PTEs
+ *                     should also be readonly, write protects them too.
+ * @pfn: start pfn.
+ * @nr_pages: number of physically contiguous pages srarting with @pfn.
+ * @pgoff: page offset that the @pfn mapped with.
+ * @vma: vma that @pfn mapped within.
+ *
+ * Returns the number of cleaned PTEs (including PMDs).
+ */
+int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
+		      struct vm_area_struct *vma)
+{
+	struct page_vma_mapped_walk pvmw = {
+		.pfn		= pfn,
+		.nr_pages	= nr_pages,
+		.pgoff		= pgoff,
+		.vma		= vma,
+		.flags		= PVMW_SYNC,
+	};
+
+	if (invalid_mkclean_vma(vma, NULL))
+		return 0;
+
+	pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma);
+	VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma);
+
+	return page_vma_mkclean_one(&pvmw);
+}
+
+/**
  * page_move_anon_rmap - move a page to our anon_vma
  * @page:	the page to move to our anon_vma
  * @vma:	the vma the page belongs to
-- 
2.11.0

[PATCH v3 4/6] mm: pvmw: add support for walking devmap pages

[Muchun Song]

The devmap pages can not use page_vma_mapped_walk() to check if a huge
devmap page is mapped into a vma.  Add support for walking huge devmap
pages so that DAX can use it in the next patch.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/page_vma_mapped.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 1187f9c1ec5b..3f337e4e7f5f 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -210,10 +210,10 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 		 */
 		pmde = READ_ONCE(*pvmw->pmd);
 
-		if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
+		if (pmd_leaf(pmde) || is_pmd_migration_entry(pmde)) {
 			pvmw->ptl = pmd_lock(mm, pvmw->pmd);
 			pmde = *pvmw->pmd;
-			if (likely(pmd_trans_huge(pmde))) {
+			if (likely(pmd_leaf(pmde))) {
 				if (pvmw->flags & PVMW_MIGRATION)
 					return not_found(pvmw);
 				if (!check_pmd(pmd_pfn(pmde), pvmw))
-- 
2.11.0

Re: [PATCH v3 4/6] mm: pvmw: add support for walking devmap pages

[kernel test robot]

Hi Muchun,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on hnaz-mm/master]
[also build test ERROR on next-20220225]
[cannot apply to linus/master v5.17-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Muchun-Song/Fix-some-bugs-related-to-ramp-and-dax/20220228-143753
base:   https://github.com/hnaz/linux-mm master
config: riscv-randconfig-r012-20220227 (https://download.01.org/0day-ci/archive/20220228/202202281913.ZakSkynK-lkp@intel.com/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project d271fc04d5b97b12e6b797c6067d3c96a8d7470e)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install riscv cross compiling tool for clang build
        # apt-get install binutils-riscv64-linux-gnu
        # https://github.com/0day-ci/linux/commit/4b08af172f30c61ae5f43ec23642e2767371247e
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Muchun-Song/Fix-some-bugs-related-to-ramp-and-dax/20220228-143753
        git checkout 4b08af172f30c61ae5f43ec23642e2767371247e
        # save the config file to linux build tree
        mkdir build_dir
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=riscv SHELL=/bin/bash

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> mm/page_vma_mapped.c:113:13: error: call to __compiletime_assert_258 declared with 'error' attribute: BUILD_BUG failed
           if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn)
                      ^
   include/linux/huge_mm.h:105:26: note: expanded from macro 'HPAGE_PMD_NR'
   #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
                            ^
   include/linux/huge_mm.h:104:26: note: expanded from macro 'HPAGE_PMD_ORDER'
   #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
                            ^
   include/linux/huge_mm.h:307:28: note: expanded from macro 'HPAGE_PMD_SHIFT'
   #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
                              ^
   note: (skipping 3 expansions in backtrace; use -fmacro-backtrace-limit=0 to see all)
   include/linux/compiler_types.h:335:2: note: expanded from macro '_compiletime_assert'
           __compiletime_assert(condition, msg, prefix, suffix)
           ^
   include/linux/compiler_types.h:328:4: note: expanded from macro '__compiletime_assert'
                           prefix ## suffix();                             \
                           ^
   <scratch space>:73:1: note: expanded from here
   __compiletime_assert_258
   ^
   1 error generated.


