* [PATCH] dcssblk: Mark DAX broken
@ 2024-09-24 22:59 Dan Williams
2024-09-24 23:26 ` Dan Williams
` (4 more replies)
0 siblings, 5 replies; 7+ messages in thread
From: Dan Williams @ 2024-09-24 22:59 UTC (permalink / raw)
To: hca, gor, agordeev
Cc: Gerald Schaefer, Christian Borntraeger, Sven Schnelle, Jan Kara,
Matthew Wilcox, Christoph Hellwig, Alistair Popple, linux-s390,
linux-mm
The dcssblk driver has long needed special case supoprt to enable
limited dax operation, so called CONFIG_FS_DAX_LIMITED. This mode
works around the incomplete support for ZONE_DEVICE on s390 by forgoing
the ability of dax-mapped pages to support GUP.
Now, pending cleanups to fsdax that fix its reference counting [1] depend on
the ability of all dax drivers to supply ZONE_DEVICE pages.
To allow that work to move forward, dax support needs to be paused for
dcssblk until ZONE_DEVICE support arrives. That work has been known for
a few years [2], and the removal of "pte_devmap" requirements [3] makes the
conversion easier.
For now, place the support behind CONFIG_BROKEN, and remove PFN_SPECIAL
(dcssblk was the only user).
Link: http://lore.kernel.org/cover.9f0e45d52f5cff58807831b6b867084d0b14b61c.1725941415.git-series.apopple@nvidia.com [1]
Link: http://lore.kernel.org/20210820210318.187742e8@thinkpad/ [2]
Link: http://lore.kernel.org/4511465a4f8429f45e2ac70d2e65dc5e1df1eb47.1725941415.git-series.apopple@nvidia.com [3]
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/s390/block/Kconfig | 12 ++++++++++--
drivers/s390/block/dcssblk.c | 26 +++++++++++++++++---------
fs/Kconfig | 9 +--------
fs/dax.c | 12 ------------
include/linux/pfn_t.h | 15 ---------------
mm/memory.c | 2 --
mm/memremap.c | 4 ----
7 files changed, 28 insertions(+), 52 deletions(-)
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index e3710a762aba..4bfe469c04aa 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -4,13 +4,21 @@ comment "S/390 block device drivers"
config DCSSBLK
def_tristate m
- select FS_DAX_LIMITED
- select DAX
prompt "DCSSBLK support"
depends on S390 && BLOCK
help
Support for dcss block device
+config DCSSBLK_DAX
+ def_bool y
+ depends on DCSSBLK
+ # requires S390 ZONE_DEVICE support
+ depends on BROKEN
+ select DAX
+ prompt "DCSSBLK DAX support"
+ help
+ Enable DAX operation for the dcss block device
+
config DASD
def_tristate y
prompt "Support for DASD devices"
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 02a4a51da1b7..d1bc79cf56bd 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -540,6 +540,21 @@ static const struct attribute_group *dcssblk_dev_attr_groups[] = {
NULL,
};
+static int dcssblk_setup_dax(struct dcssblk_dev_info *dev_info)
+{
+ struct dax_device *dax_dev;
+
+ if (!IS_ENABLED(CONFIG_DCSSBLK_DAX))
+ return 0;
+
+ dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops);
+ if (IS_ERR(dax_dev))
+ return PTR_ERR(dax_dev);
+ set_dax_synchronous(dax_dev);
+ dev_info->dax_dev = dax_dev;
+ return dax_add_host(dev_info->dax_dev, dev_info->gd);
+}
+
/*
* device attribute for adding devices
*/
@@ -680,14 +695,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
if (rc)
goto put_dev;
- dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops);
- if (IS_ERR(dax_dev)) {
- rc = PTR_ERR(dax_dev);
- goto put_dev;
- }
- set_dax_synchronous(dax_dev);
- dev_info->dax_dev = dax_dev;
- rc = dax_add_host(dev_info->dax_dev, dev_info->gd);
+ rc = dcssblk_setup_dax(dev_info);
if (rc)
goto out_dax;
@@ -923,7 +931,7 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
*kaddr = __va(dev_info->start + offset);
if (pfn)
*pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset),
- PFN_DEV|PFN_SPECIAL);
+ PFN_DEV);
return (dev_sz - offset) / PAGE_SIZE;
}
diff --git a/fs/Kconfig b/fs/Kconfig
index 0e4efec1d92e..a6f4f28fa09e 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -60,7 +60,7 @@ endif # BLOCK
config FS_DAX
bool "File system based Direct Access (DAX) support"
depends on MMU
- depends on ZONE_DEVICE || FS_DAX_LIMITED
+ depends on ZONE_DEVICE
select FS_IOMAP
select DAX
help
@@ -96,13 +96,6 @@ config FS_DAX_PMD
depends on ZONE_DEVICE
depends on TRANSPARENT_HUGEPAGE
-# Selected by DAX drivers that do not expect filesystem DAX to support
-# get_user_pages() of DAX mappings. I.e. "limited" indicates no support
-# for fork() of processes with MAP_SHARED mappings or support for
-# direct-I/O to a DAX mapping.
-config FS_DAX_LIMITED
- bool
-
# Posix ACL utility routines
#
# Note: Posix ACLs can be implemented without these helpers. Never use
diff --git a/fs/dax.c b/fs/dax.c
index becb4a6920c6..6257d3fdf8f8 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -359,9 +359,6 @@ static void dax_associate_entry(void *entry, struct address_space *mapping,
unsigned long size = dax_entry_size(entry), pfn, index;
int i = 0;
- if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
- return;
-
index = linear_page_index(vma, address & ~(size - 1));
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
@@ -381,9 +378,6 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
{
unsigned long pfn;
- if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
- return;
-
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
@@ -684,12 +678,6 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping,
pgoff_t end_idx;
XA_STATE(xas, &mapping->i_pages, start_idx);
- /*
- * In the 'limited' case get_user_pages() for dax is disabled.
- */
- if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
- return NULL;
-
if (!dax_mapping(mapping) || !mapping_mapped(mapping))
return NULL;
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 2d9148221e9a..eb8da94d1d19 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -9,18 +9,14 @@
* PFN_SG_LAST - pfn references a page and is the last scatterlist entry
* PFN_DEV - pfn is not covered by system memmap by default
* PFN_MAP - pfn has a dynamic page mapping established by a device driver
- * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not
- * get_user_pages
*/
#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
-#define PFN_SPECIAL (1ULL << (BITS_PER_LONG_LONG - 5))
#define PFN_FLAGS_TRACE \
- { PFN_SPECIAL, "SPECIAL" }, \
{ PFN_SG_CHAIN, "SG_CHAIN" }, \
{ PFN_SG_LAST, "SG_LAST" }, \
{ PFN_DEV, "DEV" }, \
@@ -117,15 +113,4 @@ pud_t pud_mkdevmap(pud_t pud);
#endif
#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
-#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
-static inline bool pfn_t_special(pfn_t pfn)
-{
- return (pfn.val & PFN_SPECIAL) == PFN_SPECIAL;
-}
-#else
-static inline bool pfn_t_special(pfn_t pfn)
-{
- return false;
-}
-#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
#endif /* _LINUX_PFN_T_H_ */
diff --git a/mm/memory.c b/mm/memory.c
index c31ea300cdf6..676f5cda992a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2462,8 +2462,6 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite)
return true;
if (pfn_t_devmap(pfn))
return true;
- if (pfn_t_special(pfn))
- return true;
if (is_zero_pfn(pfn_t_to_pfn(pfn)))
return true;
return false;
diff --git a/mm/memremap.c b/mm/memremap.c
index 40d4547ce514..a6bbbe180eab 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -332,10 +332,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
}
break;
case MEMORY_DEVICE_FS_DAX:
- if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
- WARN(1, "File system DAX not supported\n");
- return ERR_PTR(-EINVAL);
- }
params.pgprot = pgprot_decrypted(params.pgprot);
break;
case MEMORY_DEVICE_GENERIC:
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH] dcssblk: Mark DAX broken
2024-09-24 22:59 [PATCH] dcssblk: Mark DAX broken Dan Williams
@ 2024-09-24 23:26 ` Dan Williams
2024-09-25 4:29 ` kernel test robot
` (3 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: Dan Williams @ 2024-09-24 23:26 UTC (permalink / raw)
To: Dan Williams, hca, gor, agordeev
Cc: Gerald Schaefer, Christian Borntraeger, Sven Schnelle, Jan Kara,
Matthew Wilcox, Christoph Hellwig, Alistair Popple, linux-s390,
linux-mm
Dan Williams wrote:
> The dcssblk driver has long needed special case supoprt to enable
> limited dax operation, so called CONFIG_FS_DAX_LIMITED. This mode
> works around the incomplete support for ZONE_DEVICE on s390 by forgoing
> the ability of dax-mapped pages to support GUP.
>
> Now, pending cleanups to fsdax that fix its reference counting [1] depend on
> the ability of all dax drivers to supply ZONE_DEVICE pages.
>
> To allow that work to move forward, dax support needs to be paused for
> dcssblk until ZONE_DEVICE support arrives. That work has been known for
> a few years [2], and the removal of "pte_devmap" requirements [3] makes the
> conversion easier.
>
> For now, place the support behind CONFIG_BROKEN, and remove PFN_SPECIAL
> (dcssblk was the only user).
>
> Link: http://lore.kernel.org/cover.9f0e45d52f5cff58807831b6b867084d0b14b61c.1725941415.git-series.apopple@nvidia.com [1]
> Link: http://lore.kernel.org/20210820210318.187742e8@thinkpad/ [2]
> Link: http://lore.kernel.org/4511465a4f8429f45e2ac70d2e65dc5e1df1eb47.1725941415.git-series.apopple@nvidia.com [3]
> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
> Cc: Heiko Carstens <hca@linux.ibm.com>
> Cc: Vasily Gorbik <gor@linux.ibm.com>
> Cc: Alexander Gordeev <agordeev@linux.ibm.com>
> Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
> Cc: Sven Schnelle <svens@linux.ibm.com>
> Cc: Jan Kara <jack@suse.cz>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Alistair Popple <apopple@nvidia.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
> drivers/s390/block/Kconfig | 12 ++++++++++--
> drivers/s390/block/dcssblk.c | 26 +++++++++++++++++---------
> fs/Kconfig | 9 +--------
> fs/dax.c | 12 ------------
> include/linux/pfn_t.h | 15 ---------------
> mm/memory.c | 2 --
> mm/memremap.c | 4 ----
> 7 files changed, 28 insertions(+), 52 deletions(-)
As additional motivation, with this addressed, pfn_t can also be removed
for "moar red-diff!": 44 files changed, 141 insertions(+), 301 deletions(-)
Patch below is on top of Alistair's series. It will need to be rebased
on top of the final version of that, but here it is for demonstration
purposes.
