diff mbox series

[v4,1/4] hugetlb: Pass vma into huge_pte_alloc() and huge_pmd_share()

Message ID 20210218230633.15028-2-peterx@redhat.com (mailing list archive)
State New, archived
Headers show
Series hugetlb: Disable huge pmd unshare for uffd-wp | expand

Commit Message

Peter Xu Feb. 18, 2021, 11:06 p.m. UTC
It is a preparation work to be able to behave differently in the per
architecture huge_pte_alloc() according to different VMA attributes.

Pass it deeper into huge_pmd_share() so that we can avoid the find_vma() call.

Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 arch/arm64/mm/hugetlbpage.c   |  4 ++--
 arch/ia64/mm/hugetlbpage.c    |  3 ++-
 arch/mips/mm/hugetlbpage.c    |  4 ++--
 arch/parisc/mm/hugetlbpage.c  |  2 +-
 arch/powerpc/mm/hugetlbpage.c |  3 ++-
 arch/s390/mm/hugetlbpage.c    |  2 +-
 arch/sh/mm/hugetlbpage.c      |  2 +-
 arch/sparc/mm/hugetlbpage.c   |  2 +-
 include/linux/hugetlb.h       |  5 +++--
 mm/hugetlb.c                  | 15 ++++++++-------
 mm/userfaultfd.c              |  2 +-
 11 files changed, 24 insertions(+), 20 deletions(-)

Comments

kernel test robot March 4, 2021, 4:31 p.m. UTC | #1
Hi Peter,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on arm64/for-next/core]
[also build test ERROR on linux/master linus/master v5.12-rc1 next-20210304]
[cannot apply to hnaz-linux-mm/master]
[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/Peter-Xu/hugetlb-Disable-huge-pmd-unshare-for-uffd-wp/20210219-071334
base:   https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
config: mips-randconfig-m031-20210304 (attached as .config)
compiler: mipsel-linux-gcc (GCC) 9.3.0
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
        # https://github.com/0day-ci/linux/commit/7ede06d6f63e59db4b9dee54f78eeac0c9ca17e4
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Peter-Xu/hugetlb-Disable-huge-pmd-unshare-for-uffd-wp/20210219-071334
        git checkout 7ede06d6f63e59db4b9dee54f78eeac0c9ca17e4
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=mips 

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/hugetlb.c:5376:8: error: conflicting types for 'huge_pmd_share'
    5376 | pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
         |        ^~~~~~~~~~~~~~
   In file included from mm/hugetlb.c:39:
   include/linux/hugetlb.h:155:8: note: previous declaration of 'huge_pmd_share' was here
     155 | pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
         |        ^~~~~~~~~~~~~~