vim +/error +113 mm/page_vma_mapped.c

9188af981d385d Andrew Morton      2022-02-25  109  
9188af981d385d Andrew Morton      2022-02-25  110  /* Returns true if the two ranges overlap.  Careful to not overflow. */
9188af981d385d Andrew Morton      2022-02-25  111  static bool check_pmd(unsigned long pfn, struct page_vma_mapped_walk *pvmw)
9188af981d385d Andrew Morton      2022-02-25  112  {
9188af981d385d Andrew Morton      2022-02-25 @113  	if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn)
9188af981d385d Andrew Morton      2022-02-25  114  		return false;
9188af981d385d Andrew Morton      2022-02-25  115  	if (pfn > pvmw->pfn + pvmw->nr_pages - 1)
9188af981d385d Andrew Morton      2022-02-25  116  		return false;
9188af981d385d Andrew Morton      2022-02-25  117  	return true;
ace71a19cec5eb Kirill A. Shutemov 2017-02-24  118  }
ace71a19cec5eb Kirill A. Shutemov 2017-02-24  119  

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org

Re: [PATCH v3 4/6] mm: pvmw: add support for walking devmap pages

[Andrew Morton]

On Mon, 28 Feb 2022 14:35:34 +0800 Muchun Song <songmuchun@bytedance.com> wrote:

> The devmap pages can not use page_vma_mapped_walk() to check if a huge
> devmap page is mapped into a vma.  Add support for walking huge devmap
> pages so that DAX can use it in the next patch.
> 

x86_64 allnoconfig:

In file included from <command-line>:
In function 'check_pmd',
    inlined from 'page_vma_mapped_walk' at mm/page_vma_mapped.c:219:10:
././include/linux/compiler_types.h:347:45: error: call to '__compiletime_assert_232' declared with attribute error: BUILD_BUG failed
  347 |         _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
      |                                             ^
././include/linux/compiler_types.h:328:25: note: in definition of macro '__compiletime_assert'
  328 |                         prefix ## suffix();                             \
      |                         ^~~~~~
././include/linux/compiler_types.h:347:9: note: in expansion of macro '_compiletime_assert'
  347 |         _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
      |         ^~~~~~~~~~~~~~~~~~~
./include/linux/build_bug.h:39:37: note: in expansion of macro 'compiletime_assert'
   39 | #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
      |                                     ^~~~~~~~~~~~~~~~~~
./include/linux/build_bug.h:59:21: note: in expansion of macro 'BUILD_BUG_ON_MSG'
   59 | #define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
      |                     ^~~~~~~~~~~~~~~~
./include/linux/huge_mm.h:307:28: note: in expansion of macro 'BUILD_BUG'
  307 | #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
      |                            ^~~~~~~~~
./include/linux/huge_mm.h:104:26: note: in expansion of macro 'HPAGE_PMD_SHIFT'
  104 | #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
      |                          ^~~~~~~~~~~~~~~
./include/linux/huge_mm.h:105:26: note: in expansion of macro 'HPAGE_PMD_ORDER'
  105 | #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
      |                          ^~~~~~~~~~~~~~~
mm/page_vma_mapped.c:113:20: note: in expansion of macro 'HPAGE_PMD_NR'
  113 |         if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn)
      |                    ^~~~~~~~~~~~
make[1]: *** [scripts/Makefile.build:288: mm/page_vma_mapped.o] Error 1
make: *** [Makefile:1971: mm] Error 2


because check_pmd() uses HPAGE_PMD_NR and

#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })

I don't immediately see why this patch triggers it...

Re: [PATCH v3 4/6] mm: pvmw: add support for walking devmap pages

[Muchun Song]

On Tue, Mar 1, 2022 at 5:26 AM Andrew Morton <akpm@linux-foundation.org> wrote:
>
> On Mon, 28 Feb 2022 14:35:34 +0800 Muchun Song <songmuchun@bytedance.com> wrote:
>
> > The devmap pages can not use page_vma_mapped_walk() to check if a huge
> > devmap page is mapped into a vma.  Add support for walking huge devmap
> > pages so that DAX can use it in the next patch.
> >
>
> x86_64 allnoconfig:
>
> In file included from <command-line>:
> In function 'check_pmd',
>     inlined from 'page_vma_mapped_walk' at mm/page_vma_mapped.c:219:10:
> ././include/linux/compiler_types.h:347:45: error: call to '__compiletime_assert_232' declared with attribute error: BUILD_BUG failed
>   347 |         _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
>       |                                             ^
> ././include/linux/compiler_types.h:328:25: note: in definition of macro '__compiletime_assert'
>   328 |                         prefix ## suffix();                             \
>       |                         ^~~~~~
> ././include/linux/compiler_types.h:347:9: note: in expansion of macro '_compiletime_assert'
>   347 |         _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
>       |         ^~~~~~~~~~~~~~~~~~~
> ./include/linux/build_bug.h:39:37: note: in expansion of macro 'compiletime_assert'
>    39 | #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
>       |                                     ^~~~~~~~~~~~~~~~~~
> ./include/linux/build_bug.h:59:21: note: in expansion of macro 'BUILD_BUG_ON_MSG'
>    59 | #define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
>       |                     ^~~~~~~~~~~~~~~~
> ./include/linux/huge_mm.h:307:28: note: in expansion of macro 'BUILD_BUG'
>   307 | #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
>       |                            ^~~~~~~~~
> ./include/linux/huge_mm.h:104:26: note: in expansion of macro 'HPAGE_PMD_SHIFT'
>   104 | #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
>       |                          ^~~~~~~~~~~~~~~
> ./include/linux/huge_mm.h:105:26: note: in expansion of macro 'HPAGE_PMD_ORDER'
>   105 | #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
>       |                          ^~~~~~~~~~~~~~~
> mm/page_vma_mapped.c:113:20: note: in expansion of macro 'HPAGE_PMD_NR'
>   113 |         if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn)
>       |                    ^~~~~~~~~~~~
> make[1]: *** [scripts/Makefile.build:288: mm/page_vma_mapped.o] Error 1
> make: *** [Makefile:1971: mm] Error 2
>
>
> because check_pmd() uses HPAGE_PMD_NR and
>
> #else /* CONFIG_TRANSPARENT_HUGEPAGE */
> #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
>
> I don't immediately see why this patch triggers it...

