fs/dax: properly refcount fs dax pages

Currently fs dax pages are considered free when the refcount drops to one
and their refcounts are not increased when mapped via PTEs or decreased
when unmapped.  This requires special logic in mm paths to detect that
these pages should not be properly refcounted, and to detect when the
refcount drops to one instead of zero.

On the other hand get_user_pages(), etc.  will properly refcount fs dax
pages by taking a reference and dropping it when the page is unpinned.

Tracking this special behaviour requires extra PTE bits (eg.  pte_devmap)
and introduces rules that are potentially confusing and specific to FS DAX
pages.  To fix this, and to possibly allow removal of the special PTE bits
in future, convert the fs dax page refcounts to be zero based and instead
take a reference on the page each time it is mapped as is currently the
case for normal pages.

This may also allow a future clean-up to remove the pgmap refcounting that
is currently done in mm/gup.c.

Link: https://lkml.kernel.org/r/c7d886ad7468a20452ef6e0ddab6cfe220874e7c.1740713401.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Asahi Lina <lina@asahilina.net>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: linmiaohe <linmiaohe@huawei.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Michael "Camp Drill Sergeant" Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 9 insertions, 27 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 2333c30f6d36..dcc9fcdf14e4 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -209,7 +209,7 @@ int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 
 static inline bool dax_page_is_idle(struct page *page)
 {
-	return page && page_ref_count(page) == 1;
+	return page && page_ref_count(page) == 0;
 }
 
 #if IS_ENABLED(CONFIG_DAX)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 009484a07074..de008efd96aa 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1192,6 +1192,8 @@ int vma_is_stack_for_current(struct vm_area_struct *vma);
 struct mmu_gather;
 struct inode;
 
+extern void prep_compound_page(struct page *page, unsigned int order);
+
 /*
  * compound_order() can be called without holding a reference, which means
  * that niceties like page_folio() don't work.  These callers should be
@@ -1513,25 +1515,6 @@ vm_fault_t finish_fault(struct vm_fault *vmf);
  *   back into memory.
  */
 
-#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
-DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-
-bool __put_devmap_managed_folio_refs(struct folio *folio, int refs);
-static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs)
-{
-	if (!static_branch_unlikely(&devmap_managed_key))
-		return false;
-	if (!folio_is_zone_device(folio))
-		return false;
-	return __put_devmap_managed_folio_refs(folio, refs);
-}
-#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs)
-{
-	return false;
-}
-#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-
 /* 127: arbitrary random number, small enough to assemble well */
 #define folio_ref_zero_or_close_to_overflow(folio) \
 	((unsigned int) folio_ref_count(folio) + 127u <= 127u)
@@ -1652,12 +1635,6 @@ static inline void put_page(struct page *page)
 	if (folio_test_slab(folio))
 		return;
 
-	/*
-	 * For some devmap managed pages we need to catch refcount transition
-	 * from 2 to 1:
-	 */
-	if (put_devmap_managed_folio_refs(folio, 1))
-		return;
 	folio_put(folio);
 }
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0fa7907d437e..b1827d78ff89 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -296,6 +296,8 @@ typedef struct {
  *    anonymous memory.
  * @index: Offset within the file, in units of pages.  For anonymous memory,
  *    this is the index from the beginning of the mmap.
+ * @share: number of DAX mappings that reference this folio. See
+ *    dax_associate_entry.
  * @private: Filesystem per-folio data (see folio_attach_private()).
  * @swap: Used for swp_entry_t if folio_test_swapcache().
  * @_mapcount: Do not access this member directly.  Use folio_mapcount() to
@@ -345,7 +347,10 @@ struct folio {
 				struct dev_pagemap *pgmap;
 			};
 			struct address_space *mapping;
-			pgoff_t index;
+			union {
+				pgoff_t index;
+				unsigned long share;
+			};
 			union {
 				void *private;
 				swp_entry_t swap;