-- >8 --
Subject: mm: Remove pfn_t
From: Dan Williams <dan.j.williams@intel.com>
The pfn_t type was created to convey mapping constraints from
->direct_acces() methods to core mm helpers like vmf_insert_mixed(). Now
that all ->direct_access() helpers return ZONE_DEVICE pages, and
ZONE_DEVICE pages no longer require pte_devmap, there is no longer a
need for pfn_t.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/x86/mm/pat/memtype.c | 5 +-
drivers/dax/device.c | 19 +++---
drivers/dax/hmem/hmem.c | 1
drivers/dax/kmem.c | 1
drivers/dax/pmem.c | 1
drivers/dax/pmem/pmem.c | 1
drivers/dax/super.c | 3 -
drivers/gpu/drm/exynos/exynos_drm_gem.c | 1
drivers/gpu/drm/gma500/fbdev.c | 3 -
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 1
drivers/gpu/drm/msm/msm_gem.c | 1
drivers/gpu/drm/omapdrm/omap_gem.c | 7 +-
drivers/gpu/drm/v3d/v3d_bo.c | 1
drivers/md/dm-linear.c | 4 +
drivers/md/dm-log-writes.c | 5 +-
drivers/md/dm-stripe.c | 4 +
drivers/md/dm-target.c | 4 +
drivers/md/dm-writecache.c | 16 +----
drivers/md/dm.c | 4 +
drivers/nvdimm/pmem.c | 15 ++---
drivers/nvdimm/pmem.h | 6 +-
drivers/s390/block/dcssblk.c | 21 +++----
fs/cramfs/inode.c | 4 +
fs/dax.c | 53 +++++++++--------
fs/ext4/file.c | 2 -
fs/fuse/dax.c | 3 -
fs/fuse/virtio_fs.c | 5 +-
fs/xfs/xfs_file.c | 2 -
include/linux/dax.h | 12 ++--
include/linux/device-mapper.h | 7 +-
include/linux/huge_mm.h | 8 +--
include/linux/mm.h | 7 +-
include/linux/pfn.h | 13 ----
include/linux/pfn_t.h | 96 ------------------------------
include/linux/pgtable.h | 4 +
include/trace/events/fs_dax.h | 14 ++--
mm/debug_vm_pgtable.c | 1
mm/huge_memory.c | 27 ++++----
mm/memory.c | 38 +++++-------
mm/memremap.c | 1
mm/migrate.c | 1
tools/testing/nvdimm/pmem-dax.c | 8 +--
tools/testing/nvdimm/test/iomap.c | 11 ---
tools/testing/nvdimm/test/nfit_test.h | 1
44 files changed, 141 insertions(+), 301 deletions(-)
delete mode 100644 include/linux/pfn_t.h
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index eb84593cf95c..da57ccb2da34 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -36,7 +36,6 @@
#include <linux/debugfs.h>
#include <linux/ioport.h>
#include <linux/kernel.h>
-#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/highmem.h>
@@ -1074,7 +1073,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
return 0;
}
-void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
+void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn)
{
enum page_cache_mode pcm;
@@ -1082,7 +1081,7 @@ void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
return;
/* Set prot based on lookup */
- pcm = lookup_memtype(pfn_t_to_phys(pfn));
+ pcm = lookup_memtype(PFN_PHYS(pfn));
*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
cachemode2protval(pcm));
}
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 4d3ddd128790..aae90a5bcd30 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -4,7 +4,6 @@
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/device.h>
-#include <linux/pfn_t.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/dax.h>
@@ -73,8 +72,8 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
return -1;
}
-static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn,
- unsigned long fault_size)
+static void dax_set_mapping(struct vm_fault *vmf, unsigned long pfn,
+ unsigned long fault_size)
{
unsigned long i, nr_pages = fault_size / PAGE_SIZE;
struct file *filp = vmf->vma->vm_file;
@@ -89,7 +88,7 @@ static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn,
ALIGN(vmf->address, fault_size));
for (i = 0; i < nr_pages; i++) {
- struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
+ struct page *page = pfn_to_page(pfn + i);
page = compound_head(page);
if (page->mapping)
@@ -105,7 +104,7 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
{
struct device *dev = &dev_dax->dev;
phys_addr_t phys;
- pfn_t pfn;
+ unsigned long pfn;
unsigned int fault_size = PAGE_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
@@ -126,7 +125,7 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
return VM_FAULT_SIGBUS;
}
- pfn = phys_to_pfn_t(phys, 0);
+ pfn = PHYS_PFN(phys);
dax_set_mapping(vmf, pfn, fault_size);
@@ -140,7 +139,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
struct device *dev = &dev_dax->dev;
phys_addr_t phys;
pgoff_t pgoff;
- pfn_t pfn;
+ unsigned long pfn;
unsigned int fault_size = PMD_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
@@ -169,7 +168,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
return VM_FAULT_SIGBUS;
}
- pfn = phys_to_pfn_t(phys, 0);
+ pfn = PHYS_PFN(phys);
dax_set_mapping(vmf, pfn, fault_size);
@@ -184,7 +183,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
struct device *dev = &dev_dax->dev;
phys_addr_t phys;
pgoff_t pgoff;
- pfn_t pfn;
+ unsigned long pfn;
unsigned int fault_size = PUD_SIZE;
@@ -214,7 +213,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
return VM_FAULT_SIGBUS;
}
- pfn = phys_to_pfn_t(phys, 0);
+ pfn = PHYS_PFN(phys);
dax_set_mapping(vmf, pfn, fault_size);
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index 5e7c53f18491..c18451a37e4f 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -2,7 +2,6 @@
#include <linux/platform_device.h>
#include <linux/memregion.h>
#include <linux/module.h>
-#include <linux/pfn_t.h>
#include <linux/dax.h>
#include "../bus.h"
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index e97d47f42ee2..87b5321675ff 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -5,7 +5,6 @@
#include <linux/memory.h>
#include <linux/module.h>
#include <linux/device.h>
-#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/dax.h>
#include <linux/fs.h>
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index c8ebf4e281f2..bee93066a849 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -2,7 +2,6 @@
/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
#include <linux/memremap.h>
#include <linux/module.h>
-#include <linux/pfn_t.h>
#include "../nvdimm/pfn.h"
#include "../nvdimm/nd.h"
#include "bus.h"
diff --git a/drivers/dax/pmem/pmem.c b/drivers/dax/pmem/pmem.c
index dfe91a2990fe..ce3394617d15 100644
--- a/drivers/dax/pmem/pmem.c
+++ b/drivers/dax/pmem/pmem.c
@@ -3,7 +3,6 @@
#include <linux/percpu-refcount.h>
#include <linux/memremap.h>
#include <linux/module.h>
-#include <linux/pfn_t.h>
#include <linux/nd.h>
#include "../bus.h"
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 57a94a6c00e5..3706d803acbf 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -7,7 +7,6 @@
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/magic.h>
-#include <linux/pfn_t.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/uio.h>
@@ -148,7 +147,7 @@ enum dax_device_flags {
* pages accessible at the device relative @pgoff.
*/
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
- enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
+ enum dax_access_mode mode, void **kaddr, unsigned long *pfn)
{
long avail;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 638ca96830e9..ab8d6cea09f5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -7,7 +7,6 @@
#include <linux/dma-buf.h>
-#include <linux/pfn_t.h>
#include <linux/shmem_fs.h>
#include <linux/module.h>
diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c
index 98b44974d42d..997c9038db38 100644
--- a/drivers/gpu/drm/gma500/fbdev.c
+++ b/drivers/gpu/drm/gma500/fbdev.c
@@ -6,7 +6,6 @@
**************************************************************************/
#include <linux/fb.h>
-#include <linux/pfn_t.h>
#include <drm/drm_crtc_helper.h>
#include <drm/drm_drv.h>
@@ -33,7 +32,7 @@ static vm_fault_t psb_fbdev_vm_fault(struct vm_fault *vmf)
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
for (i = 0; i < page_num; ++i) {
- err = vmf_insert_mixed(vma, address, __pfn_to_pfn_t(pfn, PFN_DEV));
+ err = vmf_insert_mixed(vma, address, pfn);
if (unlikely(err & VM_FAULT_ERROR))
break;
address += PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index cac6d4184506..4faab805909d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -6,7 +6,6 @@
#include <linux/anon_inodes.h>
#include <linux/mman.h>
-#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <drm/drm_cache.h>
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index ebc9ba66efb8..1c275008b223 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -9,7 +9,6 @@
#include <linux/spinlock.h>
#include <linux/shmem_fs.h>
#include <linux/dma-buf.h>
-#include <linux/pfn_t.h>
#include <drm/drm_prime.h>
#include <drm/drm_file.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index fdae677558f3..5523196f5b28 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -8,7 +8,6 @@
#include <linux/seq_file.h>
#include <linux/shmem_fs.h>
#include <linux/spinlock.h>
-#include <linux/pfn_t.h>
#include <linux/vmalloc.h>
#include <drm/drm_prime.h>
@@ -371,8 +370,7 @@ static vm_fault_t omap_gem_fault_1d(struct drm_gem_object *obj,
VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
pfn, pfn << PAGE_SHIFT);
- return vmf_insert_mixed(vma, vmf->address,
- __pfn_to_pfn_t(pfn, PFN_DEV));
+ return vmf_insert_mixed(vma, vmf->address, pfn);
}
/* Special handling for the case of faulting in 2d tiled buffers */
@@ -467,8 +465,7 @@ static vm_fault_t omap_gem_fault_2d(struct drm_gem_object *obj,
pfn, pfn << PAGE_SHIFT);
for (i = n; i > 0; i--) {
- ret = vmf_insert_mixed(vma,
- vaddr, __pfn_to_pfn_t(pfn, PFN_DEV));
+ ret = vmf_insert_mixed(vma, vaddr, pfn);
if (ret & VM_FAULT_ERROR)
break;
pfn += priv->usergart[fmt].stride_pfn;
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index a165cbcdd27b..091bc758b23a 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -20,7 +20,6 @@
*/
#include <linux/dma-buf.h>
-#include <linux/pfn_t.h>
#include <linux/vmalloc.h>
#include "v3d_drv.h"
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 49fb0f684193..211528d1eebf 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -167,8 +167,8 @@ static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
}
static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 8d7df8303d0a..63037f0cd277 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -890,8 +890,9 @@ static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
}
static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ long nr_pages,
+ enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4112071de0be..b13c43d716f1 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -315,8 +315,8 @@ static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
}
static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 652627aea11b..6dfb6d680f2c 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -254,8 +254,8 @@ static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits)
}
static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
return -EIO;
}
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 7ce8847b3404..2c841e30ae92 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -13,7 +13,6 @@
#include <linux/dm-io.h>
#include <linux/dm-kcopyd.h>
#include <linux/dax.h>
-#include <linux/pfn_t.h>
#include <linux/libnvdimm.h>
#include <linux/delay.h>
#include "dm-io-tracker.h"