Maybe the reason is as follows.

The first check_pmd() is wrapped inside `if (pmd_trans_huge(pmde))`
block, since pmd_trans_huge() just returns 0, check_pmd() will be
optimized out.  There is a `if (!thp_migration_supported()) return;` block
before the second check_pmd(), however, thp_migration_supported()
returns 0 on riscv. So the second check_pmd() can be optimized out as
well.  I think I should replace `pmd_leaf` with `pmd_trans_huge() ||
pmd_devmap()`
to fix it.

Thanks.

[PATCH v3 5/6] dax: fix missing writeprotect the pte entry

[Muchun Song]

Currently dax_mapping_entry_mkclean() fails to clean and write protect
the pte entry within a DAX PMD entry during an *sync operation. This
can result in data loss in the following sequence:

  1) process A mmap write to DAX PMD, dirtying PMD radix tree entry and
     making the pmd entry dirty and writeable.
  2) process B mmap with the @offset (e.g. 4K) and @length (e.g. 4K)
     write to the same file, dirtying PMD radix tree entry (already
     done in 1)) and making the pte entry dirty and writeable.
  3) fsync, flushing out PMD data and cleaning the radix tree entry. We
     currently fail to mark the pte entry as clean and write protected
     since the vma of process B is not covered in dax_entry_mkclean().
  4) process B writes to the pte. These don't cause any page faults since
     the pte entry is dirty and writeable. The radix tree entry remains
     clean.
  5) fsync, which fails to flush the dirty PMD data because the radix tree
     entry was clean.
  6) crash - dirty data that should have been fsync'd as part of 5) could
     still have been in the processor cache, and is lost.

Just to use pfn_mkclean_range() to clean the pfns to fix this issue.

Fixes: 4b4bb46d00b3 ("dax: clear dirty entry tags on cache flush")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 fs/dax.c | 83 ++++++----------------------------------------------------------
 1 file changed, 7 insertions(+), 76 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index a372304c9695..7fd4a16769f9 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -24,6 +24,7 @@
 #include <linux/sizes.h>
 #include <linux/mmu_notifier.h>
 #include <linux/iomap.h>
+#include <linux/rmap.h>
 #include <asm/pgalloc.h>
 
 #define CREATE_TRACE_POINTS
@@ -789,87 +790,17 @@ static void *dax_insert_entry(struct xa_state *xas,
 	return entry;
 }
 
-static inline
-unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
-{
-	unsigned long address;
-
-	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
-	return address;
-}
-
 /* Walk all mappings of a given index of a file and writeprotect them */
-static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
-		unsigned long pfn)
+static void dax_entry_mkclean(struct address_space *mapping, unsigned long pfn,
+			      unsigned long npfn, pgoff_t start)
 {
 	struct vm_area_struct *vma;
-	pte_t pte, *ptep = NULL;
-	pmd_t *pmdp = NULL;
-	spinlock_t *ptl;
+	pgoff_t end = start + npfn - 1;
 
