[PATCH v2 0/3] hugetlbfs: close race between MADV_DONTNEED and page fault

[PATCH v2 0/3] hugetlbfs: close race between MADV_DONTNEED and page fault

[riel]

v2: fix the locking bug found with the libhugetlbfs tests.

Malloc libraries, like jemalloc and tcalloc, take decisions on when
to call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages
sitting around to satisfy a page fault. However, with hugetlbfs
systems often allocate only the exact number of huge pages that
the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:

       CPU 1                            CPU 2

       MADV_DONTNEED
       unmap page
       shoot down TLB entry
                                       page fault
                                       fail to allocate a huge page
                                       killed with SIGBUS
       free page

Fix that race by extending the hugetlb_vma_lock locking scheme to also
cover private hugetlb mappings (with resv_map), and pulling the locking 
from __unmap_hugepage_final_range into helper functions called from
zap_page_range_single. This ensures page faults stay locked out of
the MADV_DONTNEED VMA until the huge pages have actually been freed.

The third patch in the series is more of an RFC. Using the
invalidate_lock instead of the hugetlb_vma_lock greatly simplifies
the code, but at the cost of turning a per-VMA lock into a lock
per backing hugetlbfs file, which could slow things down when
multiple processes are mapping the same hugetlbfs file.

[PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[riel]

From: Rik van Riel <riel@surriel.com>

Extend the locking scheme used to protect shared hugetlb mappings
from truncate vs page fault races, in order to protect private
hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and
use that from the hugetlb_vma_(un)lock_* functions, in preparation
for closing the race between MADV_DONTNEED and page faults.

Signed-off-by: Rik van Riel <riel@surriel.com>
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b2626063f4f..694928fa06a3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -1231,6 +1232,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba6d39b71cb1..ee7497f37098 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_read(&resv_map->rw_sema);
 	}
 }
 
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_read(&resv_map->rw_sema);
 	}
 }
 
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_write(&resv_map->rw_sema);
 	}
 }
 
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_write(&resv_map->rw_sema);
 	}
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	if (!__vma_shareable_lock(vma))
-		return 1;
+	if (__vma_shareable_lock(vma)) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	return down_write_trylock(&vma_lock->rw_sema);
+		return down_write_trylock(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		return down_write_trylock(&resv_map->rw_sema);
+	}
+
+	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		lockdep_assert_held(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		lockdep_assert_held(&resv_map->rw_sema);
 	}
 }
 
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }
 
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
+	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
-- 
2.41.0

[PATCH 2/3] hugetlbfs: close race between MADV_DONTNEED and page fault

[riel]

From: Rik van Riel <riel@surriel.com>

Malloc libraries, like jemalloc and tcalloc, take decisions on when
to call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages
sitting around to satisfy a page fault. However, with hugetlbfs
systems often allocate only the exact number of huge pages that
the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:

       CPU 1                            CPU 2

       MADV_DONTNEED
       unmap page
       shoot down TLB entry
                                       page fault
                                       fail to allocate a huge page
                                       killed with SIGBUS
       free page

Fix that race by pulling the locking from __unmap_hugepage_final_range
into helper functions called from zap_page_range_single. This ensures
page faults stay locked out of the MADV_DONTNEED VMA until the
huge pages have actually been freed.

Signed-off-by: Rik van Riel <riel@surriel.com>
---
 include/linux/hugetlb.h | 35 +++++++++++++++++++++++++++++++++--
 mm/hugetlb.c            | 20 +++++++++++---------
 mm/memory.c             |  7 +++----
 3 files changed, 47 insertions(+), 15 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 694928fa06a3..d9ec500cfef9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -139,7 +139,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
 void unmap_hugepage_range(struct vm_area_struct *,
 			  unsigned long, unsigned long, struct page *,
 			  zap_flags_t);
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+void __unmap_hugepage_range(struct mmu_gather *tlb,
 			  struct vm_area_struct *vma,
 			  unsigned long start, unsigned long end,
 			  struct page *ref_page, zap_flags_t zap_flags);
@@ -246,6 +246,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 
+extern void __hugetlb_zap_begin(struct vm_area_struct *vma,
+				unsigned long *begin, unsigned long *end);
+extern void __hugetlb_zap_end(struct vm_area_struct *vma,
+			      struct zap_details *details);
+
+static inline void hugetlb_zap_begin(struct vm_area_struct *vma,
+				     unsigned long *start, unsigned long *end)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_begin(vma, start, end);
+}
+
+static inline void hugetlb_zap_end(struct vm_area_struct *vma,
+				   struct zap_details *details)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_end(vma, details);
+}
+
 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);
@@ -297,6 +316,18 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
+static inline void hugetlb_zap_begin(
+				struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
+
+static inline void hugetlb_zap_end(
+				struct vm_area_struct *vma,
+				struct zap_details *details)
+{
+}
+
 static inline struct page *hugetlb_follow_page_mask(
     struct vm_area_struct *vma, unsigned long address, unsigned int flags,
     unsigned int *page_mask)
@@ -442,7 +473,7 @@ static inline long hugetlb_change_protection(
 	return 0;
 }
 
-static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
 			unsigned long end, struct page *ref_page,
 			zap_flags_t zap_flags)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ee7497f37098..397a26f70deb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5306,9 +5306,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	return len + old_addr - old_end;
 }
 