@@ -256,7 +255,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
int r;
loff_t s;
long p, da;
- pfn_t pfn;
+ unsigned long pfn;
int id;
struct page **pages;
sector_t offset;
@@ -290,11 +289,6 @@ static int persistent_memory_claim(struct dm_writecache *wc)
r = da;
goto err2;
}
- if (!pfn_t_has_page(pfn)) {
- wc->memory_map = NULL;
- r = -EOPNOTSUPP;
- goto err2;
- }
if (da != p) {
long i;
@@ -314,13 +308,9 @@ static int persistent_memory_claim(struct dm_writecache *wc)
r = daa ? daa : -EINVAL;
goto err3;
}
- if (!pfn_t_has_page(pfn)) {
- r = -EOPNOTSUPP;
- goto err3;
- }
while (daa-- && i < p) {
- pages[i++] = pfn_t_to_page(pfn);
- pfn.val++;
+ pages[i++] = pfn_to_page(pfn);
+ pfn++;
if (!(i & 15))
cond_resched();
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 87bb90303435..d24324c49433 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1231,8 +1231,8 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
}
static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
struct mapped_device *md = dax_get_private(dax_dev);
sector_t sector = pgoff * PAGE_SECTORS;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 451cd0fa0c94..d3b3febc8124 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -20,7 +20,6 @@
#include <linux/kstrtox.h>
#include <linux/vmalloc.h>
#include <linux/blk-mq.h>
-#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/uio.h>
#include <linux/dax.h>
@@ -242,7 +241,7 @@ static void pmem_submit_bio(struct bio *bio)
/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
__weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ unsigned long *pfn)
{
resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
@@ -254,7 +253,7 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
if (kaddr)
*kaddr = pmem->virt_addr + offset;
if (pfn)
- *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+ *pfn = PHYS_PFN(pmem->phys_addr + offset);
if (bb->count &&
badblocks_check(bb, sector, num, &first_bad, &num_bad)) {
@@ -301,9 +300,9 @@ static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
PAGE_SIZE));
}
-static long pmem_dax_direct_access(struct dax_device *dax_dev,
- pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
- void **kaddr, pfn_t *pfn)
+static long pmem_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
struct pmem_device *pmem = dax_get_private(dax_dev);
@@ -432,7 +431,8 @@ static void pmem_release_disk(void *__pmem)
}
static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap,
- unsigned long pfn, unsigned long nr_pages, int mf_flags)
+ unsigned long pfn,
+ unsigned long nr_pages, int mf_flags)
{
struct pmem_device *pmem =
container_of(pgmap, struct pmem_device, pgmap);
@@ -513,7 +513,6 @@ static int pmem_attach_disk(struct device *dev,
pmem->disk = disk;
pmem->pgmap.owner = pmem;
- pmem->pfn_flags = 0;
if (is_nd_pfn(dev)) {
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
pmem->pgmap.ops = &fsdax_pagemap_ops;
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index 392b0b38acb9..99ce3ac51fdd 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -5,7 +5,6 @@
#include <linux/badblocks.h>
#include <linux/memremap.h>
#include <linux/types.h>
-#include <linux/pfn_t.h>
#include <linux/fs.h>
enum dax_access_mode;
@@ -16,7 +15,6 @@ struct pmem_device {
phys_addr_t phys_addr;
/* when non-zero this device is hosting a 'pfn' instance */
phys_addr_t data_offset;
- u64 pfn_flags;
void *virt_addr;
/* immutable base size of the namespace */
size_t size;
@@ -30,8 +28,8 @@ struct pmem_device {
};
long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn);
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn);
#ifdef CONFIG_MEMORY_FAILURE
static inline bool test_and_clear_pmem_poison(struct page *page)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index d1bc79cf56bd..9b537020fe25 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -17,7 +17,6 @@
#include <linux/blkdev.h>
#include <linux/completion.h>
#include <linux/interrupt.h>
-#include <linux/pfn_t.h>
#include <linux/uio.h>
#include <linux/dax.h>
#include <linux/io.h>
@@ -32,8 +31,8 @@ static int dcssblk_open(struct gendisk *disk, blk_mode_t mode);
static void dcssblk_release(struct gendisk *disk);
static void dcssblk_submit_bio(struct bio *bio);
static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn);
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn);
static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
@@ -919,9 +918,9 @@ dcssblk_submit_bio(struct bio *bio)
bio_io_error(bio);
}
-static long
-__dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
+static long __dcssblk_direct_access(struct dcssblk_dev_info *dev_info,
+ pgoff_t pgoff, long nr_pages, void **kaddr,
+ unsigned long *pfn)
{
resource_size_t offset = pgoff * PAGE_SIZE;
unsigned long dev_sz;
@@ -930,16 +929,14 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
if (kaddr)
*kaddr = __va(dev_info->start + offset);
if (pfn)
- *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset),
- PFN_DEV);
+ *pfn = PFN_DOWN(dev_info->start + offset);
return (dev_sz - offset) / PAGE_SIZE;
}
-static long
-dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
struct dcssblk_dev_info *dev_info = dax_get_private(dax_dev);
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index b84d1747a020..ba7f7ca2aebc 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -17,7 +17,6 @@
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
-#include <linux/pfn_t.h>
#include <linux/ramfs.h>
#include <linux/init.h>
#include <linux/string.h>
@@ -412,7 +411,8 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
for (i = 0; i < pages && !ret; i++) {
vm_fault_t vmf;
unsigned long off = i * PAGE_SIZE;
- pfn_t pfn = phys_to_pfn_t(address + off, PFN_DEV);
+ unsigned long pfn = PHYS_PFN(address + off);
+
vmf = vmf_insert_mixed(vma, vma->vm_start + off, pfn);
if (vmf & VM_FAULT_ERROR)
ret = vm_fault_to_errno(vmf, 0);
diff --git a/fs/dax.c b/fs/dax.c
index 72d6d4586330..fcbe62bde685 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -20,7 +20,6 @@
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
-#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
@@ -76,9 +75,9 @@ static struct folio *dax_to_folio(void *entry)
return page_folio(pfn_to_page(dax_to_pfn(entry)));
}
-static void *dax_make_entry(pfn_t pfn, unsigned long flags)
+static void *dax_make_entry(unsigned long pfn, unsigned long flags)
{
- return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
+ return xa_mk_value(flags | (pfn << DAX_SHIFT));
}
static bool dax_is_locked(void *entry)
@@ -612,7 +611,7 @@ static void *grab_mapping_entry(struct xa_state *xas,
if (order > 0)
flags |= DAX_PMD;
- entry = dax_make_entry(pfn_to_pfn_t(0), flags);
+ entry = dax_make_entry(0, flags);
dax_lock_entry(xas, entry);
if (xas_error(xas))
goto out_unlock;
@@ -837,7 +836,7 @@ static bool dax_fault_is_synchronous(const struct iomap_iter *iter,
* appropriate.
*/
static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
- const struct iomap_iter *iter, void *entry, pfn_t pfn,
+ const struct iomap_iter *iter, void *entry, unsigned long pfn,
unsigned long flags)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
@@ -1036,7 +1035,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
- size_t size, void **kaddr, pfn_t *pfnp)
+ size_t size, void **kaddr,
+ unsigned long *pfnp)
{
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
int id, rc = 0;
@@ -1054,7 +1054,7 @@ static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
rc = -EINVAL;
if (PFN_PHYS(length) < size)
goto out;
- if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
+ if (*pfnp & (PHYS_PFN(size)-1))
goto out;
rc = 0;
@@ -1158,8 +1158,8 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf,
{
struct inode *inode = iter->inode;
unsigned long vaddr = vmf->address;
- pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
- struct page *page = pfn_t_to_page(pfn);
+ unsigned long pfn = my_zero_pfn(vaddr);
+ struct page *page = pfn_to_page(pfn);
vm_fault_t ret;
*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE);
@@ -1183,7 +1183,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
struct folio *zero_folio;
spinlock_t *ptl;
pmd_t pmd_entry;
- pfn_t pfn;
+ unsigned long pfn;
if (arch_needs_pgtable_deposit()) {
pgtable = pte_alloc_one(vma->vm_mm);
@@ -1195,7 +1195,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
if (unlikely(!zero_folio))
goto fallback;
- pfn = page_to_pfn_t(&zero_folio->page);
+ pfn = page_to_pfn(&zero_folio->page);
*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn,
DAX_PMD | DAX_ZERO_PAGE);
@@ -1564,7 +1564,7 @@ static vm_fault_t dax_fault_return(int error)
* insertion for now and return the pfn so that caller can insert it after the
* fsync is done.
*/
-static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
+static vm_fault_t dax_fault_synchronous_pfnp(unsigned long *pfnp, unsigned long pfn)
{
if (WARN_ON_ONCE(!pfnp))
return VM_FAULT_SIGBUS;
@@ -1612,8 +1612,9 @@ static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf,
* @pmd: distinguish whether it is a pmd fault
*/
static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
- const struct iomap_iter *iter, pfn_t *pfnp,
- struct xa_state *xas, void **entry, bool pmd)
+ const struct iomap_iter *iter,
+ unsigned long *pfnp, struct xa_state *xas,
+ void **entry, bool pmd)
{
const struct iomap *iomap = &iter->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
@@ -1622,7 +1623,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
bool write = iter->flags & IOMAP_WRITE;
unsigned long entry_flags = pmd ? DAX_PMD : 0;
int ret, err = 0;
- pfn_t pfn;
+ unsigned long pfn;
void *kaddr;
struct page *page;
@@ -1657,7 +1658,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
if (dax_fault_is_synchronous(iter, vmf->vma))
return dax_fault_synchronous_pfnp(pfnp, pfn);
- page = pfn_t_to_page(pfn);
+ page = pfn_to_page(pfn);
page_ref_inc(page);
if (pmd)
@@ -1674,8 +1675,9 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
return ret;
}
-static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
- int *iomap_errp, const struct iomap_ops *ops)
+static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, unsigned long *pfnp,
+ int *iomap_errp,
+ const struct iomap_ops *ops)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
XA_STATE(xas, &mapping->i_pages, vmf->pgoff);
@@ -1784,7 +1786,7 @@ static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
return false;
}
-static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
+static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, unsigned long *pfnp,
const struct iomap_ops *ops)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
@@ -1863,8 +1865,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
return ret;
}
#else
-static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
- const struct iomap_ops *ops)
+static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, unsigned long *pfnp,
+ const struct iomap_ops *ops)
{
return VM_FAULT_FALLBACK;
}
@@ -1884,7 +1886,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
* successfully.
