mm, thp: remove infrastructure for handling splitting PMDs

With new refcounting we don't need to mark PMDs splitting.  Let's drop
code to handle this.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/proc/task_mmu.c

@@ -602,7 +602,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		smaps_pmd_entry(pmd, addr, walk);
 		spin_unlock(ptl);
 		return 0;
@@ -913,7 +913,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty_pmd(vma, addr, pmd);
 			goto out;
@@ -1187,7 +1187,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 	int err = 0;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmdp, vma, &ptl)) {
 		u64 flags = 0, frame = 0;
 		pmd_t pmd = *pmdp;
 
@@ -1519,7 +1519,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *orig_pte;
 	pte_t *pte;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 

include/asm-generic/pgtable.h

@@ -207,11 +207,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-extern void pmdp_splitting_flush(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp);
-#endif
-
 #ifndef pmdp_collapse_flush
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
@@ -627,10 +622,6 @@ static inline int pmd_trans_huge(pmd_t pmd)
 {
 	return 0;
 }
-static inline int pmd_trans_splitting(pmd_t pmd)
-{
-	return 0;
-}
 #ifndef __HAVE_ARCH_PMD_WRITE
 static inline int pmd_write(pmd_t pmd)
 {

include/linux/huge_mm.h

@@ -25,7 +25,7 @@ extern int zap_huge_pmd(struct mmu_gather *tlb,
 extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned char *vec);
-extern int move_huge_pmd(struct vm_area_struct *vma,
+extern bool move_huge_pmd(struct vm_area_struct *vma,
 			 struct vm_area_struct *new_vma,
 			 unsigned long old_addr,
 			 unsigned long new_addr, unsigned long old_end,
@@ -48,15 +48,9 @@ enum transparent_hugepage_flag {
 #endif
 };
 
-enum page_check_address_pmd_flag {
-	PAGE_CHECK_ADDRESS_PMD_FLAG,
-	PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG,
-	PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG,
-};
 extern pmd_t *page_check_address_pmd(struct page *page,
 				     struct mm_struct *mm,
 				     unsigned long address,
-				     enum page_check_address_pmd_flag flag,
 				     spinlock_t **ptl);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
@@ -100,7 +94,6 @@ extern unsigned long transparent_hugepage_flags;
 #define split_huge_page(page) BUILD_BUG()
 #define split_huge_pmd(__vma, __pmd, __address) BUILD_BUG()
 
-#define wait_split_huge_page(__anon_vma, __pmd) BUILD_BUG()
 #if HPAGE_PMD_ORDER >= MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
@@ -110,17 +103,17 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
-extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl);
 /* mmap_sem must be held on entry */
-static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
 	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
 	if (pmd_trans_huge(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma, ptl);
 	else
-		return 0;
+		return false;
 }
 static inline int hpage_nr_pages(struct page *page)
 {
@@ -165,8 +158,6 @@ static inline int split_huge_page(struct page *page)
 {
 	return 0;
 }
-#define wait_split_huge_page(__anon_vma, __pmd)	\
-	do { } while (0)
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
@@ -181,10 +172,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
-static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
-	return 0;
+	return false;
 }
 
 static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,

mm/gup.c

@@ -241,13 +241,6 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 		return follow_page_pte(vma, address, pmd, flags);
 	}
-
-	if (unlikely(pmd_trans_splitting(*pmd))) {
-		spin_unlock(ptl);
-		wait_split_huge_page(vma->anon_vma, pmd);
-		return follow_page_pte(vma, address, pmd, flags);
-	}
-
 	if (flags & FOLL_SPLIT) {
 		int ret;
 		page = pmd_page(*pmd);
@@ -1068,9 +1061,6 @@ struct page *get_dump_page(unsigned long addr)
  *  *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free
  *      pages containing page tables.
  *
- *  *) THP splits will broadcast an IPI, this can be achieved by overriding
- *      pmdp_splitting_flush.
- *
  *  *) ptes can be read atomically by the architecture.
  *
  *  *) access_ok is sufficient to validate userspace address ranges.
@@ -1267,7 +1257,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		pmd_t pmd = READ_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+		if (pmd_none(pmd))
 			return 0;
 
 		if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {

mm/huge_memory.c

@@ -986,15 +986,6 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 
-	if (unlikely(pmd_trans_splitting(pmd))) {
-		/* split huge page running from under us */
-		spin_unlock(src_ptl);
-		spin_unlock(dst_ptl);
-		pte_free(dst_mm, pgtable);
-
-		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
-		goto out;
-	}
 	src_page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
 	get_page(src_page);
@@ -1470,7 +1461,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	pmd_t orig_pmd;
 	spinlock_t *ptl;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1)
+	if (!__pmd_trans_huge_lock(pmd, vma, &ptl))
 		return 0;
 	/*
 	 * For architectures like ppc64 we look at deposited pgtable
@@ -1504,13 +1495,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return 1;
 }
 