 	i_mmap_lock_read(mapping);
-	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
-		struct mmu_notifier_range range;
-		unsigned long address;
-
+	vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) {
+		pfn_mkclean_range(pfn, npfn, start, vma);
 		cond_resched();
-
-		if (!(vma->vm_flags & VM_SHARED))
-			continue;
-
-		address = pgoff_address(index, vma);
-
-		/*
-		 * follow_invalidate_pte() will use the range to call
-		 * mmu_notifier_invalidate_range_start() on our behalf before
-		 * taking any lock.
-		 */
-		if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep,
-					  &pmdp, &ptl))
-			continue;
-
-		/*
-		 * No need to call mmu_notifier_invalidate_range() as we are
-		 * downgrading page table protection not changing it to point
-		 * to a new page.
-		 *
-		 * See Documentation/vm/mmu_notifier.rst
-		 */
-		if (pmdp) {
-#ifdef CONFIG_FS_DAX_PMD
-			pmd_t pmd;
-
-			if (pfn != pmd_pfn(*pmdp))
-				goto unlock_pmd;
-			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
-				goto unlock_pmd;
-
-			flush_cache_range(vma, address,
-					  address + HPAGE_PMD_SIZE);
-			pmd = pmdp_invalidate(vma, address, pmdp);
-			pmd = pmd_wrprotect(pmd);
-			pmd = pmd_mkclean(pmd);
-			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
-unlock_pmd:
-#endif
-			spin_unlock(ptl);
-		} else {
-			if (pfn != pte_pfn(*ptep))
-				goto unlock_pte;
-			if (!pte_dirty(*ptep) && !pte_write(*ptep))
-				goto unlock_pte;
-
-			flush_cache_page(vma, address, pfn);
-			pte = ptep_clear_flush(vma, address, ptep);
-			pte = pte_wrprotect(pte);
-			pte = pte_mkclean(pte);
-			set_pte_at(vma->vm_mm, address, ptep, pte);
-unlock_pte:
-			pte_unmap_unlock(ptep, ptl);
-		}
-
-		mmu_notifier_invalidate_range_end(&range);
 	}
 	i_mmap_unlock_read(mapping);
 }
@@ -937,7 +868,7 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
 	count = 1UL << dax_entry_order(entry);
 	index = xas->xa_index & ~(count - 1);
 
-	dax_entry_mkclean(mapping, index, pfn);
+	dax_entry_mkclean(mapping, pfn, count, index);
 	dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
 	/*
 	 * After we have flushed the cache, we can clear the dirty tag. There
-- 
2.11.0

[PATCH v3 6/6] mm: remove range parameter from follow_invalidate_pte()

[Muchun Song]

The only user (DAX) of range parameter of follow_invalidate_pte()
is gone, it safe to remove the range paramter and make it static
to simlify the code.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/mm.h |  3 ---
 mm/memory.c        | 23 +++--------------------
 2 files changed, 3 insertions(+), 23 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c9bada4096ac..be7ec4c37ebe 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1871,9 +1871,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
-			  struct mmu_notifier_range *range, pte_t **ptepp,
-			  pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pte(struct mm_struct *mm, unsigned long address,
 	       pte_t **ptepp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
diff --git a/mm/memory.c b/mm/memory.c
index cc6968dc8e4e..278ab6d62b54 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4964,9 +4964,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
-			  struct mmu_notifier_range *range, pte_t **ptepp,
-			  pmd_t **pmdpp, spinlock_t **ptlp)
+static int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
+				 pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4993,31 +4992,17 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
 		if (!pmdpp)
 			goto out;
 
-		if (range) {
-			mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0,
-						NULL, mm, address & PMD_MASK,
-						(address & PMD_MASK) + PMD_SIZE);
-			mmu_notifier_invalidate_range_start(range);
-		}
 		*ptlp = pmd_lock(mm, pmd);
 		if (pmd_huge(*pmd)) {
 			*pmdpp = pmd;
 			return 0;
 		}
 		spin_unlock(*ptlp);
-		if (range)
-			mmu_notifier_invalidate_range_end(range);
 	}
 
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
-	if (range) {
-		mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
-					address & PAGE_MASK,
-					(address & PAGE_MASK) + PAGE_SIZE);
-		mmu_notifier_invalidate_range_start(range);
-	}
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
 	if (!pte_present(*ptep))
 		goto unlock;
@@ -5025,8 +5010,6 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
 	return 0;
 unlock:
 	pte_unmap_unlock(ptep, *ptlp);
-	if (range)
-		mmu_notifier_invalidate_range_end(range);
 out:
 	return -EINVAL;
 }
@@ -5055,7 +5038,7 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
 int follow_pte(struct mm_struct *mm, unsigned long address,
 	       pte_t **ptepp, spinlock_t **ptlp)
 {
-	return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp);
+	return follow_invalidate_pte(mm, address, ptepp, NULL, ptlp);
 }
 EXPORT_SYMBOL_GPL(follow_pte);
 
-- 
2.11.0