-static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end,
-				   struct page *ref_page, zap_flags_t zap_flags)
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			    unsigned long start, unsigned long end,
+			    struct page *ref_page, zap_flags_t zap_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -5435,16 +5435,18 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		tlb_flush_mmu_tlbonly(tlb);
 }
 
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
-			  struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end, struct page *ref_page,
-			  zap_flags_t zap_flags)
+void __hugetlb_zap_begin(struct vm_area_struct *vma,
+			 unsigned long *start, unsigned long *end)
 {
+	adjust_range_if_pmd_sharing_possible(vma, start, end);
 	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
+}
 
-	/* mmu notification performed in caller */
-	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
+void __hugetlb_zap_end(struct vm_area_struct *vma,
+		       struct zap_details *details)
+{
+	zap_flags_t zap_flags = details ? details->zap_flags : 0;
 
 	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
 		/*
diff --git a/mm/memory.c b/mm/memory.c
index 6c264d2f969c..a07ae3b60530 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1683,7 +1683,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			if (vma->vm_file) {
 				zap_flags_t zap_flags = details ?
 				    details->zap_flags : 0;
-				__unmap_hugepage_range_final(tlb, vma, start, end,
+				__unmap_hugepage_range(tlb, vma, start, end,
 							     NULL, zap_flags);
 			}
 		} else
@@ -1753,9 +1753,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, end);
-	if (is_vm_hugetlb_page(vma))
-		adjust_range_if_pmd_sharing_possible(vma, &range.start,
-						     &range.end);
+	hugetlb_zap_begin(vma, &range.start, &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
@@ -1766,6 +1764,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	unmap_single_vma(&tlb, vma, address, end, details, false);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
+	hugetlb_zap_end(vma, details);
 }
 
 /**
-- 
2.41.0

[PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

[riel]

From: Rik van Riel <riel@surriel.com>

Replace the custom hugetlbfs VMA locking code with the recently
introduced invalidate_lock. This greatly simplifies things.

However, this is a large enough change that it should probably go in
separately from the other changes.

Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Rik van Riel <riel@surriel.com>
---
 fs/hugetlbfs/inode.c    |  68 +-----------
 include/linux/fs.h      |   6 +
 include/linux/hugetlb.h |   7 --
 kernel/fork.c           |   6 -
 mm/hugetlb.c            | 238 +++-------------------------------------
 5 files changed, 26 insertions(+), 299 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 316c4cebd3f3..5ff18b0933bc 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -485,7 +485,6 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 					struct folio *folio, pgoff_t index)
 {
 	struct rb_root_cached *root = &mapping->i_mmap;
-	struct hugetlb_vma_lock *vma_lock;
 	struct page *page = &folio->page;
 	struct vm_area_struct *vma;
 	unsigned long v_start;
@@ -496,8 +495,8 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 	end = (index + 1) * pages_per_huge_page(h);
 
 	i_mmap_lock_write(mapping);
-retry:
-	vma_lock = NULL;
+	filemap_invalidate_lock(mapping);
+
 	vma_interval_tree_foreach(vma, root, start, end - 1) {
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
@@ -505,62 +504,13 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 		if (!hugetlb_vma_maps_page(vma, v_start, page))
 			continue;
 
-		if (!hugetlb_vma_trylock_write(vma)) {
-			vma_lock = vma->vm_private_data;
-			/*
-			 * If we can not get vma lock, we need to drop
-			 * immap_sema and take locks in order.  First,
-			 * take a ref on the vma_lock structure so that
-			 * we can be guaranteed it will not go away when
-			 * dropping immap_sema.
-			 */
-			kref_get(&vma_lock->refs);
-			break;
-		}
-
 		unmap_hugepage_range(vma, v_start, v_end, NULL,
 				     ZAP_FLAG_DROP_MARKER);
 		hugetlb_vma_unlock_write(vma);
 	}
 
+	filemap_invalidate_unlock(mapping);
 	i_mmap_unlock_write(mapping);
-
-	if (vma_lock) {
-		/*
-		 * Wait on vma_lock.  We know it is still valid as we have
-		 * a reference.  We must 'open code' vma locking as we do
-		 * not know if vma_lock is still attached to vma.
-		 */
-		down_write(&vma_lock->rw_sema);
-		i_mmap_lock_write(mapping);
-
-		vma = vma_lock->vma;
-		if (!vma) {
-			/*
-			 * If lock is no longer attached to vma, then just
-			 * unlock, drop our reference and retry looking for
-			 * other vmas.
-			 */
-			up_write(&vma_lock->rw_sema);
-			kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
-			goto retry;
-		}
-
-		/*
-		 * vma_lock is still attached to vma.  Check to see if vma
-		 * still maps page and if so, unmap.
-		 */
-		v_start = vma_offset_start(vma, start);
-		v_end = vma_offset_end(vma, end);
-		if (hugetlb_vma_maps_page(vma, v_start, page))
-			unmap_hugepage_range(vma, v_start, v_end, NULL,
-					     ZAP_FLAG_DROP_MARKER);
-
-		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
-		hugetlb_vma_unlock_write(vma);
-
-		goto retry;
-	}
 }
 
 static void
@@ -578,20 +528,10 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
 		unsigned long v_start;
 		unsigned long v_end;
 
-		if (!hugetlb_vma_trylock_write(vma))
-			continue;
-
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
 
 		unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags);
-
-		/*
-		 * Note that vma lock only exists for shared/non-private
-		 * vmas.  Therefore, lock is not held when calling
-		 * unmap_hugepage_range for private vmas.
-		 */
-		hugetlb_vma_unlock_write(vma);
 	}
 }
 
