From d5b3afea22a52517e6bc835432e6dfd079b8bf7c Mon Sep 17 00:00:00 2001
From: Alistair Popple <apopple@nvidia.com>
Date: Fri, 28 Feb 2025 14:31:00 +1100
Subject: fs/dax: create a common implementation to break DAX layouts

Prior to freeing a block file systems supporting FS DAX must check that
the associated pages are both unmapped from user-space and not undergoing
DMA or other access from eg.  get_user_pages().  This is achieved by
unmapping the file range and scanning the FS DAX page-cache to see if any
pages within the mapping have an elevated refcount.

This is done using two functions - dax_layout_busy_page_range() which
returns a page to wait for the refcount to become idle on.  Rather than
open-code this introduce a common implementation to both unmap and wait
for the page to become idle.

Link: https://lkml.kernel.org/r/c4d381e41fc618296cee2820403c166d80599d5c.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>
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: David Hildenbrand <david@redhat.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>
---
 include/linux/dax.h | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9b1ce984d410..a6b277f1e13a 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -207,12 +207,9 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		const struct iomap_ops *ops);
 
-static inline int dax_wait_page_idle(struct page *page,
-				void (cb)(struct inode *),
-				struct inode *inode)
+static inline bool dax_page_is_idle(struct page *page)
 {
-	return ___wait_var_event(page, page_ref_count(page) == 1,
-				TASK_INTERRUPTIBLE, 0, 0, cb(inode));
+	return page && page_ref_count(page) == 1;
 }
 
 #if IS_ENABLED(CONFIG_DAX)
@@ -228,6 +225,15 @@ static inline void dax_read_unlock(int id)
 {
 }
 #endif /* CONFIG_DAX */
+
+#if !IS_ENABLED(CONFIG_FS_DAX)
+static inline int __must_check dax_break_layout(struct inode *inode,
+			    loff_t start, loff_t end, void (cb)(struct inode *))
+{
+	return 0;
+}
+#endif
+
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
@@ -251,6 +257,13 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
+int __must_check dax_break_layout(struct inode *inode, loff_t start,
+				loff_t end, void (cb)(struct inode *));
+static inline int __must_check dax_break_layout_inode(struct inode *inode,
+						void (cb)(struct inode *))
+{
+	return dax_break_layout(inode, 0, LLONG_MAX, cb);
+}
 int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 				  struct inode *dest, loff_t destoff,
 				  loff_t len, bool *is_same,
-- 
cgit v1.2.3