*/
vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
- pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops)
+ unsigned long *pfnp, int *iomap_errp,
+ const struct iomap_ops *ops)
{
if (order == 0)
return dax_iomap_pte_fault(vmf, pfnp, iomap_errp, ops);
@@ -1905,7 +1908,7 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault);
* for an mmaped DAX file. It also marks the page cache entry as dirty.
*/
static vm_fault_t
-dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
+dax_insert_pfn_mkwrite(struct vm_fault *vmf, unsigned long pfn, unsigned int order)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, order);
@@ -1927,7 +1930,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
xas_set_mark(&xas, PAGECACHE_TAG_DIRTY);
dax_lock_entry(&xas, entry);
xas_unlock_irq(&xas);
- page = pfn_t_to_page(pfn);
+ page = pfn_to_page(pfn);
page_ref_inc(page);
if (order == 0)
ret = dax_insert_pfn(vmf, pfn, true);
@@ -1954,7 +1957,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
* table entry.
*/
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order,
- pfn_t pfn)
+ unsigned long pfn)
{
int err;
loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index c89e434db6b7..13e939bcc7ac 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -722,7 +722,7 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, unsigned int order)
bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED);
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
- pfn_t pfn;
+ unsigned long pfn;
if (write) {
sb_start_pagefault(sb);
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index da505956208f..0b6b440520da 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -10,7 +10,6 @@
#include <linux/dax.h>
#include <linux/uio.h>
#include <linux/pagemap.h>
-#include <linux/pfn_t.h>
#include <linux/iomap.h>
#include <linux/interval_tree.h>
@@ -788,7 +787,7 @@ static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf, unsigned int order,
vm_fault_t ret;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct super_block *sb = inode->i_sb;
- pfn_t pfn;
+ unsigned long pfn;
int error = 0;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_conn_dax *fcd = fc->dax;
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index f79a94d148da..e49e2ae33206 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -9,7 +9,6 @@
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/group_cpus.h>
-#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/module.h>
#include <linux/virtio.h>
@@ -866,7 +865,7 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev)
*/
static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
long nr_pages, enum dax_access_mode mode,
- void **kaddr, pfn_t *pfn)
+ void **kaddr, unsigned long *pfn)
{
struct virtio_fs *fs = dax_get_private(dax_dev);
phys_addr_t offset = PFN_PHYS(pgoff);
@@ -875,7 +874,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
if (kaddr)
*kaddr = fs->window_kaddr + offset;
if (pfn)
- *pfn = phys_to_pfn_t(fs->window_phys_addr + offset, 0);
+ *pfn = PHYS_PFN(fs->window_phys_addr + offset);
return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
}
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 4cdc54dc9686..47edb2785ad2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1243,7 +1243,7 @@ xfs_dax_fault_locked(
bool write_fault)
{
vm_fault_t ret;
- pfn_t pfn;
+ unsigned long pfn;
if (!IS_ENABLED(CONFIG_FS_DAX)) {
ASSERT(0);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 0f6f355ec3b5..153dd2398178 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -26,7 +26,7 @@ struct dax_operations {
* number of pages available for DAX at that pfn.
*/
long (*direct_access)(struct dax_device *, pgoff_t, long,
- enum dax_access_mode, void **, pfn_t *);
+ enum dax_access_mode, void **, unsigned long *);
/*
* Validate whether this device is usable as an fsdax backing
* device.
@@ -241,7 +241,8 @@ static inline void dax_read_unlock(int id)
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,
- enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
+ enum dax_access_mode mode, void **kaddr,
+ unsigned long *pfn);
size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
size_t bytes, struct iov_iter *i);
size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
@@ -255,9 +256,10 @@ void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops);
vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
- pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
-vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
- unsigned int order, pfn_t pfn);
+ unsigned long *pfnp, int *errp,
+ const struct iomap_ops *ops);
+vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order,
+ unsigned long pfn);
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);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 53ca3a913d06..05fadca5b588 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -147,9 +147,10 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
* < 0 : error
* >= 0 : the number of bytes accessible at the address
*/
-typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode node, void **kaddr,
- pfn_t *pfn);
+typedef long (*dm_dax_direct_access_fn)(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages,
+ enum dax_access_mode node, void **kaddr,
+ unsigned long *pfn);
typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
size_t nr_pages);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 79a24ac31080..a047379d94ad 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -38,10 +38,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr, pgprot_t newprot,
unsigned long cp_flags);
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t dax_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, bool write);
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, bool write);
+vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, bool write);
+vm_fault_t dax_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, bool write);
enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_UNSUPPORTED,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d9517e109ac3..41a419c549ef 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3437,14 +3437,15 @@ int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
-vm_fault_t dax_insert_pfn(struct vm_fault *vmf, pfn_t pfn_t, bool write);
+vm_fault_t dax_insert_pfn(struct vm_fault *vmf, unsigned long pfn, bool write);
vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, pgprot_t pgprot);
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
- pfn_t pfn);
-int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
+ unsigned long pfn);
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start,
+ unsigned long len);
static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
unsigned long addr, struct page *page)
diff --git a/include/linux/pfn.h b/include/linux/pfn.h
index 14bc053c53d8..482cf9a07fda 100644
--- a/include/linux/pfn.h
+++ b/include/linux/pfn.h
@@ -2,19 +2,6 @@
#ifndef _LINUX_PFN_H_
#define _LINUX_PFN_H_
-#ifndef __ASSEMBLY__
-#include <linux/types.h>
-
-/*
- * pfn_t: encapsulates a page-frame number that is optionally backed
- * by memmap (struct page). Whether a pfn_t has a 'struct page'
- * backing is indicated by flags in the high bits of the value.
- */
-typedef struct {
- u64 val;
-} pfn_t;
-#endif
-
#define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK)
#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
deleted file mode 100644
index 76e519b20553..000000000000
--- a/include/linux/pfn_t.h
+++ /dev/null
@@ -1,96 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_PFN_T_H_
-#define _LINUX_PFN_T_H_
-#include <linux/mm.h>
-
-/*
- * PFN_FLAGS_MASK - mask of all the possible valid pfn_t flags
- * PFN_SG_CHAIN - pfn is a pointer to the next scatterlist entry
- * PFN_SG_LAST - pfn references a page and is the last scatterlist entry
- * PFN_DEV - pfn is not covered by system memmap by default
- * PFN_MAP - pfn has a dynamic page mapping established by a device driver
- */
-#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
-#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
-#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
-#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
-
-#define PFN_FLAGS_TRACE \
- { PFN_SG_CHAIN, "SG_CHAIN" }, \
- { PFN_SG_LAST, "SG_LAST" }, \
- { PFN_DEV, "DEV" }, \
- { PFN_MAP, "MAP" }
-
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
-{
- pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
-
- return pfn_t;
-}
-
-/* a default pfn to pfn_t conversion assumes that @pfn is pfn_valid() */
-static inline pfn_t pfn_to_pfn_t(unsigned long pfn)
-{
- return __pfn_to_pfn_t(pfn, 0);
-}
-
-static inline pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
-{
- return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
-}
-
-static inline bool pfn_t_has_page(pfn_t pfn)
-{
- return (pfn.val & PFN_MAP) == PFN_MAP || (pfn.val & PFN_DEV) == 0;
-}
-
-static inline unsigned long pfn_t_to_pfn(pfn_t pfn)
-{
- return pfn.val & ~PFN_FLAGS_MASK;
-}
-
-static inline struct page *pfn_t_to_page(pfn_t pfn)
-{
- if (pfn_t_has_page(pfn))
- return pfn_to_page(pfn_t_to_pfn(pfn));
- return NULL;
-}
-
-static inline phys_addr_t pfn_t_to_phys(pfn_t pfn)
-{
- return PFN_PHYS(pfn_t_to_pfn(pfn));
-}
-
-static inline pfn_t page_to_pfn_t(struct page *page)
-{
- return pfn_to_pfn_t(page_to_pfn(page));
-}
-
-static inline int pfn_t_valid(pfn_t pfn)
-{
- return pfn_valid(pfn_t_to_pfn(pfn));
-}
-
-#ifdef CONFIG_MMU
-static inline pte_t pfn_t_pte(pfn_t pfn, pgprot_t pgprot)
-{
- return pfn_pte(pfn_t_to_pfn(pfn), pgprot);
-}
-#endif
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
-{
- return pfn_pmd(pfn_t_to_pfn(pfn), pgprot);
-}
-
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
-{
- return pfn_pud(pfn_t_to_pfn(pfn), pgprot);
-}
-#endif
-#endif
-
-#endif /* _LINUX_PFN_T_H_ */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index f3a95e38872c..d51e87e1adae 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1513,7 +1513,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
* by vmf_insert_pfn().