@@ -726,9 +666,11 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 
 	i_size_write(inode, offset);
 	i_mmap_lock_write(mapping);
+	filemap_invalidate_lock(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
 				      ZAP_FLAG_DROP_MARKER);
+	filemap_invalidate_unlock(mapping);
 	i_mmap_unlock_write(mapping);
 	remove_inode_hugepages(inode, offset, LLONG_MAX);
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4aeb3fa11927..b455a8913db4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -847,6 +847,12 @@ static inline void filemap_invalidate_lock(struct address_space *mapping)
 	down_write(&mapping->invalidate_lock);
 }
 
+static inline int filemap_invalidate_trylock(
+					struct address_space *mapping)
+{
+	return down_write_trylock(&mapping->invalidate_lock);
+}
+
 static inline void filemap_invalidate_unlock(struct address_space *mapping)
 {
 	up_write(&mapping->invalidate_lock);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d9ec500cfef9..af60b67ed828 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,7 +60,6 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
-	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -107,12 +106,6 @@ struct file_region {
 #endif
 };
 
-struct hugetlb_vma_lock {
-	struct kref refs;
-	struct rw_semaphore rw_sema;
-	struct vm_area_struct *vma;
-};
-
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 3b6d20dfb9a8..42453437b615 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -743,12 +743,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			i_mmap_unlock_write(mapping);
 		}
 
-		/*
-		 * Copy/update hugetlb private vma information.
-		 */
-		if (is_vm_hugetlb_page(tmp))
-			hugetlb_dup_vma_private(tmp);
-
 		/* Link the vma into the MT */
 		if (vma_iter_bulk_store(&vmi, tmp))
 			goto fail_nomem_vmi_store;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 397a26f70deb..3b97bd762049 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -92,9 +92,6 @@ 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 void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
@@ -264,170 +261,41 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
  */
 void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 {
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		down_read(&vma_lock->rw_sema);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		down_read(&resv_map->rw_sema);
-	}
+	if (vma->vm_file)
+		filemap_invalidate_lock_shared(vma->vm_file->f_mapping);
 }
 
 void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 {
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		up_read(&vma_lock->rw_sema);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		up_read(&resv_map->rw_sema);
-	}
+	if (vma->vm_file)
+		filemap_invalidate_unlock_shared(vma->vm_file->f_mapping);
 }
 
 void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 {
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		down_write(&vma_lock->rw_sema);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		down_write(&resv_map->rw_sema);
-	}
+	if (vma->vm_file)
+		filemap_invalidate_lock(vma->vm_file->f_mapping);
 }
 
 void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 {
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		up_write(&vma_lock->rw_sema);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		up_write(&resv_map->rw_sema);
-	}
+	if (vma->vm_file)
+		filemap_invalidate_unlock(vma->vm_file->f_mapping);
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
 
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		return down_write_trylock(&vma_lock->rw_sema);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		return down_write_trylock(&resv_map->rw_sema);
-	}
+	if (vma->vm_file)
+		return filemap_invalidate_trylock(vma->vm_file->f_mapping);
 
 	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 {
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		lockdep_assert_held(&vma_lock->rw_sema);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		lockdep_assert_held(&resv_map->rw_sema);
-	}
-}
-
-void hugetlb_vma_lock_release(struct kref *kref)
-{
-	struct hugetlb_vma_lock *vma_lock = container_of(kref,
-			struct hugetlb_vma_lock, refs);
-
-	kfree(vma_lock);
-}
-
-static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock)
-{
-	struct vm_area_struct *vma = vma_lock->vma;
-
-	/*
-	 * vma_lock structure may or not be released as a result of put,
-	 * it certainly will no longer be attached to vma so clear pointer.
-	 * Semaphore synchronizes access to vma_lock->vma field.
-	 */
-	vma_lock->vma = NULL;
-	vma->vm_private_data = NULL;
-	up_write(&vma_lock->rw_sema);
-	kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
-}
-
-static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
-{
-	if (__vma_shareable_lock(vma)) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		__hugetlb_vma_unlock_write_put(vma_lock);
-	} else if (__vma_private_lock(vma)) {
-		struct resv_map *resv_map = vma_resv_map(vma);
-
-		/* no free for anon vmas, but still need to unlock */
-		up_write(&resv_map->rw_sema);
-	}
-}
-
-static void hugetlb_vma_lock_free(struct vm_area_struct *vma)
-{
-	/*
-	 * Only present in sharable vmas.
-	 */
-	if (!vma || !__vma_shareable_lock(vma))
-		return;
-
-	if (vma->vm_private_data) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		down_write(&vma_lock->rw_sema);
-		__hugetlb_vma_unlock_write_put(vma_lock);
-	}
-}
-
-static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
-{
-	struct hugetlb_vma_lock *vma_lock;
-
-	/* 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;
-
-	vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL);
-	if (!vma_lock) {
-		/*
-		 * If we can not allocate structure, then vma can not
-		 * participate in pmd sharing.  This is only a possible
-		 * performance enhancement and memory saving issue.
-		 * However, the lock is also used to synchronize page
-		 * faults with truncation.  If the lock is not present,
-		 * unlikely races could leave pages in a file past i_size
-		 * until the file is removed.  Warn in the unlikely case of
-		 * allocation failure.
-		 */
-		pr_warn_once("HugeTLB: unable to allocate vma specific lock\n");
-		return;
-	}
-
-	kref_init(&vma_lock->refs);
-	init_rwsem(&vma_lock->rw_sema);
-	vma_lock->vma = vma;
-	vma->vm_private_data = vma_lock;
+	if (vma->vm_file)
+		lockdep_assert_held(&vma->vm_file->f_mapping->invalidate_lock);
 }
 
