From 38607c62b34b46317c46d5baf1df03ac6e48a1c6 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Fri, 28 Feb 2025 14:31:14 +1100 Subject: 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 Reviewed-by: Dan Williams Tested-by: Alison Schofield Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Asahi Lina Cc: Balbir Singh Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: Chunyan Zhang Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: Dave Hansen Cc: Dave Jiang Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Huacai Chen Cc: Ira Weiny Cc: Jan Kara Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: John Hubbard Cc: linmiaohe Cc: Logan Gunthorpe Cc: Matthew Wilcow (Oracle) Cc: Michael "Camp Drill Sergeant" Ellerman Cc: Nicholas Piggin Cc: Peter Xu Cc: Sven Schnelle Cc: Ted Ts'o Cc: Vasily Gorbik Cc: Vishal Verma Cc: Vivek Goyal Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- drivers/nvdimm/pmem.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/nvdimm') diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index d81faa9d89c9..785b2d2dbc82 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -513,7 +513,7 @@ static int pmem_attach_disk(struct device *dev, pmem->disk = disk; pmem->pgmap.owner = pmem; - pmem->pfn_flags = PFN_DEV; + pmem->pfn_flags = 0; if (is_nd_pfn(dev)) { pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; pmem->pgmap.ops = &fsdax_pagemap_ops; @@ -522,7 +522,6 @@ static int pmem_attach_disk(struct device *dev, pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); pmem->pfn_pad = resource_size(res) - range_len(&pmem->pgmap.range); - pmem->pfn_flags |= PFN_MAP; bb_range = pmem->pgmap.range; bb_range.start += pmem->data_offset; } else if (pmem_should_map_pages(dev)) { @@ -532,7 +531,6 @@ static int pmem_attach_disk(struct device *dev, pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); - pmem->pfn_flags |= PFN_MAP; bb_range = pmem->pgmap.range; } else { addr = devm_memremap(dev, pmem->phys_addr, -- cgit v1.2.3