*/
static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
- pfn_t pfn)
+ unsigned long pfn)
{
}
@@ -1549,7 +1549,7 @@ extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr,
unsigned long size);
extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
- pfn_t pfn);
+ unsigned long pfn);
extern int track_pfn_copy(struct vm_area_struct *vma);
extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size, bool mm_wr_locked);
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index 86fe6aecff1e..10f706e37040 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -104,14 +104,14 @@ DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
TP_PROTO(struct inode *inode, struct vm_fault *vmf,
- long length, pfn_t pfn, void *radix_entry),
+ long length, unsigned long pfn, void *radix_entry),
TP_ARGS(inode, vmf, length, pfn, radix_entry),
TP_STRUCT__entry(
__field(unsigned long, ino)
__field(unsigned long, vm_flags)
__field(unsigned long, address)
__field(long, length)
- __field(u64, pfn_val)
+ __field(unsigned long, pfn)
__field(void *, radix_entry)
__field(dev_t, dev)
__field(int, write)
@@ -123,11 +123,11 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
__entry->address = vmf->address;
__entry->write = vmf->flags & FAULT_FLAG_WRITE;
__entry->length = length;
- __entry->pfn_val = pfn.val;
+ __entry->pfn = pfn;
__entry->radix_entry = radix_entry;
),
TP_printk("dev %d:%d ino %#lx %s %s address %#lx length %#lx "
- "pfn %#llx %s radix_entry %#lx",
+ "pfn %#lx radix_entry %#lx",
MAJOR(__entry->dev),
MINOR(__entry->dev),
__entry->ino,
@@ -135,9 +135,7 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
__entry->write ? "write" : "read",
__entry->address,
__entry->length,
- __entry->pfn_val & ~PFN_FLAGS_MASK,
- __print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|",
- PFN_FLAGS_TRACE),
+ __entry->pfn,
(unsigned long)__entry->radix_entry
)
)
@@ -145,7 +143,7 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
#define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
- long length, pfn_t pfn, void *radix_entry), \
+ long length, unsigned long pfn, void *radix_entry), \
TP_ARGS(inode, vmf, length, pfn, radix_entry))
DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 1262148d97b7..ec8e8d746658 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -20,7 +20,6 @@
#include <linux/mman.h>
#include <linux/mm_types.h>
#include <linux/module.h>
-#include <linux/pfn_t.h>
#include <linux/printk.h>
#include <linux/pgtable.h>
#include <linux/random.h>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7c39950bfdae..ea65c2db2bb1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -23,7 +23,6 @@
#include <linux/mm_types.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
-#include <linux/pfn_t.h>
#include <linux/mman.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
@@ -1232,15 +1231,15 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
}
static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
- pgtable_t pgtable)
+ pmd_t *pmd, unsigned long pfn, pgprot_t prot,
+ bool write, pgtable_t pgtable)
{
struct mm_struct *mm = vma->vm_mm;
pmd_t entry;
if (!pmd_none(*pmd)) {
if (write) {
- if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
+ if (pmd_pfn(*pmd) != pfn) {
WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
return;
}
@@ -1253,7 +1252,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
return;
}
- entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
+ entry = pmd_mkhuge(pfn_pmd(pfn, prot));
if (write) {
entry = pmd_mkyoung(pmd_mkdirty(entry));
entry = maybe_pmd_mkwrite(entry, vma);
@@ -1279,7 +1278,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
*
* Return: vm_fault_t value.
*/
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, bool write)
{
unsigned long addr = vmf->address & PMD_MASK;
struct vm_area_struct *vma = vmf->vma;
@@ -1316,7 +1315,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
-vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
+vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, bool write)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address & PMD_MASK;
@@ -1339,7 +1338,7 @@ vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
ptl = pmd_lock(mm, vmf->pmd);
if (pmd_none(*vmf->pmd)) {
- page = pfn_t_to_page(pfn);
+ page = pfn_to_page(pfn);
folio = page_folio(page);
folio_get(folio);
folio_add_file_rmap_pmd(folio, page, vma);
@@ -1364,7 +1363,7 @@ static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
}
static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud, pfn_t pfn, bool write)
+ pud_t *pud, unsigned long pfn, bool write)
{
struct mm_struct *mm = vma->vm_mm;
pgprot_t prot = vma->vm_page_prot;
@@ -1372,7 +1371,7 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
if (!pud_none(*pud)) {
if (write) {
- if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
+ if (pud_pfn(*pud) != pfn) {
WARN_ON_ONCE(!is_huge_zero_pud(*pud));
return;
}
@@ -1384,7 +1383,7 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
return;
}
- entry = pud_mkhuge(pfn_t_pud(pfn, prot));
+ entry = pud_mkhuge(pfn_pud(pfn, prot));
if (write) {
entry = pud_mkyoung(pud_mkdirty(entry));
entry = maybe_pud_mkwrite(entry, vma);
@@ -1403,7 +1402,7 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
*
* Return: vm_fault_t value.
*/
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, bool write)
{
unsigned long addr = vmf->address & PUD_MASK;
struct vm_area_struct *vma = vmf->vma;
@@ -1440,7 +1439,7 @@ EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
*
* Return: vm_fault_t value.
*/
-vm_fault_t dax_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
+vm_fault_t dax_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, bool write)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address & PUD_MASK;
@@ -1458,7 +1457,7 @@ vm_fault_t dax_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
ptl = pud_lock(mm, pud);
if (pud_none(*vmf->pud)) {
- page = pfn_t_to_page(pfn);
+ page = pfn_to_page(pfn);
folio = page_folio(page);
folio_get(folio);
folio_add_file_rmap_pud(folio, page, vma);
diff --git a/mm/memory.c b/mm/memory.c
index 721aac02a636..ed75f561d445 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -59,7 +59,6 @@
#include <linux/export.h>
#include <linux/delayacct.h>
#include <linux/init.h>
-#include <linux/pfn_t.h>
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
@@ -2327,7 +2326,7 @@ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
EXPORT_SYMBOL(vm_map_pages_zero);
static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
- pfn_t pfn, pgprot_t prot)
+ unsigned long pfn, pgprot_t prot)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte, entry;
@@ -2341,7 +2340,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
goto out_unlock;
/* Ok, finally just insert the thing.. */
- entry = pte_mkspecial(pfn_t_pte(pfn, prot));
+ entry = pte_mkspecial(pfn_pte(pfn, prot));
set_pte_at(mm, addr, pte, entry);
update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
@@ -2385,7 +2384,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
- unsigned long pfn, pgprot_t pgprot)
+ unsigned long pfn, pgprot_t pgprot)
{
/*
* Technically, architectures with pte_special can avoid all these
@@ -2405,9 +2404,9 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
if (!pfn_modify_allowed(pfn, pgprot))
return VM_FAULT_SIGBUS;
- track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
+ track_pfn_insert(vma, &pgprot, pfn);
- return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot);
+ return insert_pfn(vma, addr, pfn, pgprot);
}
EXPORT_SYMBOL(vmf_insert_pfn_prot);
@@ -2438,21 +2437,20 @@ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
}
EXPORT_SYMBOL(vmf_insert_pfn);
-static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
+static bool vm_mixed_ok(struct vm_area_struct *vma, unsigned long pfn)
{
- if (unlikely(is_zero_pfn(pfn_t_to_pfn(pfn))) &&
- !vm_mixed_zeropage_allowed(vma))
+ if (unlikely(is_zero_pfn(pfn)) && !vm_mixed_zeropage_allowed(vma))
return false;
/* these checks mirror the abort conditions in vm_normal_page */
if (vma->vm_flags & VM_MIXEDMAP)
return true;
- if (is_zero_pfn(pfn_t_to_pfn(pfn)))
+ if (is_zero_pfn(pfn))
return true;
return false;
}
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
- pfn_t pfn)
+ unsigned long pfn)
{
pgprot_t pgprot = vma->vm_page_prot;
int err;
@@ -2465,7 +2463,7 @@ vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
track_pfn_insert(vma, &pgprot, pfn);
- if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+ if (!pfn_modify_allowed(pfn, pgprot))
return VM_FAULT_SIGBUS;
/*
@@ -2475,15 +2473,10 @@ vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
* than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP
* without pte special, it would there be refcounted as a normal page.
*/
- if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_t_valid(pfn)) {
+ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_valid(pfn)) {
struct page *page;
- /*
- * At this point we are committed to insert_page()
- * regardless of whether the caller specified flags that
- * result in pfn_t_has_page() == false.
- */
- page = pfn_to_page(pfn_t_to_pfn(pfn));
+ page = pfn_to_page(pfn);
err = insert_page(vma, addr, page, pgprot, false);
} else {
return insert_pfn(vma, addr, pfn, pgprot);
@@ -2498,11 +2491,10 @@ vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
}
EXPORT_SYMBOL(vmf_insert_mixed);
-vm_fault_t dax_insert_pfn(struct vm_fault *vmf, pfn_t pfn_t, bool write)
+vm_fault_t dax_insert_pfn(struct vm_fault *vmf, unsigned long pfn, bool write)
{
struct vm_area_struct *vma = vmf->vma;
pgprot_t pgprot = vma->vm_page_prot;
- unsigned long pfn = pfn_t_to_pfn(pfn_t);
struct page *page = pfn_to_page(pfn);
unsigned long addr = vmf->address;
int err;
@@ -2510,7 +2502,7 @@ vm_fault_t dax_insert_pfn(struct vm_fault *vmf, pfn_t pfn_t, bool write)
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
- track_pfn_insert(vma, &pgprot, pfn_t);
+ track_pfn_insert(vma, &pgprot, pfn);
if (!pfn_modify_allowed(pfn, pgprot))
return VM_FAULT_SIGBUS;
@@ -2518,7 +2510,7 @@ vm_fault_t dax_insert_pfn(struct vm_fault *vmf, pfn_t pfn_t, bool write)
/*
* We refcount the page normally so make sure pfn_valid is true.