 /* Helper that removes a struct file_region from the resv_map cache and returns
@@ -1100,7 +968,6 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
-	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
@@ -1190,30 +1057,6 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
-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 shared mappings this is a per-vma semaphore that may be
-	 *   allocated in a subsequent call to hugetlb_vm_op_open.
-	 *   Before clearing, make sure pointer is not associated with vma
-	 *   as this will leak the structure.  This is the case when called
-	 *   via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already
-	 *   been called to allocate a new structure.
-	 * - 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.
-	 */
-	if (vma->vm_flags & VM_MAYSHARE) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		if (vma_lock && vma_lock->vma != vma)
-			vma->vm_private_data = NULL;
-	} else
-		vma->vm_private_data = NULL;
-}
-
 /*
  * Reset and decrement one ref on hugepage private reservation.
  * Called with mm->mmap_lock writer semaphore held.
@@ -1241,8 +1084,6 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
 		resv_map_put_hugetlb_cgroup_uncharge_info(reservations);
 		kref_put(&reservations->refs, resv_map_release);
 	}
-
-	hugetlb_dup_vma_private(vma);
 }
 
 /* Returns true if the VMA has associated reserve pages */
@@ -4846,25 +4687,6 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 		resv_map_dup_hugetlb_cgroup_uncharge_info(resv);
 		kref_get(&resv->refs);
 	}
-
-	/*
-	 * vma_lock structure for sharable mappings is vma specific.
-	 * Clear old pointer (if copied via vm_area_dup) and allocate
-	 * new structure.  Before clearing, make sure vma_lock is not
-	 * for this vma.
-	 */
-	if (vma->vm_flags & VM_MAYSHARE) {
-		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-		if (vma_lock) {
-			if (vma_lock->vma != vma) {
-				vma->vm_private_data = NULL;
-				hugetlb_vma_lock_alloc(vma);
-			} else
-				pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__);
-		} else
-			hugetlb_vma_lock_alloc(vma);
-	}
 }
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
@@ -4875,8 +4697,6 @@ static void hugetlb_vm_op_close(struct vm_area_struct *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;
@@ -5446,24 +5266,8 @@ void __hugetlb_zap_begin(struct vm_area_struct *vma,
 void __hugetlb_zap_end(struct vm_area_struct *vma,
 		       struct zap_details *details)
 {
-	zap_flags_t zap_flags = details ? details->zap_flags : 0;
-
-	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
-		/*
-		 * Unlock and free the vma lock before releasing i_mmap_rwsem.
-		 * When the vma_lock is freed, this makes the vma ineligible
-		 * for pmd sharing.  And, i_mmap_rwsem is required to set up
-		 * pmd sharing.  This is important as page tables for this
-		 * unmapped range will be asynchrously deleted.  If the page
-		 * tables are shared, there will be issues when accessed by
-		 * someone else.
-		 */
-		__hugetlb_vma_unlock_write_free(vma);
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
-	} else {
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
-		hugetlb_vma_unlock_write(vma);
-	}
+	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	hugetlb_vma_unlock_write(vma);
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
@@ -6706,12 +6510,6 @@ bool hugetlb_reserve_pages(struct inode *inode,
 		return false;
 	}
 
-	/*
-	 * vma specific semaphore used for pmd sharing and fault/truncation
-	 * 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
@@ -6834,7 +6632,6 @@ 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.
@@ -6904,13 +6701,10 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 	/*
 	 * match the virtual addresses, permission and the alignment of the
 	 * page table page.
-	 *
-	 * Also, vma_lock (vm_private_data) is required for sharing.
 	 */
 	if (pmd_index(addr) != pmd_index(saddr) ||
 	    vm_flags != svm_flags ||
-	    !range_in_vma(svma, sbase, s_end) ||
-	    !svma->vm_private_data)
+	    !range_in_vma(svma, sbase, s_end))
 		return 0;
 
 	return saddr;
@@ -6930,8 +6724,6 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
 	 */
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		return false;
-	if (!vma->vm_private_data)	/* vma lock required for sharing */
-		return false;
 	if (!range_in_vma(vma, start, end))
 		return false;
 	return true;
-- 
2.41.0

Re: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

[kernel test robot]

Hi,

kernel test robot noticed the following build errors:

[auto build test ERROR on akpm-mm/mm-everything]
[also build test ERROR on linus/master v6.6-rc2 next-20230921]
[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#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/riel-surriel-com/hugetlbfs-extend-hugetlb_vma_lock-to-private-VMAs/20230923-030756
base:   https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link:    https://lore.kernel.org/r/20230922190552.3963067-4-riel%40surriel.com
patch subject: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock
config: i386-buildonly-randconfig-004-20230924 (https://download.01.org/0day-ci/archive/20230924/202309241415.pQmcSx8R-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230924/202309241415.pQmcSx8R-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202309241415.pQmcSx8R-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from arch/x86/include/asm/bug.h:87,
                    from include/linux/bug.h:5,
                    from include/linux/jump_label.h:256,
                    from include/linux/static_key.h:1,
                    from arch/x86/include/asm/nospec-branch.h:6,
                    from arch/x86/include/asm/irqflags.h:9,
                    from include/linux/irqflags.h:17,
                    from include/linux/rcupdate.h:26,
                    from include/linux/rculist.h:11,
                    from include/linux/pid.h:5,
                    from include/linux/sched.h:14,
                    from include/linux/audit.h:12,
                    from security/commoncap.c:6:
   include/linux/hugetlb.h: In function 'hugetlb_walk':
>> include/linux/hugetlb.h:1285:56: error: invalid use of undefined type 'struct hugetlb_vma_lock'
    1285 |                 WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                                                        ^~
   include/asm-generic/bug.h:168:32: note: in definition of macro 'WARN_ON'
     168 |         int __ret_warn_on = !!(condition);                              \
         |                                ^~~~~~~~~
   include/linux/hugetlb.h:1285:17: note: in expansion of macro 'WARN_ON_ONCE'
    1285 |                 WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                 ^~~~~~~~~~~~
   include/linux/hugetlb.h:1285:31: note: in expansion of macro 'lockdep_is_held'
    1285 |                 WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                               ^~~~~~~~~~~~~~~
--
   In file included from arch/x86/include/asm/bug.h:87,
                    from include/linux/bug.h:5,
                    from include/linux/mmdebug.h:5,
                    from include/linux/mm.h:6,
                    from mm/rmap.c:56:
   include/linux/hugetlb.h: In function 'hugetlb_walk':
>> include/linux/hugetlb.h:1285:56: error: invalid use of undefined type 'struct hugetlb_vma_lock'
    1285 |                 WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                                                        ^~
   include/asm-generic/bug.h:168:32: note: in definition of macro 'WARN_ON'
     168 |         int __ret_warn_on = !!(condition);                              \
         |                                ^~~~~~~~~
   include/linux/hugetlb.h:1285:17: note: in expansion of macro 'WARN_ON_ONCE'
    1285 |                 WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                 ^~~~~~~~~~~~
   include/linux/hugetlb.h:1285:31: note: in expansion of macro 'lockdep_is_held'
    1285 |                 WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                               ^~~~~~~~~~~~~~~
   In file included from mm/rmap.c:85:
   mm/internal.h: In function 'shrinker_debugfs_name_alloc':
   mm/internal.h:1223:9: warning: function 'shrinker_debugfs_name_alloc' might be a candidate for 'gnu_printf' format attribute [-Wsuggest-attribute=format]
    1223 |         shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
         |         ^~~~~~~~


vim +1285 include/linux/hugetlb.h

185d8dcce62020 Rik van Riel 2023-09-22  1265  
9c67a20704e763 Peter Xu     2022-12-16  1266  /*
9c67a20704e763 Peter Xu     2022-12-16  1267   * Safe version of huge_pte_offset() to check the locks.  See comments
9c67a20704e763 Peter Xu     2022-12-16  1268   * above huge_pte_offset().
9c67a20704e763 Peter Xu     2022-12-16  1269   */
9c67a20704e763 Peter Xu     2022-12-16  1270  static inline pte_t *
9c67a20704e763 Peter Xu     2022-12-16  1271  hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz)
9c67a20704e763 Peter Xu     2022-12-16  1272  {
9c67a20704e763 Peter Xu     2022-12-16  1273  #if defined(CONFIG_HUGETLB_PAGE) && \
9c67a20704e763 Peter Xu     2022-12-16  1274  	defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP)
9c67a20704e763 Peter Xu     2022-12-16  1275  	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
9c67a20704e763 Peter Xu     2022-12-16  1276  
9c67a20704e763 Peter Xu     2022-12-16  1277  	/*
9c67a20704e763 Peter Xu     2022-12-16  1278  	 * If pmd sharing possible, locking needed to safely walk the
9c67a20704e763 Peter Xu     2022-12-16  1279  	 * hugetlb pgtables.  More information can be found at the comment
9c67a20704e763 Peter Xu     2022-12-16  1280  	 * above huge_pte_offset() in the same file.
9c67a20704e763 Peter Xu     2022-12-16  1281  	 *
9c67a20704e763 Peter Xu     2022-12-16  1282  	 * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP.
9c67a20704e763 Peter Xu     2022-12-16  1283  	 */
9c67a20704e763 Peter Xu     2022-12-16  1284  	if (__vma_shareable_lock(vma))
9c67a20704e763 Peter Xu     2022-12-16 @1285  		WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
9c67a20704e763 Peter Xu     2022-12-16  1286  			     !lockdep_is_held(
9c67a20704e763 Peter Xu     2022-12-16  1287  				 &vma->vm_file->f_mapping->i_mmap_rwsem));
9c67a20704e763 Peter Xu     2022-12-16  1288  #endif
9c67a20704e763 Peter Xu     2022-12-16  1289  	return huge_pte_offset(vma->vm_mm, addr, sz);
9c67a20704e763 Peter Xu     2022-12-16  1290  }
9c67a20704e763 Peter Xu     2022-12-16  1291  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

[kernel test robot]

Hi,

kernel test robot noticed the following build errors:

[auto build test ERROR on akpm-mm/mm-everything]
[also build test ERROR on linus/master v6.6-rc3 next-20230921]
[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#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/riel-surriel-com/hugetlbfs-extend-hugetlb_vma_lock-to-private-VMAs/20230923-030756
base:   https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link:    https://lore.kernel.org/r/20230922190552.3963067-4-riel%40surriel.com
patch subject: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock
config: x86_64-randconfig-013-20230925 (https://download.01.org/0day-ci/archive/20230925/202309250923.NEPT0ip2-lkp@intel.com/config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230925/202309250923.NEPT0ip2-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202309250923.NEPT0ip2-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from arch/x86/include/asm/bug.h:87,
                    from include/linux/bug.h:5,
                    from include/linux/thread_info.h:13,
                    from arch/x86/include/asm/preempt.h:9,
                    from include/linux/preempt.h:79,
                    from include/linux/spinlock.h:56,
                    from include/linux/mmzone.h:8,
                    from include/linux/gfp.h:7,
                    from include/linux/slab.h:16,
                    from fs/nfs/write.c:11:
   include/linux/hugetlb.h: In function 'hugetlb_walk':
>> include/linux/hugetlb.h:1285:42: error: dereferencing pointer to incomplete type 'struct hugetlb_vma_lock'
    1285 |   WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                                          ^~
   include/asm-generic/bug.h:111:25: note: in definition of macro 'WARN_ON_ONCE'
     111 |  int __ret_warn_on = !!(condition);   \
         |                         ^~~~~~~~~
   include/linux/hugetlb.h:1285:17: note: in expansion of macro 'lockdep_is_held'
    1285 |   WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
         |                 ^~~~~~~~~~~~~~~


vim +1285 include/linux/hugetlb.h

185d8dcce62020 Rik van Riel 2023-09-22  1265  
9c67a20704e763 Peter Xu     2022-12-16  1266  /*
9c67a20704e763 Peter Xu     2022-12-16  1267   * Safe version of huge_pte_offset() to check the locks.  See comments
9c67a20704e763 Peter Xu     2022-12-16  1268   * above huge_pte_offset().
9c67a20704e763 Peter Xu     2022-12-16  1269   */
9c67a20704e763 Peter Xu     2022-12-16  1270  static inline pte_t *
9c67a20704e763 Peter Xu     2022-12-16  1271  hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz)
9c67a20704e763 Peter Xu     2022-12-16  1272  {
9c67a20704e763 Peter Xu     2022-12-16  1273  #if defined(CONFIG_HUGETLB_PAGE) && \
9c67a20704e763 Peter Xu     2022-12-16  1274  	defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP)
9c67a20704e763 Peter Xu     2022-12-16  1275  	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
9c67a20704e763 Peter Xu     2022-12-16  1276  
9c67a20704e763 Peter Xu     2022-12-16  1277  	/*
9c67a20704e763 Peter Xu     2022-12-16  1278  	 * If pmd sharing possible, locking needed to safely walk the
9c67a20704e763 Peter Xu     2022-12-16  1279  	 * hugetlb pgtables.  More information can be found at the comment
9c67a20704e763 Peter Xu     2022-12-16  1280  	 * above huge_pte_offset() in the same file.
9c67a20704e763 Peter Xu     2022-12-16  1281  	 *
9c67a20704e763 Peter Xu     2022-12-16  1282  	 * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP.
9c67a20704e763 Peter Xu     2022-12-16  1283  	 */
9c67a20704e763 Peter Xu     2022-12-16  1284  	if (__vma_shareable_lock(vma))
9c67a20704e763 Peter Xu     2022-12-16 @1285  		WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
9c67a20704e763 Peter Xu     2022-12-16  1286  			     !lockdep_is_held(
9c67a20704e763 Peter Xu     2022-12-16  1287  				 &vma->vm_file->f_mapping->i_mmap_rwsem));
9c67a20704e763 Peter Xu     2022-12-16  1288  #endif
9c67a20704e763 Peter Xu     2022-12-16  1289  	return huge_pte_offset(vma->vm_mm, addr, sz);
9c67a20704e763 Peter Xu     2022-12-16  1290  }
9c67a20704e763 Peter Xu     2022-12-16  1291  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

[Rik van Riel]

On Mon, 2023-09-25 at 10:04 +0800, kernel test robot wrote:
> Hi,
> 
> kernel test robot noticed the following build errors:
> 
> [auto build test ERROR on akpm-mm/mm-everything]
> [also build test ERROR on linus/master v6.6-rc3 next-20230921]
> [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#_base_tree_information]

OK, so I have a fix for patch 3/3 that gets rid of the
compile error, but the libhugetlbfs test cases show that
patch 3/3 opens up a condition where resv_hugepages 
underflows.

I have not figured out the cause of that yet, but
patches 1 & 2 seem to survive all tests fine.

-- 
All Rights Reversed.

Re: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

[Mike Kravetz]

On 09/25/23 15:22, Rik van Riel wrote:
> On Mon, 2023-09-25 at 10:04 +0800, kernel test robot wrote:
> > Hi,
> > 
> > kernel test robot noticed the following build errors:
> > 
> > [auto build test ERROR on akpm-mm/mm-everything]
> > [also build test ERROR on linus/master v6.6-rc3 next-20230921]
> > [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#_base_tree_information]
> 
> OK, so I have a fix for patch 3/3 that gets rid of the
> compile error, but the libhugetlbfs test cases show that
> patch 3/3 opens up a condition where resv_hugepages 
> underflows.
> 
> I have not figured out the cause of that yet, but
> patches 1 & 2 seem to survive all tests fine.