-int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
+bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		  unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
 		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
-	int ret = 0;
 	pmd_t pmd;
 
 	struct mm_struct *mm = vma->vm_mm;
@@ -1519,23 +1509,22 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 	    (new_addr & ~HPAGE_PMD_MASK) ||
 	    old_end - old_addr < HPAGE_PMD_SIZE ||
 	    (new_vma->vm_flags & VM_NOHUGEPAGE))
-		goto out;
+		return false;
 
 	/*
 	 * The destination pmd shouldn't be established, free_pgtables()
 	 * should have release it.
 	 */
 	if (WARN_ON(!pmd_none(*new_pmd))) {
 		VM_BUG_ON(pmd_trans_huge(*new_pmd));
-		goto out;
+		return false;
 	}
 
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_sem prevents deadlock.
 	 */
-	ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl);
-	if (ret == 1) {
+	if (__pmd_trans_huge_lock(old_pmd, vma, &old_ptl)) {
 		new_ptl = pmd_lockptr(mm, new_pmd);
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -1551,9 +1540,9 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		if (new_ptl != old_ptl)
 			spin_unlock(new_ptl);
 		spin_unlock(old_ptl);
+		return true;
 	}
-out:
-	return ret;
+	return false;
 }
 
 /*
@@ -1569,7 +1558,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		pmd_t entry;
 		bool preserve_write = prot_numa && pmd_write(*pmd);
 		ret = 1;
@@ -1600,29 +1589,19 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 }
 
 /*
- * Returns 1 if a given pmd maps a stable (not under splitting) thp.
- * Returns -1 if it maps a thp under splitting. Returns 0 otherwise.
+ * Returns true if a given pmd maps a thp, false otherwise.
  *
- * Note that if it returns 1, this routine returns without unlocking page
- * table locks. So callers must unlock them.
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
  */
-int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
 	*ptl = pmd_lock(vma->vm_mm, pmd);
-	if (likely(pmd_trans_huge(*pmd))) {
-		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(*ptl);
-			wait_split_huge_page(vma->anon_vma, pmd);
-			return -1;
-		} else {
-			/* Thp mapped by 'pmd' is stable, so we can
-			 * handle it as it is. */
-			return 1;
-		}
-	}
+	if (likely(pmd_trans_huge(*pmd)))
+		return true;
 	spin_unlock(*ptl);
-	return 0;
+	return false;
 }
 
 /*
@@ -1636,7 +1615,6 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 pmd_t *page_check_address_pmd(struct page *page,
 			      struct mm_struct *mm,
 			      unsigned long address,
-			      enum page_check_address_pmd_flag flag,
 			      spinlock_t **ptl)
 {
 	pgd_t *pgd;
@@ -1659,21 +1637,8 @@ pmd_t *page_check_address_pmd(struct page *page,
 		goto unlock;
 	if (pmd_page(*pmd) != page)
 		goto unlock;
-	/*
-	 * split_vma() may create temporary aliased mappings. There is
-	 * no risk as long as all huge pmd are found and have their
-	 * splitting bit set before __split_huge_page_refcount
-	 * runs. Finding the same huge pmd more than once during the
-	 * same rmap walk is not a problem.
-	 */
-	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
-	    pmd_trans_splitting(*pmd))
-		goto unlock;
-	if (pmd_trans_huge(*pmd)) {
-		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
-			  !pmd_trans_splitting(*pmd));
+	if (pmd_trans_huge(*pmd))
 		return pmd;
-	}
 unlock:
 	spin_unlock(*ptl);
 	return NULL;

mm/memcontrol.c

@@ -4675,7 +4675,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
 		spin_unlock(ptl);
@@ -4863,16 +4863,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	union mc_target target;
 	struct page *page;
 
-	/*
-	 * No race with splitting thp happens because:
-	 *  - if pmd_trans_huge_lock() returns 1, the relevant thp is not
-	 *    under splitting, which means there's no concurrent thp split,
-	 *  - if another thread runs into split_huge_page() just after we
-	 *    entered this if-block, the thread must wait for page table lock
-	 *    to be unlocked in __split_huge_page_splitting(), where the main
-	 *    part of thp split is not executed yet.
-	 */
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		if (mc.precharge < HPAGE_PMD_NR) {
 			spin_unlock(ptl);
 			return 0;