vim +/huge_pmd_share +5376 mm/hugetlb.c

  5343	
  5344	/*
  5345	 * unmap huge page backed by shared pte.
  5346	 *
  5347	 * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
  5348	 * indicated by page_count > 1, unmap is achieved by clearing pud and
  5349	 * decrementing the ref count. If count == 1, the pte page is not shared.
  5350	 *
  5351	 * Called with page table lock held and i_mmap_rwsem held in write mode.
  5352	 *
  5353	 * returns: 1 successfully unmapped a shared pte page
  5354	 *	    0 the underlying pte page is not shared, or it is the last user
  5355	 */
  5356	int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
  5357						unsigned long *addr, pte_t *ptep)
  5358	{
  5359		pgd_t *pgd = pgd_offset(mm, *addr);
  5360		p4d_t *p4d = p4d_offset(pgd, *addr);
  5361		pud_t *pud = pud_offset(p4d, *addr);
  5362	
  5363		i_mmap_assert_write_locked(vma->vm_file->f_mapping);
  5364		BUG_ON(page_count(virt_to_page(ptep)) == 0);
  5365		if (page_count(virt_to_page(ptep)) == 1)
  5366			return 0;
  5367	
  5368		pud_clear(pud);
  5369		put_page(virt_to_page(ptep));
  5370		mm_dec_nr_pmds(mm);
  5371		*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
  5372		return 1;
  5373	}
  5374	#define want_pmd_share()	(1)
  5375	#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
> 5376	pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
  5377			      unsigned long addr, pud_t *pud)
  5378	{
  5379		return NULL;
  5380	}
  5381	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
Peter Xu March 4, 2021, 4:46 p.m. UTC | #2
On Fri, Mar 05, 2021 at 12:31:00AM +0800, kernel test robot wrote:
> Hi Peter,
> 
> Thank you for the patch! Yet something to improve:
> 
> [auto build test ERROR on arm64/for-next/core]
> [also build test ERROR on linux/master linus/master v5.12-rc1 next-20210304]
> [cannot apply to hnaz-linux-mm/master]
> [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/Peter-Xu/hugetlb-Disable-huge-pmd-unshare-for-uffd-wp/20210219-071334
> base:   https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
> config: mips-randconfig-m031-20210304 (attached as .config)
> compiler: mipsel-linux-gcc (GCC) 9.3.0
> 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
>         # https://github.com/0day-ci/linux/commit/7ede06d6f63e59db4b9dee54f78eeac0c9ca17e4
>         git remote add linux-review https://github.com/0day-ci/linux
>         git fetch --no-tags linux-review Peter-Xu/hugetlb-Disable-huge-pmd-unshare-for-uffd-wp/20210219-071334
>         git checkout 7ede06d6f63e59db4b9dee54f78eeac0c9ca17e4
>         # save the attached .config to linux build tree
>         COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=mips 
> 
> 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/hugetlb.c:5376:8: error: conflicting types for 'huge_pmd_share'
>     5376 | pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
>          |        ^~~~~~~~~~~~~~
>    In file included from mm/hugetlb.c:39:
>    include/linux/hugetlb.h:155:8: note: previous declaration of 'huge_pmd_share' was here
>      155 | pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
>          |        ^~~~~~~~~~~~~~
> 
> 
> vim +/huge_pmd_share +5376 mm/hugetlb.c
> 
>   5343	
>   5344	/*
>   5345	 * unmap huge page backed by shared pte.
>   5346	 *
>   5347	 * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
>   5348	 * indicated by page_count > 1, unmap is achieved by clearing pud and
>   5349	 * decrementing the ref count. If count == 1, the pte page is not shared.
>   5350	 *
>   5351	 * Called with page table lock held and i_mmap_rwsem held in write mode.
>   5352	 *
>   5353	 * returns: 1 successfully unmapped a shared pte page
>   5354	 *	    0 the underlying pte page is not shared, or it is the last user
>   5355	 */
>   5356	int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
>   5357						unsigned long *addr, pte_t *ptep)
>   5358	{
>   5359		pgd_t *pgd = pgd_offset(mm, *addr);
>   5360		p4d_t *p4d = p4d_offset(pgd, *addr);
>   5361		pud_t *pud = pud_offset(p4d, *addr);
>   5362	
>   5363		i_mmap_assert_write_locked(vma->vm_file->f_mapping);
>   5364		BUG_ON(page_count(virt_to_page(ptep)) == 0);
>   5365		if (page_count(virt_to_page(ptep)) == 1)
>   5366			return 0;
>   5367	
>   5368		pud_clear(pud);
>   5369		put_page(virt_to_page(ptep));
>   5370		mm_dec_nr_pmds(mm);
>   5371		*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
>   5372		return 1;
>   5373	}
>   5374	#define want_pmd_share()	(1)
>   5375	#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
> > 5376	pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
>   5377			      unsigned long addr, pud_t *pud)
>   5378	{
>   5379		return NULL;
>   5380	}
>   5381	

Sorry for this!  I think we need to squash below into this patch for
!CONFIG_ARCH_WANT_HUGE_PMD_SHARE:

-----8<-----
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fc62932c31cb..94ac419f88cd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5415,7 +5415,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
-pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
                      unsigned long addr, pud_t *pud)
 {
        return NULL;
-----8<-----

Andrew, please kindly let me know when a repost is needed.