In addition, I suspect patch 3 is going to cause a performance regression.
It is taking me a little while to resurrect the test environment used when
the hugetlb vma lock was introduced.  My plan is to exercise the series in
that environment.

I should be able to review patches 1 & 2 later (my) today.
-- 
Mike Kravetz

Re: [PATCH 3/3] hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

[Rik van Riel]

On Mon, 2023-09-25 at 13:06 -0700, Mike Kravetz wrote:
> On 09/25/23 15:22, Rik van Riel wrote:
> > On Mon, 2023-09-25 at 10:04 +0800, kernel test robot wrote:
> > > Hi,
> > > 
> > > kernel test robot noticed the following build errors:
> > > 
> > > [auto build test ERROR on akpm-mm/mm-everything]
> > > [also build test ERROR on linus/master v6.6-rc3 next-20230921]
> > > [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#_base_tree_information]
> > 
> > OK, so I have a fix for patch 3/3 that gets rid of the
> > compile error, but the libhugetlbfs test cases show that
> > patch 3/3 opens up a condition where resv_hugepages 
> > underflows.
> > 
> > I have not figured out the cause of that yet, but
> > patches 1 & 2 seem to survive all tests fine.
> 
> In addition, I suspect patch 3 is going to cause a performance
> regression.
> It is taking me a little while to resurrect the test environment used
> when
> the hugetlb vma lock was introduced.  My plan is to exercise the
> series in
> that environment.
> 
I am planning to send a v3 of the series soon, once I have
confirmed that the bugs in patch 3 have all been fixed.

I have no strong opinion on whether or not patch 3 gets
merged at all. Patches 1 & 2 fix the actual bug that I am
trying to fix, and I am perfectly fine if patch 3 ends up
getting dropped in the end.

It seemed worth trying to get that cleanup though ;)

> I should be able to review patches 1 & 2 later (my) today.

Thank you!

-- 
All Rights Reversed.

[PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[riel]

From: Rik van Riel <riel@surriel.com>

Extend the locking scheme used to protect shared hugetlb mappings
from truncate vs page fault races, in order to protect private
hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and
use that from the hugetlb_vma_(un)lock_* functions, in preparation
for closing the race between MADV_DONTNEED and page faults.

Signed-off-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: stable@kernel.org
Fixes: 04ada095dcfc ("hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing")
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b2626063f4f..694928fa06a3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -1231,6 +1232,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba6d39b71cb1..ee7497f37098 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_read(&resv_map->rw_sema);
 	}
 }
 
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_read(&resv_map->rw_sema);
 	}
 }
 
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_write(&resv_map->rw_sema);
 	}
 }
 
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_write(&resv_map->rw_sema);
 	}
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	if (!__vma_shareable_lock(vma))
-		return 1;
+	if (__vma_shareable_lock(vma)) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	return down_write_trylock(&vma_lock->rw_sema);
+		return down_write_trylock(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		return down_write_trylock(&resv_map->rw_sema);
+	}
+
+	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		lockdep_assert_held(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		lockdep_assert_held(&resv_map->rw_sema);
 	}
 }
 
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }
 
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
+	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
-- 
2.41.0

[PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[riel]

From: Rik van Riel <riel@surriel.com>

Extend the locking scheme used to protect shared hugetlb mappings
from truncate vs page fault races, in order to protect private
hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and
use that from the hugetlb_vma_(un)lock_* functions, in preparation
for closing the race between MADV_DONTNEED and page faults.

Signed-off-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b2626063f4f..694928fa06a3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -1231,6 +1232,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba6d39b71cb1..ee7497f37098 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_read(&resv_map->rw_sema);
 	}
 }
 
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_read(&resv_map->rw_sema);
 	}
 }
 
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_write(&resv_map->rw_sema);
 	}
 }
 
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_write(&resv_map->rw_sema);
 	}
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	if (!__vma_shareable_lock(vma))
-		return 1;
+	if (__vma_shareable_lock(vma)) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	return down_write_trylock(&vma_lock->rw_sema);
+		return down_write_trylock(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		return down_write_trylock(&resv_map->rw_sema);
+	}
+
+	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		lockdep_assert_held(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		lockdep_assert_held(&resv_map->rw_sema);
 	}
 }
 
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }
 
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
+	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
-- 
2.41.0

Re: [PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[Rik van Riel]

On Fri, 2023-09-29 at 19:28 -0700, Mike Kravetz wrote:
> On 09/25/23 23:10, riel@surriel.com wrote:
> 
> 
> In reply to patch 1, I suggested the changes:
> 
> > diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> > index f906c5fa4d09..8f3d5895fffc 100644
> > --- a/mm/hugetlb.c
> > +++ b/mm/hugetlb.c
> > @@ -372,6 +372,11 @@ static void
> > __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
> >                 struct hugetlb_vma_lock *vma_lock = vma-
> > >vm_private_data;
> >  
> >                 __hugetlb_vma_unlock_write_put(vma_lock);
> > +       } else if (__vma_private_lock(vma)) {
> > +               struct resv_map *resv_map = vma_resv_map(vma);
> > +
> > +               /* no free for anon vmas, but still need to unlock
> > */
> > +               up_write(&resv_map->rw_sema);
> >         }
> >  }
> 
> However, the check for 'if (__vma_private_lock(vma))' was dropped.

