[PATCH 6/8] hugetlb: add vma based lock for pmd sharing

[Mike Kravetz <mike.kravetz@oracle.com>]

Allocate a rw semaphore and hang off vm_private_data for
synchronization use by vmas that could be involved in pmd sharing.  Only
add infrastructure for the new lock here.  Actual use will be added in
subsequent patch.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 include/linux/hugetlb.h |  36 ++++++++-
 kernel/fork.c           |   6 +-
 mm/hugetlb.c            | 170 ++++++++++++++++++++++++++++++++++++----
 mm/rmap.c               |   8 +-
 4 files changed, 197 insertions(+), 23 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index acace1a25226..852f911d676e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -126,7 +126,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
 						long min_hpages);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
-void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
+void hugetlb_dup_vma_private(struct vm_area_struct *vma);
 void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *);
 int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *,
@@ -214,6 +214,13 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
 			     pgd_t *pgd, int flags);
 
+void hugetlb_vma_lock_read(struct vm_area_struct *vma);
+void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
+void hugetlb_vma_lock_write(struct vm_area_struct *vma);
+void hugetlb_vma_unlock_write(struct vm_area_struct *vma);
+int hugetlb_vma_trylock_write(struct vm_area_struct *vma);
+void hugetlb_vma_assert_locked(struct vm_area_struct *vma);
+
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
@@ -225,7 +232,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
-static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
+static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 }
 
@@ -336,6 +343,31 @@ static inline int prepare_hugepage_range(struct file *file,
 	return -EINVAL;
 }
 
+static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
+{
+}
+
+static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
+{
+	return 1;
+}
+
+static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
+{
+}
+
 static inline int pmd_huge(pmd_t pmd)
 {
 	return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 9470220e8f43..421c143286d2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -675,12 +675,10 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		}
 
 		/*
-		 * Clear hugetlb-related page reserves for children. This only
-		 * affects MAP_PRIVATE mappings. Faults generated by the child
-		 * are not guaranteed to succeed, even if read-only
+		 * Copy/update hugetlb private vma information.
 		 */
 		if (is_vm_hugetlb_page(tmp))
-			reset_vma_resv_huge_pages(tmp);
+			hugetlb_dup_vma_private(tmp);
 
 		/*
 		 * Link in the new vma and copy the page table entries.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 758b6844d566..6fb0bff2c7ee 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -91,6 +91,8 @@ struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
+static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
+static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -1008,12 +1010,25 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
-/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
-void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
+void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
+	/*
+	 * Clear vm_private_data
+	 * - For MAP_PRIVATE mappings, this is the reserve map which does
+	 *   not apply to children.  Faults generated by the children are
+	 *   not guaranteed to succeed, even if read-only.
+	 * - For shared mappings this is a per-vma semaphore that may be
+	 *   allocated below.
+	 */
+	vma->vm_private_data = (void *)0;
 	if (!(vma->vm_flags & VM_MAYSHARE))
-		vma->vm_private_data = (void *)0;
+		return;
+
+	/*
+	 * Allocate semaphore if pmd sharing is possible.
+	 */
+	hugetlb_vma_lock_alloc(vma);
 }
 
 /*
@@ -1044,7 +1059,7 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
 		kref_put(&reservations->refs, resv_map_release);
 	}
 
-	reset_vma_resv_huge_pages(vma);
+	hugetlb_dup_vma_private(vma);
 }
 
 /* Returns true if the VMA has associated reserve pages */
@@ -4623,16 +4638,21 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 		resv_map_dup_hugetlb_cgroup_uncharge_info(resv);
 		kref_get(&resv->refs);
 	}
+
+	hugetlb_vma_lock_alloc(vma);
 }
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
-	struct resv_map *resv = vma_resv_map(vma);
+	struct resv_map *resv;
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	unsigned long reserve, start, end;
 	long gbl_reserve;
 
+	hugetlb_vma_lock_free(vma);
+
+	resv = vma_resv_map(vma);
 	if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		return;
 
@@ -6447,6 +6467,11 @@ bool hugetlb_reserve_pages(struct inode *inode,
 		return false;
 	}
 
+	/*
+	 * vma specific semaphore used for pmd sharing synchronization
+	 */
+	hugetlb_vma_lock_alloc(vma);
+
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
@@ -6470,12 +6495,11 @@ bool hugetlb_reserve_pages(struct inode *inode,
 		resv_map = inode_resv_map(inode);
 
 		chg = region_chg(resv_map, from, to, &regions_needed);
-
 	} else {
 		/* Private mapping. */
 		resv_map = resv_map_alloc();
 		if (!resv_map)
-			return false;
+			goto out_err;
 
 		chg = to - from;
 