Thanks,
diff mbox series

Patch

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 55ecf6de9ff7..6e3bcffe2837 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -252,7 +252,7 @@  void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 		set_pte(ptep, pte);
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
@@ -286,7 +286,7 @@  pte_t *huge_pte_alloc(struct mm_struct *mm,
 	} else if (sz == PMD_SIZE) {
 		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
 		    pud_none(READ_ONCE(*pudp)))
-			ptep = huge_pmd_share(mm, addr, pudp);
+			ptep = huge_pmd_share(mm, vma, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
 	} else if (sz == (CONT_PMD_SIZE)) {
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index b331f94d20ac..f993cb36c062 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -25,7 +25,8 @@  unsigned int hpage_shift = HPAGE_SHIFT_DEFAULT;
 EXPORT_SYMBOL(hpage_shift);
 
 pte_t *
-huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+	       unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index b9f76f433617..7eaff5b07873 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -21,8 +21,8 @@ 
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr,
-		      unsigned long sz)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index d7ba014a7fbb..e141441bfa64 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -44,7 +44,7 @@  hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 }
 
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8b3cc4d688e8..d57276b8791c 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -106,7 +106,8 @@  static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
  * At this point we do the placement change only for BOOK3S 64. This would
  * possibly work on other subarchs.
  */
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pg;
 	p4d_t *p4;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 3b5a4d25ca9b..da36d13ffc16 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -189,7 +189,7 @@  pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 220d7bc43d2b..999ab5916e69 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -21,7 +21,7 @@ 
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index ad4b42f04988..04d8790f6c32 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -279,7 +279,7 @@  unsigned long pud_leaf_size(pud_t pud) { return 1UL << tte_to_shift(*(pte_t *)&p
 unsigned long pmd_leaf_size(pmd_t pmd) { return 1UL << tte_to_shift(*(pte_t *)&pmd); }
 unsigned long pte_leaf_size(pte_t pte) { return 1UL << tte_to_shift(pte); }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b5807f23caf8..a6113fa6d21d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -152,7 +152,8 @@  void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
 u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
 
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud);
 
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage);
 
@@ -161,7 +162,7 @@  extern struct list_head huge_boot_pages;
 
 /* arch callbacks */
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4bdb58ab14cb..07bb9bdc3282 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3807,7 +3807,7 @@  int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, addr, sz);
+		dst_pte = huge_pte_alloc(dst, vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
 			break;
@@ -4544,7 +4544,7 @@  vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	mapping = vma->vm_file->f_mapping;
 	i_mmap_lock_read(mapping);
-	ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
+	ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h));
 	if (!ptep) {
 		i_mmap_unlock_read(mapping);
 		return VM_FAULT_OOM;
@@ -5334,9 +5334,9 @@  void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
  * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is
  * only required for subsequent processing.
  */
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud)
 {
-	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
 			vma->vm_pgoff;
@@ -5414,7 +5414,8 @@  int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 #define want_pmd_share()	(1)
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
+		      unsigned long addr, pud_t *pud)
 {
 	return NULL;
 }
@@ -5433,7 +5434,7 @@  void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
 #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
@@ -5452,7 +5453,7 @@  pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (want_pmd_share() && pud_none(*pud))
-				pte = huge_pmd_share(mm, addr, pud);
+				pte = huge_pmd_share(mm, vma, addr, pud);
 			else
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9a3d451402d7..063cbb17e8d8 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -290,7 +290,7 @@  static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		err = -ENOMEM;
-		dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize);
+		dst_pte = huge_pte_alloc(dst_mm, dst_vma, dst_addr, vma_hpagesize);
 		if (!dst_pte) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);