*/
- if (!pfn_t_valid(pfn_t))
+ if (!pfn_valid(pfn))
return VM_FAULT_SIGBUS;
if (WARN_ON(is_zero_pfn(pfn) && write))
diff --git a/mm/memremap.c b/mm/memremap.c
index 30bb99301b18..2b92195638db 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -5,7 +5,6 @@
#include <linux/kasan.h>
#include <linux/memory_hotplug.h>
#include <linux/memremap.h>
-#include <linux/pfn_t.h>
#include <linux/swap.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
diff --git a/mm/migrate.c b/mm/migrate.c
index ba4893d42618..18d19ef24311 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -37,7 +37,6 @@
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
-#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/balloon_compaction.h>
diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
index c1ec099a3b1d..f5ef3d034db5 100644
--- a/tools/testing/nvdimm/pmem-dax.c
+++ b/tools/testing/nvdimm/pmem-dax.c
@@ -9,8 +9,8 @@
#include <nd.h>
long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
- long nr_pages, enum dax_access_mode mode, void **kaddr,
- pfn_t *pfn)
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, unsigned long *pfn)
{
resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
@@ -29,7 +29,7 @@ long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
*kaddr = pmem->virt_addr + offset;
page = vmalloc_to_page(pmem->virt_addr + offset);
if (pfn)
- *pfn = page_to_pfn_t(page);
+ *pfn = page_to_pfn(page);
pr_debug_ratelimited("%s: pmem: %p pgoff: %#lx pfn: %#lx\n",
__func__, pmem, pgoff, page_to_pfn(page));
@@ -39,7 +39,7 @@ long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
if (kaddr)
*kaddr = pmem->virt_addr + offset;
if (pfn)
- *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+ *pfn = PHYS_PFN(pmem->phys_addr + offset);
/*
* If badblocks are present, limit known good range to the
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index e4313726fae3..f7e7bfe9bb85 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -8,7 +8,6 @@
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/types.h>
-#include <linux/pfn_t.h>
#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/mm.h>
@@ -135,16 +134,6 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
}
EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);
-pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
-{
- struct nfit_test_resource *nfit_res = get_nfit_res(addr);
-
- if (nfit_res)
- flags &= ~PFN_MAP;
- return phys_to_pfn_t(addr, flags);
-}
-EXPORT_SYMBOL(__wrap_phys_to_pfn_t);
-
void *__wrap_memremap(resource_size_t offset, size_t size,
unsigned long flags)
{
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index b00583d1eace..b9047fb8ea4a 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -212,7 +212,6 @@ void __iomem *__wrap_devm_ioremap(struct device *dev,
void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
size_t size, unsigned long flags);
void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
-pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
void *__wrap_memremap(resource_size_t offset, size_t size,
unsigned long flags);
void __wrap_devm_memunmap(struct device *dev, void *addr);
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH] dcssblk: Mark DAX broken
2024-09-24 22:59 [PATCH] dcssblk: Mark DAX broken Dan Williams
2024-09-24 23:26 ` Dan Williams
@ 2024-09-25 4:29 ` kernel test robot
2024-09-26 17:58 ` Alexander Gordeev
` (2 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: kernel test robot @ 2024-09-25 4:29 UTC (permalink / raw)
To: Dan Williams, hca, gor, agordeev
Cc: oe-kbuild-all, Gerald Schaefer, Christian Borntraeger,
Sven Schnelle, Jan Kara, Matthew Wilcox, Christoph Hellwig,
Alistair Popple, linux-s390, linux-mm
Hi Dan,
kernel test robot noticed the following build warnings:
[auto build test WARNING on s390/features]
[also build test WARNING on brauner-vfs/vfs.all akpm-mm/mm-everything linus/master v6.11 next-20240924]
[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/Dan-Williams/dcssblk-Mark-DAX-broken/20240925-070047
base: https://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git features
patch link: https://lore.kernel.org/r/172721874675.497781.3277495908107141898.stgit%40dwillia2-xfh.jf.intel.com
patch subject: [PATCH] dcssblk: Mark DAX broken
config: s390-allyesconfig (https://download.01.org/0day-ci/archive/20240925/202409251251.i8yVl4yR-lkp@intel.com/config)
compiler: s390-linux-gcc (GCC) 14.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240925/202409251251.i8yVl4yR-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/202409251251.i8yVl4yR-lkp@intel.com/
All warnings (new ones prefixed by >>):
drivers/s390/block/dcssblk.c: In function 'dcssblk_add_store':
>> drivers/s390/block/dcssblk.c:571:28: warning: unused variable 'dax_dev' [-Wunused-variable]
571 | struct dax_device *dax_dev;
| ^~~~~~~
vim +/dax_dev +571 drivers/s390/block/dcssblk.c
e265834f5da2c4 Dan Williams 2024-09-24 557
^1da177e4c3f41 Linus Torvalds 2005-04-16 558 /*
^1da177e4c3f41 Linus Torvalds 2005-04-16 559 * device attribute for adding devices
^1da177e4c3f41 Linus Torvalds 2005-04-16 560 */
^1da177e4c3f41 Linus Torvalds 2005-04-16 561 static ssize_t
e404e274f62665 Yani Ioannou 2005-05-17 562 dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
^1da177e4c3f41 Linus Torvalds 2005-04-16 563 {
af190c53c995bf Christoph Hellwig 2024-02-15 564 struct queue_limits lim = {
af190c53c995bf Christoph Hellwig 2024-02-15 565 .logical_block_size = 4096,
f467fee48da450 Christoph Hellwig 2024-06-17 566 .features = BLK_FEAT_DAX,
af190c53c995bf Christoph Hellwig 2024-02-15 567 };
b2300b9efe1b81 Hongjie Yang 2008-10-10 568 int rc, i, j, num_of_segments;
^1da177e4c3f41 Linus Torvalds 2005-04-16 569 struct dcssblk_dev_info *dev_info;
b2300b9efe1b81 Hongjie Yang 2008-10-10 570 struct segment_info *seg_info, *temp;
cf7fe690abbbe5 Mathieu Desnoyers 2024-02-15 @571 struct dax_device *dax_dev;
^1da177e4c3f41 Linus Torvalds 2005-04-16 572 char *local_buf;
^1da177e4c3f41 Linus Torvalds 2005-04-16 573 unsigned long seg_byte_size;
^1da177e4c3f41 Linus Torvalds 2005-04-16 574
^1da177e4c3f41 Linus Torvalds 2005-04-16 575 dev_info = NULL;
b2300b9efe1b81 Hongjie Yang 2008-10-10 576 seg_info = NULL;
^1da177e4c3f41 Linus Torvalds 2005-04-16 577 if (dev != dcssblk_root_dev) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 578 rc = -EINVAL;
^1da177e4c3f41 Linus Torvalds 2005-04-16 579 goto out_nobuf;
^1da177e4c3f41 Linus Torvalds 2005-04-16 580 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 581 if ((count < 1) || (buf[0] == '\0') || (buf[0] == '\n')) {
b2300b9efe1b81 Hongjie Yang 2008-10-10 582 rc = -ENAMETOOLONG;
b2300b9efe1b81 Hongjie Yang 2008-10-10 583 goto out_nobuf;
b2300b9efe1b81 Hongjie Yang 2008-10-10 584 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 585
^1da177e4c3f41 Linus Torvalds 2005-04-16 586 local_buf = kmalloc(count + 1, GFP_KERNEL);
^1da177e4c3f41 Linus Torvalds 2005-04-16 587 if (local_buf == NULL) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 588 rc = -ENOMEM;
^1da177e4c3f41 Linus Torvalds 2005-04-16 589 goto out_nobuf;
^1da177e4c3f41 Linus Torvalds 2005-04-16 590 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 591
^1da177e4c3f41 Linus Torvalds 2005-04-16 592 /*
^1da177e4c3f41 Linus Torvalds 2005-04-16 593 * parse input
^1da177e4c3f41 Linus Torvalds 2005-04-16 594 */
b2300b9efe1b81 Hongjie Yang 2008-10-10 595 num_of_segments = 0;
3a9f9183bdd341 Ameen Ali 2015-02-24 596 for (i = 0; (i < count && (buf[i] != '\0') && (buf[i] != '\n')); i++) {
42cfc6b590c5eb Martin Schwidefsky 2015-08-19 597 for (j = i; j < count &&
42cfc6b590c5eb Martin Schwidefsky 2015-08-19 598 (buf[j] != ':') &&
b2300b9efe1b81 Hongjie Yang 2008-10-10 599 (buf[j] != '\0') &&
42cfc6b590c5eb Martin Schwidefsky 2015-08-19 600 (buf[j] != '\n'); j++) {
b2300b9efe1b81 Hongjie Yang 2008-10-10 601 local_buf[j-i] = toupper(buf[j]);
b2300b9efe1b81 Hongjie Yang 2008-10-10 602 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 603 local_buf[j-i] = '\0';
b2300b9efe1b81 Hongjie Yang 2008-10-10 604 if (((j - i) == 0) || ((j - i) > 8)) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 605 rc = -ENAMETOOLONG;
b2300b9efe1b81 Hongjie Yang 2008-10-10 606 goto seg_list_del;
^1da177e4c3f41 Linus Torvalds 2005-04-16 607 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 608
b2300b9efe1b81 Hongjie Yang 2008-10-10 609 rc = dcssblk_load_segment(local_buf, &seg_info);
b2300b9efe1b81 Hongjie Yang 2008-10-10 610 if (rc < 0)
b2300b9efe1b81 Hongjie Yang 2008-10-10 611 goto seg_list_del;
^1da177e4c3f41 Linus Torvalds 2005-04-16 612 /*
^1da177e4c3f41 Linus Torvalds 2005-04-16 613 * get a struct dcssblk_dev_info
^1da177e4c3f41 Linus Torvalds 2005-04-16 614 */
b2300b9efe1b81 Hongjie Yang 2008-10-10 615 if (num_of_segments == 0) {
b2300b9efe1b81 Hongjie Yang 2008-10-10 616 dev_info = kzalloc(sizeof(struct dcssblk_dev_info),
b2300b9efe1b81 Hongjie Yang 2008-10-10 617 GFP_KERNEL);
^1da177e4c3f41 Linus Torvalds 2005-04-16 618 if (dev_info == NULL) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 619 rc = -ENOMEM;
^1da177e4c3f41 Linus Torvalds 2005-04-16 620 goto out;
^1da177e4c3f41 Linus Torvalds 2005-04-16 621 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 622 strcpy(dev_info->segment_name, local_buf);
b2300b9efe1b81 Hongjie Yang 2008-10-10 623 dev_info->segment_type = seg_info->segment_type;
b2300b9efe1b81 Hongjie Yang 2008-10-10 624 INIT_LIST_HEAD(&dev_info->seg_list);
b2300b9efe1b81 Hongjie Yang 2008-10-10 625 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 626 list_add_tail(&seg_info->lh, &dev_info->seg_list);
b2300b9efe1b81 Hongjie Yang 2008-10-10 627 num_of_segments++;