Oh ugh. I definitely added that in somewhere, but must
have committed that to the wrong git branch :(

Let me send out a new version with that change.

Sorry about that.

-- 
All Rights Reversed.

Re: [PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[Mike Kravetz]

On 09/25/23 23:10, riel@surriel.com wrote:
> From: Rik van Riel <riel@surriel.com>
> 
> Extend the locking scheme used to protect shared hugetlb mappings
> from truncate vs page fault races, in order to protect private
> hugetlb mappings (with resv_map) against MADV_DONTNEED.
> 
> Add a read-write semaphore to the resv_map data structure, and
> use that from the hugetlb_vma_(un)lock_* functions, in preparation
> for closing the race between MADV_DONTNEED and page faults.
> 
> Signed-off-by: Rik van Riel <riel@surriel.com>
> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
> ---
>  include/linux/hugetlb.h |  6 ++++++
>  mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
>  2 files changed, 43 insertions(+), 4 deletions(-)

My bad during the review of patch 2!

In reply to patch 1, I suggested the changes:

> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index f906c5fa4d09..8f3d5895fffc 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -372,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
>  		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
>  
>  		__hugetlb_vma_unlock_write_put(vma_lock);
> +	} else if (__vma_private_lock(vma)) {
> +		struct resv_map *resv_map = vma_resv_map(vma);
> +
> +		/* no free for anon vmas, but still need to unlock */
> +		up_write(&resv_map->rw_sema);
>  	}
>  }

However, the check for 'if (__vma_private_lock(vma))' was dropped.

> @@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
>  		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
>  
>  		__hugetlb_vma_unlock_write_put(vma_lock);
> +	} else {
> +		struct resv_map *resv_map = vma_resv_map(vma);
> +
> +		/* no free for anon vmas, but still need to unlock */
> +		up_write(&resv_map->rw_sema);
>  	}
>  }

So, the map_high_truncate_2 (2M: 32) libhugetlbfs test still BUGs with:

BUG: kernel NULL pointer dereference
-- 
Mike Kravetz

[PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[riel]

From: Rik van Riel <riel@surriel.com>

Extend the locking scheme used to protect shared hugetlb mappings
from truncate vs page fault races, in order to protect private
hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and
use that from the hugetlb_vma_(un)lock_* functions, in preparation
for closing the race between MADV_DONTNEED and page faults.

Signed-off-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b2626063f4f..694928fa06a3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -1231,6 +1232,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba6d39b71cb1..e859fba5bc7d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_read(&resv_map->rw_sema);
 	}
 }
 
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_read(&resv_map->rw_sema);
 	}
 }
 
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_write(&resv_map->rw_sema);
 	}
 }
 
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_write(&resv_map->rw_sema);
 	}
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	if (!__vma_shareable_lock(vma))
-		return 1;
+	if (__vma_shareable_lock(vma)) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	return down_write_trylock(&vma_lock->rw_sema);
+		return down_write_trylock(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		return down_write_trylock(&resv_map->rw_sema);
+	}
+
+	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		lockdep_assert_held(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		lockdep_assert_held(&resv_map->rw_sema);
 	}
 }
 
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }
 
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
+	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
-- 
2.41.0

Re: [PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[Mike Kravetz]

On 09/25/23 16:28, riel@surriel.com wrote:
> From: Rik van Riel <riel@surriel.com>
> 
> Extend the locking scheme used to protect shared hugetlb mappings
> from truncate vs page fault races, in order to protect private
> hugetlb mappings (with resv_map) against MADV_DONTNEED.

The only time an anon hugetlb mapping would not have a resv_map would
be in the case where MAP_NORESERVE was specified.  In this case the user
should be prepared for allocation failures.  I am good with this approach
not adding locking for the MAP_NORESERVE case.

> Add a read-write semaphore to the resv_map data structure, and
> use that from the hugetlb_vma_(un)lock_* functions, in preparation
> for closing the race between MADV_DONTNEED and page faults.
> 
> Signed-off-by: Rik van Riel <riel@surriel.com>
> ---
>  include/linux/hugetlb.h |  6 ++++++
>  mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
>  2 files changed, 43 insertions(+), 4 deletions(-)

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>

-- 
Mike Kravetz

[PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

[riel]

From: Rik van Riel <riel@surriel.com>

Extend the locking scheme used to protect shared hugetlb mappings
from truncate vs page fault races, in order to protect private
hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and
use that from the hugetlb_vma_(un)lock_* functions, in preparation
for closing the race between MADV_DONTNEED and page faults.

Signed-off-by: Rik van Riel <riel@surriel.com>
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b2626063f4f..694928fa06a3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -1231,6 +1232,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba6d39b71cb1..e859fba5bc7d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_read(&resv_map->rw_sema);
 	}
 }
 
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_read(&resv_map->rw_sema);
 	}
 }
 
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_write(&resv_map->rw_sema);
 	}
 }
 
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_write(&resv_map->rw_sema);
 	}
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	if (!__vma_shareable_lock(vma))
-		return 1;
+	if (__vma_shareable_lock(vma)) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	return down_write_trylock(&vma_lock->rw_sema);
+		return down_write_trylock(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		return down_write_trylock(&resv_map->rw_sema);
+	}
+
+	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		lockdep_assert_held(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		lockdep_assert_held(&resv_map->rw_sema);
 	}
 }
 
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }
 
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
+	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
-- 
2.41.0