@@ -6570,6 +6594,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 	hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
 					    chg * pages_per_huge_page(h), h_cg);
 out_err:
+	hugetlb_vma_lock_free(vma);
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		/* Only call region_abort if the region_chg succeeded but the
 		 * region_add failed or didn't run.
@@ -6649,14 +6674,34 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 }
 
 static bool __vma_aligned_range_pmd_shareable(struct vm_area_struct *vma,
-				unsigned long start, unsigned long end)
+				unsigned long start, unsigned long end,
+				bool check_vma_lock)
 {
+#ifdef CONFIG_USERFAULTFD
+	if (uffd_disable_huge_pmd_share(vma))
+		return false;
+#endif
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, start, end))
-		return true;
-	return false;
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return false;
+	if (check_vma_lock && !vma->vm_private_data)
+		return false;
+	if (!range_in_vma(vma, start, end))
+		return false;
+	return true;
+}
+
+static bool vma_pmd_shareable(struct vm_area_struct *vma)
+{
+	unsigned long start = ALIGN(vma->vm_start, PUD_SIZE),
+		      end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
+
+	if (start >= end)
+		return false;
+
+	return __vma_aligned_range_pmd_shareable(vma, start, end, false);
 }
 
 static bool vma_addr_pmd_shareable(struct vm_area_struct *vma,
@@ -6665,15 +6710,11 @@ static bool vma_addr_pmd_shareable(struct vm_area_struct *vma,
 	unsigned long start = addr & PUD_MASK;
 	unsigned long end = start + PUD_SIZE;
 
-	return __vma_aligned_range_pmd_shareable(vma, start, end);
+	return __vma_aligned_range_pmd_shareable(vma, start, end, true);
 }
 
 bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
 {
-#ifdef CONFIG_USERFAULTFD
-	if (uffd_disable_huge_pmd_share(vma))
-		return false;
-#endif
 	return vma_addr_pmd_shareable(vma, addr);
 }
 
@@ -6704,6 +6745,95 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 		*end = ALIGN(*end, PUD_SIZE);
 }
 
+static bool __vma_shareable_flags_pmd(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & (VM_MAYSHARE | VM_SHARED) &&
+		vma->vm_private_data;
+}
+
+void hugetlb_vma_lock_read(struct vm_area_struct *vma)
+{
+	if (__vma_shareable_flags_pmd(vma))
+		down_read((struct rw_semaphore *)vma->vm_private_data);
+}
+
+void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
+{
+	if (__vma_shareable_flags_pmd(vma))
+		up_read((struct rw_semaphore *)vma->vm_private_data);
+}
+
+void hugetlb_vma_lock_write(struct vm_area_struct *vma)
+{
+	if (__vma_shareable_flags_pmd(vma))
+		down_write((struct rw_semaphore *)vma->vm_private_data);
+}
+
+void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
+{
+	if (__vma_shareable_flags_pmd(vma))
+		up_write((struct rw_semaphore *)vma->vm_private_data);
+}
+
+int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
+{
+	if (!__vma_shareable_flags_pmd(vma))
+		return 1;
+
+	return down_write_trylock((struct rw_semaphore *)vma->vm_private_data);
+}
+
+void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
+{
+	if (__vma_shareable_flags_pmd(vma))
+		lockdep_assert_held((struct rw_semaphore *)
+				vma->vm_private_data);
+}
+
+static void hugetlb_vma_lock_free(struct vm_area_struct *vma)
+{
+	/*
+	 * Only present in sharable vmas.  See comment in
+	 * __unmap_hugepage_range_final about the neeed to check both
+	 * VM_SHARED and VM_MAYSHARE in free path
+	 */
+	if (!vma || !(vma->vm_flags & (VM_MAYSHARE | VM_SHARED)))
+		return;
+
+	if (vma->vm_private_data) {
+		kfree(vma->vm_private_data);
+		vma->vm_private_data = NULL;
+	}
+}
+
+static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
+{
+	struct rw_semaphore *vma_sema;
+
+	/* Only establish in (flags) sharable vmas */
+	if (!vma || !(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	/* Should never get here with non-NULL vm_private_data */
+	if (vma->vm_private_data)
+		return;
+
+	/* Check size/alignment for pmd sharing possible */
+	if (!vma_pmd_shareable(vma))
+		return;
+
+	vma_sema = kmalloc(sizeof(*vma_sema), GFP_KERNEL);
+	if (!vma_sema)
+		/*
+		 * If we can not allocate semaphore, then vma can not
+		 * participate in pmd sharing.
+		 */
+		return;
+
+	init_rwsem(vma_sema);
+	vma->vm_private_data = vma_sema;
+}
+
 /*
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
@@ -6790,6 +6920,14 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+static void hugetlb_vma_lock_free(struct vm_area_struct *vma)
+{
+}
+
+static void hugetlb_vma_lock_alloc(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)
 {
diff --git a/mm/rmap.c b/mm/rmap.c
index ad9c97c6445c..55209e029847 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -24,7 +24,7 @@
  *   mm->mmap_lock
  *     mapping->invalidate_lock (in filemap_fault)
  *       page->flags PG_locked (lock_page)
- *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
+ *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below)
  *           mapping->i_mmap_rwsem
  *             anon_vma->rwsem
  *               mm->page_table_lock or pte_lock
@@ -44,6 +44,12 @@
  * anon_vma->rwsem,mapping->i_mmap_rwsem   (memory_failure, collect_procs_anon)
  *   ->tasklist_lock
  *     pte map lock
+ *
+ * hugetlbfs PageHuge() take locks in this order:
+ *   hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
+ *     vma_lock (hugetlb specific lock for pmd_sharing)
+ *       mapping->i_mmap_rwsem (also used for hugetlb pmd sharing)
+ *         page->flags PG_locked (lock_page)
  */
 
 #include <linux/mm.h>
-- 
2.37.1