b2300b9efe1b81 Hongjie Yang 2008-10-10 628 i = j;
b2300b9efe1b81 Hongjie Yang 2008-10-10 629
b2300b9efe1b81 Hongjie Yang 2008-10-10 630 if ((buf[j] == '\0') || (buf[j] == '\n'))
b2300b9efe1b81 Hongjie Yang 2008-10-10 631 break;
b2300b9efe1b81 Hongjie Yang 2008-10-10 632 }
b2300b9efe1b81 Hongjie Yang 2008-10-10 633
b2300b9efe1b81 Hongjie Yang 2008-10-10 634 /* no trailing colon at the end of the input */
b2300b9efe1b81 Hongjie Yang 2008-10-10 635 if ((i > 0) && (buf[i-1] == ':')) {
b2300b9efe1b81 Hongjie Yang 2008-10-10 636 rc = -ENAMETOOLONG;
b2300b9efe1b81 Hongjie Yang 2008-10-10 637 goto seg_list_del;
b2300b9efe1b81 Hongjie Yang 2008-10-10 638 }
820109fb11f24b Wolfram Sang 2022-08-18 639 strscpy(local_buf, buf, i + 1);
b2300b9efe1b81 Hongjie Yang 2008-10-10 640 dev_info->num_of_segments = num_of_segments;
b2300b9efe1b81 Hongjie Yang 2008-10-10 641 rc = dcssblk_is_continuous(dev_info);
b2300b9efe1b81 Hongjie Yang 2008-10-10 642 if (rc < 0)
b2300b9efe1b81 Hongjie Yang 2008-10-10 643 goto seg_list_del;
b2300b9efe1b81 Hongjie Yang 2008-10-10 644
b2300b9efe1b81 Hongjie Yang 2008-10-10 645 dev_info->start = dcssblk_find_lowest_addr(dev_info);
b2300b9efe1b81 Hongjie Yang 2008-10-10 646 dev_info->end = dcssblk_find_highest_addr(dev_info);
b2300b9efe1b81 Hongjie Yang 2008-10-10 647
ef283688f54cc8 Kees Cook 2014-06-10 648 dev_set_name(&dev_info->dev, "%s", dev_info->segment_name);
^1da177e4c3f41 Linus Torvalds 2005-04-16 649 dev_info->dev.release = dcssblk_release_segment;
521b3d790c16fa Sebastian Ott 2012-10-01 650 dev_info->dev.groups = dcssblk_dev_attr_groups;
^1da177e4c3f41 Linus Torvalds 2005-04-16 651 INIT_LIST_HEAD(&dev_info->lh);
af190c53c995bf Christoph Hellwig 2024-02-15 652 dev_info->gd = blk_alloc_disk(&lim, NUMA_NO_NODE);
74fa8f9c553f7b Christoph Hellwig 2024-02-15 653 if (IS_ERR(dev_info->gd)) {
74fa8f9c553f7b Christoph Hellwig 2024-02-15 654 rc = PTR_ERR(dev_info->gd);
b2300b9efe1b81 Hongjie Yang 2008-10-10 655 goto seg_list_del;
^1da177e4c3f41 Linus Torvalds 2005-04-16 656 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 657 dev_info->gd->major = dcssblk_major;
0692ef289f067d Christoph Hellwig 2021-05-21 658 dev_info->gd->minors = DCSSBLK_MINORS_PER_DISK;
^1da177e4c3f41 Linus Torvalds 2005-04-16 659 dev_info->gd->fops = &dcssblk_devops;
^1da177e4c3f41 Linus Torvalds 2005-04-16 660 dev_info->gd->private_data = dev_info;
a41a11b4009580 Gerald Schaefer 2022-10-27 661 dev_info->gd->flags |= GENHD_FL_NO_PART;
b2300b9efe1b81 Hongjie Yang 2008-10-10 662
^1da177e4c3f41 Linus Torvalds 2005-04-16 663 seg_byte_size = (dev_info->end - dev_info->start + 1);
^1da177e4c3f41 Linus Torvalds 2005-04-16 664 set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors
93098bf0157876 Hongjie Yang 2008-12-25 665 pr_info("Loaded %s with total size %lu bytes and capacity %lu "
93098bf0157876 Hongjie Yang 2008-12-25 666 "sectors\n", local_buf, seg_byte_size, seg_byte_size >> 9);
^1da177e4c3f41 Linus Torvalds 2005-04-16 667
^1da177e4c3f41 Linus Torvalds 2005-04-16 668 dev_info->save_pending = 0;
^1da177e4c3f41 Linus Torvalds 2005-04-16 669 dev_info->is_shared = 1;
^1da177e4c3f41 Linus Torvalds 2005-04-16 670 dev_info->dev.parent = dcssblk_root_dev;
^1da177e4c3f41 Linus Torvalds 2005-04-16 671
^1da177e4c3f41 Linus Torvalds 2005-04-16 672 /*
^1da177e4c3f41 Linus Torvalds 2005-04-16 673 *get minor, add to list
^1da177e4c3f41 Linus Torvalds 2005-04-16 674 */
^1da177e4c3f41 Linus Torvalds 2005-04-16 675 down_write(&dcssblk_devices_sem);
b2300b9efe1b81 Hongjie Yang 2008-10-10 676 if (dcssblk_get_segment_by_name(local_buf)) {
04f64b5756872b Gerald Schaefer 2008-08-21 677 rc = -EEXIST;
b2300b9efe1b81 Hongjie Yang 2008-10-10 678 goto release_gd;
04f64b5756872b Gerald Schaefer 2008-08-21 679 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 680 rc = dcssblk_assign_free_minor(dev_info);
b2300b9efe1b81 Hongjie Yang 2008-10-10 681 if (rc)
b2300b9efe1b81 Hongjie Yang 2008-10-10 682 goto release_gd;
^1da177e4c3f41 Linus Torvalds 2005-04-16 683 sprintf(dev_info->gd->disk_name, "dcssblk%d",
d0591485e15ccd Gerald Schaefer 2009-06-12 684 dev_info->gd->first_minor);
^1da177e4c3f41 Linus Torvalds 2005-04-16 685 list_add_tail(&dev_info->lh, &dcssblk_devices);
^1da177e4c3f41 Linus Torvalds 2005-04-16 686
^1da177e4c3f41 Linus Torvalds 2005-04-16 687 if (!try_module_get(THIS_MODULE)) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 688 rc = -ENODEV;
b2300b9efe1b81 Hongjie Yang 2008-10-10 689 goto dev_list_del;
^1da177e4c3f41 Linus Torvalds 2005-04-16 690 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 691 /*
^1da177e4c3f41 Linus Torvalds 2005-04-16 692 * register the device
^1da177e4c3f41 Linus Torvalds 2005-04-16 693 */
^1da177e4c3f41 Linus Torvalds 2005-04-16 694 rc = device_register(&dev_info->dev);
b2300b9efe1b81 Hongjie Yang 2008-10-10 695 if (rc)
521b3d790c16fa Sebastian Ott 2012-10-01 696 goto put_dev;
^1da177e4c3f41 Linus Torvalds 2005-04-16 697
e265834f5da2c4 Dan Williams 2024-09-24 698 rc = dcssblk_setup_dax(dev_info);
fb08a1908cb119 Christoph Hellwig 2021-11-29 699 if (rc)
fb08a1908cb119 Christoph Hellwig 2021-11-29 700 goto out_dax;
7a2765f6e82063 Dan Williams 2017-01-26 701
521b3d790c16fa Sebastian Ott 2012-10-01 702 get_device(&dev_info->dev);
1a5db707c859a4 Gerald Schaefer 2021-09-27 703 rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL);
1a5db707c859a4 Gerald Schaefer 2021-09-27 704 if (rc)
fb08a1908cb119 Christoph Hellwig 2021-11-29 705 goto out_dax_host;
436d1bc7fe6e78 Christian Borntraeger 2007-12-04 706
^1da177e4c3f41 Linus Torvalds 2005-04-16 707 switch (dev_info->segment_type) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 708 case SEG_TYPE_SR:
^1da177e4c3f41 Linus Torvalds 2005-04-16 709 case SEG_TYPE_ER:
^1da177e4c3f41 Linus Torvalds 2005-04-16 710 case SEG_TYPE_SC:
^1da177e4c3f41 Linus Torvalds 2005-04-16 711 set_disk_ro(dev_info->gd,1);
^1da177e4c3f41 Linus Torvalds 2005-04-16 712 break;
^1da177e4c3f41 Linus Torvalds 2005-04-16 713 default:
^1da177e4c3f41 Linus Torvalds 2005-04-16 714 set_disk_ro(dev_info->gd,0);
^1da177e4c3f41 Linus Torvalds 2005-04-16 715 break;
^1da177e4c3f41 Linus Torvalds 2005-04-16 716 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 717 up_write(&dcssblk_devices_sem);
^1da177e4c3f41 Linus Torvalds 2005-04-16 718 rc = count;
^1da177e4c3f41 Linus Torvalds 2005-04-16 719 goto out;
^1da177e4c3f41 Linus Torvalds 2005-04-16 720
fb08a1908cb119 Christoph Hellwig 2021-11-29 721 out_dax_host:
c8f40a0bccefd6 Gerald Schaefer 2023-08-10 722 put_device(&dev_info->dev);
fb08a1908cb119 Christoph Hellwig 2021-11-29 723 dax_remove_host(dev_info->gd);
1a5db707c859a4 Gerald Schaefer 2021-09-27 724 out_dax:
1a5db707c859a4 Gerald Schaefer 2021-09-27 725 kill_dax(dev_info->dax_dev);
1a5db707c859a4 Gerald Schaefer 2021-09-27 726 put_dax(dev_info->dax_dev);
521b3d790c16fa Sebastian Ott 2012-10-01 727 put_dev:
^1da177e4c3f41 Linus Torvalds 2005-04-16 728 list_del(&dev_info->lh);
8b9ab62662048a Christoph Hellwig 2022-06-19 729 put_disk(dev_info->gd);
b2300b9efe1b81 Hongjie Yang 2008-10-10 730 list_for_each_entry(seg_info, &dev_info->seg_list, lh) {
b2300b9efe1b81 Hongjie Yang 2008-10-10 731 segment_unload(seg_info->segment_name);
b2300b9efe1b81 Hongjie Yang 2008-10-10 732 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 733 put_device(&dev_info->dev);
^1da177e4c3f41 Linus Torvalds 2005-04-16 734 up_write(&dcssblk_devices_sem);
^1da177e4c3f41 Linus Torvalds 2005-04-16 735 goto out;
b2300b9efe1b81 Hongjie Yang 2008-10-10 736 dev_list_del:
^1da177e4c3f41 Linus Torvalds 2005-04-16 737 list_del(&dev_info->lh);
b2300b9efe1b81 Hongjie Yang 2008-10-10 738 release_gd:
8b9ab62662048a Christoph Hellwig 2022-06-19 739 put_disk(dev_info->gd);
b2300b9efe1b81 Hongjie Yang 2008-10-10 740 up_write(&dcssblk_devices_sem);
b2300b9efe1b81 Hongjie Yang 2008-10-10 741 seg_list_del:
b2300b9efe1b81 Hongjie Yang 2008-10-10 742 if (dev_info == NULL)
b2300b9efe1b81 Hongjie Yang 2008-10-10 743 goto out;
b2300b9efe1b81 Hongjie Yang 2008-10-10 744 list_for_each_entry_safe(seg_info, temp, &dev_info->seg_list, lh) {
b2300b9efe1b81 Hongjie Yang 2008-10-10 745 list_del(&seg_info->lh);
b2300b9efe1b81 Hongjie Yang 2008-10-10 746 segment_unload(seg_info->segment_name);
b2300b9efe1b81 Hongjie Yang 2008-10-10 747 kfree(seg_info);
b2300b9efe1b81 Hongjie Yang 2008-10-10 748 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 749 kfree(dev_info);
^1da177e4c3f41 Linus Torvalds 2005-04-16 750 out:
^1da177e4c3f41 Linus Torvalds 2005-04-16 751 kfree(local_buf);
^1da177e4c3f41 Linus Torvalds 2005-04-16 752 out_nobuf:
^1da177e4c3f41 Linus Torvalds 2005-04-16 753 return rc;
^1da177e4c3f41 Linus Torvalds 2005-04-16 754 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 755
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] dcssblk: Mark DAX broken
2024-09-24 22:59 [PATCH] dcssblk: Mark DAX broken Dan Williams
2024-09-24 23:26 ` Dan Williams
2024-09-25 4:29 ` kernel test robot
@ 2024-09-26 17:58 ` Alexander Gordeev
2024-09-27 12:31 ` David Hildenbrand
2024-10-01 10:29 ` Gerald Schaefer
4 siblings, 0 replies; 7+ messages in thread
From: Alexander Gordeev @ 2024-09-26 17:58 UTC (permalink / raw)
To: Dan Williams
Cc: hca, gor, Gerald Schaefer, Christian Borntraeger, Sven Schnelle,
Jan Kara, Matthew Wilcox, Christoph Hellwig, Alistair Popple,
linux-s390, linux-mm
On Tue, Sep 24, 2024 at 03:59:08PM -0700, Dan Williams wrote:
Hi Dan,
> The dcssblk driver has long needed special case supoprt to enable
> limited dax operation, so called CONFIG_FS_DAX_LIMITED. This mode
> works around the incomplete support for ZONE_DEVICE on s390 by forgoing
> the ability of dax-mapped pages to support GUP.
>
> Now, pending cleanups to fsdax that fix its reference counting [1] depend on
> the ability of all dax drivers to supply ZONE_DEVICE pages.
>
> To allow that work to move forward, dax support needs to be paused for
> dcssblk until ZONE_DEVICE support arrives. That work has been known for
> a few years [2], and the removal of "pte_devmap" requirements [3] makes the
> conversion easier.
>
> For now, place the support behind CONFIG_BROKEN, and remove PFN_SPECIAL
> (dcssblk was the only user).
>
> Link: http://lore.kernel.org/cover.9f0e45d52f5cff58807831b6b867084d0b14b61c.1725941415.git-series.apopple@nvidia.com [1]
> Link: http://lore.kernel.org/20210820210318.187742e8@thinkpad/ [2]
> Link: http://lore.kernel.org/4511465a4f8429f45e2ac70d2e65dc5e1df1eb47.1725941415.git-series.apopple@nvidia.com [3]
...
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
> drivers/s390/block/Kconfig | 12 ++++++++++--
> drivers/s390/block/dcssblk.c | 26 +++++++++++++++++---------
> fs/Kconfig | 9 +--------
> fs/dax.c | 12 ------------
> include/linux/pfn_t.h | 15 ---------------
> mm/memory.c | 2 --
> mm/memremap.c | 4 ----
> 7 files changed, 28 insertions(+), 52 deletions(-)
...
I guess you want to remove dcssblk from Documentation/filesystems/dax.rst.
Gerald is back from vacation on Monday and he will likely comment on this.
Tested-by: Alexander Gordeev <agordeev@linux.ibm.com>
Thanks!
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] dcssblk: Mark DAX broken
2024-09-24 22:59 [PATCH] dcssblk: Mark DAX broken Dan Williams
` (2 preceding siblings ...)
2024-09-26 17:58 ` Alexander Gordeev
@ 2024-09-27 12:31 ` David Hildenbrand
2024-10-01 10:29 ` Gerald Schaefer
4 siblings, 0 replies; 7+ messages in thread
From: David Hildenbrand @ 2024-09-27 12:31 UTC (permalink / raw)
To: Dan Williams, hca, gor, agordeev
Cc: Gerald Schaefer, Christian Borntraeger, Sven Schnelle, Jan Kara,
Matthew Wilcox, Christoph Hellwig, Alistair Popple, linux-s390,
linux-mm
On 25.09.24 00:59, Dan Williams wrote:
> The dcssblk driver has long needed special case supoprt to enable
> limited dax operation, so called CONFIG_FS_DAX_LIMITED. This mode
> works around the incomplete support for ZONE_DEVICE on s390 by forgoing
> the ability of dax-mapped pages to support GUP.
>
> Now, pending cleanups to fsdax that fix its reference counting [1] depend on
> the ability of all dax drivers to supply ZONE_DEVICE pages.
>
> To allow that work to move forward, dax support needs to be paused for
> dcssblk until ZONE_DEVICE support arrives. That work has been known for
> a few years [2], and the removal of "pte_devmap" requirements [3] makes the
> conversion easier.
>
> For now, place the support behind CONFIG_BROKEN, and remove PFN_SPECIAL
> (dcssblk was the only user).
>
> Link: http://lore.kernel.org/cover.9f0e45d52f5cff58807831b6b867084d0b14b61c.1725941415.git-series.apopple@nvidia.com [1]
> Link: http://lore.kernel.org/20210820210318.187742e8@thinkpad/ [2]
> Link: http://lore.kernel.org/4511465a4f8429f45e2ac70d2e65dc5e1df1eb47.1725941415.git-series.apopple@nvidia.com [3]
> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
> Cc: Heiko Carstens <hca@linux.ibm.com>
> Cc: Vasily Gorbik <gor@linux.ibm.com>
> Cc: Alexander Gordeev <agordeev@linux.ibm.com>
> Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
> Cc: Sven Schnelle <svens@linux.ibm.com>
> Cc: Jan Kara <jack@suse.cz>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Alistair Popple <apopple@nvidia.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
Acked-by: David Hildenbrand <david@redhat.com>
--
Cheers,
David / dhildenb
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] dcssblk: Mark DAX broken
2024-09-24 22:59 [PATCH] dcssblk: Mark DAX broken Dan Williams
` (3 preceding siblings ...)
2024-09-27 12:31 ` David Hildenbrand
@ 2024-10-01 10:29 ` Gerald Schaefer
2024-10-08 0:28 ` Dan Williams
4 siblings, 1 reply; 7+ messages in thread
From: Gerald Schaefer @ 2024-10-01 10:29 UTC (permalink / raw)
To: Dan Williams
Cc: hca, gor, agordeev, Christian Borntraeger, Sven Schnelle,
Jan Kara, Matthew Wilcox, Christoph Hellwig, Alistair Popple,
linux-s390, linux-mm
On Tue, 24 Sep 2024 15:59:08 -0700
Dan Williams <dan.j.williams@intel.com> wrote:
> The dcssblk driver has long needed special case supoprt to enable
> limited dax operation, so called CONFIG_FS_DAX_LIMITED. This mode
> works around the incomplete support for ZONE_DEVICE on s390 by forgoing
> the ability of dax-mapped pages to support GUP.
>
> Now, pending cleanups to fsdax that fix its reference counting [1] depend on
> the ability of all dax drivers to supply ZONE_DEVICE pages.
>
> To allow that work to move forward, dax support needs to be paused for
> dcssblk until ZONE_DEVICE support arrives. That work has been known for
> a few years [2], and the removal of "pte_devmap" requirements [3] makes the
> conversion easier.
Thanks, that's great news! Without requiring the extra PTE bit, it should
now finally be possible to add struct pages and ZONE_DEVICE support for
dcssblk.
In the meantime, it is OK to pause the DAX support for dcssblk as you
suggested, and finally remove that ugly CONFIG_FS_DAX_LIMITED. Thanks
for bearing with us for so long!
>
> For now, place the support behind CONFIG_BROKEN, and remove PFN_SPECIAL
> (dcssblk was the only user).
Ok, I guess that PFN_SPECIAL was there because we had no struct pages for
the DCSS memory. When we come back, with proper ZONE_DEVICE and struct
pages, it should not be needed any more.
And yes, the chance to completely remove pfn_t, after Alistair's series,
is quite impressive and even more motivation than CONFIG_FS_DAX_LIMITED.
>
> Link: http://lore.kernel.org/cover.9f0e45d52f5cff58807831b6b867084d0b14b61c.1725941415.git-series.apopple@nvidia.com [1]
> Link: http://lore.kernel.org/20210820210318.187742e8@thinkpad/ [2]
> Link: http://lore.kernel.org/4511465a4f8429f45e2ac70d2e65dc5e1df1eb47.1725941415.git-series.apopple@nvidia.com [3]
> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
> Cc: Heiko Carstens <hca@linux.ibm.com>
> Cc: Vasily Gorbik <gor@linux.ibm.com>
> Cc: Alexander Gordeev <agordeev@linux.ibm.com>
> Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
> Cc: Sven Schnelle <svens@linux.ibm.com>
> Cc: Jan Kara <jack@suse.cz>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Alistair Popple <apopple@nvidia.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
> drivers/s390/block/Kconfig | 12 ++++++++++--
> drivers/s390/block/dcssblk.c | 26 +++++++++++++++++---------
> fs/Kconfig | 9 +--------
> fs/dax.c | 12 ------------
> include/linux/pfn_t.h | 15 ---------------
> mm/memory.c | 2 --
> mm/memremap.c | 4 ----
> 7 files changed, 28 insertions(+), 52 deletions(-)
When you also remove the now unused dax_dev definition at the top of
dcssblk_add_store(), as noticed by kernel test robot:
Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] dcssblk: Mark DAX broken
2024-10-01 10:29 ` Gerald Schaefer
@ 2024-10-08 0:28 ` Dan Williams
0 siblings, 0 replies; 7+ messages in thread
From: Dan Williams @ 2024-10-08 0:28 UTC (permalink / raw)
To: Gerald Schaefer, Dan Williams
Cc: hca, gor, agordeev, Christian Borntraeger, Sven Schnelle,
Jan Kara, Matthew Wilcox, Christoph Hellwig, Alistair Popple,
linux-s390, linux-mm
Gerald Schaefer wrote:
[..]
> When you also remove the now unused dax_dev definition at the top of
> dcssblk_add_store(), as noticed by kernel test robot:
Yup, already have that fixup locally.
> Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Thanks!
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2024-10-08 0:29 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-09-24 22:59 [PATCH] dcssblk: Mark DAX broken Dan Williams
2024-09-24 23:26 ` Dan Williams
2024-09-25 4:29 ` kernel test robot
2024-09-26 17:58 ` Alexander Gordeev
2024-09-27 12:31 ` David Hildenbrand
2024-10-01 10:29 ` Gerald Schaefer
2024-10-08 0:28 ` Dan Williams
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).